diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 772924df9c..ce1518066b 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -273,7 +273,7 @@ export interface Config { } ``` -Source: [`packages/hooks/hooks-claude/src/index.ts:56`](../packages/hooks/hooks-claude/src/index.ts) +Source: [`packages/hooks/hooks-claude/src/index.ts:57`](../packages/hooks/hooks-claude/src/index.ts) ## `@deepseek-ai/dsh-hooks-codex` @@ -298,7 +298,7 @@ export interface Config { } ``` -Source: [`packages/hooks/hooks-codex/src/index.ts:43`](../packages/hooks/hooks-codex/src/index.ts) +Source: [`packages/hooks/hooks-codex/src/index.ts:44`](../packages/hooks/hooks-codex/src/index.ts) ## `@deepseek-ai/dsh-invariants` @@ -446,7 +446,7 @@ export interface Config { } ``` -Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:35`](../packages/session-persistence/session-persistence-jsonl/src/index.ts) +Source: [`packages/session-persistence/session-persistence-jsonl/src/index.ts:36`](../packages/session-persistence/session-persistence-jsonl/src/index.ts) ## `@deepseek-ai/dsh-session-persistence-sqlite` @@ -481,7 +481,7 @@ export interface Config { export type JournalMode = 'wal' | 'delete' | 'truncate' | 'persist' ``` -Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:50`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) +Source: [`packages/session-persistence/session-persistence-sqlite/src/index.ts:51`](../packages/session-persistence/session-persistence-sqlite/src/index.ts) ## `@deepseek-ai/dsh-stdio-agent` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 79902ba2fc..a21a80fb77 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -159,6 +159,7 @@ Contracts every implementation MUST honor (a DB backend asserts them inside a tr - **Durability.** append returns only once the batch is durable (the file backend fsyncs; a DB commits). create MAY defer the physical write until the first append (lazy materialization). ```ts cordis-catalog +abstract locate(meta: SessionHeader): SessionLocation | undefined abstract create(meta: SessionHeader): Promise abstract append(id: SessionId, events: readonly SessionEvent[]): Promise abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }> @@ -167,7 +168,7 @@ abstract list(): Promise Types: [SessionEvent](../core-data-structures/core.md) -Source: [`packages/session-persistence/session-persistence/src/index.ts:102`](../../packages/session-persistence/session-persistence/src/index.ts) +Source: [`packages/session-persistence/session-persistence/src/index.ts:114`](../../packages/session-persistence/session-persistence/src/index.ts) ## `ctx.sessions` — `SessionStore` diff --git a/docs/core-data-structures/persistence.md b/docs/core-data-structures/persistence.md index 4dbb8fb2af..b5aa887e30 100644 --- a/docs/core-data-structures/persistence.md +++ b/docs/core-data-structures/persistence.md @@ -2,7 +2,7 @@ The **durability seam** for the event log. [session.md](session.md) describes the in-memory `Session` — the append-only `SessionEvent` log that is the source of truth. This page describes how that log is made durable: the abstract `SessionPersistence` service, its backends, the flush checkpoint, crash recovery, and the metadata header that travels alongside the log. The event vocabulary the log carries is enumerated, member by member, in the generated [persistence log event catalog](../persistence-catalog.md). -The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md): one abstract service ([dsh-session-persistence](../../packages/session-persistence/session-persistence), `ctx.sessionPersistence`) defining create/append/load/list over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence RFC](../rfc/implemented/architecture/2026-06-14-session-persistence.md). +The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06-13-capability-seams.md): one abstract service ([dsh-session-persistence](../../packages/session-persistence/session-persistence), `ctx.sessionPersistence`) defining locate/create/append/load/list over the existing `SessionEvent` — **no parallel persisted type** — and two interchangeable backends that pass the same `runPersistenceContract` suite. See the [session-persistence RFC](../rfc/implemented/architecture/2026-06-14-session-persistence.md). ## The flush checkpoint @@ -12,6 +12,19 @@ The seam is a textbook [capability seam](../rfc/implemented/architecture/2026-06 A backend that reloads a log crashed mid-turn finds an open `turn/start` with no `turn/end`. It does **not** truncate — a single turn can be huge in a long-horizon task (many steps, large tool output), and those events were durably appended before the crash. Instead it closes the orphaned turn with a synthetic `turn/end { reason: { kind: 'interrupted' } }`, keeping the log balanced and the turn-enclosure invariant intact. `interrupted` is the one `TurnEndReason` no loop emits (see [session.md](session.md#why-a-turn-ended-turnendreasonmap)). +## `SessionLocation` — optional per-session artifact target + +`SessionPersistence.locate(meta)` synchronously resolves a backend-owned independent artifact without reading, creating, or flushing it. JSONL returns its absolute target path; SQLite returns `undefined` because sessions share one database. A returned path can therefore name a file that does not yet exist or lacks the current unflushed turn; it is a location hint, not authorization or a freshness guarantee. + +```ts type-equiv +interface SessionLocation { + /** Backend-specific artifact kind, for example `jsonl`. */ + readonly kind: string + /** Absolute path to this session's backend-owned artifact. */ + readonly path: string +} +``` + ## `SessionHeader` — metadata beside the log Per-session metadata travels **separately** from the event log: format version, cwd, lineage, and the seed boundary are storage concerns, not conversation events, so they stay out of `SessionEventMap` and never reach `deriveMessages()`. The header is attached to a `Session` via `session.header`. @@ -75,7 +88,7 @@ Replay/fork is therefore `ctx.sessions.create(id, { seed: seedEvents })`; resumi ## The backends -Both implement the same abstract `SessionPersistence` (create/append/load/list over `SessionEvent`) and pass `runPersistenceContract`, proving the seam is genuinely backend-agnostic: +Both implement the same abstract `SessionPersistence` (locate/create/append/load/list over `SessionEvent`) and pass `runPersistenceContract`, proving the seam is genuinely backend-agnostic: - **[dsh-session-persistence-jsonl](../../packages/session-persistence/session-persistence-jsonl)** — an append-only JSONL log per session with crash-safe atomic writes, the interrupted-turn crash recovery above, and a read/replay path. - **[dsh-session-persistence-sqlite](../../packages/session-persistence/session-persistence-sqlite)** — `node:sqlite`, one row per `SessionEvent`. The row shape `(session_id, seq, type, time, data, source_event_seqs, surface_op)` maps 1:1 onto the event, including optional surface metadata, so there is no parallel persisted schema to keep in sync. diff --git a/docs/module-graph.md b/docs/module-graph.md index 68c680c914..bab33bdddd 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -162,6 +162,7 @@ flowchart TD pkg_tool_bash --> pkg_agent pkg_tool_bash --> pkg_bash pkg_tool_bash --> pkg_llm + pkg_tool_bash --> pkg_session_persistence pkg_tool_bash --> pkg_system_prompt pkg_tool_bash --> pkg_tools pkg_tool_fs --> pkg_fs @@ -187,6 +188,7 @@ flowchart TD pkg_hooks_codex --> pkg_hook_protocol pkg_hooks_codex --> pkg_llm pkg_hooks_codex --> pkg_session + pkg_hooks_codex --> pkg_session_persistence pkg_hooks_codex --> pkg_tools pkg_acp --> pkg_agent pkg_acp --> pkg_llm @@ -230,6 +232,7 @@ flowchart TD pkg_hooks_claude --> pkg_hook_protocol pkg_hooks_claude --> pkg_llm pkg_hooks_claude --> pkg_session + pkg_hooks_claude --> pkg_session_persistence pkg_hooks_claude --> pkg_subagent pkg_hooks_claude --> pkg_tools pkg_subagent_mock --> pkg_agent @@ -301,14 +304,14 @@ flowchart TD | [`user-interaction`](../packages/ui/user-interaction) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm) | | [`workflow`](../packages/workflow/workflow) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm) | | [`agent-loop`](../packages/core/agent-loop) | `core` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | -| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | +| [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | | [`tool-todo`](../packages/todo/tool-todo) | `todo` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-cordis`](../packages/cordis/tool-cordis) | `cordis` | [`tools`](../packages/core/tools) | -| [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | +| [`hooks-codex`](../packages/hooks/hooks-codex) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools) | | [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`tool-ask-user`](../packages/ui/tool-ask-user) | `ui` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools), [`user-interaction`](../packages/ui/user-interaction) | | [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | `guard` | [`agent`](../packages/core/agent), [`tools`](../packages/core/tools) | @@ -317,7 +320,7 @@ flowchart TD | [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`subagent-subprocess`](../packages/subagent/subagent-subprocess) | | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | -| [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | +| [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index ba2b9d88dc..603ccdbf26 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -67,6 +67,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [The session prefix — request-only messages in front of the derived history](implemented/feature/2026-07-07-session-prefix.md) | 2026-07-07 | | [Repeat-tool-call guard plugin](implemented/feature/2026-07-08-repeat-tool-guard.md) | 2026-07-08 | | [The self-referential cordis toolset](implemented/feature/2026-07-08-self-referential-cordis-toolset.md) | 2026-07-08 | +| [Expose agent session identity and JSONL location to tools and hooks](implemented/feature/2026-07-10-agent-session-identity-and-log-location.md) | 2026-07-10 | ### Simplification diff --git a/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md b/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md index e6ecc974d7..756436d07d 100644 --- a/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md +++ b/docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md @@ -14,7 +14,7 @@ Add `stdin?: string` and `env?: Record` to **both** `BashExecReq Three deliberate choices: -1. **The model-facing `bash` tool simply does NOT expose `stdin`/`env` as parameters** — not as a security wall, but because bash syntax already covers the model's needs, so duplicating them as tool params would be redundant surface. [dsh-tool-bash](../../../../packages/bash/tool-bash)'s `bash` tool builds its `BashExecRequest` from `command`/`workdir`/`timeoutMs`/`signal`/`owner` only; a model that includes `env`/`stdin` keys in its tool-call arguments simply has them ignored. A regression guard (`tool-bash` "does not forward env/stdin" tests) drives the real tool with those extra args and asserts the recorded request carries neither field — its purpose is to catch a future refactor that blindly spreads `...args` into the request and silently starts forwarding model input into the post-scrub `env` merge, NOT to defend a trust boundary. In-process plugins (the hooks bridges, native plugins) that construct a `BashExecRequest` directly set the fields; the seam imposes no access policy (consistent with how `owner` works — the executor stores but never interprets it). +1. **The model-facing `bash` tool does NOT expose `stdin`/`env` as parameters** — not as a security wall, but because bash syntax already covers the model's needs, so duplicating them as tool params would be redundant surface. [dsh-tool-bash](../../../../packages/bash/tool-bash)'s `bash` tool builds its `BashExecRequest` from named schema fields and may add harness-owned environment such as the current [session identity and JSONL location](../feature/2026-07-10-agent-session-identity-and-log-location.md); a model that includes `env`/`stdin` keys in its tool-call arguments has them ignored and cannot replace that overlay. Regression guards drive the real tool with extra args and assert no model-provided field enters the request. In-process plugins (the hooks bridges, native plugins) that construct a `BashExecRequest` directly set the fields; the seam imposes no access policy (consistent with how `owner` works — the executor stores but never interprets it). 2. **`env` merges AFTER the credential scrub, so an explicit caller entry always wins** — even a credential-shaped name. This is correct because the scrub's job is narrow: stop the harness's *ambient* `process.env` credentials from leaking into a spawned command. A caller that explicitly sets a var has named a value it already holds (not the ambient secret), so the scrub is not a constraint on it. `childEnv(extra?)` layers `scrub(process.env)` → `ENV_OVERRIDES` (the model-friendly `TERM=dumb` etc.) → `extra`, last-wins. diff --git a/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md b/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md index 630d4dd3ed..431166e932 100644 --- a/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md +++ b/docs/rfc/implemented/feature/2026-06-30-hook-bridges.md @@ -12,8 +12,8 @@ The framing that shapes the whole design: **a bridge is a faithfulness adapter, Two independent plugins in the `packages/hooks/` group, each a function/namespace plugin (`name`/`inject`/`Config`/`apply`, NO default export — see [postmortem 0001](../../../postmortem/0001-acp-default-export-drops-inject.md)) injecting only `bash`: -- **`dsh-hooks-claude`** — the CC dialect. Seven hook points: `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStart`, `SubagentStop`. Owns CC's per-event stdin payloads (a base of `session_id`/`cwd`/`hook_event_name` plus per-event fields), CC's env + `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the literal-or-regex matcher mode. A CC hook's stdin carries a **trailing newline**. -- **`dsh-hooks-codex`** — the Codex dialect: a deliberate SUBSET. Five hook points (`PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop` — no subagent/notification/compaction), an always-regex matcher, snake_case payloads with `turn_id`/`model`/`permission_mode` extras written WITHOUT a trailing newline, no env and no `${…}` substitution, and a block-only decision model (a Codex hook can never pre-approve, so `allow`/`ask` are not honored). A tool call's payload carries the real `tool_name` (the value the matcher tests, so a config's tool matcher fires) in Codex's `tool_input: { command }` shape. +- **`dsh-hooks-claude`** — the CC dialect. Seven hook points: `SessionStart`, `UserPromptSubmit`, `PreToolUse`, `PostToolUse`, `Stop`, `SubagentStart`, `SubagentStop`. Owns CC's per-event stdin payloads (a base of `session_id`/`transcript_path`/`cwd`/`hook_event_name` plus per-event fields), CC's env + `${CLAUDE_PLUGIN_ROOT}`/`${CLAUDE_PROJECT_DIR}` substitution, and the literal-or-regex matcher mode. `transcript_path` comes from the persistence locator or is `''`; a CC hook's stdin carries a **trailing newline**. +- **`dsh-hooks-codex`** — the Codex dialect: a deliberate SUBSET. Five hook points (`PreToolUse`, `PostToolUse`, `SessionStart`, `UserPromptSubmit`, `Stop` — no subagent/notification/compaction), an always-regex matcher, snake_case payloads with `turn_id`/`model`/`permission_mode` extras written WITHOUT a trailing newline, no env and no `${…}` substitution, and a block-only decision model (a Codex hook can never pre-approve, so `allow`/`ask` are not honored). Its `transcript_path` comes from the same locator or is `null`; a tool call's payload carries the real `tool_name` (the value the matcher tests, so a config's tool matcher fires) in Codex's `tool_input: { command }` shape. ### Outcome → Decision mapping diff --git a/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md new file mode 100644 index 0000000000..8bc5f33820 --- /dev/null +++ b/docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md @@ -0,0 +1,86 @@ +# RFC: Expose agent session identity and JSONL location to tools and hooks + +Status: implemented + +## Problem + +An agent can identify its workspace through `session.header.cwd`, but a model using the bash tool cannot identify the session that owns the call or the durable JSONL file that records it. The default apps happen to use `./.sessions`, yet that is deployment config rather than a contract: `persistenceRoot` can point elsewhere, the JSONL backend hashes `cwd` into a bucket, and arbitrary session ids are path-encoded. Asking the agent to run `find` therefore makes the model guess backend layout and can select the wrong log under concurrent, resumed, forked, or subagent sessions. + +The same missing ownership boundary appears in the hook bridges. The Codex bridge emits `session_id` but fixes `transcript_path` to `null`; the Claude Code bridge emits `session_id` and `cwd` but no transcript path. Teaching each consumer to reconstruct the JSONL layout would duplicate backend policy and couple model tools and protocol adapters to one persistence implementation. + +The feature needs two distinct facts: a stable session identity that exists even without persistence, and an optional physical location owned by the active persistence backend. They must be resolved per agent invocation rather than written to global `process.env`, because one harness process can run multiple agents and in-process subagents concurrently. + +## Decision + +Extend the [`SessionPersistence`](../../implemented/architecture/2026-06-14-session-persistence.md) seam with a synchronous, side-effect-free location query: + +```ts +import type { SessionHeader } from '@deepseek-ai/dsh-session' + +export interface SessionLocation { + readonly kind: string + readonly path: string +} + +export abstract class SessionPersistence { + abstract locate(meta: SessionHeader): SessionLocation | undefined +} +``` + +`path` is an absolute local path to the backend's dedicated log for `meta`; `kind` identifies the representation. The JSONL backend returns `{ kind: 'jsonl', path }` using its already-resolved absolute root and existing cwd-bucket/id-encoding helpers. The SQLite backend returns `undefined` because a session is rows inside a shared database, not a dedicated transcript file. A backend with no honest local per-session path also returns `undefined`. + +`locate` performs no filesystem I/O, creates nothing, flushes nothing, and never searches by convention. It reports where this backend would materialize the session, so callers can receive a path before the file exists. Making the query synchronous and local-path-only keeps it usable while constructing tool and hook invocation context; a future remote/object-store locator is a separate capability rather than a blocking network call hidden inside prompt or tool assembly. + +The model-facing bash consumer derives a trusted environment overlay for each `ToolExecution` with an agent: + +- `DSH_SESSION_ID` is always the current `agent.session.header.id`, including when persistence is absent or non-file-backed. +- `DSH_SESSION_JSONL` is present only when the active `ctx.sessionPersistence.locate(header)` returns `kind: 'jsonl'`; its value is that location's absolute path. +- A call without an agent receives neither variable. + +The overlay is passed through the existing `BashExecRequest.env` surface from the [trusted stdin/env decision](../../implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). It applies to foreground and background starts, and `dsh-bash-local` merges it after its ambient credential scrub and terminal overrides. The model-facing tool continues to build the request from named schema fields: model-supplied `env`/`stdin` keys are ignored and cannot replace the overlay. A shell command can still overwrite its own variables (`DSH_SESSION_ID=x command`); these values are correlation metadata, never authority. + +The bash tool description tells the model that the current session id is available as `$DSH_SESSION_ID` and that JSONL deployments additionally expose `$DSH_SESSION_JSONL`. This guidance belongs with the tool that provides the variables, not in a permanent system-prompt section. The schema is already recorded in the request header under the [reconstructable-request contract](../../implemented/architecture/2026-07-05-reconstructable-requests.md), and every resulting tool output is a durable `tool/result`, so no new session event is needed. + +The [Claude Code and Codex hook bridges](../../implemented/feature/2026-06-30-hook-bridges.md) resolve transcript location from the same seam at payload construction time. Codex payloads use `transcript_path: string | null`; Claude Code payloads keep their string-shaped dialect field and use `transcript_path: string`, falling back to `''` when no local per-session file exists. Hook lookup is the same side-effect-free snapshot as bash lookup: it does not force materialization or make a pre-turn hook create an otherwise abandoned session artifact. + +## Peer product findings + +Peer products separate stable identity from physical storage rather than treating an absolute path as the only session key. Codex injects `CODEX_THREAD_ID` into each spawned shell environment after its environment policy has run, while its rollout recorder owns the exact path and exposes it separately to client events and hooks. Claude Code supplies `session_id` and `transcript_path` as structured hook/status-line input rather than a general Bash transcript environment contract. OpenCode carries session identity in structured tool execution context; Kimi Code expands a session-id placeholder in skill content; Reasonix keeps the active session path on its controller and rebinds it on branch/resume. + +The reusable principles are narrower than any one product's API: inject identity at the invocation boundary, let persistence resolve storage, do not mutate process-global environment for concurrent agents, and do not promise that a precomputed path is already materialized. DeepSeek Harness adds the optional JSONL path to bash because its requested user behavior is explicitly “ask the agent for this session's log,” while retaining the stable id as the primary identity. + +## Lifecycle and persistence semantics + +A fresh session receives its id before any turn. Its bash environment can therefore carry both values during the first turn, but JSONL lazy materialization remains unchanged: before the first successful turn-end `session/flush`, `$DSH_SESSION_JSONL` can name a file that does not yet exist. During an open later turn, the file contains only the last durably flushed prefix, not the current buffered events. Consumers that need a readable up-to-date transcript require a separate explicit checkpoint/materialization API; this decision deliberately does not add one. + +Resume reuses the loaded session header, so it exposes the same id and backend location. Fork and in-process spawn create a new session id; the JSONL backend derives a new file while preserving the existing `parentSession` lineage and inherited cwd rules. Concurrent parent/child agents compute overlays from their own `ToolExecution.agent`, so neither can inherit or overwrite the other's identity. + +Consumers resolve the active service through the Cordis context at invocation time and do not cache a concrete JSONL backend instance. This keeps HMR/reload behavior aligned with the service store: a replacement backend controls subsequent locations, and an absent/inactive backend removes only `DSH_SESSION_JSONL`, never the session id. + +## Testing + +Unit coverage pins each boundary. The persistence seam contract asserts JSONL returns an absolute encoded path under a custom root while SQLite returns `undefined`; JSONL tests cover cwd/no-cwd buckets and ids requiring escaping. Tool-bash request-recording tests cover foreground/background overlays, no-agent calls, absent/SQLite persistence, ignored model `env` keys, and separate parent/child identities. Both hook bridge suites assert their exact available/unavailable `transcript_path` dialect shapes. + +A keyless full-loop integration uses the real agent loop, JSONL persistence, `dsh-tool-bash`, and `dsh-bash-local` with only the model scripted. On the first turn the model runs a command that prints both variables and reports whether the path exists; the test verifies the values against the live session header and locator, verifies the file can be absent inside the tool call, then waits for idle and confirms the materialized file's header carries the same session id. Request-recording tests prove parent/child calls receive different overlays, while locator tests prove resume keeps the path and fork changes it. + +Snapshot coverage updates the existing request-header pin for the bash description and the hook payload scenarios affected by `transcript_path`. No with-key e2e is required: model choice is not the contract, and the deterministic behavior is exercised through the real local executor, persistence backend, loader composition, and snapshot replay without depending on a provider credential. + +## Alternatives considered + +**Expose only `DSH_SESSION_ID` and make the agent search.** This copies Codex's shell surface but not its separate persistence resolver. A recursive `find` knows neither a custom root nor a non-JSONL backend, duplicates layout rules, and can race or mis-select under multiple sessions. Stable id remains necessary, but it is insufficient for the requested direct-path behavior. + +**Expose only the absolute path.** A path can be unavailable for non-file persistence and can name a not-yet-created lazy artifact; it is not the stable identity other APIs use for resume, lineage, or ownership. Keeping id and optional location separate makes those semantics explicit. + +**Write the current session into global `process.env`.** One process can drive multiple ACP sessions and in-process subagents concurrently, so a global assignment is last-writer-wins shared mutable state. Per-`ToolExecution` request env gives every child process an immutable snapshot of the correct agent instead. + +**Add a model-facing `session_info` tool.** A dedicated tool would add schema and another call when bash already supplies the requested query surface. It would also need the same persistence resolver, so it does not remove the seam work; the environment variables are smaller and compose with ordinary shell scripts. + +**Make tool-bash depend directly on the JSONL backend.** Reading backend config or importing `logPath` from the implementation would violate the interface/implementation/consumer split and leave hooks to invent another route. The persistence service is the only layer that can state whether a physical per-session path exists. + +## Consequences + +Foreground and background bash calls now expose the current agent's stable session id, while only JSONL-backed sessions expose a file path. No-agent calls receive neither variable; absent and SQLite persistence still leave `DSH_SESSION_ID` available. Resume retains identity and location, while forks, spawns, and concurrent child agents derive new values from their own immutable headers. Model-supplied `env`/`stdin` fields remain ignored, and both hook bridges consume the same locator with their dialect-specific unavailable value. + +The path reveals the configured persistence root to the model and hooks. The bash tool already runs with the executor's filesystem authority, so this adds discoverability rather than permission; deployments needing isolation use a sandboxing executor or omit local-file persistence. A valid location can be absent or stale relative to an open turn because durability checkpoints happen at turn end. + +Commands can overwrite either variable inside their own shell syntax. The values are debugging/correlation facts rather than credentials, so external consumers still verify the file header before attributing a transcript. `DSH_SESSION_JSONL` remains representation-specific, and backends without a dedicated per-session file return `undefined` instead of squeezing database coordinates into a path contract. The pre-release seam extension intentionally requires every persistence backend to make that supported/unsupported choice without a compatibility shim. diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 6d97017f1d..dc7dcd3d71 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -124,7 +124,7 @@ Registered by the tool registry itself under `mode: code` / `mode: both` (see th ### `bash` -Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. +Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. ```json { diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl index df7187bbbb..b8cf737a02 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611774323,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611774323,"data":{"content":[{"type":"text","text":"Call the run_code tool (NOT the native bash tool directly) with a program that runs exactly `echo BOTH_OK` via tools.bash and returns its output. Then reply with that output only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611774324,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-52lrTl.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.\n- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ndeclare const tools: {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */\n bash(args: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately. No timeout applies. */\n run_in_background?: boolean;\n }): Promise;\n /** Ask the executor to kill a running background bash task by task id. */\n bash_kill(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */\n bash_output(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit(args: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n }): Promise;\n /** Read a UTF-8 text file and return line-numbered content. */\n read(args: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n }): Promise;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */\n subagent(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n }): Promise;\n /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n }): Promise;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write(args: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n }): Promise;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow(args: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: {\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n }[];\n };\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n }): Promise;\n /** Create or fully replace a UTF-8 text file. */\n write(args: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n }): Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-52lrTl.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.\n- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ndeclare const tools: {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */\n bash(args: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately. No timeout applies. */\n run_in_background?: boolean;\n }): Promise;\n /** Ask the executor to kill a running background bash task by task id. */\n bash_kill(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */\n bash_output(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit(args: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n }): Promise;\n /** Read a UTF-8 text file and return line-numbered content. */\n read(args: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n }): Promise;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */\n subagent(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n }): Promise;\n /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n }): Promise;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write(args: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n }): Promise;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow(args: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: {\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n }[];\n };\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n }): Promise;\n /** Create or fully replace a UTF-8 text file. */\n write(args: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n }): Promise;\n}\n```","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611774792,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611774879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl index 72533bcdeb..3d6e65d390 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611771394,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611771394,"data":{"content":[{"type":"text","text":"Using ONE run_code program: call the bash tool twice — exactly `echo CODE_ONE` then exactly `echo CODE_TWO` — and return the two outputs joined with a plus sign. Then reply with that joined string only and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611771396,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-BteTVR.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.\n- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ndeclare const tools: {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */\n bash(args: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately. No timeout applies. */\n run_in_background?: boolean;\n }): Promise;\n /** Ask the executor to kill a running background bash task by task id. */\n bash_kill(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */\n bash_output(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit(args: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n }): Promise;\n /** Read a UTF-8 text file and return line-numbered content. */\n read(args: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n }): Promise;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */\n subagent(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n }): Promise;\n /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n }): Promise;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write(args: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n }): Promise;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow(args: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: {\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n }[];\n };\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n }): Promise;\n /** Create or fully replace a UTF-8 text file. */\n write(args: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n }): Promise;\n}\n```","tools":[{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611771396,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-BteTVR.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.\n\n## Writing code for run_code\n\nPass `run_code` the body of an async TypeScript function (erasable syntax only — no `enum` or namespaces; type annotations are advisory, the code runs type-stripped). Inside the program:\n\n- Call tools as `await tools.name(args)` — quoted access for exotic names: `tools[\"my-tool\"](args)`. Every call resolves to the tool's text output as a string. Tool arguments must be JSON-serializable.\n- A FAILED tool call rejects with an `Error` carrying the tool's error text — `try/catch` it to handle and continue.\n- Calls execute sequentially, even under `Promise.all`.\n- Emit results with `return` and/or `console.log(...)`. ONLY what you print or return comes back to you — intermediate tool results never enter the conversation, so extract just what you need.\n\nThe available tools:\n\n```ts\ndeclare const tools: {\n /** Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`. */\n bash(args: {\n /** The bash command to execute. */\n command: string;\n /** Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\". */\n description: string;\n /** Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry. */\n timeoutMs?: number;\n /** Working directory for this command. Defaults to the session workspace; a relative path is resolved against it. */\n workdir?: string;\n /** Run in the background and return a task id immediately. No timeout applies. */\n run_in_background?: boolean;\n }): Promise;\n /** Ask the executor to kill a running background bash task by task id. */\n bash_kill(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output. */\n bash_output(args: {\n /** Task id returned by the bash tool. */\n task_id: string;\n }): Promise;\n /** Edit an existing UTF-8 text file by replacing literal text. */\n edit(args: {\n /** Path to edit, resolved by the filesystem backend. */\n file_path: string;\n /** Literal text to replace. Must match exactly. */\n old_string: string;\n /** Literal replacement text. Use an empty string to delete the match. */\n new_string: string;\n /** Replace all matches. Defaults to false; when false, old_string must appear exactly once. */\n replace_all?: boolean;\n }): Promise;\n /** Read a UTF-8 text file and return line-numbered content. */\n read(args: {\n /** Path to read, resolved by the filesystem backend. */\n file_path: string;\n /** 1-based first line to return. Defaults to 1. */\n offset?: number;\n /** Maximum number of lines to return. Defaults to 2000. */\n limit?: number;\n }): Promise;\n /** Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation. */\n subagent(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs. */\n prompt: string;\n }): Promise;\n /** Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps. */\n subagent_fork(args: {\n /** A short (3-5 word) description of the delegated task, for display. */\n description: string;\n /** The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new. */\n prompt: string;\n }): Promise;\n /** Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished). */\n todo_write(args: {\n /** The COMPLETE task list, replacing any previous list. */\n todos: ({\n /** What the task is — a short imperative line. */\n content: string;\n /** pending (not started) | in_progress (now) | completed (done). */\n status: \"pending\" | \"in_progress\" | \"completed\";\n })[];\n }): Promise;\n /** Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn. The workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result. Script-body hooks: - `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. - `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages. - `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`. - `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim. Misused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`. Constraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes. */\n workflow(args: {\n /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */\n script: string;\n /** The workflow identity block (plain JSON — never code). */\n meta: {\n /** Short kebab-case workflow name. */\n name: string;\n /** One-line description of what the workflow does. */\n description: string;\n /** Optional guidance on when this workflow applies. */\n whenToUse?: string;\n /** Optional phase declarations matched by phase() calls. */\n phases?: {\n /** The phase title phase() calls match by exact string. */\n title: string;\n /** Optional one-line description of the phase. */\n detail?: string;\n /** Optional model override this phase is expected to use. */\n model?: string;\n }[];\n };\n /** Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]}). */\n args?: Record;\n }): Promise;\n /** Create or fully replace a UTF-8 text file. */\n write(args: {\n /** Path to write, resolved by the filesystem backend. */\n file_path: string;\n /** Full UTF-8 text content to write. */\n content: string;\n }): Promise;\n}\n```","tools":[{"name":"run_code","description":"Execute a TypeScript program against the available tools. Write the BODY of an async function (erasable syntax only; top-level `await` and `return` work) and call tools as `await tools.name(args)` per the declarations in the system prompt. Only what you print or return comes back — curate it.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"The program: the body of an async TypeScript function."}},"required":["code"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611771869,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611771978,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 8475c97896..5f49c4295d 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600629541,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600629541,"data":{"content":[{"type":"text","text":"Reply with exactly the word: PONG. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600629542,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/bn/vj1dvck95yd5jh3x4wskflxm0000gn/T/acp-snap-cwd-ka5r8w.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"You are an AI agent powered by the DeepSeek Harness SDK.\n\nYou are a coding assistant powered by the deepseek-v4-flash model. Your working\ndirectory is /var/folders/bn/vj1dvck95yd5jh3x4wskflxm0000gn/T/acp-snap-cwd-ka5r8w.\n\nVerify your work by running the code or tests. Keep answers brief and\nfactual.\n\n\nUse the read tool — not shell commands like cat — to inspect text files. Results include line numbers. Use offset and limit to continue reading large files.\n\nUse the write tool to create files or completely replace file contents. Existing files are overwritten, so read an existing file first (the default fs-policy requires it) and prefer edit for targeted changes.\n\nUse the edit tool for targeted changes to existing UTF-8 text files. It replaces literal old_string with new_string; by default old_string must appear exactly once. If old_string appears multiple times, provide a more specific old_string or set replace_all to true. Read the file first (the default fs-policy requires it), unless you just created or edited it in this session.\n\nCheck the [exit code: N] marker on every bash result; investigate failures before moving on.\n\nUse the workflow tool ONLY when the user explicitly asks for a workflow or for large multi-agent orchestration: you write a JavaScript script (the tool description documents the exact format) that fans work out across many subagents with phases and structured results. For one or two delegations, prefer plain subagent calls.","tools":[{"name":"bash","description":"Execute a bash command (`bash -c`) and return its stdout/stderr. Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, `$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. Set `run_in_background: true` for long-running commands: the call returns a task id immediately; poll it with `bash_output` and stop it with `bash_kill`.","parameters":{"type":"object","properties":{"command":{"type":"string","description":"The bash command to execute."},"description":{"type":"string","description":"Clear, concise description of what this command does in active voice, 5-10 words (shown in the UI). Examples: \"ls\" → \"List files in current directory\"; \"git status\" → \"Show working tree status\"; \"npm install\" → \"Install package dependencies\"."},"timeoutMs":{"type":"number","description":"Timeout in milliseconds. The executor applies its configured default and cap, and kills the command on expiry."},"workdir":{"type":"string","description":"Working directory for this command. Defaults to the session workspace; a relative path is resolved against it."},"run_in_background":{"type":"boolean","description":"Run in the background and return a task id immediately. No timeout applies."}},"required":["command","description"]}},{"name":"bash_kill","description":"Ask the executor to kill a running background bash task by task id.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"bash_output","description":"Read new output from a background bash task started with `bash` + `run_in_background`. Returns only output produced since the previous bash_output call, plus the task status. Tasks keep running while you do other work; poll again later for more output.","parameters":{"type":"object","properties":{"task_id":{"type":"string","description":"Task id returned by the bash tool."}},"required":["task_id"]}},{"name":"edit","description":"Edit an existing UTF-8 text file by replacing literal text.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to edit, resolved by the filesystem backend."},"old_string":{"type":"string","description":"Literal text to replace. Must match exactly."},"new_string":{"type":"string","description":"Literal replacement text. Use an empty string to delete the match."},"replace_all":{"type":"boolean","description":"Replace all matches. Defaults to false; when false, old_string must appear exactly once."}},"required":["file_path","old_string","new_string"]}},{"name":"read","description":"Read a UTF-8 text file and return line-numbered content.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to read, resolved by the filesystem backend."},"offset":{"type":"number","description":"1-based first line to return. Defaults to 1."},"limit":{"type":"number","description":"Maximum number of lines to return. Defaults to 2000."}},"required":["file_path"]}},{"name":"subagent","description":"Delegate a self-contained task to a subagent (a separate agent that works in its own context) and return its final result. Use this to offload focused, independent work — research, a scoped implementation, an analysis — so it does not consume this conversation's context. The subagent runs to completion and you receive only its final answer, not its intermediate steps. Give it a complete, standalone prompt: it does not see this conversation.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The complete, self-contained task for the subagent. It does not share this conversation's context, so include everything it needs."}},"required":["description","prompt"]}},{"name":"subagent_fork","description":"Delegate a task to a subagent that INHERITS this conversation: a child agent seeded with all completed turns so far (it does not see the current in-flight turn), returning only its final result. Use this when the subtask builds on this conversation's context — a follow-up analysis, a review, a continuation — without consuming this conversation's context for the work itself. You receive only its final answer, not its intermediate steps.","parameters":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 word) description of the delegated task, for display."},"prompt":{"type":"string","description":"The task for the subagent. It already sees this conversation's completed turns, so build on them freely and state only what is new."}},"required":["description","prompt"]}},{"name":"todo_write","description":"Record and update a structured task list for the current work. Send the ENTIRE list every call — it REPLACES the previous list (there are no partial updates, no per-item edits). Use it to plan multi-step work and show progress: add one todo per concrete step before you start. Keep AT MOST ONE todo `in_progress` at a time; while work remains, exactly one active task should be `in_progress`. Mark a todo `completed` the moment it is done (do not batch completions), and allow no `in_progress` item only once all work is complete. Skip the list for trivial single-step tasks. Statuses: `pending` (not started), `in_progress` (being worked on now), `completed` (finished).","parameters":{"type":"object","properties":{"todos":{"type":"array","description":"The COMPLETE task list, replacing any previous list.","items":{"type":"object","properties":{"content":{"type":"string","description":"What the task is — a short imperative line."},"status":{"type":"string","description":"pending (not started) | in_progress (now) | completed (done).","enum":["pending","in_progress","completed"]}},"required":["content","status"]}}},"required":["todos"]}},{"name":"workflow","description":"Run a JavaScript workflow script that orchestrates subagents at scale. Use this for work that fans out across many independent pieces — an audit over many files, a migration, multi-angle research, adversarial verification of findings — where you write the orchestration as a script instead of delegating turn by turn.\n\nThe workflow's identity rides the `meta` parameter as JSON: required `name` (short kebab-case) and `description` strings, optional `whenToUse` string and `phases` array (`{title, detail?, model?}`). The `script` parameter is the plain JavaScript body ONLY (NOT TypeScript, and NO `export const meta` statement — meta is a parameter, not code), running with top-level await; end with `return ` — the value must be JSON-serializable and is this tool's result.\n\nScript-body hooks:\n- `agent(prompt, opts?): Promise` — run one subagent to completion. Without `opts.schema` it resolves to the child's final text; with `opts.schema` (an object-rooted JSON Schema using ONLY type/properties/required/additionalProperties/items/enum/const — no oneOf/pattern/format/numeric bounds) it resolves to the validated object. Resolves `null` when the child fails (filter with `.filter(Boolean)`). Other opts: `label` (display), `phase` (progress group), `model` (override). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly.\n- `pipeline(items, ...stages): Promise` — run each item through the stages independently with NO barrier between stages (prefer this for multi-stage work). Each stage receives `(prev, item, index)`. An ordinary stage throw drops that ITEM to `null` and skips its remaining stages.\n- `parallel(thunks): Promise` — run zero-argument functions concurrently and await ALL of them (a barrier; use only when a stage genuinely needs every prior result together). A throwing thunk resolves to `null`.\n- `phase(title)` — start a progress phase; `log(message)` — narrate progress; `args` — the tool call's `args` input, verbatim.\n\nMisused hooks (bad arguments, unknown options, unsupported schemas, tripped caps) throw errors that ALWAYS kill the script — they never dissolve into a per-item `null`.\n\nConstraints: concurrency and total-agent caps apply; no filesystem, network, timers, or Node.js APIs are provided — the agents do the work, the script only coordinates them. The run executes in the foreground: this call returns when the whole script finishes.","parameters":{"type":"object","properties":{"script":{"type":"string","description":"The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `)."},"meta":{"type":"object","description":"The workflow identity block (plain JSON — never code).","properties":{"name":{"type":"string","description":"Short kebab-case workflow name."},"description":{"type":"string","description":"One-line description of what the workflow does."},"whenToUse":{"type":"string","description":"Optional guidance on when this workflow applies."},"phases":{"type":"array","description":"Optional phase declarations matched by phase() calls.","items":{"type":"object","properties":{"title":{"type":"string","description":"The phase title phase() calls match by exact string."},"detail":{"type":"string","description":"Optional one-line description of the phase."},"model":{"type":"string","description":"Optional model override this phase is expected to use."}},"required":["title"]}}},"required":["name","description"]},"args":{"type":"object","description":"Optional JSON input exposed to the script as the `args` global (wrap a bare list as a field, e.g. {\"files\": [...]})."}},"required":["script","meta"]}},{"name":"write","description":"Create or fully replace a UTF-8 text file.","parameters":{"type":"object","properties":{"file_path":{"type":"string","description":"Path to write, resolved by the filesystem backend."},"content":{"type":"string","description":"Full UTF-8 text content to write."}},"required":["file_path","content"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600630819,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600630820,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600630822,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/packages/bash/tool-bash/README.md b/packages/bash/tool-bash/README.md index eabb9298aa..40918ccefb 100644 --- a/packages/bash/tool-bash/README.md +++ b/packages/bash/tool-bash/README.md @@ -20,6 +20,12 @@ The plugin also contributes the `tool:bash` prompt section (order 105) — the c `command`, `workdir`, and `timeoutMs` are resolved against the executor's config defaults via `ctx.bash.resolve()` before execution, so the executor seam (`BashExecSpec`) receives explicit `workdir`/`timeoutMs` values. The workdir default is applied in the tool layer (from the calling agent's `session.header.cwd`) BEFORE `resolve()` — the per-session cwd must come from `exec.agent`, since N sessions share one executor; only when no session cwd is available does the executor fall back to its own config / `process.cwd()`. +### Session identity environment + +Every foreground and background call made for an agent receives `DSH_SESSION_ID=agent.session.header.id`. When the active persistence backend locates a JSONL artifact, the call also receives `DSH_SESSION_JSONL=`; absent persistence and non-file backends still provide the id but omit the JSONL variable. The path is a location hint: lazy materialization means it may not exist on the first turn, and during an open turn it can omit buffered events that have not reached `session/flush`. Neither value is an authorization credential. + +The overlay is computed from `ToolExecution.agent` for each call and passed through `BashExecRequest.env`; `process.env` is never modified, so concurrent parent/child agents keep separate values. The tool description names both variables so the model can inspect them without a permanent system-prompt section. + Result text: stdout, then a `[stderr]` section, then status markers — `[timed out after Nms]` whenever the executor's timer fired (reported independently of how the process ended, so a command that traps SIGTERM and exits 0 still shows it), `[killed by signal: …]` for a signal death, `[exit code: N]` for a non-zero exit (reported, **not** `isError`: the model decides how to react), and `[output truncated; full output: ]` when the tail was kept and a safe spill file is available. If the executor knows output was dropped but cannot safely advertise a complete spill file, the path is reported as `(unavailable)`. Only infrastructure failures (spawn errors, aborts) surface as `isError` results. ### `bash_output` @@ -44,7 +50,7 @@ When a background task finishes, a short notice is injected into the owning agen ## The tool builds its request from named args only -The `BashExecRequest` seam carries optional `stdin` and `env`, used by the hooks bridges to feed a hook command its JSON payload and `CLAUDE_*` env. This tool does **not** expose them as parameters: its request is built from `command`/`workdir`/`timeoutMs`/`signal`/`owner` only, so a model that includes `env` or `stdin` keys in its tool arguments has them ignored. This is not a trust boundary — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), and the real defense against leaking the harness's ambient secrets is `dsh-bash-local`'s credential scrub, which works regardless. A regression guard drives the real tool with those extra args and asserts the resulting request carries neither field — its job is to catch a future refactor that blindly spreads `...args` into the request (which would silently forward model input into the post-scrub `env` merge), not to defend a wall. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). +The `BashExecRequest` seam carries optional `stdin` and `env`, used by trusted consumers. This tool does **not** expose them as model parameters: it builds the request from named schema fields and adds only the session overlay above, so model-supplied `env`/`stdin` keys are ignored and cannot replace the trusted values. This is not a trust boundary — a model already has equivalent power through shell syntax (`FOO=bar cmd`, a heredoc), and the real defense against leaking ambient secrets is `dsh-bash-local`'s credential scrub. Regression guards assert extra model fields never enter the request while the trusted overlay still does. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md). ## Permissions diff --git a/packages/bash/tool-bash/package.json b/packages/bash/tool-bash/package.json index d8836d6a21..fabbdea076 100644 --- a/packages/bash/tool-bash/package.json +++ b/packages/bash/tool-bash/package.json @@ -25,6 +25,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-bash": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", + "@deepseek-ai/dsh-session-persistence": "^0.0.1", "@deepseek-ai/dsh-system-prompt": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -36,6 +37,8 @@ "@deepseek-ai/dsh-bash-local": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-session-persistence": "workspace:^", + "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.6" diff --git a/packages/bash/tool-bash/src/index.ts b/packages/bash/tool-bash/src/index.ts index d4a3105165..777332b7c3 100644 --- a/packages/bash/tool-bash/src/index.ts +++ b/packages/bash/tool-bash/src/index.ts @@ -43,6 +43,7 @@ import { isAbsolute, resolve as resolvePath } from 'node:path' import { defineTool } from '@deepseek-ai/dsh-tools' import type { GenericCallView, TerminalCallView, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools' import type { Agent } from '@deepseek-ai/dsh-agent' +import type {} from '@deepseek-ai/dsh-session-persistence' import type {} from '@deepseek-ai/dsh-system-prompt' import { BashTaskId, OwnerToken } from '@deepseek-ai/dsh-bash' import type { BashRunResult, BashTask, CollectedOutput } from '@deepseek-ai/dsh-bash' @@ -278,6 +279,22 @@ function resolveWorkdir(modelWorkdir: string | undefined, exec: { agent?: Agent return modelWorkdir } +/** + * Build the trusted per-execution session environment. Identity always comes + * from the calling agent's immutable session header; an optional JSONL path + * comes from the active persistence backend's side-effect-free locator. A + * non-agent caller has no current session, so it receives neither variable. + */ +function sessionEnvironment(ctx: Context, exec: { agent?: Agent }): Record | undefined { + const agent = exec.agent + if (agent === undefined) return undefined + + const env: Record = { DSH_SESSION_ID: agent.session.header.id } + const location = ctx.get('sessionPersistence')?.locate(agent.session.header) + if (location?.kind === 'jsonl') env.DSH_SESSION_JSONL = location.path + return env +} + /** Status line for background task reads. */ function statusLine(task: BashTask): string { switch (task.status) { @@ -360,6 +377,8 @@ export function apply(ctx: Context): void { description: 'Execute a bash command (`bash -c`) and return its stdout/stderr. ' + 'Each call runs in a fresh shell: no state (cwd, variables, functions) persists between calls — ' + 'pass `workdir` instead of using `cd`. Non-zero exits are reported as `[exit code: N]`. ' + + 'The current agent session id is available as `$DSH_SESSION_ID`; when JSONL persistence is configured, ' + + '`$DSH_SESSION_JSONL` is its absolute target path and may not exist or contain the current unflushed turn yet. ' + 'Long output is truncated to its tail; the full output is saved to a file whose path is reported when available. ' + 'Set `run_in_background: true` for long-running commands: the call returns a task id immediately; ' + 'poll it with `bash_output` and stop it with `bash_kill`.', @@ -385,11 +404,13 @@ export function apply(ctx: Context): void { // session runs in its own workspace (see resolveWorkdir); an explicit // model workdir still wins. const workdir = resolveWorkdir(args.workdir, exec) + const env = sessionEnvironment(ctx, exec) const request = { command: args.command, ...workdir !== undefined ? { workdir } : {}, ...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {}, ...exec.signal ? { signal: exec.signal } : {}, + ...env !== undefined ? { env } : {}, } if (args.run_in_background === true) { // Stamp the owner token (the agent's session id) onto the spec so the diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index b3d6bb3f77..430b0c3f11 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -1,8 +1,12 @@ -import { describe, expect, it } from 'vitest' +import { afterEach, describe, expect, it } from 'vitest' import { Context } from 'cordis' +import { existsSync, mkdtempSync, readFileSync, rmSync } from 'node:fs' +import { tmpdir } from 'node:os' +import { join } from 'node:path' import LlmService from '@deepseek-ai/dsh-llm' -import SessionStore from '@deepseek-ai/dsh-session' +import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { SessionEvent } from '@deepseek-ai/dsh-session' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' @@ -17,10 +21,11 @@ import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent * through the agent loop, exercising the same seams a live model would * (tool/call + tool/result session events, agent.inject notifications). */ -async function harness(adapter: MockAdapter) { +async function harness(adapter: MockAdapter, sessionRoot?: string) { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(SessionStore) + if (sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: sessionRoot }) await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) @@ -31,6 +36,9 @@ async function harness(adapter: MockAdapter) { return ctx } +const dirs: string[] = [] +afterEach(() => { for (const dir of dirs.splice(0)) rmSync(dir, { recursive: true, force: true }) }) + function waitForIdle(ctx: Context, agent: ReactLoopAgent): Promise { return new Promise((resolve) => { const dispose = ctx.on('agent/status', (subject, status) => { @@ -68,6 +76,37 @@ function resultText(event: SessionEvent): string { } describe('bash tool through the agent loop', () => { + it('first-turn bash receives session identity before the lazy JSONL file materializes', async () => { + const root = mkdtempSync(join(tmpdir(), 'dsh-bash-session-env-')) + dirs.push(root) + const adapter = new MockAdapter([ + toolCallResponse('call-1', 'bash', { + command: 'printf \'%s\\n%s\\n\' "$DSH_SESSION_ID" "$DSH_SESSION_JSONL"; if [ -e "$DSH_SESSION_JSONL" ]; then printf \'present\\n\'; else printf \'absent\\n\'; fi', + description: 'inspect session environment', + }), + textResponse('Session environment inspected.'), + ]) + const ctx = await harness(adapter, root) + const handle = ctx.agents.create({ + agentId: AgentId('session-env'), + sessionId: SessionId('session-env-id'), + agentOptions: { model: 'mock' }, + }) + const agent = handle.agent as ReactLoopAgent + const location = ctx.sessionPersistence.locate(agent.session.header) + expect(location?.kind).toBe('jsonl') + + agent.send([{ type: 'text', text: 'inspect the current session' }]) + await waitForIdle(ctx, agent) + + const result = findEvent(events(agent), 'tool/result') + expect(resultText(result)).toBe(`session-env-id\n${location?.path}\nabsent\n`) + expect(existsSync(location!.path)).toBe(true) + const header = JSON.parse(readFileSync(location!.path, 'utf8').split('\n')[0]!) as { type: string; id: string } + expect(header).toMatchObject({ type: 'session', id: 'session-env-id' }) + await handle.dispose() + }) + it('foreground: model calls bash, sees the result, replies', async () => { const adapter = new MockAdapter([ toolCallResponse('call-1', 'bash', { command: 'echo integration-ok', description: 'test command' }, 'Running it.'), diff --git a/packages/bash/tool-bash/tests/tools.spec.ts b/packages/bash/tool-bash/tests/tools.spec.ts index 7d4b34f74f..5539787399 100644 --- a/packages/bash/tool-bash/tests/tools.spec.ts +++ b/packages/bash/tool-bash/tests/tools.spec.ts @@ -10,6 +10,8 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry from '@deepseek-ai/dsh-tools' import AgentRegistry from '@deepseek-ai/dsh-agent' import type { Agent } from '@deepseek-ai/dsh-agent' +import SessionStore from '@deepseek-ai/dsh-session' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' import * as ToolBash from '@deepseek-ai/dsh-tool-bash' import { renderResult } from '@deepseek-ai/dsh-tool-bash' @@ -910,16 +912,111 @@ describe('the model-facing bash tool builds its request from named args only (no kill(): boolean { return false } } - async function setupRecording() { + async function setupRecording(withJsonl = false) { const ctx = new Context() await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) + if (withJsonl) { + await ctx.plugin(SessionStore) + await ctx.plugin(SessionPersistenceJsonl, { root: join(spillDir, 'jsonl') }) + } await ctx.plugin(RecordingBashExecutor) await ctx.plugin(ToolBash) return { ctx, bash: ctx.bash as RecordingBashExecutor } } + it('describes the trusted session variables to the model', async () => { + const { ctx } = await setupRecording() + const description = ctx.tools.get('bash')?.description ?? '' + expect(description).toContain('DSH_SESSION_ID') + expect(description).toContain('DSH_SESSION_JSONL') + }) + + it('injects the session id and JSONL target path into a foreground request', async () => { + const { ctx, bash } = await setupRecording(true) + const agent = registerFakeAgent(ctx, 'request-fg', () => undefined) + const path = ctx.sessionPersistence.locate(agent.session.header)?.path + + await ctx.tools.execute({ + callId: CallId('session-env-fg'), + name: 'bash', + arguments: { command: 'true', description: 'run command' }, + agent, + }) + + expect(bash.requests[0]?.env).toEqual({ + DSH_SESSION_ID: 'request-fg', + DSH_SESSION_JSONL: path, + }) + }) + + it('injects the same trusted variables into a background request without forwarding model env', async () => { + const { ctx, bash } = await setupRecording(true) + const agent = registerFakeAgent(ctx, 'request-bg', () => undefined) + const path = ctx.sessionPersistence.locate(agent.session.header)?.path + + await ctx.tools.execute({ + callId: CallId('session-env-bg'), + name: 'bash', + arguments: { + command: 'sleep 1', + description: 'run command', + run_in_background: true, + env: { DSH_SESSION_ID: 'spoofed', DSH_SESSION_JSONL: '/tmp/spoofed' }, + }, + agent, + }) + + expect(bash.requests[0]?.env).toEqual({ + DSH_SESSION_ID: 'request-bg', + DSH_SESSION_JSONL: path, + }) + }) + + it('injects only the stable session id when no JSONL locator is available', async () => { + const { ctx, bash } = await setupRecording() + const agent = registerFakeAgent(ctx, 'request-id-only', () => undefined) + const ambient = process.env.DSH_SESSION_ID + + await ctx.tools.execute({ + callId: CallId('session-env-id-only'), + name: 'bash', + arguments: { command: 'true', description: 'run command' }, + agent, + }) + + expect(bash.requests[0]?.env).toEqual({ DSH_SESSION_ID: 'request-id-only' }) + expect(process.env.DSH_SESSION_ID).toBe(ambient) + }) + + it('keeps parent and child agent session environments isolated', async () => { + const { ctx, bash } = await setupRecording(true) + const parent = registerFakeAgent(ctx, 'request-parent', () => undefined) + const child = registerFakeAgent(ctx, 'request-child', () => undefined) + + for (const [callId, agent] of [['parent', parent], ['child', child]] as const) { + await ctx.tools.execute({ + callId: CallId(`session-env-${callId}`), + name: 'bash', + arguments: { command: 'true', description: 'run command' }, + agent, + }) + } + + expect(bash.requests.map(request => request.env)).toEqual([ + { + DSH_SESSION_ID: 'request-parent', + DSH_SESSION_JSONL: ctx.sessionPersistence.locate(parent.session.header)?.path, + }, + { + DSH_SESSION_ID: 'request-child', + DSH_SESSION_JSONL: ctx.sessionPersistence.locate(child.session.header)?.path, + }, + ]) + expect(bash.requests[0]?.env?.DSH_SESSION_JSONL).not.toBe(bash.requests[1]?.env?.DSH_SESSION_JSONL) + }) + it('does not forward env/stdin even when the model includes them as extra arguments', async () => { const { ctx, bash } = await setupRecording() // Extra args: the model includes `env` and `stdin` keys hoping they reach the diff --git a/packages/bash/tool-bash/tsconfig.json b/packages/bash/tool-bash/tsconfig.json index 89b10bfea8..6828cd1738 100644 --- a/packages/bash/tool-bash/tsconfig.json +++ b/packages/bash/tool-bash/tsconfig.json @@ -23,6 +23,9 @@ { "path": "../../core/agent" }, + { + "path": "../../session-persistence/session-persistence" + }, { "path": "../../bash/bash" } diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 68fd63ae25..667bf69fae 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -129,6 +129,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'sessionPersistence', summary: 'Abstract durable session-persistence service.', methods: [ + 'abstract locate(meta: SessionHeader): SessionLocation | undefined', 'abstract create(meta: SessionHeader): Promise', 'abstract append(id: SessionId, events: readonly SessionEvent[]): Promise', 'abstract load(id: SessionId): Promise<{ meta: SessionHeader; events: SessionEvent[] }>', @@ -701,6 +702,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'SessionId', declaration: 'export type SessionId = Branded<\'SessionId\'>;', }, + { + name: 'SessionLocation', + declaration: 'export interface SessionLocation {\n readonly kind: string;\n readonly path: string;\n}', + }, { name: 'StreamChunk', declaration: 'export type StreamChunk = {\n type: \'block-start\';\n index: number;\n blockType: ContentBlockType;\n} | {\n type: \'text-delta\';\n index: number;\n text: string;\n} | {\n type: \'reasoning-delta\';\n index: number;\n text: string;\n} | {\n type: \'tool-call-delta\';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n} | {\n type: \'block-end\';\n index: number;\n block: ContentBlock;\n} | {\n type: \'usage\';\n usage: TokenUsage;\n} | {\n type: \'finish\';\n reason: FinishReason;\n};', diff --git a/packages/hooks/hooks-claude/README.md b/packages/hooks/hooks-claude/README.md index 306bfdbfeb..b2e593cd4a 100644 --- a/packages/hooks/hooks-claude/README.md +++ b/packages/hooks/hooks-claude/README.md @@ -46,6 +46,8 @@ The three emit points run detached — no seam awaits a `SessionStart`/`Subagent The matcher subject is the tool name (`PreToolUse`/`PostToolUse`), the session source (`SessionStart`), or a constant `agent_type` of `general-purpose` (`SubagentStart`/`SubagentStop` — the harness subagent seam carries no per-kind label, so the bridge reports Claude Code's own Task-tool default; a default/`*`/empty `agent_type` matcher fires, a specific-kind matcher does not); `UserPromptSubmit`/`Stop` ignore matchers. Multiple file-configured hooks on one point run **serially, in config order**, and fold most-restrictively (`deny > ask > allow`, see `dsh-hook-protocol`); serial keeps each hook's `hook/invoked`/`hook/result` pair adjacent in the log, and the fold is order-independent for the decision (see the RFC's "run serially, not concurrently" note). +Every agent-scoped stdin payload carries `session_id` and string-shaped `transcript_path`. The bridge resolves the latter through `ctx.sessionPersistence.locate(session.header)` when available and otherwise sends `''`. Lookup does not create or flush the artifact, so a path can be absent before the first turn-end checkpoint or omit the current open turn. + ## Context source Injected context carries an explicit `{ kind: 'plugin', plugin: 'hooks-claude' }` source. `agent.inject()` defaults a missing source to `{ kind: 'user' }`, which would mislabel plugin context as a user prompt — so the bridge always names itself. diff --git a/packages/hooks/hooks-claude/package.json b/packages/hooks/hooks-claude/package.json index 5cc39f9999..571f533723 100644 --- a/packages/hooks/hooks-claude/package.json +++ b/packages/hooks/hooks-claude/package.json @@ -29,6 +29,7 @@ "@deepseek-ai/dsh-hook-protocol": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-session-persistence": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -41,6 +42,8 @@ "@deepseek-ai/dsh-hook-protocol": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-session-persistence": "workspace:^", + "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", diff --git a/packages/hooks/hooks-claude/src/index.ts b/packages/hooks/hooks-claude/src/index.ts index d16e26e4a6..2e86329d56 100644 --- a/packages/hooks/hooks-claude/src/index.ts +++ b/packages/hooks/hooks-claude/src/index.ts @@ -27,6 +27,7 @@ import type { Context } from 'cordis' import z from 'schemastery' import type { Agent, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' +import type {} from '@deepseek-ai/dsh-session-persistence' import type { PostToolDecision, PreToolDecision, ToolExecution, ToolExecutionResult } from '@deepseek-ai/dsh-tools' import { appendHookInvoked, @@ -246,7 +247,7 @@ export function apply(ctx: Context, config: Config): void { // to the interception seams; today the contract is "injected as soon as the // hook resolves", not "before the first request". --- ctx.on('agent/session-start', (agent, source) => { - detached.track(runPoint('SessionStart', source, sessionStartPayload(agent, source), { agent, signal: detached.signal }) + detached.track(runPoint('SessionStart', source, sessionStartPayload(ctx, agent, source), { agent, signal: detached.signal }) .then((merged) => { const context = contextFrom(merged) if (context) agent.inject(context.content, { source: context.source }) @@ -260,7 +261,7 @@ export function apply(ctx: Context, config: Config): void { // matcher subject (CC ignores matchers for this event). --- ctx.on('agent/prompt-submit', async (agent, content, _source, next): Promise => { const turn = lastTurn(agent) - const merged = await runPoint('UserPromptSubmit', '', promptPayload(agent, content), { agent, turn }) + const merged = await runPoint('UserPromptSubmit', '', promptPayload(ctx, agent, content), { agent, turn }) if (merged.decision === 'deny') { return { kind: 'block', reason: merged.reason ?? 'blocked by UserPromptSubmit hook' } } @@ -281,7 +282,7 @@ export function apply(ctx: Context, config: Config): void { // --- PreToolUse → PreToolDecision. Matcher subject is the tool name. --- ctx.on('tools/pre-execute', async (exec, next): Promise => { const turn = lastTurn(exec.agent) - const merged = await runPoint('PreToolUse', exec.name, preToolPayload(exec), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) + const merged = await runPoint('PreToolUse', exec.name, preToolPayload(ctx, exec), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) if (merged.decision === 'deny') return { kind: 'deny', reason: merged.reason ?? 'blocked by PreToolUse hook' } if (merged.decision === 'ask') return { kind: 'ask', ...merged.reason !== undefined ? { reason: merged.reason } : {} } return next() @@ -290,7 +291,7 @@ export function apply(ctx: Context, config: Config): void { // --- PostToolUse → PostToolDecision. Matcher subject is the tool name. --- ctx.on('tools/post-execute', async (exec, result, next): Promise => { const turn = lastTurn(exec.agent) - const merged = await runPoint('PostToolUse', exec.name, postToolPayload(exec, result), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) + const merged = await runPoint('PostToolUse', exec.name, postToolPayload(ctx, exec, result), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) const context = contextFrom(merged) if (merged.decision === 'deny') { return { kind: 'block', feedback: [{ type: 'text', text: merged.reason ?? 'blocked by PostToolUse hook' }], ...context ? { additionalContext: context } : {} } @@ -317,7 +318,7 @@ export function apply(ctx: Context, config: Config): void { // false, so a Stop hook that unconditionally blocks would force-continue every // step — a hook author must self-limit until the guard lands. --- ctx.on('agent/turn-continuation', async (agent, turn, _default, next): Promise => { - const merged = await runPoint('Stop', '', stopPayload(agent), { agent, turn }) + const merged = await runPoint('Stop', '', stopPayload(ctx, agent), { agent, turn }) if (merged.decision === 'deny') { // A blocking Stop hook forces continuation. It carries its reason as // next-step steering; a blocking hook that emitted no reason (exit 2, empty @@ -339,7 +340,7 @@ export function apply(ctx: Context, config: Config): void { // a specific-kind matcher does not (documented in the RFC). --- ctx.on('subagent/start', (info) => { const child = ctx.get('agents')?.get(info.id) - detached.track(runPoint('SubagentStart', SUBAGENT_TYPE, subagentPayload('SubagentStart', info, child), { ...child ? { agent: child } : {}, signal: detached.signal }) + detached.track(runPoint('SubagentStart', SUBAGENT_TYPE, subagentPayload(ctx, 'SubagentStart', info, child), { ...child ? { agent: child } : {}, signal: detached.signal }) .then((merged) => { const context = contextFrom(merged) if (context && child) child.inject(context.content, { source: context.source }) @@ -355,7 +356,7 @@ export function apply(ctx: Context, config: Config): void { // reject — no `.catch` is needed (the tracker's settlement bookkeeping // would absorb one anyway). const child = ctx.get('agents')?.get(info.id) - detached.track(runPoint('SubagentStop', SUBAGENT_TYPE, subagentPayload('SubagentStop', info, child), { ...child ? { agent: child } : {}, signal: detached.signal })) + detached.track(runPoint('SubagentStop', SUBAGENT_TYPE, subagentPayload(ctx, 'SubagentStop', info, child), { ...child ? { agent: child } : {}, signal: detached.signal })) }) } @@ -385,28 +386,31 @@ function blocksToText(content: ContentBlock[]): string { return content.filter((b): b is Extract => b.type === 'text').map(b => b.text).join('') } -function base(agent: Agent | undefined, event: string): Record { +function base(ctx: Context, agent: Agent | undefined, event: string): Record { return { session_id: agent?.session.header.id ?? '', + transcript_path: agent === undefined + ? '' + : ctx.get('sessionPersistence')?.locate(agent.session.header)?.path ?? '', cwd: agent?.session.header.cwd ?? process.cwd(), hook_event_name: event, } } -function sessionStartPayload(agent: Agent, source: string): Record { - return { ...base(agent, 'SessionStart'), source } +function sessionStartPayload(ctx: Context, agent: Agent, source: string): Record { + return { ...base(ctx, agent, 'SessionStart'), source } } -function promptPayload(agent: Agent, content: ContentBlock[]): Record { - return { ...base(agent, 'UserPromptSubmit'), prompt: blocksToText(content) } +function promptPayload(ctx: Context, agent: Agent, content: ContentBlock[]): Record { + return { ...base(ctx, agent, 'UserPromptSubmit'), prompt: blocksToText(content) } } -function preToolPayload(exec: ToolExecution): Record { - return { ...base(exec.agent, 'PreToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId } +function preToolPayload(ctx: Context, exec: ToolExecution): Record { + return { ...base(ctx, exec.agent, 'PreToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId } } -function postToolPayload(exec: ToolExecution, result: ToolExecutionResult): Record { - return { ...base(exec.agent, 'PostToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId, tool_response: blocksToText(result.content) } +function postToolPayload(ctx: Context, exec: ToolExecution, result: ToolExecutionResult): Record { + return { ...base(ctx, exec.agent, 'PostToolUse'), tool_name: exec.name, tool_input: exec.arguments, tool_use_id: exec.callId, tool_response: blocksToText(result.content) } } -function stopPayload(agent: Agent): Record { - return { ...base(agent, 'Stop'), stop_hook_active: false } +function stopPayload(ctx: Context, agent: Agent): Record { + return { ...base(ctx, agent, 'Stop'), stop_hook_active: false } } /** * Build a SubagentStart/SubagentStop payload from the CC base (the child's @@ -414,9 +418,9 @@ function stopPayload(agent: Agent): Record { * fields. `agent_type` is the CC-default {@link SUBAGENT_TYPE}; `stop_hook_active` * is present on SubagentStop only (the loop-guard flag, always false this cut). */ -function subagentPayload(event: 'SubagentStart' | 'SubagentStop', info: { id: string }, child: Agent | undefined): Record { +function subagentPayload(ctx: Context, event: 'SubagentStart' | 'SubagentStop', info: { id: string }, child: Agent | undefined): Record { return { - ...base(child, event), + ...base(ctx, child, event), agent_id: info.id, agent_type: SUBAGENT_TYPE, ...event === 'SubagentStop' ? { stop_hook_active: false } : {}, diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index f06cdcf6b4..fb7705a149 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -1,10 +1,11 @@ import { afterEach, describe, expect, it, vi } from 'vitest' -import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync } from 'node:fs' +import { mkdtempSync, rmSync, writeFileSync, chmodSync, existsSync, readFileSync } from 'node:fs' import { tmpdir } from 'node:os' import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' @@ -27,11 +28,12 @@ function hooks(d: string, h: unknown): string { writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json') } -type HarnessOpts = { pluginRoot?: string; projectDir?: string; stderrSummaryMaxChars?: number } +type HarnessOpts = { pluginRoot?: string; projectDir?: string; stderrSummaryMaxChars?: number; sessionRoot?: string } async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(SessionStore) + if (opts.sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: opts.sessionRoot }) await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) @@ -56,6 +58,28 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): } describe('hooks-claude coverage — config option arms + substitution + skip warning', () => { + it('uses the persistence locator for transcript_path and an empty string without one', async () => { + async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string }; expected: string | undefined }> { + const d = dir() + const cap = join(d, 'payload') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + return { + payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string }, + expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, + } + } + + const located = await capture(dir()) + expect(located.payload.transcript_path).toBe(located.expected) + expect((await capture()).payload.transcript_path).toBe('') + }) + it('honors pluginRoot + projectDir substitution and warns on a skipped non-command hook', async () => { const d = dir() // ${CLAUDE_PLUGIN_ROOT} resolves to d; the script writes its own cwd-independent marker. diff --git a/packages/hooks/hooks-claude/tsconfig.json b/packages/hooks/hooks-claude/tsconfig.json index 909db9b5c3..07c88610f9 100644 --- a/packages/hooks/hooks-claude/tsconfig.json +++ b/packages/hooks/hooks-claude/tsconfig.json @@ -29,6 +29,9 @@ { "path": "../../core/session" }, + { + "path": "../../session-persistence/session-persistence" + }, { "path": "../../subagent/subagent" }, diff --git a/packages/hooks/hooks-codex/README.md b/packages/hooks/hooks-codex/README.md index b3fbc39928..255108de50 100644 --- a/packages/hooks/hooks-codex/README.md +++ b/packages/hooks/hooks-codex/README.md @@ -48,6 +48,8 @@ The hooks themselves run in the agent's session workspace: for the agent-scoped A tool call's payload carries the real `tool_name` (the same value the matcher tests) and Codex's `tool_input: { command }` shape (the `command` arg when present, else `''`). The matcher subject is the tool name (`PreToolUse`/`PostToolUse`) or the session source (`SessionStart`); `UserPromptSubmit`/`Stop` ignore matchers. +Every agent-scoped stdin payload carries `session_id` and `transcript_path`. The bridge resolves the latter through `ctx.sessionPersistence.locate(session.header)` when available and otherwise sends `null`, preserving the Codex `string | null` shape. Lookup does not create or flush the artifact, so a path can be absent before the first turn-end checkpoint or omit the current open turn. + `SessionStart` — the one emit point — runs detached; each run chain is tracked, and disposing the bridge aborts a still-running hook process, then drains the continuation before the dispose resolves (`createDetachedRuns` in `dsh-hook-protocol`). ## Context source diff --git a/packages/hooks/hooks-codex/package.json b/packages/hooks/hooks-codex/package.json index f26b57fe11..2dc358e461 100644 --- a/packages/hooks/hooks-codex/package.json +++ b/packages/hooks/hooks-codex/package.json @@ -29,6 +29,7 @@ "@deepseek-ai/dsh-hook-protocol": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", + "@deepseek-ai/dsh-session-persistence": "^0.0.1", "@deepseek-ai/dsh-tools": "^0.0.1", "cordis": "^4.0.0-rc.6" }, @@ -40,6 +41,8 @@ "@deepseek-ai/dsh-hook-protocol": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", + "@deepseek-ai/dsh-session-persistence": "workspace:^", + "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-system-prompt": "workspace:^", "@deepseek-ai/dsh-tools": "workspace:^", "cordis": "^4.0.0-rc.6" diff --git a/packages/hooks/hooks-codex/src/index.ts b/packages/hooks/hooks-codex/src/index.ts index e164d98a70..798743b38b 100644 --- a/packages/hooks/hooks-codex/src/index.ts +++ b/packages/hooks/hooks-codex/src/index.ts @@ -20,6 +20,7 @@ import type { Context } from 'cordis' import z from 'schemastery' import type { Agent, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm' +import type {} from '@deepseek-ai/dsh-session-persistence' import type { PostToolDecision, PreToolDecision, ToolExecution, ToolExecutionResult } from '@deepseek-ai/dsh-tools' import { appendHookInvoked, @@ -196,7 +197,7 @@ export function apply(ctx: Context, config: Config): void { // the model (a slow hook can miss the first request). Gating is a deferred // loop-level change; the contract is "injected as soon as the hook resolves". ctx.on('agent/session-start', (agent, source) => { - detached.track(runPoint('SessionStart', source, { ...base(agent, 'SessionStart', model), source }, { agent, plainStdoutAsContext: true, signal: detached.signal }) + detached.track(runPoint('SessionStart', source, { ...base(ctx, agent, 'SessionStart', model), source }, { agent, plainStdoutAsContext: true, signal: detached.signal }) .then((merged) => { const context = contextFrom(merged) if (context) agent.inject(context.content, { source: context.source }) @@ -207,7 +208,7 @@ export function apply(ctx: Context, config: Config): void { // UserPromptSubmit → PromptDecision. Codex can only BLOCK (no allow/ask). ctx.on('agent/prompt-submit', async (agent, content, _source, next): Promise => { const turn = lastTurn(agent) - const merged = await runPoint('UserPromptSubmit', '', { ...turnBase(agent, 'UserPromptSubmit', model), prompt: blocksToText(content) }, { agent, turn, plainStdoutAsContext: true }) + const merged = await runPoint('UserPromptSubmit', '', { ...turnBase(ctx, agent, 'UserPromptSubmit', model), prompt: blocksToText(content) }, { agent, turn, plainStdoutAsContext: true }) if (merged.decision === 'deny') return { kind: 'block', reason: merged.reason ?? 'blocked by UserPromptSubmit hook' } // Context alone is not a veto: DELEGATE so a later prompt-submit listener can // still block/rewrite, then fold our context onto its decision. @@ -224,7 +225,7 @@ export function apply(ctx: Context, config: Config): void { // PreToolUse → PreToolDecision. Codex blocks only (no allow/ask honored). ctx.on('tools/pre-execute', async (exec, next): Promise => { const turn = lastTurn(exec.agent) - const merged = await runPoint('PreToolUse', exec.name, preToolPayload(exec, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) + const merged = await runPoint('PreToolUse', exec.name, preToolPayload(ctx, exec, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) if (merged.decision === 'deny') return { kind: 'deny', reason: merged.reason ?? 'blocked by PreToolUse hook' } return next() }) @@ -232,7 +233,7 @@ export function apply(ctx: Context, config: Config): void { // PostToolUse → PostToolDecision (block with feedback, or attach context). ctx.on('tools/post-execute', async (exec, result, next): Promise => { const turn = lastTurn(exec.agent) - const merged = await runPoint('PostToolUse', exec.name, postToolPayload(exec, result, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) + const merged = await runPoint('PostToolUse', exec.name, postToolPayload(ctx, exec, result, model), { ...exec.agent ? { agent: exec.agent } : {}, turn, ...exec.signal ? { signal: exec.signal } : {} }) const context = contextFrom(merged) if (merged.decision === 'deny') { return { kind: 'block', feedback: [{ type: 'text', text: merged.reason ?? 'blocked by PostToolUse hook' }], ...context ? { additionalContext: context } : {} } @@ -256,7 +257,7 @@ export function apply(ctx: Context, config: Config): void { // force-continue every step (`stop_hook_active` is always false here); the // loop-guard (stop_hook_active + a max-consecutive cap) is deferred. ctx.on('agent/turn-continuation', async (agent, turn, _default, next): Promise => { - const merged = await runPoint('Stop', '', { ...turnBase(agent, 'Stop', model), stop_hook_active: false, last_assistant_message: null }, { agent, turn }) + const merged = await runPoint('Stop', '', { ...turnBase(ctx, agent, 'Stop', model), stop_hook_active: false, last_assistant_message: null }, { agent, turn }) if (merged.decision === 'deny') { // A blocking Stop hook forces continuation; a block with no reason (exit 2, // empty stderr) still forces it — fall back to a generic steering line @@ -285,10 +286,12 @@ function blocksToText(content: ContentBlock[]): string { } /** Base fields on every Codex payload (no turn_id). */ -function base(agent: Agent | undefined, event: string, model: string): Record { +function base(ctx: Context, agent: Agent | undefined, event: string, model: string): Record { return { session_id: agent?.session.header.id ?? '', - transcript_path: null, + transcript_path: agent === undefined + ? null + : ctx.get('sessionPersistence')?.locate(agent.session.header)?.path ?? null, cwd: agent?.session.header.cwd ?? process.cwd(), hook_event_name: event, model, @@ -297,8 +300,8 @@ function base(agent: Agent | undefined, event: string, model: string): Record { - return { ...base(agent, event, model), turn_id: String(lastTurn(agent)) } +function turnBase(ctx: Context, agent: Agent | undefined, event: string, model: string): Record { + return { ...base(ctx, agent, event, model), turn_id: String(lastTurn(agent)) } } /** Extract a `command` string from a tool call's parsed arguments, else ''. */ @@ -310,14 +313,14 @@ function commandOf(args: unknown): string { return '' } -function preToolPayload(exec: ToolExecution, model: string): Record { +function preToolPayload(ctx: Context, exec: ToolExecution, model: string): Record { // `tool_name` is the REAL tool name (matching the `exec.name` matcher subject); // a hardcoded constant would disagree with what the matcher tests and make a // config's tool matcher never fire. `tool_input` keeps Codex's `{ command }` // shape (its shell payload), derived from the call's `command` arg when present. - return { ...turnBase(exec.agent, 'PreToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId } + return { ...turnBase(ctx, exec.agent, 'PreToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId } } -function postToolPayload(exec: ToolExecution, result: ToolExecutionResult, model: string): Record { - return { ...turnBase(exec.agent, 'PostToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId, tool_response: blocksToText(result.content) } +function postToolPayload(ctx: Context, exec: ToolExecution, result: ToolExecutionResult, model: string): Record { + return { ...turnBase(ctx, exec.agent, 'PostToolUse', model), tool_name: exec.name, tool_input: { command: commandOf(exec.arguments) }, tool_use_id: exec.callId, tool_response: blocksToText(result.content) } } diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index c83137df53..0dfac498d2 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -5,6 +5,7 @@ import { join } from 'node:path' import { Context } from 'cordis' import LlmService from '@deepseek-ai/dsh-llm' import SessionStore, { type SessionEvent } from '@deepseek-ai/dsh-session' +import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools' import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent' @@ -23,9 +24,12 @@ function hooks(d: string, h: unknown): string { writeFileSync(join(d, 'hooks.json'), JSON.stringify({ hooks: h })); return join(d, 'hooks.json') } -async function harness(configPath: string, adapter: MockAdapter, opts: { stderrSummaryMaxChars?: number } = {}): Promise { +type HarnessOpts = { stderrSummaryMaxChars?: number; sessionRoot?: string } +async function harness(configPath: string, adapter: MockAdapter, opts: HarnessOpts = {}): Promise { const ctx = new Context() - await ctx.plugin(LlmService); await ctx.plugin(SessionStore); await ctx.plugin(SystemPrompt) + await ctx.plugin(LlmService); await ctx.plugin(SessionStore) + if (opts.sessionRoot !== undefined) await ctx.plugin(SessionPersistenceJsonl, { root: opts.sessionRoot }) + await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry); await ctx.plugin(AgentRegistry); await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksCodex, { configPath, model: 'm', ...opts }) @@ -47,6 +51,28 @@ async function waitFor(predicate: () => boolean, timeout = 5000, interval = 10): } describe('hooks-codex coverage — decision mapping paths', () => { + it('uses the persistence locator for transcript_path and null without one', async () => { + async function capture(sessionRoot?: string): Promise<{ payload: { transcript_path: string | null }; expected: string | undefined }> { + const d = dir() + const cap = join(d, 'payload') + const path = hooks(d, { PreToolUse: [{ hooks: [{ type: 'command', command: sh(d, 'capture.sh', `#!/usr/bin/env bash\ncat > "${cap}"\n`) }] }] }) + const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) + const ctx = await harness(path, adapter, { ...sessionRoot !== undefined ? { sessionRoot } : {} }) + ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) + const agent = ctx.agentLoop.create(AgentId('transcript'), { model: 'mock' }) + agent.send([{ type: 'text', text: 'go' }]) + await waitForIdle(ctx, agent) + return { + payload: JSON.parse(readFileSync(cap, 'utf8')) as { transcript_path: string | null }, + expected: ctx.get('sessionPersistence')?.locate(agent.session.header)?.path, + } + } + + const located = await capture(dir()) + expect(located.payload.transcript_path).toBe(located.expected) + expect((await capture()).payload.transcript_path).toBeNull() + }) + it('UserPromptSubmit block (exit 2) → rejected turn; default reason on empty stderr', async () => { const d = dir() hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) diff --git a/packages/hooks/hooks-codex/tsconfig.json b/packages/hooks/hooks-codex/tsconfig.json index f936b500aa..ae3c91e9dd 100644 --- a/packages/hooks/hooks-codex/tsconfig.json +++ b/packages/hooks/hooks-codex/tsconfig.json @@ -29,6 +29,9 @@ { "path": "../../core/session" }, + { + "path": "../../session-persistence/session-persistence" + }, { "path": "../../llm/llm" }, diff --git a/packages/session-persistence/session-persistence-jsonl/README.md b/packages/session-persistence/session-persistence-jsonl/README.md index 9a76381614..7d04f90629 100644 --- a/packages/session-persistence/session-persistence-jsonl/README.md +++ b/packages/session-persistence/session-persistence-jsonl/README.md @@ -19,6 +19,8 @@ The JSONL durable session-persistence backend — a concrete `SessionPersistence |---|---|---| | `root` | `string` (required) | Root directory for all session files. **No default** — a `process.cwd()` default would scatter files as the process's cwd changes (bash calls, subprocesses). | +`locate(meta)` returns `{ kind: 'jsonl', path }` using the resolved absolute root and the same cwd-bucket/id encoding as materialization. It performs no filesystem I/O: the target can be returned before the file exists, and an existing file contains only the last flushed prefix. + ## Durability and crash semantics - **Lazy materialization.** `create(meta)` writes nothing; the `.jsonl` (header + first batch) is written atomically (temp-write + `fsync` + rename) on the first `append`. A created-but-never-appended session leaves nothing on disk and is absent from `list`. diff --git a/packages/session-persistence/session-persistence-jsonl/src/index.ts b/packages/session-persistence/session-persistence-jsonl/src/index.ts index a69c979756..658deb156e 100644 --- a/packages/session-persistence/session-persistence-jsonl/src/index.ts +++ b/packages/session-persistence/session-persistence-jsonl/src/index.ts @@ -11,8 +11,9 @@ * (the `session/event` → buffer → `session/flush` drain, per-session * serialization, write cursors, fork-seed persistence, HMR live-adoption, * crash-repair sequencing, dispose quiescence) lives in the backend-agnostic - * {@link PersistenceCoordinator} this class composes. The four public - * {@link SessionPersistence} methods delegate to the coordinator. + * {@link PersistenceCoordinator} this class composes. The four stateful public + * {@link SessionPersistence} methods delegate to the coordinator; the pure + * locator remains backend-owned. * * @module @deepseek-ai/dsh-session-persistence-jsonl */ @@ -24,7 +25,7 @@ import { dirname, resolve } from 'node:path' import { randomBytes } from 'node:crypto' import { SessionPersistence, PersistenceCoordinator, - type PersistenceBackend, type StoredPrefix, + type PersistenceBackend, type SessionLocation, type StoredPrefix, } from '@deepseek-ai/dsh-session-persistence' import type { Session, SessionEvent, SessionId, SessionHeader } from '@deepseek-ai/dsh-session' import { @@ -90,6 +91,11 @@ export class SessionPersistenceJsonl extends SessionPersistence implements Persi // --- SessionPersistence service surface (delegated to the coordinator) --- + /** Resolve the absolute target path without touching the filesystem. */ + locate(meta: SessionHeader): SessionLocation { + return { kind: 'jsonl', path: logPath(this.root, meta.cwd, meta.id) } + } + create(meta: SessionHeader): Promise { return this.coordinator.create(meta) } diff --git a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts index 6eed63a2f4..3b052cdfde 100644 --- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts +++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts @@ -2,7 +2,7 @@ import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' import { appendFile, mkdtemp, mkdir, rm, readFile, writeFile, readdir, stat } from 'node:fs/promises' import { tmpdir } from 'node:os' -import { join } from 'node:path' +import { isAbsolute, join, relative, resolve } from 'node:path' import SessionStore, { SessionId } from '@deepseek-ai/dsh-session' import type { Session, SessionEvent } from '@deepseek-ai/dsh-session' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' @@ -96,6 +96,19 @@ describe('SessionPersistenceJsonl: format helpers', () => { it('encodeSegment rejects an empty id', () => { expect(() => encodeSegment('')).toThrow(/empty/) }) + + it('resolves a relative custom root before locating a session', async () => { + const absoluteRoot = await freshRoot() + const ctx = new Context() + await ctx.plugin(SessionStore) + const fiber = await ctx.plugin(SessionPersistenceJsonl, { root: relative(process.cwd(), absoluteRoot) }) + const m = meta('relative-location', '/work') + expect(ctx.sessionPersistence.locate(m)).toEqual({ + kind: 'jsonl', + path: logPath(resolve(absoluteRoot), '/work', m.id), + }) + await fiber.dispose() + }) }) describe('SessionPersistenceJsonl: durability and crash semantics', () => { @@ -110,8 +123,13 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { it('lazy materialization: create() writes no file until the first append', async () => { const m = meta('lazy', '/work') + const location = ctx.sessionPersistence.locate(m) + expect(location).toEqual({ kind: 'jsonl', path: logPath(root, '/work', m.id) }) + expect(isAbsolute(location!.path)).toBe(true) + await ctx.sessionPersistence.create(m) - // nothing on disk yet + // locate() is a pure target-path calculation: neither it nor create() + // materializes a file before the first append. const dir = sessionDir(root, '/work') await expect(stat(logPath(root, '/work', m.id))).rejects.toThrow() expect((await ctx.sessionPersistence.list()).map(h => h.id)).not.toContain(m.id) @@ -123,6 +141,26 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { void dir }) + it('keeps the same location on resume and gives a fork its own location', async () => { + const parent = meta('location-parent', '/work') + const parentLocation = ctx.sessionPersistence.locate(parent) + await ctx.sessionPersistence.create(parent) + await ctx.sessionPersistence.append(parent.id, oneTurnLog()) + + const loaded = await ctx.sessionPersistence.load(parent.id) + expect(ctx.sessionPersistence.locate(loaded.meta)).toEqual(parentLocation) + + const child = { + ...loaded.meta, + id: SessionId('location-child'), + parentSession: parent.id, + seedLength: loaded.events.length, + } + const childLocation = ctx.sessionPersistence.locate(child) + expect(childLocation?.path).not.toBe(parentLocation?.path) + expect(childLocation).toEqual({ kind: 'jsonl', path: logPath(root, '/work', child.id) }) + }) + it('round-trip is byte-identical (incl. assistant/chunk verbatim)', async () => { const m = meta('chunks') const log: SessionEvent[] = [ diff --git a/packages/session-persistence/session-persistence-sqlite/README.md b/packages/session-persistence/session-persistence-sqlite/README.md index c14d3a70ea..4ac84c9173 100644 --- a/packages/session-persistence/session-persistence-sqlite/README.md +++ b/packages/session-persistence/session-persistence-sqlite/README.md @@ -2,6 +2,8 @@ A SQLite durable session-persistence backend — a second `SessionPersistence` implementation ([session persistence](../../../docs/rfc/implemented/architecture/2026-06-14-session-persistence.md)), built to validate that the abstract seam and the shared `runPersistenceContract` suite are genuinely backend-agnostic. It satisfies the SAME contract as `dsh-session-persistence-jsonl` (append-only, contiguous-seq, lazy materialization, interrupted-turn close on load), expressed over `node:sqlite` rows instead of file bytes. +`locate(meta)` returns `undefined`: all sessions share one database, so there is no honest independent per-session transcript path. + > **TODO:** this backend talks to `node:sqlite` directly. If a cordis database service (`cordis/db` / a `@cordisjs` SQL driver plugin) is adopted, route through that instead of holding a raw `DatabaseSync` here — the contract surface (`SessionPersistence`) would not change, only the storage driver. ## Storage model diff --git a/packages/session-persistence/session-persistence-sqlite/src/index.ts b/packages/session-persistence/session-persistence-sqlite/src/index.ts index 30387b4837..29b8042cd3 100644 --- a/packages/session-persistence/session-persistence-sqlite/src/index.ts +++ b/packages/session-persistence/session-persistence-sqlite/src/index.ts @@ -11,8 +11,9 @@ * Like the JSONL backend it supplies ONLY the storage primitives (the * {@link PersistenceBackend} hooks below — INSERT/DELETE/SELECT inside * transactions); all the write-path orchestration lives in the backend-agnostic - * {@link PersistenceCoordinator} this class composes. The four public - * {@link SessionPersistence} methods delegate to the coordinator. + * {@link PersistenceCoordinator} this class composes. The four stateful public + * {@link SessionPersistence} methods delegate to the coordinator; the pure + * locator remains backend-owned. * * @module @deepseek-ai/dsh-session-persistence-sqlite */ @@ -24,7 +25,7 @@ import { mkdir } from 'node:fs/promises' import { dirname, resolve } from 'node:path' import { SessionPersistence, PersistenceCoordinator, - type PersistenceBackend, type StoredPrefix, + type PersistenceBackend, type SessionLocation, type StoredPrefix, } from '@deepseek-ai/dsh-session-persistence' import type { Session, SessionEvent, SurfaceEventType, SessionId, SessionHeader } from '@deepseek-ai/dsh-session' import { @@ -109,6 +110,11 @@ export class SessionPersistenceSqlite extends SessionPersistence implements Pers // --- SessionPersistence service surface (delegated to the coordinator) --- + /** SQLite has one database, not an independent local artifact per session. */ + locate(_meta: SessionHeader): SessionLocation | undefined { + return undefined + } + create(meta: SessionHeader): Promise { return this.coordinator.create(meta) } diff --git a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts index a6eda72685..e055ea436e 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -144,6 +144,12 @@ describe('scanRows', () => { }) describe('SessionPersistenceSqlite: durability and crash semantics', () => { + it('has no independent per-session log location', async () => { + const { ctx, dispose } = await backend() + expect(ctx.sessionPersistence.locate(meta('sqlite-location'))).toBeUndefined() + await dispose() + }) + it('an interrupted turn (rows after the last turn/end) is PRESERVED and closed during load', async () => { const path = await freshDbPath() const m = meta('crash') diff --git a/packages/session-persistence/session-persistence/README.md b/packages/session-persistence/session-persistence/README.md index 8bd3fed568..ca86ee0e71 100644 --- a/packages/session-persistence/session-persistence/README.md +++ b/packages/session-persistence/session-persistence/README.md @@ -8,6 +8,7 @@ The persisted unit IS the existing `SessionEvent` (event-sourced model — the l | Method | Contract | |---|---| +| `locate(meta): SessionLocation \| undefined` | Resolve an absolute per-session artifact target without I/O or materialization. Backends without an independent local artifact return `undefined`. | | `create(meta): Promise` | Register a new session's metadata. MAY defer the physical write until the first `append` (lazy materialization). | | `append(id, events): Promise` | Durably persist a batch (from the `session/flush` drain). Append-only; first event `seq` == stored next-seq after any repair; rejects non-JSON-serializable data naming the offending type. | | `load(id): Promise<{ meta; events }>` | Reload meta + log. Preserves an interrupted (unclosed) final turn and closes it with synthetic closers — an error `tool/result` per unanswered `tool-call`, then `step/end?`+`turn/end {interrupted}` (a turn can be huge — never truncated); only a torn tail fragment is dropped. Events contiguous (`events[i].seq === i`); rejects a committed-region gap/parse error or unknown `version`. | @@ -24,7 +25,7 @@ The persisted unit IS the existing `SessionEvent` (event-sourced model — the l The two first-party backends were byte-identical (or same-algorithm) for ALL of their write-path orchestration — the in-memory bookkeeping (per-id state, write-behind buffers, per-id serialization chains, per-session init promises), the `session/event` → buffer → `session/flush` drain, lazy materialization, crash-tail repair on load, the four `session/created` adoption cases (new / HMR-adopt / collision / ownerless-claim), and dispose-time quiescence. Only the STORAGE primitives differed (write bytes vs. INSERT rows). -`PersistenceCoordinator` owns that orchestration once. A first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements the small `PersistenceBackend` hook interface, and delegates its four public service methods to the coordinator. This keeps the duplicated, correctness-heavy orchestration in a single place (it used to receive the same fixes twice). +`PersistenceCoordinator` owns that orchestration once. A first-party backend composes one (`new PersistenceCoordinator(ctx, this)`), implements the small `PersistenceBackend` hook interface, and delegates its four stateful service methods to the coordinator; the pure `locate` query stays backend-owned. This keeps the duplicated, correctness-heavy orchestration in a single place (it used to receive the same fixes twice). The `PersistenceBackend` hooks (the only seam between the coordinator and storage): @@ -46,6 +47,6 @@ Import `runPersistenceContract` from `tests/contract.ts` (the public-API contrac Three backends run these suites: an in-memory reference (in `tests/`), `dsh-session-persistence-jsonl` (append-only file log) and `dsh-session-persistence-sqlite` (`node:sqlite`, each `SessionEvent` one row `(session_id, seq, type, time, data, source_event_seqs, surface_op)`). All passing the same contract + coordinator suite is the proof that the seam is genuinely backend-agnostic — lazy materialization, crash-tail-on-load, and contiguous-seq hold identically over file bytes and over a transactional store. -## Metadata types +## Metadata and location types -Re-exported from `dsh-session`: `SessionHeader` (immutable session metadata: `version`, `id`, `createdAt`, `cwd?`, `parentSession?`, `seedLength?`). +Re-exported from `dsh-session`: `SessionHeader` (immutable session metadata: `version`, `id`, `createdAt`, `cwd?`, `parentSession?`, `seedLength?`). `SessionLocation` is `{ readonly kind: string; readonly path: string }`; its path is an absolute backend target, not proof that the artifact exists or contains an unflushed turn. diff --git a/packages/session-persistence/session-persistence/src/index.ts b/packages/session-persistence/session-persistence/src/index.ts index 1588ed2526..7e3a532f65 100644 --- a/packages/session-persistence/session-persistence/src/index.ts +++ b/packages/session-persistence/session-persistence/src/index.ts @@ -38,6 +38,18 @@ declare module 'cordis' { } } +/** + * A backend-resolved, per-session local artifact location. The path is an + * absolute target path and can name an artifact that has not materialized yet. + * Consumers must treat it as a location hint, never as an authorization token. + */ +export interface SessionLocation { + /** Backend-specific artifact kind, for example `jsonl`. */ + readonly kind: string + /** Absolute path to this session's backend-owned artifact. */ + readonly path: string +} + /** * Whether a live session's seed reproduces a persisted prefix exactly. Backends * use this collision check to distinguish a legitimate resume/HMR rebind from a @@ -104,6 +116,15 @@ export abstract class SessionPersistence extends Service { super(ctx, 'sessionPersistence') } + /** + * Resolve this backend's independent local artifact for a session without + * reading, creating, flushing, or otherwise materializing it. Backends such + * as SQLite that do not own one artifact per session return `undefined`. + * @param meta - the immutable session header whose artifact is requested. + * @returns the backend-specific absolute location, when one exists. + */ + abstract locate(meta: SessionHeader): SessionLocation | undefined + /** * Register a new session's metadata. A backend MAY defer the physical write * until the first {@link append} (lazy materialization), in which case a diff --git a/packages/session-persistence/session-persistence/tests/persistence.spec.ts b/packages/session-persistence/session-persistence/tests/persistence.spec.ts index 4e4cf67822..2e28931a98 100644 --- a/packages/session-persistence/session-persistence/tests/persistence.spec.ts +++ b/packages/session-persistence/session-persistence/tests/persistence.spec.ts @@ -49,6 +49,10 @@ class MemoryPersistence extends SessionPersistence implements PersistenceBackend // --- service surface (delegated to the coordinator) --- + locate(_meta: SessionHeader): undefined { + return undefined + } + create(m: SessionHeader): Promise { return this.coordinator.create(m) } diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 4425c6bd41..b42cd5dae0 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -120,6 +120,12 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session + '@deepseek-ai/dsh-session-persistence': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence + '@deepseek-ai/dsh-session-persistence-jsonl': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence-jsonl '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../../core/system-prompt @@ -514,6 +520,12 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session + '@deepseek-ai/dsh-session-persistence': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence + '@deepseek-ai/dsh-session-persistence-jsonl': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence-jsonl '@deepseek-ai/dsh-subagent': specifier: workspace:^ version: link:../../subagent/subagent @@ -554,6 +566,12 @@ importers: '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session + '@deepseek-ai/dsh-session-persistence': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence + '@deepseek-ai/dsh-session-persistence-jsonl': + specifier: workspace:^ + version: link:../../session-persistence/session-persistence-jsonl '@deepseek-ai/dsh-system-prompt': specifier: workspace:^ version: link:../../core/system-prompt diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index 881ce06578..937ca72a0d 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -34,6 +34,7 @@ { "doc": "docs/core-data-structures/persistence.md", "symbol": "SessionHeader", "source": "packages/core/session/src/types.ts" }, { "doc": "docs/core-data-structures/persistence.md", "symbol": "CreateSessionOptions", "source": "packages/core/session/src/types.ts" }, + { "doc": "docs/core-data-structures/persistence.md", "symbol": "SessionLocation", "source": "packages/session-persistence/session-persistence/src/index.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "ToolDefinition", "source": "packages/core/tools/src/index.ts" }, { "doc": "docs/core-data-structures/tools.md", "symbol": "SchemaProp", "source": "packages/core/tools/src/schema.ts" },