From e547980d77368fe83f6e4ad20956dc64f2d4e20d Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Tue, 14 Jul 2026 21:57:52 +0800 Subject: [PATCH 1/9] feat(llm): route adapters by provider --- docs/architecture.md | 2 +- docs/config-catalog.md | 71 ++- docs/cookbook/adding-an-llm-adapter.md | 7 +- docs/cordis-catalog/events.md | 28 +- docs/cordis-catalog/services.md | 8 +- docs/core-data-structures/compaction.md | 2 +- docs/core-data-structures/core.md | 26 +- docs/core-data-structures/llm-streaming.md | 14 +- docs/core-data-structures/session.md | 8 +- docs/event-producer-consumer.md | 28 +- docs/persistence-catalog.md | 8 +- docs/rfc/INDEX.md | 1 + ...2026-07-14-provider-routed-llm-adapters.md | 89 ++++ docs/tool-catalog.md | 8 +- .../acp-agent/advanced.cordis.snapshot.yml | 1 + examples/acp-agent/advanced.cordis.yml | 1 + .../acp-agent/both-mode.cordis.snapshot.yml | 1 + examples/acp-agent/both-mode.cordis.yml | 1 + .../acp-agent/code-mode.cordis.snapshot.yml | 1 + examples/acp-agent/code-mode.cordis.yml | 1 + examples/acp-agent/cordis.yml | 4 +- .../advanced-toolchain/session.1.jsonl | 4 +- .../advanced-toolchain/session.2.jsonl | 4 +- .../advanced-toolchain/session.jsonl | 14 +- .../system-prompt.golden.md | 4 +- .../snapshots/both-mode-turn/session.jsonl | 6 +- .../both-mode-turn/system-prompt.golden.md | 4 +- .../tests/snapshots/cancel/session.jsonl | 2 +- .../snapshots/code-mode-turn/session.jsonl | 6 +- .../code-mode-turn/system-prompt.golden.md | 4 +- .../snapshots/error-finish/session.jsonl | 2 +- .../tests/snapshots/fs-edit/session.jsonl | 8 +- .../snapshots/fs-policy-reject/session.jsonl | 10 +- .../snapshots/fs-read-window/session.jsonl | 6 +- .../tests/snapshots/fs-read/session.jsonl | 6 +- .../snapshots/fs-terminal-card/session.jsonl | 6 +- .../fs-write-overwrite/session.jsonl | 8 +- .../tests/snapshots/fs-write/session.jsonl | 6 +- .../hook-cc-posttool-block/session.jsonl | 20 +- .../hook-cc-posttool-context/session.jsonl | 6 +- .../hook-cc-pretool-ask/session.jsonl | 6 +- .../hook-cc-pretool-deny/session.jsonl | 6 +- .../session.jsonl | 4 +- .../hook-cc-stop-continue/session.jsonl | 6 +- .../hook-codex-posttool-block/session.jsonl | 6 +- .../hook-codex-posttool-context/session.jsonl | 6 +- .../hook-codex-pretool-block/session.jsonl | 6 +- .../session.jsonl | 4 +- .../hook-codex-stop-continue/session.jsonl | 6 +- .../tests/snapshots/multi-turn/session.jsonl | 6 +- .../snapshots/repeat-tool-guard/session.jsonl | 14 +- .../tests/snapshots/skill-load/session.jsonl | 6 +- .../snapshots/subagent-fork/session.1.jsonl | 8 +- .../snapshots/subagent-fork/session.jsonl | 8 +- .../snapshots/subagent-mixed/session.1.jsonl | 4 +- .../snapshots/subagent-mixed/session.2.jsonl | 8 +- .../snapshots/subagent-mixed/session.jsonl | 10 +- .../snapshots/subagent-multi/session.1.jsonl | 4 +- .../snapshots/subagent-multi/session.2.jsonl | 4 +- .../snapshots/subagent-multi/session.jsonl | 8 +- .../snapshots/subagent-spawn/session.1.jsonl | 4 +- .../snapshots/subagent-spawn/session.jsonl | 6 +- .../tests/snapshots/text-turn/session.jsonl | 4 +- .../tests/snapshots/todo-plan/session.jsonl | 6 +- .../snapshots/tool-call-turn/session.jsonl | 6 +- .../snapshots/workflow-run/session.1.jsonl | 4 +- .../snapshots/workflow-run/session.jsonl | 6 +- .../snapshots/workspace-edit/session.jsonl | 10 +- examples/coding-agent/code-mode.cordis.yml | 1 + examples/coding-agent/cordis.yml | 8 +- examples/coding-agent/tests/code-mode.e2e.ts | 4 +- .../coding-agent/tests/coding-task.e2e.ts | 2 +- examples/coding-agent/tests/compaction.e2e.ts | 3 +- examples/coding-agent/tests/full-loop.e2e.ts | 2 +- examples/coding-agent/tests/harness.ts | 2 +- examples/coding-agent/tests/resume.e2e.ts | 4 +- examples/coding-agent/tests/todo-write.e2e.ts | 2 +- examples/cordis-agent/cordis.yml | 4 +- .../cordis-agent/tests/cordis-tools.e2e.ts | 6 +- examples/cordis-agent/tests/harness.ts | 2 +- examples/echo-agent/cordis.yml | 1 + examples/echo-agent/src/mock-llm.ts | 2 +- examples/sandbox-acp-agent/cordis.yml | 3 +- .../escalation-approved/session.jsonl | 6 +- .../escalation-rejected/session.jsonl | 6 +- .../snapshots/mode-switching/session.jsonl | 12 +- .../bash/tool-bash/tests/integration.spec.ts | 6 +- packages/compact/compact-basic/README.md | 8 +- packages/compact/compact-basic/src/index.ts | 29 +- packages/compact/compact-basic/src/types.ts | 10 +- .../compact-basic/tests/compact-basic.spec.ts | 56 ++- .../tests/compact-loop-repro.spec.ts | 7 +- packages/compact/compact/README.md | 2 +- packages/compact/compact/src/types.ts | 2 + .../compact/compact/tests/compact.spec.ts | 1 + packages/compact/compact/tests/render.spec.ts | 4 +- .../cordis/tool-cordis/src/api-catalog.ts | 20 +- .../tool-cordis/tests/integration.spec.ts | 2 +- .../core/agent-core/tests/agent-core.spec.ts | 2 +- packages/core/agent-loop/README.md | 3 +- packages/core/agent-loop/src/index.ts | 2 + packages/core/agent-loop/src/loop.ts | 70 ++- packages/core/agent-loop/tests/agent.spec.ts | 50 +- packages/core/agent-loop/tests/cancel.spec.ts | 34 +- .../tests/config-session-id.spec.ts | 10 +- .../agent-loop/tests/coverage-edges.spec.ts | 16 +- .../agent-loop/tests/interception.spec.ts | 50 +- packages/core/agent-loop/tests/loop.spec.ts | 80 +-- .../core/agent-loop/tests/properties.spec.ts | 6 +- .../agent-loop/tests/request-cache.e2e.ts | 4 +- .../core/agent-loop/tests/request-log.spec.ts | 12 +- .../tests/request-reconstruction.spec.ts | 20 +- packages/core/agent-loop/tests/resume.spec.ts | 16 +- .../agent-loop/tests/review-fixes.spec.ts | 105 ++-- .../agent-loop/tests/scope-lifecycle.spec.ts | 86 ++-- .../core/agent-loop/tests/tool-order.spec.ts | 4 +- .../core/agent-loop/tests/turn-stop.spec.ts | 14 +- packages/core/agent/src/types.ts | 4 +- packages/core/session/README.md | 6 +- packages/core/session/src/index.ts | 29 +- packages/core/session/src/types.ts | 8 +- .../core/session/tests/derived-cache.spec.ts | 6 +- packages/core/session/tests/fork.spec.ts | 4 +- .../core/session/tests/properties.spec.ts | 4 +- packages/core/session/tests/repair.spec.ts | 14 +- .../core/session/tests/request-header.spec.ts | 16 +- packages/core/session/tests/session.spec.ts | 41 +- packages/core/session/tests/surface.spec.ts | 30 +- .../core/session/tests/tool-pairing.spec.ts | 14 +- packages/fs/tool-fs/tests/fs-tools.e2e.ts | 4 +- packages/fs/tool-fs/tests/harness.ts | 2 +- .../tests/repeat-tool-guard.spec.ts | 34 +- .../hooks/hooks-claude/tests/bridge.spec.ts | 20 +- .../hooks/hooks-claude/tests/coverage.spec.ts | 58 +-- .../hooks/hooks-codex/tests/bridge.spec.ts | 12 +- .../hooks/hooks-codex/tests/coverage.spec.ts | 68 +-- packages/llm/README.md | 4 +- packages/llm/llm-deepseek/README.md | 5 +- packages/llm/llm-deepseek/src/index.ts | 11 +- .../llm/llm-deepseek/tests/adapter.e2e.ts | 5 +- .../llm/llm-deepseek/tests/adapter.spec.ts | 25 +- packages/llm/llm-deepseek/tests/assemble.ts | 14 +- .../llm/llm-deepseek/tests/serialize.spec.ts | 2 +- packages/llm/llm-pi-ai/README.md | 58 ++- packages/llm/llm-pi-ai/src/adapter.ts | 209 +++----- packages/llm/llm-pi-ai/src/config.ts | 99 ++++ packages/llm/llm-pi-ai/src/context.ts | 85 ++++ packages/llm/llm-pi-ai/src/convert.ts | 289 ----------- packages/llm/llm-pi-ai/src/index.ts | 79 +-- packages/llm/llm-pi-ai/src/replay.ts | 208 ++++++++ packages/llm/llm-pi-ai/src/stream.ts | 141 ++++++ packages/llm/llm-pi-ai/tests/adapter.e2e.ts | 32 +- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 462 ++++++------------ packages/llm/llm-pi-ai/tests/assemble.ts | 14 +- packages/llm/llm-pi-ai/tests/convert.spec.ts | 215 +++++++- packages/llm/llm/README.md | 12 +- packages/llm/llm/src/assembler.ts | 7 + packages/llm/llm/src/call-config.ts | 11 +- packages/llm/llm/src/index.ts | 66 ++- packages/llm/llm/src/types.ts | 30 +- packages/llm/llm/tests/call-config.spec.ts | 18 +- packages/llm/llm/tests/service.spec.ts | 125 ++++- .../tests/jsonl.spec.ts | 2 +- .../tests/sqlite.spec.ts | 2 +- .../session-persistence/tests/contract.ts | 4 +- .../tests/multi-subagent.spec.ts | 2 +- .../subagent-fork/tests/subagent-fork.spec.ts | 2 +- .../subagent/subagent-inprocess/src/index.ts | 2 + .../tests/structured.spec.ts | 2 +- .../tests/subagent-inprocess.spec.ts | 2 +- .../subagent/subagent-spawn/tests/harness.ts | 2 +- .../subagent-spawn/tests/spawn.e2e.ts | 2 +- .../tests/subagent-spawn.spec.ts | 14 +- packages/subagent/tool-subagent/src/index.ts | 3 +- .../invariants/tests/invariants.spec.ts | 52 +- .../llm-replay/tests/llm-replay.spec.ts | 44 +- .../todo/tool-todo/tests/integration.spec.ts | 4 +- packages/ui/acp-agent/README.md | 3 +- packages/ui/acp-agent/src/index.ts | 13 +- packages/ui/acp-agent/tests/acp-agent.spec.ts | 9 +- packages/ui/acp-agent/tests/built-bin.e2e.ts | 2 +- packages/ui/acp-agent/tests/load-path.e2e.ts | 2 +- packages/ui/acp/README.md | 1 + packages/ui/acp/src/index.ts | 10 +- packages/ui/acp/tests/dispose.spec.ts | 8 +- packages/ui/acp/tests/edges.spec.ts | 2 +- packages/ui/acp/tests/harness.ts | 9 +- packages/ui/acp/tests/stream-update.spec.ts | 1 + packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 23 +- .../ui/jsonrpc/tests/plugin-apply.spec.ts | 10 +- packages/ui/jsonrpc/tests/server.spec.ts | 44 +- packages/ui/stdio-agent/README.md | 7 +- packages/ui/stdio-agent/src/index.ts | 8 +- .../ui/stdio-agent/tests/built-bin.e2e.ts | 1 + .../ui/stdio-agent/tests/stdio-agent.spec.ts | 10 +- .../ui/user-approval/tests/approval.spec.ts | 2 +- packages/workflow/tool-workflow/src/index.ts | 12 +- .../workflow-workerthread/src/host.ts | 9 +- .../workflow-workerthread/src/meta.ts | 4 +- .../workflow-workerthread/src/runtime.ts | 16 +- .../workflow-workerthread/src/types.ts | 2 + .../tests/integration.spec.ts | 2 +- .../workflow-workerthread/tests/meta.spec.ts | 5 +- .../tests/session.spec.ts | 13 +- .../tests/workflow-workerthread.e2e.ts | 4 +- .../tests/workflow-workerthread.spec.ts | 8 + packages/workflow/workflow/src/types.ts | 2 + .../runtime/cordis.yml | 3 - python/sdk/README.i18n.yaml | 4 +- python/sdk/README.md | 3 + python/sdk/README.zh.md | 3 + python/sdk/src/deepseek_harness/api.py | 2 + python/sdk/src/deepseek_harness/client.py | 2 + python/sdk/tests/test_bundled_runtime.py | 4 +- python/sdk/tests/test_client.py | 26 +- scripts/smoke-python-runtime.py | 5 +- scripts/type-equiv.manifest.json | 1 + 218 files changed, 2605 insertions(+), 1844 deletions(-) create mode 100644 docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md create mode 100644 packages/llm/llm-pi-ai/src/config.ts create mode 100644 packages/llm/llm-pi-ai/src/context.ts delete mode 100644 packages/llm/llm-pi-ai/src/convert.ts create mode 100644 packages/llm/llm-pi-ai/src/replay.ts create mode 100644 packages/llm/llm-pi-ai/src/stream.ts diff --git a/docs/architecture.md b/docs/architecture.md index a1f0cae9a8..23f2268ff7 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -125,7 +125,7 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, compaction pricing, and persistence, so block types remain a repo-wide contract. -Streaming is a raw chunk protocol (`block-start` through `finish`) with `BlockAssembler` as the shared chunk-to-block assembler. The loop logs raw chunks while assembling them for dispatch. `LlmAdapter` is the provider seam: subclass, implement `stream()`, and register with `ctx.llm.registerAdapter(models, adapter)`. StreamChunk conventions live in [llm-streaming.md](core-data-structures/llm-streaming.md). +Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing assistant provider/model provenance plus replay state. An `LlmAdapter` implements `stream()` and registers routes with `ctx.llm.registerAdapter(providers, adapter)`; requests route by `provider`, while the adapter resolves `model`. Replay state reaches a target only when both routes map to the same adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). ## Extension And Composition diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 9d4b8038b5..7d346f076f 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -16,6 +16,8 @@ Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInte ```ts config-catalog /** Plugin config: the agent template ACP sessions are created from. */ export interface AcpConfig { + /** Provider route for created agents. */ + provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string /** @@ -37,7 +39,7 @@ Source: [`packages/ui/acp/src/index.ts:250`](../packages/ui/acp/src/index.ts) ```ts config-catalog /** - * App config: the swappable per-deployment values. `model` configures the + * App config: the swappable per-deployment values. `provider` and `model` configure the * agent template the ACP bridge creates each session's agent from (NOT a * pre-created agent — ACP creates agents at `session/new`); `persona` is the * deployment persona (forwarded to the system-prompt plugin); `toolOrder` is @@ -46,6 +48,8 @@ Source: [`packages/ui/acp/src/index.ts:250`](../packages/ui/acp/src/index.ts) * through agent-core); `persistenceRoot` is the JSONL backend's directory. */ export interface Config { + /** Provider route for ACP-created agents. */ + provider: string /** Model name for ACP-created agents (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ @@ -234,7 +238,9 @@ export interface BasicCompactConfig { thresholdRatio: number /** Number of tokens of recent context to retain during compaction. */ retainTokens: number - /** Model to use for summarization (`''` — uses the agent's model). */ + /** Provider to use for summarization (`''` with an empty model inherits the conversation target). */ + summarizationProvider: string + /** Model to use for summarization (`''` with an empty provider inherits the conversation target). */ summarizationModel: string /** Provider generation cap for the summarization call. */ maxTokens: number @@ -380,8 +386,6 @@ export interface Config { apiKey?: string /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */ baseURL?: string - /** Model names to register (sent verbatim on the wire). */ - models?: string[] /** Thinking-mode default for every request (provider default: enabled). */ thinking?: 'enabled' | 'disabled' /** Thinking effort (only meaningful with thinking enabled). */ @@ -389,38 +393,51 @@ export interface Config { } ``` -Source: [`packages/llm/llm-deepseek/src/index.ts:43`](../packages/llm/llm-deepseek/src/index.ts) +Source: [`packages/llm/llm-deepseek/src/index.ts:42`](../packages/llm/llm-deepseek/src/index.ts) ## `@deepseek-ai/dsh-llm-pi-ai` Requires: `llm` ```ts config-catalog -/** - * Plugin config, validated by the same-named schemastery schema. Every field - * is optional in yml: credentials/endpoint fall back to the environment (a - * missing API key fails plugin load, not the first call). - */ +/** Plugin configuration: the non-empty provider profiles this instance owns. */ export interface Config { - /** API key; falls back to $DEEPSEEK_API_KEY. Required one way or the other. */ - apiKey?: string - /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */ - baseURL?: string - /** Model names to register (sent verbatim on the wire). */ - models?: string[] - /** - * Thinking level for every request: 'off' disables thinking mode; 'high' - * and 'xhigh' (wire 'max') set the effort. Omitted = provider default - * (thinking enabled), matching llm-deepseek's omission semantics. - */ - reasoning?: PiAiReasoning + /** Non-empty set of pi-ai provider routes this adapter instance owns. */ + providers: PiAiProviderProfile[] } -/** Reasoning levels surfaced by this adapter (DeepSeek wire: high|max). */ -export type PiAiReasoning = 'off' | 'high' | 'xhigh' +/** Configuration for one pi-ai provider route. */ +export interface PiAiProviderProfile { + /** pi-ai provider catalog name and Harness route key. */ + provider: string + /** Provider credential; when absent pi-ai uses its provider-native ambient discovery. */ + apiKey?: string + /** Override the selected catalog model's endpoint without changing its protocol metadata. */ + baseURL?: string + /** Provider request headers; Harness attribution wins reserved names. */ + headers?: Record + /** Provider-neutral pi-ai reasoning level. */ + reasoning?: ThinkingLevel + /** Token budgets used by reasoning providers that support them. */ + thinkingBudgets?: ThinkingBudgets + /** Prompt-cache retention preference. */ + cacheRetention?: CacheRetention + /** Streaming transport preference. */ + transport?: Transport + /** HTTP/provider SDK timeout in milliseconds. */ + timeoutMs?: number + /** WebSocket connection timeout in milliseconds. */ + websocketConnectTimeoutMs?: number + /** Provider SDK retry count. */ + maxRetries?: number + /** Maximum provider-requested retry delay in milliseconds. */ + maxRetryDelayMs?: number +} ``` -Source: [`packages/llm/llm-pi-ai/src/index.ts:37`](../packages/llm/llm-pi-ai/src/index.ts) +Depends on: `CacheRetention` (`@earendil-works/pi-ai`) · `ThinkingBudgets` (`@earendil-works/pi-ai`) · `ThinkingLevel` (`@earendil-works/pi-ai`) · `Transport` (`@earendil-works/pi-ai`) + +Source: [`packages/llm/llm-pi-ai/src/config.ts:40`](../packages/llm/llm-pi-ai/src/config.ts) ## `@deepseek-ai/dsh-llm-replay` @@ -611,7 +628,7 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l ```ts config-catalog /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `provider`/`model`/`resumeSessionId` configure the pre-created `main` agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -620,6 +637,8 @@ Source: [`packages/skill/skill-local/src/index.ts:39`](../packages/skill/skill-l * `welcome` is the UI banner. */ export interface Config { + /** Provider route for the `main` agent. */ + provider: string /** Model name for the `main` agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ diff --git a/docs/cookbook/adding-an-llm-adapter.md b/docs/cookbook/adding-an-llm-adapter.md index fb59969e52..866f401d42 100644 --- a/docs/cookbook/adding-an-llm-adapter.md +++ b/docs/cookbook/adding-an-llm-adapter.md @@ -14,11 +14,11 @@ export const inject = ['llm'] export const Config: z = z.object({ apiKey: z.string(), … }) export function apply(ctx: Context, config: Config) { - ctx.llm.registerAdapter(['model-a', 'model-b'], new MyAdapter(…)) + ctx.llm.registerAdapter(['my-provider'], new MyAdapter(…)) } ``` -Registration is effect-based (HMR-safe); one adapter per model name — duplicates throw. Secrets are cordis-native: schemastery Config with env fallbacks, fed from cordis.yml via `!!js process.env.MY_KEY`. Never read ad-hoc key files in code. +Registration is effect-based (HMR-safe); one adapter per provider route — duplicates throw, and multi-route registration is all-or-nothing. `options.provider` selects the adapter and `options.model` is the provider model id, so a dynamic catalog adapter can serve new models without lifecycle reconfiguration. Secrets are cordis-native: schemastery Config with env fallbacks, fed from cordis.yml via `!!js process.env.MY_KEY`. Never read ad-hoc key files in code. ## Protocol obligations (the contract two implementations verified) @@ -28,6 +28,7 @@ Registration is effect-based (HMR-safe); one adapter per model name — duplicat - Errors have exactly two sanctioned paths: THROW from `stream()` (transport and protocol failures — use `LlmError` with a stable code), or end the stream with `finish {kind: 'error' | 'aborted'}` (provider in-band failures). Consumers handle both; pick per failure class and document it. - Honor `options.signal` (pass it to fetch / your SDK). - A `GenerateOptions` field your provider cannot honor (e.g. a `stop` list on a provider without stop sequences): throw `LlmError(..., 'UNSUPPORTED')` rather than silently dropping it. +- If the provider requires response ids, signatures, or other native metadata on follow-up calls, emit the minimal lossless-JSON projection as `finish.replayState`. Validate it when rebuilding history. `LlmService` passes it only when the historical provider route and target provider route are currently owned by the exact same adapter instance; your adapter decides whether same-model, cross-model, or cross-provider restoration is legal. Never infer native replay from provider/model names alone when state is absent. Provider-specific request knobs (thinking modes, effort levels) belong in the ADAPTER's Config, not in `GenerateOptions` — the core vocabulary stays provider-neutral. @@ -39,5 +40,5 @@ Split the adapter into testable stages (llm-deepseek's layout): wire types (`typ - **Unit: mock the provider, not the harness.** A scripted `node:http` server speaking the provider's wire format covers happy paths, every error status, malformed payloads, premature closes, and aborts — no network, and it drives the 100% per-file coverage gate. Works for SDK-backed adapters too (point the SDK's baseURL at the mock). - **Hostile framing tests.** Split stream payloads at arbitrary byte positions (including mid-UTF-8) — real networks do. -- **E2E: `tests/*.e2e.ts`** under `pnpm run test:e2e`, gated with `describe.skipIf(!process.env.MY_KEY)` so CI (no secrets) stays green. Cover each model × each provider mode you map (thinking on/off, effort levels), a tool-call round trip INCLUDING the follow-up turn with results in history, and loose assertions only (substring/structure, bounded maxTokens — real models are nondeterministic). +- **E2E: `tests/*.e2e.ts`** under `pnpm run test:e2e`, gated with `describe.skipIf(!process.env.MY_KEY)` so CI (no secrets) stays green. Cover representative model/provider/API families and every provider mode you map, a tool-call round trip INCLUDING the follow-up turn with results in history, and loose assertions only (substring/structure, bounded maxTokens — real models are nondeterministic). - Register the e2e file pattern in `knip.json` (per-workspace `entry` override) or knip flags it unused. diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index acbd39b8fa..9e005006bd 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -23,7 +23,7 @@ An agent's fully composed scoped world was published in the AgentRegistry. Its s Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:316`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:318`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -35,7 +35,7 @@ An agent was removed from the registry. The concrete AgentLoop lifecycle emits t Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:331`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:333`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -47,7 +47,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:605`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:607`](../../packages/core/agent/src/types.ts) ### `agent/pre-step` — serial @@ -61,7 +61,7 @@ Serial (awaited in registration order), not a waterfall: a listener mutates the Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:438`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:440`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -73,7 +73,7 @@ Waterfall: decide what happens to ONE drained queued message before it becomes a Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:456`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:458`](../../packages/core/agent/src/types.ts) ### `agent/queued` — emit @@ -85,7 +85,7 @@ A message entered the agent's inbox (queued or steering). Content and the resolv Types: [Agent](../core-data-structures/core.md) · [ContentBlock](../core-data-structures/core.md) · [MessageSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:360`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:362`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -97,7 +97,7 @@ Waterfall: shape the step's call configuration — model switching, sampling ove Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:485`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:487`](../../packages/core/agent/src/types.ts) ### `agent/session-prefix` — waterfall @@ -113,7 +113,7 @@ The seed is a frozen empty list; a contributing listener returns a NEW array — Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:537`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:539`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -125,7 +125,7 @@ The agent's session lifecycle began, fired once before its first turn. `source` Types: [Agent](../core-data-structures/core.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:381`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:383`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -137,7 +137,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). Drive lifecycle Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:345`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:347`](../../packages/core/agent/src/types.ts) ### `agent/step-result` — waterfall @@ -149,7 +149,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va Types: [Agent](../core-data-structures/core.md) · [Message](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:552`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:554`](../../packages/core/agent/src/types.ts) ### `agent/turn-continuation` — waterfall @@ -161,7 +161,7 @@ Waterfall: override the turn-continuation decision via a typed ContinuationDecis Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:570`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:572`](../../packages/core/agent/src/types.ts) ### `agent/turn-stop` — serial @@ -173,7 +173,7 @@ Serial terminal-stop checkpoint after the ordinary `agent/turn-continuation` wat Types: [Agent](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:588`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:590`](../../packages/core/agent/src/types.ts) ## `approval/*` @@ -239,7 +239,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:39`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:40`](../../packages/llm/llm/src/index.ts) ## `session/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 0aea3f1589..5011f83066 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -152,14 +152,14 @@ Source: [`packages/fs/fs/src/index.ts:172`](../../packages/fs/fs/src/index.ts) The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall. ```ts cordis-catalog -registerAdapter(models: string[], adapter: LlmAdapter): () => void -models(): string[] +registerAdapter(providers: string[], adapter: LlmAdapter): () => void +providers(): string[] stream(options: GenerateOptions): AsyncIterable ``` Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:88`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:89`](../../packages/llm/llm/src/index.ts) ## `ctx.sandbox` — `SandboxProvider` (abstract seam) @@ -218,7 +218,7 @@ list(): Session[] fork(source: SessionForkSource, boundary?: number, childSessionId?: SessionId): Session ``` -Source: [`packages/core/session/src/index.ts:590`](../../packages/core/session/src/index.ts) +Source: [`packages/core/session/src/index.ts:617`](../../packages/core/session/src/index.ts) ## `ctx.skills` — `SkillService` diff --git a/docs/core-data-structures/compaction.md b/docs/core-data-structures/compaction.md index 2f402be57d..32d1ac3715 100644 --- a/docs/core-data-structures/compaction.md +++ b/docs/core-data-structures/compaction.md @@ -11,7 +11,7 @@ Compaction extends [`SessionEventMap`](session.md) with three event types via de | Event | Payload | Role | |---|---|---| | `compact/start` | `{ turn }` | acquires the log-recorded lock | -| `compact/summary` | `{ summary, shadowedRange, shadowedSeqs, shadowedTokenCount, model, maxTokens? }` | provenance: the summary blocks, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability RFC) | +| `compact/summary` | `{ summary, shadowedRange, shadowedSeqs, shadowedTokenCount, provider, model, maxTokens? }` | provenance: the summary blocks, the shadowed surface-boundary pair (`start`/`end` seqs — a position span, not a numeric interval), the shadowed seqs in surface order, the estimated token count, and the summarize call's envelope (`provider`, `model`, plus its generation cap when one applied) — logged so the one-shot request is reconstructable from log + code (the reconstructability RFC) | | `compact/end` | `{ turn, error? }` | releases the lock (`error` set when summarization threw) | The lock brackets the **whole** operation: `compact/start` is appended first, then summarization, the `compact/summary` provenance record, and the `user/message` replacement all land, and only then `compact/end`. Releasing the lock last turns a crash mid-operation into a detectable orphaned lock (a `compact/start` with no matching `compact/end`) rather than a `compact/end` that falsely claims compaction finished. diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 757c74f399..5a3ea6680b 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -102,12 +102,29 @@ interface ContentBlockMap { The block interfaces (full fields in source): `TextBlock` (`text`), `ReasoningBlock` (thinking, distinct from visible text), `ToolCallBlock` (`id: CallId`, `name`, raw-JSON `arguments`), `ToolResultBlock` (`toolCallId`, nested `content: ContentBlock[]`, `isError?`). `ContentBlock = ContentBlockMap[ContentBlockType]`. The core set is limited to blocks every shipping path honors — multimodal content (images, audio, …) has no core block type; a feature that needs one adds it via the merge-extensible map together with the adapter/UI/compaction support that honors it. -A `Message` is a role plus blocks: +A `Message` is a role plus blocks. Loop-derived assistant messages carry their durable provider/model identity and optional adapter-private replay metadata: + +```ts type-equiv +interface AssistantProvenance { + /** Provider route that produced the message. */ + provider: string + /** Provider model id that produced the message. */ + model: string + /** + * Lossless-JSON adapter state needed to replay the provider response. + * `LlmService` exposes it to a target adapter only when that adapter instance + * currently owns both this historical provider and the target provider. + */ + replayState?: unknown +} +``` ```ts type-equiv interface Message { role: 'system' | 'user' | 'assistant' content: ContentBlock[] + /** Present only on assistant messages produced by a routed adapter. */ + provenance?: AssistantProvenance } ``` @@ -134,6 +151,8 @@ Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) ```ts type-equiv interface GenerateOptions { + /** Registered provider route selecting the adapter instance. */ + provider: string model: string /** * Ordered conversation messages, exactly as the provider sees them (after @@ -201,7 +220,7 @@ The model-facing `ToolSchema` is the wire shape; the registered `ToolDefinition` ### The request envelope: `LlmCallConfig` and the logged header -Requests are built by the loop, not shaped per call: the non-history half of a request — the `EpochHeader`: this call configuration plus the rendered system prompt, the tool schemas in the authoritative returned assembly order (initially canonicalized by dsh-system-prompt's `toolOrder` config, or lexicographically when unset), and the session prefix — is logged session state (`request/header` snapshot and delta events, [session.md](session.md#the-request-header-events-requestheader-and-requestheader-delta)), so every conversation request is a pure function of the session log ([reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). The `agent/request` waterfall receives a frozen `LlmCallConfig` seed and a listener returns a replacement to switch model or sampling; the `agent/session-prefix` waterfall — fired once per loop instance — composes the request-only messages fronting the derived history (recorded as the header's `messagePrefix`) — the loop logs whatever the request actually uses. Loop-built requests arrive at `llm/stream` deep-frozen; mutation throws. +Requests are built by the loop, not shaped per call: the non-history half of a request — the `EpochHeader`: this call configuration plus the rendered system prompt, the tool schemas in the authoritative returned assembly order (initially canonicalized by dsh-system-prompt's `toolOrder` config, or lexicographically when unset), and the session prefix — is logged session state (`request/header` snapshot and delta events, [session.md](session.md#the-request-header-events-requestheader-and-requestheader-delta)), so every conversation request is a pure function of the session log ([reconstructability RFC](../rfc/implemented/architecture/2026-07-05-reconstructable-requests.md)). The `agent/request` waterfall receives a frozen `LlmCallConfig` seed and a listener returns a replacement to switch provider, model, or sampling; the `agent/session-prefix` waterfall — fired once per loop instance — composes the request-only messages fronting the derived history (recorded as the header's `messagePrefix`) — the loop logs whatever the request actually uses. Loop-built requests arrive at `llm/stream` deep-frozen; mutation throws. On the wire, a loop-built request reads in this order: the `system` slot (the rendered prompt assembly) → `messagePrefix` (the frozen session prefix) → the derived history — the boundary snapshot, whose tail is the newest `user/message` on a turn's first step and the previous step's tool results on later steps. The prefix never enters the derived history; its durable record is the header events, and the dev invariant recomputes exactly this equation against every loop-built request. @@ -209,6 +228,7 @@ FIXME(call-config-shape): revisit the exact definition of this type — which fi ```ts type-equiv interface LlmCallConfig { + provider: string model: string temperature?: number maxTokens?: number @@ -353,7 +373,7 @@ interface Agent { } ``` -`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`model?`) is merge-extensible — plugins add creation options by declaration merging. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. +`AgentStatus` is `'idle' | 'running' | 'disposed'`. `AgentId` is a branded string. `AgentOptions` (`provider?`, `model?`) is merge-extensible — plugins add creation options by declaration merging. A model dispatch requires both route fields after the `agent/request` waterfall. Persona is not an agent option: the `dsh-system-prompt` config supplies the global default, and an agent-scoped `deployment:persona` section may shadow it. The `agent/*` event taxonomy (lifecycle emits incl. `agent/session-start`, serial `agent/pre-step`/`agent/turn-stop` checkpoints, and the `agent/prompt-submit`/`agent/request`/`agent/session-prefix`/`agent/step-result`/`agent/turn-continuation` waterfalls) is in [architecture.md § Event taxonomy](../architecture.md#event-taxonomy); turn/step boundaries are durable `session/event` records, not `agent/*` emits. ## Interception decisions diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index fff329310a..b4b9d0f840 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -16,7 +16,12 @@ type StreamChunk = | { type: 'tool-call-delta'; index: number; id: CallId; name?: string; argumentsDelta: string } | { type: 'block-end'; index: number; block: ContentBlock } | { type: 'usage'; usage: TokenUsage } - | { type: 'finish'; reason: FinishReason } + | { + type: 'finish' + reason: FinishReason + /** Adapter-private lossless-JSON state for replaying a successful response. */ + replayState?: unknown + } ``` ## The adapter contract @@ -27,8 +32,9 @@ Every adapter MUST obey these, and every consumer may rely on them: - **Tool-call `arguments` stay raw JSON strings end-to-end.** Partial fragments stream via `argumentsDelta`; a provider that hands back parsed objects re-stringifies at `block-end`. - **Two sanctioned error paths.** A failure may either THROW from `stream()` (transport/protocol errors) **or** end the stream with `finish {kind:'error'|'aborted'}` (provider in-band errors, for adapters that can't throw mid-stream). Consumers must handle *both*. The agent loop translates a finish-error/aborted into a turn error — it never logs a normal completed assistant message for a failed step. - **Every provider HTTP request carries the app-attribution header.** Adapters send `attributionHeaders()` (below) - the `User-Agent` baseline - and prove it with a wire-level test (mock server asserting the received header, or the library's header hook for a library-backed adapter). +- **Replay state is adapter-owned.** A successful `finish` may carry lossless-JSON state needed to reconstruct a native provider response. The loop stores it with the assembled assistant message unless an `agent/step-result` listener rewrote the content. On a later request, `LlmService` passes the state only when the historical provider and target provider are currently registered to the exact same adapter instance. That adapter validates the state and owns any cross-model or cross-provider conversion; other adapters receive the provider-neutral content and provenance without the private state. -This contract is why two adapters exist as a deliberate pair: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (the same endpoint through `@earendil-works/pi-ai`). Two independent internals over one contract is what pinned the protocol down — the library-backed adapter can't throw mid-stream, so it exercises the finish-chunk error path the hand-rolled one might not. +This contract was pinned down by two deliberately independent implementations: `dsh-llm-deepseek` (hand-rolled fetch/SSE) and `dsh-llm-pi-ai` (a generic multi-provider adapter through `@earendil-works/pi-ai`). The library-backed adapter cannot throw mid-stream, so it exercises the finish-chunk error path the hand-rolled one might not. ## `AppIdentity` — app attribution @@ -58,11 +64,11 @@ interface TokenUsage { ## `BlockAssembler` -`BlockAssembler` ([`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts)) is the single shared implementation that folds a `StreamChunk` stream back into `ContentBlock`s and a final `Message`. The loop logs the raw chunks (for replay fidelity) while feeding the same chunks through an assembler — so the canonical log keeps token-level detail and the derived message is rebuilt deterministically. A consumer that needs the assembled result without re-implementing the fold uses this. +`BlockAssembler` ([`packages/llm/llm/src/assembler.ts`](../../packages/llm/llm/src/assembler.ts)) is the single shared implementation that folds a `StreamChunk` stream back into `ContentBlock`s, usage, finish reason, and replay state. The loop logs the raw chunks while feeding the same chunks through an assembler, then stores the assembled assistant content with its provider/model provenance. A consumer that needs the assembled result without re-implementing the fold uses this. ## The seam -`LlmAdapter` is the provider seam: subclass, implement `stream()`, register with `ctx.llm.registerAdapter(models, adapter)`. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). +`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). `ContentBlockType` (the key set the `index`-correlated blocks carry) derives from `ContentBlockMap`: diff --git a/docs/core-data-structures/session.md b/docs/core-data-structures/session.md index 1b12c3fc48..e45a39957e 100644 --- a/docs/core-data-structures/session.md +++ b/docs/core-data-structures/session.md @@ -41,7 +41,7 @@ interface SessionEventMap { * the model output and its accounting travel together (there is no separate * usage record). `usage` is absent when the adapter reported none. */ - 'assistant/message': { turn: number; step: number; content: ContentBlock[]; usage?: TokenUsage } + 'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage } 'tool/call': { turn: number; step: number; callId: CallId; name: string; arguments: string } 'tool/result': { turn: number; step: number; callId: CallId; content: ContentBlock[]; isError: boolean; error?: { name: string; code: string }; meta?: unknown } /** Steering content injected between steps of a running turn. */ @@ -103,7 +103,7 @@ The request envelope — the `EpochHeader` (call config + rendered system prompt ```ts type-equiv export interface EpochHeader { - /** The conversation's call configuration (model + sampling scalars). */ + /** The conversation's call configuration (provider + model + sampling scalars). */ config: LlmCallConfig /** Rendered system prompt text; absent for a system-less request. */ system?: string @@ -201,11 +201,11 @@ export interface SurfaceNode { `Session.deriveMessages()` projects the event log into the `Message[]` the model sees — cached (each surface node projected once, when first seen; a surface rewrite rebuilds) and frozen (a fresh array per call over shared, deep-frozen messages, so mutating logged history through a projection is unrepresentable). `deriveEventMessage(event)` is the per-node pure function the fold applies — public so external reconstructors and the dev invariant project a log prefix with exactly the same rules and cannot disagree with the cache. The projection rules: - `user/message` → a user message. -- `assistant/message` → an assistant message. Raw `assistant/chunk` events are replay/UI data and are **skipped** in derivation (the assembled message is authoritative). An **empty-content** `assistant/message` is also skipped — a max-tokens step cut off with no content still records an `assistant/message` to host its `usage`, but a content-less assistant turn must not enter the provider transcript. +- `assistant/message` → an assistant message with the event's provider/model provenance and optional adapter-private replay state. Raw `assistant/chunk` events are replay/UI data and are **skipped** in derivation (the assembled message is authoritative). An **empty-content** `assistant/message` is also skipped — a max-tokens step cut off with no content still records an `assistant/message` to host its usage/provenance, but a content-less assistant turn must not enter the provider transcript. - `tool/result` → a user message carrying a `tool-result` block. - `context/message`, `steering/message` → user-role messages wrapped in a tagged envelope (`…`) at their chronological position — the "system-reminder" pattern; the model distinguishes them from real prompts by the envelope. -Everything else (`turn/*`, `step/*`) is structural and does not project into a message. Token usage is observed on `assistant/message.usage` (the step that produced it); an operational error's step number is on `turn/end.reason` for `kind: 'error'`. +Everything else (`turn/*`, `step/*`) is structural and does not project into a message. Token usage is observed on `assistant/message.usage` (the step that produced it); an operational error's step number is on `turn/end.reason` for `kind: 'error'`. Because this unreleased format intentionally has no compatibility promise, seed/load validation rejects request headers without provider+model and assistant messages without provider/model provenance instead of guessing a route for historical data. ## Live-session fork API diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 5b0a82673e..3665232b86 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,24 +7,24 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:316`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:331`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:605`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:438`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:456`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:360`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:485`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:537`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:381`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:345`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:552`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:570`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:588`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:318`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:333`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:607`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:440`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:458`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:362`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:487`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:539`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:383`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`invariants`](../packages/support/invariants) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:347`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:554`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:572`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:590`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:70`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:123`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:138`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/write-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:109`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | -| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:39`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | +| `llm/stream` | `waterfall` | [`packages/llm/llm/src/index.ts:40`](../packages/llm/llm/src/index.ts) | [`llm`](../packages/llm/llm) (`waterfall`) | [`invariants`](../packages/support/invariants), [`llm-replay`](../packages/support/llm-replay) | | `session/created` | `emit` | [`packages/core/session/src/index.ts:52`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:64`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | - | | `session/event` | `emit` | [`packages/core/session/src/index.ts:83`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`acp`](../packages/ui/acp), [`invariants`](../packages/support/invariants), [`jsonrpc`](../packages/ui/jsonrpc), [`session-persistence`](../packages/session-persistence/session-persistence), [`stdio-agent`](../packages/ui/stdio-agent) | diff --git a/docs/persistence-catalog.md b/docs/persistence-catalog.md index 245d25fa5f..8f2118d7ba 100644 --- a/docs/persistence-catalog.md +++ b/docs/persistence-catalog.md @@ -64,7 +64,7 @@ Source: [`packages/core/session/src/types.ts:322`](../packages/core/session/src/ Assembled assistant message for one step (derived history uses this). Carries the step's `usage` when the adapter reported token accounting, so the model output and its accounting travel together (there is no separate usage record). `usage` is absent when the adapter reported none. ```ts persistence-catalog -'assistant/message': { turn: number; step: number; content: ContentBlock[]; usage?: TokenUsage } +'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage } ``` Types: [ContentBlock](core-data-structures/core.md) · [TokenUsage](core-data-structures/llm-streaming.md) @@ -93,7 +93,7 @@ Marks the end of a compaction — log-only, releases the lock. `error` set if su 'compact/end': { turn: number; error?: string } ``` -Source: [`packages/compact/compact/src/types.ts:46`](../packages/compact/compact/src/types.ts) +Source: [`packages/compact/compact/src/types.ts:48`](../packages/compact/compact/src/types.ts) #### `compact/start` — log-only @@ -110,7 +110,7 @@ Source: [`packages/compact/compact/src/types.ts:23`](../packages/compact/compact Provenance record of a completed summarization — log-only, no surfaceOp. The summary content is in `data.summary`; the actual surface replacement is performed by a subsequent `user/message` event that shadows the compacted range. ```ts persistence-catalog -'compact/summary': { summary: ContentBlock[]; shadowedRange: { start: number; end: number }; shadowedSeqs: number[]; shadowedTokenCount: number; model: string; maxTokens?: number } +'compact/summary': { summary: ContentBlock[]; shadowedRange: { start: number; end: number }; shadowedSeqs: number[]; shadowedTokenCount: number; provider: string; model: string; maxTokens?: number } ``` Types: [ContentBlock](core-data-structures/core.md) @@ -181,7 +181,7 @@ Source: [`packages/core/session/src/types.ts:374`](../packages/core/session/src/ #### `request/header-delta` — log-only -Amendment to the folded EpochHeader: at least one of a SystemDelta, a ToolsDelta, a whole replacement LlmCallConfig (four scalars — not worth diffing), or a whole replacement session prefix (`messagePrefix` — small advisory content, replaced whole; an EMPTY array encodes the transition to "none", mirroring the canonical form's absent field — the loop never produces one in practice: the prefix is composed once per instance and anchored by that instance's snapshot, so this arm exists for codec totality). Appended by the loop inside the step, before dispatch, when the header for this request differs from the fold of the log so far; the writer verifies `applyHeaderDelta(previous, delta)` reproduces the new header exactly and falls back to a `'fallback'` `request/header` snapshot when it cannot, so a logged delta ALWAYS round-trips. NOT a SurfaceEventType. +Amendment to the folded EpochHeader: at least one of a SystemDelta, a ToolsDelta, a whole replacement LlmCallConfig (provider/model plus sampling scalars — not worth diffing), or a whole replacement session prefix (`messagePrefix` — small advisory content, replaced whole; an EMPTY array encodes the transition to "none", mirroring the canonical form's absent field — the loop never produces one in practice: the prefix is composed once per instance and anchored by that instance's snapshot, so this arm exists for codec totality). Appended by the loop inside the step, before dispatch, when the header for this request differs from the fold of the log so far; the writer verifies `applyHeaderDelta(previous, delta)` reproduces the new header exactly and falls back to a `'fallback'` `request/header` snapshot when it cannot, so a logged delta ALWAYS round-trips. NOT a SurfaceEventType. ```ts persistence-catalog 'request/header-delta': { system?: SystemDelta; tools?: ToolsDelta; config?: LlmCallConfig; messagePrefix?: Message[] } diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index b338edfc52..3823f04022 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -141,6 +141,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [The agent is a registration scope](implemented/architecture/2026-07-08-agent-scope-contexts.md) | 2026-07-08 | | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | +| [Provider-routed LLM adapters and a generic pi-ai backend](implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) | 2026-07-14 | ### Process diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md new file mode 100644 index 0000000000..e43fb1f2e7 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md @@ -0,0 +1,89 @@ +# RFC: Provider-routed LLM adapters and a generic pi-ai backend + +Status: implemented + +## Problem + +`dsh-llm` registered adapters by exact model name. A plugin supplied a model list at Cordis startup, `LlmService` stored one adapter per listed string, and `GenerateOptions.model` selected the adapter and the provider model at once. This worked while both shipping adapters targeted the same two DeepSeek models, but it conflated two independent decisions: which upstream provider owns a request, and which model that provider should run. + +The conflation prevents a provider gateway from serving an open-ended model catalog. OpenRouter, for example, is one provider with many model ids, while a private OpenAI-compatible endpoint may add models without changing the Harness plugin tree. Every newly selected model currently needs to have been registered during plugin startup. The same model id can also exist at multiple providers, so model-only registration cannot state which provider the caller intended. + +`dsh-llm-pi-ai` exposed none of pi-ai's provider abstraction. It constructed an inline DeepSeek `openai-completions` model, applied DeepSeek-specific payload patches, and stamped every replayed assistant message as DeepSeek. pi-ai itself has a provider/model catalog, selects APIs such as `openai-responses`, `anthropic-messages`, and `google-generative-ai`, and preserves provider-specific response ids and reasoning/tool signatures for later turns. The Harness conversion dropped that provenance, so simply replacing the inline model with a catalog lookup would have made same-model replay and cross-provider handoff incomplete. + +The adapter configuration also assumes one DeepSeek API key and endpoint. A generic backend needs independent credentials and endpoint overrides per provider while leaving AWS, Google ADC, OAuth, and other ambient authentication mechanisms to pi-ai. + +## Decision + +### Provider is the adapter registration key + +`GenerateOptions` and `LlmCallConfig` carry `provider: string` beside `model: string`; `AgentOptions` carries the corresponding optional creation field. A loop request is valid only after both values are non-empty, and both values are part of the logged request header. `agent/request` may return a replacement pair on any step, so a session can switch providers and models without changing the Cordis plugin lifecycle. + +`LlmService` registers and resolves adapters by provider. `registerAdapter(providers, adapter)` checks the entire provider list before mutating the registry, rejects a duplicate with `DUPLICATE_ADAPTER`, and disposes the whole registration as one effect. `providers()` reports the registered keys. Model ids are not registered or enumerated by the service; the selected adapter validates or forwards them. + +A provider has exactly one adapter owner in a Cordis context. `dsh-llm-deepseek` registers `deepseek`; `dsh-llm-pi-ai` may also register `deepseek`, but loading both owners is a configuration error rather than an ordering rule or fallback. A deployment that wants the hand-rolled DeepSeek implementation excludes `deepseek` from the pi-ai profiles. A deployment that wants pi-ai's DeepSeek implementation does not mount `dsh-llm-deepseek`. + +`dsh-llm-deepseek` removes its model registration list and accepts any model string routed through provider `deepseek`. Its request serialization, `/chat/completions` endpoint, thinking options, SSE parsing, and error behavior remain unchanged; `options.model` is still sent verbatim. + +### Explicit pi-ai provider profiles + +`dsh-llm-pi-ai` takes one non-empty list of provider profiles. Provider names must be unique within the list and present in pi-ai's `getProviders()` result. Each profile contains the provider name plus optional `apiKey`, `baseURL`, headers, reasoning level and budgets, cache retention, transport, timeouts, and retry settings. Credentials are never global: an explicit key applies only to its profile, while an absent key lets pi-ai resolve its standard environment variable, OAuth token, AWS credential chain, Google ADC, or other provider-native ambient authentication. An explicitly empty key is invalid configuration rather than an environment fallback. + +The plugin registers all configured provider names against one `PiAiAdapter` in one all-or-nothing call. A request uses its provider to select the matching profile and finds its model in `getModels(provider)` to obtain the catalog descriptor. An unknown provider fails at plugin load; an unknown model fails before network I/O with `UNKNOWN_MODEL`. The catalog object is never mutated. When a profile supplies `baseURL`, the adapter clones the selected descriptor and overrides only `baseUrl`, so a private endpoint can retain pi-ai's API, capabilities, compatibility flags, context limits, and reasoning map. The private endpoint must implement the selected provider's protocol, and the model id must still exist in the installed pi-ai catalog. + +The adapter calls pi-ai's `streamSimple()` so each catalog model chooses its registered API implementation, including OpenAI Responses instead of Chat Completions where the descriptor says `openai-responses`. Harness temperature, maximum tokens, signal, session id, and the profile's common stream options flow through directly. Profile headers merge with the mandatory Harness attribution headers, with Harness attribution winning its reserved names. The adapter no longer maintains DeepSeek-specific payload rewrites or a provider-protocol matrix. + +pi-ai's common stream options do not expose stop sequences. `dsh-llm-pi-ai` rejects a defined Harness `stop` option with `UNSUPPORTED_OPTION` rather than silently ignoring it or growing a second provider-specific payload implementation. `dsh-llm-deepseek` continues to support `stop` through its native request serializer. + +### Durable assistant provenance and replay state + +Assistant messages carry provider-neutral provenance containing the request's `provider` and `model`, plus an optional JSON-serializable adapter replay state. A successful `assistant/message` session event records this provenance and `deriveMessages()` returns it with the assistant message. User, system, context, and tool-result messages carry no assistant provenance. The provider/model fields are authoritative loop data; an adapter owns only its opaque replay-state payload. + +A terminal successful `finish` chunk may carry replay state, and `BlockAssembler` retains it alongside usage and finish reason. The loop attaches it to the assistant provenance only when the post-`agent/step-result` content is structurally equal to the assembled provider output. A listener that rewrites content keeps the provider/model provenance but loses the now-stale replay state. Error and aborted responses do not produce a normal assistant message and therefore do not enter future model history. + +The pi-ai replay state is a versioned, minimal projection of its successful `AssistantMessage`: source API/provider/model, response id/model, stop reason, and index-aligned text, thinking, and tool-call signatures. It does not duplicate text or tool arguments already carried by Harness content blocks, and it omits diagnostics, timestamps, usage, and errors. On a later request, `LlmService` gives replay state to the target adapter only when the historical provider and target provider are currently owned by the same adapter instance. That adapter combines the logged Harness content with replay state when it can restore the historical response, and owns any required cross-model or cross-provider conversion. An adapter receiving replay state with an unknown version or mismatched block shape fails explicitly; a different adapter receives only provider-neutral content and provenance. + +This state is model-visible replay input and therefore follows the existing [reconstructable-request rule](../../implemented/architecture/2026-07-05-reconstructable-requests.md): it is present in both the terminal `finish` chunk and the assembled `assistant/message` provenance that drives derivation. Resume and fork preserve it verbatim. Compaction that shadows the assistant message also removes its replay state from the active surface; the summary is ordinary provider-neutral content. + +### Propagate the target through every request producer + +Every model-selection surface carries provider and model together: declarative agents, ACP and stdio app config, the JSON-RPC initialize request, subagent overrides and inheritance, workflow child overrides, and direct compaction summarization. Subagents inherit both fields from their parent before applying request overrides. The system-prompt variable set gains `provider` beside `model`. + +Compaction configuration gains `summarizationProvider` beside `summarizationModel`. Both are empty to inherit, or both are non-empty to select an explicit target; a half-configured pair fails load. Inheritance uses the last logged request target when one exists and falls back to the agent's creation options. `compact/summary` records both fields with the existing model-call envelope. + +The JSON-RPC runtime receives provider and model explicitly. Its convenience fallback mounts `dsh-llm-deepseek` only for provider `deepseek` when that provider has no registered owner; other missing providers fail without guessing an adapter. + +The on-disk session format remains the pre-release pinned version `0`, with no compatibility promise. Seed/load validation rejects request headers lacking provider and assistant messages lacking required provenance instead of accepting an old shape that can no longer reconstruct the request. + +## Alternatives considered + +**Keep model names as registry keys and add wildcard adapters.** A wildcard introduces fallback ordering between exact registrations and catch-all plugins, makes duplicate ownership dependent on listener order, and still cannot distinguish the same model id at two providers without another convention. + +**Encode provider and model into one string.** Values such as OpenRouter's `openai/gpt-*` already contain provider-like prefixes and slashes. A delimiter convention would leak routing syntax into every model selector and require escaping rules; two explicit fields are unambiguous and independently loggable. + +**Add `backend + provider + model`.** A backend key would allow `dsh-llm-deepseek` and pi-ai's DeepSeek implementation to coexist and switch per request. The accepted deployment rule is instead one adapter owner per provider: implementations of the same upstream are alternatives selected by plugin composition. A third routing dimension would burden every request and configuration for a capability with no current consumer. + +**Let `dsh-llm-pi-ai` automatically register every pi-ai provider.** This would claim ambient credentials and provider names the deployment never intended to expose, and would conflict with native adapters such as `dsh-llm-deepseek`. Explicit profiles make capability and credential scope reviewable. + +**Mount one pi-ai plugin instance per provider.** Separate instances isolate config but repeat plugin declarations and cannot make profile registration atomic. One adapter already receives provider on every request, so a validated profile map is the smaller lifecycle surface. + +**Accept arbitrary inline pi-ai model descriptors.** This would support catalog-external private model ids, but it exposes pi-ai's model and compatibility schema as Harness configuration and makes the adapter responsible for validating protocol-specific combinations. The first version supports custom endpoints by overriding `baseURL` on catalog models; custom descriptors require a separate decision after a real catalog-external deployment is identified. + +## Consequences + +- Provider names are deployment-wide route ownership keys: two providers may use the same model string, but mounting two adapters for one provider fails at load instead of creating fallback order. +- Model selection no longer changes the Cordis plugin graph. Catalog-backed adapters can accept any installed catalog model selected after startup, while the native DeepSeek adapter forwards arbitrary DeepSeek model ids. +- A custom `baseURL` preserves the selected catalog model's protocol and capabilities; it does not make catalog-external model ids valid. Private endpoints must implement that catalog entry's protocol. +- pi-ai credentials and transport knobs are scoped per provider profile. An omitted key delegates to pi-ai ambient authentication, while an explicitly empty key is invalid. +- `dsh-llm-pi-ai` rejects stop sequences because pi-ai's common stream API cannot express them; the native DeepSeek adapter retains its stop support. +- Replay state is portable only within the adapter instance that owns both the historical and target providers. Cross-provider and cross-model restoration is an adapter responsibility, and another adapter receives provider-neutral history without the opaque state. +- Current pre-release session JSONL requires provider/model request headers and assistant provenance. Older shapes remain version `0` but are rejected rather than migrated. + +## Testing + +- Unit coverage exercises registry conflicts, request reconstruction, session validation, profile resolution, option forwarding, native API selection including OpenAI Responses, conversion, replay validation, error mapping, cancellation, content rewrites, and same-instance versus different-instance replay dispatch. +- Keyless loop/session tests and ACP snapshots exercise durable provider/model metadata, resume and fork propagation, workflow/subagent overrides, and unchanged user-visible transcripts; the key-gated DeepSeek e2e retains real provider streaming and tool follow-up coverage. +- Public JSDoc, package READMEs, architecture and core-data-structure docs, generated catalogs, examples, session fixtures, and Python SDK pairs use provider/model targets consistently and are checked by the repository documentation and type-equivalence gates. + +## Risks + +This is a repo-wide pre-release API break: model-only request construction, adapter registration, app protocols, fixtures, and persisted version-0 event shapes all change together, with no compatibility aliases. The provider exclusivity rule deliberately prevents two implementations of the same upstream from coexisting in one context. A pi-ai dependency update can change the accepted provider/model catalog, so the lockfile and adapter e2e matrix define the tested set. Custom `baseURL` endpoints inherit the chosen catalog model's protocol assumptions and cannot repair an incompatible proxy. Catalog-external model descriptors and multimodal content remain unsupported. pi-ai replay state may contain opaque encrypted reasoning signatures; it is persisted because the provider requires it for continuity, but it is never rendered or logged outside the existing session record. diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 9ea71d3005..292b592d93 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -477,10 +477,10 @@ todo_write is session-owned state; UIs render the latest todo/write event as a c 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. +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?, provider?, 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. +- `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), `provider` and `model` (paired LLM target overrides). 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. @@ -527,6 +527,10 @@ Constraints: concurrency and total-agent caps apply; no filesystem, network, tim "type": "string", "description": "Optional one-line description of the phase." }, + "provider": { + "type": "string", + "description": "Optional provider override this phase is expected to use." + }, "model": { "type": "string", "description": "Optional model override this phase is expected to use." diff --git a/examples/acp-agent/advanced.cordis.snapshot.yml b/examples/acp-agent/advanced.cordis.snapshot.yml index 64802e1da9..8768407050 100644 --- a/examples/acp-agent/advanced.cordis.snapshot.yml +++ b/examples/acp-agent/advanced.cordis.snapshot.yml @@ -12,6 +12,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/advanced.cordis.yml b/examples/acp-agent/advanced.cordis.yml index 772369578f..ef1155d39d 100644 --- a/examples/acp-agent/advanced.cordis.yml +++ b/examples/acp-agent/advanced.cordis.yml @@ -10,6 +10,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/both-mode.cordis.snapshot.yml b/examples/acp-agent/both-mode.cordis.snapshot.yml index 8ee54b3078..4d12851fa5 100644 --- a/examples/acp-agent/both-mode.cordis.snapshot.yml +++ b/examples/acp-agent/both-mode.cordis.snapshot.yml @@ -15,6 +15,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/both-mode.cordis.yml b/examples/acp-agent/both-mode.cordis.yml index 3dff66d60a..da70c572a4 100644 --- a/examples/acp-agent/both-mode.cordis.yml +++ b/examples/acp-agent/both-mode.cordis.yml @@ -14,6 +14,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/code-mode.cordis.snapshot.yml b/examples/acp-agent/code-mode.cordis.snapshot.yml index d525afc5d6..de5666bd15 100644 --- a/examples/acp-agent/code-mode.cordis.snapshot.yml +++ b/examples/acp-agent/code-mode.cordis.snapshot.yml @@ -15,6 +15,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/code-mode.cordis.yml b/examples/acp-agent/code-mode.cordis.yml index 323c35b5b4..439c31111a 100644 --- a/examples/acp-agent/code-mode.cordis.yml +++ b/examples/acp-agent/code-mode.cordis.yml @@ -15,6 +15,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' tools: diff --git a/examples/acp-agent/cordis.yml b/examples/acp-agent/cordis.yml index dc03ea6b03..014222951b 100644 --- a/examples/acp-agent/cordis.yml +++ b/examples/acp-agent/cordis.yml @@ -19,9 +19,6 @@ config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-flash - - deepseek-v4-pro # Local bash executor for agent-core's tool-bash schema (one of several tool # stacks in this tree: filesystem, subagent, and todo_write load below). @@ -36,6 +33,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persistenceRoot: !!js process.env.DSH_SNAPSHOT_SESSIONS_ROOT ?? './.sessions' # The persona: identity + behavior only, nothing about transports or diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 1eabba53b3..580b20280f 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,12 +2,12 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} {"type":"assistant/chunk","seq":7,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":8,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":1783957884564,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"step/end","seq":10,"time":1783957884564,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":11,"time":1783957884564,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index 7787ed2ab1..abbbf5fef5 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,12 +2,12 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} {"type":"assistant/chunk","seq":7,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":8,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":1783957884701,"data":{"turn":1,"step":1,"content":[{"type":"text","text":"WORKFLOW_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"step/end","seq":10,"time":1783957884701,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":11,"time":1783957884701,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index bb74382b22..55717bbc1b 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,13 +2,13 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} {"type":"assistant/chunk","seq":7,"time":1783950000008,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":8,"time":1783950000009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":1783957884487,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"tool/call","seq":10,"time":1783957884487,"data":{"turn":1,"step":1,"callId":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}} {"type":"tool/result","seq":11,"time":1783957884488,"data":{"turn":1,"step":1,"callId":"advanced-mount","content":[{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} {"type":"step/end","seq":12,"time":1783957884489,"data":{"turn":1,"step":1}} @@ -18,7 +18,7 @@ {"type":"assistant/chunk","seq":16,"time":1783950000017,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}}}} {"type":"assistant/chunk","seq":17,"time":1783950000018,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":18,"time":1783950000019,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} +{"type":"assistant/message","seq":19,"time":1783957884490,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[14,15,16,17,18],"surfaceOp":"append"} {"type":"tool/call","seq":20,"time":1783957884490,"data":{"turn":1,"step":2,"callId":"advanced-code","name":"run_code","arguments":"{\"code\":\"return await tools.cordis_inspect({ what: 'dynamic' })\"}"}} {"type":"tool/code-dispatch","seq":21,"time":1783957884560,"data":{"parentCallId":"advanced-code","subCallId":"advanced-code:code:1","name":"cordis_inspect","arguments":{"what":"dynamic"},"isError":false,"resultSummary":"## dynamic\n- dyn-1: snapshot-marker [active]"}} {"type":"tool/result","seq":22,"time":1783957884561,"data":{"turn":1,"step":2,"callId":"advanced-code","content":[{"type":"text","text":"## dynamic\n- dyn-1: snapshot-marker [active]"}],"isError":false,"meta":{"logs":[],"dispatches":1}},"sourceEventSeqs":[20],"surfaceOp":"append"} @@ -29,7 +29,7 @@ {"type":"assistant/chunk","seq":27,"time":1783950000028,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":28,"time":1783950000029,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":29,"time":1783950000030,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"} +{"type":"assistant/message","seq":30,"time":1783957884562,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[25,26,27,28,29],"surfaceOp":"append"} {"type":"tool/call","seq":31,"time":1783957884562,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","name":"subagent","arguments":"{\"description\":\"Check direct child\",\"prompt\":\"Reply with exactly DIRECT_CHILD_OK and nothing else.\"}"}} {"type":"tool/result","seq":32,"time":1783957884593,"data":{"turn":1,"step":3,"callId":"advanced-direct-child","content":[{"type":"text","text":"DIRECT_CHILD_OK"}],"isError":false},"sourceEventSeqs":[31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783957884593,"data":{"turn":1,"step":3}} @@ -39,7 +39,7 @@ {"type":"assistant/chunk","seq":37,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}}}} {"type":"assistant/chunk","seq":38,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":39,"time":1783957884594,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"} +{"type":"assistant/message","seq":40,"time":1783957884594,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[35,36,37,38,39],"surfaceOp":"append"} {"type":"tool/call","seq":41,"time":1783957884594,"data":{"turn":1,"step":4,"callId":"advanced-workflow","name":"workflow","arguments":"{\"script\":\"phase('Delegate')\\nconst reply = await agent('Reply with exactly WORKFLOW_CHILD_OK and nothing else.', { label: 'workflow-child' })\\nreturn { reply }\",\"meta\":{\"name\":\"advanced-acp-snapshot\",\"description\":\"exercise one workflow child through ACP\"}}"}} {"type":"tool/result","seq":42,"time":1783957884717,"data":{"turn":1,"step":4,"callId":"advanced-workflow","content":[{"type":"text","text":"workflow \"advanced-acp-snapshot\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WORKFLOW_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[41],"surfaceOp":"append"} {"type":"step/end","seq":43,"time":1783957884718,"data":{"turn":1,"step":4}} @@ -49,7 +49,7 @@ {"type":"assistant/chunk","seq":47,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}}}} {"type":"assistant/chunk","seq":48,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":49,"time":1783957884719,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} +{"type":"assistant/message","seq":50,"time":1783957884719,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[45,46,47,48,49],"surfaceOp":"append"} {"type":"tool/call","seq":51,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","name":"cordis_unmount","arguments":"{\"id\":\"dyn-1\"}"}} {"type":"tool/result","seq":52,"time":1783957884719,"data":{"turn":1,"step":5,"callId":"advanced-unmount","content":[{"type":"text","text":"unmounted dyn-1 (plugin \"snapshot-marker\")"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"} {"type":"step/end","seq":53,"time":1783957884719,"data":{"turn":1,"step":5}} @@ -59,6 +59,6 @@ {"type":"assistant/chunk","seq":57,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"ADVANCED_ACP_OK"}}}} {"type":"assistant/chunk","seq":58,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":3,"outputTokens":3}}}} {"type":"assistant/chunk","seq":59,"time":1783957884720,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} +{"type":"assistant/message","seq":60,"time":1783957884720,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"ADVANCED_ACP_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3,"outputTokens":3}},"sourceEventSeqs":[55,56,57,58,59],"surfaceOp":"append"} {"type":"step/end","seq":61,"time":1783957884721,"data":{"turn":1,"step":6}} {"type":"turn/end","seq":62,"time":1783957884721,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index e70cfcce44..d5edb3e296 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -115,7 +115,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** 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. */ + /** 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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; @@ -133,6 +133,8 @@ declare const tools: { title: string; /** Optional one-line description of the phase. */ detail?: string; + /** Optional provider override this phase is expected to use. */ + provider?: string; /** Optional model override this phase is expected to use. */ model?: string; }[]; 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 b49097188e..8d422579ed 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":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"}}} @@ -84,7 +84,7 @@ {"type":"assistant/chunk","seq":82,"time":1783611775498,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_AZFzvUwuC4vAUoICrfke5147","name":"run_code","arguments":"{\"code\": \"const result = await tools.bash({ command: \\\"echo BOTH_OK\\\", description: \\\"Echo BOTH_OK\\\" });\\nreturn result;\"}"}}}} {"type":"assistant/chunk","seq":83,"time":1783611775498,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":5530,"outputTokens":108,"cacheReadTokens":0,"reasoningTokens":37}}}} {"type":"assistant/chunk","seq":84,"time":1783611775498,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":85,"time":1783611775503,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the `run_code` tool to execute a program that calls `tools.bash` with the command `echo BOTH_OK` and returns its output."},{"type":"tool-call","id":"call_00_AZFzvUwuC4vAUoICrfke5147","name":"run_code","arguments":"{\"code\": \"const result = await tools.bash({ command: \\\"echo BOTH_OK\\\", description: \\\"Echo BOTH_OK\\\" });\\nreturn result;\"}"}],"usage":{"inputTokens":5530,"outputTokens":108,"cacheReadTokens":0,"reasoningTokens":37}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"surfaceOp":"append"} +{"type":"assistant/message","seq":85,"time":1783611775503,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the `run_code` tool to execute a program that calls `tools.bash` with the command `echo BOTH_OK` and returns its output."},{"type":"tool-call","id":"call_00_AZFzvUwuC4vAUoICrfke5147","name":"run_code","arguments":"{\"code\": \"const result = await tools.bash({ command: \\\"echo BOTH_OK\\\", description: \\\"Echo BOTH_OK\\\" });\\nreturn result;\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":5530,"outputTokens":108,"cacheReadTokens":0,"reasoningTokens":37}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"surfaceOp":"append"} {"type":"tool/call","seq":86,"time":1783611775504,"data":{"turn":1,"step":1,"callId":"call_00_AZFzvUwuC4vAUoICrfke5147","name":"run_code","arguments":"{\"code\": \"const result = await tools.bash({ command: \\\"echo BOTH_OK\\\", description: \\\"Echo BOTH_OK\\\" });\\nreturn result;\"}"}} {"type":"tool/code-dispatch","seq":87,"time":1783611775590,"data":{"parentCallId":"call_00_AZFzvUwuC4vAUoICrfke5147","subCallId":"call_00_AZFzvUwuC4vAUoICrfke5147:code:1","name":"bash","arguments":{"command":"echo BOTH_OK","description":"Echo BOTH_OK"},"isError":false,"resultSummary":"BOTH_OK\n"}} {"type":"tool/result","seq":88,"time":1783611775592,"data":{"turn":1,"step":1,"callId":"call_00_AZFzvUwuC4vAUoICrfke5147","content":[{"type":"text","text":"BOTH_OK\n"}],"isError":false,"meta":{"logs":[],"dispatches":1}},"sourceEventSeqs":[86],"surfaceOp":"append"} @@ -116,6 +116,6 @@ {"type":"assistant/chunk","seq":114,"time":1783611776440,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"BOTH_OK"}}}} {"type":"assistant/chunk","seq":115,"time":1783611776440,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":22,"outputTokens":21,"cacheReadTokens":5632,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":116,"time":1783611776440,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":117,"time":1783611776441,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output is \"BOTH_OK\". I need to reply with that output only."},{"type":"text","text":"BOTH_OK"}],"usage":{"inputTokens":22,"outputTokens":21,"cacheReadTokens":5632,"reasoningTokens":17}},"sourceEventSeqs":[91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116],"surfaceOp":"append"} +{"type":"assistant/message","seq":117,"time":1783611776441,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output is \"BOTH_OK\". I need to reply with that output only."},{"type":"text","text":"BOTH_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":22,"outputTokens":21,"cacheReadTokens":5632,"reasoningTokens":17}},"sourceEventSeqs":[91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116],"surfaceOp":"append"} {"type":"step/end","seq":118,"time":1783611776441,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":119,"time":1783611776441,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index 5dd8547aa8..8c44068330 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -100,7 +100,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** 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. */ + /** 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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; @@ -118,6 +118,8 @@ declare const tools: { title: string; /** Optional one-line description of the phase. */ detail?: string; + /** Optional provider override this phase is expected to use. */ + provider?: string; /** Optional model override this phase is expected to use. */ model?: string; }[]; diff --git a/examples/acp-agent/tests/snapshots/cancel/session.jsonl b/examples/acp-agent/tests/snapshots/cancel/session.jsonl index 7b2f5adff1..347951db62 100644 --- a/examples/acp-agent/tests/snapshots/cancel/session.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Start a long task; this turn will be cancelled mid-stream."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"partial"}}} {"type":"step/end","seq":6,"time":0,"data":{"turn":1,"step":1}} 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 9367e2deb0..deb4b7e136 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":"{{system}}","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":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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"}}} @@ -108,7 +108,7 @@ {"type":"assistant/chunk","seq":106,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}}}} {"type":"assistant/chunk","seq":107,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}}}} {"type":"assistant/chunk","seq":108,"time":1783611772836,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":109,"time":1783611772840,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."},{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}],"usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} +{"type":"assistant/message","seq":109,"time":1783611772840,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants a single run_code program that calls bash twice, then returns the two outputs joined with a plus sign. Let me write this."},{"type":"tool-call","id":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3009,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} {"type":"tool/call","seq":110,"time":1783611772840,"data":{"turn":1,"step":1,"callId":"call_00_DRxnM6R1TThfDwcudW0f2050","name":"run_code","arguments":"{\"code\": \"const out1 = await tools.bash({ command: \\\"echo CODE_ONE\\\", description: \\\"First echo\\\" });\\nconst out2 = await tools.bash({ command: \\\"echo CODE_TWO\\\", description: \\\"Second echo\\\" });\\nreturn out1.trim() + \\\"+\\\" + out2.trim();\"}"}} {"type":"tool/code-dispatch","seq":111,"time":1783611772933,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:1","name":"bash","arguments":{"command":"echo CODE_ONE","description":"First echo"},"isError":false,"resultSummary":"CODE_ONE\n"}} {"type":"tool/code-dispatch","seq":112,"time":1783611772936,"data":{"parentCallId":"call_00_DRxnM6R1TThfDwcudW0f2050","subCallId":"call_00_DRxnM6R1TThfDwcudW0f2050:code:2","name":"bash","arguments":{"command":"echo CODE_TWO","description":"Second echo"},"isError":false,"resultSummary":"CODE_TWO\n"}} @@ -145,6 +145,6 @@ {"type":"assistant/chunk","seq":143,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CODE_ONE+CODE_TWO"}}}} {"type":"assistant/chunk","seq":144,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":89,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":145,"time":1783611773686,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":146,"time":1783611773687,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output is exactly what the user asked for: CODE_ONE+CODE_TWO"},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"usage":{"inputTokens":89,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":17}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145],"surfaceOp":"append"} +{"type":"assistant/message","seq":146,"time":1783611773687,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output is exactly what the user asked for: CODE_ONE+CODE_TWO"},{"type":"text","text":"CODE_ONE+CODE_TWO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":89,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":17}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145],"surfaceOp":"append"} {"type":"step/end","seq":147,"time":1783611773687,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":148,"time":1783611773687,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index 5dd8547aa8..8c44068330 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -100,7 +100,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** 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. */ + /** 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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; @@ -118,6 +118,8 @@ declare const tools: { title: string; /** Optional one-line description of the phase. */ detail?: string; + /** Optional provider override this phase is expected to use. */ + provider?: string; /** Optional model override this phase is expected to use. */ model?: string; }[]; diff --git a/examples/acp-agent/tests/snapshots/error-finish/session.jsonl b/examples/acp-agent/tests/snapshots/error-finish/session.jsonl index 98538a94c2..f0ef4267ac 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/session.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/session.jsonl @@ -2,6 +2,6 @@ {"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"This prompt triggers a recorded provider error."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"step/end","seq":4,"time":0,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":5,"time":0,"data":{"turn":1,"reason":{"kind":"error","step":1,"message":"simulated provider error (HTTP 401)","code":"AUTH"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl index 90f009946d..00587e34c2 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352084740,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352084740,"data":{"content":[{"type":"text","text":"First use the read tool to read config.txt in the current directory. Then use the edit tool (NOT bash) to replace the literal text DEBUG with RELEASE in that file. Then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352084742,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352084742,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352084742,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352085426,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352085426,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352085563,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -67,7 +67,7 @@ {"type":"assistant/chunk","seq":65,"time":1783352086057,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}}}} {"type":"assistant/chunk","seq":66,"time":1783352086057,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2900,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":46}}}} {"type":"assistant/chunk","seq":67,"time":1783352086057,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":68,"time":1783352086059,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read config.txt in the current directory\n2. Use the edit tool to replace DEBUG with RELEASE\n3. Reply with exactly \"DONE\"\n\nLet me start by reading the file."},{"type":"tool-call","id":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}],"usage":{"inputTokens":2900,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":46}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67],"surfaceOp":"append"} +{"type":"assistant/message","seq":68,"time":1783352086059,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read config.txt in the current directory\n2. Use the edit tool to replace DEBUG with RELEASE\n3. Reply with exactly \"DONE\"\n\nLet me start by reading the file."},{"type":"tool-call","id":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2900,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":46}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67],"surfaceOp":"append"} {"type":"tool/call","seq":69,"time":1783352086059,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","name":"read","arguments":"{\"file_path\": \"config.txt\"}"}} {"type":"tool/result","seq":70,"time":1783352086065,"data":{"turn":1,"step":1,"callId":"call_00_S6krdIDHoSCGWv7WnXX97617","content":[{"type":"text","text":"/tmp/acp-snap-cwd-0BxHdV/config.txt\nfile\n\n1: mode=DEBUG\n2: level=info\n\n(End of file - total 2 lines)\n"}],"isError":false},"sourceEventSeqs":[69],"surfaceOp":"append"} {"type":"step/end","seq":71,"time":1783352086065,"data":{"turn":1,"step":1}} @@ -127,7 +127,7 @@ {"type":"assistant/chunk","seq":125,"time":1783352087469,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}}}} {"type":"assistant/chunk","seq":126,"time":1783352087469,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":241,"outputTokens":98,"cacheReadTokens":2816,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":127,"time":1783352087469,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":128,"time":1783352087469,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Now I need to replace \"DEBUG\" with \"RELEASE\" using the edit tool."},{"type":"tool-call","id":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}],"usage":{"inputTokens":241,"outputTokens":98,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"surfaceOp":"append"} +{"type":"assistant/message","seq":128,"time":1783352087469,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"Now I need to replace \"DEBUG\" with \"RELEASE\" using the edit tool."},{"type":"tool-call","id":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":241,"outputTokens":98,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127],"surfaceOp":"append"} {"type":"tool/call","seq":129,"time":1783352087469,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","name":"edit","arguments":"{\"file_path\": \"config.txt\", \"old_string\": \"DEBUG\", \"new_string\": \"RELEASE\"}"}} {"type":"tool/result","seq":130,"time":1783352087476,"data":{"turn":1,"step":2,"callId":"call_00_vOytneZ0XpsLslEEJAxR6398","content":[{"type":"text","text":"The file /tmp/acp-snap-cwd-0BxHdV/config.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"config.txt","oldText":"mode=DEBUG\nlevel=info","newText":"mode=RELEASE\nlevel=info"}]}},"sourceEventSeqs":[129],"surfaceOp":"append"} {"type":"step/end","seq":131,"time":1783352087477,"data":{"turn":1,"step":2}} @@ -154,6 +154,6 @@ {"type":"assistant/chunk","seq":152,"time":1783352088523,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":153,"time":1783352088523,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":244,"outputTokens":17,"cacheReadTokens":2944,"reasoningTokens":14}}}} {"type":"assistant/chunk","seq":154,"time":1783352088523,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":155,"time":1783352088523,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Done. The user wants me to reply with exactly \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":244,"outputTokens":17,"cacheReadTokens":2944,"reasoningTokens":14}},"sourceEventSeqs":[133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154],"surfaceOp":"append"} +{"type":"assistant/message","seq":155,"time":1783352088523,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Done. The user wants me to reply with exactly \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":244,"outputTokens":17,"cacheReadTokens":2944,"reasoningTokens":14}},"sourceEventSeqs":[133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154],"surfaceOp":"append"} {"type":"step/end","seq":156,"time":1783352088523,"data":{"turn":1,"step":3}} {"type":"turn/end","seq":157,"time":1783352088524,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl index 802120fd9c..03a64d2e39 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783611702550,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783611702550,"data":{"content":[{"type":"text","text":"Do NOT use the read tool and do NOT use bash or shell commands. Immediately use the edit tool to replace the literal text blue with green in settings.txt in the current directory. Do not read the file first. After the tool result, reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783611702550,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783611702551,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611702551,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783611703185,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783611703185,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783611703352,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -75,7 +75,7 @@ {"type":"assistant/chunk","seq":73,"time":1783611703969,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}}}} {"type":"assistant/chunk","seq":74,"time":1783611703969,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}}}} {"type":"assistant/chunk","seq":75,"time":1783611703969,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":76,"time":1783611703972,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the edit tool to replace \"blue\" with \"green\" in settings.txt without reading the file first, and then reply with just \"DONE\"."},{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"surfaceOp":"append"} +{"type":"assistant/message","seq":76,"time":1783611703972,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the edit tool to replace \"blue\" with \"green\" in settings.txt without reading the file first, and then reply with just \"DONE\"."},{"type":"tool-call","id":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3132,"outputTokens":115,"cacheReadTokens":0,"reasoningTokens":36}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75],"surfaceOp":"append"} {"type":"tool/call","seq":77,"time":1783611703972,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}} {"type":"tool/result","seq":78,"time":1783611703978,"data":{"turn":1,"step":1,"callId":"call_00_x0zlnXl5JOxLrAYL9y7P0119","content":[{"type":"text","text":"Error: edit requires reading \"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt\" first"}],"isError":true,"error":{"name":"FsError","code":"FS_NOT_OBSERVED"}},"sourceEventSeqs":[77],"surfaceOp":"append"} {"type":"step/end","seq":79,"time":1783611703978,"data":{"turn":1,"step":1}} @@ -142,7 +142,7 @@ {"type":"assistant/chunk","seq":140,"time":1783611705572,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}}}} {"type":"assistant/chunk","seq":141,"time":1783611705572,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":235,"outputTokens":89,"cacheReadTokens":3072,"reasoningTokens":44}}}} {"type":"assistant/chunk","seq":142,"time":1783611705572,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":143,"time":1783611705573,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The edit tool requires reading the file first. The user said \"Do not read the file first\" but the tool's own constraints require reading. I need to follow the tool requirements. Let me read the file first."},{"type":"tool-call","id":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}],"usage":{"inputTokens":235,"outputTokens":89,"cacheReadTokens":3072,"reasoningTokens":44}},"sourceEventSeqs":[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} +{"type":"assistant/message","seq":143,"time":1783611705573,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The edit tool requires reading the file first. The user said \"Do not read the file first\" but the tool's own constraints require reading. I need to follow the tool requirements. Let me read the file first."},{"type":"tool-call","id":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":235,"outputTokens":89,"cacheReadTokens":3072,"reasoningTokens":44}},"sourceEventSeqs":[81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} {"type":"tool/call","seq":144,"time":1783611705573,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","name":"read","arguments":"{\"file_path\": \"settings.txt\"}"}} {"type":"tool/result","seq":145,"time":1783611705579,"data":{"turn":1,"step":2,"callId":"call_00_tfr0gdIclW92oIEgi7NF0891","content":[{"type":"text","text":"/var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt\nfile\n\n1: color: blue\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[144],"surfaceOp":"append"} {"type":"step/end","seq":146,"time":1783611705579,"data":{"turn":1,"step":2}} @@ -223,7 +223,7 @@ {"type":"assistant/chunk","seq":221,"time":1783611707096,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}}}} {"type":"assistant/chunk","seq":222,"time":1783611707096,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":281,"outputTokens":119,"cacheReadTokens":3200,"reasoningTokens":40}}}} {"type":"assistant/chunk","seq":223,"time":1783611707096,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":224,"time":1783611707097,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file contains \"color: blue\". I need to replace \"blue\" with \"green\". The edit tool said it requires reading first — now I've read it, so the edit should work."},{"type":"tool-call","id":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"usage":{"inputTokens":281,"outputTokens":119,"cacheReadTokens":3200,"reasoningTokens":40}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223],"surfaceOp":"append"} +{"type":"assistant/message","seq":224,"time":1783611707097,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file contains \"color: blue\". I need to replace \"blue\" with \"green\". The edit tool said it requires reading first — now I've read it, so the edit should work."},{"type":"tool-call","id":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":281,"outputTokens":119,"cacheReadTokens":3200,"reasoningTokens":40}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223],"surfaceOp":"append"} {"type":"tool/call","seq":225,"time":1783611707097,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","name":"edit","arguments":"{\"file_path\": \"settings.txt\", \"old_string\": \"blue\", \"new_string\": \"green\"}"}} {"type":"tool/result","seq":226,"time":1783611707114,"data":{"turn":1,"step":3,"callId":"call_00_GVknJu2tksKkP4lALCwh0926","content":[{"type":"text","text":"The file /var/folders/2c/psb0_fmx7hbgz558xjt_f0l00000gn/T/acp-snap-cwd-QzoqnB/settings.txt has been updated successfully."}],"isError":false,"meta":{"diffs":[{"path":"settings.txt","oldText":"color: blue","newText":"color: green"}]}},"sourceEventSeqs":[225],"surfaceOp":"append"} {"type":"step/end","seq":227,"time":1783611707114,"data":{"turn":1,"step":3}} @@ -253,6 +253,6 @@ {"type":"assistant/chunk","seq":251,"time":1783611707952,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":252,"time":1783611707952,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":202,"outputTokens":20,"cacheReadTokens":3456,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":253,"time":1783611707952,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":254,"time":1783611707953,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The replacement was successful. I'll reply with just \"DONE\" as instructed."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":202,"outputTokens":20,"cacheReadTokens":3456,"reasoningTokens":17}},"sourceEventSeqs":[229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253],"surfaceOp":"append"} +{"type":"assistant/message","seq":254,"time":1783611707953,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The replacement was successful. I'll reply with just \"DONE\" as instructed."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":202,"outputTokens":20,"cacheReadTokens":3456,"reasoningTokens":17}},"sourceEventSeqs":[229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253],"surfaceOp":"append"} {"type":"step/end","seq":255,"time":1783611707953,"data":{"turn":1,"step":4}} {"type":"turn/end","seq":256,"time":1783611707953,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl index becc503c65..e587011cfd 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352099838,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352099839,"data":{"content":[{"type":"text","text":"Use the read tool (NOT bash) with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352099840,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352099841,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352099841,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352100468,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352100468,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352100587,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -89,7 +89,7 @@ {"type":"assistant/chunk","seq":87,"time":1783352101346,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}}}} {"type":"assistant/chunk","seq":88,"time":1783352101346,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2894,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":56}}}} {"type":"assistant/chunk","seq":89,"time":1783352101346,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":90,"time":1783352101348,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the read tool with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE.\n\nLet me first check the current directory, then read the file."},{"type":"tool-call","id":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}],"usage":{"inputTokens":2894,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":56}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89],"surfaceOp":"append"} +{"type":"assistant/message","seq":90,"time":1783352101348,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the read tool with offset 5 and limit 4 to read lines 5 through 8 of big.txt in the current directory. Then reply with exactly the single word DONE.\n\nLet me first check the current directory, then read the file."},{"type":"tool-call","id":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2894,"outputTokens":133,"cacheReadTokens":0,"reasoningTokens":56}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89],"surfaceOp":"append"} {"type":"tool/call","seq":91,"time":1783352101348,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","name":"read","arguments":"{\"file_path\": \"big.txt\", \"offset\": 5, \"limit\": 4}"}} {"type":"tool/result","seq":92,"time":1783352101353,"data":{"turn":1,"step":1,"callId":"call_00_GIZwZS9a7vhWTFCIc7Z35497","content":[{"type":"text","text":"/tmp/acp-snap-cwd-N9HCkt/big.txt\nfile\n\n5: line five\n6: line six\n7: line seven\n8: line eight\n\n(Showing lines 5-8 of 10. Use offset=9 to continue.)\n"}],"isError":false},"sourceEventSeqs":[91],"surfaceOp":"append"} {"type":"step/end","seq":93,"time":1783352101353,"data":{"turn":1,"step":1}} @@ -129,6 +129,6 @@ {"type":"assistant/chunk","seq":127,"time":1783352102357,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":128,"time":1783352102358,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":292,"outputTokens":30,"cacheReadTokens":2816,"reasoningTokens":27}}}} {"type":"assistant/chunk","seq":129,"time":1783352102358,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":130,"time":1783352102358,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The read tool returned lines 5 through 8 as expected. Now I need to reply with exactly the single word \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":292,"outputTokens":30,"cacheReadTokens":2816,"reasoningTokens":27}},"sourceEventSeqs":[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} +{"type":"assistant/message","seq":130,"time":1783352102358,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The read tool returned lines 5 through 8 as expected. Now I need to reply with exactly the single word \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":292,"outputTokens":30,"cacheReadTokens":2816,"reasoningTokens":27}},"sourceEventSeqs":[95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"step/end","seq":131,"time":1783352102358,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":132,"time":1783352102358,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl index 3af4b2ac61..81737364f8 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352072468,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352072469,"data":{"content":[{"type":"text","text":"Use the read tool (NOT bash) to read the file greeting.txt in the current directory, then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352072470,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352072471,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352072471,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352073089,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352073090,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352073210,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -51,7 +51,7 @@ {"type":"assistant/chunk","seq":49,"time":1783352073705,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}}}} {"type":"assistant/chunk","seq":50,"time":1783352073705,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2882,"outputTokens":75,"cacheReadTokens":0,"reasoningTokens":29}}}} {"type":"assistant/chunk","seq":51,"time":1783352073705,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":52,"time":1783352073708,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read the file greeting.txt using the read tool (not bash), then reply with exactly the single word \"DONE\"."},{"type":"tool-call","id":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"usage":{"inputTokens":2882,"outputTokens":75,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} +{"type":"assistant/message","seq":52,"time":1783352073708,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to read the file greeting.txt using the read tool (not bash), then reply with exactly the single word \"DONE\"."},{"type":"tool-call","id":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2882,"outputTokens":75,"cacheReadTokens":0,"reasoningTokens":29}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352073709,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}} {"type":"tool/result","seq":54,"time":1783352073717,"data":{"turn":1,"step":1,"callId":"call_00_hHPZCcivsIkXAGS9jTGy8417","content":[{"type":"text","text":"/tmp/acp-snap-cwd-PEETkS/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":55,"time":1783352073718,"data":{"turn":1,"step":1}} @@ -101,6 +101,6 @@ {"type":"assistant/chunk","seq":99,"time":1783352075045,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":100,"time":1783352075045,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":200,"outputTokens":40,"cacheReadTokens":2816,"reasoningTokens":37}}}} {"type":"assistant/chunk","seq":101,"time":1783352075045,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":102,"time":1783352075045,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to read the file and then reply with exactly the single word \"DONE\". I've read the file. Now I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":200,"outputTokens":40,"cacheReadTokens":2816,"reasoningTokens":37}},"sourceEventSeqs":[57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101],"surfaceOp":"append"} +{"type":"assistant/message","seq":102,"time":1783352075045,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to read the file and then reply with exactly the single word \"DONE\". I've read the file. Now I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":200,"outputTokens":40,"cacheReadTokens":2816,"reasoningTokens":37}},"sourceEventSeqs":[57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101],"surfaceOp":"append"} {"type":"step/end","seq":103,"time":1783352075046,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":104,"time":1783352075046,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/session.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/session.jsonl index 9552a7a8f9..e53f4b3da3 100644 --- a/examples/acp-agent/tests/snapshots/fs-terminal-card/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352050753,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352050753,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo TERMINAL_OK. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352050755,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352050756,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352050756,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352051421,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352051422,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352051590,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -58,7 +58,7 @@ {"type":"assistant/chunk","seq":56,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}}}} {"type":"assistant/chunk","seq":57,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":58,"time":1783352052118,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":59,"time":1783352052121,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}],"usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58],"surfaceOp":"append"} +{"type":"assistant/message","seq":59,"time":1783352052121,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2877,"outputTokens":90,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58],"surfaceOp":"append"} {"type":"tool/call","seq":60,"time":1783352052121,"data":{"turn":1,"step":1,"callId":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","name":"bash","arguments":"{\"command\": \"echo TERMINAL_OK\", \"description\": \"Echo TERMINAL_OK to verify terminal access\"}"}} {"type":"tool/result","seq":61,"time":1783352052136,"data":{"turn":1,"step":1,"callId":"call_00_fkbBRJsUrGKd1pWVc4Gn8233","content":[{"type":"text","text":"TERMINAL_OK\n"}],"isError":false},"sourceEventSeqs":[60],"surfaceOp":"append"} {"type":"step/end","seq":62,"time":1783352052137,"data":{"turn":1,"step":1}} @@ -93,6 +93,6 @@ {"type":"assistant/chunk","seq":91,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":92,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}}}} {"type":"assistant/chunk","seq":93,"time":1783352052986,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":94,"time":1783352052987,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"surfaceOp":"append"} +{"type":"assistant/message","seq":94,"time":1783352052987,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully and output \"TERMINAL_OK\". I should now reply with just \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":168,"outputTokens":25,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93],"surfaceOp":"append"} {"type":"step/end","seq":95,"time":1783352052987,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":96,"time":1783352052987,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl index 47627ae7a5..08ec0f1323 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352092220,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352092221,"data":{"content":[{"type":"text","text":"First use the read tool to read data.txt in the current directory. Then use the write tool (NOT bash) to replace its entire contents with exactly the single line: replaced. Then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352092223,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352092223,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352092223,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352092902,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352092902,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352093090,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -63,7 +63,7 @@ {"type":"assistant/chunk","seq":61,"time":1783352093614,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}}}} {"type":"assistant/chunk","seq":62,"time":1783352093614,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2899,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":42}}}} {"type":"assistant/chunk","seq":63,"time":1783352093614,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":64,"time":1783352093617,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read data.txt using the read tool\n2. Replace its entire contents with exactly \"replaced\" using the write tool\n3. Reply with exactly \"DONE\""},{"type":"tool-call","id":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}],"usage":{"inputTokens":2899,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":42}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"} +{"type":"assistant/message","seq":64,"time":1783352093617,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read data.txt using the read tool\n2. Replace its entire contents with exactly \"replaced\" using the write tool\n3. Reply with exactly \"DONE\""},{"type":"tool-call","id":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2899,"outputTokens":87,"cacheReadTokens":0,"reasoningTokens":42}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63],"surfaceOp":"append"} {"type":"tool/call","seq":65,"time":1783352093617,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","name":"read","arguments":"{\"file_path\": \"data.txt\"}"}} {"type":"tool/result","seq":66,"time":1783352093624,"data":{"turn":1,"step":1,"callId":"call_00_n4eRJuGoxNR07svgNtk82243","content":[{"type":"text","text":"/tmp/acp-snap-cwd-hH2sGY/data.txt\nfile\n\n1: original contents\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[65],"surfaceOp":"append"} {"type":"step/end","seq":67,"time":1783352093624,"data":{"turn":1,"step":1}} @@ -112,7 +112,7 @@ {"type":"assistant/chunk","seq":110,"time":1783352094988,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}}}} {"type":"assistant/chunk","seq":111,"time":1783352094988,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":228,"outputTokens":79,"cacheReadTokens":2816,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":112,"time":1783352094988,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":113,"time":1783352094988,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"original contents\". Now I'll replace it with \"replaced\"."},{"type":"tool-call","id":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}],"usage":{"inputTokens":228,"outputTokens":79,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} +{"type":"assistant/message","seq":113,"time":1783352094988,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"original contents\". Now I'll replace it with \"replaced\"."},{"type":"tool-call","id":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":228,"outputTokens":79,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} {"type":"tool/call","seq":114,"time":1783352094988,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","name":"write","arguments":"{\"file_path\": \"data.txt\", \"content\": \"replaced\"}"}} {"type":"tool/result","seq":115,"time":1783352094995,"data":{"turn":1,"step":2,"callId":"call_00_N23EvXjDo4c8enyWpIUq4043","content":[{"type":"text","text":"/tmp/acp-snap-cwd-hH2sGY/data.txt\nfile\n\nUpdated file\n"}],"isError":false,"meta":{"diffs":[{"path":"data.txt","oldText":"original contents","newText":"replaced"}]}},"sourceEventSeqs":[114],"surfaceOp":"append"} {"type":"step/end","seq":116,"time":1783352094995,"data":{"turn":1,"step":2}} @@ -141,6 +141,6 @@ {"type":"assistant/chunk","seq":139,"time":1783352096309,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":140,"time":1783352096309,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":225,"outputTokens":19,"cacheReadTokens":2944,"reasoningTokens":16}}}} {"type":"assistant/chunk","seq":141,"time":1783352096309,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":142,"time":1783352096310,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file has been replaced successfully. Now I just reply with \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":225,"outputTokens":19,"cacheReadTokens":2944,"reasoningTokens":16}},"sourceEventSeqs":[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141],"surfaceOp":"append"} +{"type":"assistant/message","seq":142,"time":1783352096310,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The file has been replaced successfully. Now I just reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":225,"outputTokens":19,"cacheReadTokens":2944,"reasoningTokens":16}},"sourceEventSeqs":[118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141],"surfaceOp":"append"} {"type":"step/end","seq":143,"time":1783352096310,"data":{"turn":1,"step":3}} {"type":"turn/end","seq":144,"time":1783352096310,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl index 7e4b2dda01..59ba868817 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/session.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352078754,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352078754,"data":{"content":[{"type":"text","text":"Use the write tool (NOT bash) to create a file named notes.txt in the current directory containing exactly the single line: hello world. Then reply with exactly the single word DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352078756,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352078756,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352078756,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352079254,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352079254,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352079333,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -60,7 +60,7 @@ {"type":"assistant/chunk","seq":58,"time":1783352079886,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}}}} {"type":"assistant/chunk","seq":59,"time":1783352079886,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2891,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":60,"time":1783352079886,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":61,"time":1783352079888,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to create a file named notes.txt with the content \"hello world\" using the write tool, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}],"usage":{"inputTokens":2891,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":30}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} +{"type":"assistant/message","seq":61,"time":1783352079888,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to create a file named notes.txt with the content \"hello world\" using the write tool, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2891,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":30}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"tool/call","seq":62,"time":1783352079888,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","name":"write","arguments":"{\"file_path\": \"notes.txt\", \"content\": \"hello world\"}"}} {"type":"tool/result","seq":63,"time":1783352079897,"data":{"turn":1,"step":1,"callId":"call_00_APMUCJJm9lrTSlVbg6dB0185","content":[{"type":"text","text":"/tmp/acp-snap-cwd-sNvn5N/notes.txt\nfile\n\nCreated file\n"}],"isError":false},"sourceEventSeqs":[62],"surfaceOp":"append"} {"type":"step/end","seq":64,"time":1783352079898,"data":{"turn":1,"step":1}} @@ -90,6 +90,6 @@ {"type":"assistant/chunk","seq":88,"time":1783352081056,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":89,"time":1783352081056,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":214,"outputTokens":20,"cacheReadTokens":2816,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":90,"time":1783352081056,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":91,"time":1783352081057,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file has been created. Now I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":214,"outputTokens":20,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90],"surfaceOp":"append"} +{"type":"assistant/message","seq":91,"time":1783352081057,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file has been created. Now I just need to reply with \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":214,"outputTokens":20,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90],"surfaceOp":"append"} {"type":"step/end","seq":92,"time":1783352081057,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":93,"time":1783352081057,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl index 1a72a2e5ef..07bd28c2cd 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352177366,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352177367,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352177368,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352177372,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352177372,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352178017,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352178018,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352178131,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -59,7 +59,7 @@ {"type":"assistant/chunk","seq":57,"time":1783352178592,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_qcIzLImnOm5qiKOBJUqY5047","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}}}} {"type":"assistant/chunk","seq":58,"time":1783352178592,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2879,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":59,"time":1783352178592,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":60,"time":1783352178594,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_qcIzLImnOm5qiKOBJUqY5047","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}],"usage":{"inputTokens":2879,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59],"surfaceOp":"append"} +{"type":"assistant/message","seq":60,"time":1783352178594,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_qcIzLImnOm5qiKOBJUqY5047","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2879,"outputTokens":91,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59],"surfaceOp":"append"} {"type":"tool/call","seq":61,"time":1783352178594,"data":{"turn":1,"step":1,"callId":"call_00_qcIzLImnOm5qiKOBJUqY5047","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO to stdout\"}"}} {"type":"hook/invoked","seq":62,"time":1783352178614,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":63,"time":1783352178624,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":9.49630100000013}} @@ -130,7 +130,7 @@ {"type":"assistant/chunk","seq":128,"time":1783352180488,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_nzhKxYvCYj8OqI2tjOKb8506","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO command\"}"}}}} {"type":"assistant/chunk","seq":129,"time":1783352180489,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":178,"outputTokens":99,"cacheReadTokens":2816,"reasoningTokens":32}}}} {"type":"assistant/chunk","seq":130,"time":1783352180489,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":131,"time":1783352180489,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The tool output was rejected by policy, which says \"rerun with a summary instead\". Let me try again with a description that summarizes what we're doing."},{"type":"tool-call","id":"call_00_nzhKxYvCYj8OqI2tjOKb8506","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO command\"}"}],"usage":{"inputTokens":178,"outputTokens":99,"cacheReadTokens":2816,"reasoningTokens":32}},"sourceEventSeqs":[67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"surfaceOp":"append"} +{"type":"assistant/message","seq":131,"time":1783352180489,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The tool output was rejected by policy, which says \"rerun with a summary instead\". Let me try again with a description that summarizes what we're doing."},{"type":"tool-call","id":"call_00_nzhKxYvCYj8OqI2tjOKb8506","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO command\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":178,"outputTokens":99,"cacheReadTokens":2816,"reasoningTokens":32}},"sourceEventSeqs":[67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130],"surfaceOp":"append"} {"type":"tool/call","seq":132,"time":1783352180489,"data":{"turn":1,"step":2,"callId":"call_00_nzhKxYvCYj8OqI2tjOKb8506","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO command\"}"}} {"type":"hook/invoked","seq":133,"time":1783352180524,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:2","matcher":"bash"}} {"type":"hook/result","seq":134,"time":1783352180530,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:2","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":6.622174999999515}} @@ -182,7 +182,7 @@ {"type":"assistant/chunk","seq":180,"time":1783352181933,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_VumDDhhB4n5507EUXq650912","name":"bash","arguments":"{\"description\": \"Print HELLO to stdout\", \"command\": \"echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":181,"time":1783352181933,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":173,"outputTokens":80,"cacheReadTokens":2944,"reasoningTokens":13}}}} {"type":"assistant/chunk","seq":182,"time":1783352181933,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":183,"time":1783352181934,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The tool keeps rejecting. Let me try a slightly different description."},{"type":"tool-call","id":"call_00_VumDDhhB4n5507EUXq650912","name":"bash","arguments":"{\"description\": \"Print HELLO to stdout\", \"command\": \"echo HELLO\"}"}],"usage":{"inputTokens":173,"outputTokens":80,"cacheReadTokens":2944,"reasoningTokens":13}},"sourceEventSeqs":[138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182],"surfaceOp":"append"} +{"type":"assistant/message","seq":183,"time":1783352181934,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"The tool keeps rejecting. Let me try a slightly different description."},{"type":"tool-call","id":"call_00_VumDDhhB4n5507EUXq650912","name":"bash","arguments":"{\"description\": \"Print HELLO to stdout\", \"command\": \"echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":173,"outputTokens":80,"cacheReadTokens":2944,"reasoningTokens":13}},"sourceEventSeqs":[138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182],"surfaceOp":"append"} {"type":"tool/call","seq":184,"time":1783352181934,"data":{"turn":1,"step":3,"callId":"call_00_VumDDhhB4n5507EUXq650912","name":"bash","arguments":"{\"description\": \"Print HELLO to stdout\", \"command\": \"echo HELLO\"}"}} {"type":"hook/invoked","seq":185,"time":1783352181945,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:3","matcher":"bash"}} {"type":"hook/result","seq":186,"time":1783352181953,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:3","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":7.827785000000404}} @@ -234,7 +234,7 @@ {"type":"assistant/chunk","seq":232,"time":1783352183049,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_i5NCqPa2LGAy1wk8uJQR2369","name":"bash","arguments":"{\"description\": \"echo HELLO\", \"command\": \"echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":233,"time":1783352183049,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":149,"outputTokens":80,"cacheReadTokens":3072,"reasoningTokens":15}}}} {"type":"assistant/chunk","seq":234,"time":1783352183049,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":235,"time":1783352183049,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The policy keeps rejecting my attempts. Let me try a very short description."},{"type":"tool-call","id":"call_00_i5NCqPa2LGAy1wk8uJQR2369","name":"bash","arguments":"{\"description\": \"echo HELLO\", \"command\": \"echo HELLO\"}"}],"usage":{"inputTokens":149,"outputTokens":80,"cacheReadTokens":3072,"reasoningTokens":15}},"sourceEventSeqs":[190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234],"surfaceOp":"append"} +{"type":"assistant/message","seq":235,"time":1783352183049,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The policy keeps rejecting my attempts. Let me try a very short description."},{"type":"tool-call","id":"call_00_i5NCqPa2LGAy1wk8uJQR2369","name":"bash","arguments":"{\"description\": \"echo HELLO\", \"command\": \"echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":149,"outputTokens":80,"cacheReadTokens":3072,"reasoningTokens":15}},"sourceEventSeqs":[190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234],"surfaceOp":"append"} {"type":"tool/call","seq":236,"time":1783352183050,"data":{"turn":1,"step":4,"callId":"call_00_i5NCqPa2LGAy1wk8uJQR2369","name":"bash","arguments":"{\"description\": \"echo HELLO\", \"command\": \"echo HELLO\"}"}} {"type":"hook/invoked","seq":237,"time":1783352183069,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:4","matcher":"bash"}} {"type":"hook/result","seq":238,"time":1783352183077,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:4","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":8.41934399999991}} @@ -280,7 +280,7 @@ {"type":"assistant/chunk","seq":278,"time":1783352184233,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_0IuOIk6iuG6ZesROSyAM3669","name":"bash","arguments":"{\"command\": \"echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":279,"time":1783352184233,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":125,"outputTokens":66,"cacheReadTokens":3200,"reasoningTokens":20}}}} {"type":"assistant/chunk","seq":280,"time":1783352184233,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":281,"time":1783352184233,"data":{"turn":1,"step":5,"content":[{"type":"reasoning","text":"Hmm, the policy keeps rejecting. Let me try without the description field, just the command."},{"type":"tool-call","id":"call_00_0IuOIk6iuG6ZesROSyAM3669","name":"bash","arguments":"{\"command\": \"echo HELLO\"}"}],"usage":{"inputTokens":125,"outputTokens":66,"cacheReadTokens":3200,"reasoningTokens":20}},"sourceEventSeqs":[242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280],"surfaceOp":"append"} +{"type":"assistant/message","seq":281,"time":1783352184233,"data":{"turn":1,"step":5,"content":[{"type":"reasoning","text":"Hmm, the policy keeps rejecting. Let me try without the description field, just the command."},{"type":"tool-call","id":"call_00_0IuOIk6iuG6ZesROSyAM3669","name":"bash","arguments":"{\"command\": \"echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":125,"outputTokens":66,"cacheReadTokens":3200,"reasoningTokens":20}},"sourceEventSeqs":[242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280],"surfaceOp":"append"} {"type":"tool/call","seq":282,"time":1783352184233,"data":{"turn":1,"step":5,"callId":"call_00_0IuOIk6iuG6ZesROSyAM3669","name":"bash","arguments":"{\"command\": \"echo HELLO\"}"}} {"type":"hook/invoked","seq":283,"time":1783352184234,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:5","matcher":"bash"}} {"type":"hook/result","seq":284,"time":1783352184243,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:5","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":8.810661999999866}} @@ -428,7 +428,7 @@ {"type":"assistant/chunk","seq":426,"time":1783352186527,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_mGqWmySh60rWKNcyVBFk2747","name":"bash","arguments":"{\"description\": \"Echo the string HELLO\", \"command\": \"echo \\\"HELLO\\\"\"}"}}}} {"type":"assistant/chunk","seq":427,"time":1783352186527,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":215,"outputTokens":176,"cacheReadTokens":3200,"reasoningTokens":106}}}} {"type":"assistant/chunk","seq":428,"time":1783352186527,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":429,"time":1783352186527,"data":{"turn":1,"step":6,"content":[{"type":"reasoning","text":"The tool is consistently being rejected by policy. The policy says \"rerun with a summary instead\" - it seems the content of the output (which would be \"HELLO\") is being blocked. Let me try a different approach - maybe I need to use a different command or approach to satisfy the policy.\n\nWait, the user explicitly asked me to \"run exactly: echo HELLO\" and \"Report the tool result you got back verbatim\". Let me try `echo \"HELLO\"` with quotes."},{"type":"tool-call","id":"call_00_mGqWmySh60rWKNcyVBFk2747","name":"bash","arguments":"{\"description\": \"Echo the string HELLO\", \"command\": \"echo \\\"HELLO\\\"\"}"}],"usage":{"inputTokens":215,"outputTokens":176,"cacheReadTokens":3200,"reasoningTokens":106}},"sourceEventSeqs":[288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339,340,341,342,343,344,345,346,347,348,349,350,351,352,353,354,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370,371,372,373,374,375,376,377,378,379,380,381,382,383,384,385,386,387,388,389,390,391,392,393,394,395,396,397,398,399,400,401,402,403,404,405,406,407,408,409,410,411,412,413,414,415,416,417,418,419,420,421,422,423,424,425,426,427,428],"surfaceOp":"append"} +{"type":"assistant/message","seq":429,"time":1783352186527,"data":{"turn":1,"step":6,"content":[{"type":"reasoning","text":"The tool is consistently being rejected by policy. The policy says \"rerun with a summary instead\" - it seems the content of the output (which would be \"HELLO\") is being blocked. Let me try a different approach - maybe I need to use a different command or approach to satisfy the policy.\n\nWait, the user explicitly asked me to \"run exactly: echo HELLO\" and \"Report the tool result you got back verbatim\". Let me try `echo \"HELLO\"` with quotes."},{"type":"tool-call","id":"call_00_mGqWmySh60rWKNcyVBFk2747","name":"bash","arguments":"{\"description\": \"Echo the string HELLO\", \"command\": \"echo \\\"HELLO\\\"\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":215,"outputTokens":176,"cacheReadTokens":3200,"reasoningTokens":106}},"sourceEventSeqs":[288,289,290,291,292,293,294,295,296,297,298,299,300,301,302,303,304,305,306,307,308,309,310,311,312,313,314,315,316,317,318,319,320,321,322,323,324,325,326,327,328,329,330,331,332,333,334,335,336,337,338,339,340,341,342,343,344,345,346,347,348,349,350,351,352,353,354,355,356,357,358,359,360,361,362,363,364,365,366,367,368,369,370,371,372,373,374,375,376,377,378,379,380,381,382,383,384,385,386,387,388,389,390,391,392,393,394,395,396,397,398,399,400,401,402,403,404,405,406,407,408,409,410,411,412,413,414,415,416,417,418,419,420,421,422,423,424,425,426,427,428],"surfaceOp":"append"} {"type":"tool/call","seq":430,"time":1783352186527,"data":{"turn":1,"step":6,"callId":"call_00_mGqWmySh60rWKNcyVBFk2747","name":"bash","arguments":"{\"description\": \"Echo the string HELLO\", \"command\": \"echo \\\"HELLO\\\"\"}"}} {"type":"hook/invoked","seq":431,"time":1783352186538,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:6","matcher":"bash"}} {"type":"hook/result","seq":432,"time":1783352186545,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:6","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":6.910448999999062}} @@ -549,7 +549,7 @@ {"type":"assistant/chunk","seq":547,"time":1783352188511,"data":{"turn":1,"step":7,"chunk":{"type":"block-end","index":2,"block":{"type":"tool-call","id":"call_00_Y371DzUR0Pz6IrkO8qgB9050","name":"bash","arguments":"{\"description\": \"Echo test message\", \"command\": \"echo \\\"TEST\\\"\"}"}}}} {"type":"assistant/chunk","seq":548,"time":1783352188511,"data":{"turn":1,"step":7,"chunk":{"type":"usage","usage":{"inputTokens":287,"outputTokens":146,"cacheReadTokens":3328,"reasoningTokens":70}}}} {"type":"assistant/chunk","seq":549,"time":1783352188512,"data":{"turn":1,"step":7,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":550,"time":1783352188512,"data":{"turn":1,"step":7,"content":[{"type":"reasoning","text":"The policy is blocking the output \"HELLO\" - it seems like the word \"HELLO\" (which might be a misspelling of \"HELLO\" that looks like \"HELL\" with \"O\") could be triggering some content filter. Let me try a completely different word to see if the tool works at all."},{"type":"text","text":"Let me try a different word to verify the tool works:"},{"type":"tool-call","id":"call_00_Y371DzUR0Pz6IrkO8qgB9050","name":"bash","arguments":"{\"description\": \"Echo test message\", \"command\": \"echo \\\"TEST\\\"\"}"}],"usage":{"inputTokens":287,"outputTokens":146,"cacheReadTokens":3328,"reasoningTokens":70}},"sourceEventSeqs":[436,437,438,439,440,441,442,443,444,445,446,447,448,449,450,451,452,453,454,455,456,457,458,459,460,461,462,463,464,465,466,467,468,469,470,471,472,473,474,475,476,477,478,479,480,481,482,483,484,485,486,487,488,489,490,491,492,493,494,495,496,497,498,499,500,501,502,503,504,505,506,507,508,509,510,511,512,513,514,515,516,517,518,519,520,521,522,523,524,525,526,527,528,529,530,531,532,533,534,535,536,537,538,539,540,541,542,543,544,545,546,547,548,549],"surfaceOp":"append"} +{"type":"assistant/message","seq":550,"time":1783352188512,"data":{"turn":1,"step":7,"content":[{"type":"reasoning","text":"The policy is blocking the output \"HELLO\" - it seems like the word \"HELLO\" (which might be a misspelling of \"HELLO\" that looks like \"HELL\" with \"O\") could be triggering some content filter. Let me try a completely different word to see if the tool works at all."},{"type":"text","text":"Let me try a different word to verify the tool works:"},{"type":"tool-call","id":"call_00_Y371DzUR0Pz6IrkO8qgB9050","name":"bash","arguments":"{\"description\": \"Echo test message\", \"command\": \"echo \\\"TEST\\\"\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":287,"outputTokens":146,"cacheReadTokens":3328,"reasoningTokens":70}},"sourceEventSeqs":[436,437,438,439,440,441,442,443,444,445,446,447,448,449,450,451,452,453,454,455,456,457,458,459,460,461,462,463,464,465,466,467,468,469,470,471,472,473,474,475,476,477,478,479,480,481,482,483,484,485,486,487,488,489,490,491,492,493,494,495,496,497,498,499,500,501,502,503,504,505,506,507,508,509,510,511,512,513,514,515,516,517,518,519,520,521,522,523,524,525,526,527,528,529,530,531,532,533,534,535,536,537,538,539,540,541,542,543,544,545,546,547,548,549],"surfaceOp":"append"} {"type":"tool/call","seq":551,"time":1783352188512,"data":{"turn":1,"step":7,"callId":"call_00_Y371DzUR0Pz6IrkO8qgB9050","name":"bash","arguments":"{\"description\": \"Echo test message\", \"command\": \"echo \\\"TEST\\\"\"}"}} {"type":"hook/invoked","seq":552,"time":1783352188524,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:7","matcher":"bash"}} {"type":"hook/result","seq":553,"time":1783352188532,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:7","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":7.573905000001105}} @@ -605,7 +605,7 @@ {"type":"assistant/chunk","seq":603,"time":1783352189858,"data":{"turn":1,"step":8,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_S2XENjVanaHtBn3RZfhO7965","name":"bash","arguments":"{\"description\": \"Print working directory\", \"command\": \"pwd\"}"}}}} {"type":"assistant/chunk","seq":604,"time":1783352189858,"data":{"turn":1,"step":8,"chunk":{"type":"usage","usage":{"inputTokens":201,"outputTokens":84,"cacheReadTokens":3584,"reasoningTokens":22}}}} {"type":"assistant/chunk","seq":605,"time":1783352189858,"data":{"turn":1,"step":8,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":606,"time":1783352189859,"data":{"turn":1,"step":8,"content":[{"type":"reasoning","text":"Even \"TEST\" is rejected. Let me try a simpler command like `pwd` or `ls`."},{"type":"tool-call","id":"call_00_S2XENjVanaHtBn3RZfhO7965","name":"bash","arguments":"{\"description\": \"Print working directory\", \"command\": \"pwd\"}"}],"usage":{"inputTokens":201,"outputTokens":84,"cacheReadTokens":3584,"reasoningTokens":22}},"sourceEventSeqs":[557,558,559,560,561,562,563,564,565,566,567,568,569,570,571,572,573,574,575,576,577,578,579,580,581,582,583,584,585,586,587,588,589,590,591,592,593,594,595,596,597,598,599,600,601,602,603,604,605],"surfaceOp":"append"} +{"type":"assistant/message","seq":606,"time":1783352189859,"data":{"turn":1,"step":8,"content":[{"type":"reasoning","text":"Even \"TEST\" is rejected. Let me try a simpler command like `pwd` or `ls`."},{"type":"tool-call","id":"call_00_S2XENjVanaHtBn3RZfhO7965","name":"bash","arguments":"{\"description\": \"Print working directory\", \"command\": \"pwd\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":201,"outputTokens":84,"cacheReadTokens":3584,"reasoningTokens":22}},"sourceEventSeqs":[557,558,559,560,561,562,563,564,565,566,567,568,569,570,571,572,573,574,575,576,577,578,579,580,581,582,583,584,585,586,587,588,589,590,591,592,593,594,595,596,597,598,599,600,601,602,603,604,605],"surfaceOp":"append"} {"type":"tool/call","seq":607,"time":1783352189859,"data":{"turn":1,"step":8,"callId":"call_00_S2XENjVanaHtBn3RZfhO7965","name":"bash","arguments":"{\"description\": \"Print working directory\", \"command\": \"pwd\"}"}} {"type":"hook/invoked","seq":608,"time":1783352189876,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:8","matcher":"bash"}} {"type":"hook/result","seq":609,"time":1783352189883,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:8","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by policy: rerun with a summary instead","durationMs":7.748225999999704}} @@ -747,6 +747,6 @@ {"type":"assistant/chunk","seq":745,"time":1783352192246,"data":{"turn":1,"step":9,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"I'm unable to run the `echo HELLO` command via the bash tool — every invocation is being rejected by the policy with the message \"tool output rejected by policy: rerun with a summary instead\". This appears to be a systemic policy restriction on the bash tool in this environment, as even simple commands like `pwd` and `echo \"TEST\"` are blocked.\n\nI cannot produce the tool result you asked for because the bash tool is not currently available for use."}}}} {"type":"assistant/chunk","seq":746,"time":1783352192246,"data":{"turn":1,"step":9,"chunk":{"type":"usage","usage":{"inputTokens":181,"outputTokens":130,"cacheReadTokens":3712,"reasoningTokens":31}}}} {"type":"assistant/chunk","seq":747,"time":1783352192246,"data":{"turn":1,"step":9,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":748,"time":1783352192247,"data":{"turn":1,"step":9,"content":[{"type":"reasoning","text":"All bash commands are being rejected. This seems like a system-level policy issue where the bash tool is blocked entirely. Let me report this to the user."},{"type":"text","text":"I'm unable to run the `echo HELLO` command via the bash tool — every invocation is being rejected by the policy with the message \"tool output rejected by policy: rerun with a summary instead\". This appears to be a systemic policy restriction on the bash tool in this environment, as even simple commands like `pwd` and `echo \"TEST\"` are blocked.\n\nI cannot produce the tool result you asked for because the bash tool is not currently available for use."}],"usage":{"inputTokens":181,"outputTokens":130,"cacheReadTokens":3712,"reasoningTokens":31}},"sourceEventSeqs":[613,614,615,616,617,618,619,620,621,622,623,624,625,626,627,628,629,630,631,632,633,634,635,636,637,638,639,640,641,642,643,644,645,646,647,648,649,650,651,652,653,654,655,656,657,658,659,660,661,662,663,664,665,666,667,668,669,670,671,672,673,674,675,676,677,678,679,680,681,682,683,684,685,686,687,688,689,690,691,692,693,694,695,696,697,698,699,700,701,702,703,704,705,706,707,708,709,710,711,712,713,714,715,716,717,718,719,720,721,722,723,724,725,726,727,728,729,730,731,732,733,734,735,736,737,738,739,740,741,742,743,744,745,746,747],"surfaceOp":"append"} +{"type":"assistant/message","seq":748,"time":1783352192247,"data":{"turn":1,"step":9,"content":[{"type":"reasoning","text":"All bash commands are being rejected. This seems like a system-level policy issue where the bash tool is blocked entirely. Let me report this to the user."},{"type":"text","text":"I'm unable to run the `echo HELLO` command via the bash tool — every invocation is being rejected by the policy with the message \"tool output rejected by policy: rerun with a summary instead\". This appears to be a systemic policy restriction on the bash tool in this environment, as even simple commands like `pwd` and `echo \"TEST\"` are blocked.\n\nI cannot produce the tool result you asked for because the bash tool is not currently available for use."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":181,"outputTokens":130,"cacheReadTokens":3712,"reasoningTokens":31}},"sourceEventSeqs":[613,614,615,616,617,618,619,620,621,622,623,624,625,626,627,628,629,630,631,632,633,634,635,636,637,638,639,640,641,642,643,644,645,646,647,648,649,650,651,652,653,654,655,656,657,658,659,660,661,662,663,664,665,666,667,668,669,670,671,672,673,674,675,676,677,678,679,680,681,682,683,684,685,686,687,688,689,690,691,692,693,694,695,696,697,698,699,700,701,702,703,704,705,706,707,708,709,710,711,712,713,714,715,716,717,718,719,720,721,722,723,724,725,726,727,728,729,730,731,732,733,734,735,736,737,738,739,740,741,742,743,744,745,746,747],"surfaceOp":"append"} {"type":"step/end","seq":749,"time":1783352192247,"data":{"turn":1,"step":9}} {"type":"turn/end","seq":750,"time":1783352192247,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl index 6c98868284..2e167db28c 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352196662,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352196662,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352196664,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352196664,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352196664,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352197315,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352197315,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352197457,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -57,7 +57,7 @@ {"type":"assistant/chunk","seq":55,"time":1783352197953,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_HbCMzTslWBZTSphWN0z97382","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":56,"time":1783352197953,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":57,"time":1783352197954,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":58,"time":1783352197956,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_HbCMzTslWBZTSphWN0z97382","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} +{"type":"assistant/message","seq":58,"time":1783352197956,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_HbCMzTslWBZTSphWN0z97382","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} {"type":"tool/call","seq":59,"time":1783352197956,"data":{"turn":1,"step":1,"callId":"call_00_HbCMzTslWBZTSphWN0z97382","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}} {"type":"hook/invoked","seq":60,"time":1783352197968,"data":{"turn":1,"point":"PostToolUse","dialect":"claude","handlerId":"claude:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":61,"time":1783352197976,"data":{"turn":1,"point":"PostToolUse","handlerId":"claude:PostToolUse:1","decision":"pass","exitCode":0,"durationMs":7.404540999999881}} @@ -121,6 +121,6 @@ {"type":"assistant/chunk","seq":119,"time":1783352199410,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result was:\n\n```\nHELLO\n```\n\nIt completed successfully with exit code 0."}}}} {"type":"assistant/chunk","seq":120,"time":1783352199411,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":188,"outputTokens":51,"cacheReadTokens":2816,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":121,"time":1783352199411,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":122,"time":1783352199411,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to report the tool result verbatim. The result was \"HELLO\" with an exit code of 0 (success)."},{"type":"text","text":"The tool result was:\n\n```\nHELLO\n```\n\nIt completed successfully with exit code 0."}],"usage":{"inputTokens":188,"outputTokens":51,"cacheReadTokens":2816,"reasoningTokens":30}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"surfaceOp":"append"} +{"type":"assistant/message","seq":122,"time":1783352199411,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to report the tool result verbatim. The result was \"HELLO\" with an exit code of 0 (success)."},{"type":"text","text":"The tool result was:\n\n```\nHELLO\n```\n\nIt completed successfully with exit code 0."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":188,"outputTokens":51,"cacheReadTokens":2816,"reasoningTokens":30}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121],"surfaceOp":"append"} {"type":"step/end","seq":123,"time":1783352199411,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":124,"time":1783352199412,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index 46a5e135a6..18c5510b8a 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352171519,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352171520,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352171527,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352171528,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352171528,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352171991,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352171991,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352172088,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -51,7 +51,7 @@ {"type":"assistant/chunk","seq":49,"time":1783352172555,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":50,"time":1783352172555,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":51,"time":1783352172555,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":52,"time":1783352172557,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}],"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} +{"type":"assistant/message","seq":52,"time":1783352172557,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} @@ -108,6 +108,6 @@ {"type":"assistant/chunk","seq":106,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}}}} {"type":"assistant/chunk","seq":107,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}}}} {"type":"assistant/chunk","seq":108,"time":1783352173964,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":109,"time":1783352173964,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool returned an error saying it requires manual approval in this session. I'll report this verbatim."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}],"usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} +{"type":"assistant/message","seq":109,"time":1783352173964,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool returned an error saying it requires manual approval in this session. I'll report this verbatim."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash requires manual approval in this session\n```"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":166,"outputTokens":45,"cacheReadTokens":2816,"reasoningTokens":22}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} {"type":"step/end","seq":110,"time":1783352173964,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":111,"time":1783352173965,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl index b8f30ee327..9633075e5b 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352165195,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352165196,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352165198,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352165199,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352165199,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352165899,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352165899,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352166048,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -51,7 +51,7 @@ {"type":"assistant/chunk","seq":49,"time":1783352166512,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":50,"time":1783352166512,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":51,"time":1783352166512,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":52,"time":1783352166514,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} +{"type":"assistant/message","seq":52,"time":1783352166514,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352166514,"data":{"turn":1,"step":1,"callId":"call_00_JliP571Bh0QQ8QExbSPk0080","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352166515,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352166528,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"block","exitCode":2,"stderrSummary":"bash is disabled by policy in this session","durationMs":12.367074000000684}} @@ -115,6 +115,6 @@ {"type":"assistant/chunk","seq":113,"time":1783352167933,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}}}} {"type":"assistant/chunk","seq":114,"time":1783352167933,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21}}}} {"type":"assistant/chunk","seq":115,"time":1783352167933,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":116,"time":1783352167934,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool is disabled by policy. I need to report this error verbatim back to the user."},{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}],"usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115],"surfaceOp":"append"} +{"type":"assistant/message","seq":116,"time":1783352167934,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool is disabled by policy. I need to report this error verbatim back to the user."},{"type":"text","text":"The tool returned:\n\n> Error: bash is disabled by policy in this session\n\nI cannot run the command because the bash tool is disabled by policy."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":167,"outputTokens":52,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115],"surfaceOp":"append"} {"type":"step/end","seq":117,"time":1783352167934,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":118,"time":1783352167934,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl index 3e07124e41..886761da18 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/session.jsonl @@ -5,7 +5,7 @@ {"type":"user/message","seq":3,"time":1783352160564,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"context/message","seq":4,"time":1783352160564,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-claude"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783352160565,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783352160566,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783352160566,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783352161228,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783352161229,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783352161335,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -33,6 +33,6 @@ {"type":"assistant/chunk","seq":31,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"teal"}}}} {"type":"assistant/chunk","seq":32,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}}}} {"type":"assistant/chunk","seq":33,"time":1783352161512,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":34,"time":1783352161515,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user's favorite color is teal, as stated in the context provided by the plugin."},{"type":"text","text":"teal"}],"usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} +{"type":"assistant/message","seq":34,"time":1783352161515,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user's favorite color is teal, as stated in the context provided by the plugin."},{"type":"text","text":"teal"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2892,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} {"type":"step/end","seq":35,"time":1783352161516,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":36,"time":1783352161516,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl index 2bed8d839a..5f6b0e6e9e 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352203369,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352203370,"data":{"content":[{"type":"text","text":"Reply with the single word FIRST and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352203371,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352203372,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352203372,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352204036,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352204036,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352204247,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -28,7 +28,7 @@ {"type":"assistant/chunk","seq":26,"time":1783352204393,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"FIRST"}}}} {"type":"assistant/chunk","seq":27,"time":1783352204393,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2862,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":28,"time":1783352204393,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":29,"time":1783352204396,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with the single word \"FIRST\" and stop."},{"type":"text","text":"FIRST"}],"usage":{"inputTokens":2862,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"} +{"type":"assistant/message","seq":29,"time":1783352204396,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with the single word \"FIRST\" and stop."},{"type":"text","text":"FIRST"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2862,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"} {"type":"step/end","seq":30,"time":1783352204396,"data":{"turn":1,"step":1}} {"type":"hook/invoked","seq":31,"time":1783352204396,"data":{"turn":1,"point":"Stop","dialect":"claude","handlerId":"claude:Stop:1"}} {"type":"hook/result","seq":32,"time":1783352204443,"data":{"turn":1,"point":"Stop","handlerId":"claude:Stop:1","decision":"block","exitCode":2,"stderrSummary":"Also reply with the single word SECOND, then stop.","durationMs":47.01462700000047}} @@ -185,7 +185,7 @@ {"type":"assistant/chunk","seq":183,"time":1783352206162,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"FIRST"}}}} {"type":"assistant/chunk","seq":184,"time":1783352206162,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":73,"outputTokens":146,"cacheReadTokens":2816,"reasoningTokens":143}}}} {"type":"assistant/chunk","seq":185,"time":1783352206162,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":186,"time":1783352206162,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user wants me to reply with \"FIRST\" only, but there's a steering input telling me to also reply with \"SECOND\". However, the user's explicit instruction is to reply with the single word FIRST and stop. The steering is from a plugin, not the user themselves. I should follow the user's original instruction.\n\nWait, let me re-read. The user said \"Reply with the single word FIRST and stop.\" Then there's a steering from \"plugin\" saying \"Also reply with the single word SECOND, then stop.\"\n\nThe user's instruction is clear: reply with FIRST and stop. The steering is from a plugin source, not the user. I'll follow the user's instruction."},{"type":"text","text":"FIRST"}],"usage":{"inputTokens":73,"outputTokens":146,"cacheReadTokens":2816,"reasoningTokens":143}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185],"surfaceOp":"append"} +{"type":"assistant/message","seq":186,"time":1783352206162,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user wants me to reply with \"FIRST\" only, but there's a steering input telling me to also reply with \"SECOND\". However, the user's explicit instruction is to reply with the single word FIRST and stop. The steering is from a plugin, not the user themselves. I should follow the user's original instruction.\n\nWait, let me re-read. The user said \"Reply with the single word FIRST and stop.\" Then there's a steering from \"plugin\" saying \"Also reply with the single word SECOND, then stop.\"\n\nThe user's instruction is clear: reply with FIRST and stop. The steering is from a plugin source, not the user. I'll follow the user's instruction."},{"type":"text","text":"FIRST"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":73,"outputTokens":146,"cacheReadTokens":2816,"reasoningTokens":143}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185],"surfaceOp":"append"} {"type":"step/end","seq":187,"time":1783352206163,"data":{"turn":1,"step":2}} {"type":"hook/invoked","seq":188,"time":1783352206163,"data":{"turn":1,"point":"Stop","dialect":"claude","handlerId":"claude:Stop:2"}} {"type":"hook/result","seq":189,"time":1783352206190,"data":{"turn":1,"point":"Stop","handlerId":"claude:Stop:2","decision":"pass","exitCode":0,"durationMs":26.904655000000275}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl index 0936881298..4272fe6a94 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352220747,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352220748,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352220749,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352220750,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352220750,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352221451,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352221651,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -60,7 +60,7 @@ {"type":"assistant/chunk","seq":58,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}}}} {"type":"assistant/chunk","seq":59,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}}}} {"type":"assistant/chunk","seq":60,"time":1783352222121,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":61,"time":1783352222124,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}],"usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} +{"type":"assistant/message","seq":61,"time":1783352222124,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run the command \"echo HELLO\" using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":92,"cacheReadTokens":0,"reasoningTokens":25}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"tool/call","seq":62,"time":1783352222124,"data":{"turn":1,"step":1,"callId":"call_00_wNJIQDMLdssZp45zIXvz2684","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Print HELLO to stdout\"}"}} {"type":"hook/invoked","seq":63,"time":1783352222138,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":64,"time":1783352222148,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"block","exitCode":2,"stderrSummary":"tool output rejected by codex policy: summarize instead","durationMs":9.571565000000192}} @@ -217,6 +217,6 @@ {"type":"assistant/chunk","seq":215,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}}}} {"type":"assistant/chunk","seq":216,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}}}} {"type":"assistant/chunk","seq":217,"time":1783352224654,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":218,"time":1783352224655,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."},{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}],"usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}},"sourceEventSeqs":[68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217],"surfaceOp":"append"} +{"type":"assistant/message","seq":218,"time":1783352224655,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The output was rejected by the codex policy with the instruction to \"summarize instead\". This means I cannot show the raw output verbatim as the user requested. Let me try to comply but report what happened.\n\nActually, the user asked me to report the tool result verbatim. The tool result I got back is:\n\n\"tool output rejected by codex policy: summarize instead\"\n\nSo I should report that verbatim."},{"type":"text","text":"The tool result I got back is:\n\n> `tool output rejected by codex policy: summarize instead`\n\nThis is the verbatim result from the tool — it was not the expected `\"HELLO\"` output because the codex policy blocked it and instructed me to summarize instead."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":176,"outputTokens":145,"cacheReadTokens":2816,"reasoningTokens":86}},"sourceEventSeqs":[68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217],"surfaceOp":"append"} {"type":"step/end","seq":219,"time":1783352224655,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":220,"time":1783352224655,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl index 6932a1f47e..d60858ee0a 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352228441,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352228442,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352228443,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352228443,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352228443,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352228985,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352228985,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352229106,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -57,7 +57,7 @@ {"type":"assistant/chunk","seq":55,"time":1783352229598,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_Q6wHtakaip2QNfIXaVJY5458","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":56,"time":1783352229598,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":57,"time":1783352229598,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":58,"time":1783352229601,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_Q6wHtakaip2QNfIXaVJY5458","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} +{"type":"assistant/message","seq":58,"time":1783352229601,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `echo HELLO` using the bash tool and report the result verbatim."},{"type":"tool-call","id":"call_00_Q6wHtakaip2QNfIXaVJY5458","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2878,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} {"type":"tool/call","seq":59,"time":1783352229601,"data":{"turn":1,"step":1,"callId":"call_00_Q6wHtakaip2QNfIXaVJY5458","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}} {"type":"hook/invoked","seq":60,"time":1783352229622,"data":{"turn":1,"point":"PostToolUse","dialect":"codex","handlerId":"codex:PostToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":61,"time":1783352229632,"data":{"turn":1,"point":"PostToolUse","handlerId":"codex:PostToolUse:1","decision":"pass","exitCode":0,"durationMs":9.27664199999981}} @@ -111,6 +111,6 @@ {"type":"assistant/chunk","seq":109,"time":1783352231379,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I received is:\n\n```\nHELLO\n```"}}}} {"type":"assistant/chunk","seq":110,"time":1783352231379,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":188,"outputTokens":41,"cacheReadTokens":2816,"reasoningTokens":27}}}} {"type":"assistant/chunk","seq":111,"time":1783352231379,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":112,"time":1783352231380,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to report the tool result verbatim. The result I got back is:\n\nHELLO\n\nThat's it."},{"type":"text","text":"The tool result I received is:\n\n```\nHELLO\n```"}],"usage":{"inputTokens":188,"outputTokens":41,"cacheReadTokens":2816,"reasoningTokens":27}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"surfaceOp":"append"} +{"type":"assistant/message","seq":112,"time":1783352231380,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user asked me to report the tool result verbatim. The result I got back is:\n\nHELLO\n\nThat's it."},{"type":"text","text":"The tool result I received is:\n\n```\nHELLO\n```"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":188,"outputTokens":41,"cacheReadTokens":2816,"reasoningTokens":27}},"sourceEventSeqs":[66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111],"surfaceOp":"append"} {"type":"step/end","seq":113,"time":1783352231380,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":114,"time":1783352231380,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl index a2022d9d6d..812998aad5 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352214604,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352214605,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo HELLO. Report the tool result you got back verbatim, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352214607,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352214608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352214608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352215181,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352215181,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352215351,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -51,7 +51,7 @@ {"type":"assistant/chunk","seq":49,"time":1783352215801,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_tv0SMeLXaTuyuVrOxnV97085","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}}}} {"type":"assistant/chunk","seq":50,"time":1783352215801,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2880,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":51,"time":1783352215801,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":52,"time":1783352215804,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_tv0SMeLXaTuyuVrOxnV97085","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"usage":{"inputTokens":2880,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} +{"type":"assistant/message","seq":52,"time":1783352215804,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a simple bash command and report the result verbatim."},{"type":"tool-call","id":"call_00_tv0SMeLXaTuyuVrOxnV97085","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2880,"outputTokens":83,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51],"surfaceOp":"append"} {"type":"tool/call","seq":53,"time":1783352215804,"data":{"turn":1,"step":1,"callId":"call_00_tv0SMeLXaTuyuVrOxnV97085","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Run echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352215805,"data":{"turn":1,"point":"PreToolUse","dialect":"codex","handlerId":"codex:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352215832,"data":{"turn":1,"point":"PreToolUse","handlerId":"codex:PreToolUse:1","decision":"block","exitCode":2,"stderrSummary":"bash is disabled by codex policy in this session","durationMs":26.08518500000082}} @@ -112,6 +112,6 @@ {"type":"assistant/chunk","seq":110,"time":1783352217214,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash is disabled by codex policy in this session\n```"}}}} {"type":"assistant/chunk","seq":111,"time":1783352217214,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":171,"outputTokens":49,"cacheReadTokens":2816,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":112,"time":1783352217214,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":113,"time":1783352217214,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool is disabled by policy in this session. I need to report this result verbatim to the user."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash is disabled by codex policy in this session\n```"}],"usage":{"inputTokens":171,"outputTokens":49,"cacheReadTokens":2816,"reasoningTokens":23}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} +{"type":"assistant/message","seq":113,"time":1783352217214,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The bash tool is disabled by policy in this session. I need to report this result verbatim to the user."},{"type":"text","text":"The tool result I got back verbatim is:\n\n```\nError: bash is disabled by codex policy in this session\n```"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":171,"outputTokens":49,"cacheReadTokens":2816,"reasoningTokens":23}},"sourceEventSeqs":[59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} {"type":"step/end","seq":114,"time":1783352217215,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":115,"time":1783352217215,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl index e9efd04100..1c710ff8e1 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/session.jsonl @@ -5,7 +5,7 @@ {"type":"user/message","seq":3,"time":1783352209707,"data":{"content":[{"type":"text","text":"What is my favorite color? Reply with just the color and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"context/message","seq":4,"time":1783352209707,"data":{"content":[{"type":"text","text":"The user has previously stated their favorite color is teal."}],"source":{"kind":"plugin","plugin":"hooks-codex"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783352209709,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783352209710,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783352209710,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783352210353,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783352210353,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783352210470,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -52,6 +52,6 @@ {"type":"assistant/chunk","seq":50,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"teal"}}}} {"type":"assistant/chunk","seq":51,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}}}} {"type":"assistant/chunk","seq":52,"time":1783352210788,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":53,"time":1783352210790,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked about their favorite color, and the context tells me they previously stated it's teal. They asked me to reply with just the color and stop, without using any tools."},{"type":"text","text":"teal"}],"usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52],"surfaceOp":"append"} +{"type":"assistant/message","seq":53,"time":1783352210790,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked about their favorite color, and the context tells me they previously stated it's teal. They asked me to reply with just the color and stop, without using any tools."},{"type":"text","text":"teal"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2891,"outputTokens":41,"cacheReadTokens":0,"reasoningTokens":38}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52],"surfaceOp":"append"} {"type":"step/end","seq":54,"time":1783352210790,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":55,"time":1783352210790,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl index 252ff8e262..bba879203d 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352235020,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352235020,"data":{"content":[{"type":"text","text":"Reply with the single word FIRST and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352235022,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352235023,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352235023,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352235669,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352235670,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352235879,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -30,7 +30,7 @@ {"type":"assistant/chunk","seq":28,"time":1783352236041,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"FIRST"}}}} {"type":"assistant/chunk","seq":29,"time":1783352236041,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2862,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}}}} {"type":"assistant/chunk","seq":30,"time":1783352236041,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":31,"time":1783352236043,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with only the single word \"FIRST\" and then stop."},{"type":"text","text":"FIRST"}],"usage":{"inputTokens":2862,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30],"surfaceOp":"append"} +{"type":"assistant/message","seq":31,"time":1783352236043,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with only the single word \"FIRST\" and then stop."},{"type":"text","text":"FIRST"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2862,"outputTokens":22,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30],"surfaceOp":"append"} {"type":"step/end","seq":32,"time":1783352236043,"data":{"turn":1,"step":1}} {"type":"hook/invoked","seq":33,"time":1783352236043,"data":{"turn":1,"point":"Stop","dialect":"codex","handlerId":"codex:Stop:1"}} {"type":"hook/result","seq":34,"time":1783352236059,"data":{"turn":1,"point":"Stop","handlerId":"codex:Stop:1","decision":"block","exitCode":2,"stderrSummary":"Also reply with the single word SECOND, then stop.","durationMs":14.77945499999987}} @@ -60,7 +60,7 @@ {"type":"assistant/chunk","seq":58,"time":1783352236876,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"SECOND"}}}} {"type":"assistant/chunk","seq":59,"time":1783352236876,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":73,"outputTokens":19,"cacheReadTokens":2816,"reasoningTokens":16}}}} {"type":"assistant/chunk","seq":60,"time":1783352236877,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":61,"time":1783352236877,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user is asking me to reply with the single word SECOND, then stop."},{"type":"text","text":"SECOND"}],"usage":{"inputTokens":73,"outputTokens":19,"cacheReadTokens":2816,"reasoningTokens":16}},"sourceEventSeqs":[37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} +{"type":"assistant/message","seq":61,"time":1783352236877,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user is asking me to reply with the single word SECOND, then stop."},{"type":"text","text":"SECOND"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":73,"outputTokens":19,"cacheReadTokens":2816,"reasoningTokens":16}},"sourceEventSeqs":[37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"step/end","seq":62,"time":1783352236877,"data":{"turn":1,"step":2}} {"type":"hook/invoked","seq":63,"time":1783352236877,"data":{"turn":1,"point":"Stop","dialect":"codex","handlerId":"codex:Stop:2"}} {"type":"hook/result","seq":64,"time":1783352236908,"data":{"turn":1,"point":"Stop","handlerId":"codex:Stop:2","decision":"pass","exitCode":0,"durationMs":30.947317000000112}} diff --git a/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl index 3b8c470ded..cd32072eaa 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352113765,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352113765,"data":{"content":[{"type":"text","text":"Reply with exactly the word: ONE. No tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352113767,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352113768,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352113768,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352114428,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352114428,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352114542,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -28,7 +28,7 @@ {"type":"assistant/chunk","seq":26,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ONE"}}}} {"type":"assistant/chunk","seq":27,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":28,"time":1783352114687,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":29,"time":1783352114690,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."},{"type":"text","text":"ONE"}],"usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"} +{"type":"assistant/message","seq":29,"time":1783352114690,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ONE\" and use no tools."},{"type":"text","text":"ONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2864,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28],"surfaceOp":"append"} {"type":"step/end","seq":30,"time":1783352114690,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":31,"time":1783352114690,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":32,"time":1783352114699,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -60,6 +60,6 @@ {"type":"assistant/chunk","seq":58,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"TWO"}}}} {"type":"assistant/chunk","seq":59,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":60,"time":1783352115610,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":61,"time":1783352115611,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."},{"type":"text","text":"TWO"}],"usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} +{"type":"assistant/message","seq":61,"time":1783352115611,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"TWO\" and no tools."},{"type":"text","text":"TWO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":64,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60],"surfaceOp":"append"} {"type":"step/end","seq":62,"time":1783352115611,"data":{"turn":2,"step":1}} {"type":"turn/end","seq":63,"time":1783352115611,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl index 7e50e71b3b..20d18973d9 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/session.jsonl @@ -2,13 +2,13 @@ {"type":"turn/start","seq":0,"time":0,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":0,"data":{"content":[{"type":"text","text":"Write the todo list 'watch the kettle boil' five times in a row without changing it, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":0,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":0,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"call_1","name":"todo_write","argumentsDelta":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}} {"type":"assistant/chunk","seq":6,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":7,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":8,"time":0,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} +{"type":"assistant/message","seq":9,"time":0,"data":{"turn":1,"step":1,"content":[{"type":"tool-call","id":"call_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[4,5,6,7,8],"surfaceOp":"append"} {"type":"tool/call","seq":10,"time":0,"data":{"turn":1,"step":1,"callId":"call_1","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":11,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":12,"time":0,"data":{"turn":1,"step":1,"callId":"call_1","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[10],"surfaceOp":"append"} @@ -19,7 +19,7 @@ {"type":"assistant/chunk","seq":17,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_2","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":18,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":19,"time":0,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_2","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"} +{"type":"assistant/message","seq":20,"time":0,"data":{"turn":1,"step":2,"content":[{"type":"tool-call","id":"call_2","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[15,16,17,18,19],"surfaceOp":"append"} {"type":"tool/call","seq":21,"time":0,"data":{"turn":1,"step":2,"callId":"call_2","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":22,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":23,"time":0,"data":{"turn":1,"step":2,"callId":"call_2","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[21],"surfaceOp":"append"} @@ -30,7 +30,7 @@ {"type":"assistant/chunk","seq":28,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":29,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":30,"time":0,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"} +{"type":"assistant/message","seq":31,"time":0,"data":{"turn":1,"step":3,"content":[{"type":"tool-call","id":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[26,27,28,29,30],"surfaceOp":"append"} {"type":"tool/call","seq":32,"time":0,"data":{"turn":1,"step":3,"callId":"call_3","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":33,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":34,"time":0,"data":{"turn":1,"step":3,"callId":"call_3","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[32],"surfaceOp":"append"} @@ -42,7 +42,7 @@ {"type":"assistant/chunk","seq":40,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_4","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":41,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":42,"time":0,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":43,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"call_4","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[38,39,40,41,42],"surfaceOp":"append"} +{"type":"assistant/message","seq":43,"time":0,"data":{"turn":1,"step":4,"content":[{"type":"tool-call","id":"call_4","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[38,39,40,41,42],"surfaceOp":"append"} {"type":"tool/call","seq":44,"time":0,"data":{"turn":1,"step":4,"callId":"call_4","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":45,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":46,"time":0,"data":{"turn":1,"step":4,"callId":"call_4","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[44],"surfaceOp":"append"} @@ -53,7 +53,7 @@ {"type":"assistant/chunk","seq":51,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}}}} {"type":"assistant/chunk","seq":52,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":5}}}} {"type":"assistant/chunk","seq":53,"time":0,"data":{"turn":1,"step":5,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":54,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[49,50,51,52,53],"surfaceOp":"append"} +{"type":"assistant/message","seq":54,"time":0,"data":{"turn":1,"step":5,"content":[{"type":"tool-call","id":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":5}},"sourceEventSeqs":[49,50,51,52,53],"surfaceOp":"append"} {"type":"tool/call","seq":55,"time":0,"data":{"turn":1,"step":5,"callId":"call_5","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"watch the kettle boil\", \"status\": \"in_progress\"}]}"}} {"type":"todo/write","seq":56,"time":0,"data":{"todos":[{"content":"watch the kettle boil","status":"in_progress"}]}} {"type":"tool/result","seq":57,"time":0,"data":{"turn":1,"step":5,"callId":"call_5","content":[{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[55],"surfaceOp":"append"} @@ -65,6 +65,6 @@ {"type":"assistant/chunk","seq":63,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DONE."}}}} {"type":"assistant/chunk","seq":64,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":3}}}} {"type":"assistant/chunk","seq":65,"time":0,"data":{"turn":1,"step":6,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":66,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"DONE."}],"usage":{"inputTokens":10,"outputTokens":3}},"sourceEventSeqs":[61,62,63,64,65],"surfaceOp":"append"} +{"type":"assistant/message","seq":66,"time":0,"data":{"turn":1,"step":6,"content":[{"type":"text","text":"DONE."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":10,"outputTokens":3}},"sourceEventSeqs":[61,62,63,64,65],"surfaceOp":"append"} {"type":"step/end","seq":67,"time":0,"data":{"turn":1,"step":6}} {"type":"turn/end","seq":68,"time":0,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 645671709e..9b5bdfa503 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} @@ -11,7 +11,7 @@ {"type":"assistant/chunk","seq":9,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}}}} {"type":"assistant/chunk","seq":10,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}}}} {"type":"assistant/chunk","seq":11,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":12,"time":1783654655609,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}],"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"} +{"type":"assistant/message","seq":12,"time":1783654655609,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"Load the requested skill."},{"type":"tool-call","id":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":100,"outputTokens":20,"cacheReadTokens":0,"reasoningTokens":5}},"sourceEventSeqs":[4,5,6,7,8,9,10,11],"surfaceOp":"append"} {"type":"tool/call","seq":13,"time":1783654655609,"data":{"turn":1,"step":1,"callId":"call_skill_load","name":"skill","arguments":"{\"name\":\"snapshot-skill\"}"}} {"type":"tool/result","seq":14,"time":1783654655610,"data":{"turn":1,"step":1,"callId":"call_skill_load","content":[{"type":"text","text":"\n\nBase directory for this skill: /var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-DhYwNW/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n\n"}],"isError":false},"sourceEventSeqs":[13],"surfaceOp":"append"} {"type":"step/end","seq":15,"time":1783654655610,"data":{"turn":1,"step":1}} @@ -24,6 +24,6 @@ {"type":"assistant/chunk","seq":22,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":23,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}}}} {"type":"assistant/chunk","seq":24,"time":1783654655611,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":25,"time":1783654655611,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The skill is loaded."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}},"sourceEventSeqs":[17,18,19,20,21,22,23,24],"surfaceOp":"append"} +{"type":"assistant/message","seq":25,"time":1783654655611,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The skill is loaded."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":180,"outputTokens":10,"cacheReadTokens":0,"reasoningTokens":4}},"sourceEventSeqs":[17,18,19,20,21,22,23,24],"surfaceOp":"append"} {"type":"step/end","seq":26,"time":1783654655611,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":27,"time":1783654655611,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl index 409fa1428d..4ecb61b60f 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352134837,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352134838,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352134840,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352135621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -33,13 +33,13 @@ {"type":"assistant/chunk","seq":31,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} {"type":"assistant/chunk","seq":32,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":33,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} +{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} {"type":"step/end","seq":35,"time":1783352135773,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":36,"time":1783352135773,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":37,"time":1783352137162,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":38,"time":1783352137163,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":39,"time":1783352137163,"data":{"turn":2,"step":1}} -{"type":"request/header","seq":40,"time":1783352137163,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} +{"type":"request/header","seq":40,"time":1783352137163,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} {"type":"assistant/chunk","seq":41,"time":1783352137783,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":42,"time":1783352137783,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":43,"time":1783352137961,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -84,6 +84,6 @@ {"type":"assistant/chunk","seq":82,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"MARMALADE"}}}} {"type":"assistant/chunk","seq":83,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}}}} {"type":"assistant/chunk","seq":84,"time":1783352138307,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":85,"time":1783352138308,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user asked me to remember the project codeword \"MARMALADE\" and now they're asking what it is. I should just reply with that word."},{"type":"text","text":"MARMALADE"}],"usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}},"sourceEventSeqs":[41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"surfaceOp":"append"} +{"type":"assistant/message","seq":85,"time":1783352138308,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user asked me to remember the project codeword \"MARMALADE\" and now they're asking what it is. I should just reply with that word."},{"type":"text","text":"MARMALADE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":97,"outputTokens":39,"cacheReadTokens":2816,"reasoningTokens":34}},"sourceEventSeqs":[41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84],"surfaceOp":"append"} {"type":"step/end","seq":86,"time":1783352138308,"data":{"turn":2,"step":1}} {"type":"turn/end","seq":87,"time":1783352138308,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl index d61503ffbb..64da6e60e5 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352134837,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352134838,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is MARMALADE. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352134840,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352134840,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352135465,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352135621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -33,7 +33,7 @@ {"type":"assistant/chunk","seq":31,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} {"type":"assistant/chunk","seq":32,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":33,"time":1783352135771,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} +{"type":"assistant/message","seq":34,"time":1783352135773,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember the codeword \"MARMALADE\" and reply with just \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2885,"outputTokens":25,"cacheReadTokens":0,"reasoningTokens":23}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"surfaceOp":"append"} {"type":"step/end","seq":35,"time":1783352135773,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":36,"time":1783352135773,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":37,"time":1783352135780,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -149,7 +149,7 @@ {"type":"assistant/chunk","seq":147,"time":1783352137158,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":148,"time":1783352137158,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":158,"outputTokens":147,"cacheReadTokens":2816,"reasoningTokens":59}}}} {"type":"assistant/chunk","seq":149,"time":1783352137159,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":150,"time":1783352137159,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use subagent_fork to delegate a question to a child agent. The child agent inherits this conversation and should be able to answer: the project codeword is MARMALADE. After the subagent returns, I should reply with PARENT_DONE."},{"type":"tool-call","id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"usage":{"inputTokens":158,"outputTokens":147,"cacheReadTokens":2816,"reasoningTokens":59}},"sourceEventSeqs":[40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} +{"type":"assistant/message","seq":150,"time":1783352137159,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use subagent_fork to delegate a question to a child agent. The child agent inherits this conversation and should be able to answer: the project codeword is MARMALADE. After the subagent returns, I should reply with PARENT_DONE."},{"type":"tool-call","id":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":158,"outputTokens":147,"cacheReadTokens":2816,"reasoningTokens":59}},"sourceEventSeqs":[40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} {"type":"tool/call","seq":151,"time":1783352137159,"data":{"turn":2,"step":1,"callId":"call_00_sAtKUseRzHRBvL4CF7XF1334","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}} {"type":"tool/result","seq":152,"time":1783352138315,"data":{"turn":2,"step":1,"callId":"call_00_sAtKUseRzHRBvL4CF7XF1334","content":[{"type":"text","text":"MARMALADE"}],"isError":false},"sourceEventSeqs":[151],"surfaceOp":"append"} {"type":"step/end","seq":153,"time":1783352138316,"data":{"turn":2,"step":1}} @@ -189,6 +189,6 @@ {"type":"assistant/chunk","seq":187,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} {"type":"assistant/chunk","seq":188,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":65,"outputTokens":30,"cacheReadTokens":3072,"reasoningTokens":25}}}} {"type":"assistant/chunk","seq":189,"time":1783352139274,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":190,"time":1783352139274,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The forked child agent correctly returned \"MARMALADE\". Now I need to reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"usage":{"inputTokens":65,"outputTokens":30,"cacheReadTokens":3072,"reasoningTokens":25}},"sourceEventSeqs":[155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189],"surfaceOp":"append"} +{"type":"assistant/message","seq":190,"time":1783352139274,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The forked child agent correctly returned \"MARMALADE\". Now I need to reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":65,"outputTokens":30,"cacheReadTokens":3072,"reasoningTokens":25}},"sourceEventSeqs":[155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189],"surfaceOp":"append"} {"type":"step/end","seq":191,"time":1783352139274,"data":{"turn":2,"step":2}} {"type":"turn/end","seq":192,"time":1783352139274,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl index 85a6405535..c99a5681e2 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352145224,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352145224,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352145224,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352145224,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352145224,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352145820,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352145821,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352145985,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -31,6 +31,6 @@ {"type":"assistant/chunk","seq":29,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}}} {"type":"assistant/chunk","seq":30,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}}}} {"type":"assistant/chunk","seq":31,"time":1783352146129,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783352146130,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"usage":{"inputTokens":48,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"assistant/message","seq":32,"time":1783352146130,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user asked me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":48,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783352146130,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":34,"time":1783352146130,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl index b9b6b48a9a..adfcb6f60e 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352142834,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352142834,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352142835,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352143493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352143494,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352143621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -27,13 +27,13 @@ {"type":"assistant/chunk","seq":25,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} {"type":"assistant/chunk","seq":26,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":27,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} +{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} {"type":"step/end","seq":29,"time":1783352143771,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":30,"time":1783352143771,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":31,"time":1783352147508,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":32,"time":1783352147509,"data":{"content":[{"type":"text","text":"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":33,"time":1783352147509,"data":{"turn":2,"step":1}} -{"type":"request/header","seq":34,"time":1783352147509,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} +{"type":"request/header","seq":34,"time":1783352147509,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"resume"}} {"type":"assistant/chunk","seq":35,"time":1783352147925,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":36,"time":1783352147925,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":37,"time":1783352148019,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -74,6 +74,6 @@ {"type":"assistant/chunk","seq":72,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"SAFFRON"}}}} {"type":"assistant/chunk","seq":73,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}}}} {"type":"assistant/chunk","seq":74,"time":1783352148345,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":75,"time":1783352148345,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user is asking me to recall the project codeword that was mentioned earlier in the conversation. I was told to remember it: SAFFRON."},{"type":"text","text":"SAFFRON"}],"usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74],"surfaceOp":"append"} +{"type":"assistant/message","seq":75,"time":1783352148345,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user is asking me to recall the project codeword that was mentioned earlier in the conversation. I was told to remember it: SAFFRON."},{"type":"text","text":"SAFFRON"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":95,"outputTokens":35,"cacheReadTokens":2816,"reasoningTokens":31}},"sourceEventSeqs":[35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74],"surfaceOp":"append"} {"type":"step/end","seq":76,"time":1783352148345,"data":{"turn":2,"step":1}} {"type":"turn/end","seq":77,"time":1783352148345,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl index ff5cfda975..1ea4f541e1 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352142834,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352142834,"data":{"content":[{"type":"text","text":"Remember this fact for later: the project codeword is SAFFRON. Reply with the single word OK and stop. Do not use any tools."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352142835,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352142836,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352143493,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352143494,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352143621,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -27,7 +27,7 @@ {"type":"assistant/chunk","seq":25,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"OK"}}}} {"type":"assistant/chunk","seq":26,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":27,"time":1783352143768,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} +{"type":"assistant/message","seq":28,"time":1783352143771,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to remember a codeword and just reply with \"OK\"."},{"type":"text","text":"OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2883,"outputTokens":19,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27],"surfaceOp":"append"} {"type":"step/end","seq":29,"time":1783352143771,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":30,"time":1783352143771,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":31,"time":1783352143779,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -108,7 +108,7 @@ {"type":"assistant/chunk","seq":106,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":107,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":185,"outputTokens":110,"cacheReadTokens":2816,"reasoningTokens":35}}}} {"type":"assistant/chunk","seq":108,"time":1783352145221,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":109,"time":1783352145221,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"Let me do these two delegations one at a time as requested.\n\nFirst, I'll use the subagent tool (fresh child) to reply with \"ALPHA\"."},{"type":"tool-call","id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"usage":{"inputTokens":185,"outputTokens":110,"cacheReadTokens":2816,"reasoningTokens":35}},"sourceEventSeqs":[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} +{"type":"assistant/message","seq":109,"time":1783352145221,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"Let me do these two delegations one at a time as requested.\n\nFirst, I'll use the subagent tool (fresh child) to reply with \"ALPHA\"."},{"type":"tool-call","id":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":185,"outputTokens":110,"cacheReadTokens":2816,"reasoningTokens":35}},"sourceEventSeqs":[34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108],"surfaceOp":"append"} {"type":"tool/call","seq":110,"time":1783352145222,"data":{"turn":2,"step":1,"callId":"call_00_YvHr2bGomk5HhpgDTvE81896","name":"subagent","arguments":"{\"description\": \"Reply ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}} {"type":"tool/result","seq":111,"time":1783352146133,"data":{"turn":2,"step":1,"callId":"call_00_YvHr2bGomk5HhpgDTvE81896","content":[{"type":"text","text":"ALPHA"}],"isError":false},"sourceEventSeqs":[110],"surfaceOp":"append"} {"type":"step/end","seq":112,"time":1783352146134,"data":{"turn":2,"step":1}} @@ -204,7 +204,7 @@ {"type":"assistant/chunk","seq":202,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":203,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":54,"outputTokens":128,"cacheReadTokens":3072,"reasoningTokens":40}}}} {"type":"assistant/chunk","seq":204,"time":1783352147502,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":205,"time":1783352147503,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to use the subagent_fork tool (forked child that inherits this conversation) to ask about the project codeword."},{"type":"tool-call","id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"usage":{"inputTokens":54,"outputTokens":128,"cacheReadTokens":3072,"reasoningTokens":40}},"sourceEventSeqs":[114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} +{"type":"assistant/message","seq":205,"time":1783352147503,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"The first subagent returned \"ALPHA\". Now I need to use the subagent_fork tool (forked child that inherits this conversation) to ask about the project codeword."},{"type":"tool-call","id":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":54,"outputTokens":128,"cacheReadTokens":3072,"reasoningTokens":40}},"sourceEventSeqs":[114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} {"type":"tool/call","seq":206,"time":1783352147503,"data":{"turn":2,"step":2,"callId":"call_00_JSr5rhREq23wSmwSkCP77184","name":"subagent_fork","arguments":"{\"description\": \"Recall project codeword\", \"prompt\": \"What is the project codeword mentioned earlier in this conversation? Reply with exactly that one word and nothing else.\"}"}} {"type":"tool/result","seq":207,"time":1783352148348,"data":{"turn":2,"step":2,"callId":"call_00_JSr5rhREq23wSmwSkCP77184","content":[{"type":"text","text":"SAFFRON"}],"isError":false},"sourceEventSeqs":[206],"surfaceOp":"append"} {"type":"step/end","seq":208,"time":1783352148348,"data":{"turn":2,"step":2}} @@ -283,6 +283,6 @@ {"type":"assistant/chunk","seq":281,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} {"type":"assistant/chunk","seq":282,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":69,"outputTokens":69,"cacheReadTokens":3200,"reasoningTokens":64}}}} {"type":"assistant/chunk","seq":283,"time":1783352149821,"data":{"turn":2,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":284,"time":1783352149822,"data":{"turn":2,"step":3,"content":[{"type":"reasoning","text":"Both subagents returned:\n1. First (fresh child): \"ALPHA\"\n2. Second (forked child): \"SAFFRON\" - correctly inherited the conversation context where I was asked to remember the codeword \"SAFFRON\".\n\nNow I reply with \"PARENT_DONE\" as instructed."},{"type":"text","text":"PARENT_DONE"}],"usage":{"inputTokens":69,"outputTokens":69,"cacheReadTokens":3200,"reasoningTokens":64}},"sourceEventSeqs":[210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283],"surfaceOp":"append"} +{"type":"assistant/message","seq":284,"time":1783352149822,"data":{"turn":2,"step":3,"content":[{"type":"reasoning","text":"Both subagents returned:\n1. First (fresh child): \"ALPHA\"\n2. Second (forked child): \"SAFFRON\" - correctly inherited the conversation context where I was asked to remember the codeword \"SAFFRON\".\n\nNow I reply with \"PARENT_DONE\" as instructed."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":69,"outputTokens":69,"cacheReadTokens":3200,"reasoningTokens":64}},"sourceEventSeqs":[210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240,241,242,243,244,245,246,247,248,249,250,251,252,253,254,255,256,257,258,259,260,261,262,263,264,265,266,267,268,269,270,271,272,273,274,275,276,277,278,279,280,281,282,283],"surfaceOp":"append"} {"type":"step/end","seq":285,"time":1783352149822,"data":{"turn":2,"step":3}} {"type":"turn/end","seq":286,"time":1783352149822,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl index e046c226d0..86c481c5ff 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352127670,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352127670,"data":{"content":[{"type":"text","text":"Reply with exactly the word ALPHA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352127671,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352127671,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352127671,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352128125,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352128125,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352128240,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -31,6 +31,6 @@ {"type":"assistant/chunk","seq":29,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"ALPHA"}}}} {"type":"assistant/chunk","seq":30,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}}}} {"type":"assistant/chunk","seq":31,"time":1783352128365,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783352128365,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"assistant/message","seq":32,"time":1783352128365,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"ALPHA\" and nothing else."},{"type":"text","text":"ALPHA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":49,"outputTokens":23,"cacheReadTokens":2816,"reasoningTokens":19}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783352128365,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":34,"time":1783352128366,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl index e113159d39..483e687a14 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352129662,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352129662,"data":{"content":[{"type":"text","text":"Reply with exactly the word BETA and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352129663,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352129663,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352129663,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352130236,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352130236,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352130375,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -29,6 +29,6 @@ {"type":"assistant/chunk","seq":27,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"BETA"}}}} {"type":"assistant/chunk","seq":28,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":29,"time":1783352130527,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":30,"time":1783352130528,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."},{"type":"text","text":"BETA"}],"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"assistant/message","seq":30,"time":1783352130528,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"BETA\" and nothing else."},{"type":"text","text":"BETA"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} {"type":"step/end","seq":31,"time":1783352130528,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":32,"time":1783352130528,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl index c7a079391f..a8093fba04 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352126251,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352126251,"data":{"content":[{"type":"text","text":"Use the subagent tool TWICE, once at a time, to delegate two subtasks to child agents. First subtask: 'Reply with exactly the word ALPHA and nothing else.' Second subtask (after the first returns): 'Reply with exactly the word BETA and nothing else.' After both subagents return, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352126252,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352126253,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352126253,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352126729,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352126729,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352126848,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -92,7 +92,7 @@ {"type":"assistant/chunk","seq":90,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":91,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}}}} {"type":"assistant/chunk","seq":92,"time":1783352127665,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":93,"time":1783352127668,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."},{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92],"surfaceOp":"append"} +{"type":"assistant/message","seq":93,"time":1783352127668,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the subagent tool twice, sequentially (one at a time). First subagent should reply with \"ALPHA\", second with \"BETA\". After both return, I reply with \"PARENT_DONE\"."},{"type":"tool-call","id":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2938,"outputTokens":124,"cacheReadTokens":0,"reasoningTokens":49}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92],"surfaceOp":"append"} {"type":"tool/call","seq":94,"time":1783352127668,"data":{"turn":1,"step":1,"callId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","name":"subagent","arguments":"{\"description\": \"Return ALPHA only\", \"prompt\": \"Reply with exactly the word ALPHA and nothing else.\"}"}} {"type":"tool/result","seq":95,"time":1783352128371,"data":{"turn":1,"step":1,"callId":"call_00_7zDCCjdsQgrk5LR2bAEQ1010","content":[{"type":"text","text":"ALPHA"}],"isError":false},"sourceEventSeqs":[94],"surfaceOp":"append"} {"type":"step/end","seq":96,"time":1783352128371,"data":{"turn":1,"step":1}} @@ -158,7 +158,7 @@ {"type":"assistant/chunk","seq":156,"time":1783352129661,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":157,"time":1783352129661,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}}}} {"type":"assistant/chunk","seq":158,"time":1783352129661,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":159,"time":1783352129661,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."},{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}],"usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}},"sourceEventSeqs":[98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} +{"type":"assistant/message","seq":159,"time":1783352129661,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"First subagent returned \"ALPHA\". Now I'll call the second subagent to return \"BETA\"."},{"type":"tool-call","id":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":133,"outputTokens":96,"cacheReadTokens":2944,"reasoningTokens":23}},"sourceEventSeqs":[98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} {"type":"tool/call","seq":160,"time":1783352129661,"data":{"turn":1,"step":2,"callId":"call_00_FudNKuJ0fchSptGy3Scw1411","name":"subagent","arguments":"{\"description\": \"Return BETA only\", \"prompt\": \"Reply with exactly the word BETA and nothing else.\"}"}} {"type":"tool/result","seq":161,"time":1783352130531,"data":{"turn":1,"step":2,"callId":"call_00_FudNKuJ0fchSptGy3Scw1411","content":[{"type":"text","text":"BETA"}],"isError":false},"sourceEventSeqs":[160],"surfaceOp":"append"} {"type":"step/end","seq":162,"time":1783352130531,"data":{"turn":1,"step":2}} @@ -203,6 +203,6 @@ {"type":"assistant/chunk","seq":201,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} {"type":"assistant/chunk","seq":202,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":203,"time":1783352131242,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":204,"time":1783352131243,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203],"surfaceOp":"append"} +{"type":"assistant/message","seq":204,"time":1783352131243,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Both subagents have returned: first with \"ALPHA\", second with \"BETA\". Now I should reply with \"PARENT_DONE\"."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":115,"outputTokens":35,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203],"surfaceOp":"append"} {"type":"step/end","seq":205,"time":1783352131243,"data":{"turn":1,"step":3}} {"type":"turn/end","seq":206,"time":1783352131243,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl index fedd7cbfb4..8dd26c4e70 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352120856,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352120856,"data":{"content":[{"type":"text","text":"Reply with exactly the word CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352120856,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352120856,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352120856,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352121437,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352121438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352121635,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -29,6 +29,6 @@ {"type":"assistant/chunk","seq":27,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"CHILD_OK"}}}} {"type":"assistant/chunk","seq":28,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":29,"time":1783352121777,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":30,"time":1783352121777,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word CHILD_OK and nothing else."},{"type":"text","text":"CHILD_OK"}],"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} +{"type":"assistant/message","seq":30,"time":1783352121777,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word CHILD_OK and nothing else."},{"type":"text","text":"CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":48,"outputTokens":21,"cacheReadTokens":2816,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29],"surfaceOp":"append"} {"type":"step/end","seq":31,"time":1783352121778,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":32,"time":1783352121778,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl index b550a8cb19..6a87cfabb5 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352119273,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352119274,"data":{"content":[{"type":"text","text":"Use the subagent tool exactly once to delegate this subtask to a child agent: 'Reply with exactly the word CHILD_OK and nothing else.' After the subagent returns, reply with the single word PARENT_DONE and stop. Do not use the bash tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352119275,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352119281,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352119281,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352119925,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352119925,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352120053,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -110,7 +110,7 @@ {"type":"assistant/chunk","seq":108,"time":1783352120851,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}}}} {"type":"assistant/chunk","seq":109,"time":1783352120852,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2907,"outputTokens":142,"cacheReadTokens":0,"reasoningTokens":67}}}} {"type":"assistant/chunk","seq":110,"time":1783352120852,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":111,"time":1783352120854,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Use the subagent tool exactly once to delegate the task: \"Reply with exactly the word CHILD_OK and nothing else.\"\n2. After the subagent returns, reply with the single word PARENT_DONE and stop.\n3. Do not use the bash tool.\n\nLet me do this."},{"type":"tool-call","id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}],"usage":{"inputTokens":2907,"outputTokens":142,"cacheReadTokens":0,"reasoningTokens":67}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110],"surfaceOp":"append"} +{"type":"assistant/message","seq":111,"time":1783352120854,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Use the subagent tool exactly once to delegate the task: \"Reply with exactly the word CHILD_OK and nothing else.\"\n2. After the subagent returns, reply with the single word PARENT_DONE and stop.\n3. Do not use the bash tool.\n\nLet me do this."},{"type":"tool-call","id":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2907,"outputTokens":142,"cacheReadTokens":0,"reasoningTokens":67}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110],"surfaceOp":"append"} {"type":"tool/call","seq":112,"time":1783352120854,"data":{"turn":1,"step":1,"callId":"call_00_gVbLWC12Qu8JheZpVRRz8749","name":"subagent","arguments":"{\"description\": \"Reply with CHILD_OK\", \"prompt\": \"Reply with exactly the word CHILD_OK and nothing else.\"}"}} {"type":"tool/result","seq":113,"time":1783352121784,"data":{"turn":1,"step":1,"callId":"call_00_gVbLWC12Qu8JheZpVRRz8749","content":[{"type":"text","text":"CHILD_OK"}],"isError":false},"sourceEventSeqs":[112],"surfaceOp":"append"} {"type":"step/end","seq":114,"time":1783352121784,"data":{"turn":1,"step":1}} @@ -155,6 +155,6 @@ {"type":"assistant/chunk","seq":153,"time":1783352122731,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PARENT_DONE"}}}} {"type":"assistant/chunk","seq":154,"time":1783352122732,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":120,"outputTokens":35,"cacheReadTokens":2944,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":155,"time":1783352122732,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":156,"time":1783352122732,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The subagent returned \"CHILD_OK\" as expected. Now I need to reply with the single word \"PARENT_DONE\" and stop."},{"type":"text","text":"PARENT_DONE"}],"usage":{"inputTokens":120,"outputTokens":35,"cacheReadTokens":2944,"reasoningTokens":30}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"surfaceOp":"append"} +{"type":"assistant/message","seq":156,"time":1783352122732,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The subagent returned \"CHILD_OK\" as expected. Now I need to reply with the single word \"PARENT_DONE\" and stop."},{"type":"text","text":"PARENT_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":120,"outputTokens":35,"cacheReadTokens":2944,"reasoningTokens":30}},"sourceEventSeqs":[116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155],"surfaceOp":"append"} {"type":"step/end","seq":157,"time":1783352122732,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":158,"time":1783352122732,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 324ef8d4eb..b8afff45de 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":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"}}} @@ -31,6 +31,6 @@ {"type":"assistant/chunk","seq":29,"time":1783600631009,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PONG"}}}} {"type":"assistant/chunk","seq":30,"time":1783600631009,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}}}} {"type":"assistant/chunk","seq":31,"time":1783600631009,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783600631011,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"PONG\" and not use any tools."},{"type":"text","text":"PONG"}],"usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"assistant/message","seq":32,"time":1783600631011,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly the word \"PONG\" and not use any tools."},{"type":"text","text":"PONG"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3091,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783600631011,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":34,"time":1783600631011,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl index 8e93132d30..909afc44cd 100644 --- a/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-plan/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352057655,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352057655,"data":{"content":[{"type":"text","text":"Use the todo_write tool to record a plan with exactly three todos: \"read the code\" (in_progress), \"write the fix\" (pending), \"run the tests\" (pending). Send all three in one todo_write call. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352057657,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352057657,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352057657,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352058320,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352058320,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352058426,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -94,7 +94,7 @@ {"type":"assistant/chunk","seq":92,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}}}} {"type":"assistant/chunk","seq":93,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}}}} {"type":"assistant/chunk","seq":94,"time":1783352059096,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":95,"time":1783352059099,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}],"usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"surfaceOp":"append"} +{"type":"assistant/message","seq":95,"time":1783352059099,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the todo_write tool to record a plan with exactly three todos in the specified statuses, then reply with \"DONE\"."},{"type":"tool-call","id":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2913,"outputTokens":121,"cacheReadTokens":0,"reasoningTokens":31}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94],"surfaceOp":"append"} {"type":"tool/call","seq":96,"time":1783352059099,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","name":"todo_write","arguments":"{\"todos\": [{\"content\": \"read the code\", \"status\": \"in_progress\"}, {\"content\": \"write the fix\", \"status\": \"pending\"}, {\"content\": \"run the tests\", \"status\": \"pending\"}]}"}} {"type":"todo/write","seq":97,"time":1783352059100,"data":{"todos":[{"content":"read the code","status":"in_progress"},{"content":"write the fix","status":"pending"},{"content":"run the tests","status":"pending"}]}} {"type":"tool/result","seq":98,"time":1783352059101,"data":{"turn":1,"step":1,"callId":"call_00_fjAnBThbDjxepBtp3hDt3264","content":[{"type":"text","text":"Updated todo list: 2 pending, 1 in progress, 0 completed."}],"isError":false},"sourceEventSeqs":[96],"surfaceOp":"append"} @@ -129,6 +129,6 @@ {"type":"assistant/chunk","seq":127,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":128,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}}}} {"type":"assistant/chunk","seq":129,"time":1783352059980,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":130,"time":1783352059981,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} +{"type":"assistant/message","seq":130,"time":1783352059981,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The todos have been written successfully. Now I just need to reply with the single word \"DONE\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":237,"outputTokens":24,"cacheReadTokens":2816,"reasoningTokens":21}},"sourceEventSeqs":[101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"step/end","seq":131,"time":1783352059981,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":132,"time":1783352059981,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl index 20a11443a7..f631c9bf54 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352044771,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352044771,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: echo SNAPSHOT_OK. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352044773,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352044773,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352044773,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352045294,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352045294,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352045396,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -57,7 +57,7 @@ {"type":"assistant/chunk","seq":55,"time":1783352045866,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","name":"bash","arguments":"{\"command\": \"echo SNAPSHOT_OK\", \"description\": \"Run echo SNAPSHOT_OK\"}"}}}} {"type":"assistant/chunk","seq":56,"time":1783352045866,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2879,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":57,"time":1783352045866,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":58,"time":1783352045867,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific bash command and then reply with DONE."},{"type":"tool-call","id":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","name":"bash","arguments":"{\"command\": \"echo SNAPSHOT_OK\", \"description\": \"Run echo SNAPSHOT_OK\"}"}],"usage":{"inputTokens":2879,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} +{"type":"assistant/message","seq":58,"time":1783352045867,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific bash command and then reply with DONE."},{"type":"tool-call","id":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","name":"bash","arguments":"{\"command\": \"echo SNAPSHOT_OK\", \"description\": \"Run echo SNAPSHOT_OK\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2879,"outputTokens":89,"cacheReadTokens":0,"reasoningTokens":17}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57],"surfaceOp":"append"} {"type":"tool/call","seq":59,"time":1783352045867,"data":{"turn":1,"step":1,"callId":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","name":"bash","arguments":"{\"command\": \"echo SNAPSHOT_OK\", \"description\": \"Run echo SNAPSHOT_OK\"}"}} {"type":"tool/result","seq":60,"time":1783352045879,"data":{"turn":1,"step":1,"callId":"call_00_Rn2Mz1y8uZN62ukEXiNO2077","content":[{"type":"text","text":"SNAPSHOT_OK\n"}],"isError":false},"sourceEventSeqs":[59],"surfaceOp":"append"} {"type":"step/end","seq":61,"time":1783352045880,"data":{"turn":1,"step":1}} @@ -95,6 +95,6 @@ {"type":"assistant/chunk","seq":93,"time":1783352047156,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":94,"time":1783352047156,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":170,"outputTokens":28,"cacheReadTokens":2816,"reasoningTokens":25}}}} {"type":"assistant/chunk","seq":95,"time":1783352047156,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":96,"time":1783352047158,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command executed successfully and printed SNAPSHOT_OK. Now I need to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":170,"outputTokens":28,"cacheReadTokens":2816,"reasoningTokens":25}},"sourceEventSeqs":[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"surfaceOp":"append"} +{"type":"assistant/message","seq":96,"time":1783352047158,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command executed successfully and printed SNAPSHOT_OK. Now I need to reply with the single word DONE."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":170,"outputTokens":28,"cacheReadTokens":2816,"reasoningTokens":25}},"sourceEventSeqs":[63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95],"surfaceOp":"append"} {"type":"step/end","seq":97,"time":1783352047158,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":98,"time":1783352047158,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl index a8c1d6018b..3d89428bbd 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600636316,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600636316,"data":{"content":[{"type":"text","text":"Reply with exactly the word WF_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600636316,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600636317,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600636317,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600638073,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600638073,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600638173,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -31,6 +31,6 @@ {"type":"assistant/chunk","seq":29,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WF_CHILD_OK"}}}} {"type":"assistant/chunk","seq":30,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":31,"time":1783600638280,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":32,"time":1783600638281,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."},{"type":"text","text":"WF_CHILD_OK"}],"usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"assistant/message","seq":32,"time":1783600638281,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"WF_CHILD_OK\" and nothing else."},{"type":"text","text":"WF_CHILD_OK"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":17,"outputTokens":23,"cacheReadTokens":3072,"reasoningTokens":18}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} {"type":"step/end","seq":33,"time":1783600638281,"data":{"turn":1,"step":1}} {"type":"turn/end","seq":34,"time":1783600638281,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl index ab53f20550..3e0ae3da73 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783600631838,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783600631838,"data":{"content":[{"type":"text","text":"Use the workflow tool exactly once, with args omitted, meta set to { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }, and this EXACT script body (copy it verbatim):\nphase('Run')\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\nreturn { reply }\nAfter the workflow returns, reply with the single word WORKFLOW_DONE and stop. Do not use any other tool."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783600631839,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783600631839,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600631839,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783600634643,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783600634643,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783600635634,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -158,7 +158,7 @@ {"type":"assistant/chunk","seq":156,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}}}} {"type":"assistant/chunk","seq":157,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}}}} {"type":"assistant/chunk","seq":158,"time":1783600636246,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":159,"time":1783600636247,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."},{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}],"usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} +{"type":"assistant/message","seq":159,"time":1783600636247,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to use the workflow tool exactly once with specific parameters. Let me carefully follow the instructions:\n\n1. args omitted (so I don't include it)\n2. meta = { \"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\" }\n3. script = as given verbatim\n4. After it returns, reply with \"WORKFLOW_DONE\"\n\nLet me do exactly that."},{"type":"tool-call","id":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3174,"outputTokens":191,"cacheReadTokens":0,"reasoningTokens":88}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,158],"surfaceOp":"append"} {"type":"tool/call","seq":160,"time":1783600636247,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","name":"workflow","arguments":"{\"meta\": {\"name\": \"snapshot-flow\", \"description\": \"one child for the snapshot\"}, \"script\": \"\\nphase('Run')\\nconst reply = await agent('Reply with exactly the word WF_CHILD_OK and nothing else.')\\nreturn { reply }\\n\"}"}} {"type":"tool/result","seq":161,"time":1783600638304,"data":{"turn":1,"step":1,"callId":"call_00_dD2BLuNeJCTh2iiYC1QR3449","content":[{"type":"text","text":"workflow \"snapshot-flow\" completed (1 agent).\nReturn value:\n{\n \"reply\": \"WF_CHILD_OK\"\n}"}],"isError":false},"sourceEventSeqs":[160],"surfaceOp":"append"} {"type":"step/end","seq":162,"time":1783600638304,"data":{"turn":1,"step":1}} @@ -204,6 +204,6 @@ {"type":"assistant/chunk","seq":202,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"WORKFLOW_DONE"}}}} {"type":"assistant/chunk","seq":203,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}}}} {"type":"assistant/chunk","seq":204,"time":1783600640865,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":205,"time":1783600640865,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."},{"type":"text","text":"WORKFLOW_DONE"}],"usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} +{"type":"assistant/message","seq":205,"time":1783600640865,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The workflow returned successfully with the reply \"WF_CHILD_OK\". Now I need to reply with exactly \"WORKFLOW_DONE\" and stop."},{"type":"text","text":"WORKFLOW_DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":328,"outputTokens":36,"cacheReadTokens":3072,"reasoningTokens":30}},"sourceEventSeqs":[164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204],"surfaceOp":"append"} {"type":"step/end","seq":206,"time":1783600640865,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":207,"time":1783600640865,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl index 9a908f24a3..6b9b03a95e 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783352264080,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783352264081,"data":{"content":[{"type":"text","text":"A file named greeting.txt in the current directory contains one word. Use the bash tool to append a second line containing the word WORLD to it (so it has two lines), then read the file back with `cat greeting.txt` to confirm, and reply with the single word DONE. Use a single bash call per action."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783352264082,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783352264083,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783352264083,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783352264544,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783352264544,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783352264642,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -77,7 +77,7 @@ {"type":"assistant/chunk","seq":75,"time":1783352265489,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}}}} {"type":"assistant/chunk","seq":76,"time":1783352265489,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":2918,"outputTokens":101,"cacheReadTokens":0,"reasoningTokens":55}}}} {"type":"assistant/chunk","seq":77,"time":1783352265489,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":78,"time":1783352265491,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read the file greeting.txt\n2. Append the word WORLD as a second line\n3. Read the file back with cat to confirm\n4. Reply with DONE\n\nLet me start by reading the file to see its contents."},{"type":"tool-call","id":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"usage":{"inputTokens":2918,"outputTokens":101,"cacheReadTokens":0,"reasoningTokens":55}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77],"surfaceOp":"append"} +{"type":"assistant/message","seq":78,"time":1783352265491,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to:\n1. Read the file greeting.txt\n2. Append the word WORLD as a second line\n3. Read the file back with cat to confirm\n4. Reply with DONE\n\nLet me start by reading the file to see its contents."},{"type":"tool-call","id":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":2918,"outputTokens":101,"cacheReadTokens":0,"reasoningTokens":55}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77],"surfaceOp":"append"} {"type":"tool/call","seq":79,"time":1783352265491,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","name":"read","arguments":"{\"file_path\": \"greeting.txt\"}"}} {"type":"tool/result","seq":80,"time":1783352265504,"data":{"turn":1,"step":1,"callId":"call_00_OjRFB4zvxu6UALDjytZD0978","content":[{"type":"text","text":"/tmp/acp-snap-cwd-rxbEpP/greeting.txt\nfile\n\n1: hello\n\n(End of file - total 1 lines)\n"}],"isError":false},"sourceEventSeqs":[79],"surfaceOp":"append"} {"type":"step/end","seq":81,"time":1783352265504,"data":{"turn":1,"step":1}} @@ -154,7 +154,7 @@ {"type":"assistant/chunk","seq":152,"time":1783352267302,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_IUUvbNiPcnwhVL8ErEFS4806","name":"bash","arguments":"{\"command\": \"printf '\\\\nWORLD' >> greeting.txt\", \"description\": \"Append newline and WORLD to greeting.txt\"}"}}}} {"type":"assistant/chunk","seq":153,"time":1783352267302,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":261,"outputTokens":107,"cacheReadTokens":2816,"reasoningTokens":32}}}} {"type":"assistant/chunk","seq":154,"time":1783352267302,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":155,"time":1783352267302,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"hello\" on one line. Now I need to append a second line with \"WORLD\" to it. Then cat it to confirm."},{"type":"tool-call","id":"call_00_IUUvbNiPcnwhVL8ErEFS4806","name":"bash","arguments":"{\"command\": \"printf '\\\\nWORLD' >> greeting.txt\", \"description\": \"Append newline and WORLD to greeting.txt\"}"}],"usage":{"inputTokens":261,"outputTokens":107,"cacheReadTokens":2816,"reasoningTokens":32}},"sourceEventSeqs":[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154],"surfaceOp":"append"} +{"type":"assistant/message","seq":155,"time":1783352267302,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The file contains \"hello\" on one line. Now I need to append a second line with \"WORLD\" to it. Then cat it to confirm."},{"type":"tool-call","id":"call_00_IUUvbNiPcnwhVL8ErEFS4806","name":"bash","arguments":"{\"command\": \"printf '\\\\nWORLD' >> greeting.txt\", \"description\": \"Append newline and WORLD to greeting.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":261,"outputTokens":107,"cacheReadTokens":2816,"reasoningTokens":32}},"sourceEventSeqs":[83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154],"surfaceOp":"append"} {"type":"tool/call","seq":156,"time":1783352267302,"data":{"turn":1,"step":2,"callId":"call_00_IUUvbNiPcnwhVL8ErEFS4806","name":"bash","arguments":"{\"command\": \"printf '\\\\nWORLD' >> greeting.txt\", \"description\": \"Append newline and WORLD to greeting.txt\"}"}} {"type":"tool/result","seq":157,"time":1783352267330,"data":{"turn":1,"step":2,"callId":"call_00_IUUvbNiPcnwhVL8ErEFS4806","content":[{"type":"text","text":"(no output)"}],"isError":false},"sourceEventSeqs":[156],"surfaceOp":"append"} {"type":"step/end","seq":158,"time":1783352267330,"data":{"turn":1,"step":2}} @@ -201,7 +201,7 @@ {"type":"assistant/chunk","seq":199,"time":1783352268414,"data":{"turn":1,"step":3,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_Wo4H7tFNheZJWKVDrAHK5851","name":"bash","arguments":"{\"command\": \"cat greeting.txt\", \"description\": \"Read greeting.txt to confirm\"}"}}}} {"type":"assistant/chunk","seq":200,"time":1783352268414,"data":{"turn":1,"step":3,"chunk":{"type":"usage","usage":{"inputTokens":126,"outputTokens":77,"cacheReadTokens":3072,"reasoningTokens":12}}}} {"type":"assistant/chunk","seq":201,"time":1783352268414,"data":{"turn":1,"step":3,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":202,"time":1783352268415,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Good, now let me read the file back with cat."},{"type":"tool-call","id":"call_00_Wo4H7tFNheZJWKVDrAHK5851","name":"bash","arguments":"{\"command\": \"cat greeting.txt\", \"description\": \"Read greeting.txt to confirm\"}"}],"usage":{"inputTokens":126,"outputTokens":77,"cacheReadTokens":3072,"reasoningTokens":12}},"sourceEventSeqs":[160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201],"surfaceOp":"append"} +{"type":"assistant/message","seq":202,"time":1783352268415,"data":{"turn":1,"step":3,"content":[{"type":"reasoning","text":"Good, now let me read the file back with cat."},{"type":"tool-call","id":"call_00_Wo4H7tFNheZJWKVDrAHK5851","name":"bash","arguments":"{\"command\": \"cat greeting.txt\", \"description\": \"Read greeting.txt to confirm\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":126,"outputTokens":77,"cacheReadTokens":3072,"reasoningTokens":12}},"sourceEventSeqs":[160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201],"surfaceOp":"append"} {"type":"tool/call","seq":203,"time":1783352268415,"data":{"turn":1,"step":3,"callId":"call_00_Wo4H7tFNheZJWKVDrAHK5851","name":"bash","arguments":"{\"command\": \"cat greeting.txt\", \"description\": \"Read greeting.txt to confirm\"}"}} {"type":"tool/result","seq":204,"time":1783352268429,"data":{"turn":1,"step":3,"callId":"call_00_Wo4H7tFNheZJWKVDrAHK5851","content":[{"type":"text","text":"hello\n\nWORLD"}],"isError":false},"sourceEventSeqs":[203],"surfaceOp":"append"} {"type":"step/end","seq":205,"time":1783352268429,"data":{"turn":1,"step":3}} @@ -236,6 +236,6 @@ {"type":"assistant/chunk","seq":234,"time":1783352269538,"data":{"turn":1,"step":4,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":235,"time":1783352269538,"data":{"turn":1,"step":4,"chunk":{"type":"usage","usage":{"inputTokens":219,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":22}}}} {"type":"assistant/chunk","seq":236,"time":1783352269538,"data":{"turn":1,"step":4,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":237,"time":1783352269538,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The file now has two lines:\n1. hello\n2. WORLD\n\nI can reply with DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":219,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":22}},"sourceEventSeqs":[207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236],"surfaceOp":"append"} +{"type":"assistant/message","seq":237,"time":1783352269538,"data":{"turn":1,"step":4,"content":[{"type":"reasoning","text":"The file now has two lines:\n1. hello\n2. WORLD\n\nI can reply with DONE."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":219,"outputTokens":25,"cacheReadTokens":3072,"reasoningTokens":22}},"sourceEventSeqs":[207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236],"surfaceOp":"append"} {"type":"step/end","seq":238,"time":1783352269538,"data":{"turn":1,"step":4}} {"type":"turn/end","seq":239,"time":1783352269539,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/coding-agent/code-mode.cordis.yml b/examples/coding-agent/code-mode.cordis.yml index ac4ce03570..87075b1d85 100644 --- a/examples/coding-agent/code-mode.cordis.yml +++ b/examples/coding-agent/code-mode.cordis.yml @@ -16,6 +16,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: deepseek model: deepseek-v4-flash resumeSessionId: !!js process.env.RESUME_SESSION_ID persistenceRoot: './.sessions' diff --git a/examples/coding-agent/cordis.yml b/examples/coding-agent/cordis.yml index cf2e267e06..74318aea4f 100644 --- a/examples/coding-agent/cordis.yml +++ b/examples/coding-agent/cordis.yml @@ -17,16 +17,12 @@ config: root: ['.'] -# The DeepSeek adapter. Swap to '@deepseek-ai/dsh-llm-pi-ai' for the pi-ai-backed -# twin (same config shape; `reasoning: high` replaces thinking/reasoningEffort). +# The native DeepSeek adapter. - id: llm-deepseek name: '@deepseek-ai/dsh-llm-deepseek' config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-pro - - deepseek-v4-flash # Local bash executor for agent-core's tool-bash schema (one of several tool # stacks in this tree: filesystem, subagent, and todo_write load below). @@ -40,6 +36,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: deepseek model: deepseek-v4-flash # Set RESUME_SESSION_ID to continue a prior persisted session (the ids live # under ./.sessions); unset starts a fresh session each run. @@ -66,6 +63,7 @@ contextWindow: 128000 thresholdRatio: 0.8 retainTokens: 20480 + summarizationProvider: '' summarizationModel: '' maxTokens: 8192 compactionRetries: 1 diff --git a/examples/coding-agent/tests/code-mode.e2e.ts b/examples/coding-agent/tests/code-mode.e2e.ts index 512688d88d..b8209e119d 100644 --- a/examples/coding-agent/tests/code-mode.e2e.ts +++ b/examples/coding-agent/tests/code-mode.e2e.ts @@ -50,7 +50,7 @@ async function codeModeHarness(cwd: string): Promise { await harness.plugin(ToolRegistry, { mode: 'code' }) await harness.plugin(AgentRegistry) await harness.plugin(AgentLoop, { agents: [] }) - await harness.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await harness.plugin(LlmDeepSeek) await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 }) await harness.plugin(ToolBash) await harness.plugin(WorkerCodeRuntime, {}) @@ -72,7 +72,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-')) ctx = await codeModeHarness(workdir) - const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/coding-task.e2e.ts b/examples/coding-agent/tests/coding-task.e2e.ts index ce716bdb2c..d53688835e 100644 --- a/examples/coding-agent/tests/coding-task.e2e.ts +++ b/examples/coding-agent/tests/coding-task.e2e.ts @@ -54,7 +54,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('coding task: fix a failing test expect(before.status).not.toBe(0) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-task'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-task'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/compaction.e2e.ts b/examples/coding-agent/tests/compaction.e2e.ts index 854cf49d2a..ab32e7f8a8 100644 --- a/examples/coding-agent/tests/compaction.e2e.ts +++ b/examples/coding-agent/tests/compaction.e2e.ts @@ -58,13 +58,14 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('compaction: a long session compa contextWindow: 2000, thresholdRatio: 0.5, retainTokens: 400, + summarizationProvider: '', summarizationModel: '', maxTokens: 1024, compactionRetries: 1, }, persistenceRoot: join(workdir, '.sessions'), }) - const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-compaction'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/coding-agent/tests/full-loop.e2e.ts b/examples/coding-agent/tests/full-loop.e2e.ts index 8718139ced..7314b7ab21 100644 --- a/examples/coding-agent/tests/full-loop.e2e.ts +++ b/examples/coding-agent/tests/full-loop.e2e.ts @@ -28,7 +28,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('full loop: real model + real bas it('runs a bash command on request and reports its output', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-full-loop-e2e-')) ctx = await codingHarness(workdir, { persona: SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-loop'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Run `echo e2e-ok` with the bash tool and tell me its exact output.' }]) await waitForIdle(ctx, agent) diff --git a/examples/coding-agent/tests/harness.ts b/examples/coding-agent/tests/harness.ts index dd0bc42a1b..378414a6be 100644 --- a/examples/coding-agent/tests/harness.ts +++ b/examples/coding-agent/tests/harness.ts @@ -56,7 +56,7 @@ export async function codingHarness(workdir: string, options: CodingHarnessOptio await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek) await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) await ctx.plugin(ToolBash) await ctx.plugin(ToolTodo) diff --git a/examples/coding-agent/tests/resume.e2e.ts b/examples/coding-agent/tests/resume.e2e.ts index 70382b4beb..c9081c659f 100644 --- a/examples/coding-agent/tests/resume.e2e.ts +++ b/examples/coding-agent/tests/resume.e2e.ts @@ -42,7 +42,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const first = (await ctx.agents.create({ agentId: AgentId('resume-1'), sessionId: SESSION_ID, - agentOptions: { model: 'deepseek-v4-flash' }, + agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent first.send([{ type: 'text', text: `Remember this code for later: ${SECRET}. Just acknowledge it.` }]) await waitForIdle(ctx, first) @@ -56,7 +56,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('resume: continue a persisted ses const resumed = (await ctx.agents.resume({ agentId: AgentId('resume-2'), resumeSessionId: SESSION_ID, - agentOptions: { model: 'deepseek-v4-flash' }, + agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, })).agent as ReactLoopAgent expect(resumed.session.id).toBe(SESSION_ID) // The prior user turn is in the rehydrated log before the model is asked. diff --git a/examples/coding-agent/tests/todo-write.e2e.ts b/examples/coding-agent/tests/todo-write.e2e.ts index 698fbd9e9e..a16f15528d 100644 --- a/examples/coding-agent/tests/todo-write.e2e.ts +++ b/examples/coding-agent/tests/todo-write.e2e.ts @@ -26,7 +26,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a it('appends a todo/write event with the model-produced task list', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-')) ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT }) - const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('e2e-todo'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Use the todo_write tool to record a plan of exactly two steps: first ' diff --git a/examples/cordis-agent/cordis.yml b/examples/cordis-agent/cordis.yml index 65d5e6eb36..2fd88199ab 100644 --- a/examples/cordis-agent/cordis.yml +++ b/examples/cordis-agent/cordis.yml @@ -25,9 +25,6 @@ config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-pro - - deepseek-v4-flash # Local bash executor for agent-core's tool-bash schema — gives the agent an # ordinary tool whose calls make the mounted listeners observably fire. @@ -58,6 +55,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: deepseek model: deepseek-v4-flash resumeSessionId: !!js process.env.RESUME_SESSION_ID persistenceRoot: './.sessions' diff --git a/examples/cordis-agent/tests/cordis-tools.e2e.ts b/examples/cordis-agent/tests/cordis-tools.e2e.ts index 388fcb0058..5b742d8830 100644 --- a/examples/cordis-agent/tests/cordis-tools.e2e.ts +++ b/examples/cordis-agent/tests/cordis-tools.e2e.ts @@ -38,7 +38,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('mounts a status listener whose tagged output actually fires, then unmounts it', async () => { ctx = await cordisHarness() const log = vi.spyOn(console, 'log').mockImplementation(() => {}) - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-listener'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('cordis-e2e-listener'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -66,7 +66,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('builds itself a reverse_text tool and actually calls it', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-selftool'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('cordis-e2e-selftool'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', @@ -114,7 +114,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('cordis tools: a real model modif it('composes two mounts through provide/inject, and unmounting the provider parks the consumer', async () => { ctx = await cordisHarness() - const agent = ctx.agentLoop.create(AgentId('cordis-e2e-compose'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('cordis-e2e-compose'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', diff --git a/examples/cordis-agent/tests/harness.ts b/examples/cordis-agent/tests/harness.ts index 78e5b0bb93..062e643ca8 100644 --- a/examples/cordis-agent/tests/harness.ts +++ b/examples/cordis-agent/tests/harness.ts @@ -29,7 +29,7 @@ export async function cordisHarness(): Promise { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek) await ctx.plugin(ToolCordis) return ctx } diff --git a/examples/echo-agent/cordis.yml b/examples/echo-agent/cordis.yml index b66c5e8163..bbe6c78b7c 100644 --- a/examples/echo-agent/cordis.yml +++ b/examples/echo-agent/cordis.yml @@ -32,6 +32,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: mock model: mock-echo persona: 'You are echo-agent, a demo agent.' welcome: 'echo-agent ready. Type a message ("echo " triggers the tool).' diff --git a/examples/echo-agent/src/mock-llm.ts b/examples/echo-agent/src/mock-llm.ts index 93132711de..1f61dc4ee3 100644 --- a/examples/echo-agent/src/mock-llm.ts +++ b/examples/echo-agent/src/mock-llm.ts @@ -55,5 +55,5 @@ export const name = 'mock-llm' export const inject = ['llm'] export function apply(ctx: Context) { - ctx.llm.registerAdapter(['mock-echo'], new MockEchoAdapter()) + ctx.llm.registerAdapter(['mock'], new MockEchoAdapter()) } diff --git a/examples/sandbox-acp-agent/cordis.yml b/examples/sandbox-acp-agent/cordis.yml index d02253342e..5ab8becd69 100644 --- a/examples/sandbox-acp-agent/cordis.yml +++ b/examples/sandbox-acp-agent/cordis.yml @@ -18,8 +18,6 @@ config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-flash # The sandbox stack: the platform-runner provider (bwrap → per-platform # Landlock launcher → Seatbelt, functionally probed), then the confined bash executor. @@ -49,6 +47,7 @@ - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash # Persistence root: $DSH_SNAPSHOT_SESSIONS_ROOT when the snapshot harness # sets it (so a record run's logs land where the harness harvests them), diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl index 2ac9d27044..526524e870 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783486769426,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783486769426,"data":{"content":[{"type":"text","text":"The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will approve the permission prompt. After the result, reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783486769427,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783486769427,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783486769427,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783486770051,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783486770052,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783486770179,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -112,7 +112,7 @@ {"type":"assistant/chunk","seq":110,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}}} {"type":"assistant/chunk","seq":111,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}}}} {"type":"assistant/chunk","seq":112,"time":1783486771232,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":113,"time":1783486771236,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."},{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} +{"type":"assistant/message","seq":113,"time":1783486771236,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the command with sandbox_permissions set to workspace-write. They explicitly said they will approve the permission prompt. Let me proceed."},{"type":"tool-call","id":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1255,"outputTokens":160,"cacheReadTokens":0,"reasoningTokens":34}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112],"surfaceOp":"append"} {"type":"tool/call","seq":114,"time":1783486771236,"data":{"turn":1,"step":1,"callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt and cat its content\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}} {"type":"approval/asked","seq":115,"time":1783486771238,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","toolName":"bash","callId":"call_00_ZSEIrZNdgQhL2QJgVHww8689","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} {"type":"approval/decided","seq":116,"time":1783486771243,"data":{"id":"3ec45405-5add-4929-a755-e8c077ec7a7e","outcome":"allowed-once"}} @@ -144,6 +144,6 @@ {"type":"assistant/chunk","seq":142,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":143,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":144,"time":1783486772229,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":145,"time":1783486772230,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command succeeded. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}},"sourceEventSeqs":[120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144],"surfaceOp":"append"} +{"type":"assistant/message","seq":145,"time":1783486772230,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command succeeded. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":23,"outputTokens":20,"cacheReadTokens":1408,"reasoningTokens":17}},"sourceEventSeqs":[120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144],"surfaceOp":"append"} {"type":"step/end","seq":146,"time":1783486772230,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":147,"time":1783486772230,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl index ee2586bc34..cca88b26c9 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783486772551,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783486772551,"data":{"content":[{"type":"text","text":"The sandbox already denied writing escalated.txt in this workspace earlier. Retry it now exactly once: one single bash call with the command printf 'escalated\\n' > escalated.txt && cat escalated.txt, with sandbox_permissions set to workspace-write and the justification 'the user asked to write escalated.txt in the workspace'. Do not run it without sandbox_permissions first. I will reject the permission prompt; after the rejection, do not retry and do not work around it — explain in one short sentence that the escalation was rejected, then stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783486772552,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783486772552,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783486772552,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783486773136,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783486773136,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783486773275,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -149,7 +149,7 @@ {"type":"assistant/chunk","seq":147,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}}}} {"type":"assistant/chunk","seq":148,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}}}} {"type":"assistant/chunk","seq":149,"time":1783486774569,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":150,"time":1783486774572,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."},{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} +{"type":"assistant/message","seq":150,"time":1783486774572,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to retry the exact command `printf 'escalated\\n' > escalated.txt && cat escalated.txt` with `sandbox_permissions` set to `workspace-write` and the justification they specified. They explicitly say they will reject the permission prompt, so after rejection I should explain in one short sentence and stop."},{"type":"tool-call","id":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1269,"outputTokens":197,"cacheReadTokens":0,"reasoningTokens":70}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149],"surfaceOp":"append"} {"type":"tool/call","seq":151,"time":1783486774572,"data":{"turn":1,"step":1,"callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > escalated.txt && cat escalated.txt\", \"description\": \"Write escalated.txt with workspace-write permission\", \"sandbox_permissions\": \"workspace-write\", \"justification\": \"the user asked to write escalated.txt in the workspace\"}"}} {"type":"approval/asked","seq":152,"time":1783486774574,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","toolName":"bash","callId":"call_00_ODln9LCQtuvTw4FDZEfe3479","reason":"escalate sandbox to workspace-write: the user asked to write escalated.txt in the workspace"}} {"type":"approval/decided","seq":153,"time":1783486774578,"data":{"id":"ed977255-38a3-4c1d-9f4e-0e258ef86e94","outcome":"rejected"}} @@ -197,6 +197,6 @@ {"type":"assistant/chunk","seq":195,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}}}} {"type":"assistant/chunk","seq":196,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}}}} {"type":"assistant/chunk","seq":197,"time":1783486776185,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":198,"time":1783486776186,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user rejected the escalation. I need to explain in one short sentence and stop."},{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}],"usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}},"sourceEventSeqs":[157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197],"surfaceOp":"append"} +{"type":"assistant/message","seq":198,"time":1783486776186,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The user rejected the escalation. I need to explain in one short sentence and stop."},{"type":"text","text":"The escalation request to write to the workspace was rejected, so the command was not executed."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":341,"outputTokens":36,"cacheReadTokens":1152,"reasoningTokens":17}},"sourceEventSeqs":[157,158,159,160,161,162,163,164,165,166,167,168,169,170,171,172,173,174,175,176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197],"surfaceOp":"append"} {"type":"step/end","seq":199,"time":1783486776186,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":200,"time":1783486776186,"data":{"turn":1,"reason":{"kind":"completed"}}} diff --git a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl index ef287390aa..18aa91c7a0 100644 --- a/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl +++ b/examples/sandbox-acp-agent/tests/snapshots/mode-switching/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783613224997,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783613224997,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly: cat notes.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783613224997,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783613224997,"data":{"header":{"config":{"model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783613224997,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command IS denied and a wider mode would let it succeed, escalate immediately in the SAME turn — the ONE sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry IS how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one THIS command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for THAT command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783613225437,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783613225438,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":6,"time":1783613225658,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} @@ -49,7 +49,7 @@ {"type":"assistant/chunk","seq":47,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}}}} {"type":"assistant/chunk","seq":48,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1202,"outputTokens":81,"cacheReadTokens":0,"reasoningTokens":16}}}} {"type":"assistant/chunk","seq":49,"time":1783613226061,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":50,"time":1783613226064,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `cat notes.txt` using the bash tool."},{"type":"tool-call","id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}],"usage":{"inputTokens":1202,"outputTokens":81,"cacheReadTokens":0,"reasoningTokens":16}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"surfaceOp":"append"} +{"type":"assistant/message","seq":50,"time":1783613226064,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run `cat notes.txt` using the bash tool."},{"type":"tool-call","id":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1202,"outputTokens":81,"cacheReadTokens":0,"reasoningTokens":16}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49],"surfaceOp":"append"} {"type":"tool/call","seq":51,"time":1783613226064,"data":{"turn":1,"step":1,"callId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","name":"bash","arguments":"{\"command\": \"cat notes.txt\", \"description\": \"Show contents of notes.txt\"}"}} {"type":"tool/result","seq":52,"time":1783613226148,"data":{"turn":1,"step":1,"callId":"call_00_I9sT0gKlfz9YP4dlf2pA3899","content":[{"type":"text","text":"hello from the sandboxed workspace\n"}],"isError":false},"sourceEventSeqs":[51],"surfaceOp":"append"} {"type":"step/end","seq":53,"time":1783613226148,"data":{"turn":1,"step":1}} @@ -80,7 +80,7 @@ {"type":"assistant/chunk","seq":78,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":79,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":23,"outputTokens":21,"cacheReadTokens":1280,"reasoningTokens":18}}}} {"type":"assistant/chunk","seq":80,"time":1783613227141,"data":{"turn":1,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":81,"time":1783613227142,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":23,"outputTokens":21,"cacheReadTokens":1280,"reasoningTokens":18}},"sourceEventSeqs":[55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80],"surfaceOp":"append"} +{"type":"assistant/message","seq":81,"time":1783613227142,"data":{"turn":1,"step":2,"content":[{"type":"reasoning","text":"The command ran successfully. The user asked me to reply with the single word DONE."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":23,"outputTokens":21,"cacheReadTokens":1280,"reasoningTokens":18}},"sourceEventSeqs":[55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80],"surfaceOp":"append"} {"type":"step/end","seq":82,"time":1783613227142,"data":{"turn":1,"step":2}} {"type":"turn/end","seq":83,"time":1783613227142,"data":{"turn":1,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":84,"time":1783613227169,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -142,7 +142,7 @@ {"type":"assistant/chunk","seq":140,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"tool-call","id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}}}} {"type":"assistant/chunk","seq":141,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":70,"outputTokens":90,"cacheReadTokens":1280,"reasoningTokens":15}}}} {"type":"assistant/chunk","seq":142,"time":1783613228325,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} -{"type":"assistant/message","seq":143,"time":1783613228325,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command. Let me execute it."},{"type":"tool-call","id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}],"usage":{"inputTokens":70,"outputTokens":90,"cacheReadTokens":1280,"reasoningTokens":15}},"sourceEventSeqs":[88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} +{"type":"assistant/message","seq":143,"time":1783613228325,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command. Let me execute it."},{"type":"tool-call","id":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":70,"outputTokens":90,"cacheReadTokens":1280,"reasoningTokens":15}},"sourceEventSeqs":[88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142],"surfaceOp":"append"} {"type":"tool/call","seq":144,"time":1783613228325,"data":{"turn":2,"step":1,"callId":"call_00_htXcbtvwTFK0NqfclLWL7784","name":"bash","arguments":"{\"description\": \"Write and read out.txt\", \"command\": \"printf 'switched\\\\n' > out.txt && cat out.txt\"}"}} {"type":"tool/result","seq":145,"time":1783613228412,"data":{"turn":2,"step":1,"callId":"call_00_htXcbtvwTFK0NqfclLWL7784","content":[{"type":"text","text":"switched\n"}],"isError":false},"sourceEventSeqs":[144],"surfaceOp":"append"} {"type":"step/end","seq":146,"time":1783613228412,"data":{"turn":2,"step":1}} @@ -166,7 +166,7 @@ {"type":"assistant/chunk","seq":164,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"DONE"}}}} {"type":"assistant/chunk","seq":165,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"usage","usage":{"inputTokens":47,"outputTokens":14,"cacheReadTokens":1408,"reasoningTokens":11}}}} {"type":"assistant/chunk","seq":166,"time":1783613229048,"data":{"turn":2,"step":2,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":167,"time":1783613229049,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"Command executed successfully. The output is \"switched\"."},{"type":"text","text":"DONE"}],"usage":{"inputTokens":47,"outputTokens":14,"cacheReadTokens":1408,"reasoningTokens":11}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166],"surfaceOp":"append"} +{"type":"assistant/message","seq":167,"time":1783613229049,"data":{"turn":2,"step":2,"content":[{"type":"reasoning","text":"Command executed successfully. The output is \"switched\"."},{"type":"text","text":"DONE"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":47,"outputTokens":14,"cacheReadTokens":1408,"reasoningTokens":11}},"sourceEventSeqs":[148,149,150,151,152,153,154,155,156,157,158,159,160,161,162,163,164,165,166],"surfaceOp":"append"} {"type":"step/end","seq":168,"time":1783613229049,"data":{"turn":2,"step":2}} {"type":"turn/end","seq":169,"time":1783613229049,"data":{"turn":2,"reason":{"kind":"completed"}}} {"type":"turn/start","seq":170,"time":1783613229056,"data":{"turn":3,"trigger":{"kind":"message","source":{"kind":"user"}}}} @@ -240,6 +240,6 @@ {"type":"assistant/chunk","seq":238,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"Approvals are never asked; any action requiring approval is automatically rejected."}}}} {"type":"assistant/chunk","seq":239,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":1530,"outputTokens":60,"cacheReadTokens":0,"reasoningTokens":45}}}} {"type":"assistant/chunk","seq":240,"time":1783613230689,"data":{"turn":3,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} -{"type":"assistant/message","seq":241,"time":1783613230690,"data":{"turn":3,"step":1,"content":[{"type":"reasoning","text":"The user wants me to state my current approval policy without using any tools. From the context, the approval policy is \"never\" — meaning actions that require approval are rejected automatically, and I should not request sandbox escalation."},{"type":"text","text":"Approvals are never asked; any action requiring approval is automatically rejected."}],"usage":{"inputTokens":1530,"outputTokens":60,"cacheReadTokens":0,"reasoningTokens":45}},"sourceEventSeqs":[176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240],"surfaceOp":"append"} +{"type":"assistant/message","seq":241,"time":1783613230690,"data":{"turn":3,"step":1,"content":[{"type":"reasoning","text":"The user wants me to state my current approval policy without using any tools. From the context, the approval policy is \"never\" — meaning actions that require approval are rejected automatically, and I should not request sandbox escalation."},{"type":"text","text":"Approvals are never asked; any action requiring approval is automatically rejected."}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1530,"outputTokens":60,"cacheReadTokens":0,"reasoningTokens":45}},"sourceEventSeqs":[176,177,178,179,180,181,182,183,184,185,186,187,188,189,190,191,192,193,194,195,196,197,198,199,200,201,202,203,204,205,206,207,208,209,210,211,212,213,214,215,216,217,218,219,220,221,222,223,224,225,226,227,228,229,230,231,232,233,234,235,236,237,238,239,240],"surfaceOp":"append"} {"type":"step/end","seq":242,"time":1783613230690,"data":{"turn":3,"step":1}} {"type":"turn/end","seq":243,"time":1783613230690,"data":{"turn":3,"reason":{"kind":"completed"}}} diff --git a/packages/bash/tool-bash/tests/integration.spec.ts b/packages/bash/tool-bash/tests/integration.spec.ts index a22e86bd99..bc65ae799b 100644 --- a/packages/bash/tool-bash/tests/integration.spec.ts +++ b/packages/bash/tool-bash/tests/integration.spec.ts @@ -74,7 +74,7 @@ describe('bash tool through the agent loop', () => { textResponse('The command printed integration-ok.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-fg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-fg'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run echo integration-ok' }]) await waitForIdle(ctx, agent) @@ -106,7 +106,7 @@ describe('bash tool through the agent loop', () => { textResponse('It failed with code 9.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-exit'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-exit'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run exit 9' }]) await waitForIdle(ctx, agent) @@ -128,7 +128,7 @@ describe('bash tool through the agent loop', () => { let taskId = '' const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-bg'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-bg'), { provider: 'mock', model: 'mock' }) // Capture the generated id so the deterministic fixture is checked against // the real executor instead of silently assuming it. diff --git a/packages/compact/compact-basic/README.md b/packages/compact/compact-basic/README.md index a06e74b818..ce8067dbb3 100644 --- a/packages/compact/compact-basic/README.md +++ b/packages/compact/compact-basic/README.md @@ -11,13 +11,13 @@ The abstract contract states only WHAT compaction does; this backend owns every - **Token estimation** — `estimateContentTokens()`: chars divided by the `charsPerToken` config (default 4) with per-block structural overhead (`text`/`reasoning` = `ceil(len/charsPerToken) + 4`, `tool-call` from name + arguments, `tool-result` recursive, unknown blocks via JSON length). The pressure gate estimates the NEXT request via `estimatePressure()`: the session prefix (the `agent/session-prefix` product — composed by the loop BEFORE the pre-step seam and handed through it, so the gate counts the prefix this instance will actually send in front of the history, never a stale logged one) + the derived history + the system prompt. - **Retention policy** — `compactIfNeeded()` walks the surface nodes tail→head summing per-node token estimates, and retains the smallest tail-run of WHOLE units (a closed step, or a single no-step node such as a pre-step `user/message` or inter-step `steering/message`) whose total reaches `retainTokens`; everything older is compacted. Retention is **turn-agnostic** — turn boundaries play no role, so a single runaway turn that alone exceeds the window compacts its OWN early closed steps rather than being retained verbatim (the failure mode that motivated dropping turn-protection: a tool-heavy turn must stay compactable or the harness dies exactly when compaction is needed). The only structural guard is **tool-pairing balance**: the compacted region's edges are balanced cuts on the surface (no unanswered tool-call crosses either edge), so it never splits a step's `assistant/message` tool-calls from their `tool/result`s. When the only compactable content left is an un-splittable open tail step, it declines (returns `null`) and retries once an older step closes. **Single-unit overflow is out of scope, by design**: if one retained unit (a single closed step, or a large pasted `user/message`) ALONE exceeds the budget, compaction cannot help and the call may go out over-budget — bounding an individual unit's size is a separate concern. `compactRegion()` enforces tool-pairing balance strictly, throwing on a boundary that would split a step. `dsh-session` exports `isToolPairingBalanced` for the check. - **Dynamic convergence** — no static summary-length config pretends to bound what the model will write. If framing/estimator/system overhead leaves the compacted surface above threshold, `compactIfNeeded()` re-compacts the head checkpoint up to `compactionRetries` extra times; if it still cannot get below threshold, it throws. A summary whose estimated stored size is not smaller than the shadowed content fails closed before it mutates the surface. -- **Summarization** — `summarize()`: a `GenerateOptions` request assembled via `BlockAssembler` with a fixed system prompt that asks for a structured checkpoint (Primary Request and Intent · Key Technical Concepts · Files and Code · Errors and Fixes · Pending Tasks · Current Work · Next Step · Critical Context), every section mandatory, exact paths/commands/identifiers preserved. The request is a direct one-shot `ctx.llm.stream()` call — NOT a loop step, so it does not run `agent/request` (that seam shapes the loop's conversation requests); the model comes from `summarizationModel` falling back to the agent's own, and per-call routing happens at `llm/stream` like any other direct call. `maxTokens` is the provider-side generation cap; only text blocks from the model's reply are kept before the checkpoint is stored (reasoning is dropped so private chain-of-thought never leaks into the durable summary, and a stray `tool-call` is dropped so the synthesized `user/message` summary cannot land an orphaned call with no matching `tool-result`). The compacted region is flattened to a plain-text transcript first: text and reasoning contribute their text, and every non-text block (tool-call, tool-result, plugin-added types) contributes a type-tagged placeholder (`[tool-call: name(args)]`, `[tool-result: …]`, …) so the summarizer is told what existed rather than silently dropping it. +- **Summarization** — `summarize()`: a `GenerateOptions` request assembled via `BlockAssembler` with a fixed system prompt that asks for a structured checkpoint (Primary Request and Intent · Key Technical Concepts · Files and Code · Errors and Fixes · Pending Tasks · Current Work · Next Step · Critical Context), every section mandatory, exact paths/commands/identifiers preserved. The request is a direct one-shot `ctx.llm.stream()` call — NOT a loop step, so it does not run `agent/request` (that seam shapes the loop's conversation requests); the target comes from the explicit `summarizationProvider`+`summarizationModel` pair, otherwise the latest logged request pair, otherwise the agent pair. Per-call routing happens at `llm/stream` like any other direct call. `maxTokens` is the provider-side generation cap; only text blocks from the model's reply are kept before the checkpoint is stored (reasoning is dropped so private chain-of-thought never leaks into the durable summary, and a stray `tool-call` is dropped so the synthesized `user/message` summary cannot land an orphaned call with no matching `tool-result`). The compacted region is flattened to a plain-text transcript first: text and reasoning contribute their text, and every non-text block (tool-call, tool-result, plugin-added types) contributes a type-tagged placeholder (`[tool-call: name(args)]`, `[tool-result: …]`, …) so the summarizer is told what existed rather than silently dropping it. - **Checkpoint framing** — the raw summary is not landed directly. `compactRegion()` wraps it in a checkpoint preamble (so a resuming model reads it as a checkpoint, not a fresh user request, and builds on the captured context rather than restating it) plus `…` tags. Because region compaction can be invoked manually, a surface may hold several checkpoints, so the framing does not claim everything after it is recent or verbatim. The tags make a prior checkpoint detectable in the transcript on the next compaction cycle: the summarization prompt then instructs the model to merge it in place (preserve still-true facts, drop stale ones) rather than re-summarize it verbatim — a cheap incremental merge that needs no extra log/event machinery. The unframed summary stays on the `compact/summary` provenance event. - **Surface mutation** — `compactRegion()` appends the `compact/start` → `compact/summary` → `compact/end` log records and the single `user/message` replace node carrying the framed summary (see the interface README). - **Auto-compaction** — an `agent/pre-step` listener delegates to `compactIfNeeded()` before every step (not just a turn's first — a tool-heavy turn grows the surface mid-turn, so a runaway turn still compacts, and per-step firing is the only moment to rescue it before overflow). `agent/pre-step` is a serial (awaited, in-order) surface-mutation checkpoint that fires after `turn/start` and BEFORE the step opens (`step/start`) and its request history is derived, so compaction mutates the surface — with its log-only `compact/*` records landing cleanly outside any step — and the loop derives once from the result: no double-derive, and the listener cannot see (or need to rewrite) an already-assembled `messages` array. The listener owns no threshold logic of its own (the single token-pressure check lives in `compactIfNeeded()`); because Cordis `serial` bails early on non-void return values, the listener returns `void` and does not use the dispatcher's bail channel as a veto surface. - **Failure handling** — the `compact/start … compact/end` bracket is a log-recorded lock: it makes a crash mid-summarization a detectable orphan (a `compact/start` with no `compact/end`), records provenance, and prevents a concurrent compaction. Two failure paths: a **crash** (the loop dies mid-summarization) leaves a dangling `compact/start` that is inert — `compact/*` events are log-only, the surface replacement never landed, so the full history derives fine and generic turn-repair closes the turn; a **recoverable** failure (summarization throws but the loop survives) appends `compact/end` with its `error` field set, leaving the surface untouched so the call proceeds with full history. Core session repair stays compaction-agnostic by design — it never learns about `compact/*`. -`estimateContentTokens()` and `summarize()` are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the retention walk and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. +`estimateContentTokens()` and `summarize()` are overridable hooks: a tokenizer-based or template-based backend can subclass `BasicCompactService` and override just those, reusing the retention walk and surface plumbing. `summarize()` returns the summary blocks together with the call envelope it actually used (`{ summary, provider, model, maxTokens? }`) — the caller logs that envelope on the `compact/summary` provenance event, so an overriding backend reports its own envelope honestly. ## Config (`BasicCompactConfig`) @@ -28,7 +28,8 @@ Every knob is **required** except `auto` — there is no concrete data yet to ju | `contextWindow` | yes | Context window size in tokens. | | `thresholdRatio` | yes | Compact when estimated usage exceeds this fraction of the window. | | `retainTokens` | yes | Tokens of recent context to keep intact. | -| `summarizationModel` | yes | Model for summarization (`''` → use the agent's model). | +| `summarizationProvider` | yes | Provider for summarization (`''` together with an empty model → use the latest logged request pair, then the agent pair). | +| `summarizationModel` | yes | Model for summarization (`''` together with an empty provider → use the latest logged request pair, then the agent pair). | | `maxTokens` | yes | Provider generation cap for the summarization call; may include reasoning tokens. | | `compactionRetries` | yes | Extra compaction attempts after the first if the compacted surface remains over threshold. | | `auto` | no (default `true`) | Register the `agent/pre-step` auto-compaction listener. Set `false` for manual-only. | @@ -48,6 +49,7 @@ export function apply(ctx: Context): void { contextWindow: 128000, thresholdRatio: 0.8, retainTokens: 20480, + summarizationProvider: '', summarizationModel: '', maxTokens: 8192, compactionRetries: 1, diff --git a/packages/compact/compact-basic/src/index.ts b/packages/compact/compact-basic/src/index.ts index c0d4ff483a..32dc8bf9aa 100644 --- a/packages/compact/compact-basic/src/index.ts +++ b/packages/compact/compact-basic/src/index.ts @@ -294,8 +294,8 @@ export class BasicCompactService extends CompactService { * loop step: it does not run the `agent/request` waterfall (that seam shapes * the loop's conversation requests); per-call * interception happens at `llm/stream` like any other direct call. The model - * comes from `BasicCompactConfig.summarizationModel`, falling back to the - * agent's own model. + * target comes from the explicit summarization provider/model pair, falling + * back to the last logged request target and then the agent's creation options. * Override in a subclass for a template or remote summarizer. * * Honors the adapter failure contract: an adapter may report a model failure @@ -307,23 +307,27 @@ export class BasicCompactService extends CompactService { * down the in-flight summarization rather than orphaning the model call. * * Returns the summary blocks TOGETHER with the call envelope it actually - * used (`model`, `maxTokens`) — the caller logs the envelope on the + * used (`provider`, `model`, `maxTokens`) — the caller logs the envelope on the * `compact/summary` provenance event, so an overriding subclass (template * or remote summarizer) reports its own envelope honestly. * * @param text - plain-text rendering of the conversation region to condense. - * @param agent - supplies the fallback model and the session id stamped on - * the call; throws when neither it nor the config names a model. + * @param agent - supplies the request-header/creation fallback target and the + * session id stamped on the call; throws when no complete target exists. * @param signal - optional abort signal, forwarded into the model call. * @returns the text-only summary blocks plus the call envelope used - * (`model`, and `maxTokens` when the summarizer has a cap). + * (`provider`, `model`, and `maxTokens` when the summarizer has a cap). */ async summarize( text: string, agent: Agent, signal?: AbortSignal, - ): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { + ): Promise<{ summary: ContentBlock[]; provider: string; model: string; maxTokens?: number }> { const assembler = new BlockAssembler() + const logged = agent.session.requestHeader()?.config + const provider = this.config.summarizationProvider || logged?.provider || agent.options.provider || '' + const model = this.config.summarizationModel || logged?.model || agent.options.model || '' const options: GenerateOptions = { - model: this.config.summarizationModel || agent.options.model || '', + provider, + model, messages: [{ role: 'user', content: [{ type: 'text', text: `Summarize this conversation history:\n\n${text}\n\nSummary:` }], @@ -335,8 +339,8 @@ export class BasicCompactService extends CompactService { // exactOptionalPropertyTypes: only set `signal` when present — assigning // `undefined` to an optional `signal?: AbortSignal` is a type error. if (signal) options.signal = signal - if (!options.model) { - throw new Error('no model available for summarization: set BasicCompactConfig.summarizationModel or AgentOptions.model') + if (!options.provider || !options.model) { + throw new Error('no provider/model available for summarization: set both summarization fields or provide a logged/agent target') } for await (const chunk of this.ctx.llm.stream(options)) { assembler.push(chunk) @@ -353,7 +357,7 @@ export class BasicCompactService extends CompactService { // config.maxTokens is required and validated positive, so this backend's // envelope always carries the cap; the return type's optionality exists // for overriding subclasses whose summarizer has none. - return { summary, model: options.model, maxTokens: this.config.maxTokens } + return { summary, provider: options.provider, model: options.model, maxTokens: this.config.maxTokens } } // ---- Core API (implements the abstract contract) ---- @@ -511,7 +515,7 @@ export class BasicCompactService extends CompactService { try { // --- Extract text and summarize --- const text = renderTranscript(session.events, shadowedSeqs) - const { summary, model, maxTokens } = await this.summarize(text, agent, signal) + const { summary, provider, model, maxTokens } = await this.summarize(text, agent, signal) // Estimate token count of the shadowed content for provenance. let shadowedTokenCount = 0 @@ -533,6 +537,7 @@ export class BasicCompactService extends CompactService { shadowedRange: { start, end }, shadowedSeqs, shadowedTokenCount, + provider, model, ...maxTokens !== undefined ? { maxTokens } : {}, }) diff --git a/packages/compact/compact-basic/src/types.ts b/packages/compact/compact-basic/src/types.ts index a590c01431..741412f421 100644 --- a/packages/compact/compact-basic/src/types.ts +++ b/packages/compact/compact-basic/src/types.ts @@ -24,7 +24,9 @@ export interface BasicCompactConfig { thresholdRatio: number /** Number of tokens of recent context to retain during compaction. */ retainTokens: number - /** Model to use for summarization (`''` — uses the agent's model). */ + /** Provider to use for summarization (`''` with an empty model inherits the conversation target). */ + summarizationProvider: string + /** Model to use for summarization (`''` with an empty provider inherits the conversation target). */ summarizationModel: string /** Provider generation cap for the summarization call. */ maxTokens: number @@ -70,6 +72,12 @@ export function resolveConfig(config: BasicCompactConfig): ResolvedConfig { if (typeof resolved.summarizationModel !== 'string') { throw new Error('BasicCompactConfig: summarizationModel must be a string.') } + if (typeof resolved.summarizationProvider !== 'string') { + throw new Error('BasicCompactConfig: summarizationProvider must be a string.') + } + if ((resolved.summarizationProvider.length === 0) !== (resolved.summarizationModel.length === 0)) { + throw new Error('BasicCompactConfig: summarizationProvider and summarizationModel must both be empty or both be set.') + } if (typeof resolved.auto !== 'boolean') { throw new Error('BasicCompactConfig: auto must be a boolean.') } diff --git a/packages/compact/compact-basic/tests/compact-basic.spec.ts b/packages/compact/compact-basic/tests/compact-basic.spec.ts index e47ca434e3..71193f6c7f 100644 --- a/packages/compact/compact-basic/tests/compact-basic.spec.ts +++ b/packages/compact/compact-basic/tests/compact-basic.spec.ts @@ -21,6 +21,7 @@ const TEST_CONFIG: BasicCompactConfig = { contextWindow: 128000, thresholdRatio: 0.8, retainTokens: 20480, + summarizationProvider: '', summarizationModel: '', maxTokens: 8192, compactionRetries: 1, @@ -58,13 +59,17 @@ class TestCompactService extends BasicCompactService { return blocks.length * 10 } - override async summarize(text: string, agent: Agent): Promise<{ summary: ContentBlock[]; model: string; maxTokens?: number }> { + override async summarize( + text: string, + agent: Agent, + ): Promise<{ summary: ContentBlock[]; provider: string; model: string; maxTokens?: number }> { + const provider = this.config.summarizationProvider || agent.options.provider || '' const model = this.config.summarizationModel || agent.options.model || '' this.summarizeCalls.push({ text, model }) if (this.summarizeError) throw this.summarizeError const summary = this.mockSummaryQueue.shift() ?? this.mockSummary this.summaryOutputs.add(summary) - return { summary, model } + return { summary, provider, model } } } @@ -102,7 +107,7 @@ function multiTurnSession(turns: number, messagesPerTurn: number = 2, opts: { le content: [{ type: 'text', text: `turn ${t} user message ${m + 1}.${LONG_FIXTURE_TEXT}` }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: t, step: 1, content: [{ type: 'text', text: `turn ${t} assistant response ${m + 1}.${LONG_FIXTURE_TEXT}` }], }, { surfaceOp: 'append' }) @@ -127,7 +132,7 @@ function sessionWithTools(): Session { content: [{ type: 'text', text: 'read file x' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'text', text: 'Let me read that file.' }, @@ -140,7 +145,7 @@ function sessionWithTools(): Session { content: [{ type: 'text', text: 'hello world' }], isError: false, }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'The file contains: hello world' }], }, { surfaceOp: 'append' }) @@ -169,7 +174,7 @@ function toolTurnSession(turns: number): Session { source: { kind: 'user' }, }, { surfaceOp: 'append' }) s.append('step/start', { turn: t, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: t, step: 1, content: [ { type: 'text', text: `turn ${t} calling tool` }, @@ -240,7 +245,7 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai const s = new Session(SessionId('one-step')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'calling' }, { type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -286,7 +291,7 @@ describe('BasicCompactService step-alignment (never split a tool-call/result pai s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('user/message', { content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -348,7 +353,7 @@ describe('BasicCompactService.estimateEventTokens', () => { const userEvent: SessionEvent = { type: 'user/message', seq: 0, time: 1, data: { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } } } expect(svc.estimateEventTokens(userEvent)).toBe(10) - const asstEvent: SessionEvent = { type: 'assistant/message', seq: 1, time: 2, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }, { type: 'text', text: 'b' }] } } + const asstEvent: SessionEvent = { type: 'assistant/message', seq: 1, time: 2, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }, { type: 'text', text: 'b' }], provenance: { provider: 'mock', model: 'mock' } } } expect(svc.estimateEventTokens(asstEvent)).toBe(20) const toolEvent: SessionEvent = { type: 'tool/result', seq: 2, time: 3, data: { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'output' }], isError: false } } @@ -633,7 +638,7 @@ describe('BasicCompactService.compactIfNeeded', () => { s.append('user/message', { content: [{ type: 'text', text: 'do a big multi-step task' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) for (let step = 1; step <= 5; step++) { s.append('step/start', { turn: 1, step }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step, content: [{ type: 'text', text: `step ${step}` }, { type: 'tool-call', id: CallId(`c${step}`), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -686,7 +691,7 @@ describe('BasicCompactService.compactIfNeeded', () => { // the fresh nodes are retained. s.append('step/start', { turn: 5, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'turn 5 work' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 5, step: 1, content: [{ type: 'text', text: 'reply 5' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 5, step: 1, content: [{ type: 'text', text: 'reply 5' }] }, { surfaceOp: 'append' }) s.append('step/end', { turn: 5, step: 1 }) const second = await compactIfNeeded(svc, s, '', 'm', SIGNAL) @@ -785,7 +790,7 @@ describe('BasicCompactService blocking (compaction in progress)', () => { s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'turn 1' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply 1' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'reply 1' }] }, { surfaceOp: 'append' }) s.append('compact/start', { turn: 1 }) // ← orphaned: no matching compact/end s.append('step/end', { turn: 1, step: 1 }) s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) // repair closed the turn @@ -991,7 +996,7 @@ async function ctxWithFinish(reason: (StreamChunk & { type: 'finish' })['reason' /** A minimal Agent stub carrying just session + options (enough for the listeners). */ function stubAgent(session: Session, model?: string): Agent { - return { session, options: { model } } as unknown as Agent + return { session, options: { provider: model, model } } as unknown as Agent } function compactIfNeeded( @@ -1076,7 +1081,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { it('throws when no model is provided', async () => { const { ctx } = await ctxWithModel('x') const svc = new BasicCompactService(ctx, cfg({ auto: false })) - await expect(summarize(svc, 'text', '')).rejects.toThrow(/no model available/) + await expect(summarize(svc, 'text', '')).rejects.toThrow(/no provider\/model available/) }) it('rethrows when the stream ends with a finish-error chunk', async () => { @@ -1153,7 +1158,7 @@ describe('BasicCompactService.summarize (real ctx.llm.stream)', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) session.append('user/message', { content: [{ type: 'text', text: 'tiny user' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'tiny assistant' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'tiny assistant' }] }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 1 }) session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) @@ -1262,9 +1267,10 @@ describe('BasicCompactService auto-compaction (agent/pre-step listener)', () => // The summarize call is a direct one-shot model call, not a loop step: it // does not run agent/request (that seam shapes the loop's conversation // requests). llm/stream is its interception surface, and a hand-built - // request is not frozen, so mutate-then-next model routing works — the - // adapter resolves AFTER the waterfall, so the rewrite picks the adapter. + // request is not frozen, so mutate-then-next provider/model routing works — + // the adapter resolves AFTER the waterfall, so the rewrite picks it. ctx.on('llm/stream', (options, next) => { + options.provider = 'routed-model' options.model = 'routed-model' return next() }) @@ -1307,7 +1313,7 @@ describe('BasicCompactService transcript rendering (delegated to dsh-compact)', content: [{ type: 'text', text: 'project context here' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'reasoning', text: 'thinking hard' }, { type: 'text', text: 'answer' }], }, { surfaceOp: 'append' }) @@ -1335,7 +1341,7 @@ describe('BasicCompactService transcript rendering (delegated to dsh-compact)', s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'run it' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c9'), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -1364,7 +1370,7 @@ describe('BasicCompactService edge cases', () => { // assistant/message carrying a nested tool-result block, an unknown block, // and the tool-call that the following tool/result answers (so the surface // is tool-pairing balanced). - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'tool-result', toolCallId: CallId('n1'), content: [{ type: 'chart', data: 'x' } as unknown as ContentBlock] }, @@ -1427,7 +1433,7 @@ describe('BasicCompactService edge cases', () => { s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'orphan' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' }) s.append('step/end', { turn: 1, step: 1 }) s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) const nodes = s.surface.nodes @@ -1522,7 +1528,7 @@ describe('BasicCompactService edge cases', () => { // nothing and are skipped. s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'reasoning', text: '' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'reasoning', text: '' }] }, { surfaceOp: 'append' }) s.append('context/message', { content: [], source: { kind: 'user' } }, { surfaceOp: 'append' }) s.append('steering/message', { turn: 1, content: [{ type: 'text', text: '' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) s.append('step/end', { turn: 1, step: 1 }) @@ -1531,7 +1537,7 @@ describe('BasicCompactService edge cases', () => { // surface stays tool-pairing balanced; its text extracts to the tool-call // placeholder (the one surviving line). s.append('step/start', { turn: 1, step: 2 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [{ type: 'tool-call', id: CallId('z1'), name: 'bash', arguments: '{}' }], }, { surfaceOp: 'append' }) @@ -1562,7 +1568,7 @@ describe('BasicCompactService edge cases', () => { s.append('user/message', { content: [chart('y')], source: { kind: 'user' } }, { surfaceOp: 'append' }) // assistant/message with a plugin-added block AND the tool-call its // tool/result answers (so the surface is tool-pairing balanced). - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ chart('z'), @@ -1713,7 +1719,7 @@ describe('BasicCompactService under the real invariants plugin', () => { session.append('turn/start', { turn, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn, step: 1 }) session.append('user/message', { content: [{ type: 'text', text: `turn ${turn} user.${LONG_FIXTURE_TEXT}` }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn, step: 1, content: [{ type: 'text', text: `turn ${turn} assistant.${LONG_FIXTURE_TEXT}` }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn, step: 1, content: [{ type: 'text', text: `turn ${turn} assistant.${LONG_FIXTURE_TEXT}` }] }, { surfaceOp: 'append' }) session.append('step/end', { turn, step: 1 }) session.append('turn/end', { turn, reason: { kind: 'completed' } }) } diff --git a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts index 1efb417b48..acee9036ed 100644 --- a/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts +++ b/packages/compact/compact-basic/tests/compact-loop-repro.spec.ts @@ -41,8 +41,8 @@ class ReproCompactService extends BasicCompactService { return blocks.length * TOKENS_PER_BLOCK } - override async summarize(): Promise<{ summary: ContentBlock[]; model: string }> { - return { summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }], model: 'stub' } + override async summarize(): Promise<{ summary: ContentBlock[]; provider: string; model: string }> { + return { summary: [{ type: 'text', text: 'CHECKPOINT SUMMARY' }], provider: 'mock', model: 'stub' } } } @@ -97,6 +97,7 @@ async function harness(toolSteps: number): Promise<{ ctx: Context; compact: Repr contextWindow: 64, thresholdRatio: 0.5, retainTokens: 20, + summarizationProvider: '', summarizationModel: '', maxTokens: 8192, compactionRetries: 1, @@ -119,7 +120,7 @@ describe('CBR-001: a real-loop checkpoint is a valid boundary on both sides', () it('the head checkpoint the loop lands is a balanced cut on both sides', async () => { const { ctx } = await harness(8) try { - const agent = ctx.agentLoop.create(AgentId('repro'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('repro'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'do a long multi-step task' }]) await waitForIdle(ctx, agent) diff --git a/packages/compact/compact/README.md b/packages/compact/compact/README.md index e98f00899f..4c45ec2d6f 100644 --- a/packages/compact/compact/README.md +++ b/packages/compact/compact/README.md @@ -29,7 +29,7 @@ Both methods are **abstract** — the backend owns the entire strategy (token es 1. appends `compact/start` (log-only) — acquires the lock, 2. summarizes the range, -3. appends `compact/summary` (log-only) — provenance: summary, range, shadowed seqs, token count, +3. appends `compact/summary` (log-only) — provenance: summary, range, shadowed seqs, token count, and provider/model call envelope, 4. appends a single `user/message` with `surfaceOp: { op: 'replace', start, end }` carrying the summary — **the only surface mutation**, 5. appends `compact/end` (log-only) — releases the lock. diff --git a/packages/compact/compact/src/types.ts b/packages/compact/compact/src/types.ts index ba9834910f..0ef28a4ff6 100644 --- a/packages/compact/compact/src/types.ts +++ b/packages/compact/compact/src/types.ts @@ -32,6 +32,8 @@ declare module '@deepseek-ai/dsh-session' { shadowedRange: { start: number; end: number } shadowedSeqs: number[] shadowedTokenCount: number + /** The provider route that wrote the summary. */ + provider: string /** * The model that wrote the summary — the summarize call's envelope, * reported by the backend that made the call, logged so the one-shot diff --git a/packages/compact/compact/tests/compact.spec.ts b/packages/compact/compact/tests/compact.spec.ts index c4daa8cc5a..f272b1fe85 100644 --- a/packages/compact/compact/tests/compact.spec.ts +++ b/packages/compact/compact/tests/compact.spec.ts @@ -41,6 +41,7 @@ class StubCompactService extends CompactService { shadowedRange: { start, end }, shadowedSeqs: [], shadowedTokenCount: 0, + provider: 'mock', model: 'stub', }) const endEvent = session.append('compact/end', { turn: 0 }) diff --git a/packages/compact/compact/tests/render.spec.ts b/packages/compact/compact/tests/render.spec.ts index 1a22296565..3b4bb41ac2 100644 --- a/packages/compact/compact/tests/render.spec.ts +++ b/packages/compact/compact/tests/render.spec.ts @@ -54,7 +54,7 @@ describe('renderTranscript', () => { content: [{ type: 'text', text: 'fix the bug' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - const assistant = s.append('assistant/message', { + const assistant = s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 0, step: 0, content: [{ type: 'text', text: 'looking' }], }, { surfaceOp: 'append' }) @@ -111,7 +111,7 @@ describe('renderTranscript', () => { content: [{ type: 'text', text: '' }], source: { kind: 'user' }, }, { surfaceOp: 'append' }) - const emptyAssistant = s.append('assistant/message', { + const emptyAssistant = s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 0, step: 0, content: [{ type: 'text', text: '' }], }, { surfaceOp: 'append' }) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index b4420e80c7..e3d7665ea6 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -129,8 +129,8 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ key: 'llm', summary: 'The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.', methods: [ - 'registerAdapter(models: string[], adapter: LlmAdapter): () => void', - 'models(): string[]', + 'registerAdapter(providers: string[], adapter: LlmAdapter): () => void', + 'providers(): string[]', 'stream(options: GenerateOptions): AsyncIterable', ], }, @@ -504,7 +504,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'AgentOptions', - declaration: 'export interface AgentOptions {\n model?: string;\n}', + declaration: 'export interface AgentOptions {\n provider?: string;\n model?: string;\n}', }, { name: 'AgentStatus', @@ -546,6 +546,10 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'AssembledSection', declaration: 'export interface AssembledSection {\n name: string;\n order: number;\n text: string;\n}', }, + { + name: 'AssistantProvenance', + declaration: 'export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n}', + }, { name: 'BashExecRequest', declaration: 'export interface BashExecRequest {\n command: string;\n workdir?: string | undefined;\n timeoutMs?: number | undefined;\n signal?: AbortSignal | undefined;\n stdin?: string | undefined;\n env?: Record | undefined;\n owner?: OwnerToken | undefined;\n sandboxMode?: SandboxMode | undefined;\n}', @@ -712,7 +716,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'GenerateOptions', - declaration: 'export interface GenerateOptions {\n model: string;\n messages: Message[];\n system?: string;\n tools?: ToolSchema[];\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n signal?: AbortSignal;\n sessionId?: Branded<\'SessionId\'>;\n}', + declaration: 'export interface GenerateOptions {\n provider: string;\n model: string;\n messages: Message[];\n system?: string;\n tools?: ToolSchema[];\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n signal?: AbortSignal;\n sessionId?: Branded<\'SessionId\'>;\n}', }, { name: 'GenericCallView', @@ -728,7 +732,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'Message', - declaration: 'export interface Message {\n role: \'system\' | \'user\' | \'assistant\';\n content: ContentBlock[];\n}', + declaration: 'export interface Message {\n role: \'system\' | \'user\' | \'assistant\';\n content: ContentBlock[];\n provenance?: AssistantProvenance;\n}', }, { name: 'MessageSource', @@ -784,7 +788,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SessionEventMap', - declaration: 'export interface SessionEventMap {\n \'turn/start\': {\n turn: number;\n trigger: TurnTrigger;\n };\n \'turn/end\': {\n turn: number;\n reason: TurnEndReason;\n };\n \'step/start\': {\n turn: number;\n step: number;\n };\n \'step/end\': {\n turn: number;\n step: number;\n };\n \'user/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'prompt/blocked\': {\n content: ContentBlock[];\n source: MessageSource;\n reason: string;\n };\n \'context/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'assistant/chunk\': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n \'assistant/message\': {\n turn: number;\n step: number;\n content: ContentBlock[];\n usage?: TokenUsage;\n };\n \'tool/call\': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n \'tool/result\': {\n turn: number;\n step: number;\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: {\n name: string;\n code: string;\n };\n meta?: unknown;\n };\n \'steering/message\': {\n turn: number;\n content: ContentBlock[];\n source: MessageSource;\n };\n \'todo/write\': {\n todos: TodoItem[];\n };\n \'request/header\': {\n header: E /* …truncated — full shape in source */', + declaration: 'export interface SessionEventMap {\n \'turn/start\': {\n turn: number;\n trigger: TurnTrigger;\n };\n \'turn/end\': {\n turn: number;\n reason: TurnEndReason;\n };\n \'step/start\': {\n turn: number;\n step: number;\n };\n \'step/end\': {\n turn: number;\n step: number;\n };\n \'user/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'prompt/blocked\': {\n content: ContentBlock[];\n source: MessageSource;\n reason: string;\n };\n \'context/message\': {\n content: ContentBlock[];\n source: MessageSource;\n };\n \'assistant/chunk\': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n \'assistant/message\': {\n turn: number;\n step: number;\n content: ContentBlock[];\n provenance: AssistantProvenance;\n usage?: TokenUsage;\n };\n \'tool/call\': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n \'tool/result\': {\n turn: number;\n step: number;\n callId: CallId;\n content: ContentBlock[];\n isError: boolean;\n error?: {\n name: string;\n code: string;\n };\n meta?: unknown;\n };\n \'steering/message\': {\n turn: number;\n content: ContentBlock[];\n source: MessageSource;\n };\n \'todo/write\': {\n todos: TodoItem[];\n };\n /* …truncated — full shape in source */', }, { name: 'SessionEventType', @@ -836,7 +840,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { 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};', + 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 replayState?: unknown;\n};', }, { name: 'StructuredOutputSchema', @@ -1040,7 +1044,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'WorkflowPhase', - declaration: 'export interface WorkflowPhase {\n title: string;\n detail?: string;\n model?: string;\n}', + declaration: 'export interface WorkflowPhase {\n title: string;\n detail?: string;\n provider?: string;\n model?: string;\n}', }, { name: 'WorkflowResult', diff --git a/packages/cordis/tool-cordis/tests/integration.spec.ts b/packages/cordis/tool-cordis/tests/integration.spec.ts index 94331df7c0..540339bc93 100644 --- a/packages/cordis/tool-cordis/tests/integration.spec.ts +++ b/packages/cordis/tool-cordis/tests/integration.spec.ts @@ -51,7 +51,7 @@ describe('cordis tools through the agent loop', () => { textResponse('Done.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-cordis'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-cordis'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'give yourself reverse_text, use it, clean up' }]) await waitForIdle(ctx, agent) diff --git a/packages/core/agent-core/tests/agent-core.spec.ts b/packages/core/agent-core/tests/agent-core.spec.ts index 855bb28d49..54eb102a54 100644 --- a/packages/core/agent-core/tests/agent-core.spec.ts +++ b/packages/core/agent-core/tests/agent-core.spec.ts @@ -108,7 +108,7 @@ describe('dsh-agent-core bundle', () => { it('forwards a pre-created agent to the loop and the persona to system-prompt', async () => { const ctx = await mount({ - agents: [{ id: AgentId('main'), model: 'mock' }], + agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock' }], persona: 'You are main.', }) expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 6832800d2e..0d9e09c687 100644 --- a/packages/core/agent-loop/README.md +++ b/packages/core/agent-loop/README.md @@ -33,6 +33,7 @@ The config-driven `ctx.agentLoop.create()` path keeps its agent owned by the loo interface Config { agents: Array<{ id: string // required + provider?: string model?: string resumeSessionId?: string // load this persisted session instead of creating one cwd?: string // optional workspace cwd for the fresh session @@ -40,7 +41,7 @@ interface Config { } ``` -Agents listed in config are auto-created at startup. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. +Agents listed in config are auto-created at startup. A model call requires both `provider` and `model`; a request-waterfall listener may supply the pair before dispatch when they are absent from creation options. `cwd` applies only to fresh config-created sessions; `resumeSessionId` keeps the persisted session header. Config agents have no per-agent persona field: they use `dsh-system-prompt`'s deployment default, while programmatic factory callers can register an agent-scoped `deployment:persona` shadow in `setup`. The plugin registers the built-in `provider`/`model`/`cwd` prompt variables on `ctx.systemPrompt`, resolved per step from `assembleContextFor(agent)` — the helper couples the typed agent with its matching scope selector. These are runtime facts of the agents THIS loop drives, unlike the `harness:identity` and default `deployment:persona` sections, which live on `dsh-system-prompt` so they survive a swapped loop plugin. ### Exported concrete class diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 4ad4779176..6ecde4f088 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/packages/core/agent-loop/src/index.ts @@ -342,6 +342,7 @@ export class AgentLoop extends Service implements AgentFactory { static Config = z.object({ agents: z.array(z.object({ id: z.string().required(), + provider: z.string(), model: z.string(), cwd: z.string(), resumeSessionId: z.string(), @@ -358,6 +359,7 @@ export class AgentLoop extends Service implements AgentFactory { this.runtime = { ctx } ctx.effect(() => () => this.ownership.dispose(), 'agentLoop.transactions()') ctx.effect(() => ctx.agents.setFactory(this), 'agentLoop.setFactory()') + ctx.systemPrompt.variable('provider', context => context.agent?.options.provider) ctx.systemPrompt.variable('model', context => context.agent?.options.model) ctx.systemPrompt.variable('cwd', context => context.agent?.session.header.cwd) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 7a7ca2e28c..5c4ab89f05 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -9,6 +9,7 @@ import type { Context } from 'cordis' import type { FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm' +import { isDeepStrictEqual } from 'node:util' import { BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision } from '@deepseek-ai/dsh-agent' @@ -757,7 +758,7 @@ async function runStep( const seedConfig: LlmCallConfig = deepFreeze(structuredClone(transmission.loggedHeader // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- loggedHeader ⟹ a snapshot is in the log ? session.requestHeader()!.config - : { model: options.model ?? '' })) + : { provider: options.provider ?? '', model: options.model ?? '' })) // Shape the call config: listeners return a replacement to switch model or // sampling (the seed is frozen — content shaping is not expressible here; @@ -765,8 +766,8 @@ async function runStep( // below records whatever the request ACTUALLY uses, so a listener's switch // is a logged, reconstructable fact, never silent drift. const config = await events.waterfall('agent/request', turn, step, seedConfig, () => Promise.resolve(seedConfig)) - if (!config.model) { - throw new Error(`agent "${agent.id}" has no model: set AgentOptions.model or supply one via the agent/request waterfall`) + if (!config.provider || !config.model) { + throw new Error(`agent "${agent.id}" has no provider/model: set AgentOptions.provider and AgentOptions.model or supply both via the agent/request waterfall`) } // The session prefix was composed (once per instance) before this step's @@ -791,6 +792,7 @@ async function runStep( // keys on. Message order: header.messagePrefix, then the boundary // snapshot — the reconstruction equation the invariant recomputes. const request: GenerateOptions = deepFreeze({ + provider: header.config.provider, model: header.config.model, messages: [...header.messagePrefix ?? [], ...boundaryMessages], ...header.system !== undefined ? { system: header.system } : {}, @@ -822,7 +824,8 @@ async function runStep( if (stepError) throw stepError if (assembler.finish.kind === 'max-tokens') { - let message: Message = withoutToolCalls(assembler.message()) + const assembled = assembler.message() + let message: Message = withoutToolCalls(assembled) message = withoutToolCalls(await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message))) // Fire the assistant/message when there is content OR usage: a max-tokens // step can be cut off with empty content but still carry token accounting, @@ -830,22 +833,15 @@ async function runStep( // usage event). An empty-content assistant/message is skipped by // deriveMessages(), so hosting usage on it never injects a spurious assistant // turn into derived history. - if (message.content.length > 0 || assembler.usage) { - // A max-tokens finish is itself a streamed `finish` chunk, so chunkSeqs is - // never empty here — pass the provenance unconditionally. - session.append( - 'assistant/message', - { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, - { surfaceOp: 'append', sourceEventSeqs: chunkSeqs }, - ) - } + recordAssistantMessage(session, turn, step, header.config, assembled, message, assembler, chunkSeqs) return { hadToolCalls: false, finish: assembler.finish } } // The step-result waterfall runs BEFORE the session append so the log (the // source of truth for derived history and replay) records the message that // tool dispatch actually uses. - let message: Message = assembler.message() + const assembled = assembler.message() + let message: Message = assembled message = await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message)) // Same content-or-usage guard as the max-tokens branch: a step that finishes @@ -856,13 +852,7 @@ async function runStep( // // sourceEventSeqs records the assistant/chunk provenance, but is omitted when // no chunks streamed (the surface invariant rejects an empty sourceEventSeqs). - if (message.content.length > 0 || assembler.usage) { - session.append( - 'assistant/message', - { turn, step, content: message.content, ...(assembler.usage ? { usage: assembler.usage } : {}) }, - { surfaceOp: 'append', ...(chunkSeqs.length > 0 ? { sourceEventSeqs: chunkSeqs } : {}) }, - ) - } + recordAssistantMessage(session, turn, step, header.config, assembled, message, assembler, chunkSeqs) // --- Tool execution (sequential; parallel execution is a TODO) --- // ToolRegistry.execute converts tool failures (including aborts) into @@ -933,6 +923,44 @@ async function runStep( return { hadToolCalls: toolCalls.length > 0, finish: assembler.finish } } +/** Record one content-or-usage assistant message with replay-safe provenance. */ +function recordAssistantMessage( + session: Session, + turn: number, + step: number, + config: LlmCallConfig, + assembled: Message, + message: Message, + assembler: BlockAssembler, + chunkSeqs: number[], +): void { + if (message.content.length === 0 && assembler.usage === undefined) return + session.append( + 'assistant/message', + { + turn, + step, + content: message.content, + provenance: assistantProvenance( + config, + assembler.replayState, + isDeepStrictEqual(message.content, assembled.content), + ), + ...assembler.usage === undefined ? {} : { usage: assembler.usage }, + }, + { surfaceOp: 'append', ...chunkSeqs.length > 0 ? { sourceEventSeqs: chunkSeqs } : {} }, + ) +} + +/** Build durable assistant provenance, dropping replay state after any content rewrite. */ +function assistantProvenance(config: LlmCallConfig, replayState: unknown, contentUnchanged: boolean): NonNullable { + return { + provider: config.provider, + model: config.model, + ...contentUnchanged && replayState !== undefined ? { replayState } : {}, + } +} + function withoutToolCalls(message: Message): Message { return { ...message, content: message.content.filter(block => block.type !== 'tool-call') } } diff --git a/packages/core/agent-loop/tests/agent.spec.ts b/packages/core/agent-loop/tests/agent.spec.ts index 7f65bbc5f3..3d42e8e088 100644 --- a/packages/core/agent-loop/tests/agent.spec.ts +++ b/packages/core/agent-loop/tests/agent.spec.ts @@ -53,10 +53,10 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('exclusive-driver')) - const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, AgentId('first-driver'), { provider: 'mock', model: 'mock' }, session) expect(() => prepared.agent.ctx).toThrow('context is not bound') - expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { model: 'mock' }, session)) + expect(() => prepareReactLoopAgent(ctx, AgentId('second-driver'), { provider: 'mock', model: 'mock' }, session)) .toThrow('already has a concrete agent driver') await prepared.dispose() @@ -65,7 +65,7 @@ describe('ReactLoopAgent', () => { it('borrows caller options and binds its scoped context exactly once', async () => { const ctx = await harness(new MockAdapter([textResponse('unused')])) - const options = { model: 'mock' } + const options = { provider: 'mock', model: 'mock' } const agent = ctx.agentLoop.create(AgentId('owned-bindings'), options) expect(agent.options).toBe(options) @@ -81,7 +81,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -96,7 +96,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -111,7 +111,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -124,7 +124,7 @@ describe('ReactLoopAgent', () => { it('inject() decides enclosure from the LOG (open turn), not agent status', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Simulate an OPEN turn in the log while the agent is idle (status is not a // reliable open-turn signal). inject must append into that open turn, NOT @@ -150,7 +150,7 @@ describe('ReactLoopAgent', () => { // A persistence-like listener whose flush rejects. ctx.on('session/flush', () => { throw new Error('disk gone') }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // inject() is synchronous and fires a fire-and-forget flush; a rejecting // flush must be contained (logged), never thrown into the caller. @@ -163,7 +163,7 @@ describe('ReactLoopAgent', () => { it('idle inject() closes its one-shot turn AND still checkpoints even if the append throws', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) @@ -183,7 +183,7 @@ describe('ReactLoopAgent', () => { it('idle inject() still checkpoints when a listener throws on the synthetic turn/end', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let flushes = 0 ctx.on('session/flush', () => { flushes += 1 }) // Session contains a throwing post-commit turn/end observer. The accepted @@ -206,7 +206,7 @@ describe('ReactLoopAgent', () => { // A non-Error rejection exercises the String() normalization branch. ctx.on('session/flush', () => { throw 'disk gone' }) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const errors: { turn: number; step: number; message: string }[] = [] ctx.on('agent/error', (_a, turn, step, error) => void errors.push({ turn, step, message: error.message })) @@ -225,7 +225,7 @@ describe('ReactLoopAgent', () => { it('idle inject() with a non-serializable source opens no turn (nothing to close)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A non-serializable source makes the turn/start append throw BEFORE the // event is pushed (Session.append validates before push), so NO turn opens. @@ -240,7 +240,7 @@ describe('ReactLoopAgent', () => { it('steer() when idle falls through to send() and starts a turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // steer while idle delegates to send agent.steer([{ type: 'text', text: 'steer idle' }], { source: { kind: 'plugin', plugin: 'test' } }) @@ -258,7 +258,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('test')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session) const { agent } = prepared // Start the loop to get the disposer; the agent waits for messages @@ -280,7 +280,7 @@ describe('ReactLoopAgent', () => { const ctx = new Context() await ctx.plugin(SessionStore) const session = ctx.sessions.create(SessionId('pre-start-dispose')) - const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, AgentId('pre-start-dispose'), { provider: 'mock', model: 'mock' }, session) await prepared.dispose() expect(prepared.agent.status).toBe('disposed') @@ -294,7 +294,7 @@ describe('ReactLoopAgent', () => { it('setting the same status does not emit agent/status again', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const statuses: string[] = [] ctx.on('agent/status', (subject, status) => { @@ -313,7 +313,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() resolves immediately when the agent is not running', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Fresh agent is idle — whenIdle() takes the not-running fast path and // resolves without subscribing. await must not hang. @@ -324,7 +324,7 @@ describe('ReactLoopAgent', () => { it('whenIdle() waits for queued work that has not flipped status yet', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'queued') let settled = false @@ -342,8 +342,8 @@ describe('ReactLoopAgent', () => { it('whenIdle() awaits the running→idle transition, ignoring other subjects/running events', async () => { const adapter = new MockAdapter([textResponse('ok'), textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const other = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' }) // Drive `agent` into `running`, then await whenIdle() — it subscribes to // agent/status and resolves on the first transition out of running. @@ -379,7 +379,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter(['hang']) ctx.llm.registerAdapter(['mock'], adapter) const session = ctx.sessions.create(SessionId('bare')) - const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { model: 'mock' }, session) + const prepared = prepareReactLoopAgent(ctx, AgentId('bare'), { provider: 'mock', model: 'mock' }, session) const { agent } = prepared prepared.markPublished() const dispose = prepared.startDriver() @@ -404,7 +404,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -425,7 +425,7 @@ describe('ReactLoopAgent', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -446,7 +446,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'running') throw new Error('bad running listener') }) @@ -464,7 +464,7 @@ describe('ReactLoopAgent', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/status', (_subject, status) => { if (status === 'idle') throw new Error('bad idle listener') }) diff --git a/packages/core/agent-loop/tests/cancel.spec.ts b/packages/core/agent-loop/tests/cancel.spec.ts index 56376b69a7..25e90326cf 100644 --- a/packages/core/agent-loop/tests/cancel.spec.ts +++ b/packages/core/agent-loop/tests/cancel.spec.ts @@ -57,7 +57,7 @@ describe('Agent.cancel()', () => { it('cancel() on an idle agent with nothing queued is a no-op; the next prompt runs (F2 leak guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // The loop is parked at the idle wait with nothing queued. A cancel here must // NOT arm the marker — otherwise the next legitimate prompt would be dropped. @@ -74,7 +74,7 @@ describe('Agent.cancel()', () => { it('pre-step cancel drops the about-to-start turn (no turn is opened)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // send() queues synchronously (status still idle, loop microtask not yet // resumed). Cancel in that pre-step window: the queued turn must not run. @@ -93,7 +93,7 @@ describe('Agent.cancel()', () => { it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => { const adapter = new MockAdapter([textResponse('x')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Queue work, then register a whenIdle() waiter while in the pre-step window // (status idle, hasQueued true) — it does NOT take the fast path. Then cancel. @@ -114,7 +114,7 @@ describe('Agent.cancel()', () => { it('cancel() mid-step aborts the in-flight model call; the turn ends aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -131,7 +131,7 @@ describe('Agent.cancel()', () => { it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -147,7 +147,7 @@ describe('Agent.cancel()', () => { it('a prompt sent AFTER a cancelled turn settles runs normally (marker reset)', async () => { const adapter = new MockAdapter(['hang', textResponse('second reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // First turn hangs; cancel it mid-step. send(agent, 'first') @@ -169,7 +169,7 @@ describe('Agent.cancel()', () => { it('cancel from inside the agent/session-prefix waterfall drops the step (prefix-composition window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Prefix composition runs before the pre-step seam on the instance's first // step; a cancel landing inside it must drop the about-to-start step @@ -205,7 +205,7 @@ describe('Agent.cancel()', () => { const handle = await ctx.agents.create({ agentId: AgentId('a-dispose-prefix'), sessionId: SessionId('dispose-prefix-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const agent = handle.agent as ReactLoopAgent @@ -232,7 +232,7 @@ describe('Agent.cancel()', () => { it('a cancel-interrupted prefix composition is discarded: the next send recomposes and ships the fresh prefix (stale-cache guard)', async () => { const adapter = new MockAdapter([textResponse('reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // The first composition is interrupted mid-waterfall and — like an // abort-aware listener bailing on a firing signal — contributes nothing. @@ -266,7 +266,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous turn/start session-event listener drops the step (step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A turn/start listener fires right after turn/start is appended, BEFORE any // AbortController is installed for the step. Cancelling there must still drop @@ -295,7 +295,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous step/start session-event listener drops the step (post-step-start window)', async () => { const adapter = new MockAdapter([textResponse('should not stream')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A step/start session-event listener fires AFTER step/start is appended // (and after the pre-step seam), so cancelling there lands in the SECOND @@ -336,7 +336,7 @@ describe('Agent.cancel()', () => { const handle = await ctx.agents.create({ agentId: AgentId('a-dispose-step-start'), sessionId: SessionId('dispose-step-start-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const agent = handle.agent as ReactLoopAgent @@ -366,7 +366,7 @@ describe('Agent.cancel()', () => { // `aborted` and run NO second step. const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steps = 0 const reasons: TurnEndReason[] = [] @@ -398,7 +398,7 @@ describe('Agent.cancel()', () => { it('cancel from a synchronous agent/status(running) listener drops the turn (window 2)', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // setStatus('running') emits agent/status SYNCHRONOUSLY, so a running // listener can cancel in the gap between the loop's pre-step check and @@ -428,7 +428,7 @@ describe('Agent.cancel()', () => { // so whenIdle() resolves on the replacement turn's running→idle, not before. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let replaced = false const dispose = ctx.on('agent/status', (subject, status) => { @@ -458,7 +458,7 @@ describe('Agent.cancel()', () => { // settle (the quiescence contract), not resolve before B's first event. const adapter = new MockAdapter([textResponse('A reply'), textResponse('B reply')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'A') // queues A (status still idle, loop microtask pending) const idle = agent.whenIdle() // registers a waiter (idle + hasQueued → no fast path) @@ -478,7 +478,7 @@ describe('Agent.cancel()', () => { it("cancel clears the turn's steering — it is not re-enqueued as a fresh turn", async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) diff --git a/packages/core/agent-loop/tests/config-session-id.spec.ts b/packages/core/agent-loop/tests/config-session-id.spec.ts index 07d6cd9e9b..cc30906707 100644 --- a/packages/core/agent-loop/tests/config-session-id.spec.ts +++ b/packages/core/agent-loop/tests/config-session-id.spec.ts @@ -32,7 +32,7 @@ describe('config-driven session id', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) const loopFiber = await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('deferred') }], + agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('deferred') }], }) const resumeEffect = loopFiber.getEffects().find(effect => effect.label === 'agentLoop.resume(main)') @@ -53,7 +53,7 @@ describe('config-driven session id', () => { await ctx1.plugin(SystemPrompt) await ctx1.plugin(ToolRegistry) await ctx1.plugin(AgentRegistry) - await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx1.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), provider: 'mock', model: 'mock' }] }) await ctx1.plugin(SessionPersistenceJsonl, { root }) ctx1.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg')])) const a1 = ctx1.agents.get(AgentId('cfg')) as ReactLoopAgent @@ -70,7 +70,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), model: 'mock' }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('cfg'), provider: 'mock', model: 'mock' }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('cfg2')])) const a2 = ctx2.agents.get(AgentId('cfg')) as ReactLoopAgent @@ -110,7 +110,7 @@ describe('config-driven session id', () => { await ctx2.plugin(SystemPrompt) await ctx2.plugin(ToolRegistry) await ctx2.plugin(AgentRegistry) - await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) + await ctx2.plugin(AgentLoop, { agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('sticky-1') }] }) await ctx2.plugin(SessionPersistenceJsonl, { root }) ctx2.llm.registerAdapter(['mock'], new MockAdapter([textResponse('second')])) @@ -138,7 +138,7 @@ describe('config-driven session id', () => { await ctx.plugin(SystemPrompt) await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) - await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) + await ctx.plugin(AgentLoop, { agents: [{ id: AgentId('main'), provider: 'mock', model: 'mock', resumeSessionId: SessionId('does-not-exist') }] }) const warn = vi.spyOn((ctx.agentLoop as unknown as { ctx: { logger: { warn: (...a: unknown[]) => void } } }).ctx.logger, 'warn') .mockImplementation(() => undefined) await ctx.plugin(SessionPersistenceJsonl, { root }) diff --git a/packages/core/agent-loop/tests/coverage-edges.spec.ts b/packages/core/agent-loop/tests/coverage-edges.spec.ts index 23e5670f85..bd1e528f0a 100644 --- a/packages/core/agent-loop/tests/coverage-edges.spec.ts +++ b/packages/core/agent-loop/tests/coverage-edges.spec.ts @@ -40,7 +40,7 @@ describe('inbox acceptance', () => { it('rejects non-serializable content or source synchronously before notification or enqueue', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let queued = 0 ctx.on('agent/queued', () => { queued += 1 }) @@ -80,7 +80,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: typeof args === 'string' ? `raw: ${args}` : JSON.stringify(args) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -113,7 +113,7 @@ describe('tool JSON parse', () => { return [{ type: 'text', text: 'ran with empty args' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -126,7 +126,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from pre-commit dispatch validation via the runLoop backstop', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threwOnce = false ctx.on('internal/dispatch', (_mode, name, args) => { @@ -152,7 +152,7 @@ describe('toError normalization', () => { it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => { const adapter = new MockAdapter([textResponse('irrelevant')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, _next) => { @@ -180,7 +180,7 @@ describe('coded error data emission', () => { it('errorData includes code when a coded error (LlmError) is thrown from a plugin', async () => { const adapter = new MockAdapter([textResponse('turn 1')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threwOnce = false ctx.on('agent/request', async (_agent, _turn, _step, _options, next) => { @@ -214,7 +214,7 @@ describe('disposed vs aborted branching', () => { const ctx = await harness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -242,7 +242,7 @@ describe('structured tool error propagation (the runtime-validation RFC, part 2) textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'boom', description: 'always fails', diff --git a/packages/core/agent-loop/tests/interception.spec.ts b/packages/core/agent-loop/tests/interception.spec.ts index d4ec6312ba..6ba2b02b41 100644 --- a/packages/core/agent-loop/tests/interception.spec.ts +++ b/packages/core/agent-loop/tests/interception.spec.ts @@ -57,7 +57,7 @@ describe('agent/prompt-submit', () => { it('allow (default via next) records the user/message unchanged', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const seen: string[] = [] ctx.on('agent/prompt-submit', async (_agent, content, _source, next) => { @@ -76,7 +76,7 @@ describe('agent/prompt-submit', () => { it('allow with content REWRITES the prompt before it is recorded', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'allow', content: [{ type: 'text', text: 'REWRITTEN' }] })) @@ -94,7 +94,7 @@ describe('agent/prompt-submit', () => { it('allow with additionalContext injects a separate context/message into the turn', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -127,7 +127,7 @@ describe('agent/prompt-submit', () => { // elsewhere; this asserts they see each other's effects on the same turn). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ @@ -157,7 +157,7 @@ describe('agent/prompt-submit', () => { it('block drops the (only) prompt → zero-step turn ends rejected, model never called', async () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (): Promise => ({ kind: 'block', reason: 'blocked by policy' })) @@ -194,7 +194,7 @@ describe('agent/prompt-submit', () => { // vetoed prompt and its reason would vanish from the log entirely. const adapter = new MockAdapter([textResponse('ran once')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise => { const text = content.map(b => (b.type === 'text' ? b.text : '')).join('') @@ -230,7 +230,7 @@ describe('agent/prompt-submit', () => { it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => { const adapter = new MockAdapter([textResponse('after')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('agent/prompt-submit', async () => { @@ -263,7 +263,7 @@ describe('agent/session-start', () => { const sources: SessionStartSource[] = [] ctx.on('agent/session-start', (_agent, source) => void sources.push(source)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // fires synchronously at create, before any turn expect(sources).toEqual(['startup']) expect(events(agent).some(e => e.type === 'turn/start')).toBe(false) @@ -282,7 +282,7 @@ describe('agent/session-start', () => { agent.inject([{ type: 'text', text: 'session preamble' }], { source: { kind: 'plugin', plugin: 'test' } }) }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -300,7 +300,7 @@ describe('agent/session-start', () => { ctx.on('agent/session-start', () => { throw new Error('session-start hook broke') }) // create must not throw — the listener error is contained/logged - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) expect(agent.id).toBe(AgentId('a1')) // and the agent still runs @@ -314,8 +314,8 @@ describe('agent/session-prefix', () => { it('dispatches to global and matching agent-scope listeners only', async () => { const adapter = new MockAdapter([textResponse('a done'), textResponse('b done')]) const ctx = await harness(adapter) - const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { model: 'mock' }) - const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { model: 'mock' }) + const agentA = ctx.agentLoop.create(AgentId('prefix-a'), { provider: 'mock', model: 'mock' }) + const agentB = ctx.agentLoop.create(AgentId('prefix-b'), { provider: 'mock', model: 'mock' }) const seen: string[] = [] ctx.on('agent/session-prefix', async (agent, _prefix, _signal, next) => { seen.push(`global:${agent.id}`) @@ -352,7 +352,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'catalog' }] } let composed = 0 @@ -385,7 +385,7 @@ describe('agent/session-prefix', () => { it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reminder: Message = { role: 'user', content: [{ type: 'text', text: 'opener' }] } const order: string[] = [] @@ -412,7 +412,7 @@ describe('agent/session-prefix', () => { it('the canonical prepend pattern composes contributions in registration order', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Both listeners use the canonical `[mine, ...await next()]` prepend: the // waterfall unwinds innermost-first (the second listener's array is built @@ -434,7 +434,7 @@ describe('agent/session-prefix', () => { it('with no contributions the header omits messagePrefix and the request is the bare derivation', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A listener that delegates without contributing — the canonical no-op. ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => next()) @@ -450,7 +450,7 @@ describe('agent/session-prefix', () => { it('the frozen seed rejects in-place mutation — a contribution is a returned extension', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let mutationError: unknown ctx.on('agent/session-prefix', async (_agent, prefix, _signal, next): Promise => { @@ -479,7 +479,7 @@ describe('agent/session-prefix', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const held: Message = { role: 'user', content: [{ type: 'text', text: 'v1' }] } ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise => [...await next(), held]) @@ -500,7 +500,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { it('a continue decision with a reason records next-step steering in the same turn', async () => { const adapter = new MockAdapter([textResponse('step 1 no tools'), textResponse('step 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let forced = false ctx.on('agent/turn-continuation', async (_agent, _turn, _default, next): Promise => { @@ -533,7 +533,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => { name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/turn-continuation', async (): Promise => ({ action: 'stop' })) @@ -563,7 +563,7 @@ describe('tools/post-execute additionalContext buffering across a multi-call ste name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Each call attaches additionalContext naming itself. ctx.on('tools/post-execute', async (exec, _result): Promise => @@ -599,7 +599,7 @@ describe('tools/pre-execute gate (native-plugin permission pattern, end-to-end t name: 'danger', description: 'danger', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('tools/pre-execute', async (exec, next): Promise => { if (exec.name === 'danger') return { kind: 'deny', reason: 'blocked dangerous tool' } @@ -663,7 +663,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se name: 'echo', description: 'echo', parameters: { text: { type: 'string' } }, async execute(args) { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'please echo hi') await waitForIdle(ctx, agent) @@ -686,7 +686,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(adapter) await ctx.plugin(NativeGuard) - const agent = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -705,7 +705,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se await fiber.dispose() // After disposal, a destructive prompt is NOT blocked (the listener is gone). - const agent = ctx.agentLoop.create(AgentId('a3'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a3'), { provider: 'mock', model: 'mock' }) send(agent, 'run rm -rf /') await waitForIdle(ctx, agent) // the prompt ran (not rejected) — proving the prompt-submit listener was disposed diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index 71be5b339e..0e9ce85ac9 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/packages/core/agent-loop/tests/loop.spec.ts @@ -44,7 +44,7 @@ describe('agent loop', () => { it('runs a simple turn: queued message → model → idle, with ordered events', async () => { const adapter = new MockAdapter([textResponse('hello there')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // All boundaries — turn and step — are durable session events on the // session/event feed (no agent/* mirror). Record them in fire order to @@ -92,7 +92,7 @@ describe('agent loop', () => { return [{ type: 'text', text: `echo: ${args.text}` }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -131,7 +131,7 @@ describe('agent loop', () => { return { content: [{ type: 'text', text: 'ok' }], meta: { diffs: [{ path: 'a.txt', oldText: null, newText: 'x' }] } } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -155,7 +155,7 @@ describe('agent loop', () => { return [] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -172,7 +172,7 @@ describe('agent loop', () => { agentId: AgentId('a-cwd'), sessionId: SessionId('s-cwd'), meta: { cwd: '/work/space' }, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const agent = handle.agent as ReactLoopAgent @@ -192,7 +192,7 @@ describe('agent loop', () => { const ctx = await harness(adapter, 'In {{cwd}}.') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -227,11 +227,12 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter, 'You run on {{model}}.') ctx.on('system-prompt/assemble', async (assembly, _context, next) => { + assembly.variables['provider'] = 'mock' assembly.variables['model'] = 'mock' return next() }) ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { - return { ...config, model: 'mock' } + return { ...config, provider: 'mock', model: 'mock' } }) const agent = ctx.agentLoop.create(AgentId('a-late-model'), {}) @@ -259,7 +260,7 @@ describe('agent loop', () => { parameters: {}, execute: () => Promise.resolve({ content: [{ type: 'text' as const, text: 'apparent success' }], meta }), })) - const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('bad-meta-agent'), { provider: 'mock', model: 'mock' }) send(agent, 'use the tool') await waitForIdle(ctx, agent) @@ -288,7 +289,7 @@ describe('agent loop', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) ctx.on('system-prompt/assemble', async () => ({ sections: [], tools: [], variables: {} })) - const agent = ctx.agentLoop.create(AgentId('a-no-system'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-no-system'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -300,7 +301,7 @@ describe('agent loop', () => { it('records raw chunks for replay as assistant/chunk session events', async () => { const adapter = new MockAdapter([textResponse('abc')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'hi') await waitForIdle(ctx, agent) @@ -324,7 +325,7 @@ describe('agent loop', () => { ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'slow', description: '', @@ -356,7 +357,7 @@ describe('agent loop', () => { it('steering while idle behaves like send (starts a turn)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.steer([{ type: 'text', text: 'hello' }]) await waitForIdle(ctx, agent) @@ -366,7 +367,7 @@ describe('agent loop', () => { it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.inject([{ type: 'text', text: 'file changed: a.ts' }], { source: { kind: 'plugin', plugin: 'watcher' } }) // The idle inject records a self-contained turn (turn/start → context/message @@ -393,7 +394,7 @@ describe('agent loop', () => { textResponse('done'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // A tool that injects mid-execution: at this point the agent is running, so // inject must append the context/message into the ALREADY-open turn rather // than wrap it in its own one-shot turn. @@ -427,7 +428,7 @@ describe('agent loop', () => { textResponse('step 3'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -453,7 +454,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/turn-continuation', async () => ({ action: 'stop' }) as const) @@ -468,8 +469,7 @@ describe('agent loop', () => { it('agent/request waterfall switches models by returning a replacement config; the switch is logged', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - ctx.llm.registerAdapter(['other-model'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { // The seed is frozen — config is not a mutable per-call knob; a switch @@ -502,7 +502,7 @@ describe('agent loop', () => { name: 'echo', description: 'echo', parameters: {}, async execute() { return [{ type: 'text', text: 'echoed' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const fires: { turn: number; step: number; fullSystemPrompt: string }[] = [] ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => { @@ -527,7 +527,7 @@ describe('agent loop', () => { // the derived request for that step (derive happens after step/start). const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let injected = false ctx.on('agent/pre-step', (subject) => { @@ -563,7 +563,7 @@ describe('agent loop', () => { // The loop survives and a follow-up prompt still runs. const adapter = new MockAdapter([textResponse('second turn ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let throwOnce = true ctx.on('agent/pre-step', () => { @@ -597,7 +597,7 @@ describe('agent loop', () => { it('cancel() mid-stream ends the turn with reason aborted', async () => { const adapter = new MockAdapter(['hang']) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -617,7 +617,7 @@ describe('agent loop', () => { // turn stops by default and ends max-tokens, not completed. const adapter = new MockAdapter([maxTokensResponse('truncat')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -642,7 +642,7 @@ describe('agent loop', () => { textResponse('second half'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steps = 0 ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ }) @@ -663,7 +663,7 @@ describe('agent loop', () => { expect(adapter.requests).toHaveLength(2) expect(adapter.requests[1]!.messages).toEqual([ { role: 'user', content: [{ type: 'text', text: 'go' }] }, - { role: 'assistant', content: [{ type: 'text', text: 'first half' }] }, + { role: 'assistant', content: [{ type: 'text', text: 'first half' }], provenance: { provider: 'mock', model: 'mock' } }, ]) expect(reasons).toEqual([{ kind: 'max-tokens' }]) }) @@ -673,7 +673,7 @@ describe('agent loop', () => { // stop. The per-turn reason must be independent — turn 2 ends completed. const adapter = new MockAdapter([maxTokensResponse('cut'), textResponse('clean')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -706,7 +706,7 @@ describe('agent loop', () => { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -725,7 +725,7 @@ describe('agent loop', () => { // the derived history above is NOT corrupted by a spurious assistant turn. const assistantMessage = agent.session.events.find(e => e.type === 'assistant/message') expect(assistantMessage?.type === 'assistant/message' && assistantMessage.data).toEqual({ - turn: 1, step: 1, content: [], usage: { inputTokens: 10, outputTokens: 5 }, + turn: 1, step: 1, content: [], provenance: { provider: 'mock', model: 'mock' }, usage: { inputTokens: 10, outputTokens: 5 }, }) }) @@ -748,7 +748,7 @@ describe('agent loop', () => { parameters: { text: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'should not run' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -767,7 +767,7 @@ describe('agent loop', () => { // on the normal step path suppresses a pure trace-only empty assistant/message. const adapter = new MockAdapter([[{ type: 'finish', reason: { kind: 'stop' } }]]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -797,7 +797,7 @@ describe('agent loop', () => { expect(message.content).toEqual([{ type: 'text', text: 'partial text' }]) return next() }) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -806,7 +806,7 @@ describe('agent loop', () => { expect(agent.session.events.some(e => e.type === 'tool/call')).toBe(false) expect(agent.session.deriveMessages()).toEqual([ { role: 'user', content: [{ type: 'text', text: 'go' }] }, - { role: 'assistant', content: [{ type: 'text', text: 'partial text' }] }, + { role: 'assistant', content: [{ type: 'text', text: 'partial text' }], provenance: { provider: 'mock', model: 'mock' } }, ]) }) @@ -824,7 +824,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threw = false // Post-commit session observers cannot control the loop. The tool call still // drives the second model request, and the turn completes normally. @@ -843,7 +843,7 @@ describe('agent loop', () => { it('chains queued messages into consecutive turns', async () => { const adapter = new MockAdapter([textResponse('first'), textResponse('second')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const turns: number[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/start') turns.push(event.data.turn) }) @@ -868,7 +868,7 @@ describe('agent loop', () => { it('awaits session/flush at turn end (persistence checkpoint)', async () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let flushed = 0 let flushedBeforeIdle = false @@ -888,7 +888,7 @@ describe('agent loop', () => { it('errors from the model surface as agent/error and end the turn', async () => { const adapter = new MockAdapter([]) // script exhausted → throws const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const errors: Error[] = [] const reasons: TurnEndReason[] = [] @@ -913,7 +913,7 @@ describe('agent loop', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) expect(ctx.agents.get(AgentId('scoped'))).toBe(agent) @@ -938,7 +938,7 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock' }], + agents: [{ id: AgentId('config-agent'), provider: 'mock', model: 'mock' }], }) ctx.llm.registerAdapter(['mock'], adapter) @@ -961,7 +961,7 @@ describe('agent loop', () => { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { - agents: [{ id: AgentId('config-agent'), model: 'mock', cwd: '/work/project' }], + agents: [{ id: AgentId('config-agent'), provider: 'mock', model: 'mock', cwd: '/work/project' }], }) const agent = ctx.agents.get(AgentId('config-agent'))! as ReactLoopAgent @@ -982,7 +982,7 @@ describe('agent loop', () => { return [{ type: 'text', text: String(args.text) }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'run') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/properties.spec.ts b/packages/core/agent-loop/tests/properties.spec.ts index 1e603a1cc4..ddb401ea08 100644 --- a/packages/core/agent-loop/tests/properties.spec.ts +++ b/packages/core/agent-loop/tests/properties.spec.ts @@ -95,7 +95,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) const { seen: trace } = recordStatus(ctx, agent) const idle = nextIdle(ctx, agent) // Send all in one synchronous tick: they queue before the loop wakes. @@ -120,7 +120,7 @@ describe('agent loop scheduling properties', () => { async (texts) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) for (const text of texts) { const idle = nextIdle(ctx, agent) agent.send([{ type: 'text', text }]) @@ -145,7 +145,7 @@ describe('agent loop scheduling properties', () => { async (steps) => { const ctx = await harness() try { - const agent = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) // Capture an idle waiter before EACH send; the last one is guaranteed // to resolve because the final send always triggers (or joins) a turn // that ends idle. Awaiting an already-resolved waiter is a no-op, so a diff --git a/packages/core/agent-loop/tests/request-cache.e2e.ts b/packages/core/agent-loop/tests/request-cache.e2e.ts index 5ccaa7e797..08b6491cc0 100644 --- a/packages/core/agent-loop/tests/request-cache.e2e.ts +++ b/packages/core/agent-loop/tests/request-cache.e2e.ts @@ -45,7 +45,7 @@ async function loopHarness(): Promise { await created.plugin(ToolRegistry) await created.plugin(AgentRegistry) await created.plugin(AgentLoop, { agents: [] }) - await created.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await created.plugin(LlmDeepSeek) created.tools.register(defineTool({ name: 'lookup', description: 'Look up the stored value for a key.', @@ -71,7 +71,7 @@ function waitForIdle(context: Context, agent: Agent): Promise { describe.skipIf(!process.env.DEEPSEEK_API_KEY)('log-derived request cache hits (real API)', () => { it('every request after the first hits the provider prefix cache', async () => { ctx = await loopHarness() - const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('cache-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) // Turn 1: forces a tool call → at least two steps (two model requests). agent.send([{ type: 'text', text: 'Look up the key "deploy-color" with the lookup tool and tell me the value.' }]) diff --git a/packages/core/agent-loop/tests/request-log.spec.ts b/packages/core/agent-loop/tests/request-log.spec.ts index a6befde84e..912a13892c 100644 --- a/packages/core/agent-loop/tests/request-log.spec.ts +++ b/packages/core/agent-loop/tests/request-log.spec.ts @@ -30,7 +30,7 @@ describe('recordRequestHeader', () => { it("anchors a new conversation with an 'initial' snapshot, then logs nothing while unchanged", () => { const session = openSession('rl-initial') const state = createTransmissionLog() - const header = canonicalHeader({ config: { model: 'm' }, system: 's', tools: [tool('t')] }) + const header = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 's', tools: [tool('t')] }) recordRequestHeader(session, state, header) const [first] = headerEvents(session) @@ -42,7 +42,7 @@ describe('recordRequestHeader', () => { it("anchors a fresh loop instance over an anchored log with a 'resume' snapshot, even unchanged", () => { const session = openSession('rl-resume') - const header = canonicalHeader({ config: { model: 'm' }, system: 's' }) + const header = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 's' }) recordRequestHeader(session, createTransmissionLog(), header) // A second instance (process restart / fork): the boundary itself is a @@ -56,10 +56,10 @@ describe('recordRequestHeader', () => { it('logs a round-tripping delta for a mid-run change, and the fold reproduces the header', () => { const session = openSession('rl-delta') const state = createTransmissionLog() - const first = canonicalHeader({ config: { model: 'm' }, system: 'a\nb', tools: [tool('t')] }) + const first = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nb', tools: [tool('t')] }) recordRequestHeader(session, state, first) - const second = canonicalHeader({ config: { model: 'm' }, system: 'a\nc', tools: [tool('t'), tool('u')] }) + const second = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nc', tools: [tool('t'), tool('u')] }) recordRequestHeader(session, state, second) const events = headerEvents(session) expect(events).toHaveLength(2) @@ -70,10 +70,10 @@ describe('recordRequestHeader', () => { it("records a change the delta cannot express (pure reordering) as a 'fallback' snapshot", () => { const session = openSession('rl-fallback') const state = createTransmissionLog() - const first = canonicalHeader({ config: { model: 'm' }, tools: [tool('a'), tool('b')] }) + const first = canonicalHeader({ config: { provider: 'mock', model: 'm' }, tools: [tool('a'), tool('b')] }) recordRequestHeader(session, state, first) - const reordered = canonicalHeader({ config: { model: 'm' }, tools: [tool('b'), tool('a')] }) + const reordered = canonicalHeader({ config: { provider: 'mock', model: 'm' }, tools: [tool('b'), tool('a')] }) recordRequestHeader(session, state, reordered) const events = headerEvents(session) expect(events).toHaveLength(2) diff --git a/packages/core/agent-loop/tests/request-reconstruction.spec.ts b/packages/core/agent-loop/tests/request-reconstruction.spec.ts index bb6d613954..7600117b58 100644 --- a/packages/core/agent-loop/tests/request-reconstruction.spec.ts +++ b/packages/core/agent-loop/tests/request-reconstruction.spec.ts @@ -74,7 +74,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) @@ -95,7 +95,7 @@ describe('request stability across the loop', () => { it('a later turn append-extends the previous turn (one conversation, one log)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -109,7 +109,7 @@ describe('request stability across the loop', () => { it('a compaction replace rewrites the resend, and the log explains it', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -142,7 +142,7 @@ describe('request stability across the loop', () => { it('a real system-prompt change is a logged header delta; a stable prompt logs nothing', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two'), textResponse('three')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -165,7 +165,7 @@ describe('request stability across the loop', () => { it('an inject() during the agent/request waterfall joins the NEXT request (the step/start boundary)', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let injected = false ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { @@ -193,7 +193,7 @@ describe('request stability across the loop', () => { it('a mutation attempt on the frozen request content throws into the step (loud, not silent)', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) @@ -214,7 +214,7 @@ describe('request stability across the loop', () => { it('a fresh loop instance over a seeded log anchors with a resume snapshot and stays cache-aligned', async () => { const adapter = new MockAdapter([textResponse('one')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('gen1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('gen1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -226,7 +226,7 @@ describe('request stability across the loop', () => { agentId: AgentId('gen2'), sessionId: SessionId('gen2-session'), seed: [...agent.session.events], - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const agent2 = handle.agent as ReactLoopAgent send(agent2, 'second') @@ -243,7 +243,7 @@ describe('request stability across the loop', () => { it('a delegating listener cannot mutate the seed through next() — the fold stays log-true', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => { const config = await next() @@ -277,7 +277,7 @@ describe('request stability across the loop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await waitForIdle(ctx, agent) diff --git a/packages/core/agent-loop/tests/resume.spec.ts b/packages/core/agent-loop/tests/resume.spec.ts index 93605008ec..67f91addee 100644 --- a/packages/core/agent-loop/tests/resume.spec.ts +++ b/packages/core/agent-loop/tests/resume.spec.ts @@ -201,7 +201,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const resuming = ctx.agents.resume({ agentId: AgentId('resumed-atomic'), resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async (agentCtx) => { expect(agentCtx.agent?.id).toBe(AgentId('resumed-atomic')) expect(agentCtx.agent?.session.events).toHaveLength(2) @@ -242,7 +242,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const handle = await ctx.agents.resume({ agentId, resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const transactionLabels = [ `agentLoop.owner(${agentId})`, @@ -267,7 +267,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { await expect(ctx.agents.resume({ agentId: AgentId('resume-reject'), resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { await Promise.resolve() throw new Error('resume setup failed') @@ -280,7 +280,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { const retry = await ctx.agents.resume({ agentId: AgentId('resume-reject'), resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) await retry.dispose() await ctx.fiber.dispose() @@ -301,7 +301,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { resuming = inner.agents.resume({ agentId: AgentId('resume-owner-race'), resumeSessionId: sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { setupStarted.resolve(undefined) await gate.promise @@ -348,7 +348,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { let resuming!: ReturnType const owner = await ctx.plugin(Object.assign((inner: Context) => { - resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + resuming = inner.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } }) }, { inject: ['agents'] })) await loadStarted.promise @@ -360,7 +360,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { // owner.dispose() awaited transaction settlement, so the same identities // can be reused before awaiting the public rejection. - const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } })) + const retry = await promptly(ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } })) await rejection expect(loads).toBe(2) expect(published).toEqual(['session/created', 'agent/created', 'agent/session-start']) @@ -404,7 +404,7 @@ describe('the session-persistence RFC: AgentLoop factory create/resume', () => { ctx.on('session/created', () => void published.push('session/created')) ctx.on('agent/created', () => void published.push('agent/created')) - const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { model: 'mock' } }) + const resuming = ctx.agents.resume({ agentId, resumeSessionId: sessionId, agentOptions: { provider: 'mock', model: 'mock' } }) await loadStarted.promise const rejection = expect(promptly(resuming)).rejects.toThrow(/agent loop is not active/) await promptly(loopFiber.dispose()) diff --git a/packages/core/agent-loop/tests/review-fixes.spec.ts b/packages/core/agent-loop/tests/review-fixes.spec.ts index 5898a82ee2..467a9aecd6 100644 --- a/packages/core/agent-loop/tests/review-fixes.spec.ts +++ b/packages/core/agent-loop/tests/review-fixes.spec.ts @@ -41,7 +41,9 @@ function send(agent: ReactLoopAgent, text: string) { describe('HIGH: session log records what agent/step-result actually produced', () => { it('a step-result rewrite is what the log, derived history, and tool dispatch all see', async () => { - const adapter = new MockAdapter([textResponse('original'), textResponse('done')]) + const original = textResponse('original') + original[original.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState: { private: 'original-state' } } + const adapter = new MockAdapter([original, textResponse('done')]) const ctx = await harness(adapter) const executed: string[] = [] ctx.tools.register(defineTool({ @@ -53,7 +55,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( return [{ type: 'text', text: 'ran' }] }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Plugin rewrites the message: replaces the text AND adds a tool call. let rewritten = false @@ -78,6 +80,7 @@ describe('HIGH: session log records what agent/step-result actually produced', ( const recorded = agent.session.events.find(e => e.type === 'assistant/message')! expect(JSON.stringify(recorded.data)).toContain('rewritten') expect(JSON.stringify(recorded.data)).not.toContain('original') + expect(recorded.type === 'assistant/message' && recorded.data.provenance.replayState).toBeUndefined() // tool/call + tool/result correlate with the injected call id const callEvent = agent.session.events.find(e => e.type === 'tool/call')! if (callEvent.type !== 'tool/call') throw new Error('wrong event type') @@ -87,6 +90,26 @@ describe('HIGH: session log records what agent/step-result actually produced', ( expect(JSON.stringify(derived)).toContain('rewritten') expect(JSON.stringify(derived)).not.toContain('original') }) + + it('records adapter replay state when step-result preserves the assembled content', async () => { + const response = textResponse('unchanged') + const replayState = { private: 'state' } + response[response.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState } + const adapter = new MockAdapter([response]) + const ctx = await harness(adapter) + const agent = ctx.agentLoop.create(AgentId('replay-state'), { provider: 'mock', model: 'next-model' }) + + send(agent, 'go') + await waitForIdle(ctx, agent) + + const recorded = agent.session.events.find(e => e.type === 'assistant/message') + expect(recorded?.type === 'assistant/message' && recorded.data.provenance).toEqual({ + provider: 'mock', model: 'next-model', replayState, + }) + expect(agent.session.deriveMessages().at(-1)?.provenance).toEqual({ + provider: 'mock', model: 'next-model', replayState, + }) + }) }) describe('HIGH: abort during tool execution ends the turn', () => { @@ -104,7 +127,7 @@ describe('HIGH: abort during tool execution ends the turn', () => { ]) const ctx = await harness(adapter) const executed: string[] = [] - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'aborter', description: '', @@ -148,7 +171,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('continued because of steering'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steeredOnce = false ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, next) => { @@ -188,7 +211,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { textResponse('after goal reminder'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let steeredOnce = false ctx.on('session/event', (subject, event) => { @@ -218,7 +241,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steer() from a turn/end session-event listener becomes a queued message for the next turn', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) const turns: number[] = [] let steeredOnce = false @@ -244,7 +267,7 @@ describe('HIGH: steering from late extension points is never stranded', () => { it('steering queued during an aborted step is re-delivered, not silently consumed', async () => { const adapter = new MockAdapter(['hang', textResponse('recovered')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'go') await new Promise(r => setTimeout(r, 30)) @@ -267,7 +290,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a throwing agent/turn-continuation listener ends the turn with an error, loop survives', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let threwOnce = false ctx.on('agent/turn-continuation', async (): Promise => { @@ -295,7 +318,7 @@ describe('HIGH: plugin exceptions are contained', () => { it('a rejecting session/flush listener is reported but does not kill the agent', async () => { const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) let rejectedOnce = false ctx.on('session/flush', async () => { @@ -325,7 +348,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const statuses: string[] = [] @@ -348,7 +371,7 @@ describe('MEDIUM: disposed status is part of the agent/status contract', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('scoped'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('scoped'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) ctx.on('agent/status', (_agent, status) => { @@ -374,7 +397,7 @@ describe('MEDIUM: misc registry and config fixes', () => { expect(() => ctx.llm.registerAdapter(['m1'], new MockAdapter([]))) .toThrow('already registered') // the original registration survives the failed attempt - expect(ctx.llm.models()).toEqual(['m1']) + expect(ctx.llm.providers()).toEqual(['m1']) }) it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => { @@ -388,7 +411,7 @@ describe('MEDIUM: misc registry and config fixes', () => { send(agent, 'go') await waitForIdle(ctx, agent) expect(errors).toHaveLength(1) - expect(errors[0]!.message).toContain('has no model') + expect(errors[0]!.message).toContain('has no provider/model') expect(errors[0]!.message).toContain('agent/request') }) @@ -398,7 +421,7 @@ describe('MEDIUM: misc registry and config fixes', () => { const agent = ctx.agentLoop.create(AgentId('a1'), {}) // no model — router plugin decides ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => { - return { ...config, model: 'mock' } + return { ...config, provider: 'mock', model: 'mock' } }) send(agent, 'go') @@ -410,7 +433,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('agent/queued carries the resolved source; steering/message records its source', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'noop', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.tools.register(defineTool({ name: 'noop', description: '', @@ -438,7 +461,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('send() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('owned-send'), { provider: 'mock', model: 'mock' }) const content = [{ type: 'text' as const, text: 'accepted-send' }] const source = { kind: 'plugin' as const, plugin: 'accepted-source' } let notifiedContent: ContentBlock[] | undefined @@ -474,7 +497,7 @@ describe('MEDIUM: misc registry and config fixes', () => { it('running steer() owns content and source before notification and delivery', async () => { const adapter = new MockAdapter([toolCallResponse('c1', 'gate', {}), textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('owned-steer'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('owned-steer'), { provider: 'mock', model: 'mock' }) const entered = Promise.withResolvers() const release = Promise.withResolvers() ctx.tools.register(defineTool({ @@ -528,7 +551,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () it('a forked agent continues turn numbers after the seed log', async () => { const first = new MockAdapter([textResponse('turn one')]) const ctx = await harness(first) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) send(agent, 'first') await waitForIdle(ctx, agent) @@ -544,7 +567,7 @@ describe('MEDIUM: turn numbering continues across seeded (forked) sessions', () ctx2.llm.registerAdapter(['mock'], second) const seeded = ctx2.sessions.create(SessionId('forked'), { seed: [...agent.session.events] }) - const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { model: 'mock' }, seeded) + const prepared = prepareReactLoopAgent(ctx2, AgentId('forked-agent'), { provider: 'mock', model: 'mock' }, seeded) const forked = prepared.agent prepared.markPublished() ctx2.effect(() => prepared.startDriver()) @@ -591,7 +614,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-finish-error'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -616,7 +639,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([abortedStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-finish-aborted'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -634,7 +657,7 @@ describe('HIGH: a finish-error stream chunk ends the turn as error, not complete ] const adapter = new MockAdapter([errorStream]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-finish-error-nocode'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] ctx.on('session/event', (_s, event) => { if (event.type === 'turn/end') reasons.push(event.data.reason) }) @@ -650,7 +673,7 @@ describe('step boundary publication order', () => { it('the step/start event is in session.events when its session/event listener fires', async () => { const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-step-order'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-step-order'), { provider: 'mock', model: 'mock' }) // Session.append pushes the event BEFORE notifying session/event listeners, // so a step/start listener always finds the matching event already in the @@ -711,7 +734,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/start observer cannot change a successful turn', async () => { const adapter = new MockAdapter([textResponse('request completed')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stepstart'), { provider: 'mock', model: 'mock' }) // Session owns post-commit containment. The loop sees a successful append, // runs the request, and balances the ordinary step and turn boundaries. @@ -740,7 +763,7 @@ describe('turn and step boundary recovery', () => { it('a pre-commit step/start validation failure does not invent a step boundary', async () => { const adapter = new MockAdapter([textResponse('never reached')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stepstart-veto'), { provider: 'mock', model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -771,7 +794,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider failed' } }] const adapter = new MockAdapter([errorStream]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-turnend-veto'), { provider: 'mock', model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -805,7 +828,7 @@ describe('turn and step boundary recovery', () => { it('a one-shot step/end validation failure keeps the step open until retry succeeds', async () => { const adapter = new MockAdapter([textResponse('completed before close validation')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stepend-veto'), { provider: 'mock', model: 'mock' }) let rejected = false ctx.on('internal/dispatch', (_mode, name, args) => { if (name !== 'session/event') return @@ -839,7 +862,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-errorlistener'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('agent/error', () => { if (!threw) { threw = true; throw new Error('boom error-listener') } }) @@ -872,7 +895,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-dispose'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -901,7 +924,7 @@ describe('turn and step boundary recovery', () => { const ctx = await balancedHarness(adapter) let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-prestep-dispose-throw'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) let threw = false @@ -935,7 +958,7 @@ describe('turn and step boundary recovery', () => { it('a throwing turn/start observer cannot starve the loop or later turns', async () => { const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-preturn'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-preturn'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_session, event) => { @@ -966,7 +989,7 @@ describe('turn and step boundary recovery', () => { it('a throwing step/end observer cannot rewrite the turn outcome', async () => { const adapter = new MockAdapter([textResponse('all good'), textResponse('turn 2 ok')]) const ctx = await balancedHarness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stepend-throw'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1008,7 +1031,7 @@ describe('turn and step boundary recovery', () => { const errorStream: StreamChunk[] = [{ type: 'finish', reason: { kind: 'error', message: 'provider 500' } }] const adapter = new MockAdapter([errorStream, textResponse('turn 2 ok')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-stependthrow'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1038,7 +1061,7 @@ describe('turn and step boundary recovery', () => { // boundary stays authoritative and the loop continues normally. const adapter = new MockAdapter([textResponse('turn 1'), textResponse('turn 2')]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-turnendappend'), { provider: 'mock', model: 'mock' }) let threw = false ctx.on('session/event', (_s, event) => { @@ -1085,7 +1108,7 @@ describe('tool result call identity', () => { return Promise.resolve({ kind: 'accept', content: [{ type: 'text', text: 'ok' }] }) }, { prepend: true }) - const agent = ctx.agentLoop.create(AgentId('a-callid'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a-callid'), { provider: 'mock', model: 'mock' }) send(agent, 'use tool') await waitForIdle(ctx, agent) @@ -1120,7 +1143,7 @@ describe('surface: assistant/message omits sourceEventSeqs when no chunks stream const adapter = new MockAdapter([[]]) const ctx = await harness(adapter) await ctx.plugin(Invariants) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({ role: 'assistant' as const, @@ -1171,7 +1194,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-dispose-assemble'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1227,7 +1250,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-cancel-assemble'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1282,7 +1305,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-dispose-prestep'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1334,7 +1357,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-cancel-prestep'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) const reasons: TurnEndReason[] = [] @@ -1384,7 +1407,7 @@ describe('disposal and cancellation during pre-step assembly', () => { let agent!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { model: 'mock' }) + agent = inner.agentLoop.create(AgentId('a-dispose-no-leak'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) send(agent, 'go') diff --git a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts index 2c478ad1f0..e07ba84e8d 100644 --- a/packages/core/agent-loop/tests/scope-lifecycle.spec.ts +++ b/packages/core/agent-loop/tests/scope-lifecycle.spec.ts @@ -144,7 +144,7 @@ describe('agent scope lifecycle', () => { it('wires agent.ctx: tagged with the agent, DX field set, ctx.agent safe elsewhere', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) expect(scopeOf(agent.ctx)).toBe(agent) expect(agent.ctx.agent).toBe(agent) // The root accessor default: a plain context answers undefined, not a throw. @@ -154,7 +154,7 @@ describe('agent scope lifecycle', () => { it('scoped registrations live in the agent world and die with the agent', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } }) const { agent } = handle agent.ctx.systemPrompt.section({ name: 'deployment:persona', order: 0, text: 'You run tests.' }) agent.ctx.tools.register({ @@ -179,8 +179,8 @@ describe('agent scope lifecycle', () => { it('agent.ctx listeners hear only their own agent (scoped dispatch end to end)', async () => { const ctx = await harness(new MockAdapter([textResponse('one'), textResponse('two')])) - const a = ctx.agentLoop.create(AgentId('a'), { model: 'mock' }) - const b = ctx.agentLoop.create(AgentId('b'), { model: 'mock' }) + const a = ctx.agentLoop.create(AgentId('a'), { provider: 'mock', model: 'mock' }) + const b = ctx.agentLoop.create(AgentId('b'), { provider: 'mock', model: 'mock' }) const heard: string[] = [] a.ctx.on('agent/status', (subject, status) => void heard.push(`a-sees:${subject.id}:${status}`)) @@ -212,7 +212,7 @@ describe('agent scope lifecycle', () => { const handle = await ctx.agents.create({ agentId: AgentId('child'), sessionId: SessionId('child-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async (agentCtx) => { order.push('setup') await Promise.resolve() @@ -236,7 +236,7 @@ describe('agent scope lifecycle', () => { }) ctx.on('agent/created', () => void order.push('agent/created')) ctx.on('agent/session-start', () => void order.push('agent/session-start')) - const acceptedOptions = { model: 'mock' } + const acceptedOptions = { provider: 'mock', model: 'mock' } const creating = ctx.agents.create({ agentId: AgentId('atomic'), @@ -285,13 +285,13 @@ describe('agent scope lifecycle', () => { const first = ctx.agents.create({ agentId, sessionId: SessionId('concurrent-final-enter-a'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup, }) const second = ctx.agents.create({ agentId, sessionId: SessionId('concurrent-final-enter-b'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup, }) await bothStarted.promise @@ -320,7 +320,7 @@ describe('agent scope lifecycle', () => { const pending = ctx.agents.create({ agentId: AgentId('signal-pending'), sessionId: SessionId('signal-pending-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, signal: pendingController.signal, setup: async () => { setupStarted.resolve(undefined) @@ -337,7 +337,7 @@ describe('agent scope lifecycle', () => { const live = await ctx.agents.create({ agentId: AgentId('signal-live'), sessionId: SessionId('signal-live-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, signal: liveController.signal, }) liveController.abort(new Error('too late')) @@ -360,7 +360,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('owner-race'), sessionId: SessionId('owner-race-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { setupStarted.resolve(undefined) await gate.promise @@ -388,7 +388,7 @@ describe('agent scope lifecycle', () => { creating2 = inner.agents.create({ agentId: AgentId('owner-race-2'), sessionId: SessionId('owner-race-s-2'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { setupStarted2.resolve(undefined) await gate2.promise @@ -415,7 +415,7 @@ describe('agent scope lifecycle', () => { const creating = ctx.agents.create({ agentId: AgentId('factory-setup-race'), sessionId: SessionId('factory-setup-race-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { setupStarted.resolve(undefined) await gate.promise @@ -446,7 +446,7 @@ describe('agent scope lifecycle', () => { const creating = ctx.agents.create({ agentId: AgentId('factory-scope-race'), sessionId: SessionId('factory-scope-race-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: () => { setupCalls += 1 }, }) await expect(creating).rejects.toThrow(/agent loop is not active/) @@ -481,7 +481,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('caller-scope-race'), sessionId: SessionId('caller-scope-race-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -511,7 +511,7 @@ describe('agent scope lifecycle', () => { void loopFiber.dispose() }) - expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(AgentId('config-scope-race'), { provider: 'mock', model: 'mock' })) .toThrow(/agent loop is not active/) await loopFiber.dispose() expect(ctx.agents.get(AgentId('config-scope-race'))).toBeUndefined() @@ -523,9 +523,9 @@ describe('agent scope lifecycle', () => { const ctx = await harness() const id = AgentId('config-prepare-failure') - expect(() => ctx.agentLoop.create(id, { model: 'mock' }, { cwd: 'relative' })) + expect(() => ctx.agentLoop.create(id, { provider: 'mock', model: 'mock' }, { cwd: 'relative' })) .toThrow(/absolute path/) - const replacement = ctx.agentLoop.create(id, { model: 'mock' }, { cwd: '/recovered' }) + const replacement = ctx.agentLoop.create(id, { provider: 'mock', model: 'mock' }, { cwd: '/recovered' }) expect(ctx.agents.get(id)).toBe(replacement) await replacement.whenIdle() await ctx.fiber.dispose() @@ -544,7 +544,7 @@ describe('agent scope lifecycle', () => { await expect(ctx.agents.create({ agentId: AgentId('factory-scope-throw'), sessionId: SessionId('factory-scope-throw-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, })).rejects.toThrow('scope preparation failed') await loopFiber.dispose() expect(ctx.agents.get(AgentId('factory-scope-throw'))).toBeUndefined() @@ -560,7 +560,7 @@ describe('agent scope lifecycle', () => { const handle = await ctx.agents.create({ agentId, sessionId: SessionId('factory-live-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) await loopFiber.dispose() @@ -585,7 +585,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('dependency-origin'), sessionId: SessionId('dependency-origin-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: (agentCtx) => { agentCtx.tools.register({ name: 'dependency-origin-tool', @@ -640,7 +640,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('session-created-barrier'), sessionId: SessionId('session-created-barrier-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -689,7 +689,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('agent-created-barrier'), sessionId: SessionId('agent-created-barrier-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -723,7 +723,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('listener-dispose'), sessionId: SessionId('listener-dispose-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -764,7 +764,7 @@ describe('agent scope lifecycle', () => { creating = inner.agents.create({ agentId: AgentId('session-start-dispose'), sessionId: SessionId('session-start-dispose-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) }, { inject: ['agents'] })) @@ -789,7 +789,7 @@ describe('agent scope lifecycle', () => { await expect(ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup: async () => { await Promise.resolve() throw new Error('boom setup') @@ -800,7 +800,7 @@ describe('agent scope lifecycle', () => { expect(published).toEqual([]) expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } }) await retry.dispose() }) @@ -819,7 +819,7 @@ describe('agent scope lifecycle', () => { await expect(ctx.agents.create({ agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, seed, })).rejects.toThrow(/seed event at index 0 is not losslessly JSON-serializable/) @@ -829,7 +829,7 @@ describe('agent scope lifecycle', () => { const retry = await ctx.agents.create({ agentId: AgentId('exotic-seed'), sessionId: SessionId('exotic-seed-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) await retry.dispose() }) @@ -843,13 +843,13 @@ describe('agent scope lifecycle', () => { if (boom) { boom = false; throw new Error('boom created') } }) await expect(ctx.agents.create({ - agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' }, + agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' }, })).rejects.toThrow('boom created') expect(ctx.agents.get(AgentId('bad'))).toBeUndefined() expect(ctx.sessions.get(SessionId('bad-s'))).toBeUndefined() expect(disposed).toEqual([]) // inserted but never announced: no impossible disposed edge // The rollback also disposed the scope fiber: re-creating works cleanly. - const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { model: 'mock' } }) + const retry = await ctx.agents.create({ agentId: AgentId('bad'), sessionId: SessionId('bad-s'), agentOptions: { provider: 'mock', model: 'mock' } }) expect(scopeOf(retry.agent.ctx)).toBe(retry.agent) await retry.dispose() }) @@ -868,7 +868,7 @@ describe('agent scope lifecycle', () => { await expect(ctx.agents.create({ agentId: AgentId('partial-agent'), sessionId: SessionId('partial-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, })).rejects.toThrow('agent observer failed') expect(lifecycle).toEqual([ @@ -892,7 +892,7 @@ describe('agent scope lifecycle', () => { } }) - expect(() => ctx.agentLoop.create(AgentId('config-bad'), { model: 'mock' })) + expect(() => ctx.agentLoop.create(AgentId('config-bad'), { provider: 'mock', model: 'mock' })) .toThrow('config publish failed') expect(ctx.agents.get(AgentId('config-bad'))).toBeUndefined() expect(ctx.sessions.list()).toHaveLength(sessionsBefore) @@ -900,15 +900,15 @@ describe('agent scope lifecycle', () => { it('registrations through a disposed agent ctx throw INACTIVE_EFFECT', async () => { const ctx = await harness() - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), agentOptions: { provider: 'mock', model: 'mock' } }) await handle.dispose() expect(() => handle.agent.ctx.on('agent/status', () => {})).toThrow(/inactive context/) }) it('agentEvents fuses carrier and subject for custom drivers', async () => { const ctx = await harness() - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) - const other = ctx.agentLoop.create(AgentId('a2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) + const other = ctx.agentLoop.create(AgentId('a2'), { provider: 'mock', model: 'mock' }) const heard: string[] = [] agent.ctx.on('agent/error', (subject: Agent, turn: number) => void heard.push(`${subject.id}:${turn}`)) @@ -921,7 +921,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ agentId: AgentId('o1'), sessionId: SessionId('o1-s'), agentOptions: { provider: 'mock', model: 'mock' } }) }, { inject: ['agents'] })) const { agent } = handle @@ -955,7 +955,7 @@ describe('agent scope lifecycle', () => { const ctx = await harness() let handle!: Awaited> const owner = await ctx.plugin(Object.assign(async (inner: Context) => { - handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { model: 'mock' } }) + handle = await inner.agents.create({ agentId: AgentId('h1'), sessionId: SessionId('h1-s'), agentOptions: { provider: 'mock', model: 'mock' } }) }, { inject: ['agents'] })) const teardownDone: string[] = [] @@ -978,7 +978,7 @@ describe('agent scope lifecycle', () => { const handle = await ctx.agents.create({ agentId, sessionId: SessionId('retired-owner-effect-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) expect(ctx.fiber.getEffects().map(effect => effect.label)).toContain(`agentLoop.owner(${agentId})`) @@ -996,7 +996,7 @@ describe('agent scope lifecycle', () => { handle = await inner.agents.create({ agentId: AgentId('manual-first'), sessionId: SessionId('manual-first-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup(agentCtx) { agentCtx.effect(() => async () => { cleanupStarted.resolve(undefined) @@ -1032,7 +1032,7 @@ describe('agent scope lifecycle', () => { const first = await ctx.agents.create({ agentId, sessionId, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, setup(agentCtx) { agentCtx.effect(() => async () => { cleanupStarted.resolve(undefined) @@ -1045,7 +1045,7 @@ describe('agent scope lifecycle', () => { await Promise.all([sessionDisposed.promise, cleanupStarted.promise]) expect(ctx.agents.get(agentId)).toBeUndefined() expect(ctx.sessions.get(sessionId)).toBeUndefined() - const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { model: 'mock' } }) + const replacement = await ctx.agents.create({ agentId, sessionId, agentOptions: { provider: 'mock', model: 'mock' } }) expect(ctx.agents.get(agentId)).toBe(replacement.agent) expect(ctx.sessions.get(sessionId)).toBe(replacement.agent.session) @@ -1060,7 +1060,7 @@ describe('agent scope lifecycle', () => { const handle = await ctx.agents.create({ agentId: AgentId('idle-flush'), sessionId: SessionId('idle-flush-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const gate = Promise.withResolvers() let flushStarted = false diff --git a/packages/core/agent-loop/tests/tool-order.spec.ts b/packages/core/agent-loop/tests/tool-order.spec.ts index d9b0a87e1d..e34ec918d1 100644 --- a/packages/core/agent-loop/tests/tool-order.spec.ts +++ b/packages/core/agent-loop/tests/tool-order.spec.ts @@ -57,7 +57,7 @@ async function runTurn(registrationOrder: string[], toolOrder?: SystemPromptConf const adapter = new MockAdapter([textResponse('done')]) const ctx = await harness(adapter, toolOrder) for (const name of registrationOrder) registerNamed(ctx, name) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) return { ctx, agent, adapter } @@ -103,7 +103,7 @@ describe('loop-level canonical tool order', () => { registerNamed(ctx, 'alpha') const errors: Error[] = [] ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error)) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) diff --git a/packages/core/agent-loop/tests/turn-stop.spec.ts b/packages/core/agent-loop/tests/turn-stop.spec.ts index c275fee88c..5e979988d7 100644 --- a/packages/core/agent-loop/tests/turn-stop.spec.ts +++ b/packages/core/agent-loop/tests/turn-stop.spec.ts @@ -45,7 +45,7 @@ describe('agent/turn-stop', () => { textResponse('must not be requested'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('terminal-steering'), { provider: 'mock', model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let steered = false @@ -72,7 +72,7 @@ describe('agent/turn-stop', () => { textResponse('must not become a late-steering turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('terminal-flush-steering'), { provider: 'mock', model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let injected = false @@ -98,7 +98,7 @@ describe('agent/turn-stop', () => { textResponse('queued follow-up answer'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('terminal-flush-send'), { provider: 'mock', model: 'mock' }) agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) let queued = false @@ -124,8 +124,8 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const stopped = ctx.agentLoop.create(AgentId('stopped'), { model: 'mock' }) - const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { model: 'mock' }) + const stopped = ctx.agentLoop.create(AgentId('stopped'), { provider: 'mock', model: 'mock' }) + const ordinary = ctx.agentLoop.create(AgentId('ordinary'), { provider: 'mock', model: 'mock' }) stopped.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(stopped) @@ -145,7 +145,7 @@ describe('agent/turn-stop', () => { ]) const ctx = await harness(adapter) registerEcho(ctx) - const agent = ctx.agentLoop.create(AgentId('owned-listener'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('owned-listener'), { provider: 'mock', model: 'mock' }) const disposeStop = agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' })) await send(agent, 'first turn') @@ -162,7 +162,7 @@ describe('agent/turn-stop', () => { textResponse('healthy later turn'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('bad-policy'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('bad-policy'), { provider: 'mock', model: 'mock' }) const reasons: TurnEndReason[] = [] const errors: string[] = [] ctx.on('session/event', (session, event) => { diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index 7a046dcc82..218c15727c 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -88,7 +88,9 @@ declare module '@deepseek-ai/dsh-system-prompt' { * Merge-extensible: plugins declare extra fields via declaration merging. */ export interface AgentOptions { - /** Model name (must have a registered adapter at call time). */ + /** Provider route (must have a registered adapter at call time). */ + provider?: string + /** Model id interpreted by the selected provider adapter. */ model?: string } diff --git a/packages/core/session/README.md b/packages/core/session/README.md index 97b18b0504..cea12cfd7d 100644 --- a/packages/core/session/README.md +++ b/packages/core/session/README.md @@ -33,7 +33,7 @@ The store pairs announced creation with disposal, publishes each append, and pro Plain class (not a Cordis Service). Create via `ctx.sessions.create()`. - `session.append(type, data, opts?): SessionEvent` — synchronous, never blocks on I/O. At this durable boundary, data and surface metadata are lossless-JSON snapshotted and deep-frozen. For an attached session, a reentrant append during dispatch/observer publication rejects, and detach waits for that publication to unwind. Callbacks resolve before the log push; the push is the commit point, after which each observer failure is contained independently. Runtime surface validation covers widened unions and raw seed/load logs. -- `session.deriveMessages(): Message[]` — the LLM message history, CACHED: each surface node is projected exactly once, when first seen (O(new nodes) per call; a surface rewrite rebuilds via `surface.replaceGeneration`). Returns a fresh array per call over shared, deep-frozen `Message` objects. Each projection reuses the already deep-frozen content in its durable log event, so no second deep clone is needed and a consumer still cannot mutate logged data. The surface is the single source of derived history — there is no raw-log fallback. +- `session.deriveMessages(): Message[]` — the LLM message history, CACHED: each surface node is projected exactly once, when first seen (O(new nodes) per call; a surface rewrite rebuilds via `surface.replaceGeneration`). Returns a fresh array per call over shared, deep-frozen `Message` objects. Assistant projections preserve the event's provider/model provenance and optional adapter-private replay state. Each projection reuses the already deep-frozen content in its durable log event, so no second deep clone is needed and a consumer still cannot mutate logged data. The surface is the single source of derived history — there is no raw-log fallback. - `session.deriveEventMessage(event): Message | null` — the per-event projection `deriveMessages()` folds: a fresh message wrapper that reuses the event's already frozen content, or `null` when the event produces none (a non-surface event, or an empty-content `assistant/message` hosting only usage). External reconstructors and the dev invariant fold the same function over a log prefix's surface, so no two paths can disagree about what a request's messages were (the reconstructability RFC). - `session.surface: SurfaceManager` — the derived surface, lazily rebuilt from `surfaceOp` markers in the log. Processes only new events (delta) on each access — the log is append-only, so prior events never change. `surface.replaceGeneration` is the rewrite signal: bumped by every folded `replace` and by `invalidate()`, never reset, so an incremental consumer comparing generations cannot be fooled. - `session.events` — a cached, frozen array snapshot over deep-frozen events. Repeated reads without an append return the same array; an append invalidates the cache and the next read returns a new snapshot, while earlier snapshots stay unchanged. Neither a cast nor a retained reference can push into the live log or rewrite an accepted event. @@ -57,7 +57,7 @@ The `request/header` (full `EpochHeader` snapshot with a `RequestHeaderReason`) ### Session event vocabulary (`types.ts`) -The append-only log's event types, enumerated member by member — payloads, surface badges, provenance — in the generated [persistence log event catalog](../../../docs/persistence-catalog.md). Token usage rides on `assistant/message.usage`; an operational error's step is on `turn/end.reason` for `kind: 'error'`. +The append-only log's event types, enumerated member by member — payloads, surface badges, provenance — in the generated [persistence log event catalog](../../../docs/persistence-catalog.md). Token usage and provider/model/replay provenance ride on `assistant/message`; an operational error's step is on `turn/end.reason` for `kind: 'error'`. Merge-extensible via `SessionEventMap` — a plugin declaration-merges its own types (the compaction seam's `compact/*`, the hook bridges' `hook/*`); merged members appear in the same catalog. @@ -75,7 +75,7 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata) ### Extension points - Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`, `session.header`) is what such a backend stores beside the log. -- Replay/fork: `ctx.sessions.create(id, { seed })` seeds a new session with an existing event log. The surface rebuilds deterministically from `surfaceOp` markers in the seeded events. The constructor reads each seed entry once and uses the same one-pass lossless-JSON snapshot and exact surface-metadata shape checks as `append`, then enforces contiguous seqs and deep-freezes every accepted record; a stateful caller, exotic nested value, marker-less or malformed surface event, metadata on a non-surface event, or retained seed reference therefore cannot silently change the reconstructed history. Broader turn-enclosure checks stay in `dsh-invariants` and persistence repair. Ordinary live-session forks use `ctx.sessions.fork(source, boundary?, childSessionId?)`, where `boundary` is the inclusive source event seq to fork through. +- Replay/fork: `ctx.sessions.create(id, { seed })` seeds a new session with an existing event log. The surface rebuilds deterministically from `surfaceOp` markers in the seeded events. The constructor reads each seed entry once and uses the same one-pass lossless-JSON snapshot and exact surface-metadata shape checks as `append`, then enforces contiguous seqs and deep-freezes every accepted record; a stateful caller, exotic nested value, marker-less or malformed surface event, metadata on a non-surface event, or retained seed reference therefore cannot silently change the reconstructed history. In the unreleased pinned-v0 format, request headers without provider/model and assistant messages without provider/model provenance are rejected rather than migrated or guessed. Broader turn-enclosure checks stay in `dsh-invariants` and persistence repair. Ordinary live-session forks use `ctx.sessions.fork(source, boundary?, childSessionId?)`, where `boundary` is the inclusive source event seq to fork through. - Compaction: the `dsh-compact-basic` plugin appends a `user/message` with `surfaceOp: { op: 'replace', start, end }` to shadow old surface nodes behind a summary checkpoint. ### What is NOT here (TODO) diff --git a/packages/core/session/src/index.ts b/packages/core/session/src/index.ts index a6dff5cd27..1e590c8e08 100644 --- a/packages/core/session/src/index.ts +++ b/packages/core/session/src/index.ts @@ -207,6 +207,33 @@ function assertSessionEventEnvelope(value: Record, index: numbe || !Object.hasOwn(event, 'data')) { throw new Error(`seed event at index ${index} has an invalid event envelope`) } + assertCurrentLlmShape(event, index) +} + +/** Reject pre-provider request headers and assistant messages at the seed/load boundary. */ +function assertCurrentLlmShape(event: Record, index: number): void { + const data = event['data'] + if (typeof data !== 'object' || data === null) return + const record = data as Record + if (event['type'] === 'request/header') { + const header = record['header'] + const config = typeof header === 'object' && header !== null ? (header as Record)['config'] : undefined + if (!hasProviderModel(config)) throw new Error(`seed request/header at index ${index} lacks provider/model`) + } + if (event['type'] === 'request/header-delta' && record['config'] !== undefined && !hasProviderModel(record['config'])) { + throw new Error(`seed request/header-delta at index ${index} lacks provider/model`) + } + if (event['type'] === 'assistant/message' && !hasProviderModel(record['provenance'])) { + throw new Error(`seed assistant/message at index ${index} lacks provider/model provenance`) + } +} + +/** Whether an unknown value carries the current provider/model pair. */ +function hasProviderModel(value: unknown): boolean { + if (typeof value !== 'object' || value === null) return false + const pair = value as Record + return typeof pair['provider'] === 'string' && pair['provider'].length > 0 + && typeof pair['model'] === 'string' && pair['model'].length > 0 } type SessionCallback = (...args: unknown[]) => unknown @@ -530,7 +557,7 @@ export class Session { // max-tokens step's usage and must not inject a content-less assistant // turn into the provider transcript. if (event.data.content.length === 0) return null - return { role: 'assistant', content: event.data.content } + return { role: 'assistant', content: event.data.content, provenance: event.data.provenance } } case 'tool/result': { const { callId, content, isError } = event.data diff --git a/packages/core/session/src/types.ts b/packages/core/session/src/types.ts index c4838808c1..74e77dc0fd 100644 --- a/packages/core/session/src/types.ts +++ b/packages/core/session/src/types.ts @@ -1,5 +1,5 @@ import type { Branded } from '@deepseek-ai/dsh-brand' -import type { CallId, ContentBlock, LlmCallConfig, Message, MessageSource, StreamChunk, TokenUsage, ToolSchema } from '@deepseek-ai/dsh-llm' +import type { AssistantProvenance, CallId, ContentBlock, LlmCallConfig, Message, MessageSource, StreamChunk, TokenUsage, ToolSchema } from '@deepseek-ai/dsh-llm' /** Identifies one session in the store (and its persistence artifacts). */ export type SessionId = Branded<'SessionId'> @@ -203,7 +203,7 @@ export interface TodoItem { * prefix are ABSENT fields, matching how requests are built. */ export interface EpochHeader { - /** The conversation's call configuration (model + sampling scalars). */ + /** The conversation's call configuration (provider, model, and sampling scalars). */ config: LlmCallConfig /** Rendered system prompt text; absent for a system-less request. */ system?: string @@ -326,7 +326,7 @@ export interface SessionEventMap { * the model output and its accounting travel together (there is no separate * usage record). `usage` is absent when the adapter reported none. */ - 'assistant/message': { turn: number; step: number; content: ContentBlock[]; usage?: TokenUsage } + 'assistant/message': { turn: number; step: number; content: ContentBlock[]; provenance: AssistantProvenance; usage?: TokenUsage } /** * The model requested one tool invocation: `name` with the raw `arguments` * JSON string exactly as the model produced it (unparsed). `callId` pairs the @@ -375,7 +375,7 @@ export interface SessionEventMap { /** * Amendment to the folded {@link EpochHeader}: at least one of a * {@link SystemDelta}, a {@link ToolsDelta}, a whole replacement - * {@link LlmCallConfig} (four scalars — not worth diffing), or a whole + * {@link LlmCallConfig} (provider/model plus sampling scalars — not worth diffing), or a whole * replacement session prefix (`messagePrefix` — small advisory content, * replaced whole; an EMPTY array encodes the transition to "none", * mirroring the canonical form's absent field — the loop never produces diff --git a/packages/core/session/tests/derived-cache.spec.ts b/packages/core/session/tests/derived-cache.spec.ts index 46015106c8..5be127a84f 100644 --- a/packages/core/session/tests/derived-cache.spec.ts +++ b/packages/core/session/tests/derived-cache.spec.ts @@ -26,10 +26,10 @@ describe('derived-message cache', () => { userText(session, 'one') expect(session.deriveMessages()).toEqual(scratch(session)) userText(session, 'two') - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'reply' }] }, { surfaceOp: 'append' }) expect(session.deriveMessages()).toEqual(scratch(session)) // An empty-content assistant/message (usage host) projects to nothing. - session.append('assistant/message', { turn: 1, step: 2, content: [], usage: { inputTokens: 1, outputTokens: 0 } }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [], usage: { inputTokens: 1, outputTokens: 0 } }, { surfaceOp: 'append' }) expect(session.deriveMessages()).toEqual(scratch(session)) }) @@ -106,7 +106,7 @@ describe('Session.deriveEventMessage — the per-event projection', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) const boundary = session.append('step/start', { turn: 1, step: 1 }) expect(session.deriveEventMessage(boundary)).toBeNull() - const empty = session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) + const empty = session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) expect(session.deriveEventMessage(empty)).toBeNull() }) }) diff --git a/packages/core/session/tests/fork.spec.ts b/packages/core/session/tests/fork.spec.ts index af143ea5ee..5344449078 100644 --- a/packages/core/session/tests/fork.spec.ts +++ b/packages/core/session/tests/fork.spec.ts @@ -195,14 +195,14 @@ describe('SessionStore.fork', () => { ['assistant/message', (session) => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'partial' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'partial' }] }, { surfaceOp: 'append' }) return lastSeq(session) }], ['tool/call', (session) => { const callId = CallId('call-open') session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - session.append('assistant/message', { + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: callId, name: 'bash', arguments: '{}' }], diff --git a/packages/core/session/tests/properties.spec.ts b/packages/core/session/tests/properties.spec.ts index c3a887e14f..dd9a8cf0c2 100644 --- a/packages/core/session/tests/properties.spec.ts +++ b/packages/core/session/tests/properties.spec.ts @@ -30,8 +30,8 @@ const textContentArb = fc.array( // explicit `surfaceOp: 'append'` intent — the marker the real loop passes. const messageEventArb: fc.Arbitrary = fc.oneof( textContentArb.map((content): Appendable => ({ type: 'user/message', data: { content, source: { kind: 'user' } }, intent: { surfaceOp: 'append' } })), - textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content }, intent: { surfaceOp: 'append' } })), - textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, usage: { inputTokens: 1, outputTokens: 1 } }, intent: { surfaceOp: 'append' } })), + textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, provenance: { provider: 'mock', model: 'mock' } }, intent: { surfaceOp: 'append' } })), + textContentArb.map((content): Appendable => ({ type: 'assistant/message', data: { turn: 1, step: 1, content, provenance: { provider: 'mock', model: 'mock' }, usage: { inputTokens: 1, outputTokens: 1 } }, intent: { surfaceOp: 'append' } })), fc.record({ id: fc.string({ minLength: 1 }), content: textContentArb, isError: fc.boolean() }) .map((r): Appendable => ({ type: 'tool/result', data: { turn: 1, step: 1, callId: CallId(r.id), content: r.content, isError: r.isError }, intent: { surfaceOp: 'append' } })), ) diff --git a/packages/core/session/tests/repair.spec.ts b/packages/core/session/tests/repair.spec.ts index e94a9b437f..a8c3d1c309 100644 --- a/packages/core/session/tests/repair.spec.ts +++ b/packages/core/session/tests/repair.spec.ts @@ -56,7 +56,7 @@ describe('interruptedTurnClosers', () => { { type: 'assistant/message', seq: 2, time: 2, data: { turn: 2, step: 1, content: [ { type: 'text', text: 'calling a tool' }, { type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, ] const closers = interruptedTurnClosers(events) // tool/result (for the orphaned call) → step/end → turn/end, contiguous seqs. @@ -74,7 +74,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 1, time: 1, data: { turn: 2, step: 1 } }, { type: 'assistant/message', seq: 2, time: 2, data: { turn: 2, step: 1, content: [ { type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, { type: 'tool/result', seq: 3, time: 3, data: { turn: 2, step: 1, callId: CallId('call-1'), content: [{ type: 'text', text: 'ok' }], isError: false } }, ] // The call is answered, so only the open step + turn need closing. @@ -88,7 +88,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 1, time: 1, data: { turn: 2, step: 1 } }, { type: 'assistant/message', seq: 2, time: 2, data: { turn: 2, step: 1, content: [ { type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, { type: 'step/end', seq: 3, time: 3, data: { turn: 2, step: 1 } }, ] @@ -105,7 +105,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 1, time: 1, data: { turn: 1, step: 1 } }, { type: 'assistant/message', seq: 2, time: 2, data: { turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('old-call'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, { type: 'tool/result', seq: 3, time: 3, data: { turn: 1, step: 1, callId: CallId('old-call'), content: [], isError: false } }, { type: 'step/end', seq: 4, time: 4, data: { turn: 1, step: 1 } }, { type: 'turn/end', seq: 5, time: 5, data: { turn: 1, reason: { kind: 'completed' } } }, @@ -113,7 +113,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 7, time: 7, data: { turn: 2, step: 1 } }, { type: 'assistant/message', seq: 8, time: 8, data: { turn: 2, step: 1, content: [ { type: 'tool-call', id: CallId('new-call'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, ] const closers = interruptedTurnClosers(events) expect(closers.map(e => e.type)).toEqual(['tool/result', 'step/end', 'turn/end']) @@ -128,7 +128,7 @@ describe('interruptedTurnClosers', () => { { type: 'assistant/message', seq: 2, time: 2, data: { turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('call-a'), name: 'bash', arguments: '{}' }, { type: 'tool-call', id: CallId('call-b'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, // call-a got answered before the crash; call-b did not. { type: 'tool/result', seq: 3, time: 3, data: { turn: 1, step: 1, callId: CallId('call-a'), content: [], isError: false } }, ] @@ -144,7 +144,7 @@ describe('interruptedTurnClosers', () => { { type: 'step/start', seq: 1, time: 1, data: { turn: 1, step: 1 } }, { type: 'assistant/message', seq: 2, time: 2, data: { turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('call-1'), name: 'bash', arguments: '{}' }, - ] } }, + ], provenance: { provider: 'mock', model: 'mock' } } }, { type: 'tool/call', seq: 3, time: 3, data: { turn: 1, step: 1, callId: CallId('call-1'), name: 'bash', arguments: '{}' } }, ] const closers = interruptedTurnClosers(events) diff --git a/packages/core/session/tests/request-header.spec.ts b/packages/core/session/tests/request-header.spec.ts index 8a5af819c3..6cd2e2c7fb 100644 --- a/packages/core/session/tests/request-header.spec.ts +++ b/packages/core/session/tests/request-header.spec.ts @@ -12,7 +12,7 @@ import { Session, SessionId, applyHeaderDelta, canonicalHeader, diffHeader, fold import type { EpochHeader, SessionEvent } from '@deepseek-ai/dsh-session' import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm' -const CONFIG = { model: 'm' } +const CONFIG = { provider: 'mock', model: 'm' } function tool(name: string, description = 'd'): ToolSchema { return { name, description, parameters: { type: 'object' } } @@ -100,10 +100,10 @@ describe('diffHeader / applyHeaderDelta', () => { }) it('replaces the config whole and leaves untouched parts alone', () => { - const prev = canonicalHeader({ config: { model: 'm' }, system: 's', tools: [tool('t')] }) - const next = canonicalHeader({ config: { model: 'm2', temperature: 0.1 }, system: 's', tools: [tool('t')] }) + const prev = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 's', tools: [tool('t')] }) + const next = canonicalHeader({ config: { provider: 'mock', model: 'm2', temperature: 0.1 }, system: 's', tools: [tool('t')] }) const delta = roundTrip(prev, next) - expect(delta).toEqual({ config: { model: 'm2', temperature: 0.1 } }) + expect(delta).toEqual({ config: { provider: 'mock', model: 'm2', temperature: 0.1 } }) }) }) @@ -163,16 +163,16 @@ describe('foldRequestHeader', () => { it('folds snapshot then deltas into the header in force, skipping unrelated events', () => { const session = new Session(SessionId('fold')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - const first = canonicalHeader({ config: { model: 'm' }, system: 'a\nb', tools: [tool('t')] }) + const first = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nb', tools: [tool('t')] }) session.append('request/header', { header: first, reason: 'initial' }) session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - const second = canonicalHeader({ config: { model: 'm' }, system: 'a\nc', tools: [tool('t')] }) + const second = canonicalHeader({ config: { provider: 'mock', model: 'm' }, system: 'a\nc', tools: [tool('t')] }) session.append('request/header-delta', diffHeader(first, second)!) expect(foldRequestHeader(headerEvents(session))).toEqual(second) // A later snapshot replaces the state wholesale (the 'resume'/'fallback' anchor). - const third = canonicalHeader({ config: { model: 'other' } }) + const third = canonicalHeader({ config: { provider: 'mock', model: 'other' } }) session.append('request/header', { header: third, reason: 'resume' }) expect(foldRequestHeader(headerEvents(session))).toEqual(third) }) @@ -180,7 +180,7 @@ describe('foldRequestHeader', () => { it('throws on a delta before any snapshot (corrupt log)', () => { const session = new Session(SessionId('fold-corrupt')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) - session.append('request/header-delta', { config: { model: 'x' } }) + session.append('request/header-delta', { config: { provider: 'mock', model: 'x' } }) expect(() => foldRequestHeader(headerEvents(session))).toThrow(/before any request\/header snapshot/) }) }) diff --git a/packages/core/session/tests/session.spec.ts b/packages/core/session/tests/session.spec.ts index 2204fc9027..e80f1b1373 100644 --- a/packages/core/session/tests/session.spec.ts +++ b/packages/core/session/tests/session.spec.ts @@ -10,7 +10,7 @@ describe('Session', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) session.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'hi' } }) - session.append('assistant/message', { + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'text', text: 'let me check' }, @@ -63,7 +63,7 @@ describe('Session', () => { const original = new Session(SessionId('s3')) original.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) original.append('user/message', { content: [{ type: 'text', text: 'q' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - original.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' }) + original.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' }) original.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) const replayed = new Session(SessionId('s3-replay'), [...original.events]) @@ -71,6 +71,43 @@ describe('Session', () => { expect(replayed.seq).toBe(original.seq) }) + it('rejects pre-provider request headers and assistant messages on seed/load', () => { + const requestHeader = { + type: 'request/header', seq: 0, time: 1, + data: { header: { config: { model: 'old-model' } }, reason: 'initial' }, + } as unknown as SessionEvent + expect(() => new Session(SessionId('old-header'), [requestHeader])) + .toThrow('seed request/header at index 0 lacks provider/model') + + const requestDelta = { + type: 'request/header-delta', seq: 0, time: 1, + data: { config: { model: 'old-model' } }, + } as unknown as SessionEvent + expect(() => new Session(SessionId('old-delta'), [requestDelta])) + .toThrow('seed request/header-delta at index 0 lacks provider/model') + + const assistantMessage = { + type: 'assistant/message', seq: 0, time: 1, + data: { turn: 1, step: 1, content: [{ type: 'text', text: 'old' }] }, + surfaceOp: 'append', + } as unknown as SessionEvent + expect(() => new Session(SessionId('old-assistant'), [assistantMessage])) + .toThrow('seed assistant/message at index 0 lacks provider/model provenance') + + const malformedHeader = { + type: 'request/header', seq: 0, time: 1, + data: { header: 'old-header' }, + } as unknown as SessionEvent + expect(() => new Session(SessionId('malformed-header'), [malformedHeader])) + .toThrow('seed request/header at index 0 lacks provider/model') + + const unrelatedPrimitiveData = { + type: 'plugin/event', seq: 0, time: 1, data: null, + } as unknown as SessionEvent + expect(new Session(SessionId('primitive-plugin-data'), [unrelatedPrimitiveData]).events) + .toEqual([unrelatedPrimitiveData]) + }) + it('isolates the log from mutation through a derived message (append-only contract)', () => { const session = new Session(SessionId('s4')) session.append('user/message', { content: [{ type: 'text', text: 'original' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) diff --git a/packages/core/session/tests/surface.spec.ts b/packages/core/session/tests/surface.spec.ts index 257828e466..ec06eba5c2 100644 --- a/packages/core/session/tests/surface.spec.ts +++ b/packages/core/session/tests/surface.spec.ts @@ -8,7 +8,7 @@ function surfaceSession(): Session { const s = new Session(SessionId('ss')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' }) s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) return s } @@ -74,7 +74,7 @@ describe('SurfaceManager', () => { // Surface nodes: seq 1 (user), seq 2 (assistant). // Replace both with a compaction marker. Both 1 and 2 are valid surface seqs. s.append('assistant/message', - { turn: 2, step: 1, content: [{ type: 'text', text: 'summary' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 2, step: 1, content: [{ type: 'text', text: 'summary' }] }, { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] }, ) // Now the surface should have just the compaction node. @@ -91,7 +91,7 @@ describe('SurfaceManager', () => { s.append('user/message', { content: [{ type: 'text', text: 'c' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // Replace seq 0 through 1 inclusive: shadow a and b, keep c. s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'summary' }] }, { surfaceOp: { op: 'replace', start: 0, end: 1 }, sourceEventSeqs: [0, 1] }, ) // seq 3 expect(s.surface.nodes.map(n => n.seq)).toEqual([3, 2]) @@ -108,7 +108,7 @@ describe('SurfaceManager', () => { s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 1 // Replace only seq 1 (single node). s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, { surfaceOp: { op: 'replace', start: 1, end: 1 }, sourceEventSeqs: [1] }, ) // seq 2 expect(s.surface.nodes.map(n => n.seq)).toEqual([0, 2]) @@ -120,7 +120,7 @@ describe('SurfaceManager', () => { const s = new Session(SessionId('bad-start')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0 s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, { surfaceOp: { op: 'replace', start: 5, end: 0 }, sourceEventSeqs: [5, 0] }, ) expect(() => s.surface.nodes).toThrow(/surface replace: start seq 5 not found/) @@ -130,7 +130,7 @@ describe('SurfaceManager', () => { const s = new Session(SessionId('bad-end')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 0 s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, { surfaceOp: { op: 'replace', start: 0, end: 99 }, sourceEventSeqs: [0] }, ) expect(() => s.surface.nodes).toThrow(/surface replace: end seq 99 not found/) @@ -142,7 +142,7 @@ describe('SurfaceManager', () => { s.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 1 // start=1, end=0 would be reversed order. s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'y' }] }, { surfaceOp: { op: 'replace', start: 1, end: 0 }, sourceEventSeqs: [1, 0] }, ) expect(() => s.surface.nodes).toThrow(/start seq 1.*after end seq 0/) @@ -151,7 +151,7 @@ describe('SurfaceManager', () => { it('sourceEventSeqs is snapshot so caller mutation does not affect logged event', () => { const s = new Session(SessionId('immutable')) const sources = [10, 20] - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, { surfaceOp: 'append', sourceEventSeqs: sources }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, { surfaceOp: 'append', sourceEventSeqs: sources }) // Mutate caller's array after append. sources.push(30) sources[0] = 99 @@ -166,7 +166,7 @@ describe('SurfaceManager', () => { s.append('user/message', { content: [{ type: 'text', text: 'c' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // Replace the middle node (seq 1) only, keeping seq 0 and seq 2. s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'x' }] }, { surfaceOp: { op: 'replace', start: 1, end: 1 }, sourceEventSeqs: [1] }, ) // seq 3 expect(s.surface.nodes.map(n => n.seq)).toEqual([0, 3, 2]) @@ -183,7 +183,7 @@ describe('SurfaceManager', () => { const s = new Session(SessionId('immutable-op')) s.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) const op = { op: 'replace' as const, start: 0, end: 0 } - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: op, sourceEventSeqs: [0] }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: op, sourceEventSeqs: [0] }) // Mutate caller's object after append. op.start = 99 const logged = s.events[1]! as SurfaceEvent @@ -208,7 +208,7 @@ describe('deriveMessages with surface', () => { s.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } }) s.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 1, text: 'i' } }) s.append('user/message', { content: [{ type: 'text', text: 'hello' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'hi' }] }, { surfaceOp: 'append' }) s.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) // Chunks and boundaries are NOT in the surface, so only 2 messages. expect(s.deriveMessages()).toHaveLength(2) @@ -217,7 +217,7 @@ describe('deriveMessages with surface', () => { it('deriveMessages via surface respects replace (shadowed nodes are excluded)', () => { const s = new Session(SessionId('compacted')) s.append('user/message', { content: [{ type: 'text', text: 'original' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'compacted' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] }) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'compacted' }] }, { surfaceOp: { op: 'replace', start: 0, end: 0 }, sourceEventSeqs: [0] }) // Only the compaction node is visible. const messages = s.deriveMessages() expect(messages).toHaveLength(1) @@ -239,7 +239,7 @@ describe('Session.append surface opts', () => { it('records sourceEventSeqs and surfaceOp on the event', () => { const s = new Session(SessionId('opts')) const event = s.append('assistant/message', - { turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, + { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'h' }] }, { surfaceOp: 'append', sourceEventSeqs: [3, 5, 7] }, ) expect(event.sourceEventSeqs).toEqual([3, 5, 7]) @@ -256,7 +256,7 @@ describe('Session.append surface opts', () => { const seed: SessionEvent[] = [ { type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } }, { type: 'step/start', seq: 1, time: 2, data: { turn: 1, step: 1 } }, - { type: 'assistant/message', seq: 2, time: 3, data: { turn: 1, step: 1, content: [] }, surfaceOp: 'append' }, + { type: 'assistant/message', seq: 2, time: 3, data: { turn: 1, step: 1, content: [], provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: 'append' }, { type: 'step/end', seq: 3, time: 4, data: { turn: 1, step: 1 } }, { type: 'turn/end', seq: 4, time: 5, data: { turn: 1, reason: { kind: 'completed' } } }, ] @@ -274,7 +274,7 @@ describe('Session.append surface opts', () => { it('surfaceOp primitives are not cloned (they are immutable)', () => { const s = new Session(SessionId('prim')) - const event = s.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) + const event = s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) // The string 'append' is a primitive — identity-preserving is fine. expect(event.surfaceOp).toBe('append') }) diff --git a/packages/core/session/tests/tool-pairing.spec.ts b/packages/core/session/tests/tool-pairing.spec.ts index 307b0d8658..9765abbd01 100644 --- a/packages/core/session/tests/tool-pairing.spec.ts +++ b/packages/core/session/tests/tool-pairing.spec.ts @@ -56,7 +56,7 @@ function toolStepSession(): Session { s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('user/message', { content: [{ type: 'text', text: 'go' }], source: { kind: 'user' } }, SURFACE) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'text', text: 'calling' }, @@ -122,7 +122,7 @@ describe('isToolPairingBalanced — region END (cut after a node)', () => { const s = new Session(SessionId('open-step')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, SURFACE) @@ -135,7 +135,7 @@ describe('isToolPairingBalanced — region END (cut after a node)', () => { const s = new Session(SessionId('trailing-steer')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, SURFACE) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, SURFACE) s.append('step/end', { turn: 1, step: 1 }) s.append('steering/message', { turn: 1, content: [{ type: 'text', text: 's' }], source: { kind: 'user' } }, SURFACE) expect(endBalanced(s, seqOf(s, 'steering/message'))).toBe(true) @@ -156,7 +156,7 @@ describe('isToolPairingBalanced — multiple tool calls in one assistant message const s = new Session(SessionId('two-call')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('c1'), name: 'a', arguments: '{}' }, @@ -190,7 +190,7 @@ describe('isToolPairingBalanced — a mid-step injection context/message', () => const s = new Session(SessionId('mid-inject')) s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, SURFACE) @@ -247,7 +247,7 @@ describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace s.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) s.append('step/start', { turn: 1, step: 1 }) s.append('user/message', { content: [{ type: 'text', text: 'u1' }], source: { kind: 'user' } }, SURFACE) - s.append('assistant/message', { + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'bash', arguments: '{}' }], }, SURFACE) @@ -267,7 +267,7 @@ describe('isToolPairingBalanced — CBR-001: a head checkpoint left by a replace }, { surfaceOp: { op: 'replace', start: u1, end: result } }) // The step's own assistant/message lands AFTER the checkpoint in the log, // still inside the open step. - s.append('assistant/message', { turn: 2, step: 1, content: [{ type: 'text', text: 'a2' }] }, SURFACE) + s.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 2, step: 1, content: [{ type: 'text', text: 'a2' }] }, SURFACE) return s } diff --git a/packages/fs/tool-fs/tests/fs-tools.e2e.ts b/packages/fs/tool-fs/tests/fs-tools.e2e.ts index a270e7c6d8..ca93bad63d 100644 --- a/packages/fs/tool-fs/tests/fs-tools.e2e.ts +++ b/packages/fs/tool-fs/tests/fs-tools.e2e.ts @@ -35,7 +35,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => ctx = await fsHarness(workdir, SYSTEM) // agentLoop.create prepares a session with no cwd, so the provider default // (config.cwd = workdir) is the workspace. - const agent = ctx.agentLoop.create(AgentId('fs-e2e'), { model: 'deepseek-v4-flash' }) + const agent = ctx.agentLoop.create(AgentId('fs-e2e'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) agent.send([{ type: 'text', text: 'Create a file named note.txt containing exactly the line: status: draft. ' @@ -68,7 +68,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('fs tools with-key smoke', () => agentId: AgentId('fs-e2e-cwd'), sessionId: SessionId(`fs-e2e-cwd-${Date.now()}`), meta: { cwd: sessionDir }, - agentOptions: { model: 'deepseek-v4-flash' }, + agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, }) handle.agent.send([{ type: 'text', text: 'Use the write tool to create a file named where.txt containing exactly the line: here. Tell me when done.' }]) diff --git a/packages/fs/tool-fs/tests/harness.ts b/packages/fs/tool-fs/tests/harness.ts index 61c163c28b..1bab80baaa 100644 --- a/packages/fs/tool-fs/tests/harness.ts +++ b/packages/fs/tool-fs/tests/harness.ts @@ -29,7 +29,7 @@ export async function fsHarness(fsCwd: string, persona = ''): Promise { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek) await ctx.plugin(LocalFileSystem, { cwd: fsCwd }) await ctx.plugin(FsPolicy) await ctx.plugin(ToolFs) diff --git a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts index 565f1076b5..89c18a5221 100644 --- a/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts +++ b/packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts @@ -57,7 +57,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -78,7 +78,7 @@ describe('threshold escalation', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -100,7 +100,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +124,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -142,7 +142,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -163,7 +163,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -179,7 +179,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -195,7 +195,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -215,8 +215,8 @@ describe('chain semantics', () => { toolCallResponse('b3', 'probe', { q: 1 }), textResponse('done'), ])) - const agentA = ctx.agentLoop.create(AgentId('a'), { model: 'mock-a' }) - const agentB = ctx.agentLoop.create(AgentId('b'), { model: 'mock-b' }) + const agentA = ctx.agentLoop.create(AgentId('a'), { provider: 'mock-a', model: 'model-a' }) + const agentB = ctx.agentLoop.create(AgentId('b'), { provider: 'mock-b', model: 'model-b' }) agentA.send([{ type: 'text', text: 'go' }]) agentB.send([{ type: 'text', text: 'go' }]) await Promise.all([waitForIdle(ctx, agentA), waitForIdle(ctx, agentB)]) @@ -235,7 +235,7 @@ describe('chain semantics', () => { textResponse('turn two done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) agent.send([{ type: 'text', text: 'again' }]) @@ -256,14 +256,14 @@ describe('chain semantics', () => { // (the loop.spec pattern): a child plugin fiber owns `first`. let first!: ReactLoopAgent const fiber = await ctx.plugin(Object.assign((inner: Context) => { - first = inner.agentLoop.create(AgentId('reused'), { model: 'mock' }) + first = inner.agentLoop.create(AgentId('reused'), { provider: 'mock', model: 'mock' }) }, { inject: ['agentLoop'] })) first.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, first) await fiber.dispose() await first.done - const second = ctx.agentLoop.create(AgentId('reused'), { model: 'mock' }) + const second = ctx.agentLoop.create(AgentId('reused'), { provider: 'mock', model: 'mock' }) second.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, second) @@ -279,7 +279,7 @@ describe('chain semantics', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -295,7 +295,7 @@ describe('chain semantics', () => { toolCallResponse('c1', 'probe', { q: 1 }), // if the direct call had counted, this would be #2 textResponse('done'), ])) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -317,7 +317,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -348,7 +348,7 @@ describe('fold onto the downstream decision', () => { textResponse('done'), ]) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 2cbc995ce3..ef2bf1087c 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -95,7 +95,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'do something' }]) await waitForIdle(ctx, agent) @@ -118,7 +118,7 @@ describe('hooks-claude bridge — UserPromptSubmit', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -143,7 +143,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'danger', description: 'd', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'should not run' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'use danger' }]) await waitForIdle(ctx, agent) @@ -166,7 +166,7 @@ describe('hooks-claude bridge — PreToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'safe', description: 's', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ran ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'use safe' }]) await waitForIdle(ctx, agent) @@ -188,7 +188,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'raw output' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -209,7 +209,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(dir, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -233,7 +233,7 @@ describe('hooks-claude bridge — PostToolUse', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -257,7 +257,7 @@ describe('hooks-claude bridge — SessionStart', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // session-start fires async (detached .then → agent.inject); wait for the // injected context/message to actually land before sending, rather than a // fixed sleep that flakes under load. @@ -359,7 +359,7 @@ describe('hooks-claude bridge — load resilience', () => { await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 }) await ctx.plugin(HooksClaude, { configPath: '/nonexistent/hooks.json' }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The turn ran normally — no hooks, no crash. @@ -385,7 +385,7 @@ describe('hooks-claude bridge — load resilience', () => { const fiber = await ctx.plugin(HooksClaude, { configPath: join(dir, 'hooks.json') }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone diff --git a/packages/hooks/hooks-claude/tests/coverage.spec.ts b/packages/hooks/hooks-claude/tests/coverage.spec.ts index 7feb46df05..af9b6e9289 100644 --- a/packages/hooks/hooks-claude/tests/coverage.spec.ts +++ b/packages/hooks/hooks-claude/tests/coverage.spec.ts @@ -72,7 +72,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war const ctx = await harness(path, adapter, { pluginRoot: d, projectDir: d }) ctx.logger.warn = warn as never ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) // substituted command ran @@ -88,7 +88,7 @@ describe('hooks-claude coverage — config option arms + substitution + skip war ctx.logger.warn = warn as never let sawArgs: unknown ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: { command: { type: 'string' } }, async execute(args) { sawArgs = args; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // updatedInput is NOT honored — the tool ran with the ORIGINAL args. @@ -104,7 +104,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ran')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // The prompt proceeded unchanged; no context/message injected. @@ -134,7 +134,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -159,7 +159,7 @@ describe('hooks-claude coverage — empty/no-op outcomes and no-agent paths', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -175,7 +175,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) @@ -192,7 +192,7 @@ describe('hooks-claude coverage — Stop continuation + subagent inject/catch', const path = hooks(d, { Stop: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // A second model request ran → the empty-reason block forced continuation. @@ -240,7 +240,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -254,7 +254,7 @@ describe('hooks-claude coverage — default reasons + sparse payloads', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -283,7 +283,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const path = hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const turnEnd = events(agent).findLast(e => e.type === 'turn/end') @@ -298,7 +298,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'x' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // ask (no reason) → degrades to deny with the registry's generic message. @@ -313,7 +313,7 @@ describe('hooks-claude coverage — more default/sparse arms', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -342,7 +342,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () // the protocol lib's reference default, not a config knob). HooksClaude.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) @@ -357,7 +357,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) @@ -372,7 +372,7 @@ describe('hooks-claude coverage — schema-bypass apply + unspawnable hook', () const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -393,7 +393,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -410,7 +410,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const adapter = new MockAdapter([toolCallResponse('c1', 'echo', {}), textResponse('done')]) const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -430,7 +430,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) let ran = false ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(ran).toBe(true) // the mismatched deny was discarded → the tool ran @@ -448,7 +448,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) // NB: no projectDir // The factory create() path honors meta.cwd (the plain agentLoop.create() does not). const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: workspace }, agentOptions: { provider: 'mock', model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(events(handle.agent as ReactLoopAgent).some(e => e.type === 'context/message' @@ -468,7 +468,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => // A later listener that blocks every prompt (registered AFTER the bridge). const { AgentId: AId } = await import('@deepseek-ai/dsh-agent') ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // the downstream block won: the model was never called, no user/message was @@ -492,7 +492,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) @@ -514,7 +514,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -533,7 +533,7 @@ describe('hooks-claude coverage — continue:false, context arm, no-cwd', () => const ctx = await harness(path, adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') @@ -557,7 +557,7 @@ describe('hooks-claude coverage — executor reject + no-open-turn', () => { const bash = ctx.bash bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') @@ -573,7 +573,7 @@ describe('hooks-claude coverage — detached-listener catch handlers', () => { const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Make inject throw, forcing the SessionStart .catch path. const original = agent.inject.bind(agent) let threw = false @@ -613,7 +613,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) @@ -649,7 +649,7 @@ describe('hooks-claude coverage — hook runs in the session cwd, not the server // Register a live child on its own session cwd; emit subagent/end with its id. const { SessionId } = await import('@deepseek-ai/dsh-session') - const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { model: 'mock' } }) + const childHandle = await ctx.agents.create({ agentId: AgentId('child-stop'), sessionId: SessionId('child-stop-session'), meta: { cwd: childDir }, agentOptions: { provider: 'mock', model: 'mock' } }) ctx.emit('subagent/end', { provider: 'inproc', id: childHandle.agent.id, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) @@ -670,7 +670,7 @@ describe('hooks-claude coverage — systemMessage is warned, not surfaced', () = const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) @@ -691,7 +691,7 @@ describe('hooks-claude coverage — SessionStart timing is best-effort (no-wait) const path = hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: s }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(path, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // Send immediately — do NOT wait for the session-start inject. agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) diff --git a/packages/hooks/hooks-codex/tests/bridge.spec.ts b/packages/hooks/hooks-codex/tests/bridge.spec.ts index e0677306b0..6cdfd2f81f 100644 --- a/packages/hooks/hooks-codex/tests/bridge.spec.ts +++ b/packages/hooks/hooks-codex/tests/bridge.spec.ts @@ -82,7 +82,7 @@ describe('hooks-codex bridge', () => { const ctx = await harness(dir, adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'no' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'run ls' }]) await waitForIdle(ctx, agent) @@ -107,7 +107,7 @@ describe('hooks-codex bridge', () => { // Step 1 has no tool calls → would stop; the Stop hook forces step 2. const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer after goal')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) @@ -124,7 +124,7 @@ describe('hooks-codex bridge', () => { const adapter = new MockAdapter([textResponse('fine')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) // Ran normally; the unknown event was dropped at parse. @@ -135,7 +135,7 @@ describe('hooks-codex bridge', () => { const dir = configDir() // no hooks.json written const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(dir, adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) @@ -161,7 +161,7 @@ describe('hooks-codex bridge', () => { const fiber = await ctx.plugin(HooksCodex, { configPath: join(dir, 'hooks.json'), model: 'm' }) await fiber.dispose() ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // not blocked → the listener is gone @@ -190,7 +190,7 @@ describe('hooks-codex bridge', () => { ctx.llm.registerAdapter(['mock'], new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) // fires agent/session-start + ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) // fires agent/session-start await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await fiber.dispose() diff --git a/packages/hooks/hooks-codex/tests/coverage.spec.ts b/packages/hooks/hooks-codex/tests/coverage.spec.ts index 774b308fa1..95d02e40a0 100644 --- a/packages/hooks/hooks-codex/tests/coverage.spec.ts +++ b/packages/hooks/hooks-codex/tests/coverage.spec.ts @@ -52,7 +52,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', '#!/usr/bin/env bash\nexit 2\n') }] }] }) const adapter = new MockAdapter([textResponse('no')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) const te = events(agent).findLast(e => e.type === 'turn/end') @@ -64,7 +64,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'c.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"UserPromptSubmit","additionalContext":"ctx-x"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('ctx-x') }) @@ -78,7 +78,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('should not run')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.on('agent/prompt-submit', async () => ({ kind: 'block' as const, reason: 'policy veto' })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(0) expect(events(agent).some(e => e.type === 'user/message')).toBe(false) @@ -96,7 +96,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { content: [{ type: 'text' as const, text: 'rewritten-prompt' }], additionalContext: { content: [{ type: 'text' as const, text: 'from-downstream' }], source: { kind: 'plugin' as const, plugin: 'policy' } }, })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const req = JSON.stringify(adapter.requests[0]!.messages) expect(req).toContain('from-bridge') @@ -111,7 +111,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'accept' as const, content: [{ type: 'text' as const, text: 'rewritten-result' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.content.some(b => b.type === 'text' && b.text === 'rewritten-result')).toBe(true) @@ -125,7 +125,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'echo', description: 'e', parameters: {}, async execute() { return [{ type: 'text', text: 'ok' }] } })) ctx.on('tools/post-execute', async () => ({ kind: 'block' as const, feedback: [{ type: 'text' as const, text: 'downstream-block' }] })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const result = events(agent).find(e => e.type === 'tool/result') expect(result?.type === 'tool/result' && result.data.isError).toBe(true) @@ -138,7 +138,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', '#!/usr/bin/env bash\necho \'{"hookSpecificOutput":{"hookEventName":"SessionStart","additionalContext":"start-ctx"}}\'\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('start-ctx')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -151,7 +151,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -164,7 +164,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('post-ctx')))).toBe(true) }) @@ -176,7 +176,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: {}, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // clean-exit hook allows; commandOf returned '' }) @@ -187,7 +187,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.exitCode).toBe(0) @@ -200,7 +200,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary?.endsWith('…')).toBe(true) @@ -223,7 +223,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter, { stderrSummaryMaxChars: 40 }) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.stderrSummary).toBe('x'.repeat(40) + '…') @@ -246,7 +246,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { // Direct apply (schema bypass) → the `model ?? ''` fallback is exercised. HooksCodex.apply(ctx, { configPath: join(d, 'hooks.json') }) ctx.llm.registerAdapter(['mock'], adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(existsSync(marker)).toBe(true) expect(warn).toHaveBeenCalledWith(expect.stringContaining('async hook')) @@ -259,7 +259,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -273,7 +273,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\ntouch "${marker}"\nexit 0\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => existsSync(marker)) // the clean no-output hook has finished agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(events(agent).some(e => e.type === 'context/message')).toBe(false) @@ -285,7 +285,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.inject = (() => { throw new Error('inject boom') }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SessionStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SessionStart hook failed')) @@ -298,7 +298,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) }) @@ -311,7 +311,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(true) // matcher didn't match → no hook ran → tool proceeded expect(events(agent).some(e => e.type === 'hook/invoked')).toBe(false) @@ -327,7 +327,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && res.data.decision).toBe('stop') // recorded @@ -340,7 +340,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.content.some(b => b.type === 'text' && b.text.includes('blocked by PreToolUse hook'))).toBe(true) @@ -352,7 +352,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 'x' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const r = events(agent).find(e => e.type === 'tool/result') expect(r?.type === 'tool/result' && r.data.isError).toBe(true) @@ -369,7 +369,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'Bash', { command: 7 }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'number' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_input: { command: string } } expect(payload.tool_input.command).toBe('') @@ -405,7 +405,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.bash.run = (() => Promise.reject(new Error('executor down'))) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const res = events(agent).find(e => e.type === 'hook/result') expect(res?.type === 'hook/result' && 'exitCode' in res.data).toBe(false) @@ -419,7 +419,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { Stop: [{ hooks: [{ type: 'command', command: sh(d, 's.sh', `#!/usr/bin/env bash\nif [ -e "${marker}" ]; then exit 0; fi\ntouch "${marker}"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('one'), textResponse('two')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(2) // empty-reason block forced continuation expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('blocked by Stop hook') @@ -432,7 +432,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'ctx.sh', '#!/usr/bin/env bash\necho "extra guidance from a plain hook"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('extra guidance from a plain hook') }) @@ -448,7 +448,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'b.sh', `#!/usr/bin/env bash\ntouch "${marker}"\necho "stale"\nexit 2\n`) }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => existsSync(marker)) // the exit-2 hook has finished expect(events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('stale')))).toBe(false) @@ -462,7 +462,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'e.sh', '#!/usr/bin/env bash\necho "stale"\nexit 1\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(adapter.requests).toHaveLength(1) // exit 1 is non-blocking → the turn ran expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('stale') @@ -473,7 +473,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { SessionStart: [{ hooks: [{ type: 'command', command: sh(d, 'ss.sh', '#!/usr/bin/env bash\necho "session preamble"\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) await waitFor(() => events(agent).some(e => e.type === 'context/message' && e.data.content.some(b => b.type === 'text' && b.text.includes('session preamble')))) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) @@ -487,7 +487,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { hooks(d, { UserPromptSubmit: [{ hooks: [{ type: 'command', command: sh(d, 'j.sh', '#!/usr/bin/env bash\necho \'{"unrelated":"json"}\'\nexit 0\n') }] }] }) const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('unrelated') }) @@ -502,7 +502,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([toolCallResponse('c1', 'shell', { command: 'ls' }), textResponse('done')]) const ctx = await harness(join(d, 'hooks.json'), adapter) ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) const payload = JSON.parse(readFileSync(cap, 'utf8')) as { tool_name: string; tool_input: { command: string } } expect(payload.tool_name).toBe('shell') @@ -518,7 +518,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const ctx = await harness(join(d, 'hooks.json'), adapter) let ran = false ctx.tools.register(defineTool({ name: 'shell', description: 'b', parameters: { command: { type: 'string' } }, async execute() { ran = true; return [{ type: 'text', text: 'ok' }] } })) - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(ran).toBe(false) // the matcher fired → the hook denied the tool expect(events(agent).some(e => e.type === 'hook/invoked' && e.data.point === 'PreToolUse')).toBe(true) @@ -530,7 +530,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { const adapter = new MockAdapter([textResponse('ok')]) const ctx = await harness(join(d, 'hooks.json'), adapter) const warn = vi.fn(); ctx.logger.warn = warn as never - const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('a1'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'go' }]); await waitForIdle(ctx, agent) expect(warn).toHaveBeenCalledWith(expect.stringContaining('systemMessage')) expect(JSON.stringify(adapter.requests[0]!.messages)).not.toContain('heads up') @@ -553,7 +553,7 @@ describe('hooks-codex coverage — decision mapping paths', () => { ctx.llm.registerAdapter(['mock'], adapter) ctx.tools.register(defineTool({ name: 'Bash', description: 'b', parameters: { command: { type: 'string' } }, async execute() { return [{ type: 'text', text: 'ok' }] } })) const { SessionId } = await import('@deepseek-ai/dsh-session') - const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { model: 'mock' } }) + const handle = await ctx.agents.create({ agentId: AgentId('a1'), sessionId: SessionId('s1'), meta: { cwd: sessionDir }, agentOptions: { provider: 'mock', model: 'mock' } }) handle.agent.send([{ type: 'text', text: 'go' }]) await waitForIdle(ctx, handle.agent as ReactLoopAgent) expect(existsSync(marker)).toBe(true) diff --git a/packages/llm/README.md b/packages/llm/README.md index 3fc5c9cf9e..d971fc830c 100644 --- a/packages/llm/README.md +++ b/packages/llm/README.md @@ -6,6 +6,6 @@ The LLM seam and its provider adapters. The interface package (`llm`) owns the a |---|---|---| | `llm/` | Abstract LLM service + content-block vocabulary + chunk assembler | `ctx.llm` | | `llm-deepseek/` | DeepSeek API adapter (hand-rolled fetch/SSE) | (registers on `ctx.llm`) | -| `llm-pi-ai/` | DeepSeek adapter via `@earendil-works/pi-ai` (design twin) | (registers on `ctx.llm`) | +| `llm-pi-ai/` | Multi-provider adapter via `@earendil-works/pi-ai` | (registers on `ctx.llm`) | -The interface lives at `llm/llm/`; adapters are flat siblings under the group. A new provider adapter joins here and registers on `ctx.llm` without touching the interface. See [twin LLM adapters](../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md) for why two adapters exist. +The interface lives at `llm/llm/`; adapters are flat siblings under the group. Requests route by `provider`, while `model` is passed through to the selected adapter. A new provider adapter joins here and registers one or more provider routes on `ctx.llm` without touching the interface. See [twin LLM adapters](../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md) for the contract-validation origin of the two shipping implementations. diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index 15fad9f881..77b62426e6 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -2,7 +2,7 @@ DeepSeek chat-completions adapter for the harness LLM seam: hand-rolled `fetch` + SSE translation from the official wire format (source of truth: the API docs — guides/thinking_mode, guides/tool_calls, api/create-chat-completion) into the `StreamChunk` protocol. -A second, independent implementation of the same seam exists in `@deepseek-ai/dsh-llm-pi-ai` (library-backed). Same Config shape — pick one per context (registering both for the same model names throws by design). +A second, library-backed implementation of the same seam exists in `@deepseek-ai/dsh-llm-pi-ai`. This package always owns the `deepseek` provider route; mounting a pi-ai profile with `provider: deepseek` in the same context throws `LlmError('DUPLICATE_ADAPTER')` by design. ## Config @@ -12,12 +12,11 @@ A second, independent implementation of the same seam exists in `@deepseek-ai/ds config: apiKey: !!js process.env.DEEPSEEK_API_KEY # or rely on the env fallback baseURL: !!js process.env.DEEPSEEK_BASE_URL # default: https://api.deepseek.com - models: [deepseek-v4-flash, deepseek-v4-pro] # one adapter, registered for each name thinking: enabled # optional; provider default is enabled reasoningEffort: high # optional; high | max — omitted ⇒ not sent ``` -`models` lists every model name this one adapter instance serves: the adapter registers itself for each (the harness model name IS the wire `model` string), so a `generate`/`stream` call routes to it whenever `options.model` is any of them. Registering a second adapter for a name already taken throws `LlmError('DUPLICATE_ADAPTER')` (the LLM service enforces one adapter per model, all-or-nothing). +The plugin registers the single provider route `deepseek`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`. `reasoningEffort` is **omitted by default** — when unset, the `reasoning_effort` wire field is not sent and the server applies its own default for the model. The only accepted values are `high` and `max` (DeepSeek's official effort levels). It is meaningful only with thinking enabled (the provider default). diff --git a/packages/llm/llm-deepseek/src/index.ts b/packages/llm/llm-deepseek/src/index.ts index 3a3d7bb4a1..b5c5758e01 100644 --- a/packages/llm/llm-deepseek/src/index.ts +++ b/packages/llm/llm-deepseek/src/index.ts @@ -1,6 +1,6 @@ /** * DeepSeek LLM adapter plugin: registers a {@link DeepSeekAdapter} for the - * configured model names on `ctx.llm`. + * `deepseek` provider route on `ctx.llm`. * * Config is cordis-native (schemastery). Secrets flow per the repo policy: * `apiKey` from cordis.yml via the `!!js` tag (`!!js process.env.DEEPSEEK_API_KEY`) @@ -12,7 +12,6 @@ * config: * apiKey: !!js process.env.DEEPSEEK_API_KEY * baseURL: !!js process.env.DEEPSEEK_BASE_URL - * models: [deepseek-v4-flash, deepseek-v4-pro] * ``` * * @module @deepseek-ai/dsh-llm-deepseek @@ -45,8 +44,6 @@ export interface Config { apiKey?: string /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */ baseURL?: string - /** Model names to register (sent verbatim on the wire). */ - models?: string[] /** Thinking-mode default for every request (provider default: enabled). */ thinking?: 'enabled' | 'disabled' /** Thinking effort (only meaningful with thinking enabled). */ @@ -56,7 +53,6 @@ export interface Config { export const Config: z = z.object({ apiKey: z.string(), baseURL: z.string(), - models: z.array(z.string()).default(['deepseek-v4-flash', 'deepseek-v4-pro']), thinking: z.union(['enabled', 'disabled']), reasoningEffort: z.union(['high', 'max']), }) @@ -70,10 +66,7 @@ export function apply(ctx: Context, config: Config): void { throw new Error('llm-deepseek: an API key is required (Config.apiKey or $DEEPSEEK_API_KEY)') } const baseURL = config.baseURL ?? process.env.DEEPSEEK_BASE_URL ?? PUBLIC_BASE_URL - // schemastery's .default() guarantees models is set after validation. - const models = config.models as string[] - - ctx.llm.registerAdapter(models, new DeepSeekAdapter({ + ctx.llm.registerAdapter(['deepseek'], new DeepSeekAdapter({ apiKey, baseURL, defaults: { diff --git a/packages/llm/llm-deepseek/tests/adapter.e2e.ts b/packages/llm/llm-deepseek/tests/adapter.e2e.ts index b01b498dff..e02476eaef 100644 --- a/packages/llm/llm-deepseek/tests/adapter.e2e.ts +++ b/packages/llm/llm-deepseek/tests/adapter.e2e.ts @@ -16,11 +16,11 @@ const FLASH = 'deepseek-v4-flash' const PRO = 'deepseek-v4-pro' const contexts: Context[] = [] -async function harness(model: string, config: Partial = {}) { +async function harness(_model: string, config: Partial = {}) { const ctx = new Context() contexts.push(ctx) await ctx.plugin(LlmService) - await ctx.plugin(LlmDeepSeek, { models: [model], ...config }) + await ctx.plugin(LlmDeepSeek, config) return ctx } @@ -134,6 +134,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-deepseek e2e (real API)', () const ctx = await harness(FLASH, { thinking: 'disabled' }) const kinds: string[] = [] for await (const chunk of ctx.llm.stream({ + provider: 'deepseek', model: FLASH, messages: ask('Count from 1 to 5, digits only.'), maxTokens: 50, diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index 46f123a1c7..e31b1c2e41 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -86,7 +86,7 @@ const textEvents = [ async function harness(baseURL: string, config: object = {}) { const ctx = new Context() await ctx.plugin(LlmService) - await ctx.plugin(LlmDeepSeek, { apiKey: 'test-key', baseURL, models: ['deepseek-v4-flash'], ...config }) + await ctx.plugin(LlmDeepSeek, { apiKey: 'test-key', baseURL, ...config }) return ctx } @@ -123,6 +123,7 @@ describe('DeepSeekAdapter against a mock server', () => { const kinds: string[] = [] for await (const chunk of ctx.llm.stream({ + provider: 'deepseek', model: 'deepseek-v4-flash', messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }], })) { @@ -198,7 +199,7 @@ describe('DeepSeekAdapter against a mock server', () => { ) try { const iterate = async (): Promise => { - for await (const _chunk of adapter.stream({ model: 'm', messages: [] })) { /* drain */ } + for await (const _chunk of adapter.stream({ provider: 'deepseek', model: 'm', messages: [] })) { /* drain */ } } await expect(iterate()).rejects.toThrow(/no response body/) } finally { @@ -224,6 +225,7 @@ describe('DeepSeekAdapter against a mock server', () => { const pending = (async () => { const chunks = [] for await (const chunk of ctx.llm.stream({ + provider: 'deepseek', model: 'deepseek-v4-flash', messages: [], signal: controller.signal, @@ -239,25 +241,24 @@ describe('DeepSeekAdapter against a mock server', () => { }) describe('plugin registration and config', () => { - it('registers the configured models and unregisters on dispose (HMR safety)', async () => { + it('registers the deepseek provider and unregisters on dispose (HMR safety)', async () => { const server = await mockServer([]) const ctx = new Context() await ctx.plugin(LlmService) const fiber = await ctx.plugin(LlmDeepSeek, { apiKey: 'k', baseURL: server.url, - models: ['deepseek-v4-flash', 'deepseek-v4-pro'], }) - expect(ctx.llm.models().sort()).toEqual(['deepseek-v4-flash', 'deepseek-v4-pro']) + expect(ctx.llm.providers()).toEqual(['deepseek']) await fiber.dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) - it('defaults the model list', async () => { + it('always owns the deepseek provider', async () => { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(LlmDeepSeek, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) - expect(ctx.llm.models().sort()).toEqual(['deepseek-v4-flash', 'deepseek-v4-pro']) + expect(ctx.llm.providers()).toEqual(['deepseek']) }) it('falls back to DEEPSEEK_API_KEY and DEEPSEEK_BASE_URL env vars', async () => { @@ -266,7 +267,7 @@ describe('plugin registration and config', () => { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(LlmDeepSeek, {}) - expect(ctx.llm.models().length).toBeGreaterThan(0) + expect(ctx.llm.providers()).toEqual(['deepseek']) }) it('throws a clear error when no API key is available', async () => { @@ -275,7 +276,7 @@ describe('plugin registration and config', () => { await ctx.plugin(LlmService) await expect(ctx.plugin(LlmDeepSeek, {})) .rejects.toThrow(/an API key is required/) - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) it('prefers explicit config over env for key and base URL', async () => { @@ -292,7 +293,7 @@ describe('plugin registration and config', () => { vi.stubEnv('DEEPSEEK_BASE_URL', server.url) const ctx = new Context() await ctx.plugin(LlmService) - await ctx.plugin(LlmDeepSeek, { apiKey: 'k', models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek, { apiKey: 'k' }) await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) expect(server.requests).toHaveLength(1) }) @@ -304,7 +305,7 @@ describe('plugin registration and config', () => { await ctx.plugin(LlmService) // Registration succeeds; no call is made (would hit api.deepseek.com). await ctx.plugin(LlmDeepSeek, {}) - expect(ctx.llm.models().length).toBeGreaterThan(0) + expect(ctx.llm.providers()).toEqual(['deepseek']) }) it('adapter is constructible directly for embedding', () => { diff --git a/packages/llm/llm-deepseek/tests/assemble.ts b/packages/llm/llm-deepseek/tests/assemble.ts index b0182615e0..494eeac494 100644 --- a/packages/llm/llm-deepseek/tests/assemble.ts +++ b/packages/llm/llm-deepseek/tests/assemble.ts @@ -15,11 +15,19 @@ export interface AssembledResult { finish: FinishReason } -export async function assemble(ctx: Context, options: GenerateOptions): Promise { +export async function assemble(ctx: Context, options: Omit & { provider?: string }): Promise { const assembler = new BlockAssembler() - for await (const chunk of ctx.llm.stream(options)) assembler.push(chunk) + const request = { provider: 'deepseek', ...options } + for await (const chunk of ctx.llm.stream(request)) assembler.push(chunk) return { - message: assembler.message(), + message: { + ...assembler.message(), + provenance: { + provider: request.provider, + model: request.model, + ...assembler.replayState === undefined ? {} : { replayState: assembler.replayState }, + }, + }, ...assembler.usage !== undefined ? { usage: assembler.usage } : {}, finish: assembler.finish, } diff --git a/packages/llm/llm-deepseek/tests/serialize.spec.ts b/packages/llm/llm-deepseek/tests/serialize.spec.ts index 3e533f8e7c..a7d5cc7e2a 100644 --- a/packages/llm/llm-deepseek/tests/serialize.spec.ts +++ b/packages/llm/llm-deepseek/tests/serialize.spec.ts @@ -4,7 +4,7 @@ import type { ContentBlock, GenerateOptions, Message } from '@deepseek-ai/dsh-ll import { serializeMessages, serializeRequest } from '@deepseek-ai/dsh-llm-deepseek' function request(overrides: Partial = {}): GenerateOptions { - return { model: 'deepseek-v4-flash', messages: [], ...overrides } + return { provider: 'deepseek', model: 'deepseek-v4-flash', messages: [], ...overrides } } describe('serializeMessages', () => { diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index f74ccd2246..ebf3fc98ed 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -1,42 +1,56 @@ # @deepseek-ai/dsh-llm-pi-ai -DeepSeek adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](https://www.npmjs.com/package/@earendil-works/pi-ai) (the LLM library behind the pi agent). - -## Why a second adapter exists - -`@deepseek-ai/dsh-llm-deepseek` already talks to the same endpoint. This package is its **design-verification twin**: same models, same wire protocol, completely different internals — a unified LLM library with its own event vocabulary versus hand-rolled fetch/SSE. Anything the harness `StreamChunk` protocol cannot express for BOTH implementations is a core-vocabulary bug. The differences it exercised on purpose: - -- pi-ai hands tool-call `arguments` around as **parsed objects**; the harness keeps raw JSON strings. The adapter patches replay payloads back to the original raw strings before sending them, and re-stringifies parsed output tool calls at `block-end`. -- pi-ai reports failures as **in-stream error events** (it never throws mid-stream); these map to `finish {kind:'error'|'aborted'}` chunks — the protocol's other sanctioned error path besides throwing (which llm-deepseek uses). -- pi-ai folds reasoning tokens into `usage.output`; there is no separate reasoning count to map. -- pi-ai's options omit some DeepSeek/OpenAI-compatible details; the adapter uses its `onPayload` hook to preserve the harness contract (`stop`, scrubbing pi-ai's own per-tool `strict` default — the hand-rolled twin sends no such field — omitted reasoning effort, raw replayed tool arguments). +Generic multi-provider adapter for the harness LLM seam backed by [`@earendil-works/pi-ai`](https://www.npmjs.com/package/@earendil-works/pi-ai). One plugin instance owns an explicit list of provider profiles; every request selects a profile with `GenerateOptions.provider` and resolves `GenerateOptions.model` dynamically from pi-ai's installed catalog. ## Config -Same shape as llm-deepseek (one-line swap in cordis.yml), with pi-ai's thinking-level vocabulary: +Configure credentials and deployment-specific transport settings per provider. Omitting `apiKey` delegates authentication to pi-ai's provider-native ambient discovery. `baseURL` overrides only the endpoint of the selected catalog model, preserving its API family and compatibility metadata, so private proxies such as `https://proxy.example.com:8443` remain supported. ```yaml - id: llm name: '@deepseek-ai/dsh-llm-pi-ai' config: - apiKey: !!js process.env.DEEPSEEK_API_KEY - baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: [deepseek-v4-flash, deepseek-v4-pro] - reasoning: high # off | high | xhigh (xhigh → wire 'max') + providers: + - provider: openai + apiKey: !!js process.env.OPENAI_API_KEY + baseURL: https://proxy.example.com:8443 + reasoning: high + - provider: anthropic + apiKey: !!js process.env.ANTHROPIC_API_KEY + maxRetries: 2 + - provider: openrouter + apiKey: !!js process.env.OPENROUTER_API_KEY + headers: + X-Deployment: production ``` +Each provider name must exist in pi-ai's installed catalog and may appear only once in this plugin instance. Registration with `ctx.llm` is atomic: a collision with any provider route already owned by another adapter fails plugin loading without registering the remaining routes. Model ids are not lifecycle config; an unknown model fails before any provider request with `LlmError('UNKNOWN_MODEL')`. + +Supported profile fields are `provider`, `apiKey`, `baseURL`, `headers`, `reasoning`, `thinkingBudgets`, `cacheRetention`, `transport`, `timeoutMs`, `websocketConnectTimeoutMs`, `maxRetries`, and `maxRetryDelayMs`. They map to pi-ai's common stream options. Harness app attribution wins a conflicting configured header name. + +## Provider/model routing and replay + +The selected pi-ai catalog descriptor supplies the protocol implementation. This includes native API differences such as OpenAI models whose descriptor uses the Responses API rather than Chat Completions; the harness adapter does not hardcode endpoint selection by model name. + +Successful assistant responses store a versioned, lossless-JSON replay state beside their durable provider/model provenance. At request time, `LlmService` passes replay state only when the historical provider route and target provider route are currently owned by this same `PiAiAdapter` instance. The adapter validates the state and restores pi-ai response ids and provider signatures even when the target provider or model changes; pi-ai then decides which metadata its target API can reuse. History without replay state is translated as foreign provider-neutral content and never impersonates a native pi-ai response. + +If a listener rewrites assembled assistant content, the loop drops replay state before logging the message because its provider metadata no longer describes the content. Invalid versions, malformed metadata, and content/block mismatches fail explicitly with `LlmError('INVALID_REPLAY_STATE')`. + +## Vocabulary differences + +- pi-ai tool-call arguments are parsed objects; the harness stores raw JSON strings. The adapter parses input and re-stringifies output. +- pi-ai reports failures as in-stream error events; these map to `finish {kind:'error'|'aborted'}` chunks. +- pi-ai folds reasoning tokens into output usage; there is no separate reasoning count to map. +- `GenerateOptions.stop` is rejected with `UNSUPPORTED_OPTION` because pi-ai's common streaming surface cannot guarantee it across providers. + ## App attribution -Every request carries the shared attribution header from dsh-llm's `attributionHeaders()`, passed through pi-ai's `headers` stream option (pi-ai merges caller headers last, so it always reaches the wire - the unit suite asserts arrival on the mock server, same as llm-deepseek). OpenRouter-specific app attribution headers are intentionally not sent by this adapter contract; they are deferred to a future explicit OpenRouter adapter or mode. See [dsh-llm § App attribution](../llm/README.md#app-attribution-attributionts). +Every request carries the shared attribution header from dsh-llm's `attributionHeaders()`, merged through pi-ai's `headers` stream option. Provider-specific app-attribution headers are not synthesized. See [dsh-llm § App attribution](../llm/README.md#app-attribution-attributionts). ## Dependency weight -pi-ai declares the openai/anthropic/google/mistral/AWS SDKs as install-time dependencies. They are lazy-loaded — only the openai SDK actually loads for this adapter — but they do land in `node_modules`. Accepted for a package whose purpose is design verification. - -## Limitations - -Same MVP contract as llm-deepseek: `tool_choice` is not mapped. +pi-ai installs several provider SDKs and lazy-loads the one selected by the catalog model. The dependency weight is isolated to this opt-in adapter package. ## Testing -Unit suites run against a local `node:http` mock SSE server (pi-ai's openai SDK happily talks to any base URL). Real-API coverage in `tests/adapter.e2e.ts` (`pnpm run test:e2e`, key-gated): V4 Flash + V4 Pro across all exposed reasoning levels (off/high/xhigh), the thinking+tools round trip, and a cross-adapter structural-equivalence check against llm-deepseek. +Unit tests use pi-ai catalog models redirected to local mock servers and cover provider/profile routing, native API selection, endpoint overrides, attribution, conversion, replay-state validation, and cross-provider/model replay within one adapter instance. Real-API coverage remains key-gated under `pnpm run test:e2e`. diff --git a/packages/llm/llm-pi-ai/src/adapter.ts b/packages/llm/llm-pi-ai/src/adapter.ts index 00107e8e1c..ae6cf21ec3 100644 --- a/packages/llm/llm-pi-ai/src/adapter.ts +++ b/packages/llm/llm-pi-ai/src/adapter.ts @@ -1,181 +1,98 @@ /** - * `PiAiAdapter`: the `@earendil-works/pi-ai`-backed implementation of the - * harness LLM seam, pointed at a DeepSeek (OpenAI-compatible) endpoint. - * - * This adapter exists as a design-verification twin of - * `@deepseek-ai/dsh-llm-deepseek`: same models, same wire protocol, - * completely different internals (a unified LLM library with its own event - * vocabulary vs hand-rolled fetch/SSE). Anything the StreamChunk protocol - * cannot express for BOTH implementations is a core-vocabulary bug. + * Generic pi-ai-backed implementation of the Harness LLM seam. * * @module dsh-llm-pi-ai/adapter */ -import { stream as piStream } from '@earendil-works/pi-ai' -import type { Model } from '@earendil-works/pi-ai' -import { attributionHeaders, LlmAdapter } from '@deepseek-ai/dsh-llm' -import { CallId } from '@deepseek-ai/dsh-llm' +import { + getModels, + streamSimple, +} from '@earendil-works/pi-ai' +import type { + Api, + KnownProvider, + Model, + SimpleStreamOptions, +} from '@earendil-works/pi-ai' +import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' -import { toPiContext, toStreamChunks } from './convert.ts' +import type { PiAiProviderProfile } from './config.ts' +import { toPiContext } from './context.ts' +import { toStreamChunks } from './stream.ts' -/** Reasoning levels surfaced by this adapter (DeepSeek wire: high|max). */ -export type PiAiReasoning = 'off' | 'high' | 'xhigh' - -/** Constructor options for {@link PiAiAdapter}; the plugin's `apply` resolves them from Config + environment. */ +/** Constructor options for {@link PiAiAdapter}. */ export interface PiAiAdapterOptions { - /** Bearer token pi-ai sends on every request. */ - apiKey: string - /** Endpoint base; `/chat/completions` is appended. */ - baseURL: string - /** Thinking level applied to every request ('off' disables thinking). */ - reasoning?: PiAiReasoning | undefined + /** Validated provider profiles this adapter instance owns. */ + profiles: readonly PiAiProviderProfile[] } /** - * Build the inline pi-ai model descriptor for one DeepSeek model name. - * @param modelId - harness model name; sent verbatim on the wire. - * @param options - adapter options; only `baseURL` is read here (key and reasoning apply per request, not per descriptor). - * @returns a descriptor with every DeepSeek compat flag explicit — pi-ai's URL-based auto-detection is never relied on. + * Resolve a catalog model dynamically and apply only the configured endpoint + * override, preserving the catalog's API/capability/compatibility metadata. */ -export function buildModel(modelId: string, options: PiAiAdapterOptions): Model<'openai-completions'> { +function resolveModel(profile: PiAiProviderProfile, modelId: string): Model { + const model = getModels(profile.provider as KnownProvider).find(candidate => candidate.id === modelId) as Model | undefined + if (model === undefined) { + throw new LlmError(`pi-ai provider "${profile.provider}" has no catalog model "${modelId}"`, 'UNKNOWN_MODEL') + } + return profile.baseURL === undefined ? model : { ...model, baseUrl: profile.baseURL } +} + +/** Copy profile stream knobs into pi-ai's common option vocabulary. */ +function profileOptions(profile: PiAiProviderProfile): SimpleStreamOptions { return { - id: modelId, - name: modelId, - api: 'openai-completions', - provider: 'deepseek', - baseUrl: options.baseURL, - // Always true: pi-ai only emits the DeepSeek `thinking` field for - // reasoning-capable models, deriving enabled/disabled from whether a - // reasoningEffort option is passed. DeepSeek's provider default is - // ENABLED, so 'off' must send an explicit {type: 'disabled'} — which - // requires this flag to stay on. - reasoning: true, - // DeepSeek's official effort levels: high|max (xhigh maps to max). - thinkingLevelMap: { minimal: null, low: null, medium: null, high: 'high', xhigh: 'max' }, - input: ['text'], - cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 }, - contextWindow: 128_000, - maxTokens: 64_000, - compat: { - // Auto-detection only fires for *.deepseek.com base URLs; the internal - // endpoint (and test mocks) need these set explicitly. - thinkingFormat: 'deepseek', - requiresReasoningContentOnAssistantMessages: true, - supportsReasoningEffort: true, - // DeepSeek documents max_tokens (not OpenAI's max_completion_tokens). - maxTokensField: 'max_tokens', - }, + ...profile.apiKey === undefined ? {} : { apiKey: profile.apiKey }, + ...profile.reasoning === undefined ? {} : { reasoning: profile.reasoning }, + ...profile.thinkingBudgets === undefined ? {} : { thinkingBudgets: profile.thinkingBudgets }, + ...profile.cacheRetention === undefined ? {} : { cacheRetention: profile.cacheRetention }, + ...profile.transport === undefined ? {} : { transport: profile.transport }, + ...profile.timeoutMs === undefined ? {} : { timeoutMs: profile.timeoutMs }, + ...profile.websocketConnectTimeoutMs === undefined ? {} : { websocketConnectTimeoutMs: profile.websocketConnectTimeoutMs }, + ...profile.maxRetries === undefined ? {} : { maxRetries: profile.maxRetries }, + ...profile.maxRetryDelayMs === undefined ? {} : { maxRetryDelayMs: profile.maxRetryDelayMs }, } } -type Payload = { - tools?: { function?: { strict?: unknown } }[] - messages?: { - role?: unknown - tool_calls?: { id?: unknown; function?: { arguments?: unknown } }[] - }[] - reasoning_effort?: unknown - stop?: unknown -} - -function rawToolArguments(options: GenerateOptions): Map { - const raw = new Map() - for (const message of options.messages) { - if (message.role !== 'assistant') continue - for (const block of message.content) { - if (block.type === 'tool-call') raw.set(block.id, block.arguments) - } - } - return raw -} - -function patchPayload(payload: unknown, options: GenerateOptions, reasoning: PiAiReasoning | undefined): unknown { - /* v8 ignore next -- pi-ai onPayload always receives an object; tolerate unusual future hooks defensively */ - if (typeof payload !== 'object' || payload === null) return payload - const body = payload as Payload - - if (reasoning === undefined) { - delete body.reasoning_effort - } - if (options.stop !== undefined) { - body.stop = options.stop - } - - // pi-ai stamps its own `strict` default on every serialized tool; the - // harness tool contract has no strict field and the hand-rolled twin sends - // none, so scrub it for wire parity. - for (const tool of body.tools ?? []) { - /* v8 ignore next -- malformed pi-ai payload guard: real tool entries always carry function */ - if (tool.function === undefined) continue - delete tool.function.strict - } - - const rawById = rawToolArguments(options) - /* v8 ignore next -- defensive for non-chat payloads; OpenAI chat payloads always carry messages */ - for (const message of body.messages ?? []) { - if (message.role !== 'assistant') continue - /* v8 ignore next -- assistant messages without tool_calls need no raw-argument patch */ - for (const call of message.tool_calls ?? []) { - /* v8 ignore next -- malformed pi-ai payload guard: real tool calls always carry a string id */ - if (typeof call.id !== 'string') continue - const raw = rawById.get(CallId(call.id)) - /* v8 ignore next -- pi-ai always emits a function object for assistant tool_calls; guard malformed payloads defensively */ - if (raw !== undefined && call.function !== undefined) call.function.arguments = raw - } - } - - return body -} - /** - * pi-ai-backed adapter. One instance serves every registered model name. - * - * Implementation notes: - * - `onPayload` patches provider payload details pi-ai cannot express directly: - * stop sequences, scrubbing pi-ai's own per-tool `strict` default (the - * hand-rolled twin sends no such field), omitted reasoning effort, and raw - * replayed tool-call arguments. - * - pi-ai reports request failures as in-stream error events; convert.ts - * maps them to `finish {kind:'error'|'aborted'}` chunks rather than - * throwing — both are sanctioned StreamChunk error paths. + * pi-ai-backed multi-provider adapter. Model descriptors are resolved for each + * request, so models need not be registered during the Cordis lifecycle. */ export class PiAiAdapter extends LlmAdapter { - constructor(private readonly options: PiAiAdapterOptions) { + private readonly profiles: ReadonlyMap + + constructor(options: PiAiAdapterOptions) { super() + this.profiles = new Map(options.profiles.map(profile => [profile.provider, profile])) } async * stream(options: GenerateOptions): AsyncIterable { - const model = buildModel(options.model, this.options) - // Undefined config means "provider default" (DeepSeek: thinking ENABLED), - // matching llm-deepseek's omission semantics. pi-ai derives the wire - // thinking toggle from whether reasoningEffort is passed, so undefined maps - // internally to 'high' to get `thinking: enabled`; patchPayload then removes - // `reasoning_effort` so the provider chooses its default effort. - const reasoning = this.options.reasoning ?? 'high' + if (options.stop !== undefined) { + throw new LlmError('llm-pi-ai does not support GenerateOptions.stop', 'UNSUPPORTED_OPTION') + } + const profile = this.profiles.get(options.provider) + if (profile === undefined) { + throw new LlmError(`pi-ai adapter does not own provider "${options.provider}"`, 'NO_ADAPTER') + } + const model = resolveModel(profile, options.model) - // pi-ai's event stream has no iterator-return cancellation hook: if our - // consumer stops early (break / loop abort), the underlying HTTP stream - // would keep draining. Chain an internal controller onto the caller's - // signal and abort it when this generator exits for any reason. + // pi-ai's event stream has no iterator-return cancellation hook: abort its + // provider stream when our consumer exits early as well as on caller abort. const controller = new AbortController() const onCallerAbort = (): void => { controller.abort(options.signal?.reason) } if (options.signal?.aborted) controller.abort(options.signal.reason) else options.signal?.addEventListener('abort', onCallerAbort, { once: true }) try { - const events = piStream(model, toPiContext(options), { - apiKey: this.options.apiKey, - // pi-ai merges caller headers last over its provider defaults, so the - // harness attribution always reaches the wire. - headers: attributionHeaders(), - ...options.temperature !== undefined ? { temperature: options.temperature } : {}, - ...options.maxTokens !== undefined ? { maxTokens: options.maxTokens } : {}, + const events = streamSimple(model, toPiContext(options), { + ...profileOptions(profile), + ...options.temperature === undefined ? {} : { temperature: options.temperature }, + ...options.maxTokens === undefined ? {} : { maxTokens: options.maxTokens }, + ...options.sessionId === undefined ? {} : { sessionId: String(options.sessionId) }, signal: controller.signal, - ...reasoning !== 'off' ? { reasoningEffort: reasoning } : {}, - onPayload: payload => patchPayload(payload, options, this.options.reasoning), - maxRetries: 0, + // Profile headers are deployment-owned; attribution names are + // Harness-owned and therefore win collisions. + headers: { ...profile.headers, ...attributionHeaders() }, }) - yield* toStreamChunks(events) } finally { options.signal?.removeEventListener('abort', onCallerAbort) diff --git a/packages/llm/llm-pi-ai/src/config.ts b/packages/llm/llm-pi-ai/src/config.ts new file mode 100644 index 0000000000..b41ca2dd61 --- /dev/null +++ b/packages/llm/llm-pi-ai/src/config.ts @@ -0,0 +1,99 @@ +/** + * Configuration schema and provider-profile validation for the pi-ai adapter. + * + * @module dsh-llm-pi-ai/config + */ + +import { getProviders } from '@earendil-works/pi-ai' +import type { CacheRetention, ThinkingBudgets, ThinkingLevel, Transport } from '@earendil-works/pi-ai' +import z from 'schemastery' + +/** Configuration for one pi-ai provider route. */ +export interface PiAiProviderProfile { + /** pi-ai provider catalog name and Harness route key. */ + provider: string + /** Provider credential; when absent pi-ai uses its provider-native ambient discovery. */ + apiKey?: string + /** Override the selected catalog model's endpoint without changing its protocol metadata. */ + baseURL?: string + /** Provider request headers; Harness attribution wins reserved names. */ + headers?: Record + /** Provider-neutral pi-ai reasoning level. */ + reasoning?: ThinkingLevel + /** Token budgets used by reasoning providers that support them. */ + thinkingBudgets?: ThinkingBudgets + /** Prompt-cache retention preference. */ + cacheRetention?: CacheRetention + /** Streaming transport preference. */ + transport?: Transport + /** HTTP/provider SDK timeout in milliseconds. */ + timeoutMs?: number + /** WebSocket connection timeout in milliseconds. */ + websocketConnectTimeoutMs?: number + /** Provider SDK retry count. */ + maxRetries?: number + /** Maximum provider-requested retry delay in milliseconds. */ + maxRetryDelayMs?: number +} + +/** Plugin configuration: the non-empty provider profiles this instance owns. */ +export interface Config { + /** Non-empty set of pi-ai provider routes this adapter instance owns. */ + providers: PiAiProviderProfile[] +} + +const thinkingBudgets = z.object({ + minimal: z.number(), + low: z.number(), + medium: z.number(), + high: z.number(), +}) + +const profile = z.object({ + provider: z.string().required(), + apiKey: z.string(), + baseURL: z.string(), + headers: z.dict(z.string()), + reasoning: z.union(['minimal', 'low', 'medium', 'high', 'xhigh']), + thinkingBudgets, + cacheRetention: z.union(['none', 'short', 'long']), + transport: z.union(['sse', 'websocket', 'websocket-cached', 'auto']), + timeoutMs: z.number(), + websocketConnectTimeoutMs: z.number(), + maxRetries: z.number(), + maxRetryDelayMs: z.number(), +}) + +/** Runtime schema for {@link Config}. */ +export const Config: z = z.object({ + providers: z.array(profile).required(), +}) + +/** + * Validate profiles against the installed pi-ai catalog and return a detached + * shallow copy suitable for adapter construction. + * @param profiles - configured provider profiles. + * @returns validated profiles in configuration order. + */ +export function resolveProfiles(profiles: readonly PiAiProviderProfile[]): PiAiProviderProfile[] { + if (profiles.length === 0) throw new Error('llm-pi-ai: providers must contain at least one profile') + const supported = new Set(getProviders()) + const seen = new Set() + return profiles.map((source) => { + if (source.provider.length === 0) throw new Error('llm-pi-ai: provider names must be non-empty') + if (!supported.has(source.provider)) throw new Error(`llm-pi-ai: unknown pi-ai provider "${source.provider}"`) + if (seen.has(source.provider)) throw new Error(`llm-pi-ai: duplicate provider profile "${source.provider}"`) + if (source.apiKey !== undefined && source.apiKey.length === 0) { + throw new Error(`llm-pi-ai: provider "${source.provider}" has an empty apiKey; omit it to use ambient authentication`) + } + if (source.baseURL !== undefined && source.baseURL.length === 0) { + throw new Error(`llm-pi-ai: provider "${source.provider}" has an empty baseURL`) + } + seen.add(source.provider) + return { + ...source, + ...source.headers === undefined ? {} : { headers: { ...source.headers } }, + ...source.thinkingBudgets === undefined ? {} : { thinkingBudgets: { ...source.thinkingBudgets } }, + } + }) +} diff --git a/packages/llm/llm-pi-ai/src/context.ts b/packages/llm/llm-pi-ai/src/context.ts new file mode 100644 index 0000000000..ddb8284448 --- /dev/null +++ b/packages/llm/llm-pi-ai/src/context.ts @@ -0,0 +1,85 @@ +/** + * Harness request-history conversion into pi-ai's Context vocabulary. + * + * @module dsh-llm-pi-ai/context + */ + +import { CallId } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, Message } from '@deepseek-ai/dsh-llm' +import type { Context as PiContext, Message as PiMessage, Tool as PiTool } from '@earendil-works/pi-ai' +import { toPiAssistant } from './replay.ts' + +/** Join the text blocks of a harness message. */ +function flattenText(message: Message): string { + return message.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('') +} + +/** + * Convert harness history to a pi-ai Context. Tool results need the tool + * NAME (pi-ai's `toolName`), which the harness doesn't carry on the result + * block — it is recovered from the preceding assistant tool-call with the + * same id. + * @param options - the harness request; `options.system` maps to pi-ai's single `systemPrompt` slot. + * @returns the pi-ai context; `tools` is omitted entirely when the request declares none. + */ +export function toPiContext(options: GenerateOptions): PiContext { + const toolNames = new Map() + const messages: PiMessage[] = [] + + for (const message of options.messages) { + if (message.role === 'system') { + // pi-ai has a single systemPrompt slot; in-history system messages are + // folded into user messages to preserve order (rare in practice — the + // harness sends the system prompt via options.system). + messages.push({ role: 'user', content: flattenText(message), timestamp: 0 }) + continue + } + if (message.role === 'assistant') { + const assistant = toPiAssistant(message) + for (const block of assistant.content) { + if (block.type === 'toolCall') toolNames.set(CallId(block.id), block.name) + } + messages.push(assistant) + continue + } + // user role: text + tool results (each result becomes its own message). + const text = flattenText(message) + const results = message.content.filter(block => block.type === 'tool-result') + if (text.length > 0 || results.length === 0) { + messages.push({ role: 'user', content: text, timestamp: 0 }) + } + for (const result of results) { + messages.push({ + role: 'toolResult', + toolCallId: result.toolCallId, + toolName: toolNames.get(result.toolCallId) ?? 'unknown', + content: [{ + type: 'text', + text: result.content + .filter(block => block.type === 'text') + .map(block => block.text) + .join('') || '(no output)', + }], + isError: result.isError ?? false, + timestamp: 0, + }) + } + } + + const tools: PiTool[] | undefined = options.tools?.map(tool => ({ + name: tool.name, + description: tool.description, + // ToolSchema.parameters is a JSON Schema object; pi-ai's TSchema + // (TypeBox) is structurally JSON Schema, so it assigns directly. + parameters: tool.parameters, + })) + + return { + ...options.system !== undefined ? { systemPrompt: options.system } : {}, + messages, + ...tools !== undefined && tools.length > 0 ? { tools } : {}, + } +} diff --git a/packages/llm/llm-pi-ai/src/convert.ts b/packages/llm/llm-pi-ai/src/convert.ts deleted file mode 100644 index 9652cb7d56..0000000000 --- a/packages/llm/llm-pi-ai/src/convert.ts +++ /dev/null @@ -1,289 +0,0 @@ -/** - * Bidirectional mapping between the harness vocabulary and pi-ai's: - * `GenerateOptions`/`Message[]` → pi-ai `Context`, and pi-ai - * `AssistantMessageEvent`s → harness `StreamChunk`s. - * - * Vocabulary differences worth knowing (they are exactly why this adapter - * exists — an independent implementation stress-tests the StreamChunk - * protocol): - * - pi-ai tool-call `arguments` are PARSED OBJECTS; the harness keeps the - * raw JSON string. We parse on the way into pi-ai, patch provider payloads - * back to the original raw string in the adapter, and re-stringify on output. - * - pi-ai reports errors as in-stream `error` events (it never throws - * mid-stream); the harness expresses those as `finish {kind:'error'}` / - * `{kind:'aborted'}` chunks. - * - pi-ai folds reasoning tokens into `usage.output`; there is no separate - * reasoning count to map. - * - * @module dsh-llm-pi-ai/convert - */ - -import { CallId, LlmError } from '@deepseek-ai/dsh-llm' -import type { FinishReason, GenerateOptions, Message, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm' -import type { - AssistantMessage, - AssistantMessageEvent, - Context as PiContext, - Message as PiMessage, - Tool as PiTool, - Usage as PiUsage, -} from '@earendil-works/pi-ai' - -/** Join the text blocks of a harness message. */ -function flattenText(message: Message): string { - return message.content - .filter(block => block.type === 'text') - .map(block => block.text) - .join('') -} - -/** Parse tool-call argument JSON; tolerate model malformations with {}. */ -function parseArguments(raw: string): Record { - try { - const parsed: unknown = JSON.parse(raw) - if (typeof parsed === 'object' && parsed !== null && !Array.isArray(parsed)) { - return parsed as Record - } - } catch { - // fall through - } - return {} -} - -/** - * Convert harness history to a pi-ai Context. Tool results need the tool - * NAME (pi-ai's `toolName`), which the harness doesn't carry on the result - * block — it is recovered from the preceding assistant tool-call with the - * same id. - * @param options - the harness request; `options.system` maps to pi-ai's single `systemPrompt` slot. - * @returns the pi-ai context; `tools` is omitted entirely when the request declares none. - */ -export function toPiContext(options: GenerateOptions): PiContext { - const toolNames = new Map() - const messages: PiMessage[] = [] - - for (const message of options.messages) { - if (message.role === 'system') { - // pi-ai has a single systemPrompt slot; in-history system messages are - // folded into user messages to preserve order (rare in practice — the - // harness sends the system prompt via options.system). - messages.push({ role: 'user', content: flattenText(message), timestamp: 0 }) - continue - } - if (message.role === 'assistant') { - const content: AssistantMessage['content'] = [] - for (const block of message.content) { - switch (block.type) { - case 'text': - content.push({ type: 'text', text: block.text }) - break - case 'reasoning': - // thinkingSignature names the wire field pi-ai replays the CoT - // under. Without it pi-ai falls back to reasoning_content: "" - // (its requiresReasoningContentOnAssistantMessages shim), which - // violates DeepSeek's thinking-mode passback rule on tool-call - // turns (guides/thinking_mode.mdx § Tool Calls). - content.push({ type: 'thinking', thinking: block.text, thinkingSignature: 'reasoning_content' }) - break - case 'tool-call': - toolNames.set(block.id, block.name) - content.push({ - type: 'toolCall', - id: block.id, - name: block.name, - arguments: parseArguments(block.arguments), - }) - break - default: - // plugin-added block types: not representable here. - break - } - } - messages.push({ - role: 'assistant', - content, - api: 'openai-completions', - provider: 'deepseek', - model: options.model, - usage: emptyPiUsage(), - stopReason: content.some(piece => piece.type === 'toolCall') ? 'toolUse' : 'stop', - timestamp: 0, - }) - continue - } - // user role: text + tool results (each result becomes its own message). - const text = flattenText(message) - const results = message.content.filter(block => block.type === 'tool-result') - if (text.length > 0 || results.length === 0) { - messages.push({ role: 'user', content: text, timestamp: 0 }) - } - for (const result of results) { - messages.push({ - role: 'toolResult', - toolCallId: result.toolCallId, - toolName: toolNames.get(result.toolCallId) ?? 'unknown', - content: [{ - type: 'text', - text: result.content - .filter(block => block.type === 'text') - .map(block => block.text) - .join('') || '(no output)', - }], - isError: result.isError ?? false, - timestamp: 0, - }) - } - } - - const tools: PiTool[] | undefined = options.tools?.map(tool => ({ - name: tool.name, - description: tool.description, - // ToolSchema.parameters is a JSON Schema object; pi-ai's TSchema - // (TypeBox) is structurally JSON Schema, so it assigns directly. - parameters: tool.parameters, - })) - - return { - ...options.system !== undefined ? { systemPrompt: options.system } : {}, - messages, - ...tools !== undefined && tools.length > 0 ? { tools } : {}, - } -} - -function emptyPiUsage(): PiUsage { - return { - input: 0, - output: 0, - cacheRead: 0, - cacheWrite: 0, - totalTokens: 0, - cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 }, - } -} - -/** - * Map pi-ai usage (reasoning folded into output by pi-ai). - * @param usage - cumulative usage from the terminal pi-ai event. - * @returns harness counts; cache fields appear only when non-zero (pi-ai reports zeros, not absence). - */ -export function mapUsage(usage: PiUsage): TokenUsage { - return { - inputTokens: usage.input, - outputTokens: usage.output, - ...usage.cacheRead > 0 ? { cacheReadTokens: usage.cacheRead } : {}, - ...usage.cacheWrite > 0 ? { cacheWriteTokens: usage.cacheWrite } : {}, - } -} - -function classifyPiAiError(message: string): string { - if (/\b(?:401|403)\b/.test(message)) return 'AUTH' - if (/\b429\b|rate.?limit/i.test(message)) return 'RATE_LIMIT' - if (/\b400\b|invalid.?request/i.test(message)) return 'INVALID_REQUEST' - if (/\b5\d\d\b/.test(message)) return 'SERVER' - return 'PI_AI_ERROR' -} - -/** - * Map a terminal pi-ai event to the harness finish reason. - * @param message - the assistant message carried by the `done` or `error` event. - * @returns the harness reason; `error` yields `{kind: 'error'}` with a code classified from the error text. - */ -export function mapStopReason(message: AssistantMessage): FinishReason { - switch (message.stopReason) { - case 'stop': return { kind: 'stop' } - case 'length': return { kind: 'max-tokens' } - case 'toolUse': return { kind: 'tool-calls' } - case 'aborted': return { kind: 'aborted' } - case 'error': { - const text = message.errorMessage ?? 'pi-ai stream error' - return { kind: 'error', message: text, code: classifyPiAiError(text) } - } - } -} - -/** - * Translate the pi-ai event stream into StreamChunks. pi-ai never throws - * mid-stream — failures arrive as `error` events, which become error/aborted - * `finish` chunks (the harness protocol's other error-delivery style). - * @param events - one assistant turn's pi-ai event stream. - * @returns the harness chunks, ending with `usage` then `finish`; throws - * `LlmError` (`STREAM_CLOSED`) if the source ends without a terminal event. - */ -export async function* toStreamChunks(events: AsyncIterable): AsyncGenerator { - // pi-ai contentIndex ↔ our block index map 1:1 (both count blocks from 0 - // in stream order), but we track ids per index for tool calls. - const toolIds = new Map() - - for await (const event of events) { - switch (event.type) { - case 'start': - break - case 'text_start': - yield { type: 'block-start', index: event.contentIndex, blockType: 'text' } - break - case 'text_delta': - yield { type: 'text-delta', index: event.contentIndex, text: event.delta } - break - case 'text_end': - yield { type: 'block-end', index: event.contentIndex, block: { type: 'text', text: event.content } } - break - case 'thinking_start': - yield { type: 'block-start', index: event.contentIndex, blockType: 'reasoning' } - break - case 'thinking_delta': - yield { type: 'reasoning-delta', index: event.contentIndex, text: event.delta } - break - case 'thinking_end': - yield { type: 'block-end', index: event.contentIndex, block: { type: 'reasoning', text: event.content } } - break - case 'toolcall_start': { - // The id/name live on the partial's content at this index. - const partial = event.partial.content[event.contentIndex] - const id = partial?.type === 'toolCall' ? partial.id : '' - const name = partial?.type === 'toolCall' ? partial.name : '' - toolIds.set(event.contentIndex, { id, name }) - yield { type: 'block-start', index: event.contentIndex, blockType: 'tool-call' } - break - } - case 'toolcall_delta': { - const known = toolIds.get(event.contentIndex) - yield { - type: 'tool-call-delta', - index: event.contentIndex, - id: CallId(known?.id ?? ''), - ...known?.name !== undefined && known.name.length > 0 ? { name: known.name } : {}, - argumentsDelta: event.delta, - } - break - } - case 'toolcall_end': - yield { - type: 'block-end', - index: event.contentIndex, - block: { - type: 'tool-call', - id: CallId(event.toolCall.id), - name: event.toolCall.name, - // pi-ai hands back the PARSED arguments; the harness vocabulary - // keeps the raw string. - arguments: JSON.stringify(event.toolCall.arguments), - }, - } - break - case 'done': - yield { type: 'usage', usage: mapUsage(event.message.usage) } - yield { type: 'finish', reason: mapStopReason(event.message) } - return - case 'error': - // In-stream error delivery (pi-ai's style) → error finish chunk - // (the harness's other sanctioned error path besides throwing). - yield { type: 'usage', usage: mapUsage(event.error.usage) } - yield { type: 'finish', reason: mapStopReason(event.error) } - return - // no default: AssistantMessageEvent is pi-ai's closed union; a new - // event type should fail compilation here via tsc's exhaustiveness - // when one is added (switch covers all current variants). - } - } - throw new LlmError('pi-ai event stream ended without done/error', 'STREAM_CLOSED') -} diff --git a/packages/llm/llm-pi-ai/src/index.ts b/packages/llm/llm-pi-ai/src/index.ts index 43468ba507..cbd0dcd435 100644 --- a/packages/llm/llm-pi-ai/src/index.ts +++ b/packages/llm/llm-pi-ai/src/index.ts @@ -1,76 +1,45 @@ /** - * pi-ai-backed DeepSeek adapter plugin. Same Config shape as - * `@deepseek-ai/dsh-llm-deepseek` (one-line swap in cordis.yml), different - * implementation underneath — see `./adapter.ts` for why both exist. + * Generic pi-ai-backed LLM adapter plugin. One plugin instance registers an + * explicit set of provider profiles; requests select a profile by provider and + * resolve the model dynamically from pi-ai's installed catalog. * * ```yaml * - id: llm * name: '@deepseek-ai/dsh-llm-pi-ai' * config: - * apiKey: !!js process.env.DEEPSEEK_API_KEY - * baseURL: !!js process.env.DEEPSEEK_BASE_URL - * models: [deepseek-v4-flash, deepseek-v4-pro] - * reasoning: high + * providers: + * - provider: openai + * apiKey: !!js process.env.OPENAI_API_KEY + * - provider: anthropic + * apiKey: !!js process.env.ANTHROPIC_API_KEY + * - provider: openrouter + * apiKey: !!js process.env.OPENROUTER_API_KEY + * baseURL: https://proxy.example.com/v1 * ``` * * @module @deepseek-ai/dsh-llm-pi-ai */ import type { Context } from 'cordis' -import z from 'schemastery' import type {} from '@deepseek-ai/dsh-llm' import { PiAiAdapter } from './adapter.ts' -import type { PiAiReasoning } from './adapter.ts' +import { Config, resolveProfiles } from './config.ts' -export { buildModel, PiAiAdapter } from './adapter.ts' -export type { PiAiAdapterOptions, PiAiReasoning } from './adapter.ts' -export { mapStopReason, mapUsage, toPiContext, toStreamChunks } from './convert.ts' +export { PiAiAdapter } from './adapter.ts' +export type { PiAiAdapterOptions } from './adapter.ts' +export { Config, resolveProfiles } from './config.ts' +export type { PiAiProviderProfile } from './config.ts' +export { toPiContext } from './context.ts' +export { toPiReplayState } from './replay.ts' +export type { PiAiReplayState } from './replay.ts' +export { mapStopReason, mapUsage, toStreamChunks } from './stream.ts' export const name = 'llm-pi-ai' export const inject = ['llm'] -/** - * Plugin config, validated by the same-named schemastery schema. Every field - * is optional in yml: credentials/endpoint fall back to the environment (a - * missing API key fails plugin load, not the first call). - */ -export interface Config { - /** API key; falls back to $DEEPSEEK_API_KEY. Required one way or the other. */ - apiKey?: string - /** Endpoint base; falls back to $DEEPSEEK_BASE_URL, then the public API. */ - baseURL?: string - /** Model names to register (sent verbatim on the wire). */ - models?: string[] - /** - * Thinking level for every request: 'off' disables thinking mode; 'high' - * and 'xhigh' (wire 'max') set the effort. Omitted = provider default - * (thinking enabled), matching llm-deepseek's omission semantics. - */ - reasoning?: PiAiReasoning -} - -export const Config: z = z.object({ - apiKey: z.string(), - baseURL: z.string(), - models: z.array(z.string()).default(['deepseek-v4-flash', 'deepseek-v4-pro']), - reasoning: z.union(['off', 'high', 'xhigh']), -}) - -/** Public API default; the internal endpoint comes from $DEEPSEEK_BASE_URL. */ -export const PUBLIC_BASE_URL = 'https://api.deepseek.com' - +/** Register one generic pi-ai adapter for all configured provider routes. */ export function apply(ctx: Context, config: Config): void { - const apiKey = config.apiKey ?? process.env.DEEPSEEK_API_KEY - if (apiKey === undefined || apiKey.length === 0) { - throw new Error('llm-pi-ai: an API key is required (Config.apiKey or $DEEPSEEK_API_KEY)') - } - const baseURL = config.baseURL ?? process.env.DEEPSEEK_BASE_URL ?? PUBLIC_BASE_URL - // schemastery's .default() guarantees models is set after validation. - const models = config.models as string[] - - ctx.llm.registerAdapter(models, new PiAiAdapter({ - apiKey, - baseURL, - reasoning: config.reasoning, - })) + const profiles = resolveProfiles(config.providers) + const adapter = new PiAiAdapter({ profiles }) + ctx.llm.registerAdapter(profiles.map(entry => entry.provider), adapter) } diff --git a/packages/llm/llm-pi-ai/src/replay.ts b/packages/llm/llm-pi-ai/src/replay.ts new file mode 100644 index 0000000000..665b236bfe --- /dev/null +++ b/packages/llm/llm-pi-ai/src/replay.ts @@ -0,0 +1,208 @@ +/** + * Durable pi-ai replay metadata and assistant-history reconstruction. + * + * Harness content remains the durable source for text and tool calls. This + * module stores only the provider-native metadata needed to reconstruct a + * pi-ai assistant message on a later request. + * + * @module dsh-llm-pi-ai/replay + */ + +import { LlmError } from '@deepseek-ai/dsh-llm' +import type { Message } from '@deepseek-ai/dsh-llm' +import type { Api, AssistantMessage, Usage as PiUsage } from '@earendil-works/pi-ai' + +type PiAiReplayBlock = + | { type: 'text'; textSignature?: string } + | { type: 'reasoning'; thinkingSignature?: string; redacted?: boolean } + | { type: 'tool-call'; thoughtSignature?: string } + +/** Versioned adapter-private projection required to replay a pi-ai response. */ +export interface PiAiReplayState { + kind: 'pi-ai' + version: 1 + api: Api + provider: string + model: string + responseModel?: string + responseId?: string + stopReason: AssistantMessage['stopReason'] + blocks: PiAiReplayBlock[] +} + +/** Parse tool-call argument JSON; tolerate model malformations with {}. */ +function parseArguments(raw: string): Record { + try { + const parsed: unknown = JSON.parse(raw) + if (typeof parsed === 'object' && parsed !== null && !Array.isArray(parsed)) { + return parsed as Record + } + } catch { + // fall through + } + return {} +} + +/** Construct the zero usage value required by historical pi-ai messages. */ +function emptyPiUsage(): PiUsage { + return { + input: 0, + output: 0, + cacheRead: 0, + cacheWrite: 0, + totalTokens: 0, + cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0, total: 0 }, + } +} + +/** + * Project a successful pi-ai response into the minimal durable replay state. + * @param message - completed native pi-ai assistant response. + * @returns the versioned lossless-JSON replay projection. + */ +export function toPiReplayState(message: AssistantMessage): PiAiReplayState { + return { + kind: 'pi-ai', + version: 1, + api: message.api, + provider: message.provider, + model: message.model, + ...message.responseModel === undefined ? {} : { responseModel: message.responseModel }, + ...message.responseId === undefined ? {} : { responseId: message.responseId }, + stopReason: message.stopReason, + blocks: message.content.map((block): PiAiReplayBlock => { + switch (block.type) { + case 'text': return { + type: 'text', + ...block.textSignature === undefined ? {} : { textSignature: block.textSignature }, + } + case 'thinking': return { + type: 'reasoning', + ...block.thinkingSignature === undefined ? {} : { thinkingSignature: block.thinkingSignature }, + ...block.redacted === undefined ? {} : { redacted: block.redacted }, + } + case 'toolCall': return { + type: 'tool-call', + ...block.thoughtSignature === undefined ? {} : { thoughtSignature: block.thoughtSignature }, + } + } + }), + } +} + +function invalidReplay(message: string): never { + throw new LlmError(`invalid pi-ai replay state: ${message}`, 'INVALID_REPLAY_STATE') +} + +/** Validate the adapter-private state before it reaches pi-ai. */ +function readReplayState(value: unknown): PiAiReplayState { + if (typeof value !== 'object' || value === null || Array.isArray(value)) return invalidReplay('expected an object') + const state = value as Record + if (state['kind'] !== 'pi-ai') return invalidReplay('unknown state kind') + if (state['version'] !== 1) return invalidReplay(`unsupported version ${String(state['version'])}`) + for (const key of ['api', 'provider', 'model'] as const) { + if (typeof state[key] !== 'string' || state[key].length === 0) return invalidReplay(`${key} must be a non-empty string`) + } + if (!['stop', 'length', 'toolUse', 'error', 'aborted'].includes(String(state['stopReason']))) { + return invalidReplay('unknown stopReason') + } + if (state['responseModel'] !== undefined && typeof state['responseModel'] !== 'string') return invalidReplay('responseModel must be a string') + if (state['responseId'] !== undefined && typeof state['responseId'] !== 'string') return invalidReplay('responseId must be a string') + if (!Array.isArray(state['blocks'])) return invalidReplay('blocks must be an array') + for (const [index, value] of state['blocks'].entries()) { + if (typeof value !== 'object' || value === null || Array.isArray(value)) return invalidReplay(`block ${index} must be an object`) + const block = value as Record + if (!['text', 'reasoning', 'tool-call'].includes(String(block['type']))) return invalidReplay(`block ${index} has an unknown type`) + for (const signature of ['textSignature', 'thinkingSignature', 'thoughtSignature'] as const) { + if (block[signature] !== undefined && typeof block[signature] !== 'string') return invalidReplay(`block ${index} ${signature} must be a string`) + } + if (block['redacted'] !== undefined && typeof block['redacted'] !== 'boolean') return invalidReplay(`block ${index} redacted must be boolean`) + } + return state as unknown as PiAiReplayState +} + +/** Convert provider-neutral blocks without trusting them as same-model replay. */ +function foreignAssistant(message: Message): AssistantMessage { + const content: AssistantMessage['content'] = [] + for (const block of message.content) { + switch (block.type) { + case 'text': content.push({ type: 'text', text: block.text }); break + case 'reasoning': content.push({ type: 'thinking', thinking: block.text }); break + case 'tool-call': content.push({ + type: 'toolCall', + id: block.id, + name: block.name, + arguments: parseArguments(block.arguments), + }); break + default: + // plugin-added block types are not representable in pi-ai. + break + } + } + return { + role: 'assistant', + content, + // Deliberately never equals a catalog API: absent replay state is foreign + // even if provenance names the same provider/model as this request. + api: 'dsh-foreign', + provider: message.provenance?.provider ?? 'dsh-foreign', + model: message.provenance?.model ?? 'dsh-foreign', + usage: emptyPiUsage(), + stopReason: content.some(piece => piece.type === 'toolCall') ? 'toolUse' : 'stop', + timestamp: 0, + } +} + +/** Recombine durable Harness content with validated pi-ai replay metadata. */ +function replayedAssistant(message: Message, rawState: unknown): AssistantMessage { + const state = readReplayState(rawState) + if (state.blocks.length !== message.content.length) return invalidReplay('block count does not match assistant content') + const content: AssistantMessage['content'] = message.content.map((block, index) => { + const replay = state.blocks[index] + if (replay === undefined || replay.type !== block.type) return invalidReplay(`block ${index} does not match assistant content`) + switch (block.type) { + case 'text': return { + type: 'text', + text: block.text, + ...replay.type === 'text' && replay.textSignature !== undefined ? { textSignature: replay.textSignature } : {}, + } + case 'reasoning': return { + type: 'thinking', + thinking: block.text, + ...replay.type === 'reasoning' && replay.thinkingSignature !== undefined ? { thinkingSignature: replay.thinkingSignature } : {}, + ...replay.type === 'reasoning' && replay.redacted !== undefined ? { redacted: replay.redacted } : {}, + } + case 'tool-call': return { + type: 'toolCall', + id: block.id, + name: block.name, + arguments: parseArguments(block.arguments), + ...replay.type === 'tool-call' && replay.thoughtSignature !== undefined ? { thoughtSignature: replay.thoughtSignature } : {}, + } + /* v8 ignore next -- readReplayState rejects unknown replay tags, so an equal plugin-added Harness tag cannot reach this switch */ + default: return invalidReplay(`block ${index} has an unsupported Harness type`) + } + }) + return { + role: 'assistant', + content, + api: state.api, + provider: state.provider, + model: state.model, + ...state.responseModel === undefined ? {} : { responseModel: state.responseModel }, + ...state.responseId === undefined ? {} : { responseId: state.responseId }, + usage: emptyPiUsage(), + stopReason: state.stopReason, + timestamp: 0, + } +} + +/** + * Convert one durable Harness assistant message into pi-ai history. + * @param message - assistant content with optional adapter-owned replay metadata. + * @returns a native pi-ai assistant message reconstructed from durable content. + */ +export function toPiAssistant(message: Message): AssistantMessage { + const replayState = message.provenance?.replayState + return replayState === undefined ? foreignAssistant(message) : replayedAssistant(message, replayState) +} diff --git a/packages/llm/llm-pi-ai/src/stream.ts b/packages/llm/llm-pi-ai/src/stream.ts new file mode 100644 index 0000000000..5bdce3c528 --- /dev/null +++ b/packages/llm/llm-pi-ai/src/stream.ts @@ -0,0 +1,141 @@ +/** + * pi-ai assistant event translation into the Harness streaming protocol. + * + * pi-ai tool-call arguments are parsed objects while the Harness keeps their + * raw JSON representation. pi-ai also reports failures as terminal stream + * events, which this module maps into Harness finish chunks. + * + * @module dsh-llm-pi-ai/stream + */ + +import { CallId, LlmError } from '@deepseek-ai/dsh-llm' +import type { FinishReason, StreamChunk, TokenUsage } from '@deepseek-ai/dsh-llm' +import type { AssistantMessage, AssistantMessageEvent, Usage as PiUsage } from '@earendil-works/pi-ai' +import { toPiReplayState } from './replay.ts' + +/** + * Map pi-ai usage (reasoning folded into output by pi-ai). + * @param usage - cumulative usage from the terminal pi-ai event. + * @returns harness counts; cache fields appear only when non-zero (pi-ai reports zeros, not absence). + */ +export function mapUsage(usage: PiUsage): TokenUsage { + return { + inputTokens: usage.input, + outputTokens: usage.output, + ...usage.cacheRead > 0 ? { cacheReadTokens: usage.cacheRead } : {}, + ...usage.cacheWrite > 0 ? { cacheWriteTokens: usage.cacheWrite } : {}, + } +} + +function classifyPiAiError(message: string): string { + if (/\b(?:401|403)\b/.test(message)) return 'AUTH' + if (/\b429\b|rate.?limit/i.test(message)) return 'RATE_LIMIT' + if (/\b400\b|invalid.?request/i.test(message)) return 'INVALID_REQUEST' + if (/\b5\d\d\b/.test(message)) return 'SERVER' + return 'PI_AI_ERROR' +} + +/** + * Map a terminal pi-ai event to the harness finish reason. + * @param message - the assistant message carried by the `done` or `error` event. + * @returns the harness reason; `error` yields `{kind: 'error'}` with a code classified from the error text. + */ +export function mapStopReason(message: AssistantMessage): FinishReason { + switch (message.stopReason) { + case 'stop': return { kind: 'stop' } + case 'length': return { kind: 'max-tokens' } + case 'toolUse': return { kind: 'tool-calls' } + case 'aborted': return { kind: 'aborted' } + case 'error': { + const text = message.errorMessage ?? 'pi-ai stream error' + return { kind: 'error', message: text, code: classifyPiAiError(text) } + } + } +} + +/** + * Translate the pi-ai event stream into StreamChunks. pi-ai never throws + * mid-stream — failures arrive as `error` events, which become error/aborted + * `finish` chunks (the harness protocol's other error-delivery style). + * @param events - one assistant turn's pi-ai event stream. + * @returns the harness chunks, ending with `usage` then `finish`; throws + * `LlmError` (`STREAM_CLOSED`) if the source ends without a terminal event. + */ +export async function* toStreamChunks(events: AsyncIterable): AsyncGenerator { + // pi-ai contentIndex ↔ our block index map 1:1 (both count blocks from 0 + // in stream order), but we track ids per index for tool calls. + const toolIds = new Map() + + for await (const event of events) { + switch (event.type) { + case 'start': + break + case 'text_start': + yield { type: 'block-start', index: event.contentIndex, blockType: 'text' } + break + case 'text_delta': + yield { type: 'text-delta', index: event.contentIndex, text: event.delta } + break + case 'text_end': + yield { type: 'block-end', index: event.contentIndex, block: { type: 'text', text: event.content } } + break + case 'thinking_start': + yield { type: 'block-start', index: event.contentIndex, blockType: 'reasoning' } + break + case 'thinking_delta': + yield { type: 'reasoning-delta', index: event.contentIndex, text: event.delta } + break + case 'thinking_end': + yield { type: 'block-end', index: event.contentIndex, block: { type: 'reasoning', text: event.content } } + break + case 'toolcall_start': { + // The id/name live on the partial's content at this index. + const partial = event.partial.content[event.contentIndex] + const id = partial?.type === 'toolCall' ? partial.id : '' + const name = partial?.type === 'toolCall' ? partial.name : '' + toolIds.set(event.contentIndex, { id, name }) + yield { type: 'block-start', index: event.contentIndex, blockType: 'tool-call' } + break + } + case 'toolcall_delta': { + const known = toolIds.get(event.contentIndex) + yield { + type: 'tool-call-delta', + index: event.contentIndex, + id: CallId(known?.id ?? ''), + ...known?.name !== undefined && known.name.length > 0 ? { name: known.name } : {}, + argumentsDelta: event.delta, + } + break + } + case 'toolcall_end': + yield { + type: 'block-end', + index: event.contentIndex, + block: { + type: 'tool-call', + id: CallId(event.toolCall.id), + name: event.toolCall.name, + // pi-ai hands back the PARSED arguments; the harness vocabulary + // keeps the raw string. + arguments: JSON.stringify(event.toolCall.arguments), + }, + } + break + case 'done': + yield { type: 'usage', usage: mapUsage(event.message.usage) } + yield { type: 'finish', reason: mapStopReason(event.message), replayState: toPiReplayState(event.message) } + return + case 'error': + // In-stream error delivery (pi-ai's style) → error finish chunk + // (the harness's other sanctioned error path besides throwing). + yield { type: 'usage', usage: mapUsage(event.error.usage) } + yield { type: 'finish', reason: mapStopReason(event.error) } + return + // no default: AssistantMessageEvent is pi-ai's closed union; a new + // event type should fail compilation here via tsc's exhaustiveness + // when one is added (switch covers all current variants). + } + } + throw new LlmError('pi-ai event stream ended without done/error', 'STREAM_CLOSED') +} diff --git a/packages/llm/llm-pi-ai/tests/adapter.e2e.ts b/packages/llm/llm-pi-ai/tests/adapter.e2e.ts index fa30226ddf..77d2cc81dd 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.e2e.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.e2e.ts @@ -3,26 +3,33 @@ import { Context } from 'cordis' import LlmService, { CallId } from '@deepseek-ai/dsh-llm' import type { Message, ToolSchema } from '@deepseek-ai/dsh-llm' import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai' -import type { Config } from '@deepseek-ai/dsh-llm-pi-ai' +import type { PiAiProviderProfile } from '@deepseek-ai/dsh-llm-pi-ai' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import { assemble, type AssembledResult } from './assemble.ts' /** - * Real-API e2e for the pi-ai-backed adapter: V4 Flash + V4 Pro across all - * reasoning levels the adapter exposes (off / high / xhigh→wire 'max'). - * Mirrors the llm-deepseek matrix so the two independent implementations - * verify the same StreamChunk contract. Key-gated. + * Real-API e2e for the pi-ai-backed adapter: V4 Flash + V4 Pro with provider + * defaults and representative high/xhigh reasoning. Mirrors the native + * adapter's StreamChunk contract and exercises a replayed tool follow-up. + * Key-gated. */ const FLASH = 'deepseek-v4-flash' const PRO = 'deepseek-v4-pro' const contexts: Context[] = [] -async function harness(model: string, config: Partial = {}) { +async function harness(_model: string, config: Partial = {}) { const ctx = new Context() contexts.push(ctx) await ctx.plugin(LlmService) - await ctx.plugin(LlmPiAi, { models: [model], ...config }) + await ctx.plugin(LlmPiAi, { + providers: [{ + provider: 'deepseek', + ...process.env.DEEPSEEK_API_KEY === undefined ? {} : { apiKey: process.env.DEEPSEEK_API_KEY }, + ...process.env.DEEPSEEK_BASE_URL === undefined ? {} : { baseURL: process.env.DEEPSEEK_BASE_URL }, + ...config, + }], + }) return ctx } @@ -56,8 +63,8 @@ const weatherTool: ToolSchema = { } describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => { - it.each([FLASH, PRO])('%s + reasoning off: plain text generation', async (model) => { - const ctx = await harness(model, { reasoning: 'off' }) + it.each([FLASH, PRO])('%s + provider-default reasoning: plain text generation', async (model) => { + const ctx = await harness(model) const result = await assemble(ctx,{ model, messages: ask('Reply with exactly the word: pong'), @@ -65,7 +72,6 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => }) expect(result.finish.kind).toBe('stop') expect(textOf(result).toLowerCase()).toContain('pong') - expect(result.message.content.some(block => block.type === 'reasoning')).toBe(false) }) it.each([FLASH, PRO])('%s + reasoning high: reasoning blocks present', async (model) => { @@ -99,7 +105,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => model: PRO, messages: [ ...ask('What is the weather in Paris right now? Use the get_weather tool.'), - { role: 'assistant', content: first.message.content }, + first.message, { role: 'user', content: [{ @@ -123,9 +129,9 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('llm-pi-ai e2e (real API)', () => const deepseekCtx = new Context() contexts.push(deepseekCtx) await deepseekCtx.plugin(LlmService) - await deepseekCtx.plugin(LlmDeepSeek, { models: [FLASH], thinking: 'disabled' }) + await deepseekCtx.plugin(LlmDeepSeek, { thinking: 'disabled' }) - const piCtx = await harness(FLASH, { reasoning: 'off' }) + const piCtx = await harness(FLASH) const prompt = ask('Reply with exactly the word: pong') const [fromDeepSeek, fromPiAi] = await Promise.all([ diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index cefaa9f745..6e6368611d 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -2,34 +2,35 @@ import { createServer } from 'node:http' import type { IncomingMessage, Server, ServerResponse } from 'node:http' import { afterEach, describe, expect, it, vi } from 'vitest' import { Context } from 'cordis' -import LlmService, { CallId, userAgent } from '@deepseek-ai/dsh-llm' +import LlmService, { LlmError, userAgent } from '@deepseek-ai/dsh-llm' import * as LlmPiAi from '@deepseek-ai/dsh-llm-pi-ai' -import { buildModel, PiAiAdapter } from '@deepseek-ai/dsh-llm-pi-ai' +import { PiAiAdapter, resolveProfiles } from '@deepseek-ai/dsh-llm-pi-ai' import { assemble } from './assemble.ts' -/** Scripted SSE responses, one per request (OpenAI chat-completions shape). */ interface MockServer { url: string + paths: string[] requests: unknown[] - /** Header bags of received requests, in order (parallel to `requests`). */ headers: IncomingMessage['headers'][] - close(): Promise } const servers: Server[] = [] afterEach(async () => { + vi.unstubAllEnvs() await Promise.all(servers.splice(0).map(server => new Promise(resolve => server.close(resolve)))) }) -async function mockServer(script: { status?: number; events?: string[]; body?: string }[]): Promise { +async function mockServer(script: { status?: number; events?: string[]; body?: string; delayMs?: number }[]): Promise { + const paths: string[] = [] const requests: unknown[] = [] const headers: IncomingMessage['headers'][] = [] const server = createServer((request: IncomingMessage, response: ServerResponse) => { let body = '' request.on('data', (chunk: Buffer) => { body += chunk.toString('utf8') }) request.on('end', () => { - requests.push(JSON.parse(body)) + paths.push(request.url ?? '') + requests.push(body.length === 0 ? undefined : JSON.parse(body)) headers.push(request.headers) const behavior = script.shift() ?? { status: 500, body: 'script exhausted' } if (behavior.status !== undefined && behavior.status !== 200) { @@ -38,20 +39,22 @@ async function mockServer(script: { status?: number; events?: string[]; body?: s return } response.writeHead(200, { 'content-type': 'text/event-stream' }) - for (const event of behavior.events ?? []) response.write(`data: ${event}\n\n`) - response.end() + let index = 0 + const writeNext = (): void => { + const event = behavior.events?.[index++] + if (event === undefined) { response.end(); return } + response.write(`data: ${event}\n\n`) + if (behavior.delayMs === undefined) writeNext() + else setTimeout(writeNext, behavior.delayMs) + } + writeNext() }) }) servers.push(server) await new Promise(resolve => server.listen(0, '127.0.0.1', resolve)) const address = server.address() if (address === null || typeof address === 'string') throw new Error('no port') - return { - url: `http://127.0.0.1:${address.port}`, - requests, - headers, - close: () => new Promise(resolve => server.close(() => { resolve() })), - } + return { url: `http://127.0.0.1:${address.port}`, paths, requests, headers } } const textEvents = [ @@ -61,347 +64,202 @@ const textEvents = [ '[DONE]', ] -const toolEvents = [ - '{"choices":[{"delta":{"role":"assistant","content":null},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{"tool_calls":[{"index":0,"id":"call-1","type":"function","function":{"name":"get_weather","arguments":""}}]},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{"tool_calls":[{"index":0,"function":{"arguments":"{\\"city\\":\\"Paris\\"}"}}]},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{},"index":0,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":20,"completion_tokens":6}}', - '[DONE]', -] - -const thinkingEvents = [ - '{"choices":[{"delta":{"role":"assistant","content":null,"reasoning_content":""},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{"reasoning_content":"pondering"},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{"content":"answer","reasoning_content":null},"index":0,"finish_reason":null}]}', - '{"choices":[{"delta":{},"index":0,"finish_reason":"stop"}],"usage":{"prompt_tokens":5,"completion_tokens":9}}', - '[DONE]', -] - -async function harness(baseURL: string, config: object = {}) { +async function harness(baseURL: string, overrides: Record = {}): Promise { const ctx = new Context() await ctx.plugin(LlmService) - await ctx.plugin(LlmPiAi, { apiKey: 'test-key', baseURL, models: ['deepseek-v4-flash'], ...config }) + await ctx.plugin(LlmPiAi, { + providers: [{ provider: 'deepseek', apiKey: 'test-key', baseURL, ...overrides }], + }) return ctx } -describe('PiAiAdapter against a mock server', () => { - it('streams a text generation through the assembler', async () => { +describe('PiAiAdapter provider routing', () => { + it('resolves a catalog model dynamically and uses a private endpoint', async () => { const server = await mockServer([{ events: textEvents }]) const ctx = await harness(server.url) - const result = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }], }) expect(result.message.content).toEqual([{ type: 'text', text: 'hello' }]) expect(result.finish).toEqual({ kind: 'stop' }) - expect(result.usage).toMatchObject({ inputTokens: 3, outputTokens: 1 }) + expect(result.usage).toEqual({ inputTokens: 3, outputTokens: 1 }) + expect(server.paths).toEqual(['/chat/completions']) + }) - // Attribution reaches the wire through pi-ai's headers hook: the exact - // shared User-Agent, and no provider-specific headers under the - // User-Agent-only contract. + it('merges profile headers with Harness attribution winning', async () => { + const server = await mockServer([{ events: textEvents }]) + const ctx = await harness(server.url, { + headers: { 'x-company': 'private', 'user-agent': 'wrong' }, + }) + await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) + expect(server.headers[0]?.['x-company']).toBe('private') expect(server.headers[0]?.['user-agent']).toBe(userAgent()) - expect(server.headers[0]).not.toHaveProperty('http-referer') - expect(server.headers[0]).not.toHaveProperty('x-openrouter-title') - expect(server.headers[0]).not.toHaveProperty('x-openrouter-categories') }) - it('streams tool calls with re-stringified arguments', async () => { - const server = await mockServer([{ events: toolEvents }]) - const ctx = await harness(server.url) - - const result = await assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [{ role: 'user', content: [{ type: 'text', text: 'weather?' }] }], - tools: [{ - name: 'get_weather', - description: 'Get weather', - parameters: { type: 'object', properties: { city: { type: 'string' } } }, - }], + it('forwards common stream options and profile reasoning', async () => { + const server = await mockServer([{ events: textEvents }]) + const ctx = await harness(server.url, { + reasoning: 'xhigh', + cacheRetention: 'none', + transport: 'sse', + timeoutMs: 5000, + websocketConnectTimeoutMs: 3000, + maxRetries: 0, + maxRetryDelayMs: 10, + thinkingBudgets: { high: 2048 }, }) - expect(result.finish).toEqual({ kind: 'tool-calls' }) - const call = result.message.content.find(block => block.type === 'tool-call') - expect(call).toMatchObject({ name: 'get_weather', arguments: '{"city":"Paris"}' }) - }) - - it('maps reasoning_content streams to reasoning blocks', async () => { - const server = await mockServer([{ events: thinkingEvents }]) - const ctx = await harness(server.url, { reasoning: 'high' }) - - const result = await assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [{ role: 'user', content: [{ type: 'text', text: 'think' }] }], - }) - expect(result.message.content).toEqual([ - { type: 'reasoning', text: 'pondering' }, - { type: 'text', text: 'answer' }, - ]) - }) - - it('sends DeepSeek thinking fields when reasoning is configured', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url, { reasoning: 'xhigh' }) - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - expect(server.requests[0]).toMatchObject({ - thinking: { type: 'enabled' }, - reasoning_effort: 'max', // xhigh maps to max via thinkingLevelMap - }) - }) - - it('disables thinking for reasoning: off', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url, { reasoning: 'off' }) - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - expect(server.requests[0]).toMatchObject({ thinking: { type: 'disabled' } }) - }) - - it('injects stop sequences through onPayload', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [], stop: ['END'] }) - expect(server.requests[0]).toMatchObject({ stop: ['END'] }) - }) - - it('scrubs pi-ai\'s own per-tool strict default through onPayload', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) - await assemble(ctx,{ + await assemble(ctx, { model: 'deepseek-v4-flash', messages: [], - tools: [ - { name: 'alpha', description: 'a', parameters: {} }, - { name: 'beta', description: 'b', parameters: {} }, - ], + temperature: 0.2, + maxTokens: 77, + sessionId: 'session-for-pi' as never, }) - - // pi-ai stamps `strict` on every serialized tool function; the harness - // contract has none and the hand-rolled twin sends no such field, so the - // payload fixup must have deleted it from every tool. - const request = server.requests[0] as { tools: { function: { name: string; strict?: boolean } }[] } - expect(request.tools.map(tool => tool.function.name)).toEqual(['alpha', 'beta']) - for (const tool of request.tools) { - expect('strict' in tool.function).toBe(false) - } - }) - - it('preserves raw replayed tool-call arguments in the provider payload', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) - await assemble(ctx,{ + expect(server.requests[0]).toMatchObject({ model: 'deepseek-v4-flash', - messages: [{ - role: 'assistant', - content: [{ type: 'tool-call', id: CallId('broken'), name: 'f', arguments: '{broken' }], - }], + temperature: 0.2, + max_completion_tokens: 77, + thinking: { type: 'enabled' }, + reasoning_effort: 'max', }) - - const request = server.requests[0] as { messages: { role: string; tool_calls?: { id: string; function: { arguments: string } }[] }[] } - const assistant = request.messages.find(message => message.role === 'assistant') - expect(assistant?.tool_calls?.[0]?.function.arguments).toBe('{broken') }) - it('maps HTTP errors to error finish chunks (pi-ai in-stream style)', async () => { - const server = await mockServer([{ - status: 401, - body: JSON.stringify({ error: { message: 'bad key' } }), - }]) + it('preserves omitted profile options when constructing the adapter directly', async () => { + const server = await mockServer([{ events: textEvents }]) + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['deepseek'], new PiAiAdapter({ + profiles: [{ provider: 'deepseek', apiKey: 'test-key', baseURL: server.url }], + })) + + const result = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) + + expect(result.message.content).toEqual([{ type: 'text', text: 'hello' }]) + }) + + it('rejects stop sequences rather than silently ignoring them', async () => { + const server = await mockServer([]) const ctx = await harness(server.url) - const result = await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - expect(result.finish).toMatchObject({ kind: 'error', code: 'AUTH' }) - expect((result.finish as { message: string }).message).toMatch(/bad key|401/) + await expect(assemble(ctx, { model: 'deepseek-v4-flash', messages: [], stop: ['END'] })) + .rejects.toMatchObject({ code: 'UNSUPPORTED_OPTION' }) + expect(server.requests).toEqual([]) + }) + + it('rejects unknown catalog models before network I/O', async () => { + const server = await mockServer([]) + const ctx = await harness(server.url) + await expect(assemble(ctx, { model: 'not-in-the-catalog', messages: [] })) + .rejects.toMatchObject({ code: 'UNKNOWN_MODEL' }) + expect(server.requests).toEqual([]) + }) + + it('uses the catalog API implementation, including OpenAI Responses', async () => { + const server = await mockServer([{ status: 401, body: JSON.stringify({ error: { message: 'expected mock failure' } }) }]) + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(LlmPiAi, { + providers: [{ provider: 'openai', apiKey: 'test-key', baseURL: `${server.url}/v1`, maxRetries: 0 }], + }) + const result = await assemble(ctx, { provider: 'openai', model: 'gpt-4.1', messages: [] }) + expect(result.finish.kind).toBe('error') + expect(server.paths).toEqual(['/v1/responses']) }) it.each([ + [401, 'AUTH'], [400, 'INVALID_REQUEST'], [429, 'RATE_LIMIT'], [500, 'SERVER'], - ] as const)('maps HTTP %s to stable error code %s', async (status, code) => { + ] as const)('maps HTTP %s failures to %s', async (status, code) => { const server = await mockServer([{ status, body: JSON.stringify({ error: { message: `provider ${status}` } }) }]) - const ctx = await harness(server.url) - const result = await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) + const ctx = await harness(server.url, { maxRetries: 0 }) + const result = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) expect(result.finish).toMatchObject({ kind: 'error', code }) }) +}) - it('registers/unregisters models on the llm service (HMR safety)', async () => { +describe('provider profile lifecycle', () => { + it('registers every profile atomically and unregisters on dispose', async () => { const ctx = new Context() await ctx.plugin(LlmService) - const fiber = await ctx.plugin(LlmPiAi, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) - expect(ctx.llm.models().sort()).toEqual(['deepseek-v4-flash', 'deepseek-v4-pro']) + const fiber = await ctx.plugin(LlmPiAi, { + providers: [{ provider: 'openai' }, { provider: 'anthropic' }], + }) + expect(ctx.llm.providers()).toEqual(['openai', 'anthropic']) await fiber.dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) - it('throws a clear error when no API key is available', async () => { - const previous = process.env.DEEPSEEK_API_KEY - delete process.env.DEEPSEEK_API_KEY - try { - const ctx = new Context() - await ctx.plugin(LlmService) - await expect(ctx.plugin(LlmPiAi, {})).rejects.toThrow(/an API key is required/) - } finally { - if (previous !== undefined) process.env.DEEPSEEK_API_KEY = previous - } + it('accepts absent credentials for pi-ai ambient authentication', async () => { + vi.stubEnv('DEEPSEEK_API_KEY', 'ambient-key') + const server = await mockServer([{ events: textEvents }]) + const ctx = await harness(server.url, { apiKey: undefined }) + await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) + expect(server.headers[0]?.authorization).toBe('Bearer ambient-key') + }) + + it('validates empty, duplicate, unknown, and explicitly blank profiles', () => { + expect(() => resolveProfiles([])).toThrow(/at least one/) + expect(() => resolveProfiles([{ provider: '' }])).toThrow(/non-empty/) + expect(() => resolveProfiles([{ provider: 'not-real' }])).toThrow(/unknown/) + expect(() => resolveProfiles([{ provider: 'openai' }, { provider: 'openai' }])).toThrow(/duplicate/) + expect(() => resolveProfiles([{ provider: 'openai', apiKey: '' }])).toThrow(/empty apiKey/) + expect(() => resolveProfiles([{ provider: 'openai', baseURL: '' }])).toThrow(/empty baseURL/) + }) + + it('constructs the adapter directly and rejects routes it does not own', async () => { + const adapter = new PiAiAdapter({ profiles: [{ provider: 'openai' }] }) + await expect((async () => { + for await (const _chunk of adapter.stream({ provider: 'anthropic', model: 'claude-sonnet-4', messages: [] })) { /* drain */ } + })()).rejects.toMatchObject({ code: 'NO_ADAPTER' }) + expect(new LlmError('x', 'X')).toBeInstanceOf(Error) }) }) -describe('option spreads and env fallbacks', () => { - it('forwards temperature, maxTokens, and signal', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) +describe('abort wiring', () => { + it('resolves catalog endpoints without an override before honoring pre-abort', async () => { + const adapter = new PiAiAdapter({ profiles: [{ provider: 'deepseek', apiKey: 'test-key', maxRetries: 0 }] }) const controller = new AbortController() - await assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [], - temperature: 0.5, - maxTokens: 40, - signal: controller.signal, - }) - expect(server.requests[0]).toMatchObject({ temperature: 0.5, max_tokens: 40 }) - }) - - it('falls back to DEEPSEEK_API_KEY / DEEPSEEK_BASE_URL env vars', async () => { - const server = await mockServer([{ events: textEvents }]) - vi.stubEnv('DEEPSEEK_API_KEY', 'env-key') - vi.stubEnv('DEEPSEEK_BASE_URL', server.url) - try { - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(LlmPiAi, { models: ['deepseek-v4-flash'] }) - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - expect(server.requests).toHaveLength(1) - } finally { - vi.unstubAllEnvs() - } - }) - - it('defaults to the public base URL without config or env', async () => { - vi.stubEnv('DEEPSEEK_API_KEY', 'k') - vi.stubEnv('DEEPSEEK_BASE_URL', undefined) - try { - const ctx = new Context() - await ctx.plugin(LlmService) - await ctx.plugin(LlmPiAi, {}) - expect(ctx.llm.models().length).toBeGreaterThan(0) - } finally { - vi.unstubAllEnvs() - } - }) -}) - -describe('buildModel', () => { - it('builds a DeepSeek-compat openai-completions model descriptor', () => { - const model = buildModel('deepseek-v4-pro', { apiKey: 'k', baseURL: 'http://x', reasoning: 'high' }) - expect(model).toMatchObject({ - id: 'deepseek-v4-pro', - api: 'openai-completions', + controller.abort('already stopped') + const chunks = [] + for await (const chunk of adapter.stream({ provider: 'deepseek', - baseUrl: 'http://x', - reasoning: true, - compat: { thinkingFormat: 'deepseek', requiresReasoningContentOnAssistantMessages: true }, - }) - }) - - it('keeps reasoning true even for off (pi-ai gates the thinking field on it)', () => { - // 'off' yields {thinking: {type: 'disabled'}} on the wire — pi-ai only - // emits the field at all when model.reasoning is true. - expect(buildModel('m', { apiKey: 'k', baseURL: 'http://x', reasoning: 'off' }).reasoning).toBe(true) - }) - - it('adapter is constructible directly for embedding', () => { - expect(new PiAiAdapter({ apiKey: 'k', baseURL: 'http://x' })).toBeInstanceOf(PiAiAdapter) - }) -}) - -describe('review fixes', () => { - it('defaults omitted reasoning config to thinking ENABLED (provider default)', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) // no reasoning key at all - await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [] }) - const request = server.requests[0] as Record - expect(request.thinking).toEqual({ type: 'enabled' }) - expect('reasoning_effort' in request).toBe(false) - }) - - it('replays reasoning_content on assistant tool-call turns (passback rule)', async () => { - const server = await mockServer([{ events: textEvents }]) - const ctx = await harness(server.url) - await assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [ - { role: 'user', content: [{ type: 'text', text: 'weather?' }] }, - { - role: 'assistant', - content: [ - { type: 'reasoning', text: 'I should check.' }, - { type: 'tool-call', id: CallId('c1'), name: 'get_weather', arguments: '{"city":"Paris"}' }, - ], - }, - { - role: 'user', - content: [{ type: 'tool-result', toolCallId: CallId('c1'), content: [{ type: 'text', text: 'Sunny' }] }], - }, - ], - }) - const request = server.requests[0] as { messages: { role: string; reasoning_content?: string }[] } - const assistant = request.messages.find(message => message.role === 'assistant') - expect(assistant?.reasoning_content).toBe('I should check.') - }) - - it('aborts the upstream request when the consumer stops streaming early', async () => { - // Slow server: write one chunk, then hold the connection open and record - // whether the socket closes (the adapter must cancel on early break). - let socketClosed = false - const server = createServer((request: IncomingMessage, response: ServerResponse) => { - request.on('data', () => undefined) - request.on('end', () => { - response.writeHead(200, { 'content-type': 'text/event-stream' }) - response.write(`data: ${textEvents[0]}\n\n`) - response.write(`data: ${textEvents[1]}\n\n`) - // never finish; rely on client abort - request.socket.on('close', () => { socketClosed = true }) - }) - }) - servers.push(server) - await new Promise(resolve => server.listen(0, '127.0.0.1', resolve)) - const address = server.address() - if (address === null || typeof address === 'string') throw new Error('no port') - const ctx = await harness(`http://127.0.0.1:${address.port}`) - - for await (const chunk of ctx.llm.stream({ model: 'deepseek-v4-flash', messages: [] })) { - if (chunk.type === 'text-delta') break // stop early mid-stream - } - // The finally-abort must reach the server as a closed socket. - await vi.waitFor(() => { expect(socketClosed).toBe(true) }, { timeout: 5_000 }) - }) -}) - -describe('review fixes: abort wiring', () => { - it('honors a pre-aborted caller signal', async () => { - const ctx = await harness('http://127.0.0.1:1') - const controller = new AbortController() - controller.abort('already cancelled') - // pi-ai surfaces the abort as an in-stream error event → aborted finish. - const result = await assemble(ctx,{ model: 'deepseek-v4-flash', messages: [], signal: controller.signal, - }) + })) chunks.push(chunk) + expect(chunks.at(-1)).toMatchObject({ type: 'finish', reason: { kind: 'aborted' } }) + }) + + it('honors a pre-aborted caller signal', async () => { + const server = await mockServer([{ events: textEvents, delayMs: 20 }]) + const ctx = await harness(server.url) + const controller = new AbortController() + controller.abort('already stopped') + const result = await assemble(ctx, { model: 'deepseek-v4-flash', messages: [], signal: controller.signal }) expect(result.finish.kind).toBe('aborted') }) - it('propagates a mid-stream caller abort to the upstream request', async () => { - const server = await mockServer([{ events: textEvents }]) + it('forwards an abort that arrives while provider streaming is active', async () => { + const server = await mockServer([{ events: textEvents, delayMs: 30 }]) const ctx = await harness(server.url) const controller = new AbortController() - const pending = assemble(ctx,{ - model: 'deepseek-v4-flash', - messages: [], - signal: controller.signal, + const resultPromise = assemble(ctx, { + model: 'deepseek-v4-flash', messages: [], signal: controller.signal, }) - controller.abort() - const result = await pending - // Either the abort lands before any chunk (aborted) or after the tiny - // mock stream finished (stop) — both are valid races; never a hang. - expect(['aborted', 'stop']).toContain(result.finish.kind) + setTimeout(() => { controller.abort('stopped during stream') }, 10) + const result = await resultPromise + expect(result.finish.kind).toBe('aborted') + }) + + it('aborts upstream when a consumer stops early', async () => { + const server = await mockServer([{ events: textEvents, delayMs: 30 }]) + const ctx = await harness(server.url) + for await (const chunk of ctx.llm.stream({ provider: 'deepseek', model: 'deepseek-v4-flash', messages: [] })) { + if (chunk.type === 'block-start') break + } + await new Promise(resolve => setTimeout(resolve, 20)) + expect(server.requests).toHaveLength(1) }) }) diff --git a/packages/llm/llm-pi-ai/tests/assemble.ts b/packages/llm/llm-pi-ai/tests/assemble.ts index b0182615e0..494eeac494 100644 --- a/packages/llm/llm-pi-ai/tests/assemble.ts +++ b/packages/llm/llm-pi-ai/tests/assemble.ts @@ -15,11 +15,19 @@ export interface AssembledResult { finish: FinishReason } -export async function assemble(ctx: Context, options: GenerateOptions): Promise { +export async function assemble(ctx: Context, options: Omit & { provider?: string }): Promise { const assembler = new BlockAssembler() - for await (const chunk of ctx.llm.stream(options)) assembler.push(chunk) + const request = { provider: 'deepseek', ...options } + for await (const chunk of ctx.llm.stream(request)) assembler.push(chunk) return { - message: assembler.message(), + message: { + ...assembler.message(), + provenance: { + provider: request.provider, + model: request.model, + ...assembler.replayState === undefined ? {} : { replayState: assembler.replayState }, + }, + }, ...assembler.usage !== undefined ? { usage: assembler.usage } : {}, finish: assembler.finish, } diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index 078d2a4d3b..cf8e07de5c 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -1,8 +1,8 @@ import { describe, expect, it } from 'vitest' -import { CallId } from '@deepseek-ai/dsh-llm' +import { CallId, LlmError } from '@deepseek-ai/dsh-llm' import type { ContentBlock, StreamChunk } from '@deepseek-ai/dsh-llm' import type { AssistantMessage, AssistantMessageEvent, Usage } from '@earendil-works/pi-ai' -import { mapStopReason, mapUsage, toPiContext, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai' +import { mapStopReason, mapUsage, toPiContext, toPiReplayState, toStreamChunks } from '@deepseek-ai/dsh-llm-pi-ai' function usage(input = 0, output = 0, cacheRead = 0, cacheWrite = 0): Usage { return { @@ -42,6 +42,7 @@ async function collect(stream: AsyncIterable): Promise { it('maps system prompt, user text, and tools', () => { const context = toPiContext({ + provider: 'deepseek', model: 'deepseek-v4-flash', system: 'be helpful', messages: [{ role: 'user', content: [{ type: 'text', text: 'hi' }] }], @@ -55,13 +56,14 @@ describe('toPiContext', () => { }) it('omits empty tools and absent system prompt', () => { - const context = toPiContext({ model: 'm', messages: [], tools: [] }) + const context = toPiContext({ provider: 'deepseek', model: 'm', messages: [], tools: [] }) expect(context.systemPrompt).toBeUndefined() expect(context.tools).toBeUndefined() }) it('maps assistant text/reasoning/tool-call blocks', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', @@ -76,8 +78,7 @@ describe('toPiContext', () => { expect(message.role).toBe('assistant') expect(message.stopReason).toBe('toolUse') expect(message.content).toEqual([ - // thinkingSignature names the replay field — DeepSeek's passback rule. - { type: 'thinking', thinking: 'hmm', thinkingSignature: 'reasoning_content' }, + { type: 'thinking', thinking: 'hmm' }, { type: 'text', text: 'calling' }, { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 } }, ]) @@ -85,6 +86,7 @@ describe('toPiContext', () => { it('marks tool-call-free assistant messages with stopReason stop', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', content: [{ type: 'text', text: 'done' }] }], }) @@ -93,6 +95,7 @@ describe('toPiContext', () => { it('parses malformed tool-call arguments to {}', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', @@ -105,6 +108,7 @@ describe('toPiContext', () => { it('parses non-object argument JSON (arrays, scalars) to {}', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', @@ -116,6 +120,7 @@ describe('toPiContext', () => { it('recovers toolName for tool results from the preceding assistant call', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [ { @@ -140,6 +145,7 @@ describe('toPiContext', () => { it('labels unmatched tool results with toolName unknown and keeps isError', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'user', @@ -156,6 +162,7 @@ describe('toPiContext', () => { it('splits mixed user text + tool results and folds history system messages', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [ { role: 'system', content: [{ type: 'text', text: 'rule' }] }, @@ -173,6 +180,7 @@ describe('toPiContext', () => { it('skips plugin-added (unknown) blocks in assistant content', () => { const context = toPiContext({ + provider: 'deepseek', model: 'm', messages: [{ role: 'assistant', @@ -184,6 +192,173 @@ describe('toPiContext', () => { }) expect((context.messages[0] as AssistantMessage).content).toEqual([{ type: 'text', text: 'visible' }]) }) + + it('recombines durable content with pi-ai replay metadata across target providers and models', () => { + const state = toPiReplayState(assistant({ + api: 'openai-responses', + provider: 'openai', + model: 'gpt-5', + responseModel: 'gpt-5-2026-01-01', + responseId: 'resp_123', + stopReason: 'toolUse', + content: [ + { type: 'thinking', thinking: 'private reasoning', thinkingSignature: 'think-sig', redacted: true }, + { type: 'text', text: 'calling', textSignature: 'text-sig' }, + { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 }, thoughtSignature: 'tool-sig' }, + ], + })) + const context = toPiContext({ + provider: 'anthropic', + model: 'claude-next', + messages: [{ + role: 'assistant', + content: [ + { type: 'reasoning', text: 'private reasoning' }, + { type: 'text', text: 'calling' }, + { type: 'tool-call', id: CallId('c1'), name: 'f', arguments: '{"a":1}' }, + ], + provenance: { provider: 'openai', model: 'gpt-5', replayState: state }, + }], + }) + + expect(context.messages[0]).toMatchObject({ + role: 'assistant', + api: 'openai-responses', + provider: 'openai', + model: 'gpt-5', + responseModel: 'gpt-5-2026-01-01', + responseId: 'resp_123', + stopReason: 'toolUse', + content: [ + { type: 'thinking', thinking: 'private reasoning', thinkingSignature: 'think-sig', redacted: true }, + { type: 'text', text: 'calling', textSignature: 'text-sig' }, + { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 }, thoughtSignature: 'tool-sig' }, + ], + }) + }) + + it('replays all native block kinds when optional metadata is absent', () => { + const state = toPiReplayState(assistant({ + content: [ + { type: 'thinking', thinking: 'private reasoning' }, + { type: 'text', text: 'calling' }, + { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 } }, + ], + })) + const context = toPiContext({ + provider: 'deepseek', + model: 'new-model', + messages: [{ + role: 'assistant', + content: [ + { type: 'reasoning', text: 'private reasoning' }, + { type: 'text', text: 'calling' }, + { type: 'tool-call', id: CallId('c1'), name: 'f', arguments: '{"a":1}' }, + ], + provenance: { provider: 'deepseek', model: 'old-model', replayState: state }, + }], + }) + + expect(context.messages[0]).toMatchObject({ + role: 'assistant', + content: [ + { type: 'thinking', thinking: 'private reasoning' }, + { type: 'text', text: 'calling' }, + { type: 'toolCall', id: 'c1', name: 'f', arguments: { a: 1 } }, + ], + }) + expect(context.messages[0]).not.toHaveProperty('responseModel') + expect(context.messages[0]).not.toHaveProperty('responseId') + }) + + it('rejects unsupported replay-state versions with a stable error code', () => { + try { + toPiContext({ + provider: 'deepseek', + model: 'm', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'done' }], + provenance: { + provider: 'deepseek', + model: 'old', + replayState: { kind: 'pi-ai', version: 2 }, + }, + }], + }) + expect.fail('expected invalid replay state') + } catch (error: unknown) { + expect(error).toBeInstanceOf(LlmError) + expect((error as LlmError).code).toBe('INVALID_REPLAY_STATE') + expect((error as Error).message).toContain('unsupported version 2') + } + }) + + it('rejects replay metadata whose blocks do not match the durable content', () => { + const state = toPiReplayState(assistant({ content: [{ type: 'text', text: 'done' }] })) + expect(() => toPiContext({ + provider: 'deepseek', + model: 'm', + messages: [{ + role: 'assistant', + content: [{ type: 'reasoning', text: 'done' }], + provenance: { provider: 'deepseek', model: 'old', replayState: state }, + }], + })).toThrow(/block 0 does not match assistant content/) + }) + + it('rejects replay metadata whose block count differs from durable content', () => { + const state = toPiReplayState(assistant()) + expect(() => toPiContext({ + provider: 'deepseek', + model: 'm', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'done' }], + provenance: { provider: 'deepseek', model: 'old', replayState: state }, + }], + })).toThrow(/block count does not match assistant content/) + }) + + const validReplay = { + kind: 'pi-ai', + version: 1, + api: 'openai-completions', + provider: 'deepseek', + model: 'deepseek-v4-flash', + stopReason: 'stop', + blocks: [{ type: 'text' }], + } + + it.each([ + ['number state', 1, 'expected an object'], + ['null state', null, 'expected an object'], + ['array state', [], 'expected an object'], + ['unknown kind', { ...validReplay, kind: 'other' }, 'unknown state kind'], + ['non-string api', { ...validReplay, api: 1 }, 'api must be a non-empty string'], + ['empty provider', { ...validReplay, provider: '' }, 'provider must be a non-empty string'], + ['missing model', { ...validReplay, model: undefined }, 'model must be a non-empty string'], + ['unknown stop reason', { ...validReplay, stopReason: 'pause' }, 'unknown stopReason'], + ['non-string response model', { ...validReplay, responseModel: 1 }, 'responseModel must be a string'], + ['non-string response id', { ...validReplay, responseId: 1 }, 'responseId must be a string'], + ['non-array blocks', { ...validReplay, blocks: 'text' }, 'blocks must be an array'], + ['number block', { ...validReplay, blocks: [1] }, 'block 0 must be an object'], + ['null block', { ...validReplay, blocks: [null] }, 'block 0 must be an object'], + ['array block', { ...validReplay, blocks: [[]] }, 'block 0 must be an object'], + ['unknown block type', { ...validReplay, blocks: [{ type: 'audio' }] }, 'block 0 has an unknown type'], + ['non-string signature', { ...validReplay, blocks: [{ type: 'text', textSignature: 1 }] }, 'textSignature must be a string'], + ['non-boolean redaction', { ...validReplay, blocks: [{ type: 'reasoning', redacted: 'yes' }] }, 'redacted must be boolean'], + ])('rejects malformed replay state: %s', (_name, replayState, message) => { + expect(() => toPiContext({ + provider: 'deepseek', + model: 'm', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'done' }], + provenance: { provider: 'deepseek', model: 'old', replayState }, + }], + })).toThrow(message) + }) }) describe('toStreamChunks', () => { @@ -205,7 +380,19 @@ describe('toStreamChunks', () => { { type: 'text-delta', index: 0, text: 'hi' }, { type: 'block-end', index: 0, block: { type: 'text', text: 'hi' } }, { type: 'usage', usage: { inputTokens: 3, outputTokens: 2 } }, - { type: 'finish', reason: { kind: 'stop' } }, + { + type: 'finish', + reason: { kind: 'stop' }, + replayState: { + kind: 'pi-ai', + version: 1, + api: 'openai-completions', + provider: 'deepseek', + model: 'deepseek-v4-flash', + stopReason: 'stop', + blocks: [{ type: 'text' }], + }, + }, ]) }) @@ -234,7 +421,7 @@ describe('toStreamChunks', () => { toolCall: { type: 'toolCall', id: 'call-1', name: 'f', arguments: { a: 1 } }, partial: partialWithToolCall, }, - { type: 'done', reason: 'toolUse', message: assistant({ stopReason: 'toolUse' }) }, + { type: 'done', reason: 'toolUse', message: assistant({ content: partialWithToolCall.content, stopReason: 'toolUse' }) }, ))) expect(chunks).toEqual([ { type: 'block-start', index: 0, blockType: 'tool-call' }, @@ -242,7 +429,19 @@ describe('toStreamChunks', () => { { type: 'tool-call-delta', index: 0, id: 'call-1', name: 'f', argumentsDelta: ':1}' }, { type: 'block-end', index: 0, block: { type: 'tool-call', id: 'call-1', name: 'f', arguments: '{"a":1}' } }, { type: 'usage', usage: { inputTokens: 0, outputTokens: 0 } }, - { type: 'finish', reason: { kind: 'tool-calls' } }, + { + type: 'finish', + reason: { kind: 'tool-calls' }, + replayState: { + kind: 'pi-ai', + version: 1, + api: 'openai-completions', + provider: 'deepseek', + model: 'deepseek-v4-flash', + stopReason: 'toolUse', + blocks: [{ type: 'tool-call' }], + }, + }, ]) }) diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 42694ba5ea..4a65e423ca 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -8,8 +8,8 @@ An adapter registry plus a single streaming call surface, interceptable via a wa ### Public API -- `ctx.llm.registerAdapter(models: string[], adapter: LlmAdapter): () => void` Register an adapter for the given model names. Disposed with the calling fiber. -- `ctx.llm.models(): string[]` — model names with a registered adapter. +- `ctx.llm.registerAdapter(providers: string[], adapter: LlmAdapter): () => void` Register one adapter instance for the given provider routes. Registration is all-or-nothing, and is disposed with the calling fiber. +- `ctx.llm.providers(): string[]` — provider routes with a registered adapter. - `ctx.llm.stream(options: GenerateOptions): AsyncIterable` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`. ### Events @@ -20,18 +20,18 @@ An adapter registry plus a single streaming call surface, interceptable via a wa ### Extension points -- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(models, adapter)` to add a new model provider. +- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(providers, adapter)` to add one or more provider routes. `GenerateOptions.provider` selects the adapter; `GenerateOptions.model` is adapter-owned and may be resolved dynamically. - Wrap `llm/stream` via `ctx.on()` waterfall listeners for caching, retry, logging, rate-limiting, etc. ### Content-block vocabulary (`types.ts`) -Messages are arrays of typed content blocks: `text`, `reasoning`, `tool-call`, `tool-result`. The union is derived from the merge-extensible `ContentBlockMap`, so plugins can add block types via declaration merging. The core set is limited to blocks every shipping path honors — multimodal content (images, audio, …) has no core block type; a feature that needs one adds it via the map together with the adapter/UI/compaction support that honors it. +Messages are arrays of typed content blocks: `text`, `reasoning`, `tool-call`, `tool-result`. The union is derived from the merge-extensible `ContentBlockMap`, so plugins can add block types via declaration merging. Assistant messages produced by the loop also carry provider/model provenance and optional adapter-private replay state. Before dispatch, `LlmService` retains that state only when the historical provider route and target provider route are currently owned by the exact same adapter instance; the adapter then decides whether it can restore or convert the state across models/providers. The core block set is limited to blocks every shipping path honors — multimodal content (images, audio, …) has no core block type; a feature that needs one adds it via the map together with the adapter/UI/compaction support that honors it. Streaming is a raw chunk protocol (`block-start`, `text-delta`, `reasoning-delta`, `tool-call-delta`, `block-end`, `usage`, `finish`). `BlockAssembler` is the single shared implementation that assembles chunks into blocks/messages. ### Call configuration (`call-config.ts`) -`LlmCallConfig` is the model + sampling scalars of one conversation's requests (`model`, `temperature`, `maxTokens`, `stop` — each mapping 1:1 onto the same-named `GenerateOptions` field). It is per-conversation state recorded in the session log as part of the request header (see the dsh-session `request/header` events), never a silently-adjustable per-call knob: the `agent/request` waterfall proposes a replacement and the loop logs a real change. `callConfigEquals(a, b)` is the field-wise real-change detector; `deepFreeze(value)` is the ownership helper the loop applies to every built request before dispatch (`llm/stream` listeners and adapters read, never rewrite). +`LlmCallConfig` is the provider + model + sampling scalars of one conversation's requests (`provider`, `model`, `temperature`, `maxTokens`, `stop` — each mapping 1:1 onto the same-named `GenerateOptions` field). It is per-conversation state recorded in the session log as part of the request header (see the dsh-session `request/header` events), never a silently-adjustable per-call knob: the `agent/request` waterfall proposes a replacement and the loop logs a real change. `callConfigEquals(a, b)` is the field-wise real-change detector; `deepFreeze(value)` is the ownership helper the loop applies to every built request before dispatch (`llm/stream` listeners and adapters read, never rewrite). ### App attribution (`attribution.ts`) @@ -46,4 +46,4 @@ Every product adapter must identify the application on every provider HTTP reque ### Real adapters -Two adapters implement `LlmAdapter` against this vocabulary, deliberately built on different internals to keep the contract honest (see [the twin LLM adapters](../../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md)): [`@deepseek-ai/dsh-llm-deepseek`](../llm-deepseek) (hand-rolled fetch/SSE) and [`@deepseek-ai/dsh-llm-pi-ai`](../llm-pi-ai) (via `@earendil-works/pi-ai`). The pair pinned down the `StreamChunk` conventions now documented in `types.ts` (usage before finish, raw-string tool arguments, the two sanctioned error paths). +Two adapters implement `LlmAdapter` against this vocabulary, deliberately built on different internals to keep the contract honest (see [the twin LLM adapters](../../../docs/rfc/implemented/architecture/2026-06-13-twin-llm-adapters.md)): [`@deepseek-ai/dsh-llm-deepseek`](../llm-deepseek) is a hand-rolled DeepSeek fetch/SSE adapter, while [`@deepseek-ai/dsh-llm-pi-ai`](../llm-pi-ai) dynamically resolves any configured provider/model in pi-ai's installed catalog. The pair pinned down the `StreamChunk` conventions now documented in `types.ts` (usage before finish, raw-string tool arguments, the two sanctioned error paths). diff --git a/packages/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index 1b8ba6e60c..31efccae37 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -36,6 +36,7 @@ export class BlockAssembler { private order: number[] = [] private _usage: TokenUsage | undefined private _finish: FinishReason | undefined + private _replayState: unknown /** * Feed one chunk. Returns the completed block when the chunk closes one @@ -87,6 +88,7 @@ export class BlockAssembler { } case 'finish': { this._finish = chunk.reason + this._replayState = chunk.replayState return } default: return assertNever(chunk, 'BlockAssembler.push') @@ -144,6 +146,11 @@ export class BlockAssembler { return this._finish ?? { kind: 'stop' } } + /** Adapter-private replay state from the terminal finish chunk, if any. */ + get replayState(): unknown { + return this._replayState + } + /** * The assembled assistant message. * @returns an assistant-role message over `blocks()` (same open-block assembly rules). diff --git a/packages/llm/llm/src/call-config.ts b/packages/llm/llm/src/call-config.ts index 53cb157214..6a117c877f 100644 --- a/packages/llm/llm/src/call-config.ts +++ b/packages/llm/llm/src/call-config.ts @@ -2,9 +2,9 @@ * The call configuration of a conversation and its comparison/freeze * utilities. `LlmCallConfig` is the non-content third of the request header * (see `EpochHeader` in dsh-session): everything about a request besides its - * message content that can undermine provider KV-cache reuse — `model` - * selects the cache namespace outright, and the sampling scalars are treated - * the same way out of caution. It is per-conversation state recorded in the + * message content that can undermine provider KV-cache reuse — `provider` and + * `model` select the adapter and cache namespace outright, and the sampling + * scalars are treated the same way out of caution. It is per-conversation state recorded in the * session log (the reconstructability RFC), never a silently-drifting * per-call knob: the `agent/request` waterfall proposes a replacement, and * the loop logs a real change as a `request/header-delta` event. @@ -13,11 +13,12 @@ */ /** - * Model + sampling scalars of one conversation's requests. Every field maps + * Provider + model + sampling scalars of one conversation's requests. Every field maps * 1:1 onto the same-named `GenerateOptions` field; the loop builds requests * from the logged header rather than accepting these per call. */ export interface LlmCallConfig { + provider: string model: string temperature?: number maxTokens?: number @@ -33,7 +34,7 @@ export interface LlmCallConfig { * @returns whether every field (including the `stop` list, element-wise) matches. */ export function callConfigEquals(a: LlmCallConfig, b: LlmCallConfig): boolean { - if (a.model !== b.model || a.temperature !== b.temperature || a.maxTokens !== b.maxTokens) return false + if (a.provider !== b.provider || a.model !== b.model || a.temperature !== b.temperature || a.maxTokens !== b.maxTokens) return false if (a.stop === undefined || b.stop === undefined) return a.stop === b.stop return a.stop.length === b.stop.length && a.stop.every((s, i) => s === b.stop?.[i]) } diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 667e9bca78..47bdc64e69 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -7,8 +7,9 @@ */ import { Context, Service } from 'cordis' -import type { GenerateOptions, StreamChunk } from './types.ts' +import type { GenerateOptions, Message, StreamChunk } from './types.ts' import { HarnessError } from './error.ts' +import { deepFreeze } from './call-config.ts' export * from './attribution.ts' export * from './brand.ts' @@ -58,7 +59,7 @@ export class LlmError extends HarnessError { * * An adapter translates between the harness vocabulary (Message/ContentBlock/ * StreamChunk) and one provider's wire format. Adapters register themselves - * via `ctx.llm.registerAdapter(models, adapter)`. + * via `ctx.llm.registerAdapter(providers, adapter)`. * * Real implementations: `@deepseek-ai/dsh-llm-deepseek` (hand-rolled * fetch/SSE) and `@deepseek-ai/dsh-llm-pi-ai` (pi-ai-backed) — two @@ -93,23 +94,27 @@ export class LlmService extends Service { } /** - * Register an adapter for the given model names. Throws `LlmError` with code - * `DUPLICATE_ADAPTER` if any model already has an adapter (all-or-nothing). + * Register an adapter for the given provider routes. Throws `LlmError` with code + * `DUPLICATE_ADAPTER` if any provider already has an adapter (all-or-nothing). * Disposed with the fiber. - * @param models - every model name this adapter should serve. - * @param adapter - the adapter that streams calls for those models. + * @param providers - every provider route this adapter should serve. + * @param adapter - the adapter that streams calls for those providers. * @returns the disposer that unregisters all of them. */ - registerAdapter(models: string[], adapter: LlmAdapter): () => void { + registerAdapter(providers: string[], adapter: LlmAdapter): () => void { const dispose = this.ctx.effect(function* (this: LlmService) { - for (const model of models) { - if (this.adapters.has(model)) { - throw new LlmError(`an adapter for model "${model}" is already registered`, 'DUPLICATE_ADAPTER') + if (providers.length === 0) throw new LlmError('an adapter must register at least one provider', 'INVALID_ADAPTER') + const unique = new Set() + for (const provider of providers) { + if (provider.length === 0) throw new LlmError('adapter provider names must be non-empty', 'INVALID_ADAPTER') + if (unique.has(provider) || this.adapters.has(provider)) { + throw new LlmError(`an adapter for provider "${provider}" is already registered`, 'DUPLICATE_ADAPTER') } + unique.add(provider) } - for (const model of models) this.adapters.set(model, adapter) + for (const provider of providers) this.adapters.set(provider, adapter) yield () => { - for (const model of models) this.adapters.delete(model) + for (const provider of providers) this.adapters.delete(provider) } }.bind(this), 'llm.registerAdapter()') // ctx.effect's disposer returns Promise; our disposer API is @@ -118,29 +123,48 @@ export class LlmService extends Service { } /** - * Model names with a registered adapter. - * @returns the registered names, in registration order. + * Provider routes with a registered adapter. + * @returns the registered provider names, in registration order. */ - models(): string[] { + providers(): string[] { return [...this.adapters.keys()] } - private adapter(model: string): LlmAdapter { - const adapter = this.adapters.get(model) - if (!adapter) throw new LlmError(`no adapter registered for model "${model}"`, 'NO_ADAPTER') + private adapter(provider: string): LlmAdapter { + const adapter = this.adapters.get(provider) + if (!adapter) throw new LlmError(`no adapter registered for provider "${provider}"`, 'NO_ADAPTER') return adapter } + /** Remove replay state whose historical route is owned by another adapter. */ + private forAdapter(options: GenerateOptions, adapter: LlmAdapter): GenerateOptions { + const messages: Message[] = options.messages.map((message) => { + const provenance = message.provenance + if (message.role !== 'assistant' || provenance?.replayState === undefined) return message + if (this.adapters.get(provenance.provider) === adapter) return message + return { + ...message, + provenance: { provider: provenance.provider, model: provenance.model }, + } + }) + if (messages.every((message, index) => message === options.messages[index])) return options + const filtered = { ...options, messages } + return Object.isFrozen(options) ? deepFreeze(filtered) : filtered + } + /** * Stream one model call as raw chunks (token-level deltas). Throws * `LlmError` with code `NO_ADAPTER` if no adapter is registered for - * `options.model`. Dispatches through the `llm/stream` waterfall. - * @param options - the full request; `options.model` selects the adapter. + * `options.provider`. Replay state is retained only when the same adapter + * instance owns its historical provider and the target provider. Dispatches + * through the `llm/stream` waterfall. + * @param options - the full request; `options.provider` selects the adapter. * @returns the chunk stream, possibly wrapped by `llm/stream` listeners. */ stream(options: GenerateOptions): AsyncIterable { return this.ctx.waterfall(this, 'llm/stream', options, () => { - return this.adapter(options.model).stream(options) + const adapter = this.adapter(options.provider) + return adapter.stream(this.forAdapter(options, adapter)) }) } } diff --git a/packages/llm/llm/src/types.ts b/packages/llm/llm/src/types.ts index e3339869a5..b3280acb03 100644 --- a/packages/llm/llm/src/types.ts +++ b/packages/llm/llm/src/types.ts @@ -75,10 +75,29 @@ export type ContentBlockType = keyof ContentBlockMap /** Any known content block, derived from {@link ContentBlockMap}; switch on `type` and fall through unknowns (merge-extensible). */ export type ContentBlock = ContentBlockMap[ContentBlockType] -/** A single message in a conversation history. */ +/** Provider ownership and adapter-private replay data for an assistant message. */ +export interface AssistantProvenance { + /** Provider route that produced the message. */ + provider: string + /** Provider model id that produced the message. */ + model: string + /** + * Lossless-JSON adapter state needed to replay the provider response. + * `LlmService` exposes it to a target adapter only when that adapter instance + * currently owns both this historical provider and the target provider. + */ + replayState?: unknown +} + +/** + * A single message in a conversation history. Loop-derived assistant messages + * always carry provenance; callers may omit it on hand-built foreign history. + */ export interface Message { role: 'system' | 'user' | 'assistant' content: ContentBlock[] + /** Present only on assistant messages produced by a routed adapter. */ + provenance?: AssistantProvenance } /** @@ -153,7 +172,12 @@ export type StreamChunk = | { type: 'tool-call-delta'; index: number; id: CallId; name?: string; argumentsDelta: string } | { type: 'block-end'; index: number; block: ContentBlock } | { type: 'usage'; usage: TokenUsage } - | { type: 'finish'; reason: FinishReason } + | { + type: 'finish' + reason: FinishReason + /** Adapter-private lossless-JSON state for replaying a successful response. */ + replayState?: unknown + } /** * JSON-schema description of a tool, as sent to the model. @@ -171,6 +195,8 @@ export interface ToolSchema { /** A single model request, fully assembled. */ export interface GenerateOptions { + /** Registered provider route selecting the adapter instance. */ + provider: string model: string /** * Ordered conversation messages, exactly as the provider sees them (after diff --git a/packages/llm/llm/tests/call-config.spec.ts b/packages/llm/llm/tests/call-config.spec.ts index 65ff7d7d34..4bccd2520a 100644 --- a/packages/llm/llm/tests/call-config.spec.ts +++ b/packages/llm/llm/tests/call-config.spec.ts @@ -9,14 +9,16 @@ import { callConfigEquals, deepFreeze } from '../src/call-config.ts' describe('callConfigEquals', () => { it('compares every field, including the stop list element-wise', () => { - expect(callConfigEquals({ model: 'm' }, { model: 'm' })).toBe(true) - expect(callConfigEquals({ model: 'm' }, { model: 'x' })).toBe(false) - expect(callConfigEquals({ model: 'm', temperature: 0.5 }, { model: 'm' })).toBe(false) - expect(callConfigEquals({ model: 'm', maxTokens: 1 }, { model: 'm', maxTokens: 2 })).toBe(false) - expect(callConfigEquals({ model: 'm', stop: ['a'] }, { model: 'm' })).toBe(false) - expect(callConfigEquals({ model: 'm', stop: ['a'] }, { model: 'm', stop: ['a', 'b'] })).toBe(false) - expect(callConfigEquals({ model: 'm', stop: ['a'] }, { model: 'm', stop: ['b'] })).toBe(false) - expect(callConfigEquals({ model: 'm', stop: ['a', 'b'] }, { model: 'm', stop: ['a', 'b'] })).toBe(true) + const base = { provider: 'p', model: 'm' } + expect(callConfigEquals(base, base)).toBe(true) + expect(callConfigEquals(base, { provider: 'x', model: 'm' })).toBe(false) + expect(callConfigEquals(base, { provider: 'p', model: 'x' })).toBe(false) + expect(callConfigEquals({ ...base, temperature: 0.5 }, base)).toBe(false) + expect(callConfigEquals({ ...base, maxTokens: 1 }, { ...base, maxTokens: 2 })).toBe(false) + expect(callConfigEquals({ ...base, stop: ['a'] }, base)).toBe(false) + expect(callConfigEquals({ ...base, stop: ['a'] }, { ...base, stop: ['a', 'b'] })).toBe(false) + expect(callConfigEquals({ ...base, stop: ['a'] }, { ...base, stop: ['b'] })).toBe(false) + expect(callConfigEquals({ ...base, stop: ['a', 'b'] }, { ...base, stop: ['a', 'b'] })).toBe(true) }) }) diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index f669069c44..2308a7eb3b 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -12,6 +12,15 @@ class ScriptedAdapter extends LlmAdapter { } } +class RecordingAdapter extends ScriptedAdapter { + lastOptions: GenerateOptions | undefined + + override async * stream(options: GenerateOptions): AsyncIterable { + this.lastOptions = options + yield * super.stream(options) + } +} + const SCRIPT: StreamChunk[] = [ { type: 'block-start', index: 0, blockType: 'text' }, { type: 'text-delta', index: 0, text: 'hi' }, @@ -22,18 +31,18 @@ describe('LlmService', () => { it('routes stream() to the registered adapter', async () => { const ctx = new Context() await ctx.plugin(LlmService) - ctx.llm.registerAdapter(['test-model'], new ScriptedAdapter(SCRIPT)) + ctx.llm.registerAdapter(['test-provider'], new ScriptedAdapter(SCRIPT)) const chunks: StreamChunk[] = [] - for await (const chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) chunks.push(chunk) + for await (const chunk of ctx.llm.stream({ provider: 'test-provider', model: 'test-model', messages: [] })) chunks.push(chunk) expect(chunks).toEqual(SCRIPT) }) - it('throws NO_ADAPTER for unregistered models', async () => { + it('throws NO_ADAPTER for unregistered providers', async () => { const ctx = new Context() await ctx.plugin(LlmService) await expect((async () => { - for await (const _ of ctx.llm.stream({ model: 'nope', messages: [] })) { /* drain */ } + for await (const _ of ctx.llm.stream({ provider: 'nope', model: 'any-model', messages: [] })) { /* drain */ } })()).rejects.toThrow('no adapter registered') }) @@ -44,10 +53,10 @@ describe('LlmService', () => { const fiber = await ctx.plugin(Object.assign((inner: Context) => { inner.llm.registerAdapter(['scoped-model'], new ScriptedAdapter(SCRIPT)) }, { inject: ['llm'] })) - expect(ctx.llm.models()).toEqual(['scoped-model']) + expect(ctx.llm.providers()).toEqual(['scoped-model']) await fiber.dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) it('lets llm/stream waterfall listeners wrap the underlying stream', async () => { @@ -64,11 +73,90 @@ describe('LlmService', () => { }) const chunks: StreamChunk[] = [] - for await (const chunk of ctx.llm.stream({ model: 'test-model', messages: [] })) chunks.push(chunk) + for await (const chunk of ctx.llm.stream({ provider: 'test-model', model: 'dynamic-model', messages: [] })) chunks.push(chunk) expect(chunks).toHaveLength(4) expect(chunks[0]).toMatchObject({ index: 99 }) }) + it('resolves the provider after llm/stream listeners have had a chance to route it', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const adapter = new RecordingAdapter(SCRIPT) + ctx.llm.registerAdapter(['routed'], adapter) + ctx.on('llm/stream', (options, next) => { + options.provider = 'routed' + return next() + }) + + for await (const _chunk of ctx.llm.stream({ provider: 'initial', model: 'm', messages: [] })) { /* drain */ } + expect(adapter.lastOptions?.provider).toBe('routed') + }) + + it('keeps replay state when historical and target providers belong to the same adapter instance', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const adapter = new RecordingAdapter(SCRIPT) + ctx.llm.registerAdapter(['historical', 'target'], adapter) + const replayState = { private: 'state' } + + for await (const _chunk of ctx.llm.stream({ + provider: 'target', + model: 'new-model', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'old response' }], + provenance: { provider: 'historical', model: 'old-model', replayState }, + }], + })) { /* drain */ } + + expect(adapter.lastOptions?.messages[0]?.provenance).toEqual({ + provider: 'historical', model: 'old-model', replayState, + }) + }) + + it('strips replay state but preserves provenance when the target uses a different adapter instance', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['historical'], new RecordingAdapter(SCRIPT)) + const target = new RecordingAdapter(SCRIPT) + ctx.llm.registerAdapter(['target'], target) + + for await (const _chunk of ctx.llm.stream({ + provider: 'target', + model: 'new-model', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'old response' }], + provenance: { provider: 'historical', model: 'old-model', replayState: { private: 'state' } }, + }], + })) { /* drain */ } + + expect(target.lastOptions?.messages[0]?.provenance).toEqual({ provider: 'historical', model: 'old-model' }) + }) + + it('preserves immutability while stripping replay state from frozen requests', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['historical'], new RecordingAdapter(SCRIPT)) + const target = new RecordingAdapter(SCRIPT) + ctx.llm.registerAdapter(['target'], target) + const options = Object.freeze({ + provider: 'target', + model: 'new-model', + messages: [{ + role: 'assistant' as const, + content: [{ type: 'text' as const, text: 'old response' }], + provenance: { provider: 'historical', model: 'old-model', replayState: { private: 'state' } }, + }], + }) + + for await (const _chunk of ctx.llm.stream(options)) { /* drain */ } + + expect(target.lastOptions).not.toBe(options) + expect(Object.isFrozen(target.lastOptions)).toBe(true) + expect(target.lastOptions?.messages[0]?.provenance).toEqual({ provider: 'historical', model: 'old-model' }) + }) + it('creates LlmError with a code for programmatic handling', () => { const err = new LlmError('something went wrong', 'CUSTOM_CODE') expect(err).toBeInstanceOf(Error) @@ -104,9 +192,9 @@ describe('LlmService', () => { await ctx.plugin(LlmService) const dispose = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.models()).toEqual(['m1']) + expect(ctx.llm.providers()).toEqual(['m1']) dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) it('rejects duplicate adapter registration with DUPLICATE_ADAPTER code', async () => { @@ -123,19 +211,30 @@ describe('LlmService', () => { } }) + it('rejects empty and internally duplicated provider registrations atomically', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const adapter = new ScriptedAdapter(SCRIPT) + + expect(() => ctx.llm.registerAdapter([], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) + expect(() => ctx.llm.registerAdapter([''], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) + expect(() => ctx.llm.registerAdapter(['first', 'first'], adapter)).toThrow(expect.objectContaining({ code: 'DUPLICATE_ADAPTER' })) + expect(ctx.llm.providers()).toEqual([]) + }) + it('re-registers a model after its prior registration is disposed', async () => { const ctx = new Context() await ctx.plugin(LlmService) const dispose = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.models()).toEqual(['m1']) + expect(ctx.llm.providers()).toEqual(['m1']) dispose() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) // The duplicate check is not wedged: the same model registers cleanly again. const disposeAgain = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.models()).toEqual(['m1']) + expect(ctx.llm.providers()).toEqual(['m1']) disposeAgain() - expect(ctx.llm.models()).toEqual([]) + expect(ctx.llm.providers()).toEqual([]) }) }) 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 757ba03aac..d842c2d52d 100644 --- a/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts +++ b/packages/session-persistence/session-persistence-jsonl/tests/jsonl.spec.ts @@ -137,7 +137,7 @@ describe('SessionPersistenceJsonl: durability and crash semantics', () => { { type: 'step/start', seq: 1, time: 2, data: { turn: 1, step: 1 } }, { type: 'assistant/chunk', seq: 2, time: 3, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'he' } } }, { type: 'assistant/chunk', seq: 3, time: 4, data: { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'llo' } } }, - { type: 'assistant/message', seq: 4, time: 5, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'hello' }] }, surfaceOp: 'append', sourceEventSeqs: [2, 3] }, + { type: 'assistant/message', seq: 4, time: 5, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'hello' }], provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: 'append', sourceEventSeqs: [2, 3] }, { type: 'step/end', seq: 5, time: 6, data: { turn: 1, step: 1 } }, { type: 'turn/end', seq: 6, time: 7, data: { turn: 1, reason: { kind: 'completed' } } }, ] 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..72498d71f8 100644 --- a/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts +++ b/packages/session-persistence/session-persistence-sqlite/tests/sqlite.spec.ts @@ -466,7 +466,7 @@ describe('surface field round-trip', () => { const session = ctx.sessions.create(SessionId('roundtrip-surface')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [0] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [0] }) session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) await ctx.parallel('session/flush', session) const loaded = await ctx.sessionPersistence.load(SessionId('roundtrip-surface')) diff --git a/packages/session-persistence/session-persistence/tests/contract.ts b/packages/session-persistence/session-persistence/tests/contract.ts index 789aa72c91..ac5b33e637 100644 --- a/packages/session-persistence/session-persistence/tests/contract.ts +++ b/packages/session-persistence/session-persistence/tests/contract.ts @@ -36,7 +36,7 @@ export function oneTurnLog(): SessionEvent[] { { type: 'turn/start', seq: 0, time: 1, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } } }, { type: 'user/message', seq: 1, time: 2, data: { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, surfaceOp: 'append' }, { type: 'step/start', seq: 2, time: 3, data: { turn: 1, step: 1 } }, - { type: 'assistant/message', seq: 3, time: 4, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'hello' }] }, surfaceOp: 'append' }, + { type: 'assistant/message', seq: 3, time: 4, data: { turn: 1, step: 1, content: [{ type: 'text', text: 'hello' }], provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: 'append' }, { type: 'step/end', seq: 4, time: 5, data: { turn: 1, step: 1 } }, { type: 'turn/end', seq: 5, time: 6, data: { turn: 1, reason: { kind: 'completed' } } }, ] @@ -142,7 +142,7 @@ export function runPersistenceContract(name: string, make: () => Promise startInProcessRun(request, {}), }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent, adapter, disposeProvider } } diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index 0005246523..f685490acd 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -24,7 +24,7 @@ async function setup(script: Script) { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) ctx.llm.registerAdapter(['mock'], new MockAdapter(script)) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent } } diff --git a/packages/subagent/subagent-spawn/tests/harness.ts b/packages/subagent/subagent-spawn/tests/harness.ts index e4ee2e6ab7..ac02b7abf9 100644 --- a/packages/subagent/subagent-spawn/tests/harness.ts +++ b/packages/subagent/subagent-spawn/tests/harness.ts @@ -31,7 +31,7 @@ export async function spawnHarness(workdir: string): Promise { await ctx.plugin(ToolRegistry) await ctx.plugin(AgentRegistry) await ctx.plugin(AgentLoop, { agents: [] }) - await ctx.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await ctx.plugin(LlmDeepSeek) await ctx.plugin(LocalBashExecutor, { cwd: workdir, timeoutMs: 30_000 }) await ctx.plugin(ToolBash) await ctx.plugin(SubagentService) diff --git a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts index daa032199e..1b278c9748 100644 --- a/packages/subagent/subagent-spawn/tests/spawn.e2e.ts +++ b/packages/subagent/subagent-spawn/tests/spawn.e2e.ts @@ -29,7 +29,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('spawn backend with-key smoke', ( it('a parent delegates to a child that writes a file on disk', async () => { workdir = await mkdtemp(join(tmpdir(), 'dsh-subagent-spawn-e2e-')) ctx = await spawnHarness(workdir) - const parent = ctx.agentLoop.create(AgentId('e2e-parent'), { model: 'deepseek-v4-flash' }) + const parent = ctx.agentLoop.create(AgentId('e2e-parent'), { provider: 'deepseek', model: 'deepseek-v4-flash' }) parent.send([{ type: 'text', text: 'Use the subagent tool to delegate this exact task: "Use the bash tool to write the text ' diff --git a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts index 9e4e489882..5bc9a72fb6 100644 --- a/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts +++ b/packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts @@ -36,7 +36,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent, adapter } } @@ -240,7 +240,7 @@ describe('dsh-subagent-spawn', () => { agentId: AgentId('cwd-parent'), sessionId: SessionId('cwd-parent-session'), meta: { cwd: '/tmp/parent-workspace' }, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent: parentHandle.agent }) await run.result @@ -262,7 +262,7 @@ describe('dsh-subagent-spawn', () => { const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'p' }], parent: parentHandle.agent, - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const result = await run.result expect(result.stopReason).toBe('completed') @@ -318,7 +318,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) const controller = new AbortController() const run = await start(ctx, 'spawn', { prompt: [{ type: 'text', text: 'q' }], @@ -349,7 +349,7 @@ describe('dsh-subagent-spawn', () => { await ctx.plugin(AgentLoop, { agents: [] }) await ctx.plugin(SubagentService) const fiber = await ctx.plugin(spawn, { providerName: 'spawn' }) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) const parentEffects = parent.ctx.fiber.getEffects().length const published: string[] = [] ctx.on('session/created', () => void published.push('session/created')) @@ -444,7 +444,7 @@ describe('dsh-subagent-spawn', () => { const parentHandle = await ctx.agents.create({ agentId: AgentId('doomed-parent'), sessionId: SessionId('doomed-s'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) await parentHandle.dispose() const before = ctx.agents.list().length @@ -467,7 +467,7 @@ describe('dsh-subagent-spawn', () => { const parentHandle = await ctx.agents.create({ agentId: AgentId('setup-race-parent'), sessionId: SessionId('setup-race-parent-session'), - agentOptions: { model: 'mock' }, + agentOptions: { provider: 'mock', model: 'mock' }, }) const published: string[] = [] ctx.on('session/created', () => void published.push('session/created')) diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index d07e6726dd..8696992eba 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -102,8 +102,9 @@ export const Config: z = z.object({ // present — the request would carry `agentOptions: {}` and the presence // check in execute() could never be false through config. agentOptions: z.object({ + provider: z.string(), model: z.string(), - }).default(undefined as unknown as { model: string }), + }).default(undefined as unknown as { provider: string; model: string }), persona: z.string(), // A schemastery object materializes {} (with [] for nested arrays) when the // key is omitted — for toolFilter that would mean an EMPTY ALLOW-LIST, i.e. diff --git a/packages/support/invariants/tests/invariants.spec.ts b/packages/support/invariants/tests/invariants.spec.ts index a1e824524b..c43100e602 100644 --- a/packages/support/invariants/tests/invariants.spec.ts +++ b/packages/support/invariants/tests/invariants.spec.ts @@ -48,7 +48,7 @@ describe('session-log invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) session.append('step/start', { turn: 1, step: 1 }) session.append('assistant/chunk', { turn: 1, step: 1, chunk: { type: 'text-delta', index: 0, text: 'h' } }) - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'echo', arguments: '{}' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'tool-call', id: CallId('c1'), name: 'echo', arguments: '{}' }] }, { surfaceOp: 'append' }) session.append('tool/call', { turn: 1, step: 1, callId: CallId('c1'), name: 'echo', arguments: '{}' }) session.append('tool/result', { turn: 1, step: 1, callId: CallId('c1'), content: [{ type: 'text', text: 'ok' }], isError: false }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 1 }) @@ -195,7 +195,7 @@ describe('session-log invariants', () => { expect(() => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - session.append('assistant/message', { turn: 1, step: 1, content: [ + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [ { type: 'tool-call', id: CallId('crashed'), name: 'bash', arguments: '{}' }, ] }, { surfaceOp: 'append' }) session.append('tool/result', { @@ -251,10 +251,10 @@ describe('session-log invariants', () => { expect(() => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 1 }) session.append('step/start', { turn: 1, step: 2 }) - session.append('assistant/message', { turn: 1, step: 2, content: [] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [] }, { surfaceOp: 'append' }) session.append('step/end', { turn: 1, step: 2 }) session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) session.append('turn/start', { turn: 2, trigger: { kind: 'message', source: { kind: 'user' } } }) @@ -316,7 +316,7 @@ describe('session-log invariants', () => { const session = ctx.sessions.create() session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) - expect(() => session.append('assistant/message', { turn: 1, step: 2, content: [] }, { surfaceOp: 'append' })) + expect(() => session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 2, content: [] }, { surfaceOp: 'append' })) .toThrow(/open is turn 1\/step 1/) }) }) @@ -475,7 +475,7 @@ describe('surface invariants', () => { session.append('step/start', { turn: 1, step: 1 }) expect(() => { session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) }).not.toThrow() }) @@ -485,7 +485,7 @@ describe('surface invariants', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('step/start', { turn: 1, step: 1 }) session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // no throw — well-formed replace op }) @@ -494,7 +494,7 @@ describe('surface invariants', () => { const session = ctx.sessions.create() session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [] }) }).toThrow(InvariantError) }) @@ -504,7 +504,7 @@ describe('surface invariants', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1, 1] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1, 1] }) }).toThrow(/must not contain duplicates/) }) @@ -515,7 +515,7 @@ describe('surface invariants', () => { // The next event is seq 1. Referencing its own seq fails on "must reference // earlier events" (the check order is: earlier first, then unknown). expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) }).toThrow(/must reference earlier/) }) @@ -527,7 +527,7 @@ describe('surface invariants', () => { session.append('step/start', { turn: 1, step: 1 }) // seqs so far: 0, 1. The next event at seq 2 references seq 1 → valid. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [1] }) }).not.toThrow() }) @@ -536,7 +536,7 @@ describe('surface invariants', () => { const session = ctx.sessions.create() session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [99] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [99] }) }).toThrow(/must reference earlier/) }) @@ -561,7 +561,7 @@ describe('surface invariants', () => { // is seq 3 (log.length). Reference seq 2: passes earlier (2 < 3) but not // in knownSeqs ({0, 1, 3} — gap at 2). expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: 'append', sourceEventSeqs: [2] }) }).toThrow(/unknown seq 2/) }) @@ -574,7 +574,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3 // Reversed range: start seq 3 is at a later surface position than end seq 2. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 2 }, sourceEventSeqs: [2, 3] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 2 }, sourceEventSeqs: [2, 3] }) }).toThrow(/is after end seq 2 .* on the surface/) }) @@ -587,7 +587,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3 // Replace shadows surface nodes [2, 3] but records provenance for only [2]. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'sum' }] }, { surfaceOp: { op: 'replace', start: 2, end: 3 }, sourceEventSeqs: [2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'sum' }] }, { surfaceOp: { op: 'replace', start: 2, end: 3 }, sourceEventSeqs: [2] }) }).toThrow(/must include every shadowed surface node; missing 3/) }) @@ -599,7 +599,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3 expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'sum' }] }, { surfaceOp: { op: 'replace', start: 2, end: 3 }, sourceEventSeqs: [2, 3] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'sum' }] }, { surfaceOp: { op: 'replace', start: 2, end: 3 }, sourceEventSeqs: [2, 3] }) }).not.toThrow() }) @@ -611,7 +611,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // seq 1 (step/start) is a real earlier event but never entered the surface. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 1, end: 2 }, sourceEventSeqs: [1, 2] }) }).toThrow(/start seq 1 is not on the surface/) }) @@ -623,7 +623,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // start (2) is on the surface but end (99) never entered it. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 99 }, sourceEventSeqs: [2] }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 99 }, sourceEventSeqs: [2] }) }).toThrow(/end seq 99 is not on the surface/) }) @@ -636,11 +636,11 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'b' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 3 // Replace node 2 (position 0) with seq 4 — surface is now [4, 3], so seq 4 // precedes seq 3 in linked-list order even though 4 > 3 numerically. - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4 + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4 // A replace with start=3, end=4 passes the seq check (3 <= 4) but is // reversed positionally (3 is at pos 1, 4 is at pos 0). expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 4 }, sourceEventSeqs: [3, 4] }) // seq 5 + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 3, end: 4 }, sourceEventSeqs: [3, 4] }) // seq 5 }).toThrow(/is after end seq 4 .* on the surface/) }) @@ -655,9 +655,9 @@ describe('surface invariants', () => { // head seq (4) is numerically GREATER than the tail seq (3): the surface is // not seq-ordered. A replace spanning start=4 (pos 0) … end=3 (pos 1) is // valid positionally and must be accepted even though start seq > end seq. - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4 + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 's' }] }, { surfaceOp: { op: 'replace', start: 2, end: 2 }, sourceEventSeqs: [2] }) // seq 4 expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 4, end: 3 }, sourceEventSeqs: [4, 3] }) // seq 5 + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 4, end: 3 }, sourceEventSeqs: [4, 3] }) // seq 5 }).not.toThrow() }) @@ -669,7 +669,7 @@ describe('surface invariants', () => { session.append('user/message', { content: [{ type: 'text', text: 'a' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) // seq 2 // A replace with no sourceEventSeqs records no provenance for the node it shadows. expect(() => { - session.append('assistant/message', { turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 2 } }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [] }, { surfaceOp: { op: 'replace', start: 2, end: 2 } }) }).toThrow(/must include every shadowed surface node; missing 2/) }) @@ -680,7 +680,7 @@ describe('surface invariants', () => { { type: 'step/start' as const, seq: 1, time: 0, data: { turn: 1, step: 1 } }, { type: 'user/message' as const, seq: 2, time: 0, data: { content: [{ type: 'text' as const, text: 'a' }], source: { kind: 'user' as const } }, surfaceOp: 'append' as const }, { type: 'user/message' as const, seq: 3, time: 0, data: { content: [{ type: 'text' as const, text: 'b' }], source: { kind: 'user' as const } }, surfaceOp: 'append' as const }, - { type: 'assistant/message' as const, seq: 4, time: 0, data: { turn: 1, step: 1, content: [{ type: 'text' as const, text: 'sum' }] }, surfaceOp: { op: 'replace' as const, start: 2, end: 3 }, sourceEventSeqs: [2] }, + { type: 'assistant/message' as const, seq: 4, time: 0, data: { turn: 1, step: 1, content: [{ type: 'text' as const, text: 'sum' }], provenance: { provider: 'mock', model: 'mock' } }, surfaceOp: { op: 'replace' as const, start: 2, end: 3 }, sourceEventSeqs: [2] }, ] expect(() => ctx.sessions.create(undefined, { seed: badSeed })).toThrow(/must include every shadowed surface node; missing 3/) }) @@ -715,7 +715,7 @@ describe('request-reconstruction cross-check (llm/stream)', () => { session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) const boundary = session.deriveMessages() session.append('step/start', { turn: 1, step: 1 }) - session.append('request/header', { header: { config: { model: 'm' } }, reason: 'initial' }) + session.append('request/header', { header: { config: { provider: 'mock', model: 'm' } }, reason: 'initial' }) return { ctx, session, boundary } } @@ -818,7 +818,7 @@ describe('request cross-check ordering (prepend)', () => { session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('user/message', { content: [{ type: 'text', text: 'hi' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) session.append('step/start', { turn: 1, step: 1 }) - session.append('request/header', { header: { config: { model: 'm' } }, reason: 'initial' }) + session.append('request/header', { header: { config: { provider: 'mock', model: 'm' } }, reason: 'initial' }) const divergent = Object.freeze({ model: 'm', diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index 3b4e8c5fee..19d5824e0f 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -214,7 +214,7 @@ describe('installLlmReplay (through the real waterfall)', () => { await ctx.plugin(LlmService) // No adapter registered for 'm' — replay must not reach it. installLlmReplay(ctx, { file }) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('serves the Nth call the Nth derived entry (positional)', async () => { @@ -227,8 +227,8 @@ describe('installLlmReplay (through the real waterfall)', () => { const ctx = new Context() await ctx.plugin(LlmService) installLlmReplay(ctx, { file }) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(second) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(second) }) it('replays a sidecar throw-entry as an LlmError with code/status, after its prefix chunks', async () => { @@ -244,7 +244,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const seen: StreamChunk[] = [] await expect((async () => { - for await (const c of ctx.llm.stream({ model: 'm', messages: [] })) seen.push(c) + for await (const c of ctx.llm.stream({ provider: 'm', model: 'm', messages: [] })) seen.push(c) })()).rejects.toMatchObject({ message: 'unauthorized', code: 'AUTH', status: 401 }) expect(seen).toEqual(partial) }) @@ -258,7 +258,7 @@ describe('installLlmReplay (through the real waterfall)', () => { installLlmReplay(ctx, { file, overrideFile }) const controller = new AbortController() - const iterator = ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() + const iterator = ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() // Deterministically consume the two pre-hang chunks (no sleep), then abort // and assert the next pull rejects — event-driven, per the no-sleeps rule. expect((await iterator.next()).value).toMatchObject({ type: 'block-start' }) @@ -272,8 +272,8 @@ describe('installLlmReplay (through the real waterfall)', () => { const ctx = new Context() await ctx.plugin(LlmService) installLlmReplay(ctx, { file }) - await drain(ctx.llm.stream({ model: 'm', messages: [] })) - await expect(drain(ctx.llm.stream({ model: 'm', messages: [] }))).rejects.toThrow(/exhausted/) + await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] })) + await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).rejects.toThrow(/exhausted/) }) it('aborts mid-replay when the signal is already set', async () => { @@ -283,7 +283,7 @@ describe('installLlmReplay (through the real waterfall)', () => { installLlmReplay(ctx, { file }) const controller = new AbortController() controller.abort() - await expect(drain(ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal }))) + await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal }))) .rejects.toThrow('aborted') }) @@ -305,11 +305,11 @@ describe('installLlmReplay (through the real waterfall)', () => { }, { inject: ['llm'] })) // While installed, replay short-circuits to the derived fixture ('hi'). - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) await fiber.dispose() // After dispose the listener is gone; the call reaches the real adapter. - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))) .toEqual([{ type: 'finish', reason: { kind: 'stop' } }]) }) @@ -321,7 +321,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const ctx = new Context() await ctx.plugin(LlmService) installLlmReplay(ctx, { file, overrideFile }) - await expect(drain(ctx.llm.stream({ model: 'm', messages: [] }))) + await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))) .rejects.toThrow(/llm-replay replay entry/) }) @@ -333,7 +333,7 @@ describe('installLlmReplay (through the real waterfall)', () => { await ctx.plugin(LlmService) installLlmReplay(ctx, { file, overrideFile }) const controller = new AbortController() - const iterator = ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() + const iterator = ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() // Consume the two pre-hang chunks, then start the third pull so the generator // is parked inside the await (signal NOT yet aborted — exercises the // addEventListener('abort') registration), and only THEN abort. @@ -359,7 +359,7 @@ describe('installLlmReplay (through the real waterfall)', () => { controller.abort() // Already aborted: the throw-entry's prefix loop surfaces 'aborted' before // it can reach the recorded LlmError. - await expect(drain(ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal }))) + await expect(drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal }))) .rejects.toThrow('aborted') }) @@ -373,7 +373,7 @@ describe('installLlmReplay (through the real waterfall)', () => { const controller = new AbortController() controller.abort() // The two pre-hang chunks still flow; the abort surfaces at the await. - const iterator = ctx.llm.stream({ model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() + const iterator = ctx.llm.stream({ provider: 'm', model: 'm', messages: [], signal: controller.signal })[Symbol.asyncIterator]() await iterator.next() await iterator.next() await expect(iterator.next()).rejects.toThrow('aborted') @@ -509,7 +509,7 @@ describe('installLlmReplay (per-session keying)', () => { ] const live = (id: string): GenerateOptions => - ({ model: 'm', messages: [], sessionId: id as NonNullable }) + ({ provider: 'm', model: 'm', messages: [], sessionId: id as NonNullable }) it('routes each live session to its own script by FIRST-CALL order', async () => { const parentFile = writeSession('session.jsonl', { id: 'rec-parent', createdAt: 100 }, [TEXT_CHUNKS]) @@ -546,7 +546,7 @@ describe('installLlmReplay (per-session keying)', () => { await ctx.plugin(LlmService) installLlmReplay(ctx, { file: parentFile }) // No sessionId at all — the legacy single-session path. - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('fails loud when more distinct live sessions call than were recorded', async () => { @@ -585,7 +585,7 @@ describe('apply (the plugin entry)', () => { const ctx = new Context() await ctx.plugin(LlmService) apply(ctx, { file }) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('falls back to $DSH_SNAPSHOT_FILE / $DSH_SNAPSHOT_OVERRIDE when config is empty', async () => { @@ -597,7 +597,7 @@ describe('apply (the plugin entry)', () => { const ctx = new Context() await ctx.plugin(LlmService) apply(ctx) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('uses only the file when no override path is configured or in the env', async () => { @@ -607,7 +607,7 @@ describe('apply (the plugin entry)', () => { const ctx = new Context() await ctx.plugin(LlmService) apply(ctx) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) it('throws when no fixture path is given by config or env', async () => { @@ -637,7 +637,7 @@ describe('apply (the plugin entry)', () => { await ctx.plugin(LlmService) apply(ctx, { file, childFiles: [childFile] }) const live = (id: string): GenerateOptions => - ({ model: 'm', messages: [], sessionId: id as NonNullable }) + ({ provider: 'm', model: 'm', messages: [], sessionId: id as NonNullable }) expect(await drain(ctx.llm.stream(live('A')))).toEqual(TEXT_CHUNKS) expect(await drain(ctx.llm.stream(live('B')))).toEqual(childSecond) }) @@ -657,7 +657,7 @@ describe('apply (the plugin entry)', () => { await ctx.plugin(LlmService) apply(ctx) const live = (id: string): GenerateOptions => - ({ model: 'm', messages: [], sessionId: id as NonNullable }) + ({ provider: 'm', model: 'm', messages: [], sessionId: id as NonNullable }) expect(await drain(ctx.llm.stream(live('A')))).toEqual(TEXT_CHUNKS) expect(await drain(ctx.llm.stream(live('B')))).toEqual(childChunks) }) @@ -669,6 +669,6 @@ describe('apply (the plugin entry)', () => { const ctx = new Context() await ctx.plugin(LlmService) apply(ctx) - expect(await drain(ctx.llm.stream({ model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) + expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) }) diff --git a/packages/todo/tool-todo/tests/integration.spec.ts b/packages/todo/tool-todo/tests/integration.spec.ts index 739367a699..eaea7769e6 100644 --- a/packages/todo/tool-todo/tests/integration.spec.ts +++ b/packages/todo/tool-todo/tests/integration.spec.ts @@ -64,7 +64,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Plan recorded.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-todo'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'plan a two-step task' }]) await waitForIdle(ctx, agent) @@ -92,7 +92,7 @@ describe('todo_write tool through the agent loop', () => { textResponse('Done planning.'), ]) const ctx = await harness(adapter) - const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('it-todo-2'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'plan then update' }]) await waitForIdle(ctx, agent) diff --git a/packages/ui/acp-agent/README.md b/packages/ui/acp-agent/README.md index d81c9cc091..597b1356d8 100644 --- a/packages/ui/acp-agent/README.md +++ b/packages/ui/acp-agent/README.md @@ -24,8 +24,9 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron | Key | Default | Routed to | |---|---|---| +| `provider` | (required) | the provider route for each per-session agent the bridge creates | | `model` | (required) | the per-session agent template the bridge creates agents from | -| `persona` | — | the deployment persona template (may reference `{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` | +| `persona` | — | the deployment persona template (may reference `{{provider}}`/`{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | diff --git a/packages/ui/acp-agent/src/index.ts b/packages/ui/acp-agent/src/index.ts index 43186dfcb0..d912f4ed86 100644 --- a/packages/ui/acp-agent/src/index.ts +++ b/packages/ui/acp-agent/src/index.ts @@ -17,8 +17,8 @@ * The leaf supplies the swappable backends: the LLM adapter (`llm-deepseek` for * the real model, `llm-replay` for keyless snapshot replay), the bash executor * (`bash-local`), and any optional product tools it wants to expose. This app's - * {@link Config} (model, system prompt, persistence root) routes each value to - * where it is wired — model/prompt onto the bridge's per-session agent + * {@link Config} (provider/model, system prompt, persistence root) routes each value to + * where it is wired — provider/model/prompt onto the bridge's per-session agent * template, the root onto the JSONL backend. * * Plugin export shape: named `name`/`Config`/`apply`, NO default export — the @@ -41,7 +41,7 @@ import UserInteractionService from '@deepseek-ai/dsh-user-interaction' export const name = 'acp-agent' /** - * App config: the swappable per-deployment values. `model` configures the + * App config: the swappable per-deployment values. `provider` and `model` configure the * agent template the ACP bridge creates each session's agent from (NOT a * pre-created agent — ACP creates agents at `session/new`); `persona` is the * deployment persona (forwarded to the system-prompt plugin); `toolOrder` is @@ -50,6 +50,8 @@ export const name = 'acp-agent' * through agent-core); `persistenceRoot` is the JSONL backend's directory. */ export interface Config { + /** Provider route for ACP-created agents. */ + provider: string /** Model name for ACP-created agents (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ @@ -68,6 +70,7 @@ export interface Config { // the common fields would make two small app contracts depend on a new facade. /* jscpd:ignore-start */ export const Config: z = z.object({ + provider: z.string().required(), model: z.string().required(), persona: z.string(), // The array default is forced to undefined: ABSENT means "lexicographic @@ -87,7 +90,7 @@ export const Config: z = z.object({ * NO agents (its `agents` list defaults to `[]`) and carries the deployment * `persona`; the JSONL backend persists under `persistenceRoot`; the ACP * bridge owns stdout for JSON-RPC and creates one agent per `session/new` - * from `model`. No logger, no `hmr` — stdout stays pure. + * from the provider/model pair. No logger, no `hmr` — stdout stays pure. */ export function apply(ctx: Context, config: Config): void { ctx.plugin(agentCore, { @@ -98,5 +101,5 @@ export function apply(ctx: Context, config: Config): void { }) ctx.plugin(UserInteractionService) ctx.plugin(SessionPersistenceJsonl, { root: config.persistenceRoot ?? './.sessions' }) - ctx.plugin(acp, { model: config.model }) + ctx.plugin(acp, { provider: config.provider, model: config.model }) } diff --git a/packages/ui/acp-agent/tests/acp-agent.spec.ts b/packages/ui/acp-agent/tests/acp-agent.spec.ts index 537155429c..1cc34b3b5f 100644 --- a/packages/ui/acp-agent/tests/acp-agent.spec.ts +++ b/packages/ui/acp-agent/tests/acp-agent.spec.ts @@ -69,7 +69,7 @@ async function withIsolatedSkillHomes(run: () => Promise): Promise { describe('dsh-acp-agent composition', () => { it('brings up the spine + persistence + the ACP bridge', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-acp-agent-test', skills: await isolatedSkillsConfig() }) + const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-acp-agent-test', skills: await isolatedSkillsConfig() }) expect(ctx.get('agents')).toBeDefined() expect(ctx.get('sessions')).toBeDefined() expect(ctx.get('sessionPersistence')).toBeDefined() @@ -88,7 +88,7 @@ describe('dsh-acp-agent composition', () => { // persistenceRoot, so the runtime fallback is the one that fires. const ctx = new Context() // No persona: covers the omitted-persona forwarding branch too. - acpAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) + acpAgent.apply(ctx, { provider: 'mock', model: 'mock', skills: await isolatedSkillsConfig() }) await new Promise(resolve => setTimeout(resolve, 50)) expect(ctx.get('sessionPersistence')).toBeDefined() await ctx.fiber.dispose() @@ -97,7 +97,7 @@ describe('dsh-acp-agent composition', () => { it('uses default skill config when apply is called directly without skills', async () => { await withIsolatedSkillHomes(async () => { const ctx = new Context() - acpAgent.apply(ctx, { model: 'mock' }) + acpAgent.apply(ctx, { provider: 'mock', model: 'mock' }) await new Promise(resolve => setTimeout(resolve, 50)) expect(ctx.skills).toBeDefined() expect(await ctx.skills.list()).toEqual([]) @@ -106,7 +106,7 @@ describe('dsh-acp-agent composition', () => { }) it('forwards skill config into agent-core', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) + const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) ctx.skills.register({ name: 'acp-skill', description: 'ACP skill', source: 'runtime', content: 'body' }) expect(JSON.stringify(await composePrefix(ctx))).toContain('- `acp-skill`: ACP...') await ctx.fiber.dispose() @@ -119,6 +119,7 @@ describe('dsh-acp-agent composition', () => { it('forwards toolOrder through agent-core to the system-prompt assembly', async () => { const ctx = await mount({ + provider: 'mock', model: 'mock', toolOrder: ['zulu', TOOL_ORDER_REST], persistenceRoot: '/tmp/dsh-acp-agent-test-tool-order', diff --git a/packages/ui/acp-agent/tests/built-bin.e2e.ts b/packages/ui/acp-agent/tests/built-bin.e2e.ts index de4612a40a..6bf9bfcd30 100644 --- a/packages/ui/acp-agent/tests/built-bin.e2e.ts +++ b/packages/ui/acp-agent/tests/built-bin.e2e.ts @@ -92,12 +92,12 @@ async function makeConsumer(): Promise { ' name: \'@deepseek-ai/dsh-llm-deepseek\'', ' config:', ' apiKey: !!js process.env.DEEPSEEK_API_KEY', - ' models: [deepseek-v4-flash]', '- id: bash', ' name: \'@deepseek-ai/dsh-bash-local\'', '- id: acp-agent', ' name: \'@deepseek-ai/dsh-acp-agent\'', ' config:', + ' provider: deepseek', ' model: deepseek-v4-flash', ' persona: \'test agent\'', '', diff --git a/packages/ui/acp-agent/tests/load-path.e2e.ts b/packages/ui/acp-agent/tests/load-path.e2e.ts index ec251a6e6b..b97f6c0874 100644 --- a/packages/ui/acp-agent/tests/load-path.e2e.ts +++ b/packages/ui/acp-agent/tests/load-path.e2e.ts @@ -47,12 +47,12 @@ const CORDIS_YML = ` name: '@deepseek-ai/dsh-llm-deepseek' config: apiKey: !!js process.env.DEEPSEEK_API_KEY - models: [deepseek-v4-flash] - id: bash name: '@deepseek-ai/dsh-bash-local' - id: acp-agent name: '@deepseek-ai/dsh-acp-agent' config: + provider: deepseek model: deepseek-v4-flash persona: 'You are a test agent.' ` diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index f4947e5d25..9496d40cf3 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -14,6 +14,7 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` | Key | Default | Meaning | |---|---|---| +| `provider` | — | Provider route for created agents (must have a registered adapter). | | `model` | — | Model name for created agents (must have a registered adapter). | (No persona key: `dsh-system-prompt`'s own `persona` config supplies the global default section, so ACP-created agents render it without the bridge carrying prompt text. An agent-scoped same-name section may still shadow that default.) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index a3fdc38f97..7c1a2c07d6 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -248,6 +248,8 @@ function stringArrayContent( /** Plugin config: the agent template ACP sessions are created from. */ export interface AcpConfig { + /** Provider route for created agents. */ + provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string /** @@ -261,6 +263,7 @@ export interface AcpConfig { } export const Config: Schema = Schema.object({ + provider: Schema.string(), model: Schema.string(), }) @@ -1015,11 +1018,12 @@ export function apply(ctx: Context, config: AcpConfig): void { * Build per-agent options from the plugin config, omitting absent fields * (exactOptionalPropertyTypes: never assign `undefined` to an optional key). * Exported for unit coverage of both the present and absent branches. - * @param config - the plugin config carrying the optional model name. - * @returns the per-agent options, with `model` present only when configured. + * @param config - the plugin config carrying the optional provider/model target. + * @returns the per-agent options, with each configured target field present. */ -export function agentOptions(config: AcpConfig): { model?: string } { +export function agentOptions(config: AcpConfig): { provider?: string; model?: string } { return { + ...config.provider !== undefined ? { provider: config.provider } : {}, ...config.model !== undefined ? { model: config.model } : {}, } } diff --git a/packages/ui/acp/tests/dispose.spec.ts b/packages/ui/acp/tests/dispose.spec.ts index f02a7b0649..02d7045379 100644 --- a/packages/ui/acp/tests/dispose.spec.ts +++ b/packages/ui/acp/tests/dispose.spec.ts @@ -230,10 +230,10 @@ describe('acp bridge — disposal & HMR safety', () => { // queryable, with its session still in the store. const harness = await makeBridgeHarness({ storageDir, script: [] }) const handleA = await harness.ctx.agents.create({ - agentId: AgentId('sib-a'), sessionId: SessionId('sib-a'), agentOptions: { model: 'mock' }, + agentId: AgentId('sib-a'), sessionId: SessionId('sib-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) const handleB = await harness.ctx.agents.create({ - agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { model: 'mock' }, + agentId: AgentId('sib-b'), sessionId: SessionId('sib-b'), agentOptions: { provider: 'mock', model: 'mock' }, }) expect(harness.ctx.agents.get(AgentId('sib-a'))).toBe(handleA.agent) expect(harness.ctx.agents.get(AgentId('sib-b'))).toBe(handleB.agent) @@ -262,7 +262,7 @@ describe('acp bridge — disposal & HMR safety', () => { const harness = await makeBridgeHarness({ storageDir, script: [textResponse('ok')] }) harness.ctx.on('agent/disposed', () => { throw new Error('boom disposed listener') }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('guard-a'), sessionId: SessionId('guard-a'), agentOptions: { model: 'mock' }, + agentId: AgentId('guard-a'), sessionId: SessionId('guard-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) handle.agent.send([{ type: 'text', text: 'go' }]) await handle.agent.whenIdle() @@ -283,7 +283,7 @@ describe('acp bridge — disposal & HMR safety', () => { // observe the same quiescence boundary. const harness = await makeBridgeHarness({ storageDir, script: ['hang'] }) const handle = await harness.ctx.agents.create({ - agentId: AgentId('conc-a'), sessionId: SessionId('conc-a'), agentOptions: { model: 'mock' }, + agentId: AgentId('conc-a'), sessionId: SessionId('conc-a'), agentOptions: { provider: 'mock', model: 'mock' }, }) // Drive a turn that hangs in the model stream, so the loop is mid-turn when // disposed — its exit runs a final session/flush we can gate to hold the diff --git a/packages/ui/acp/tests/edges.spec.ts b/packages/ui/acp/tests/edges.spec.ts index e86fb9fc94..de3a7a6f03 100644 --- a/packages/ui/acp/tests/edges.spec.ts +++ b/packages/ui/acp/tests/edges.spec.ts @@ -27,7 +27,7 @@ describe('acp bridge — demux & config edges', () => { await harness.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const before = harness.updates.length - const { agent: foreign } = await harness.ctx.agents.create({ agentId: AgentId('foreign'), sessionId: SessionId('foreign-session'), agentOptions: { model: 'mock' } }) + const { agent: foreign } = await harness.ctx.agents.create({ agentId: AgentId('foreign'), sessionId: SessionId('foreign-session'), agentOptions: { provider: 'mock', model: 'mock' } }) foreign.send([{ type: 'text', text: 'hi' }]) await foreign.whenIdle() await new Promise(r => setTimeout(r, 10)) diff --git a/packages/ui/acp/tests/harness.ts b/packages/ui/acp/tests/harness.ts index a24c7aa145..1a9672cafb 100644 --- a/packages/ui/acp/tests/harness.ts +++ b/packages/ui/acp/tests/harness.ts @@ -155,7 +155,7 @@ export interface BridgeHarness { * The bridge's `apply` receives the agent-side `Stream` via `config.stream`; * the test holds the `ClientSideConnection`. * - * Pass `config: { model: undefined }` to override the default `model: 'mock'` + * Pass `config: { model: undefined }` to override the default mock target * (the model key is dropped entirely when explicitly undefined). */ export async function makeBridgeHarness(options: { @@ -282,10 +282,11 @@ export async function makeBridgeHarness(options: { }) // Wire the bridge (agent side) and the client (test side). The test config - // can override `model` (including to undefined): default to 'mock' unless the - // caller explicitly set the key (even to undefined), so a `{ model: undefined }` - // override means "no model at all". + // can override either route field (including to undefined). Default both to + // `mock` unless the caller explicitly set that key, so `{ model: undefined }` + // still means "no model at all". const cfg: AcpConfig = { stream: agentStream, ...options.config } + if (!(options.config && 'provider' in options.config)) cfg.provider = 'mock' if (!(options.config && 'model' in options.config)) cfg.model = 'mock' // Mount the bridge the way production does: as a cordis PLUGIN (via // `ctx.plugin` with the real `inject`), NOT `AcpPlugin.apply(ctx, cfg)` diff --git a/packages/ui/acp/tests/stream-update.spec.ts b/packages/ui/acp/tests/stream-update.spec.ts index 0a9cf3e82e..224acce239 100644 --- a/packages/ui/acp/tests/stream-update.spec.ts +++ b/packages/ui/acp/tests/stream-update.spec.ts @@ -804,5 +804,6 @@ describe('agentOptions', () => { it('includes only the fields present in config', () => { expect(agentOptions({})).toEqual({}) expect(agentOptions({ model: 'm' })).toEqual({ model: 'm' }) + expect(agentOptions({ provider: 'p', model: 'm' })).toEqual({ provider: 'p', model: 'm' }) }) }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 007bd1a5f1..ed256c2828 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -4,7 +4,7 @@ The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC serve ## Wiring -`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`) and demuxes `subagent/end` through the registry. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`) from the `initialize.provider`+`initialize.model` pair and demuxes `subagent/end` through the registry. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): an already registered adapter for the provider route wins; when the route is `deepseek` and unowned, the plugin mounts `dsh-llm-deepseek` (credentials from `$DEEPSEEK_API_KEY` / `$DEEPSEEK_BASE_URL`); any other unowned provider fails initialization. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 86af6645f3..f96993c6d8 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -26,6 +26,8 @@ import type { JsonRpcTransportPeer } from './transport.ts' export interface InitializeParams { /** Working directory recorded on every SDK-created session's header. */ cwd: string + /** Provider route every SDK-created agent runs on. */ + provider: string /** Model name every SDK-created agent runs on (see {@link HarnessSdkServer.initialize} for adapter fallback). */ model: string } @@ -73,6 +75,7 @@ interface SubagentRecord { */ export class HarnessSdkServer { private cwd = process.cwd() + private provider = 'deepseek' private model = 'deepseek' private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() @@ -132,18 +135,20 @@ export class HarnessSdkServer { } /** - * Handle `initialize`: record the SDK deployment facts (cwd, model) and, when - * no registered adapter serves `params.model`, mount the DeepSeek adapter for - * it (credentials from `$DEEPSEEK_API_KEY`/`$DEEPSEEK_BASE_URL`) — a config - * that already registered an adapter for the model wins. + * Handle `initialize`: record the SDK deployment facts and, when provider + * `deepseek` has no registered owner, mount the native DeepSeek adapter + * (credentials from `$DEEPSEEK_API_KEY`/`$DEEPSEEK_BASE_URL`). Other missing + * providers fail without guessing an implementation. * @param params - the SDK handshake parameters. * @returns the server identity for the handshake. */ async initialize(params: InitializeParams): Promise { this.cwd = resolve(params.cwd) + this.provider = params.provider this.model = params.model - if (!this.llmFiber && !this.hasAdapterFor(this.model)) { - this.llmFiber = await this.ctx.plugin(LlmDeepSeek, { models: [this.model] }) + if (!this.hasAdapterFor(this.provider)) { + if (this.provider !== 'deepseek') throw new Error(`no adapter registered for provider "${this.provider}"`) + this.llmFiber = await this.ctx.plugin(LlmDeepSeek, {}) } return { serverInfo: { name: 'deepseek-harness-sdk-runtime', version: '0.0.1' } } } @@ -258,7 +263,7 @@ export class HarnessSdkServer { agentId: AgentId(sessionId), sessionId: SessionId(sessionId), meta: { cwd: this.cwd }, - agentOptions: { model: this.model }, + agentOptions: { provider: this.provider, model: this.model }, }) const rec: SessionRecord = { handle, lastTurnEnd: undefined, activePrompt: false } this.sessions.set(sessionId, rec) @@ -270,7 +275,7 @@ export class HarnessSdkServer { return reason.kind === 'completed' ? 'ok' : 'error' } - private hasAdapterFor(model: string): boolean { - return this.ctx.get('llm')?.models().includes(model) ?? false + private hasAdapterFor(provider: string): boolean { + return this.ctx.get('llm')?.providers().includes(provider) ?? false } } diff --git a/packages/ui/jsonrpc/tests/plugin-apply.spec.ts b/packages/ui/jsonrpc/tests/plugin-apply.spec.ts index 8f4a504264..1acd2f2edd 100644 --- a/packages/ui/jsonrpc/tests/plugin-apply.spec.ts +++ b/packages/ui/jsonrpc/tests/plugin-apply.spec.ts @@ -167,7 +167,7 @@ describe('dsh-jsonrpc plugin apply', () => { vi.stubEnv('DEEPSEEK_API_KEY', 'test-key') const harness = await mountPlugin(storageDir) try { - harness.send({ jsonrpc: '2.0', id: 'init-1', method: 'initialize', params: { cwd: storageDir, model: 'apply-model' } }) + harness.send({ jsonrpc: '2.0', id: 'init-1', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'apply-model' } }) const response = await harness.waitForFrame(frame => frame.id === 'init-1', 'initialize response') expect(response).toEqual({ @@ -189,7 +189,7 @@ describe('dsh-jsonrpc plugin apply', () => { vi.stubEnv('DEEPSEEK_BASE_URL', llmServer.url) const harness = await mountPlugin(storageDir) try { - harness.send({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { cwd: storageDir, model: 'dsagent-model' } }) + harness.send({ jsonrpc: '2.0', id: 1, method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'dsagent-model' } }) await harness.waitForFrame(frame => frame.id === 1, 'initialize response') harness.send({ @@ -256,7 +256,7 @@ describe('dsh-jsonrpc plugin apply', () => { // The plugin fiber is disposed: the transport reads no further frames. const before = harness.frames().length - harness.send({ jsonrpc: '2.0', id: 'after-exit', method: 'initialize', params: { cwd: storageDir, model: 'x' } }) + harness.send({ jsonrpc: '2.0', id: 'after-exit', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'x' } }) await settle() expect(harness.frames().length).toBe(before) } finally { @@ -277,7 +277,7 @@ describe('dsh-jsonrpc plugin apply', () => { expect(harness.outputErrors.map(error => error.message)).toEqual(['flush callback failed']) const before = harness.frames().length - harness.send({ jsonrpc: '2.0', id: 'after-flush-failure', method: 'initialize', params: { cwd: storageDir, model: 'x' } }) + harness.send({ jsonrpc: '2.0', id: 'after-flush-failure', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'x' } }) await settle() expect(harness.frames().length).toBe(before) } finally { @@ -304,7 +304,7 @@ describe('dsh-jsonrpc plugin apply', () => { // The effect disposer shut the server and closed the transport — later // frames are never read — and the exit seam was never touched. const before = harness.frames().length - harness.send({ jsonrpc: '2.0', id: 'probe-2', method: 'initialize', params: { cwd: storageDir, model: 'x' } }) + harness.send({ jsonrpc: '2.0', id: 'probe-2', method: 'initialize', params: { cwd: storageDir, provider: 'deepseek', model: 'x' } }) await settle() expect(harness.frames().length).toBe(before) expect(harness.exits()).toEqual([]) diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 1cde550f2e..28d1eda0f8 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -107,6 +107,7 @@ describe('HarnessSdkServer', () => { const init = await server.handleRequest('initialize', { cwd: storageDir, + provider: 'deepseek', model: 'dsagent-model', }) as { serverInfo: { name: string } } expect(init.serverInfo.name).toBe('deepseek-harness-sdk-runtime') @@ -138,7 +139,7 @@ describe('HarnessSdkServer', () => { agentId: AgentId('orphan-agent'), sessionId: SessionId('orphan-session'), meta: { cwd: storageDir }, - agentOptions: { model: 'dsagent-model' }, + agentOptions: { provider: 'deepseek', model: 'dsagent-model' }, }) orphanHandle.agent.send([{ type: 'text', text: 'outside the sdk session map' }]) await orphanHandle.agent.whenIdle() @@ -241,7 +242,7 @@ describe('HarnessSdkServer', () => { try { const server = new HarnessSdkServer(ctx, new FakeTransport()) - await server.initialize({ cwd: storageDir, model: 'plain-model' }) + await server.initialize({ cwd: storageDir, provider: 'deepseek', model: 'plain-model' }) await server.prompt({ sessionId: 'plain', contentBlocks: [{ type: 'text', text: 'hello' }], @@ -266,13 +267,13 @@ describe('HarnessSdkServer', () => { agentId: AgentId('parent-agent'), sessionId: SessionId('main'), meta: { cwd: storageDir }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) const handle = await ctx.agents.create({ agentId: AgentId('child-agent'), sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', @@ -314,19 +315,19 @@ describe('HarnessSdkServer', () => { agentId: AgentId('fallback-parent-agent'), sessionId: SessionId('fallback-parent'), meta: { cwd: storageDir }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) handle = await ctx.agents.create({ agentId: AgentId('fallback-child-agent'), sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) failedHandle = await ctx.agents.create({ agentId: AgentId('failed-child-agent'), sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, - agentOptions: { model: 'deepseek' }, + agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) const transport = new FakeTransport() const server = new HarnessSdkServer(ctx, transport) @@ -385,20 +386,20 @@ describe('HarnessSdkServer', () => { } }) - it('does not re-register an LLM adapter that already exists', async () => { + it('does not re-register an LLM adapter whose provider already has an owner', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-existing-llm-')) const ctx = await makeHarness(storageDir) vi.stubEnv('DEEPSEEK_API_KEY', 'test-key') - await ctx.plugin(LlmDeepSeek, { models: ['preinstalled-model'] }) + await ctx.plugin(LlmDeepSeek) try { const server = new HarnessSdkServer(ctx, new FakeTransport()) - const inspect = server as unknown as { hasAdapterFor(model: string): boolean } + const inspect = server as unknown as { hasAdapterFor(provider: string): boolean } - expect(inspect.hasAdapterFor('preinstalled-model')).toBe(true) - expect(inspect.hasAdapterFor('missing-model')).toBe(false) - await server.initialize({ cwd: storageDir, model: 'preinstalled-model' }) + expect(inspect.hasAdapterFor('deepseek')).toBe(true) + expect(inspect.hasAdapterFor('missing-provider')).toBe(false) + await server.initialize({ cwd: storageDir, provider: 'deepseek', model: 'preinstalled-model' }) - expect(ctx.get('llm')?.models().filter(model => model === 'preinstalled-model')).toEqual(['preinstalled-model']) + expect(ctx.get('llm')?.providers().filter(provider => provider === 'deepseek')).toEqual(['deepseek']) await server.shutdown() } finally { await ctx.fiber.dispose() @@ -406,17 +407,18 @@ describe('HarnessSdkServer', () => { } }) - it('registers a missing model when an LLM service already exists', async () => { + it('rejects a missing non-DeepSeek provider when an LLM service already exists', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-new-llm-')) const ctx = await makeHarness(storageDir) vi.stubEnv('DEEPSEEK_API_KEY', 'test-key') - await ctx.plugin(LlmDeepSeek, { models: ['other-model'] }) + await ctx.plugin(LlmDeepSeek) try { const server = new HarnessSdkServer(ctx, new FakeTransport()) - await server.initialize({ cwd: storageDir, model: 'new-model' }) + await expect(server.initialize({ cwd: storageDir, provider: 'private', model: 'new-model' })) + .rejects.toThrow('no adapter registered for provider "private"') - expect(ctx.get('llm')?.models()).toEqual(expect.arrayContaining(['other-model', 'new-model'])) + expect(ctx.get('llm')?.providers()).toEqual(['deepseek']) await server.shutdown() } finally { await ctx.fiber.dispose() @@ -517,15 +519,15 @@ describe('HarnessSdkServer', () => { const ctx = { on: vi.fn(() => () => undefined), agents: { create, get: () => undefined }, - get: () => ({ models: () => ['model'] }), + get: () => ({ providers: () => ['mock'] }), } as unknown as Context const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as { - initialize(params: { cwd: string; model: string }): Promise + initialize(params: { cwd: string; provider: string; model: string }): Promise getOrCreateSession(sessionId: string): Promise shutdown(): Promise> } - await server.initialize({ cwd: '.', model: 'model' }) + await server.initialize({ cwd: '.', provider: 'mock', model: 'model' }) await server.getOrCreateSession('relative') expect(create).toHaveBeenCalledWith(expect.objectContaining({ meta: { cwd: process.cwd() } })) diff --git a/packages/ui/stdio-agent/README.md b/packages/ui/stdio-agent/README.md index 27f0d20be7..d93690a096 100644 --- a/packages/ui/stdio-agent/README.md +++ b/packages/ui/stdio-agent/README.md @@ -11,7 +11,7 @@ A terminal chat always wants the same cluster, so the package owns it rather tha | Plugin | Why it is here | |---|---| | `@cordisjs/plugin-logger-console` | the console logger — stdout is just the terminal here, so logging to it is correct (the ACP app must NOT have this) | -| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating a `main` agent from this app's `model` with `process.cwd()` as the fresh session cwd and carrying its `persona` | +| `@deepseek-ai/dsh-agent-core` | the spine, pre-creating a `main` agent from this app's provider/model pair with `process.cwd()` as the fresh session cwd and carrying its `persona` | | `@deepseek-ai/dsh-session-persistence-jsonl` | durable JSONL session log under `persistenceRoot` | | `@deepseek-ai/dsh-user-interaction` | the human question/answer seam used by confirmation tools | | `@deepseek-ai/dsh-tool-ask-user` | the model-facing `ask_user_question` tool | @@ -25,8 +25,9 @@ The leaf `cordis.yml` supplies only the **swappable backends** — an LLM adapte | Key | Default | Routed to | |---|---|---| +| `provider` | (required) | the pre-created `main` agent's registered provider route | | `model` | (required) | the pre-created `main` agent's model | -| `persona` | — | the deployment persona template (may reference `{{model}}`), routed to `dsh-system-prompt` | +| `persona` | — | the deployment persona template (may reference `{{provider}}`/`{{model}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `persistenceRoot` | `./.sessions` | the JSONL backend's root directory | | `welcome` | `ready.` | the stdin-chat banner | @@ -50,7 +51,6 @@ Fresh stdio sessions use the process launch directory as `session.header.cwd`, s name: '@deepseek-ai/dsh-llm-deepseek' config: apiKey: !!js process.env.DEEPSEEK_API_KEY - models: [deepseek-v4-flash] - id: bash name: '@deepseek-ai/dsh-bash-local' config: @@ -58,6 +58,7 @@ Fresh stdio sessions use the process launch directory as `session.header.cwd`, s - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: deepseek model: deepseek-v4-flash persona: 'You are a coding assistant powered by the {{model}} model.' ``` diff --git a/packages/ui/stdio-agent/src/index.ts b/packages/ui/stdio-agent/src/index.ts index 127851eaf5..05bd9f9fd2 100644 --- a/packages/ui/stdio-agent/src/index.ts +++ b/packages/ui/stdio-agent/src/index.ts @@ -9,7 +9,7 @@ * console (stdout is just the terminal) and always pre-creates the `main` agent * the readline UI sends to. The leaf supplies the swappable backends (the LLM * adapter, the bash executor), optional product tools, the optional `hmr` - * dev-reload plugin, and this app's {@link Config} (model, prompt, persistence + * dev-reload plugin, and this app's {@link Config} (provider/model, prompt, persistence * root, welcome banner). * * `hmr` is deliberately a LEAF entry, not baked in here: it is a Loader-only, @@ -54,7 +54,7 @@ export const name = 'stdio-agent' /** * App config: the swappable per-demo values, each routed to where the app wires - * it. `model`/`resumeSessionId` configure the pre-created `main` agent (through + * it. `provider`/`model`/`resumeSessionId` configure the pre-created `main` agent (through * {@link @deepseek-ai/dsh-agent-core}'s forwarded `agents` list); `persona` is * the deployment persona (forwarded to the system-prompt plugin); `toolOrder` * is the explicit model-facing tool order (forwarded to the system-prompt plugin); @@ -63,6 +63,8 @@ export const name = 'stdio-agent' * `welcome` is the UI banner. */ export interface Config { + /** Provider route for the `main` agent. */ + provider: string /** Model name for the `main` agent (must have a registered adapter). */ model: string /** Deployment persona (the system-prompt plugin's `persona` config). */ @@ -86,6 +88,7 @@ export interface Config { } export const Config: z = z.object({ + provider: z.string().required(), model: z.string().required(), persona: z.string(), // The array default is forced to undefined: ABSENT means "lexicographic @@ -116,6 +119,7 @@ export function apply(ctx: Context, config: Config): void { ...config.tools !== undefined ? { tools: config.tools } : {}, agents: [{ id: AgentId('main'), + provider: config.provider, model: config.model, cwd: process.cwd(), ...config.resumeSessionId !== undefined ? { resumeSessionId: SessionId(config.resumeSessionId) } : {}, diff --git a/packages/ui/stdio-agent/tests/built-bin.e2e.ts b/packages/ui/stdio-agent/tests/built-bin.e2e.ts index 31cdf3eb08..537aebda89 100644 --- a/packages/ui/stdio-agent/tests/built-bin.e2e.ts +++ b/packages/ui/stdio-agent/tests/built-bin.e2e.ts @@ -91,6 +91,7 @@ async function makeConsumer(welcome: string, disabledBrokenEntry = false): Promi '- id: stdio-agent', ' name: \'@deepseek-ai/dsh-stdio-agent\'', ' config:', + ' provider: mock', ' model: mock-echo', ' persona: \'demo\'', ` welcome: '${welcome}'`, diff --git a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts index 0668d25fb0..d7c54642b7 100644 --- a/packages/ui/stdio-agent/tests/stdio-agent.spec.ts +++ b/packages/ui/stdio-agent/tests/stdio-agent.spec.ts @@ -75,7 +75,7 @@ async function withIsolatedSkillHomes(run: () => Promise): Promise { describe('dsh-stdio-agent app', () => { it('composes the spine + front-door cluster and pre-creates the main agent', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-stdio-agent-spec', skills: await isolatedSkillsConfig() }) + const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-stdio-agent-spec', skills: await isolatedSkillsConfig() }) // The spine services (brought up by the agent-core bundle) are all present. expect(ctx.get('agents')).toBeDefined() expect(ctx.get('agentLoop')).toBeDefined() @@ -96,7 +96,7 @@ describe('dsh-stdio-agent app', () => { // schema-bypassing direct-mount caller. const ctx = new Context() // No persona: covers the omitted-persona forwarding branch too. - stdioAgent.apply(ctx, { model: 'mock', skills: await isolatedSkillsConfig() }) + stdioAgent.apply(ctx, { provider: 'mock', model: 'mock', skills: await isolatedSkillsConfig() }) await new Promise(resolve => setTimeout(resolve, 80)) expect(ctx.get('sessionPersistence')).toBeDefined() expect(ctx.get('agents')?.get(AgentId('main'))).toBeDefined() @@ -106,7 +106,7 @@ describe('dsh-stdio-agent app', () => { it('uses default skill config when apply is called directly without skills', async () => { await withIsolatedSkillHomes(async () => { const ctx = new Context() - stdioAgent.apply(ctx, { model: 'mock' }) + stdioAgent.apply(ctx, { provider: 'mock', model: 'mock' }) await new Promise(resolve => setTimeout(resolve, 80)) expect(ctx.skills).toBeDefined() expect(await ctx.skills.list()).toEqual([]) @@ -119,6 +119,7 @@ describe('dsh-stdio-agent app', () => { // session the resume is contained + logged, so no `main` agent registers — // the branch that maps resumeSessionId through is what this covers. const ctx = await mount({ + provider: 'mock', model: 'mock', persona: 'hi', persistenceRoot: '/tmp/dsh-stdio-agent-spec-resume', @@ -130,7 +131,7 @@ describe('dsh-stdio-agent app', () => { }) it('forwards skill config into agent-core', async () => { - const ctx = await mount({ model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) + const ctx = await mount({ provider: 'mock', model: 'mock', persona: 'hi', skills: await isolatedSkillsConfig(6) }) ctx.skills.register({ name: 'stdio-skill', description: 'Stdio skill', source: 'runtime', content: 'body' }) expect(JSON.stringify(await composePrefix(ctx))).toContain('- `stdio-skill`: Std...') await ctx.fiber.dispose() @@ -143,6 +144,7 @@ describe('dsh-stdio-agent app', () => { it('forwards toolOrder through agent-core to the system-prompt assembly', async () => { const ctx = await mount({ + provider: 'mock', model: 'mock', toolOrder: ['zulu', TOOL_ORDER_REST], persistenceRoot: '/tmp/dsh-stdio-agent-spec-tool-order', diff --git a/packages/ui/user-approval/tests/approval.spec.ts b/packages/ui/user-approval/tests/approval.spec.ts index ff0cd5c7d8..ea02e9b182 100644 --- a/packages/ui/user-approval/tests/approval.spec.ts +++ b/packages/ui/user-approval/tests/approval.spec.ts @@ -375,7 +375,7 @@ describe('approval policy (the approval/policy fold)', () => { /** Append a `request/header` snapshot whose system text is exactly `system`. */ function appendHeader(session: Session, system: string): void { - session.append('request/header', { header: { config: { model: 'mock' }, system }, reason: 'initial' }) + session.append('request/header', { header: { config: { provider: 'mock', model: 'mock' }, system }, reason: 'initial' }) } it('folds to the last event, or undefined without one', () => { diff --git a/packages/workflow/tool-workflow/src/index.ts b/packages/workflow/tool-workflow/src/index.ts index 7cd1606b47..a952d83921 100644 --- a/packages/workflow/tool-workflow/src/index.ts +++ b/packages/workflow/tool-workflow/src/index.ts @@ -57,10 +57,10 @@ type ResolvedConfig = Required */ const 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. -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. +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?, provider?, 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. +- \`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), \`provider\` and \`model\` (paired LLM target overrides). 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. @@ -71,7 +71,12 @@ Constraints: concurrency and total-agent caps apply; no filesystem, network, tim type WorkflowCallArgs = { script: string - meta: { name: string; description: string; whenToUse?: string; phases?: { title: string; detail?: string; model?: string }[] } + meta: { + name: string + description: string + whenToUse?: string + phases?: { title: string; detail?: string; provider?: string; model?: string }[] + } args?: Record } @@ -153,6 +158,7 @@ export function apply(ctx: Context, config: Config): void { properties: { title: { type: 'string', required: true, description: 'The phase title phase() calls match by exact string.' }, detail: { type: 'string', description: 'Optional one-line description of the phase.' }, + provider: { type: 'string', description: 'Optional provider override this phase is expected to use.' }, model: { type: 'string', description: 'Optional model override this phase is expected to use.' }, }, }, diff --git a/packages/workflow/workflow-workerthread/src/host.ts b/packages/workflow/workflow-workerthread/src/host.ts index 9ce754c0c6..fa2f68e307 100644 --- a/packages/workflow/workflow-workerthread/src/host.ts +++ b/packages/workflow/workflow-workerthread/src/host.ts @@ -388,7 +388,14 @@ export class WorkerRun implements WorkflowRun { parent: this.parent, signal: this.controller.signal, ...request.schema !== undefined ? { outputSchema: request.schema } : {}, - ...request.model !== undefined ? { agentOptions: { model: request.model } } : {}, + ...request.provider !== undefined || request.model !== undefined + ? { + agentOptions: { + ...request.provider !== undefined ? { provider: request.provider } : {}, + ...request.model !== undefined ? { model: request.model } : {}, + }, + } + : {}, }) } catch (error: unknown) { const failure = this.childAdmissionFailure() diff --git a/packages/workflow/workflow-workerthread/src/meta.ts b/packages/workflow/workflow-workerthread/src/meta.ts index 848a4fc9b1..e8fe222689 100644 --- a/packages/workflow/workflow-workerthread/src/meta.ts +++ b/packages/workflow/workflow-workerthread/src/meta.ts @@ -40,15 +40,17 @@ function validateMetaShape(meta: unknown): { meta?: WorkflowMeta; violations: st } const entry = phase as Record for (const key of Object.keys(entry)) { - if (!['title', 'detail', 'model'].includes(key)) violations.push(`meta.phases[${index}].${key} is not a recognized field`) + if (!['title', 'detail', 'provider', 'model'].includes(key)) violations.push(`meta.phases[${index}].${key} is not a recognized field`) } if (typeof entry.title !== 'string' || entry.title.length === 0) violations.push(`meta.phases[${index}].title must be a non-empty string`) if (entry.detail !== undefined && typeof entry.detail !== 'string') violations.push(`meta.phases[${index}].detail must be a string`) + if (entry.provider !== undefined && typeof entry.provider !== 'string') violations.push(`meta.phases[${index}].provider must be a string`) if (entry.model !== undefined && typeof entry.model !== 'string') violations.push(`meta.phases[${index}].model must be a string`) if (violations.length === 0) { phases.push({ title: entry.title as string, ...entry.detail !== undefined ? { detail: entry.detail as string } : {}, + ...entry.provider !== undefined ? { provider: entry.provider as string } : {}, ...entry.model !== undefined ? { model: entry.model as string } : {}, }) } diff --git a/packages/workflow/workflow-workerthread/src/runtime.ts b/packages/workflow/workflow-workerthread/src/runtime.ts index 94282cb173..8a66ef7bfd 100644 --- a/packages/workflow/workflow-workerthread/src/runtime.ts +++ b/packages/workflow/workflow-workerthread/src/runtime.ts @@ -61,7 +61,7 @@ export interface ExecutionObserver { } /** The `agent()` options the script may pass; everything else rejects loud. */ -const SUPPORTED_AGENT_OPTIONS = new Set(['label', 'phase', 'schema', 'model']) +const SUPPORTED_AGENT_OPTIONS = new Set(['label', 'phase', 'schema', 'provider', 'model']) /** Deferred Claude Code options we name explicitly in the rejection message. */ const DEFERRED_AGENT_OPTIONS = new Set(['effort', 'isolation', 'agentType']) @@ -302,6 +302,7 @@ export class WorkflowExecution { run = await this.children.startAgent({ prompt: rawPrompt, ...opts.schema !== undefined ? { schema: opts.schema } : {}, + ...opts.provider !== undefined ? { provider: opts.provider } : {}, ...opts.model !== undefined ? { model: opts.model } : {}, }) } catch (error: unknown) { @@ -369,7 +370,13 @@ export class WorkflowExecution { } /** Materialize + validate the `agent()` options bag from the realm. */ - private readAgentOptions(rawOpts: unknown): { label?: string; phase?: string; model?: string; schema?: StructuredOutputSchema } { + private readAgentOptions(rawOpts: unknown): { + label?: string + phase?: string + provider?: string + model?: string + schema?: StructuredOutputSchema + } { if (rawOpts === undefined) return {} let opts: unknown try { @@ -388,9 +395,9 @@ export class WorkflowExecution { if (DEFERRED_AGENT_OPTIONS.has(key)) { throw new WorkflowError(`agent() option "${key}" is deferred and not supported by this engine (supported: label, phase, schema, model)`, 'UNSUPPORTED_OPTION') } - throw new WorkflowError(`agent() option "${key}" is not recognized (supported: label, phase, schema, model)`, 'UNSUPPORTED_OPTION') + throw new WorkflowError(`agent() option "${key}" is not recognized (supported: label, phase, schema, provider, model)`, 'UNSUPPORTED_OPTION') } - for (const key of ['label', 'phase', 'model'] as const) { + for (const key of ['label', 'phase', 'provider', 'model'] as const) { if (record[key] !== undefined && typeof record[key] !== 'string') { throw new WorkflowError(`agent() option "${key}" must be a string`, 'INVALID_ARGUMENT') } @@ -409,6 +416,7 @@ export class WorkflowExecution { return { ...record.label !== undefined ? { label: record.label as string } : {}, ...record.phase !== undefined ? { phase: record.phase as string } : {}, + ...record.provider !== undefined ? { provider: record.provider as string } : {}, ...record.model !== undefined ? { model: record.model as string } : {}, ...schema !== undefined ? { schema } : {}, } diff --git a/packages/workflow/workflow-workerthread/src/types.ts b/packages/workflow/workflow-workerthread/src/types.ts index 2f29dd8137..caf5d33178 100644 --- a/packages/workflow/workflow-workerthread/src/types.ts +++ b/packages/workflow/workflow-workerthread/src/types.ts @@ -46,6 +46,8 @@ export interface ChildStartRequest { prompt: string /** The structured-output schema, if the call passed one (already subset-checked). */ schema?: StructuredOutputSchema + /** The per-child provider override, if the call passed one. */ + provider?: string /** The per-child model override, if the call passed one. */ model?: string } diff --git a/packages/workflow/workflow-workerthread/tests/integration.spec.ts b/packages/workflow/workflow-workerthread/tests/integration.spec.ts index 0e1727f877..a247f4f9e9 100644 --- a/packages/workflow/workflow-workerthread/tests/integration.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/integration.spec.ts @@ -37,7 +37,7 @@ async function setup(script: Script) { await ctx.plugin(spawn, { providerName: 'spawn' }) await ctx.plugin(WorkerWorkflowEngine, {}) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' }) + const parent = ctx.agentLoop.create(AgentId('parent'), { provider: 'mock', model: 'mock' }) return { ctx, parent, adapter } } diff --git a/packages/workflow/workflow-workerthread/tests/meta.spec.ts b/packages/workflow/workflow-workerthread/tests/meta.spec.ts index 37b86440be..00505a6435 100644 --- a/packages/workflow/workflow-workerthread/tests/meta.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/meta.spec.ts @@ -33,7 +33,7 @@ describe('validateMeta', () => { description: 'migrate call sites', whenToUse: 'large mechanical sweeps', phases: [ - { title: 'Discover' }, + { title: 'Discover', provider: 'openai' }, { title: 'Transform', detail: 'one agent per file', model: 'deepseek-v4-pro' }, ], }) @@ -42,7 +42,7 @@ describe('validateMeta', () => { description: 'migrate call sites', whenToUse: 'large mechanical sweeps', phases: [ - { title: 'Discover' }, + { title: 'Discover', provider: 'openai' }, { title: 'Transform', detail: 'one agent per file', model: 'deepseek-v4-pro' }, ], }) @@ -73,6 +73,7 @@ describe('validateMeta', () => { expectInvalid({ name: 'x', description: 'd', phases: [{ title: '' }] }, 'meta.phases[0].title must be a non-empty string') expectInvalid({ name: 'x', description: 'd', phases: [{ title: 'Scan', order: 1 }] }, 'meta.phases[0].order is not a recognized field') expectInvalid({ name: 'x', description: 'd', phases: [{ title: 'Scan', detail: 9 }] }, 'meta.phases[0].detail must be a string') + expectInvalid({ name: 'x', description: 'd', phases: [{ title: 'Scan', provider: 9 }] }, 'meta.phases[0].provider must be a string') expectInvalid({ name: 'x', description: 'd', phases: [{ title: 'Scan', model: 9 }] }, 'meta.phases[0].model must be a string') }) diff --git a/packages/workflow/workflow-workerthread/tests/session.spec.ts b/packages/workflow/workflow-workerthread/tests/session.spec.ts index 5fc85ce647..0e5d52bab1 100644 --- a/packages/workflow/workflow-workerthread/tests/session.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/session.spec.ts @@ -35,7 +35,7 @@ interface FakeHost { interface FakeHostOptions { /** Auto-respond to child-start: reply started + settled per child index. Omit a reply to leave the child pending. */ - reply?: (request: { prompt: string; schema?: unknown; model?: string }, index: number) => ChildResult | undefined + reply?: (request: { prompt: string; schema?: unknown; provider?: string; model?: string }, index: number) => ChildResult | undefined /** Reject the start instead (child-start-error) when returning a string. */ refuse?: (index: number) => string | undefined /** Auto-send `go` on `ready` (default true). */ @@ -143,6 +143,17 @@ describe('runWorkerSession over an in-process MessageChannel', () => { host.close() }) + it('agent({provider}) forwards a provider without inventing a model', async () => { + const host = fakeHost({ reply: () => text('ok') }) + void runWorkerSession(host.port, init("return await agent('route me', { provider: 'openai' })")) + const result = await host.result() + expect(result.value).toBe('ok') + const start = host.ofType(WorkerToHostType.ChildStart)[0]! + expect(start.request.provider).toBe('openai') + expect(start.request.model).toBeUndefined() + host.close() + }) + it('a schema child completing WITHOUT a structured value resolves null with a failed outcome', async () => { const host = fakeHost({ reply: () => text('prose, no structure') }) void runWorkerSession(host.port, init("return await agent('p', { schema: { type: 'object' } })")) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts index 1d6f61432a..d49633636d 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.e2e.ts @@ -35,7 +35,7 @@ async function harness(): Promise { await built.plugin(ToolRegistry) await built.plugin(AgentRegistry) await built.plugin(AgentLoop, { agents: [] }) - await built.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] }) + await built.plugin(LlmDeepSeek) await built.plugin(SubagentService) await built.plugin(Spawn, { providerName: 'spawn' }) await built.plugin(WorkerWorkflowEngine, { provider: 'spawn' }) @@ -64,7 +64,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('worker workflow engine with-key const parentHandle = await ctx.agents.create({ agentId: AgentId('wf-worker-e2e-parent'), sessionId: 'wf-worker-e2e-session' as never, - agentOptions: { model: 'deepseek-v4-flash' }, + agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' }, }) const events: string[] = [] diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts index 4ad00ee02f..61b00f47e5 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -236,6 +236,14 @@ describe('dsh-workflow-workerthread', () => { expect(provider.runs[0]!.request.parent).toBeDefined() }) + it('agent({provider}) forwards provider-only agentOptions across the thread', async () => { + const { ctx, parent, provider } = await setup() + const result = await run(ctx, parent, scripted("return await agent('route me', { provider: 'openai' })")) + + expect(result.value).toBe('stub reply') + expect(provider.runs[0]!.request.agentOptions).toEqual({ provider: 'openai' }) + }) + it('a fatal hook error inside the worker kills the script and reports the error', async () => { const { ctx, parent } = await setup() const result = await run(ctx, parent, scripted("return await parallel([() => agent('x', { isolation: 'worktree' })])")) diff --git a/packages/workflow/workflow/src/types.ts b/packages/workflow/workflow/src/types.ts index 981a2da172..108613c559 100644 --- a/packages/workflow/workflow/src/types.ts +++ b/packages/workflow/workflow/src/types.ts @@ -30,6 +30,8 @@ export interface WorkflowPhase { title: string /** Optional one-line description of what the phase does. */ detail?: string + /** Optional provider override this phase is expected to use (informational). */ + provider?: string /** Optional model override this phase is expected to use (informational). */ model?: string } diff --git a/python/sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml b/python/sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml index 76ae18b20e..f609678fc7 100644 --- a/python/sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml +++ b/python/sdk-runtime/src/deepseek_harness_runtime/runtime/cordis.yml @@ -30,9 +30,6 @@ config: apiKey: !!js process.env.DEEPSEEK_API_KEY baseURL: !!js process.env.DEEPSEEK_BASE_URL - models: - - deepseek-v4-flash - - deepseek-v4-pro # JSONL session persistence. $DSH_SESSION_ROOT (set by the SDK whenever # `session_root` is configured) wins; otherwise ./.sessions relative to the diff --git a/python/sdk/README.i18n.yaml b/python/sdk/README.i18n.yaml index a294dc1194..e06c748c59 100644 --- a/python/sdk/README.i18n.yaml +++ b/python/sdk/README.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -README.md: 60540376c5fd85b0852e204bc8bad3f01c849de5 -README.zh.md: 241c06057889f1aa4add6fc54024fba92bd19429 +README.md: b1189a789963a5e4180cc4ee402c885b0ec82dca +README.zh.md: 721221418eb65f323f521a4fa16cbc355d283f0d diff --git a/python/sdk/README.md b/python/sdk/README.md index 60540376c5..b1189a7899 100644 --- a/python/sdk/README.md +++ b/python/sdk/README.md @@ -25,12 +25,15 @@ By default, the SDK launches the bundled single-file `dsh-jsonrpc-agent` executa from deepseek_harness import DeepSeekHarness with DeepSeekHarness( + provider="deepseek", model="deepseek-v4-flash", cordis="examples/dsbench-coding-agent/cordis.yml", ) as harness: result = harness.run("Make the requested code change.") ``` +`provider` selects a provider route registered by the chosen Cordis composition; `model` is the model id resolved by that adapter. The bundled default composition registers `deepseek`. A custom composition can mount `llm-pi-ai`, configure provider-specific credentials/endpoints there, and select any provider/model present in pi-ai's installed catalog. + `TurnResult.final_response` is the text content from the last `assistant/message` event in the turn. Use `TurnResult.events` for the complete event stream, including intermediate assistant messages and tool activity. diff --git a/python/sdk/README.zh.md b/python/sdk/README.zh.md index 241c060578..721221418e 100644 --- a/python/sdk/README.zh.md +++ b/python/sdk/README.zh.md @@ -21,12 +21,15 @@ with DeepSeekHarness() as harness: from deepseek_harness import DeepSeekHarness with DeepSeekHarness( + provider="deepseek", model="deepseek-v4-flash", cordis="examples/dsbench-coding-agent/cordis.yml", ) as harness: result = harness.run("Make the requested code change.") ``` +`provider` 用于选择当前 Cordis 组合已注册的 provider 路由；`model` 是该适配器解析的模型 ID。内置默认组合注册 `deepseek`。自定义组合可以挂载 `llm-pi-ai`，在其中配置各 provider 的凭据与端点，再选择 pi-ai 已安装目录中的任意 provider/model。 + `TurnResult.final_response` 是本轮次最后一个 `assistant/message` 事件的文本内容。完整的事件流（包括中间的助手消息与工具活动）用 `TurnResult.events` 获取。 同样的行为也可以通过 `DSH_CORDIS_CONFIG` 为运行时子进程选定。注入逻辑位于 `HarnessClient.start()`，因此底层客户端的默认启动也具有此行为：当启动解析到内置运行时，且 `cordis` 与非空的 `DSH_CORDIS_CONFIG` 均未设置时（运行时把空值视为缺省，注入检查与之一致），使用内置的默认配置；显式给出 `runtime_bin` 或 `launch_args_override` 则完全禁用注入。运行时载体（生产用 exe 与仅限开发的 `node` 闭包）及其获取方式见 [sdk-runtime README](../sdk-runtime/README.md)。 diff --git a/python/sdk/src/deepseek_harness/api.py b/python/sdk/src/deepseek_harness/api.py index 3743371cea..2b44a50c64 100644 --- a/python/sdk/src/deepseek_harness/api.py +++ b/python/sdk/src/deepseek_harness/api.py @@ -18,6 +18,7 @@ class DeepSeekHarnessConfig: intentionally override or inject variables for a subprocess. """ + provider: str = "deepseek" model: str = "deepseek-v4-flash" cwd: str | None = None runtime_cwd: str | None = None @@ -97,6 +98,7 @@ class DeepSeekHarness: self._client.start() self._client.initialize( cwd=self._cwd, + provider=self.config.provider, model=self.config.model, ) self._initialized = True diff --git a/python/sdk/src/deepseek_harness/client.py b/python/sdk/src/deepseek_harness/client.py index be457c538a..a7c8c8c7a7 100644 --- a/python/sdk/src/deepseek_harness/client.py +++ b/python/sdk/src/deepseek_harness/client.py @@ -115,10 +115,12 @@ class HarnessClient: self, *, cwd: str, + provider: str, model: str, ) -> InitializeResponse: payload: JsonObject = { "cwd": str(Path(cwd).resolve()), + "provider": provider, "model": model, } try: diff --git a/python/sdk/tests/test_bundled_runtime.py b/python/sdk/tests/test_bundled_runtime.py index a55c6c2c6a..2a04f7b7b1 100644 --- a/python/sdk/tests/test_bundled_runtime.py +++ b/python/sdk/tests/test_bundled_runtime.py @@ -74,7 +74,7 @@ def test_bundled_runtime_boots_a_cordis_config(tmp_path: Path, mode: str) -> Non (tmp_path / "cordis.yml").write_text(_CORDIS_YML) with _client(tmp_path, launch_args) as client: - init = client.initialize(cwd=str(tmp_path), model="deepseek-v4-pro") + init = client.initialize(provider="deepseek", cwd=str(tmp_path), model="deepseek-v4-pro") assert init.serverInfo is not None assert init.serverInfo.name == "deepseek-harness-sdk-runtime" @@ -91,7 +91,7 @@ def test_bundled_runtime_surfaces_unbundled_plugin_failure(tmp_path: Path, mode: client.start() try: with pytest.raises((TransportClosedError, TimeoutError)) as excinfo: - client.initialize(cwd=str(tmp_path), model="deepseek-v4-pro") + client.initialize(provider="deepseek", cwd=str(tmp_path), model="deepseek-v4-pro") finally: client.close() diff --git a/python/sdk/tests/test_client.py b/python/sdk/tests/test_client.py index 327e5f5c39..c09fc594a3 100644 --- a/python/sdk/tests/test_client.py +++ b/python/sdk/tests/test_client.py @@ -330,7 +330,7 @@ for line in sys.stdin: with HarnessClient( HarnessConfig(launch_args_override=(sys.executable, str(script))) ) as client: - init = client.initialize(cwd="/workspace", model="dsagent") + init = client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") assert init.serverInfo.name == "fake-dsh" client.session_prompt("main", [{"type": "text", "text": "fix it"}]) @@ -382,7 +382,7 @@ for line in sys.stdin: raise RuntimeError("bad notification filter") with HarnessClient(HarnessConfig(launch_args_override=(sys.executable, str(script)))) as client: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") with ( client.subscribe_notifications(broken_filter) as broken, client.subscribe_notifications(lambda notification: notification.method == "tick") as healthy, @@ -419,7 +419,7 @@ for line in sys.stdin: ) with HarnessClient(HarnessConfig(launch_args_override=(sys.executable, str(script)))) as client: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") with pytest.raises(ValueError): client.session_prompt("main", [{"type": "text", "text": "fix it"}]) @@ -448,7 +448,7 @@ for line in sys.stdin: with HarnessClient( HarnessConfig(launch_args_override=(sys.executable, str(script))) ) as client: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") request = client.next_request() assert request.id == "bridge-req-1" @@ -482,7 +482,7 @@ for line in sys.stdin: with HarnessClient( HarnessConfig(launch_args_override=(sys.executable, str(script))) ) as client: - init = client.initialize(cwd="/workspace", model="dsagent") + init = client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") assert init.serverInfo.name == "fake-dsh" @@ -504,7 +504,7 @@ time.sleep(60) ) as client: start = time.monotonic() try: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") except TimeoutError: assert time.monotonic() - start < 2 else: @@ -540,7 +540,7 @@ for line in sys.stdin: client.start() proc = client._proc assert proc is not None - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") start = time.monotonic() client.close() assert time.monotonic() - start < 2 @@ -571,7 +571,7 @@ for line in sys.stdin: assert proc is not None with pytest.raises(Exception, match="bad initialize"): - client.initialize(cwd=".", model="dsagent") + client.initialize(provider="deepseek", cwd=".", model="dsagent") assert proc.wait(timeout=1) is not None assert client._proc is None @@ -611,7 +611,7 @@ for line in sys.stdin: client = HarnessClient(HarnessConfig(launch_args_override=(sys.executable, str(script)))) client.start() - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") client.close() client.close() @@ -634,7 +634,7 @@ sys.exit(42) ) ) as client: with pytest.raises(Exception, match="fatal bridge exploded"): - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") def test_client_serializes_concurrent_writes(tmp_path: Path) -> None: @@ -665,7 +665,7 @@ with open(os.environ["SEEN"], "w") as seen: env={"SEEN": str(output)}, ) ) as client: - client.initialize(cwd="/workspace", model="dsagent") + client.initialize(provider="deepseek", cwd="/workspace", model="dsagent") threads = [ threading.Thread(target=client.notify, args=(f"notice-{index}", {"index": index})) for index in range(50) @@ -738,7 +738,7 @@ def test_client_default_launch_uses_bundled_runtime_and_injects_default_config( monkeypatch.setenv("DSH_CORDIS_CONFIG", ambient_config) with HarnessClient(HarnessConfig(env={"ENV_DUMP": str(env_dump)})) as client: - init = client.initialize(cwd="/workspace", model="deepseek-v4-pro") + init = client.initialize(provider="deepseek", cwd="/workspace", model="deepseek-v4-pro") assert init.serverInfo.name == "bundled-runtime" assert json.loads(env_dump.read_text())["DSH_CORDIS_CONFIG"] == str(default_config) @@ -754,7 +754,7 @@ def test_client_respects_explicit_config_over_bundled_default( with HarnessClient( HarnessConfig(env={"ENV_DUMP": str(env_dump), "DSH_CORDIS_CONFIG": "./explicit.yml"}) ) as client: - client.initialize(cwd="/workspace", model="deepseek-v4-pro") + client.initialize(provider="deepseek", cwd="/workspace", model="deepseek-v4-pro") assert json.loads(env_dump.read_text())["DSH_CORDIS_CONFIG"] == "./explicit.yml" diff --git a/scripts/smoke-python-runtime.py b/scripts/smoke-python-runtime.py index 2c61d07c19..461b828a19 100644 --- a/scripts/smoke-python-runtime.py +++ b/scripts/smoke-python-runtime.py @@ -379,6 +379,7 @@ def smoke_sdk_default(base_url: str) -> None: root = Path(temporary).resolve() sessions = root / "sessions" with DeepSeekHarness( + provider="deepseek", model="smoke-model", cwd=str(root), session_root=str(sessions), @@ -401,6 +402,7 @@ def smoke_sdk_custom(base_url: str, executable: Path) -> None: cordis = root / "cordis.yml" cordis.write_text(CUSTOM_CORDIS) with DeepSeekHarness( + provider="deepseek", model="smoke-model", cwd=str(root), session_root=str(sessions), @@ -432,6 +434,7 @@ def smoke_sdk_snapshot(base_url: str, executable: Path, update_snapshots: bool) cordis = root / "cordis.yml" cordis.write_text(CUSTOM_CORDIS) with DeepSeekHarness( + provider="deepseek", model="smoke-model", cwd=str(root), session_root=str(sessions), @@ -481,7 +484,7 @@ def smoke_direct(base_url: str, executable: Path) -> None: } peer = RuntimePeer([str(executable)], root, environment) try: - peer.send({"jsonrpc": "2.0", "id": "initialize", "method": "initialize", "params": {"cwd": str(root), "model": "smoke-model"}}) + peer.send({"jsonrpc": "2.0", "id": "initialize", "method": "initialize", "params": {"cwd": str(root), "provider": "deepseek", "model": "smoke-model"}}) peer.read_until(lambda message: message.get("id") == "initialize") peer.send({ "jsonrpc": "2.0", diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index a219ea1b1d..c352d2f90c 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -3,6 +3,7 @@ "entries": [ { "doc": "docs/core-data-structures/core.md", "symbol": "Branded", "source": "packages/util/brand/src/index.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ContentBlockMap", "source": "packages/llm/llm/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "AssistantProvenance", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "Message", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "MessageSourceMap", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "FinishReasonMap", "source": "packages/llm/llm/src/types.ts" }, From 0107a7a03d659f1c38444f576c8643b752fa9dcd Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Tue, 14 Jul 2026 22:25:59 +0800 Subject: [PATCH 2/9] test(context): adapt time context to provider routing --- packages/context/time-context/tests/fixtures/cordis.yml | 1 + packages/context/time-context/tests/time-context.spec.ts | 7 +++++-- 2 files changed, 6 insertions(+), 2 deletions(-) diff --git a/packages/context/time-context/tests/fixtures/cordis.yml b/packages/context/time-context/tests/fixtures/cordis.yml index e9558abec6..afd9bc24d4 100644 --- a/packages/context/time-context/tests/fixtures/cordis.yml +++ b/packages/context/time-context/tests/fixtures/cordis.yml @@ -11,6 +11,7 @@ - id: stdio-agent name: '@deepseek-ai/dsh-stdio-agent' config: + provider: mock model: mock-echo persona: 'Test the time-context plugin.' welcome: 'time-context e2e ready.' diff --git a/packages/context/time-context/tests/time-context.spec.ts b/packages/context/time-context/tests/time-context.spec.ts index 562b002b68..b371501e67 100644 --- a/packages/context/time-context/tests/time-context.spec.ts +++ b/packages/context/time-context/tests/time-context.spec.ts @@ -117,6 +117,7 @@ describe('temporal section rendering', () => { const session = new Session(SessionId('offset')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('assistant/message', { + provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'previous' }], @@ -136,6 +137,7 @@ describe('temporal section rendering', () => { const session = new Session(SessionId('backward-duration')) session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } }) session.append('assistant/message', { + provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'future by adjusted clock' }], @@ -152,7 +154,7 @@ describe('temporal section rendering', () => { session.append('user/message', { content: [{ type: 'text', text: 'u' }], source: { kind: 'user' } }, { surfaceOp: 'append' }) }], ['assistant/message', (session: Session): void => { - session.append('assistant/message', { turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' }) + session.append('assistant/message', { provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'a' }] }, { surfaceOp: 'append' }) }], ['tool/result', (session: Session): void => { session.append('tool/result', { @@ -239,6 +241,7 @@ describe('refresh policy', () => { const first = await sectionText(ctx, agent) vi.setSystemTime(BASE + 1_000) session.append('assistant/message', { + provenance: { provider: 'mock', model: 'mock' }, turn: 1, step: 1, content: [{ type: 'text', text: 'done' }], @@ -330,7 +333,7 @@ describe('real agent-loop request logging', () => { return [{ type: 'text' as const, text: 'advanced' }] }, })) - const agent = ctx.agentLoop.create(AgentId('loop'), { model: 'mock' }) + const agent = ctx.agentLoop.create(AgentId('loop'), { provider: 'mock', model: 'mock' }) agent.send([{ type: 'text', text: 'start' }]) await agent.whenIdle() From 310aa9992f365e67561032d9741a4e27f78ace6e Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 10:07:21 +0800 Subject: [PATCH 3/9] fix: address provider routing review feedback --- docs/tool-catalog.md | 2 +- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- .../acp-agent/tests/snapshots/both-mode-turn/session.jsonl | 2 +- .../tests/snapshots/both-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/escalation-approved/session.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/session.jsonl | 4 ++-- .../tests/snapshots/hook-cc-pretool-ask/session.jsonl | 4 ++-- .../tests/snapshots/permission-switching/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/skill-load/session.jsonl | 2 +- examples/acp-agent/tests/snapshots/text-turn/session.jsonl | 2 +- packages/llm/llm/src/assembler.ts | 2 +- packages/workflow/tool-workflow/src/index.ts | 2 +- packages/workflow/workflow-workerthread/src/runtime.ts | 2 +- packages/workflow/workflow-workerthread/tests/session.spec.ts | 2 +- 18 files changed, 21 insertions(+), 21 deletions(-) diff --git a/docs/tool-catalog.md b/docs/tool-catalog.md index 292b592d93..b3b84ef1fe 100644 --- a/docs/tool-catalog.md +++ b/docs/tool-catalog.md @@ -480,7 +480,7 @@ Run a JavaScript workflow script that orchestrates subagents at scale. Use this 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?, provider?, 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), `provider` and `model` (paired LLM target overrides). Anything else (`effort`/`isolation`/`agentType`) is rejected loudly. +- `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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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. diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl index 0047fe075c..de08513c68 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.1.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884563,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884563,"data":{"content":[{"type":"text","text":"Reply with exactly DIRECT_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884564,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884564,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950001005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"DIRECT_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884564,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"DIRECT_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl index e9ac30a033..eae3106743 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.2.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884700,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884700,"data":{"content":[{"type":"text","text":"Reply with exactly WORKFLOW_CHILD_OK and nothing else."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884700,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884701,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950002005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}} {"type":"assistant/chunk","seq":5,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"WORKFLOW_CHILD_OK"}}} {"type":"assistant/chunk","seq":6,"time":1783957884701,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"WORKFLOW_CHILD_OK"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl index 7fc796ada5..52e08e5b10 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783957884479,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783957884479,"data":{"content":[{"type":"text","text":"Run this advanced flow exactly once: mount a no-op Cordis plugin named snapshot-marker; use run_code to inspect the live dynamic mounts through tools.cordis_inspect; delegate once to a direct spawn child; run one workflow that delegates to another spawn child; unmount dyn-1; then reply with exactly ADVANCED_ACP_OK."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783957884486,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783957884486,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"cordis_inspect","description":"Inspect the live cordis runtime that is running THIS agent. Read-only. Sections: `services` (every provided ctx service and the plugin fiber that owns it), `plugins` (a flat list of the loaded plugins with their lifecycle states), `tools` (the model-facing tools currently registered, i.e. what you can call), `dynamic` (plugins you mounted via cordis_mount: id, name, state, provided services, awaited services), `api` (method signatures AND argument/return type shapes for every LIVE service — read this before writing plugin code that calls a service), `events` (every harness event with its dispatch mode and exact signature — pick listener targets here). Omit `what` to get all six sections.","parameters":{"type":"object","properties":{"what":{"type":"string","description":"Limit the report to one section. Omit for all sections.","enum":["services","plugins","tools","dynamic","api","events"]}}}},{"name":"cordis_mount","description":"Mount a NEW cordis plugin into the live runtime that is running THIS agent (self-modification). `code` runs as the body of an async JavaScript function in an isolated sandbox and MUST `return` a plugin. Two forms: FUNCTION form `return (ctx) => { … }` — declares no inject, so it can register tools, listen to events, and provide services, but reaching ANY service (e.g. ctx.bash) throws; use it only when you need no services. OBJECT form `return { name?, inject: ['bash', 'llm', …], apply(ctx) { … } }` — declares dependencies, and cordis activates the plugin only after the services exist; PREFER this form. You may reach ONLY the services you list in inject: an undeclared service throws even if it exists, because an undeclared dependency would not be cleaned up if its provider is unmounted. BEFORE calling a service from your code, read cordis_inspect what:\"api\" — it lists method signatures AND the type shapes of their arguments/returns (do not guess a field's type; e.g. a bash run's stdout is an object, not a string). Inside `apply`, use the standard cordis API: `ctx.on(event, listener)` to observe events (see cordis_inspect what:\"events\"), or call `harness.registerTool(ctx, harness.defineTool({ name, description, parameters: { text: { type: 'string', required: true } }, async execute(args) { … } }))` to give yourself a new tool — it becomes callable on your NEXT step. Tool parameters: each key IS a property — { type: 'string'|'number'|'boolean'|'object'|'array', required?: true, description?, enum?, items?, properties? }; a JSON-Schema-style { type: 'object', properties, required: […] } wrapper and type 'integer' are also accepted and normalized. A tool's `execute` MUST return an ARRAY of content blocks, e.g. `return [{ type: 'text', text: someString }]` — never a bare string. Mounts can COMPOSE: one plugin may `ctx.provide('name', value)` a service and another may declare `inject: ['name']` to consume it — the consumer stays pending until the provider exists and returns to pending when the provider is unmounted. Everything registered inside `apply` is cleaned up automatically on unmount. Sandbox globals: `console` (tagged `[cordis:]`, writes through to the harness terminal), `harness.defineTool`, `harness.registerTool`, `btoa`, `atob`, `TextEncoder`, `TextDecoder`. Node APIs are DISABLED — do filesystem/network/timer work through the cordis services, never Node built-ins: `require`, `setTimeout`/`setInterval`, and `fetch` throw redirect errors; `process` and `Buffer` are undefined. Instead use inject: ['fs'] + ctx.fs for files, inject: ['web'] + ctx.web for HTTP, inject: ['bash'] + ctx.bash for processes, and inject: ['timer'] + ctx.setTimeout/ctx.setInterval for timing (fiber effects, auto-cleaned on unmount) — cordis_inspect what:\"api\" shows what THIS runtime provides. Write PLAIN JavaScript, not TypeScript (no `as`, no type annotations). Cautions: (1) waterfall events (e.g. tools/pre-execute) hand the listener a trailing `next` callback which MUST be called — returning without `next()` VETOES the call; prefer plain notification events unless you intend to intercept. (2) Never await something that only resolves after the current turn (your code runs INSIDE a tool call of that turn — it would deadlock). (3) Your `ctx` is a restricted façade: you can register tools, observe events, provide/consume services, and use timers, but framework internals (ctx.root, ctx.fiber, ctx.extend, ctx.plugin, …) are withheld. It is not a security boundary though — the services you inject (e.g. ctx.bash) reach the real runtime.","parameters":{"type":"object","properties":{"code":{"type":"string","description":"Body of an async JS function; must `return` the plugin to mount."}},"required":["code"]}},{"name":"cordis_unmount","description":"Dispose a plugin previously mounted with cordis_mount, by id. All its registrations (event listeners, tools, services) are cleaned up through the cordis effect lifecycle. Returns only after disposal has fully completed (quiescence, not just a request to stop).","parameters":{"type":"object","properties":{"id":{"type":"string","description":"The dynamic mount id returned by cordis_mount (e.g. \"dyn-1\")."}},"required":["id"]}},{"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783950000005,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} {"type":"assistant/chunk","seq":5,"time":1783950000006,"data":{"turn":1,"step":1,"chunk":{"type":"tool-call-delta","index":0,"id":"advanced-mount","name":"cordis_mount","argumentsDelta":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}} {"type":"assistant/chunk","seq":6,"time":1783950000007,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"tool-call","id":"advanced-mount","name":"cordis_mount","arguments":"{\"code\":\"return { name: 'snapshot-marker', apply() {} }\"}"}}}} diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 20ba0b3849..3b0e7c08b4 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md @@ -96,7 +96,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** 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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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. */ + /** 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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; 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 c98f4a21b1..25ade25a81 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":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783611774325,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"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/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index de153cde4a..a2cdb8f70e 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md @@ -81,7 +81,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** 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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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. */ + /** 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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index de153cde4a..a2cdb8f70e 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md @@ -81,7 +81,7 @@ declare const tools: { status: "pending" | "in_progress" | "completed"; })[]; }): Promise; - /** 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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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. */ + /** 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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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. */ workflow(args: { /** The plain-JS workflow script body (top-level await allowed; NO `export const meta` statement; end with `return `). */ script: string; diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl index 4087857323..da999eb947 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl @@ -131,8 +131,8 @@ {"type":"assistant/chunk","seq":129,"time":1783962245385,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":130,"time":1783962245385,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a command with sandbox_permissions set to danger-full-access, no prior run needed, justified as instructed."},{"type":"tool-call","id":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1501,"outputTokens":174,"cacheReadTokens":0,"reasoningTokens":28}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"surfaceOp":"append"} {"type":"tool/call","seq":131,"time":1783962245385,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write file outside workspace and verify\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"ed807292-6499-4c75-adc4-a344e6fda38b","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"ed807292-6499-4c75-adc4-a344e6fda38b","outcome":"allowed-once"}} +{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"5d298f92-ced6-4fa0-ae01-cd0660b29f58","toolName":"bash","callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":133,"time":1783962245387,"data":{"id":"5d298f92-ced6-4fa0-ae01-cd0660b29f58","outcome":"allowed-once"}} {"type":"tool/result","seq":134,"time":1783962245399,"data":{"turn":1,"step":1,"callId":"call_00_d0sAHpJ9mYOJi0z7KNy30441","content":[{"type":"text","text":"escalated\n"}],"isError":false},"sourceEventSeqs":[131],"surfaceOp":"append"} {"type":"step/end","seq":135,"time":1783962245400,"data":{"turn":1,"step":1}} {"type":"step/start","seq":136,"time":1783962245400,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl index e2efeee9e9..657127b8f1 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl @@ -155,8 +155,8 @@ {"type":"assistant/chunk","seq":153,"time":1783962246274,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"tool-calls"}}}} {"type":"assistant/message","seq":154,"time":1783962246274,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to run a specific command with `sandbox_permissions` set to `danger-full-access` and a specific justification. They explicitly said NOT to run it without sandbox_permissions first. Let me do exactly that."},{"type":"tool-call","id":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":1509,"outputTokens":198,"cacheReadTokens":0,"reasoningTokens":48}},"sourceEventSeqs":[7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64,65,66,67,68,69,70,71,72,73,74,75,76,77,78,79,80,81,82,83,84,85,86,87,88,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107,108,109,110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153],"surfaceOp":"append"} {"type":"tool/call","seq":155,"time":1783962246274,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","name":"bash","arguments":"{\"command\": \"printf 'escalated\\\\n' > /tmp/dsh-escalated.txt && cat /tmp/dsh-escalated.txt && rm /tmp/dsh-escalated.txt\", \"description\": \"Write to /tmp and verify, then clean up\", \"sandbox_permissions\": \"danger-full-access\", \"justification\": \"the user asked to write a file outside the workspace\"}"}} -{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"0014f39a-22b4-4089-b90b-f42b1619e9b8","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} -{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"0014f39a-22b4-4089-b90b-f42b1619e9b8","outcome":"rejected"}} +{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"12cac992-89a6-4bbe-9d33-3254f4f13c7a","toolName":"bash","callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","reason":"escalate sandbox to danger-full-access: the user asked to write a file outside the workspace"}} +{"type":"approval/decided","seq":157,"time":1783962246275,"data":{"id":"12cac992-89a6-4bbe-9d33-3254f4f13c7a","outcome":"rejected"}} {"type":"tool/result","seq":158,"time":1783962246275,"data":{"turn":1,"step":1,"callId":"call_00_WB1vnPomi8yr6MlcFKTj7912","content":[{"type":"text","text":"Error: the user rejected escalating this command to \"danger-full-access\""}],"isError":true},"sourceEventSeqs":[155],"surfaceOp":"append"} {"type":"step/end","seq":159,"time":1783962246276,"data":{"turn":1,"step":1}} {"type":"step/start","seq":160,"time":1783962246276,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index 654965f86a..6264b68db9 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl @@ -55,8 +55,8 @@ {"type":"tool/call","seq":53,"time":1783352172557,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","name":"bash","arguments":"{\"command\": \"echo HELLO\", \"description\": \"Echo HELLO\"}"}} {"type":"hook/invoked","seq":54,"time":1783352172558,"data":{"turn":1,"point":"PreToolUse","dialect":"claude","handlerId":"claude:PreToolUse:1","matcher":"bash"}} {"type":"hook/result","seq":55,"time":1783352172573,"data":{"turn":1,"point":"PreToolUse","handlerId":"claude:PreToolUse:1","decision":"ask","exitCode":0,"durationMs":14.113374999999905}} -{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"efe463b8-0601-4607-a431-8eecfeb1b5f0","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} -{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"efe463b8-0601-4607-a431-8eecfeb1b5f0","outcome":"rejected"}} +{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"5ab08815-cec4-4615-88d4-2d5b519762e8","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} +{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"5ab08815-cec4-4615-88d4-2d5b519762e8","outcome":"rejected"}} {"type":"tool/result","seq":58,"time":1783962235814,"data":{"turn":1,"step":1,"callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","content":[{"type":"text","text":"Error: the user rejected tool \"bash\""}],"isError":true},"sourceEventSeqs":[53],"surfaceOp":"append"} {"type":"step/end","seq":59,"time":1783962235814,"data":{"turn":1,"step":1}} {"type":"step/start","seq":60,"time":1783962235814,"data":{"turn":1,"step":2}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index c1cdc1d5d9..c77300fe90 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl @@ -5,7 +5,7 @@ {"type":"approval/policy","seq":3,"time":1783962244578,"data":{"policy":"ask"}} {"type":"user/message","seq":4,"time":1783962244578,"data":{"content":[{"type":"text","text":"Use the bash tool to run exactly this one command in a single call: printf 'before\\n' > out.txt && cat out.txt. Then reply with the single word DONE and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":5,"time":1783962244579,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} {"type":"assistant/chunk","seq":7,"time":1783860667444,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":8,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} {"type":"assistant/chunk","seq":9,"time":1783860667445,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 979124a654..0cbc14dedd 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/session.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl @@ -2,7 +2,7 @@ {"type":"turn/start","seq":0,"time":1783654655602,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} {"type":"user/message","seq":1,"time":1783654655603,"data":{"content":[{"type":"text","text":"Load the snapshot-skill skill with the skill tool, then reply DONE."}],"source":{"kind":"user"}},"surfaceOp":"append"} {"type":"step/start","seq":2,"time":1783654655608,"data":{"turn":1,"step":1}} -{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783654655608,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}],"messagePrefix":[{"role":"user","content":[{"type":"text","text":"\nA skill is a reusable set of task-specific instructions. The following skills are available in this session:\n\n\n- `snapshot-skill`: Exercise project skill discovery and loading in snapshot tests.\n\n\nIf the user names a skill, or the task clearly matches a skill's description, call the `skill` tool with the exact skill name before taking task actions. Load all applicable skills, then follow their full instructions. This catalog contains summaries only; do not infer or follow a skill's instructions until it has been loaded.\n"}]}]},"reason":"initial"}} {"type":"assistant/chunk","seq":4,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} {"type":"assistant/chunk","seq":5,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"Load the requested skill."}}} {"type":"assistant/chunk","seq":6,"time":1783654655609,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"tool-call"}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 3981137f14..69b9fccfc7 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":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), `provider` and `model` (paired LLM target overrides). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"reason":"initial"}} +{"type":"request/header","seq":3,"time":1783600629542,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.","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."},"sandbox_permissions":{"type":"string","description":"The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.","enum":["workspace-write","danger-full-access"]},"justification":{"type":"string","description":"Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access."}},"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":"skill","description":"Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.","parameters":{"type":"object","properties":{"name":{"type":"string","description":"The exact skill name from the available skills list."}},"required":["name"]}},{"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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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."},"provider":{"type":"string","description":"Optional provider override this phase is expected to use."},"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"]}}]},"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/llm/llm/src/assembler.ts b/packages/llm/llm/src/assembler.ts index 68fc2c67b4..8780718c7a 100644 --- a/packages/llm/llm/src/assembler.ts +++ b/packages/llm/llm/src/assembler.ts @@ -36,7 +36,7 @@ export class BlockAssembler { private order: number[] = [] private _usage: TokenUsage | undefined private _finish: FinishReason | undefined - private _replayState: unknown + private _replayState: unknown = undefined /** * Feed one chunk. Returns the completed block when the chunk closes one diff --git a/packages/workflow/tool-workflow/src/index.ts b/packages/workflow/tool-workflow/src/index.ts index 011e45f025..2a8ef96682 100644 --- a/packages/workflow/tool-workflow/src/index.ts +++ b/packages/workflow/tool-workflow/src/index.ts @@ -47,7 +47,7 @@ const DESCRIPTION = `Run a JavaScript workflow script that orchestrates subagent 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?, provider?, 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), \`provider\` and \`model\` (paired LLM target overrides). Anything else (\`effort\`/\`isolation\`/\`agentType\`) is rejected loudly. +- \`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), and independent \`provider\`/\`model\` LLM target overrides (either may be provided alone). 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. diff --git a/packages/workflow/workflow-workerthread/src/runtime.ts b/packages/workflow/workflow-workerthread/src/runtime.ts index 15caf4203a..b5dbed1744 100644 --- a/packages/workflow/workflow-workerthread/src/runtime.ts +++ b/packages/workflow/workflow-workerthread/src/runtime.ts @@ -368,7 +368,7 @@ export class WorkflowExecution { for (const key of Object.keys(record)) { if (SUPPORTED_AGENT_OPTIONS.has(key)) continue if (DEFERRED_AGENT_OPTIONS.has(key)) { - throw new WorkflowError(`agent() option "${key}" is deferred and not supported by this engine (supported: label, phase, schema, model)`, 'UNSUPPORTED_OPTION') + throw new WorkflowError(`agent() option "${key}" is deferred and not supported by this engine (supported: label, phase, schema, provider, model)`, 'UNSUPPORTED_OPTION') } throw new WorkflowError(`agent() option "${key}" is not recognized (supported: label, phase, schema, provider, model)`, 'UNSUPPORTED_OPTION') } diff --git a/packages/workflow/workflow-workerthread/tests/session.spec.ts b/packages/workflow/workflow-workerthread/tests/session.spec.ts index 9bca53f26a..102bcbd9a0 100644 --- a/packages/workflow/workflow-workerthread/tests/session.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/session.spec.ts @@ -341,7 +341,7 @@ describe('runWorkerSession over an in-process MessageChannel', () => { ["return await agent('p', { label: 3 })", '"label" must be a string'], ["return await agent('p', { get label() { throw new Error('read failed') } })", 'options must be plain JSON data'], ["return await agent('p', { bogus: true })", '"bogus" is not recognized'], - ["return await agent('p', { effort: 'high' })", '"effort" is deferred'], + ["return await agent('p', { effort: 'high' })", '"effort" is deferred and not supported by this engine (supported: label, phase, schema, provider, model)'], ["return await agent('p', { schema: { type: 'object', oneOf: [] } })", 'outside the supported subset'], ['return await parallel([() => 1, () => 2, () => 3])', 'over the per-call cap (2)'], ['return await pipeline([1, 2, 3], (x) => x)', 'maxItemsPerCall'], From f1d39921c9e3434f166ee106c01d7eeae362f389 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 13:33:42 +0800 Subject: [PATCH 4/9] feat(acp): advertise and switch llm models --- docs/architecture.md | 2 +- docs/config-catalog.md | 42 ++- docs/cordis-catalog/services.md | 5 +- docs/core-data-structures/core.md | 24 ++ docs/core-data-structures/llm-streaming.md | 2 +- docs/event-producer-consumer.md | 28 +- docs/module-graph.md | 3 +- docs/rfc/INDEX.md | 1 + ...-14-provider-routed-llm-adapters.i18n.yaml | 4 +- ...2026-07-14-provider-routed-llm-adapters.md | 2 +- ...6-07-14-provider-routed-llm-adapters.zh.md | 2 +- ...-model-catalog-and-acp-selection.i18n.yaml | 6 + ...-15-llm-model-catalog-and-acp-selection.md | 66 +++++ ...-llm-model-catalog-and-acp-selection.zh.md | 66 +++++ .../2026-06-14-acp-agent-client-protocol.md | 2 +- .../acp-agent/advanced.cordis.snapshot.yml | 7 + .../acp-agent/both-mode.cordis.snapshot.yml | 7 + .../acp-agent/code-mode.cordis.snapshot.yml | 7 + examples/acp-agent/cordis.snapshot.yml | 7 + examples/acp-agent/fs.cordis.snapshot.yml | 7 + examples/acp-agent/tests/acp.snapshot.ts | 17 +- .../advanced-toolchain/stdout.golden.jsonl | 2 +- .../both-mode-turn/stdout.golden.jsonl | 2 +- .../snapshots/cancel/stdout.golden.jsonl | 2 +- .../code-mode-turn/stdout.golden.jsonl | 2 +- .../config-options/stdout.golden.jsonl | 6 +- .../error-finish/stdout.golden.jsonl | 2 +- .../escalation-approved/stdout.golden.jsonl | 4 +- .../escalation-rejected/stdout.golden.jsonl | 4 +- .../snapshots/fs-edit/stdout.golden.jsonl | 2 +- .../fs-policy-reject/stdout.golden.jsonl | 2 +- .../fs-read-window/stdout.golden.jsonl | 2 +- .../snapshots/fs-read/stdout.golden.jsonl | 2 +- .../fs-terminal-card/stdout.golden.jsonl | 2 +- .../fs-write-overwrite/stdout.golden.jsonl | 2 +- .../snapshots/fs-write/stdout.golden.jsonl | 2 +- .../snapshots/handshake/stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../hook-cc-pretool-ask/stdout.golden.jsonl | 2 +- .../hook-cc-pretool-deny/stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../hook-cc-stop-continue/stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../stdout.golden.jsonl | 2 +- .../snapshots/model-switching/input.json | 23 ++ .../snapshots/model-switching/session.jsonl | 69 +++++ .../model-switching/stdout.golden.jsonl | 47 ++++ .../model-switching/system-prompt.golden.md | 17 ++ .../model-switching/tool-schemas.golden.json | 249 ++++++++++++++++++ .../snapshots/multi-turn/stdout.golden.jsonl | 2 +- .../permission-switching/stdout.golden.jsonl | 6 +- .../repeat-tool-guard/stdout.golden.jsonl | 2 +- .../snapshots/skill-load/stdout.golden.jsonl | 2 +- .../subagent-fork/stdout.golden.jsonl | 2 +- .../subagent-mixed/stdout.golden.jsonl | 2 +- .../subagent-multi/stdout.golden.jsonl | 2 +- .../subagent-spawn/stdout.golden.jsonl | 2 +- .../snapshots/text-turn/stdout.golden.jsonl | 2 +- .../snapshots/todo-plan/stdout.golden.jsonl | 2 +- .../tool-call-turn/stdout.golden.jsonl | 2 +- .../workflow-run/stdout.golden.jsonl | 2 +- .../workspace-edit/stdout.golden.jsonl | 2 +- .../cordis/tool-cordis/src/api-catalog.ts | 11 +- .../tests/contract-regressions.spec.ts | 2 +- packages/llm/llm-deepseek/README.md | 7 +- packages/llm/llm-deepseek/src/adapter.ts | 27 +- packages/llm/llm-deepseek/src/index.ts | 36 ++- .../llm/llm-deepseek/tests/adapter.spec.ts | 74 +++++- packages/llm/llm-pi-ai/README.md | 2 + packages/llm/llm-pi-ai/src/adapter.ts | 14 +- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 19 +- packages/llm/llm/README.md | 7 +- packages/llm/llm/src/index.ts | 85 +++++- packages/llm/llm/src/types.ts | 20 ++ packages/llm/llm/tests/service.spec.ts | 106 +++++++- packages/support/llm-replay/README.md | 14 +- packages/support/llm-replay/src/index.ts | 88 ++++++- .../llm-replay/tests/llm-replay.spec.ts | 41 ++- packages/ui/acp-agent/README.md | 4 +- packages/ui/acp/README.md | 19 +- packages/ui/acp/acp-feature-support.md | 21 +- packages/ui/acp/package.json | 1 + packages/ui/acp/src/index.ts | 189 +++++++++++-- packages/ui/acp/tests/config-options.spec.ts | 208 ++++++++++++++- packages/ui/acp/tests/harness.ts | 35 ++- packages/ui/jsonrpc/src/server.ts | 2 +- packages/ui/jsonrpc/tests/server.spec.ts | 6 +- scripts/type-equiv.manifest.json | 2 + 94 files changed, 1657 insertions(+), 191 deletions(-) create mode 100644 docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml create mode 100644 docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md create mode 100644 docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md create mode 100644 examples/acp-agent/tests/snapshots/model-switching/input.json create mode 100644 examples/acp-agent/tests/snapshots/model-switching/session.jsonl create mode 100644 examples/acp-agent/tests/snapshots/model-switching/stdout.golden.jsonl create mode 100644 examples/acp-agent/tests/snapshots/model-switching/system-prompt.golden.md create mode 100644 examples/acp-agent/tests/snapshots/model-switching/tool-schemas.golden.json diff --git a/docs/architecture.md b/docs/architecture.md index 64a64d26f4..5bef5b52b2 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -126,7 +126,7 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, compaction pricing, and persistence, so block types remain a repo-wide contract. -Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing assistant provider/model provenance plus replay state. An `LlmAdapter` implements `stream()` and registers routes with `ctx.llm.registerAdapter(providers, adapter)`; requests route by `provider`, while the adapter resolves `model`. Replay state reaches a target only when both routes map to the same adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). +Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing assistant provider/model provenance plus replay state. An `LlmAdapter` implements `stream()`, registers provider routes, and may expose advisory selector metadata; the adapter still resolves and validates model ids. Replay state reaches a target only when both routes map to the same adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). ## Extension And Composition diff --git a/docs/config-catalog.md b/docs/config-catalog.md index b090f5b8a9..f26cd085f6 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -11,7 +11,7 @@ A `Requires:` line lists the service keys the plugin `inject`s: its `cordis.yml` ## `@deepseek-ai/dsh-acp` -Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInteraction` +Requires: `agents` · `sessions` · `sessionPersistence` · `tools` · `userInteraction` · `llm` · `systemPrompt` ```ts config-catalog /** Plugin config: the agent template ACP sessions are created from. */ @@ -27,7 +27,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:203`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:208`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` @@ -365,10 +365,22 @@ export interface Config { thinking?: 'enabled' | 'disabled' /** Thinking effort (only meaningful with thinking enabled). */ reasoningEffort?: 'high' | 'max' + /** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */ + models?: DeepSeekCatalogModel[] +} + +/** One optional model entry advertised by the hand-written adapter. */ +export interface DeepSeekCatalogModel { + /** Wire model id accepted by the configured endpoint. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Optional selector detail for deployments with similar model variants. */ + description?: string } ``` -Source: [`packages/llm/llm-deepseek/src/index.ts:30`](../packages/llm/llm-deepseek/src/index.ts) +Source: [`packages/llm/llm-deepseek/src/index.ts:36`](../packages/llm/llm-deepseek/src/index.ts) ## `@deepseek-ai/dsh-llm-pi-ai` @@ -431,10 +443,32 @@ export interface Config { * a nested-agent scenario; absent/empty for a single-session scenario. */ childFiles?: string[] + /** Optional replay-only provider catalog; absent or empty selects catch-all waterfall replay. */ + providers?: ReplayProviderConfig[] +} + +/** One provider route exposed by the replay adapter. */ +export interface ReplayProviderConfig { + /** Provider route used for replay requests. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Advisory models exposed to clients such as ACP editors. */ + models?: ReplayModelConfig[] +} + +/** One model exposed by a replay-only provider catalog. */ +export interface ReplayModelConfig { + /** Model id used for replay requests. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Optional selector description. */ + description?: string } ``` -Source: [`packages/support/llm-replay/src/index.ts:306`](../packages/support/llm-replay/src/index.ts) +Source: [`packages/support/llm-replay/src/index.ts:375`](../packages/support/llm-replay/src/index.ts) ## `@deepseek-ai/dsh-permission` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 567cbcefb2..a02bf9b0fc 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -121,13 +121,14 @@ The abstract `llm` service: an adapter registry plus a streaming model-call surf ```ts cordis-catalog registerAdapter(providers: string[], adapter: LlmAdapter): () => void -providers(): string[] +listProviders(): LlmProviderInfo[] +async listModels(provider: string): Promise stream(options: GenerateOptions): AsyncIterable ``` Types: [GenerateOptions](../core-data-structures/core.md) · [StreamChunk](../core-data-structures/llm-streaming.md) -Source: [`packages/llm/llm/src/index.ts:76`](../../packages/llm/llm/src/index.ts) +Source: [`packages/llm/llm/src/index.ts:96`](../../packages/llm/llm/src/index.ts) ## `ctx.permission` — `PermissionService` diff --git a/docs/core-data-structures/core.md b/docs/core-data-structures/core.md index 89cd9b3cb7..0004007239 100644 --- a/docs/core-data-structures/core.md +++ b/docs/core-data-structures/core.md @@ -150,6 +150,30 @@ One model call is a fully-assembled `GenerateOptions`. The adapter answers with Source: [`packages/llm/llm/src/types.ts`](../../packages/llm/llm/src/types.ts) +Provider and model discovery uses small provider-neutral descriptors. A model catalog is advisory: routing still keys on a registered provider, and an adapter may accept unlisted model ids. + +```ts type-equiv +interface LlmProviderInfo { + /** Provider route key used by {@link GenerateOptions.provider}. */ + id: string + /** Human-readable provider name for selectors and diagnostics. */ + name: string +} +``` + +```ts type-equiv +interface LlmModelInfo { + /** Provider route that owns this model entry. */ + provider: string + /** Model id passed to {@link GenerateOptions.model}. */ + id: string + /** Human-readable model name for selectors. */ + name: string + /** Optional user-facing distinction from otherwise similar models. */ + description?: string +} +``` + ```ts type-equiv interface GenerateOptions { /** Registered provider route selecting the adapter instance. */ diff --git a/docs/core-data-structures/llm-streaming.md b/docs/core-data-structures/llm-streaming.md index b4b9d0f840..f9489a6d7f 100644 --- a/docs/core-data-structures/llm-streaming.md +++ b/docs/core-data-structures/llm-streaming.md @@ -68,7 +68,7 @@ interface TokenUsage { ## The seam -`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). +`LlmAdapter` is the provider seam: subclass, implement `stream()`, and register one adapter instance with `ctx.llm.registerAdapter(providers, adapter)`. `GenerateOptions.provider` selects the registered adapter; `GenerateOptions.model` is passed to that adapter and need not be registered at lifecycle start. Duplicate provider routes fail atomically. Optional `providerInfo()` and asynchronous `listModels()` methods feed `LlmService.listProviders()` / `listModels()` with detached selector metadata. That catalog is advisory rather than a request whitelist: the adapter remains authoritative and may accept unlisted model ids. Adapter lookup happens at the terminal continuation of the `llm/stream` waterfall, so a listener may short-circuit the call or route a mutable one-shot request before lookup. The `block-start` / `block-end` `index` correlation and the assembler together mean an adapter only has to emit well-formed chunks — block reassembly is not each adapter's problem. The consumer surface (`ctx.llm.stream()`) and the `llm/stream` waterfall are described in [architecture.md § Content blocks and streaming](../architecture.md#content-blocks-and-streaming-dsh-llm). `ContentBlockType` (the key set the `index`-correlated blocks carry) derives from `ContentBlockMap`: diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 4231f0fe8d..342407cde1 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,19 +7,19 @@ This matrix shows which packages dispatch each harness-owned event and which pac | Event | Mode | Declared in | Dispatchers | Listeners | | --- | --- | --- | --- | --- | -| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:139`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | -| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:148`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | -| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:283`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:202`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | -| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:212`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | -| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:167`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | -| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:224`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:239`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | -| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:180`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:157`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | -| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:250`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | -| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:260`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | -| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:270`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:141`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio`](../packages/ui/stdio) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:150`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio`](../packages/ui/stdio) | +| `agent/error` | `emit` | [`packages/core/agent/src/types.ts:285`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:204`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`compact-basic`](../packages/compact/compact-basic), [`user-approval`](../packages/ui/user-approval) | +| `agent/prompt-submit` | `waterfall` | [`packages/core/agent/src/types.ts:214`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp), [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard) | +| `agent/queued` | `emit` | [`packages/core/agent/src/types.ts:169`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | +| `agent/request` | `waterfall` | [`packages/core/agent/src/types.ts:226`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`acp`](../packages/ui/acp) | +| `agent/session-prefix` | `waterfall` | [`packages/core/agent/src/types.ts:241`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`tool-skill`](../packages/skill/tool-skill) | +| `agent/session-start` | `emit` | [`packages/core/agent/src/types.ts:182`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/status` | `emit` | [`packages/core/agent/src/types.ts:159`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | [`invariants`](../packages/support/invariants), [`repeat-tool-guard`](../packages/guard/repeat-tool-guard), [`stdio`](../packages/ui/stdio) | +| `agent/step-result` | `waterfall` | [`packages/core/agent/src/types.ts:252`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | - | +| `agent/turn-continuation` | `waterfall` | [`packages/core/agent/src/types.ts:262`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`waterfall`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`hooks-codex`](../packages/hooks/hooks-codex) | +| `agent/turn-stop` | `serial` | [`packages/core/agent/src/types.ts:272`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`serial`) | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | `approval/request` | `waterfall` | [`packages/ui/user-approval/src/index.ts:31`](../packages/ui/user-approval/src/index.ts) | [`user-approval`](../packages/ui/user-approval) (`waterfall`) | [`acp`](../packages/ui/acp) | | `fs/edit-intent` | `waterfall` | [`packages/fs/fs/src/index.ts:59`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`waterfall`) | [`fs-policy`](../packages/fs/fs-policy) | | `fs/observed` | `emit` | [`packages/fs/fs/src/index.ts:68`](../packages/fs/fs/src/index.ts) | [`tool-fs`](../packages/fs/tool-fs) (`emit`) | [`fs-policy`](../packages/fs/fs-policy) | @@ -33,7 +33,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:66`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`emit`) | [`tool-subagent`](../packages/subagent/tool-subagent) | | `subagent/provider-removed` | `emit` | [`packages/subagent/subagent/src/index.ts:72`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`tool-subagent`](../packages/subagent/tool-subagent) | | `subagent/start` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude) | -| `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | +| `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:27`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | [`acp`](../packages/ui/acp) | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:33`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:116`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | | `tools/execute` | `waterfall` | [`packages/core/tools/src/index.ts:89`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`waterfall`) | [`timeout-policy`](../packages/timeout/timeout-policy) | diff --git a/docs/module-graph.md b/docs/module-graph.md index 7ceab41537..4793021e99 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -262,6 +262,7 @@ flowchart TD pkg_acp --> pkg_sandbox pkg_acp --> pkg_session pkg_acp --> pkg_session_persistence + pkg_acp --> pkg_system_prompt pkg_acp --> pkg_tools pkg_acp --> pkg_user_approval pkg_acp --> pkg_user_interaction @@ -404,7 +405,7 @@ flowchart TD | [`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` | [`scope`](../packages/core/scope), [`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) | -| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`user-interaction`](../packages/ui/user-interaction) | +| [`acp`](../packages/ui/acp) | `ui` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`permission`](../packages/ui/permission), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session), [`session-persistence`](../packages/session-persistence/session-persistence), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval), [`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) | | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index c2d46bfa38..3573abfd5b 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -145,6 +145,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Single-file executable SDK runtime distribution (single-exe)](implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md) | 2026-07-10 | | [Agent-scope runtime design and correctness](implemented/architecture/2026-07-12-agent-scope-runtime-design.md) | 2026-07-12 | | [Provider-routed LLM adapters and a generic pi-ai backend](implemented/architecture/2026-07-14-provider-routed-llm-adapters.md) | 2026-07-14 | +| [Advisory LLM catalogs and per-session ACP model selection](implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) | 2026-07-15 | ### Process diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml index bf3c184ef9..48055ef6b7 100644 --- a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml +++ b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.i18n.yaml @@ -2,5 +2,5 @@ # side as of the last confirmed-consistent state. Both languages carry equal authority; # after editing either side, bring the other along and re-record with: # pnpm run verify-translation-pairing --write -2026-07-14-provider-routed-llm-adapters.md: 4dc9a69cc37b4c6708b85f52ad62641102f20cdd -2026-07-14-provider-routed-llm-adapters.zh.md: dbf04eab6f163f9917837f0b93130efd3abff24e +2026-07-14-provider-routed-llm-adapters.md: 75ef047a7f95621d9a9c018b6dc57439e6f2bb22 +2026-07-14-provider-routed-llm-adapters.zh.md: 75ac9adbe5f8e96930a72a977c1969ff3a119ee8 diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md index 4dc9a69cc3..75ef047a7f 100644 --- a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md +++ b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.md @@ -20,7 +20,7 @@ The adapter configuration also assumes one DeepSeek API key and endpoint. A gene `GenerateOptions` and `LlmCallConfig` carry `provider: string` beside `model: string`; `AgentOptions` carries the corresponding optional creation field. A loop request is valid only after both values are non-empty, and both values are part of the logged request header. `agent/request` may return a replacement pair on any step, so a session can switch providers and models without changing the Cordis plugin lifecycle. -`LlmService` registers and resolves adapters by provider. `registerAdapter(providers, adapter)` checks the entire provider list before mutating the registry, rejects a duplicate with `DUPLICATE_ADAPTER`, and disposes the whole registration as one effect. `providers()` reports the registered keys. Model ids are not registered or enumerated by the service; the selected adapter validates or forwards them. +`LlmService` registers and resolves adapters by provider. `registerAdapter(providers, adapter)` checks the entire provider list before mutating the registry, rejects a duplicate with `DUPLICATE_ADAPTER`, and disposes the whole registration as one effect. Model ids are not registration keys; the selected adapter still validates or forwards them. The later [LLM catalog and ACP selection RFC](2026-07-15-llm-model-catalog-and-acp-selection.md) added advisory `listProviders()` / `listModels()` discovery without turning model membership into request validation. A provider has exactly one adapter owner in a Cordis context. `dsh-llm-deepseek` registers `deepseek`; `dsh-llm-pi-ai` may also register `deepseek`, but loading both owners is a configuration error rather than an ordering rule or fallback. A deployment that wants the hand-rolled DeepSeek implementation excludes `deepseek` from the pi-ai profiles. A deployment that wants pi-ai's DeepSeek implementation does not mount `dsh-llm-deepseek`. diff --git a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md index dbf04eab6f..75ac9adbe5 100644 --- a/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md +++ b/docs/rfc/implemented/architecture/2026-07-14-provider-routed-llm-adapters.zh.md @@ -20,7 +20,7 @@ Status: implemented `GenerateOptions` 与 `LlmCallConfig` 在 `model: string` 之外携带 `provider: string`，`AgentOptions` 则携带对应的可选创建字段。只有两个值都非空时，agent loop（智能体循环）请求才有效；两个值也都会写入请求头日志。`agent/request` 可以在任意步骤返回替换后的字段组合，因此会话可以切换提供方与模型，无需改变 Cordis 插件生命周期。 -`LlmService` 按提供方注册和解析适配器。`registerAdapter(providers, adapter)` 在修改注册表前检查整个提供方列表，遇到重复项时返回 `DUPLICATE_ADAPTER`，并将整组注册作为一个 effect 释放。`providers()` 返回已注册的键。服务不注册或枚举模型 ID；由选中的适配器负责验证或转发模型 ID。 +`LlmService` 按提供方注册和解析适配器。`registerAdapter(providers, adapter)` 在修改注册表前检查整个提供方列表，遇到重复项时返回 `DUPLICATE_ADAPTER`，并将整组注册作为一个 effect 释放。模型 ID 不作为注册键；仍由选中的适配器负责验证或转发。后续的 [LLM 目录与 ACP 模型选择 RFC](2026-07-15-llm-model-catalog-and-acp-selection.md) 增加了建议性的 `listProviders()` / `listModels()` 发现接口，但不会把目录成员关系变成请求校验规则。 在一个 Cordis 上下文中，一个提供方只能有一个适配器所有者。`dsh-llm-deepseek` 注册 `deepseek`；`dsh-llm-pi-ai` 也可以注册 `deepseek`，但同时加载两个所有者属于配置错误，不采用顺序规则或回退行为。若部署选择手写的 DeepSeek 实现，需从 pi-ai 配置中排除 `deepseek`；若部署选择 pi-ai 的 DeepSeek 实现，则不挂载 `dsh-llm-deepseek`。 diff --git a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml new file mode 100644 index 0000000000..c2fb5daa62 --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# side as of the last confirmed-consistent state. Both languages carry equal authority; +# after editing either side, bring the other along and re-record with: +# pnpm run verify-translation-pairing --write +2026-07-15-llm-model-catalog-and-acp-selection.md: bacfe180faf4d600d027a7aab6073130012b6022 +2026-07-15-llm-model-catalog-and-acp-selection.zh.md: 7e4bbf835a50c31c28bc40e3030425455390b598 diff --git a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md new file mode 100644 index 0000000000..bacfe180fa --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md @@ -0,0 +1,66 @@ +# RFC: Advisory LLM catalogs and per-session ACP model selection + +Status: implemented + +English | [中文](2026-07-15-llm-model-catalog-and-acp-selection.zh.md) + +## Problem + +Provider-routed adapters let every request choose `provider + model`, but `LlmService` exposed only routing and streaming. A UI could not discover which providers were registered or which models an adapter was prepared to recommend. ACP clients therefore received no `model` session config option, so Zed, JetBrains, and VS Code integrations had no model list even though the request seam already supported runtime switching. + +Model discovery cannot become request validation. The hand-written DeepSeek adapter deliberately forwards arbitrary model ids to a public or private endpoint, while pi-ai has a finite installed catalog that is authoritative for its own request resolution. Treating one shared catalog as a whitelist would remove the private-endpoint behavior that provider routing was designed to preserve. + +ACP selection must also preserve the provider dimension. The same model id may appear under multiple routes, and switching a global adapter or agent template would leak one editor session's choice into every other session. Prompt variables and request routing must change together; a selection that lands during asynchronous prompt assembly cannot make `{{model}}` name one model while the request reaches another. + +## Decision + +### Provider-neutral advisory discovery + +`LlmAdapter` gains `providerInfo(provider)` and asynchronous `listModels(provider)` methods. Their provider-neutral results are `LlmProviderInfo { id, name }` and `LlmModelInfo { provider, id, name, description? }`. The defaults preserve existing adapter behavior by naming a provider after its route and advertising no models. + +`LlmService.listProviders()` returns detached metadata in registration order. `LlmService.listModels(provider)` delegates to the route owner, validates non-empty ids and names, rejects a mismatched provider or duplicate model id with `INVALID_CATALOG`, and returns detached values. Unknown providers still fail with `NO_ADAPTER`. Provider metadata is validated atomically during `registerAdapter()` so a malformed display record cannot leave a partial registration. + +Catalog membership is advisory. It drives selectors and diagnostics but never changes `stream()` routing and never rejects an otherwise valid request. Provider ownership remains exclusive and lifecycle-bound; model ids remain request-time adapter input. + +`dsh-llm-pi-ai` maps the configured provider's installed `getModels(provider)` entries into the neutral catalog. Its existing request-time catalog lookup remains authoritative and still rejects unknown models with `UNKNOWN_MODEL`. `dsh-llm-deepseek` accepts an optional `models` config containing display entries, defaulting to `deepseek-v4-flash` and `deepseek-v4-pro`. An explicit list replaces those defaults and an empty list disables discovery. The entries improve selector UX for known public or private models, while every unlisted model id continues to pass through unchanged. + +### ACP session config option + +The ACP bridge advertises one select with `id: model` and `category: model` in `session/new` and `session/load` when the session has a complete target whose provider is registered. Each opaque option value encodes the full provider/model pair. Models are grouped by provider when multiple non-empty provider groups exist; a single group is flattened for clients that render simple selects better. + +The session's current target is added to the displayed options when its adapter omits it. This preserves custom DeepSeek and private-endpoint models while keeping the adapter catalog advisory. A target with an unregistered provider is not advertised, and a model-less agent remains available to another `agent/request` supplier. + +`session/set_config_option` accepts only values from the current catalog snapshot and updates a target reference owned by that ACP session. No global `LlmService` or `AgentOptions` state changes, so concurrent sessions may select different providers and models. The existing permission select remains independent, and every response returns the complete refreshed option state. + +### Prompt/request consistency and durability + +Agent setup installs scoped `system-prompt/assemble` and `agent/request` listeners. Prompt assembly snapshots the selected pair once per step, overwrites the assembled `provider` and `model` variables after downstream prompt listeners, and the request listener applies that same snapshot after downstream request listeners. A selection during asynchronous assembly therefore starts on the next step rather than splitting prompt text from routing. Other call-config fields remain untouched. + +The request header remains the durable source of truth. When a selected target is actually used, the existing `request/header` or `request/header-delta` event records it. `session/load` initializes the ACP selection from the folded last request header before falling back to bridge config. A selection that is never used by a request is intentionally in-memory only because it never became model-visible state. + +ACP's experimental `providers/*` capability is not used. That draft surface configures provider base URLs, protocols, and headers, including secrets; it does not enumerate models and would give the UI authority to rewrite deployment-owned adapter configuration. + +## Alternatives considered + +**Return model strings only.** A model-only value loses the provider route and becomes ambiguous as soon as two providers expose the same id. + +**Make catalogs mandatory whitelists.** This conflicts with the hand-written adapter's arbitrary model pass-through and private deployments. The selected adapter already owns authoritative request validation. + +**Store selection in `AgentOptions` or `LlmService`.** Those are creation-wide or deployment-wide objects. Mutating them would couple concurrent ACP sessions and bypass the logged `agent/request` replacement path. + +**Persist a new model-selection session event immediately.** An unused UI selection has not affected a model request. Recording the existing request header when the target is consumed preserves the model-visible-if-and-only-if-logged rule without adding a second source of truth. + +**Use ACP `providers/*`.** That unstable API changes endpoint and authentication configuration rather than selecting a model for one session, and its lifecycle and secret-handling semantics do not match this feature. + +## Consequences + +- Any adapter can expose a dynamic model list without leaking provider-library types into the core seam. +- Catalog consumers must treat absence as “not advertised,” never “invalid request.” +- pi-ai-backed ACP deployments automatically inherit the installed pi-ai provider catalogs; hand-written DeepSeek deployments list known choices explicitly and retain arbitrary model support. +- ACP clients receive a standard stable model config option, with provider-aware values and per-session isolation. +- Request headers remain compatible with the provider-routed session shape; no new JSONL event or format version is required. +- A catalog read can be asynchronous. ACP reads a detached snapshot before creating or resuming an agent, so discovery failure cannot leave a partially published session. + +## Testing + +Unit coverage validates catalog detachment and malformed metadata, pi-ai and DeepSeek catalog projection, ACP provider grouping, custom-current insertion, invalid values, provider/model request routing, prompt-variable alignment, concurrent-session isolation, model-less fallback, and load restoration from the request header. The existing ACP transport suites verify that the additional config option does not change prompt, cancellation, replay, approval, or tool-rendering behavior. diff --git a/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md new file mode 100644 index 0000000000..7e4bbf835a --- /dev/null +++ b/docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.zh.md @@ -0,0 +1,66 @@ +# RFC: 建议性 LLM 目录与 ACP 会话级模型选择 + +Status: implemented + +[English](2026-07-15-llm-model-catalog-and-acp-selection.md) | 中文 + +## 问题 + +基于提供方路由的适配器允许每次请求选择 `provider + model`，但 `LlmService` 只暴露路由和流式调用。UI 无法发现已注册的提供方，也无法知道适配器愿意推荐哪些模型。因此，ACP 客户端收不到 `model` 会话配置项；即使请求接缝已经支持运行时切换，Zed、JetBrains 和 VS Code 集成仍没有模型列表。 + +模型发现不能变成请求校验。手写 DeepSeek 适配器会把任意模型 ID 原样转发给公开或私有端点，而 pi-ai 的有限安装目录则是其自身请求解析的权威依据。将共享目录视为白名单，会破坏提供方路由需要保留的私有端点能力。 + +ACP 选择还必须保留提供方维度。同一个模型 ID 可能存在于多个路由下；切换全局适配器或 agent 模板会让一个编辑器会话的选择泄漏到其他会话。Prompt 变量与请求路由必须同时变化；如果选择发生在异步 prompt 组装期间，不能让 `{{model}}` 表示一个模型、实际请求却到达另一个模型。 + +## 决策 + +### 提供方中立的建议性发现 + +`LlmAdapter` 增加 `providerInfo(provider)` 与异步 `listModels(provider)` 方法。其提供方中立结果分别为 `LlmProviderInfo { id, name }` 和 `LlmModelInfo { provider, id, name, description? }`。默认实现以路由名称作为提供方名称，并且不展示模型，从而保持现有适配器行为。 + +`LlmService.listProviders()` 按注册顺序返回分离后的元数据。`LlmService.listModels(provider)` 委托给路由所有者，校验非空 ID 和名称，并在提供方不匹配或模型 ID 重复时以 `INVALID_CATALOG` 失败，最后返回分离后的值。未知提供方仍以 `NO_ADAPTER` 失败。提供方元数据在 `registerAdapter()` 期间进行原子校验，错误展示记录不会留下部分注册。 + +目录成员关系仅提供建议。它驱动选择器与诊断，但不会改变 `stream()` 路由，也不会拒绝原本有效的请求。提供方所有权仍然具有排他性并绑定生命周期；模型 ID 仍是请求时传给适配器的输入。 + +`dsh-llm-pi-ai` 将已配置提供方的安装目录 `getModels(provider)` 映射为中立目录。其现有请求时目录查询仍是权威依据，未知模型仍以 `UNKNOWN_MODEL` 失败。`dsh-llm-deepseek` 接受可选的 `models` 配置作为展示条目，默认包含 `deepseek-v4-flash` 和 `deepseek-v4-pro`。显式列表会替换这些默认值，空列表则关闭发现。这些条目改善已知公开或私有模型的选择体验，而所有未列出的模型 ID 仍会原样透传。 + +### ACP 会话配置项 + +当会话具有完整目标且目标提供方已注册时，ACP bridge 会在 `session/new` 与 `session/load` 中展示一个 `id: model`、`category: model` 的选择项。每个不透明选项值都编码完整的提供方/模型字段组合。存在多个非空提供方分组时按提供方分组；只有一个分组时将其展开，以便对简单选择器支持更好的客户端展示。 + +如果适配器目录未包含会话当前目标，该目标仍会加入展示选项。这能保留自定义 DeepSeek 与私有端点模型，同时维持目录的建议性。提供方未注册的目标不会展示；缺少模型的 agent 仍可由其他 `agent/request` 提供者补齐。 + +`session/set_config_option` 只接受当前目录快照中的值，并更新该 ACP 会话独占的目标引用。它不会修改全局 `LlmService` 或 `AgentOptions` 状态，因此并发会话可以选择不同的提供方和模型。现有权限选择项保持独立，每次响应都返回完整的刷新后配置项状态。 + +### Prompt/请求一致性与持久化 + +Agent setup 会安装作用域内的 `system-prompt/assemble` 与 `agent/request` 监听器。Prompt 组装为每个 step 只快照一次选中的字段组合，在下游 prompt 监听器完成后覆盖组装结果中的 `provider` 与 `model` 变量；请求监听器则在下游请求监听器完成后应用同一个快照。因此，异步组装期间发生的选择会从下一个 step 生效，不会导致 prompt 文本与路由分裂。其他调用配置字段保持不变。 + +请求头仍是持久化事实来源。当选中目标被实际使用时，现有 `request/header` 或 `request/header-delta` 事件会记录它。`session/load` 先从折叠后的最后请求头初始化 ACP 选择，再回退到 bridge 配置。一个从未被请求使用的选择只保留在内存中，因为它从未成为模型可见状态。 + +本功能不使用 ACP 的实验性 `providers/*` 能力。该草案接口配置提供方 base URL、协议和 headers，其中可能包含密钥；它不枚举模型，并且会赋予 UI 改写部署所有的适配器配置的权力。 + +## 考虑过的替代方案 + +**只返回模型字符串。** 仅模型值会丢失提供方路由；两个提供方暴露相同 ID 时立刻产生歧义。 + +**将目录设为强制白名单。** 这与手写适配器的任意模型透传和私有部署冲突。请求的权威校验本就属于被选中的适配器。 + +**将选择存入 `AgentOptions` 或 `LlmService`。** 这些对象分别面向创建过程或整个部署。修改它们会耦合并发 ACP 会话，并绕开带日志归因的 `agent/request` 替换路径。 + +**立即写入新的模型选择会话事件。** 尚未使用的 UI 选择没有影响模型请求。目标被消费时记录现有请求头，既满足“模型可见当且仅当已记录”的规则，也不会引入第二个事实来源。 + +**使用 ACP `providers/*`。** 该不稳定 API 用于修改端点与认证配置，而不是为单个会话选择模型；其生命周期和密钥处理语义都不适合本功能。 + +## 结果 + +- 任意适配器都能暴露动态模型列表，无需把提供方库类型泄漏到核心接缝。 +- 目录消费者必须把缺失理解为“未展示”，而不是“请求无效”。 +- 基于 pi-ai 的 ACP 部署会自动继承已安装的 pi-ai 提供方目录；手写 DeepSeek 部署显式列出已知选项，同时保留任意模型能力。 +- ACP 客户端会收到稳定标准的模型配置项，其中的值保留提供方信息，并按会话隔离。 +- 请求头继续使用基于提供方路由的会话结构；不需要增加 JSONL 事件或格式版本。 +- 目录读取可以是异步的。ACP 在创建或恢复 agent 前读取分离后的快照，因此发现失败不会留下部分发布的会话。 + +## 测试 + +单元测试覆盖目录分离与错误元数据、pi-ai 和 DeepSeek 目录投影、ACP 提供方分组、自定义当前模型补入、无效值、提供方/模型请求路由、prompt 变量一致性、并发会话隔离、无模型回退，以及从请求头恢复选择。现有 ACP 传输测试验证新增配置项不会改变 prompt、取消、回放、审批或工具展示行为。 diff --git a/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md b/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md index bfd0e6a10e..ea4b98c31d 100644 --- a/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md +++ b/docs/rfc/implemented/feature/2026-06-14-acp-agent-client-protocol.md @@ -48,7 +48,7 @@ The precise supported and deferred protocol rows live in [`packages/ui/acp/acp-f Editors can create, load, prompt, cancel, render, ask, and reconfigure multiple harness sessions over one ACP connection without a loop-specific dependency. The session event log remains the durable source for replay, prompt settlement, cwd, and per-session configuration. Tool presentation and human-answer channels remain extensible plugin contracts instead of ACP-specific behavior. -The bridge deliberately does not implement session list/delete/resume/close capabilities, MCP passthrough, additional directories, image/audio/embedded-resource prompts, runtime model selection, plans, slash commands, usage updates, editor filesystem delegation, or the ACP terminal execution sub-protocol. The feature checklist records these as unsupported rather than silently accepting them. +The bridge deliberately does not implement session list/delete/resume/close capabilities, MCP passthrough, additional directories, image/audio/embedded-resource prompts, plans, slash commands, usage updates, editor filesystem delegation, or the ACP terminal execution sub-protocol. Runtime model selection was added later through standard session config options by the [LLM catalog and ACP selection RFC](../architecture/2026-07-15-llm-model-catalog-and-acp-selection.md). An idle config selection is truthful in the live response but not durable until the next `agent/prompt-submit` anchors it inside the open turn. Crashing before that boundary loses the pending selection; this is the cost of keeping session events turn-enclosed and replay-safe. diff --git a/examples/acp-agent/advanced.cordis.snapshot.yml b/examples/acp-agent/advanced.cordis.snapshot.yml index a70da9fb49..bff2f73bd5 100644 --- a/examples/acp-agent/advanced.cordis.snapshot.yml +++ b/examples/acp-agent/advanced.cordis.snapshot.yml @@ -26,3 +26,10 @@ name: '@deepseek-ai/dsh-tool-cordis' - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/both-mode.cordis.snapshot.yml b/examples/acp-agent/both-mode.cordis.snapshot.yml index 2b9391bcbd..51c96cf2fa 100644 --- a/examples/acp-agent/both-mode.cordis.snapshot.yml +++ b/examples/acp-agent/both-mode.cordis.snapshot.yml @@ -26,3 +26,10 @@ name: '@deepseek-ai/dsh-code-runtime-worker' - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/code-mode.cordis.snapshot.yml b/examples/acp-agent/code-mode.cordis.snapshot.yml index a4f2878def..ccd5d62751 100644 --- a/examples/acp-agent/code-mode.cordis.snapshot.yml +++ b/examples/acp-agent/code-mode.cordis.snapshot.yml @@ -26,3 +26,10 @@ name: '@deepseek-ai/dsh-code-runtime-worker' - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/cordis.snapshot.yml b/examples/acp-agent/cordis.snapshot.yml index 90a2fa6a2a..e4d717a399 100644 --- a/examples/acp-agent/cordis.snapshot.yml +++ b/examples/acp-agent/cordis.snapshot.yml @@ -28,3 +28,10 @@ - insert: - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/fs.cordis.snapshot.yml b/examples/acp-agent/fs.cordis.snapshot.yml index 53f2d677e2..d66bfa61cd 100644 --- a/examples/acp-agent/fs.cordis.snapshot.yml +++ b/examples/acp-agent/fs.cordis.snapshot.yml @@ -19,3 +19,10 @@ name: '@deepseek-ai/dsh-tool-fs' - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro diff --git a/examples/acp-agent/tests/acp.snapshot.ts b/examples/acp-agent/tests/acp.snapshot.ts index 0d29f7b5ce..09af1f12a5 100644 --- a/examples/acp-agent/tests/acp.snapshot.ts +++ b/examples/acp-agent/tests/acp.snapshot.ts @@ -62,6 +62,17 @@ const SCENARIOS: Scenario[] = [ { name: 'fs-read-window', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG }, { name: 'fs-policy-reject', hasModelTurn: true, recorded: true, headerClass: 'fs', configPath: FS_CONFIG }, { name: 'multi-turn', hasModelTurn: true, recorded: true }, + // ACP exposes the adapter catalog as a session-scoped model select. This + // scenario pins the default flash request, the switch response, and the + // resulting request-header delta to pro. + { + name: 'model-switching', + hasModelTurn: true, + recorded: true, + pinsHeader: true, + expectedHeaderDeltas: 1, + headerClass: 'model-switching', + }, { name: 'error-finish', hasModelTurn: true, recorded: false, overridden: true }, // Keyless, authored (like error-finish/cancel): deterministically forcing a // LIVE model to repeat one call three times is not a stable recording, so @@ -117,9 +128,9 @@ const SCENARIOS: Scenario[] = [ // tool/code-dispatch events. Each overlay composes and pins its own header class. { name: 'code-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'code', configPath: CODE_MODE_CONFIG }, { name: 'both-mode-turn', hasModelTurn: true, recorded: true, pinsHeader: true, headerClass: 'both', configPath: BOTH_MODE_CONFIG }, - // The default tree owns the single Permissions select. Snapshot mode starts - // in danger-full-access so established fixtures stay runner-independent; - // these policy scenarios switch to workspace-write in their input scripts. + // The default tree also owns the Permissions select. Snapshot mode starts in + // danger-full-access so established fixtures stay runner-independent; these + // policy scenarios switch to workspace-write in their input scripts. // Real-kernel confinement remains in escalation.e2e.ts and the sandbox // packages' e2e suites. { name: 'config-options', hasModelTurn: false, recorded: false, headerClass: 'sandbox' }, diff --git a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl index bc4da17bb0..45d5628762 100644 --- a/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-mount","title":"Mount plugin into live cordis runtime","kind":"execute","status":"in_progress","rawInput":{"code":"return { name: 'snapshot-marker', apply() {} }"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"advanced-mount","status":"completed","content":[{"type":"content","content":{"type":"text","text":"mounted dyn-1 (plugin \"snapshot-marker\", state: active)"}}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"advanced-code","title":"return await tools.cordis_inspect({ what: 'dynamic' })","kind":"execute","status":"in_progress","rawInput":"return await tools.cordis_inspect({ what: 'dynamic' })"}}} diff --git a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl index 577f10445b..7b2dbd604c 100644 --- a/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl index 60235cac75..d31c8fdcfb 100644 --- a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl @@ -1,4 +1,4 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"partial"}}}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl index bfa379815e..31ec5df39a 100644 --- a/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/code-mode-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl index aa033fb673..1aca0c6586 100644 --- a/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/config-options/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":5,"error":{"code":-32602,"message":"Invalid params: unknown permission value \"plan\""}} {"jsonrpc":"2.0","id":6,"error":{"code":-32602,"message":"Invalid params: unknown config option \"reasoning-effort\""}} diff --git a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl index d5d4f1c400..484b241427 100644 --- a/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/error-finish/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"error":{"code":-32603,"message":"Internal error: turn failed: simulated provider error (HTTP 401)"}} diff --git a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl index f438444dc4..9180f2426a 100644 --- a/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl index b926355bd7..871f3e3281 100644 --- a/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl index 800d7d608a..df664a96b4 100644 --- a/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl index fd5c9f1aea..dda4f70968 100644 --- a/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-policy-reject/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl index ab3eb2da31..fde77464d8 100644 --- a/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read-window/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl index fc0edbbe8b..d6b2e00b1e 100644 --- a/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl index 0e7dcca6f8..b35af2c650 100644 --- a/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-terminal-card/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl index f0ca9674cb..c5dcf0a7b0 100644 --- a/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write-overwrite/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl index 3c01ab158c..7969eeba3b 100644 --- a/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl index e4c4984fc5..011175a871 100644 --- a/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/handshake/stdout.golden.jsonl @@ -1,2 +1,2 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl index 8c97f359b7..90ab26d54e 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl index e9243d8a05..e60a33bcd5 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl index 3905e82ca7..a748546e51 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl index 92906adb59..60ae1f14e4 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-pretool-deny/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl index 6304582220..765dd87f7f 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl index c4ad3ba541..e609fc0d70 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"'s"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl index 5c4a564d26..c7e8beeab3 100644 --- a/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-cc-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl index bd1e04bc59..6257014596 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl index 4bf92f3197..55310f6b3a 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-posttool-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl index 5459da1a17..8eba2d862e 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-pretool-block/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl index 6304582220..765dd87f7f 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-block/stdout.golden.jsonl @@ -1,3 +1,3 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","id":3,"result":{"stopReason":"cancelled"}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl index 8cae81a5c9..76140724de 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-promptsubmit-context/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" asked"}}}} diff --git a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl index 66d8c816be..af9959379d 100644 --- a/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/hook-codex-stop-continue/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/model-switching/input.json b/examples/acp-agent/tests/snapshots/model-switching/input.json new file mode 100644 index 0000000000..3612f367f6 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/input.json @@ -0,0 +1,23 @@ +{ + "steps": [ + { + "op": "initialize" + }, + { + "op": "newSession" + }, + { + "op": "prompt", + "text": "Without using tools, reply with exactly FLASH and stop." + }, + { + "op": "setConfigOption", + "configId": "model", + "value": "[\"deepseek\",\"deepseek-v4-pro\"]" + }, + { + "op": "prompt", + "text": "Without using tools, reply with exactly PRO and stop." + } + ] +} diff --git a/examples/acp-agent/tests/snapshots/model-switching/session.jsonl b/examples/acp-agent/tests/snapshots/model-switching/session.jsonl new file mode 100644 index 0000000000..4402c9582b --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/session.jsonl @@ -0,0 +1,69 @@ +{"type":"session","version":0,"id":"622d16ce-0a94-476b-97a4-26dad50b1fbf","createdAt":1784086275585,"cwd":"/var/folders/_g/59jgff8x2gqd39f5vy1wnbfc0000gn/T/acp-snap-cwd-Cwf7Bh"} +{"type":"turn/start","seq":0,"time":1784086275588,"data":{"turn":1,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":1,"time":1784086275588,"data":{"content":[{"type":"text","text":"Without using tools, reply with exactly FLASH and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":2,"time":1784086275590,"data":{"turn":1,"step":1}} +{"type":"request/header","seq":3,"time":1784086275590,"data":{"header":{"config":{"provider":"deepseek","model":"deepseek-v4-flash"},"system":"{{system}}","tools":"{{tools}}"},"reason":"initial"}} +{"type":"assistant/chunk","seq":4,"time":1784086276525,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":5,"time":1784086276526,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":6,"time":1784086276605,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":7,"time":1784086276639,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":8,"time":1784086276640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":9,"time":1784086276640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":10,"time":1784086276640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":11,"time":1784086276640,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":12,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":13,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":14,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"FL"}}} +{"type":"assistant/chunk","seq":15,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"ASH"}}} +{"type":"assistant/chunk","seq":16,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":17,"time":1784086276661,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":18,"time":1784086276710,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":19,"time":1784086276710,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":20,"time":1784086276771,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" without"}}} +{"type":"assistant/chunk","seq":21,"time":1784086276771,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} +{"type":"assistant/chunk","seq":22,"time":1784086276772,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" any"}}} +{"type":"assistant/chunk","seq":23,"time":1784086276772,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":24,"time":1784086276772,"data":{"turn":1,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":25,"time":1784086276777,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":26,"time":1784086276777,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"FL"}}} +{"type":"assistant/chunk","seq":27,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":1,"text":"ASH"}}} +{"type":"assistant/chunk","seq":28,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly \"FLASH\" and stop, without using any tools."}}}} +{"type":"assistant/chunk","seq":29,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"FLASH"}}}} +{"type":"assistant/chunk","seq":30,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3133,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}}}} +{"type":"assistant/chunk","seq":31,"time":1784086276778,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":32,"time":1784086276782,"data":{"turn":1,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"FLASH\" and stop, without using any tools."},{"type":"text","text":"FLASH"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-flash"},"usage":{"inputTokens":3133,"outputTokens":23,"cacheReadTokens":0,"reasoningTokens":20}},"sourceEventSeqs":[4,5,6,7,8,9,10,11,12,13,14,15,16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31],"surfaceOp":"append"} +{"type":"step/end","seq":33,"time":1784086276782,"data":{"turn":1,"step":1}} +{"type":"turn/end","seq":34,"time":1784086276783,"data":{"turn":1,"reason":{"kind":"completed"}}} +{"type":"turn/start","seq":35,"time":1784086276811,"data":{"turn":2,"trigger":{"kind":"message","source":{"kind":"user"}}}} +{"type":"user/message","seq":36,"time":1784086276812,"data":{"content":[{"type":"text","text":"Without using tools, reply with exactly PRO and stop."}],"source":{"kind":"user"}},"surfaceOp":"append"} +{"type":"step/start","seq":37,"time":1784086276812,"data":{"turn":2,"step":1}} +{"type":"request/header-delta","seq":38,"time":1784086276813,"data":{"system":{"keepStart":2,"keepEnd":10,"insert":["{{system}}"]},"config":{"provider":"deepseek","model":"deepseek-v4-pro"}}} +{"type":"assistant/chunk","seq":39,"time":1784086278053,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"reasoning"}}} +{"type":"assistant/chunk","seq":40,"time":1784086278053,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"The"}}} +{"type":"assistant/chunk","seq":41,"time":1784086278242,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" user"}}} +{"type":"assistant/chunk","seq":42,"time":1784086278312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" wants"}}} +{"type":"assistant/chunk","seq":43,"time":1784086278312,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" me"}}} +{"type":"assistant/chunk","seq":44,"time":1784086278313,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" to"}}} +{"type":"assistant/chunk","seq":45,"time":1784086278313,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" reply"}}} +{"type":"assistant/chunk","seq":46,"time":1784086278355,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" with"}}} +{"type":"assistant/chunk","seq":47,"time":1784086278356,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" exactly"}}} +{"type":"assistant/chunk","seq":48,"time":1784086278356,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" \""}}} +{"type":"assistant/chunk","seq":49,"time":1784086278356,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"PRO"}}} +{"type":"assistant/chunk","seq":50,"time":1784086278400,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"\""}}} +{"type":"assistant/chunk","seq":51,"time":1784086278400,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" and"}}} +{"type":"assistant/chunk","seq":52,"time":1784086278400,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" stop"}}} +{"type":"assistant/chunk","seq":53,"time":1784086278400,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":","}}} +{"type":"assistant/chunk","seq":54,"time":1784086278441,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" without"}}} +{"type":"assistant/chunk","seq":55,"time":1784086278442,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" using"}}} +{"type":"assistant/chunk","seq":56,"time":1784086278442,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" any"}}} +{"type":"assistant/chunk","seq":57,"time":1784086278442,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":" tools"}}} +{"type":"assistant/chunk","seq":58,"time":1784086278442,"data":{"turn":2,"step":1,"chunk":{"type":"reasoning-delta","index":0,"text":"."}}} +{"type":"assistant/chunk","seq":59,"time":1784086278494,"data":{"turn":2,"step":1,"chunk":{"type":"block-start","index":1,"blockType":"text"}}} +{"type":"assistant/chunk","seq":60,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"text-delta","index":1,"text":"PRO"}}} +{"type":"assistant/chunk","seq":61,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"reasoning","text":"The user wants me to reply with exactly \"PRO\" and stop, without using any tools."}}}} +{"type":"assistant/chunk","seq":62,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"block-end","index":1,"block":{"type":"text","text":"PRO"}}}} +{"type":"assistant/chunk","seq":63,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":3149,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}}}} +{"type":"assistant/chunk","seq":64,"time":1784086278495,"data":{"turn":2,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}} +{"type":"assistant/message","seq":65,"time":1784086278495,"data":{"turn":2,"step":1,"content":[{"type":"reasoning","text":"The user wants me to reply with exactly \"PRO\" and stop, without using any tools."},{"type":"text","text":"PRO"}],"provenance":{"provider":"deepseek","model":"deepseek-v4-pro"},"usage":{"inputTokens":3149,"outputTokens":21,"cacheReadTokens":0,"reasoningTokens":19}},"sourceEventSeqs":[39,40,41,42,43,44,45,46,47,48,49,50,51,52,53,54,55,56,57,58,59,60,61,62,63,64],"surfaceOp":"append"} +{"type":"step/end","seq":66,"time":1784086278495,"data":{"turn":2,"step":1}} +{"type":"turn/end","seq":67,"time":1784086278495,"data":{"turn":2,"reason":{"kind":"completed"}}} diff --git a/examples/acp-agent/tests/snapshots/model-switching/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/model-switching/stdout.golden.jsonl new file mode 100644 index 0000000000..011d06f5d2 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/stdout.golden.jsonl @@ -0,0 +1,47 @@ +{"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"FL"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"ASH"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" without"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" any"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tools"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"FL"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ASH"}}}} +{"jsonrpc":"2.0","id":3,"result":{"stopReason":"end_turn"}} +{"jsonrpc":"2.0","id":4,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-pro\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" me"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" to"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" reply"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" with"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" exactly"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" \""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"PRO"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"\""}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" and"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" stop"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":","}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" without"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" using"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" any"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" tools"}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"."}}}} +{"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"PRO"}}}} +{"jsonrpc":"2.0","id":5,"result":{"stopReason":"end_turn"}} diff --git a/examples/acp-agent/tests/snapshots/model-switching/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.golden.md new file mode 100644 index 0000000000..90c8cb4b17 --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/system-prompt.golden.md @@ -0,0 +1,17 @@ +You are an AI agent powered by the DeepSeek Harness SDK. + +You are a coding assistant powered by the deepseek-v4-flash model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. + +Verify your work by running the code or tests. Keep answers brief and factual. + + +Check the [exit code: N] marker on every bash result; investigate failures before moving on. + +Approval prompts are disabled in this session: actions that require approval are rejected automatically — do not request sandbox escalation (do not set `sandbox_permissions`). + + +Use 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. + + + +You are a coding assistant powered by the deepseek-v4-pro model. Your working directory is {{cwd}}. Your bash tool runs under a file sandbox — a `[sandbox: file access denied …]` result is policy, not a command bug. diff --git a/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.golden.json b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.golden.json new file mode 100644 index 0000000000..d71283647e --- /dev/null +++ b/examples/acp-agent/tests/snapshots/model-switching/tool-schemas.golden.json @@ -0,0 +1,249 @@ +{ + "initial": [ + { + "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]`. Commands may run under a file sandbox; a blocked file operation is reported as `[sandbox: file access denied under mode]` — a policy denial, not a bug in the command; do not retry another way (a background task reports the same marker via bash_output once it has finished). 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`. Attempting a command the sandbox may deny is safe and expected: run it and read the marker rather than assuming the denial. When a command is denied and a wider mode would let it succeed, escalate immediately in the same turn — the one sanctioned exception to a denial: retry the exact same command once with `sandbox_permissions` (the narrowest wider mode that suffices) plus a one-sentence `justification`. Do not detour through chat to ask permission first — the approval prompt raised by that retry is how the user consents. If the session states approval prompts are disabled, there is no exception: a denial is final — do not set `sandbox_permissions`. Never escalate speculatively: ground the request in a real denial — normally the one this command just hit; escalating up front is fine only when this session already denied the same access. A rejected escalation is final for that command — stop and explain, never work around it — but it does not forbid attempting or escalating other commands later.", + "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." + }, + "sandbox_permissions": { + "type": "string", + "description": "The wider sandbox mode this command needs. Only valid as a one-shot retry of a command the sandbox just denied; requires justification and user approval.", + "enum": [ + "workspace-write", + "danger-full-access" + ] + }, + "justification": { + "type": "string", + "description": "Required with sandbox_permissions: one sentence for the user explaining why this exact command needs the wider access." + } + }, + "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": "skill", + "description": "Load the full instructions for an available skill. Call this with the exact skill name from the session skill catalog before acting on a task that names or clearly matches that skill.", + "parameters": { + "type": "object", + "properties": { + "name": { + "type": "string", + "description": "The exact skill name from the available skills list." + } + }, + "required": [ + "name" + ] + } + }, + { + "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?, provider?, 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), and independent `provider`/`model` LLM target overrides (either may be provided alone). 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." + }, + "provider": { + "type": "string", + "description": "Optional provider override this phase is expected to use." + }, + "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" + ] + } + } + ], + "deltas": [] +} diff --git a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl index 1d9d45954a..5c38cacf55 100644 --- a/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl index 651897e850..be9ca10cf5 100644 --- a/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl @@ -1,6 +1,6 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} -{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":3,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"workspace-write","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} @@ -44,7 +44,7 @@ {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"D"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_message_chunk","content":{"type":"text","text":"ONE"}}}} {"jsonrpc":"2.0","id":4,"result":{"stopReason":"end_turn"}} -{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":5,"result":{"configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl index a0901b6297..3a900cfe34 100644 --- a/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/repeat-tool-guard/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_1","title":"Update todo list","kind":"other","status":"in_progress","rawInput":[{"content":"watch the kettle boil","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"plan","entries":[{"content":"watch the kettle boil","priority":"medium","status":"in_progress"}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_1","status":"completed","content":[{"type":"content","content":{"type":"text","text":"Updated todo list: 0 pending, 1 in progress, 0 completed."}}]}}} diff --git a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl index 10198918d6..6a3dfcc4c4 100644 --- a/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"Load the requested skill."}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_skill_load","title":"Load skill snapshot-skill","kind":"read","status":"in_progress","rawInput":"snapshot-skill"}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_skill_load","status":"completed","content":[{"type":"content","content":{"type":"text","text":"\n\nBase directory for this skill: {{cwd}}/.dsh/skills/snapshot-skill\nResolve relative paths mentioned by this skill against the base directory before using them. Load referenced resources only as needed.\n\n\n\nFollow these snapshot-only instructions.\nResolve referenced resources relative to this skill directory.\n\n"}}]}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl index 44fc4402fc..0574f2e6c4 100644 --- a/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-fork/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl index 08ad14dc9c..bfc195aa36 100644 --- a/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-mixed/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl index 93b38e33cb..7f9d2c51fa 100644 --- a/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-multi/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl index 26d45699cc..4a07c313e0 100644 --- a/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/subagent-spawn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl index 1059a9cc6c..29528d9984 100644 --- a/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl index f060b6b92f..fb2cd46879 100644 --- a/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl index 041ea02703..6abf7023b5 100644 --- a/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/tool-call-turn/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl index 9c0bbd37be..4566071090 100644 --- a/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workflow-run/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl index 5f6c7f4c52..1c76f1ac61 100644 --- a/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/workspace-edit/stdout.golden.jsonl @@ -1,5 +1,5 @@ {"jsonrpc":"2.0","id":1,"result":{"protocolVersion":1,"agentInfo":{"name":"deepseek-harness-acp","version":"0.0.1"},"agentCapabilities":{"loadSession":true,"promptCapabilities":{"image":false,"audio":false,"embeddedContext":false}},"authMethods":[]}} -{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} +{"jsonrpc":"2.0","id":2,"result":{"sessionId":"{{sessionId}}","configOptions":[{"id":"model","name":"Model","description":"Sets this session's provider and model.","category":"model","type":"select","currentValue":"[\"deepseek\",\"deepseek-v4-flash\"]","options":[{"value":"[\"deepseek\",\"deepseek-v4-flash\"]","name":"deepseek-v4-flash"},{"value":"[\"deepseek\",\"deepseek-v4-pro\"]","name":"deepseek-v4-pro"}]},{"id":"permission","name":"Permissions","description":"Sets this session's sandbox and approval behavior.","category":"mode","type":"select","currentValue":"danger-full-access","options":[{"value":"workspace-write","name":"workspace-write","description":"Write inside the workspace and permitted temporary directories; wider retries require approval."},{"value":"danger-full-access","name":"danger-full-access","description":"Full file access without approval prompts."}]}]}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":"The"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" user"}}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"agent_thought_chunk","content":{"type":"text","text":" wants"}}}} diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 2db00fe7cc..eb441da8f8 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -130,7 +130,8 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ summary: 'The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall.', methods: [ 'registerAdapter(providers: string[], adapter: LlmAdapter): () => void', - 'providers(): string[]', + 'listProviders(): LlmProviderInfo[]', + 'async listModels(provider: string): Promise', 'stream(options: GenerateOptions): AsyncIterable', ], }, @@ -741,6 +742,14 @@ export const TYPE_API: readonly TypeApiEntry[] = [ name: 'HookContext', declaration: 'export interface HookContext {\n content: ContentBlock[];\n source: MessageSource;\n}', }, + { + name: 'LlmModelInfo', + declaration: 'export interface LlmModelInfo {\n provider: string;\n id: string;\n name: string;\n description?: string;\n}', + }, + { + name: 'LlmProviderInfo', + declaration: 'export interface LlmProviderInfo {\n id: string;\n name: string;\n}', + }, { name: 'Message', declaration: 'export interface Message {\n role: \'system\' | \'user\' | \'assistant\';\n content: ContentBlock[];\n provenance?: AssistantProvenance;\n}', diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index f899b6b26c..746113a0e5 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -381,7 +381,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => { expect(() => ctx.llm.registerAdapter(['m1'], new MockAdapter([]))) .toThrow('already registered') // the original registration survives the failed attempt - expect(ctx.llm.providers()).toEqual(['m1']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm1', name: 'm1' }]) }) it('an agent without a model fails the step with a clear error (not NO_ADAPTER for "default")', async () => { diff --git a/packages/llm/llm-deepseek/README.md b/packages/llm/llm-deepseek/README.md index ded2bf2379..7da98cdebf 100644 --- a/packages/llm/llm-deepseek/README.md +++ b/packages/llm/llm-deepseek/README.md @@ -14,9 +14,14 @@ A second, library-backed implementation of the same seam exists in `@deepseek-ai baseURL: !!js process.env.DEEPSEEK_BASE_URL # default: https://api.deepseek.com thinking: enabled # optional; provider default is enabled reasoningEffort: high # optional; high | max — omitted ⇒ not sent + models: # optional; defaults to V4 Flash and V4 Pro + - id: deepseek-v4-flash + name: DeepSeek V4 Flash + - id: private-reasoner + description: Company-hosted reasoning model ``` -The plugin registers the single provider route `deepseek`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`. +The plugin registers the single provider route `deepseek`. A request selects it with `provider: deepseek`; its `model` is passed through as the wire `model` string, so changing DeepSeek models does not require lifecycle-time registration. Omitting `models` advertises `deepseek-v4-flash` and `deepseek-v4-pro`; an explicit list replaces those defaults, while `models: []` advertises none. Catalog entries are exposed through `ctx.llm.listModels('deepseek')` for clients such as ACP editors, but remain advisory: unlisted model ids still pass through unchanged. An omitted entry name defaults to its id. Registering another adapter for `deepseek` throws `LlmError('DUPLICATE_ADAPTER')`. `reasoningEffort` is **omitted by default** — when unset, the `reasoning_effort` wire field is not sent and the server applies its own default for the model. The only accepted values are `high` and `max` (DeepSeek's official effort levels). It is meaningful only with thinking enabled (the provider default). diff --git a/packages/llm/llm-deepseek/src/adapter.ts b/packages/llm/llm-deepseek/src/adapter.ts index 30760a8fbc..ece053c6b3 100644 --- a/packages/llm/llm-deepseek/src/adapter.ts +++ b/packages/llm/llm-deepseek/src/adapter.ts @@ -6,13 +6,23 @@ */ import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' -import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, StreamChunk } from '@deepseek-ai/dsh-llm' import { serializeRequest } from './serialize.ts' import type { RequestDefaults } from './serialize.ts' import { parseSse } from './sse.ts' import { translate } from './translate.ts' import type { WireError } from './types.ts' +/** One optional model entry advertised by the hand-written adapter. */ +export interface DeepSeekCatalogModel { + /** Wire model id accepted by the configured endpoint. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Optional selector detail for deployments with similar model variants. */ + description?: string +} + /** Constructor options for {@link DeepSeekAdapter}; the plugin's `apply` resolves them from Config + environment. */ export interface DeepSeekAdapterOptions { /** Bearer token sent in the `authorization` header on every request. */ @@ -21,6 +31,8 @@ export interface DeepSeekAdapterOptions { baseURL: string /** Request defaults applied to every call (thinking mode, effort). */ defaults?: RequestDefaults + /** Advisory models exposed to discovery consumers; requests remain unrestricted. */ + models?: readonly DeepSeekCatalogModel[] } /** @@ -49,6 +61,19 @@ export class DeepSeekAdapter extends LlmAdapter { super() } + override providerInfo(provider: string): LlmProviderInfo { + return { id: provider, name: 'DeepSeek' } + } + + override listModels(provider: string): Promise { + return Promise.resolve((this.options.models ?? []).map(model => ({ + provider, + id: model.id, + name: model.name ?? model.id, + ...model.description === undefined ? {} : { description: model.description }, + }))) + } + async * stream(options: GenerateOptions): AsyncIterable { const body = serializeRequest(options, this.options.defaults ?? {}) diff --git a/packages/llm/llm-deepseek/src/index.ts b/packages/llm/llm-deepseek/src/index.ts index fc68f011f1..695831b1bd 100644 --- a/packages/llm/llm-deepseek/src/index.ts +++ b/packages/llm/llm-deepseek/src/index.ts @@ -9,9 +9,10 @@ import type { Context } from 'cordis' import z from 'schemastery' import type {} from '@deepseek-ai/dsh-llm' import { DeepSeekAdapter } from './adapter.ts' +import type { DeepSeekCatalogModel } from './adapter.ts' export { DeepSeekAdapter, httpErrorCode } from './adapter.ts' -export type { DeepSeekAdapterOptions } from './adapter.ts' +export type { DeepSeekAdapterOptions, DeepSeekCatalogModel } from './adapter.ts' export { serializeMessages, serializeRequest } from './serialize.ts' export type { RequestDefaults } from './serialize.ts' export { DONE, parseSse } from './sse.ts' @@ -21,6 +22,11 @@ export type * from './types.ts' export const name = 'llm-deepseek' export const inject = ['llm'] +const DEFAULT_MODELS: DeepSeekCatalogModel[] = [ + { id: 'deepseek-v4-flash' }, + { id: 'deepseek-v4-pro' }, +] + /** * Plugin config, validated by the same-named schemastery schema. Every field * is optional in yml: credentials/endpoint fall back to the environment (a @@ -36,18 +42,45 @@ export interface Config { thinking?: 'enabled' | 'disabled' /** Thinking effort (only meaningful with thinking enabled). */ reasoningEffort?: 'high' | 'max' + /** Advisory models shown by discovery consumers; defaults to V4 Flash and V4 Pro. */ + models?: DeepSeekCatalogModel[] } +const catalogModel: z = z.object({ + id: z.string().required(), + name: z.string(), + description: z.string(), +}) + export const Config: z = z.object({ apiKey: z.string(), baseURL: z.string(), thinking: z.union(['enabled', 'disabled']), reasoningEffort: z.union(['high', 'max']), + models: z.array(catalogModel).default(DEFAULT_MODELS), }) /** Public API default; the internal endpoint comes from $DEEPSEEK_BASE_URL. */ export const PUBLIC_BASE_URL = 'https://api.deepseek.com' +/** Resolve, validate, and detach the advisory model catalog. */ +function resolveModels(models: readonly DeepSeekCatalogModel[] | undefined): DeepSeekCatalogModel[] { + const seen = new Set() + return (models ?? DEFAULT_MODELS).map((model) => { + if (model.id.length === 0) throw new Error('llm-deepseek: catalog model ids must be non-empty') + if (model.name !== undefined && model.name.length === 0) { + throw new Error(`llm-deepseek: catalog model "${model.id}" has an empty name`) + } + if (seen.has(model.id)) throw new Error(`llm-deepseek: duplicate catalog model "${model.id}"`) + seen.add(model.id) + return { + id: model.id, + ...model.name === undefined ? {} : { name: model.name }, + ...model.description === undefined ? {} : { description: model.description }, + } + }) +} + export function apply(ctx: Context, config: Config): void { const apiKey = config.apiKey ?? process.env.DEEPSEEK_API_KEY if (apiKey === undefined || apiKey.length === 0) { @@ -61,5 +94,6 @@ export function apply(ctx: Context, config: Config): void { thinking: config.thinking, reasoningEffort: config.reasoningEffort, }, + models: resolveModels(config.models), })) } diff --git a/packages/llm/llm-deepseek/tests/adapter.spec.ts b/packages/llm/llm-deepseek/tests/adapter.spec.ts index e31b1c2e41..c0a2f8f482 100644 --- a/packages/llm/llm-deepseek/tests/adapter.spec.ts +++ b/packages/llm/llm-deepseek/tests/adapter.spec.ts @@ -249,16 +249,73 @@ describe('plugin registration and config', () => { apiKey: 'k', baseURL: server.url, }) - expect(ctx.llm.providers()).toEqual(['deepseek']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) await fiber.dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) - it('always owns the deepseek provider', async () => { + it('owns the deepseek provider and advertises the default models', async () => { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(LlmDeepSeek, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) - expect(ctx.llm.providers()).toEqual(['deepseek']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([ + { provider: 'deepseek', id: 'deepseek-v4-flash', name: 'deepseek-v4-flash' }, + { provider: 'deepseek', id: 'deepseek-v4-pro', name: 'deepseek-v4-pro' }, + ]) + }) + + it('uses the default model catalog when apply is called directly', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + LlmDeepSeek.apply(ctx, { apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([ + { provider: 'deepseek', id: 'deepseek-v4-flash', name: 'deepseek-v4-flash' }, + { provider: 'deepseek', id: 'deepseek-v4-pro', name: 'deepseek-v4-pro' }, + ]) + }) + + it('advertises configured models without restricting arbitrary request ids', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(LlmDeepSeek, { + apiKey: 'k', + baseURL: 'http://127.0.0.1:1', + models: [ + { id: 'private-fast' }, + { id: 'private-reasoner', name: 'Private Reasoner', description: 'Higher reasoning budget' }, + ], + }) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([ + { provider: 'deepseek', id: 'private-fast', name: 'private-fast' }, + { provider: 'deepseek', id: 'private-reasoner', name: 'Private Reasoner', description: 'Higher reasoning budget' }, + ]) + }) + + it('allows an explicit empty model catalog', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(LlmDeepSeek, { + apiKey: 'k', + baseURL: 'http://127.0.0.1:1', + models: [], + }) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([]) + }) + + it.each([ + [[{ id: '' }], /ids must be non-empty/], + [[{ id: 'm', name: '' }], /empty name/], + [[{ id: 'm' }, { id: 'm' }], /duplicate catalog model/], + ] as const)('rejects invalid advisory model config', async (models, message) => { + const ctx = new Context() + await ctx.plugin(LlmService) + await expect(ctx.plugin(LlmDeepSeek, { + apiKey: 'k', + baseURL: 'http://127.0.0.1:1', + models: [...models], + })).rejects.toThrow(message) + expect(ctx.llm.listProviders()).toEqual([]) }) it('falls back to DEEPSEEK_API_KEY and DEEPSEEK_BASE_URL env vars', async () => { @@ -267,7 +324,7 @@ describe('plugin registration and config', () => { const ctx = new Context() await ctx.plugin(LlmService) await ctx.plugin(LlmDeepSeek, {}) - expect(ctx.llm.providers()).toEqual(['deepseek']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) }) it('throws a clear error when no API key is available', async () => { @@ -276,7 +333,7 @@ describe('plugin registration and config', () => { await ctx.plugin(LlmService) await expect(ctx.plugin(LlmDeepSeek, {})) .rejects.toThrow(/an API key is required/) - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) it('prefers explicit config over env for key and base URL', async () => { @@ -305,11 +362,12 @@ describe('plugin registration and config', () => { await ctx.plugin(LlmService) // Registration succeeds; no call is made (would hit api.deepseek.com). await ctx.plugin(LlmDeepSeek, {}) - expect(ctx.llm.providers()).toEqual(['deepseek']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) }) - it('adapter is constructible directly for embedding', () => { + it('adapter is constructible directly for embedding', async () => { const adapter = new DeepSeekAdapter({ apiKey: 'k', baseURL: 'http://127.0.0.1:1' }) expect(adapter).toBeInstanceOf(DeepSeekAdapter) + await expect(adapter.listModels('deepseek')).resolves.toEqual([]) }) }) diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index 0fa563f763..e5e9439713 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -26,6 +26,8 @@ Configure credentials and deployment-specific transport settings per provider. O Each provider name must exist in pi-ai's installed catalog and may appear only once in this plugin instance. Registration with `ctx.llm` is atomic: a collision with any provider route already owned by another adapter fails plugin loading without registering the remaining routes. Model ids are not lifecycle config; an unknown model fails before any provider request with `LlmError('UNKNOWN_MODEL')`. +The adapter exposes each configured provider's installed pi-ai models through `ctx.llm.listModels(provider)`. This is provider-neutral selector metadata derived from `getModels(provider)`; request-time resolution still performs the authoritative catalog lookup, so discovery does not create a second model registry. + Supported profile fields are `provider`, `apiKey`, `baseURL`, `headers`, `reasoning`, `thinkingBudgets`, `cacheRetention`, `transport`, `timeoutMs`, `websocketConnectTimeoutMs`, `maxRetries`, and `maxRetryDelayMs`. They map to pi-ai's common stream options. Harness app attribution wins a conflicting configured header name. ## Provider/model routing and replay diff --git a/packages/llm/llm-pi-ai/src/adapter.ts b/packages/llm/llm-pi-ai/src/adapter.ts index 185e6395b3..8eb37cfb4f 100644 --- a/packages/llm/llm-pi-ai/src/adapter.ts +++ b/packages/llm/llm-pi-ai/src/adapter.ts @@ -15,7 +15,7 @@ import type { SimpleStreamOptions, } from '@earendil-works/pi-ai' import { attributionHeaders, LlmAdapter, LlmError } from '@deepseek-ai/dsh-llm' -import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, LlmModelInfo, StreamChunk } from '@deepseek-ai/dsh-llm' import type { PiAiProviderProfile } from './config.ts' import { toPiContext } from './context.ts' import { toStreamChunks } from './stream.ts' @@ -65,6 +65,18 @@ export class PiAiAdapter extends LlmAdapter { this.profiles = new Map(options.profiles.map(profile => [profile.provider, profile])) } + override listModels(provider: string): Promise { + const profile = this.profiles.get(provider) + if (profile === undefined) { + return Promise.reject(new LlmError(`pi-ai adapter does not own provider "${provider}"`, 'NO_ADAPTER')) + } + return Promise.resolve(getModels(profile.provider as KnownProvider).map(model => ({ + provider, + id: model.id, + name: model.name, + }))) + } + async * stream(options: GenerateOptions): AsyncIterable { if (options.stop !== undefined) { throw new LlmError('llm-pi-ai does not support GenerateOptions.stop', 'UNSUPPORTED_OPTION') diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index 6e6368611d..5cb065cb48 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -186,9 +186,23 @@ describe('provider profile lifecycle', () => { const fiber = await ctx.plugin(LlmPiAi, { providers: [{ provider: 'openai' }, { provider: 'anthropic' }], }) - expect(ctx.llm.providers()).toEqual(['openai', 'anthropic']) + expect(ctx.llm.listProviders()).toEqual([ + { id: 'openai', name: 'openai' }, + { id: 'anthropic', name: 'anthropic' }, + ]) await fiber.dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) + }) + + it('exposes the installed pi-ai model catalog through provider-neutral metadata', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + await ctx.plugin(LlmPiAi, { providers: [{ provider: 'openai' }] }) + const models = await ctx.llm.listModels('openai') + expect(models.find(model => model.id === 'gpt-4.1')).toEqual({ + provider: 'openai', id: 'gpt-4.1', name: 'GPT-4.1', + }) + expect(models.every(model => model.provider === 'openai')).toBe(true) }) it('accepts absent credentials for pi-ai ambient authentication', async () => { @@ -210,6 +224,7 @@ describe('provider profile lifecycle', () => { it('constructs the adapter directly and rejects routes it does not own', async () => { const adapter = new PiAiAdapter({ profiles: [{ provider: 'openai' }] }) + await expect(adapter.listModels('anthropic')).rejects.toMatchObject({ code: 'NO_ADAPTER' }) await expect((async () => { for await (const _chunk of adapter.stream({ provider: 'anthropic', model: 'claude-sonnet-4', messages: [] })) { /* drain */ } })()).rejects.toMatchObject({ code: 'NO_ADAPTER' }) diff --git a/packages/llm/llm/README.md b/packages/llm/llm/README.md index 1f64577c60..a67859ed19 100644 --- a/packages/llm/llm/README.md +++ b/packages/llm/llm/README.md @@ -9,9 +9,12 @@ An adapter registry plus a single streaming call surface, interceptable via a wa ### Public API - `ctx.llm.registerAdapter(providers: string[], adapter: LlmAdapter): () => void` Register one adapter instance for the given provider routes. Registration is all-or-nothing, and is disposed with the calling fiber. -- `ctx.llm.providers(): string[]` — provider routes with a registered adapter. +- `ctx.llm.listProviders(): LlmProviderInfo[]` Describe registered provider routes in registration order. +- `ctx.llm.listModels(provider: string): Promise` Discover the models one registered provider currently advertises. - `ctx.llm.stream(options: GenerateOptions): AsyncIterable` Stream one model call as raw chunks (token-level deltas). Consumers assemble the chunks into blocks/messages with `BlockAssembler`. +Provider and model metadata is a discovery surface, not a routing whitelist. `registerAdapter()` still owns provider exclusivity, while an adapter may accept model ids absent from `listModels()`; consumers must not reject a request because its model is unlisted. Returned metadata is detached and invalid or duplicate adapter entries fail with `INVALID_ADAPTER` or `INVALID_CATALOG`. + ### Events | Event | Mode | Purpose | @@ -20,7 +23,7 @@ An adapter registry plus a single streaming call surface, interceptable via a wa ### Extension points -- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(providers, adapter)` to add one or more provider routes. `GenerateOptions.provider` selects the adapter; `GenerateOptions.model` is adapter-owned and may be resolved dynamically. +- Subclass `LlmAdapter` and call `ctx.llm.registerAdapter(providers, adapter)` to add one or more provider routes. `GenerateOptions.provider` selects the adapter; `GenerateOptions.model` is adapter-owned and may be resolved dynamically. Override `providerInfo()` and asynchronous `listModels()` to expose selector metadata; their defaults use the route id as its name and advertise no models. - Wrap `llm/stream` via `ctx.on()` waterfall listeners for caching, retry, logging, rate-limiting, etc. ### Content-block vocabulary (`types.ts`) diff --git a/packages/llm/llm/src/index.ts b/packages/llm/llm/src/index.ts index 9b826a79fd..26e9e3b289 100644 --- a/packages/llm/llm/src/index.ts +++ b/packages/llm/llm/src/index.ts @@ -7,7 +7,7 @@ */ import { Context, Service } from 'cordis' -import type { GenerateOptions, Message, StreamChunk } from './types.ts' +import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, Message, StreamChunk } from './types.ts' import { HarnessError } from './error.ts' import { deepFreeze } from './call-config.ts' @@ -61,6 +61,26 @@ export class LlmError extends HarnessError { * DeepSeek and pi-ai adapters intentionally exercise this contract through different internals. */ export abstract class LlmAdapter { + /** + * Describe one provider route owned by this adapter. + * @param provider - a route passed to `registerAdapter()` for this instance. + * @returns detached display metadata whose id must equal `provider`. + */ + providerInfo(provider: string): LlmProviderInfo { + return { id: provider, name: provider } + } + + /** + * List models this adapter can currently advertise for one owned provider. + * The result is advisory: an adapter may accept unlisted model ids, and + * consumers must not turn absence into request rejection. + * @param _provider - one provider route owned by this adapter. + * @returns discoverable models in adapter-preferred order. + */ + listModels(_provider: string): Promise { + return Promise.resolve([]) + } + /** * Stream one model call as raw chunks. The only required method. * @param options - the fully-assembled request; implementations must honor `options.signal`. @@ -74,7 +94,7 @@ export abstract class LlmAdapter { * surface, interceptable via the `llm/stream` waterfall. */ export class LlmService extends Service { - private adapters = new Map() + private adapters = new Map() constructor(ctx: Context) { super(ctx, 'llm') @@ -92,14 +112,20 @@ export class LlmService extends Service { const dispose = this.ctx.effect(function* (this: LlmService) { if (providers.length === 0) throw new LlmError('an adapter must register at least one provider', 'INVALID_ADAPTER') const unique = new Set() + const registrations: { adapter: LlmAdapter; provider: LlmProviderInfo }[] = [] for (const provider of providers) { if (provider.length === 0) throw new LlmError('adapter provider names must be non-empty', 'INVALID_ADAPTER') if (unique.has(provider) || this.adapters.has(provider)) { throw new LlmError(`an adapter for provider "${provider}" is already registered`, 'DUPLICATE_ADAPTER') } + const info = adapter.providerInfo(provider) + if (typeof info.id !== 'string' || info.id !== provider || typeof info.name !== 'string' || info.name.length === 0) { + throw new LlmError(`adapter metadata for provider "${provider}" must preserve its id and have a non-empty name`, 'INVALID_ADAPTER') + } unique.add(provider) + registrations.push({ adapter, provider: { id: info.id, name: info.name } }) } - for (const provider of providers) this.adapters.set(provider, adapter) + for (const registration of registrations) this.adapters.set(registration.provider.id, registration) yield () => { for (const provider of providers) this.adapters.delete(provider) } @@ -110,17 +136,50 @@ export class LlmService extends Service { } /** - * Provider routes with a registered adapter. - * @returns the registered provider names, in registration order. + * Describe provider routes with a registered adapter. + * @returns detached provider metadata in registration order. */ - providers(): string[] { - return [...this.adapters.keys()] + listProviders(): LlmProviderInfo[] { + return [...this.adapters.values()].map(({ provider }) => ({ ...provider })) } - private adapter(provider: string): LlmAdapter { - const adapter = this.adapters.get(provider) - if (!adapter) throw new LlmError(`no adapter registered for provider "${provider}"`, 'NO_ADAPTER') - return adapter + /** + * Discover models advertised by one registered provider. Catalog membership + * is advisory and never changes routing or request validation. + * @param provider - registered provider route to inspect. + * @returns detached model metadata in adapter-preferred order. + */ + async listModels(provider: string): Promise { + const adapter = this.registration(provider).adapter + const models = await adapter.listModels(provider) + const seen = new Set() + return models.map((model) => { + if ( + typeof model.provider !== 'string' + || model.provider !== provider + || typeof model.id !== 'string' + || model.id.length === 0 + || typeof model.name !== 'string' + || model.name.length === 0 + || (model.description !== undefined && typeof model.description !== 'string') + || seen.has(model.id) + ) { + throw new LlmError(`adapter returned invalid or duplicate model metadata for provider "${provider}"`, 'INVALID_CATALOG') + } + seen.add(model.id) + return { + provider: model.provider, + id: model.id, + name: model.name, + ...model.description === undefined ? {} : { description: model.description }, + } + }) + } + + private registration(provider: string): { adapter: LlmAdapter; provider: LlmProviderInfo } { + const registration = this.adapters.get(provider) + if (!registration) throw new LlmError(`no adapter registered for provider "${provider}"`, 'NO_ADAPTER') + return registration } /** Remove replay state whose historical route is owned by another adapter. */ @@ -128,7 +187,7 @@ export class LlmService extends Service { const messages: Message[] = options.messages.map((message) => { const provenance = message.provenance if (message.role !== 'assistant' || provenance?.replayState === undefined) return message - if (this.adapters.get(provenance.provider) === adapter) return message + if (this.adapters.get(provenance.provider)?.adapter === adapter) return message return { ...message, provenance: { provider: provenance.provider, model: provenance.model }, @@ -150,7 +209,7 @@ export class LlmService extends Service { */ stream(options: GenerateOptions): AsyncIterable { return this.ctx.waterfall(this, 'llm/stream', options, () => { - const adapter = this.adapter(options.provider) + const adapter = this.registration(options.provider).adapter return adapter.stream(this.forAdapter(options, adapter)) }) } diff --git a/packages/llm/llm/src/types.ts b/packages/llm/llm/src/types.ts index c1bc33bf08..b8054c2046 100644 --- a/packages/llm/llm/src/types.ts +++ b/packages/llm/llm/src/types.ts @@ -121,6 +121,26 @@ export interface TokenUsage { reasoningTokens?: number } +/** Display metadata for one registered provider route. */ +export interface LlmProviderInfo { + /** Provider route key used by {@link GenerateOptions.provider}. */ + id: string + /** Human-readable provider name for selectors and diagnostics. */ + name: string +} + +/** One adapter-discovered model; catalog membership is advisory, not request validation. */ +export interface LlmModelInfo { + /** Provider route that owns this model entry. */ + provider: string + /** Model id passed to {@link GenerateOptions.model}. */ + id: string + /** Human-readable model name for selectors. */ + name: string + /** Optional user-facing distinction from otherwise similar models. */ + description?: string +} + /** * Raw streaming protocol emitted by adapters. * Block indexes correlate interleaved deltas, and `block-end` carries the diff --git a/packages/llm/llm/tests/service.spec.ts b/packages/llm/llm/tests/service.spec.ts index 2308a7eb3b..83429ba0cd 100644 --- a/packages/llm/llm/tests/service.spec.ts +++ b/packages/llm/llm/tests/service.spec.ts @@ -1,6 +1,7 @@ import { describe, expect, it } from 'vitest' import { Context } from 'cordis' import LlmService, { GenerateOptions, LlmAdapter, LlmError, StreamChunk } from '@deepseek-ai/dsh-llm' +import type { LlmModelInfo, LlmProviderInfo } from '@deepseek-ai/dsh-llm' class ScriptedAdapter extends LlmAdapter { constructor(private script: StreamChunk[]) { @@ -21,6 +22,23 @@ class RecordingAdapter extends ScriptedAdapter { } } +class CatalogAdapter extends ScriptedAdapter { + constructor( + private readonly provider: LlmProviderInfo, + private readonly models: readonly LlmModelInfo[], + ) { + super(SCRIPT) + } + + override providerInfo(_provider: string): LlmProviderInfo { + return this.provider + } + + override listModels(_provider: string): Promise { + return Promise.resolve(this.models) + } +} + const SCRIPT: StreamChunk[] = [ { type: 'block-start', index: 0, blockType: 'text' }, { type: 'text-delta', index: 0, text: 'hi' }, @@ -53,10 +71,80 @@ describe('LlmService', () => { const fiber = await ctx.plugin(Object.assign((inner: Context) => { inner.llm.registerAdapter(['scoped-model'], new ScriptedAdapter(SCRIPT)) }, { inject: ['llm'] })) - expect(ctx.llm.providers()).toEqual(['scoped-model']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'scoped-model', name: 'scoped-model' }]) await fiber.dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) + }) + + it('discovers detached provider and advisory model metadata', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const provider = { id: 'catalog', name: 'Catalog Provider' } + const model = { provider: 'catalog', id: 'fast', name: 'Fast', description: 'Low latency' } + ctx.llm.registerAdapter(['catalog'], new CatalogAdapter(provider, [model])) + + const providers = ctx.llm.listProviders() + const models = await ctx.llm.listModels('catalog') + expect(providers).toEqual([provider]) + expect(models).toEqual([model]) + + providers[0]!.name = 'mutated' + models[0]!.name = 'mutated' + provider.name = 'source mutated' + model.name = 'source mutated' + expect(ctx.llm.listProviders()).toEqual([{ id: 'catalog', name: 'Catalog Provider' }]) + await expect(ctx.llm.listModels('catalog')).resolves.toEqual([{ + provider: 'catalog', id: 'fast', name: 'source mutated', description: 'Low latency', + }]) + }) + + it('defaults adapters to their route name and an empty advisory model list', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['plain'], new ScriptedAdapter(SCRIPT)) + expect(ctx.llm.listProviders()).toEqual([{ id: 'plain', name: 'plain' }]) + await expect(ctx.llm.listModels('plain')).resolves.toEqual([]) + await expect(ctx.llm.listModels('missing')).rejects.toMatchObject({ code: 'NO_ADAPTER' }) + }) + + it.each([ + [{ id: 1, name: 'Name' }, 'non-string id'], + [{ id: 'other', name: 'Name' }, 'mismatched id'], + [{ id: 'route', name: 1 }, 'non-string name'], + [{ id: 'route', name: '' }, 'empty name'], + ] as const)('rejects invalid provider metadata atomically (%s: %s)', async (metadata, _label) => { + const ctx = new Context() + await ctx.plugin(LlmService) + const adapter = new CatalogAdapter(metadata as unknown as LlmProviderInfo, []) + expect(() => ctx.llm.registerAdapter(['route'], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) + expect(ctx.llm.listProviders()).toEqual([]) + }) + + it.each([ + [{ provider: 1, id: 'm', name: 'M' }, 'non-string provider'], + [{ provider: 'other', id: 'm', name: 'M' }, 'mismatched provider'], + [{ provider: 'route', id: 1, name: 'M' }, 'non-string id'], + [{ provider: 'route', id: '', name: 'M' }, 'empty id'], + [{ provider: 'route', id: 'm', name: 1 }, 'non-string name'], + [{ provider: 'route', id: 'm', name: '' }, 'empty name'], + [{ provider: 'route', id: 'm', name: 'M', description: 1 }, 'non-string description'], + ] as const)('rejects invalid model metadata (%s: %s)', async (metadata, _label) => { + const ctx = new Context() + await ctx.plugin(LlmService) + ctx.llm.registerAdapter(['route'], new CatalogAdapter( + { id: 'route', name: 'Route' }, + [metadata as unknown as LlmModelInfo], + )) + await expect(ctx.llm.listModels('route')).rejects.toMatchObject({ code: 'INVALID_CATALOG' }) + }) + + it('rejects duplicate model ids in one provider catalog', async () => { + const ctx = new Context() + await ctx.plugin(LlmService) + const model = { provider: 'route', id: 'same', name: 'Same' } + ctx.llm.registerAdapter(['route'], new CatalogAdapter({ id: 'route', name: 'Route' }, [model, model])) + await expect(ctx.llm.listModels('route')).rejects.toMatchObject({ code: 'INVALID_CATALOG' }) }) it('lets llm/stream waterfall listeners wrap the underlying stream', async () => { @@ -192,9 +280,9 @@ describe('LlmService', () => { await ctx.plugin(LlmService) const dispose = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.providers()).toEqual(['m1']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm1', name: 'm1' }]) dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) it('rejects duplicate adapter registration with DUPLICATE_ADAPTER code', async () => { @@ -219,7 +307,7 @@ describe('LlmService', () => { expect(() => ctx.llm.registerAdapter([], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) expect(() => ctx.llm.registerAdapter([''], adapter)).toThrow(expect.objectContaining({ code: 'INVALID_ADAPTER' })) expect(() => ctx.llm.registerAdapter(['first', 'first'], adapter)).toThrow(expect.objectContaining({ code: 'DUPLICATE_ADAPTER' })) - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) it('re-registers a model after its prior registration is disposed', async () => { @@ -227,14 +315,14 @@ describe('LlmService', () => { await ctx.plugin(LlmService) const dispose = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.providers()).toEqual(['m1']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm1', name: 'm1' }]) dispose() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) // The duplicate check is not wedged: the same model registers cleanly again. const disposeAgain = ctx.llm.registerAdapter(['m1'], new ScriptedAdapter(SCRIPT)) - expect(ctx.llm.providers()).toEqual(['m1']) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm1', name: 'm1' }]) disposeAgain() - expect(ctx.llm.providers()).toEqual([]) + expect(ctx.llm.listProviders()).toEqual([]) }) }) diff --git a/packages/support/llm-replay/README.md b/packages/support/llm-replay/README.md index 847064b160..3272f29b9a 100644 --- a/packages/support/llm-replay/README.md +++ b/packages/support/llm-replay/README.md @@ -1,6 +1,6 @@ # @deepseek-ai/dsh-llm-replay -A replay LLM plugin for keyless snapshot tests. It installs a single `llm/stream` waterfall listener that short-circuits the waterfall (never calls `next()`) and yields model streams reconstructed from a recorded **session JSONL** fixture — so a test can boot the real agent against a fixed model transcript with no API key. +A replay LLM plugin for keyless snapshot tests. It yields model streams reconstructed from a recorded **session JSONL** fixture, so a test can boot the real agent against a fixed model transcript with no API key. With `providers` configured it registers a replay-only adapter whose catalog is visible to clients such as ACP editors; without `providers` it installs the catch-all `llm/stream` waterfall used by tests that do not need discovery. Its consumer is the ACP snapshot harness in `examples/acp-agent`, which loads this plugin (via `cordis.snapshot.yml`) in place of a real LLM adapter. The package exists so its derive/parse/replay logic falls under the per-file 100% coverage gate on `packages/*/src` (the same logic, while it lived under `examples/`, was outside the gate). @@ -23,10 +23,18 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s | `file` | string | `$DSH_SNAPSHOT_FILE` | Path to the primary (parent) `session.jsonl` fixture. Required (config or env). | | `overrideFile` | string | `$DSH_SNAPSHOT_OVERRIDE` | Optional path to a `ReplayEntry[]` sidecar that replaces the PRIMARY session's derived script. | | `childFiles` | string[] | `$DSH_SNAPSHOT_CHILD_FILES` (path-delimited) | Recorded subagent child-session logs for a nested scenario; empty for a single-session scenario. | +| `providers` | `ReplayProviderConfig[]` | — | Optional replay-only provider and model catalog. Configured routes dispatch through the replay adapter and never perform provider I/O. | ```yaml - id: llm-replay name: '@deepseek-ai/dsh-llm-replay' + config: + providers: + - id: deepseek + name: DeepSeek + models: + - id: deepseek-v4-flash + - id: deepseek-v4-pro # file/overrideFile/childFiles default to $DSH_SNAPSHOT_FILE / # $DSH_SNAPSHOT_OVERRIDE / $DSH_SNAPSHOT_CHILD_FILES, set by the snapshot # harness per scenario. @@ -34,11 +42,11 @@ Replay keys every call by its calling session id (`GenerateOptions.sessionId`, s ## Exports -- `installLlmReplay(ctx, config)` — install the `llm/stream` listener; returns the disposer (HMR safety). Use this in tests to drive replay without the Loader or env vars. +- `installLlmReplay(ctx, config)` — install the configured replay adapter or catch-all `llm/stream` listener; returns the disposer (HMR safety). Use this in tests to drive replay without the Loader or env vars. - `loadSessionScripts(config)` — resolve the ordered `SessionScript[]` (primary + children) for a scenario, ready to bind to live sessions in first-call order. - `loadReplayScript(config)` — resolve the `ReplayEntry[]` for the PRIMARY session only (sidecar override if present, else derived from the JSONL; fail-loud if the fixture is missing). - `deriveReplayScript(events)` / `parseSessionLog(text)` / `parseSessionHeader(text)` — the pure helpers that turn a recorded session log into a script and read its header `id`/`createdAt`. A derived group must end in a `finish` chunk; a group without one is the fingerprint of a thrown `stream()` and must instead be expressed via an override sidecar. -- Types `ReplayEntry` / `SessionScript` / `ReplayConfig` / `Config`. +- Types `ReplayEntry` / `SessionScript` / `ReplayConfig` / `ReplayProviderConfig` / `ReplayModelConfig` / `Config`. ## Plugin export shape diff --git a/packages/support/llm-replay/src/index.ts b/packages/support/llm-replay/src/index.ts index 2e509973e5..51e799114f 100644 --- a/packages/support/llm-replay/src/index.ts +++ b/packages/support/llm-replay/src/index.ts @@ -10,8 +10,8 @@ import { existsSync, readFileSync } from 'node:fs' import { delimiter as pathDelimiter } from 'node:path' import type { Context } from 'cordis' import type { SessionEvent } from '@deepseek-ai/dsh-session' -import type { GenerateOptions, StreamChunk } from '@deepseek-ai/dsh-llm' -import { LlmError, assertNever } from '@deepseek-ai/dsh-llm' +import type { GenerateOptions, LlmModelInfo, LlmProviderInfo, StreamChunk } from '@deepseek-ai/dsh-llm' +import { LlmAdapter, LlmError, assertNever } from '@deepseek-ai/dsh-llm' /** * One recorded model call. `throw` may replay prefix chunks before failing; @@ -23,6 +23,26 @@ export type ReplayEntry = | { kind: 'throw'; chunks: StreamChunk[]; message: string; code: string; status?: number } | { kind: 'hang' } +/** One model exposed by a replay-only provider catalog. */ +export interface ReplayModelConfig { + /** Model id used for replay requests. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Optional selector description. */ + description?: string +} + +/** One provider route exposed by the replay adapter. */ +export interface ReplayProviderConfig { + /** Provider route used for replay requests. */ + id: string + /** Selector label; defaults to {@link id}. */ + name?: string + /** Advisory models exposed to clients such as ACP editors. */ + models?: ReplayModelConfig[] +} + /** Resolved plugin configuration. */ export interface ReplayConfig { /** @@ -45,6 +65,12 @@ export interface ReplayConfig { * for a single-session scenario. */ childFiles?: string[] + /** + * Optional provider catalog. When non-empty, replay registers an adapter for + * these routes; when absent or empty, it retains the catch-all waterfall used + * by tests that do not need discovery. + */ + providers?: ReplayProviderConfig[] } /** @@ -203,6 +229,42 @@ export function loadSessionScripts(config: ReplayConfig): SessionScript[] { return [primary, ...children] } +/** Replay adapter that makes a configured provider catalog discoverable without provider I/O. */ +class ReplayAdapter extends LlmAdapter { + private readonly providers: ReadonlyMap + + constructor( + providers: readonly ReplayProviderConfig[], + private readonly replay: (options: GenerateOptions) => AsyncIterable, + ) { + super() + this.providers = new Map(providers.map(provider => [provider.id, provider])) + } + + override providerInfo(provider: string): LlmProviderInfo { + const configured = this.providers.get(provider) + /* v8 ignore next -- LlmService only asks about routes registered from this same map. */ + if (configured === undefined) return super.providerInfo(provider) + return { id: provider, name: configured.name ?? provider } + } + + override listModels(provider: string): Promise { + const configured = this.providers.get(provider) + /* v8 ignore next -- LlmService only asks about routes registered from this same map. */ + if (configured === undefined) return Promise.resolve([]) + return Promise.resolve((configured.models ?? []).map(model => ({ + provider, + id: model.id, + name: model.name ?? model.id, + ...model.description === undefined ? {} : { description: model.description }, + }))) + } + + override stream(options: GenerateOptions): AsyncIterable { + return this.replay(options) + } +} + /** Yield a recorded stream back, honoring abort like a real adapter. */ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined): AsyncIterable { switch (entry.kind) { @@ -243,12 +305,14 @@ async function* replayEntry(entry: ReplayEntry, signal: AbortSignal | undefined) /** * Install per-session positional replay. A newly seen live session takes the * next ordered recorded script, then advances its own cursor synchronously at - * invocation time; calls without `sessionId` share one anonymous session. - * Returns the effect disposer for HMR-safe removal. + * invocation time; calls without `sessionId` share one anonymous session. A + * non-empty provider catalog registers a routed replay adapter; otherwise a + * catch-all waterfall intercepts requests. Returns the effect disposer for + * HMR-safe removal. * - * @param ctx - the context whose `llm/stream` waterfall the listener short-circuits. + * @param ctx - the context whose LLM service receives the replay route or waterfall. * @param config - the resolved fixture paths (env-var defaulting is `apply`'s job). - * @returns the `ctx.on` disposer that removes the listener. + * @returns the disposer that removes the registered adapter or listener. */ export function installLlmReplay(ctx: Context, config: ReplayConfig): () => void { const scripts = loadSessionScripts(config) @@ -258,7 +322,7 @@ export function installLlmReplay(ctx: Context, config: ReplayConfig): () => void const bound = new Map() let nextScript = 0 const ANON = '\0anon\0' // the key for a call that carries no sessionId - return ctx.on('llm/stream', (options: GenerateOptions, _next) => { + const replay = (options: GenerateOptions): AsyncIterable => { const key = options.sessionId ?? ANON let state = bound.get(key) let unrecorded = false @@ -296,7 +360,12 @@ export function installLlmReplay(ctx: Context, config: ReplayConfig): () => void } yield* replayEntry(entry, options.signal) })() - }) + } + const providers = config.providers ?? [] + if (providers.length > 0) { + return ctx.llm.registerAdapter(providers.map(provider => provider.id), new ReplayAdapter(providers, replay)) + } + return ctx.on('llm/stream', (options: GenerateOptions, _next) => replay(options)) } export const name = 'llm-replay' @@ -314,6 +383,8 @@ export interface Config { * a nested-agent scenario; absent/empty for a single-session scenario. */ childFiles?: string[] + /** Optional replay-only provider catalog; absent or empty selects catch-all waterfall replay. */ + providers?: ReplayProviderConfig[] } export function apply(ctx: Context, config: Config = {}): void { @@ -329,5 +400,6 @@ export function apply(ctx: Context, config: Config = {}): void { file, ...overrideFile !== undefined && overrideFile.length > 0 ? { overrideFile } : {}, ...childFiles.length > 0 ? { childFiles } : {}, + ...config.providers !== undefined ? { providers: config.providers } : {}, }) } diff --git a/packages/support/llm-replay/tests/llm-replay.spec.ts b/packages/support/llm-replay/tests/llm-replay.spec.ts index 86e77473a5..c9bd545b36 100644 --- a/packages/support/llm-replay/tests/llm-replay.spec.ts +++ b/packages/support/llm-replay/tests/llm-replay.spec.ts @@ -198,7 +198,7 @@ describe('loadReplayScript', () => { }) }) -describe('installLlmReplay (through the real waterfall)', () => { +describe('installLlmReplay (through the real LlmService)', () => { function writeLog(...calls: StreamChunk[][]): void { let seq = 1 const events: SessionEvent[] = [] @@ -217,6 +217,40 @@ describe('installLlmReplay (through the real waterfall)', () => { expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) + it('registers a replay-only provider catalog when configured', async () => { + writeLog(TEXT_CHUNKS) + const ctx = new Context() + await ctx.plugin(LlmService) + const dispose = installLlmReplay(ctx, { + file, + providers: [ + { + id: 'deepseek', + name: 'DeepSeek', + models: [ + { id: 'flash' }, + { id: 'pro', name: 'Pro', description: 'Larger model' }, + ], + }, + { id: 'empty' }, + ], + }) + + expect(ctx.llm.listProviders()).toEqual([ + { id: 'deepseek', name: 'DeepSeek' }, + { id: 'empty', name: 'empty' }, + ]) + await expect(ctx.llm.listModels('deepseek')).resolves.toEqual([ + { provider: 'deepseek', id: 'flash', name: 'flash' }, + { provider: 'deepseek', id: 'pro', name: 'Pro', description: 'Larger model' }, + ]) + await expect(ctx.llm.listModels('empty')).resolves.toEqual([]) + expect(await drain(ctx.llm.stream({ provider: 'deepseek', model: 'pro', messages: [] }))).toEqual(TEXT_CHUNKS) + + dispose() + expect(ctx.llm.listProviders()).toEqual([]) + }) + it('serves the Nth call the Nth derived entry (positional)', async () => { const second: StreamChunk[] = [ { type: 'block-start', index: 0, blockType: 'text' }, @@ -574,11 +608,12 @@ describe('apply (the plugin entry)', () => { expect(inject).toEqual(['llm']) }) - it('installs replay from an explicit config.file', async () => { + it('installs replay and its catalog from explicit config', async () => { writeFileSync(file, sessionJsonl(TEXT_CHUNKS.map((c, i) => chunkEvent(i + 1, 1, 1, c))), 'utf8') const ctx = new Context() await ctx.plugin(LlmService) - apply(ctx, { file }) + apply(ctx, { file, providers: [{ id: 'm', models: [{ id: 'm' }] }] }) + expect(ctx.llm.listProviders()).toEqual([{ id: 'm', name: 'm' }]) expect(await drain(ctx.llm.stream({ provider: 'm', model: 'm', messages: [] }))).toEqual(TEXT_CHUNKS) }) diff --git a/packages/ui/acp-agent/README.md b/packages/ui/acp-agent/README.md index 53e54545a2..97964e3b01 100644 --- a/packages/ui/acp-agent/README.md +++ b/packages/ui/acp-agent/README.md @@ -25,8 +25,8 @@ Because the package wires no logger entry, an ACP leaf has **nothing to get wron | Key | Default | Routed to | |---|---|---| -| `provider` | (required) | the provider route for each per-session agent the bridge creates | -| `model` | (required) | the per-session agent template the bridge creates agents from | +| `provider` | (required) | the initial provider route for each per-session agent the bridge creates; ACP model selection may replace it per session | +| `model` | (required) | the initial model for each per-session agent; ACP clients may switch among adapter-advertised models | | `persona` | — | the deployment persona template (may reference `{{provider}}`/`{{model}}`/`{{cwd}}`), routed to `dsh-system-prompt` | | `toolOrder` | — | explicit model-facing tool order (a name list with one `''` rest entry; absent — lexicographic; an unregistered name fails each turn at prompt assembly), routed to `dsh-system-prompt` | | `tools` | `{ mode: 'native' }` | tool-registry presentation config (`native` / `code` / `both`), routed through `dsh-agent-core` | diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index eaf3f6c6d2..324552e7e1 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,14 +8,14 @@ It is a **client-driver / UI plugin**, the structured analogue of the readline ` `apply(ctx, config)` — wires an `AgentSideConnection` (from `@agentclientprotocol/sdk`) to `process.stdin`/`process.stdout` and implements the ACP `Agent` method surface. -The plugin injects `agents`, `sessions`, `sessionPersistence`, `tools`, and `userInteraction`, never the concrete loop. Persistence backs `session/load`; tool definitions own presentation; user interaction maps agent questions to ACP forms. +The plugin injects `agents`, `sessions`, `sessionPersistence`, `tools`, `userInteraction`, `llm`, and `systemPrompt`, never the concrete loop. Persistence backs `session/load`; the LLM catalog backs model selection; prompt assembly keeps model variables aligned with routing; tool definitions own presentation; user interaction maps agent questions to ACP forms. ### Config | Key | Default | Meaning | |---|---|---| -| `provider` | — | Provider route for created agents (must have a registered adapter). | -| `model` | — | Model name for created agents (must have a registered adapter). | +| `provider` | — | Initial provider route for created agents (must have a registered adapter). | +| `model` | — | Initial model id for created agents. | (No persona key: `dsh-system-prompt`'s own `persona` config supplies the global default section, so ACP-created agents render it without the bridge carrying prompt text. An agent-scoped same-name section may still shadow that default.) @@ -33,7 +33,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: | `session/update` | `session/event` | streams user replay, assistant text/reasoning, and tool render intents | | `elicitation/create` | `ctx.userInteraction.ask()` | maps `ask_user_question` questions to ACP form elicitations; option descriptions are shown in enum titles, `multi_select` uses ACP array enums, optionless requests use a required `custom` field, and a non-empty custom answer overrides any selected choice | | `session/request_permission` | `approval/request` listener | answers one-shot allow/reject requests for bridge-owned calls; foreign or call-less requests delegate and fail closed if unanswered — see "Permission prompts" | -| `session/set_config_option` | `ctx.permission.set()` | per-session permission-preset switching over [session config options](https://agentclientprotocol.com/protocol/session-config-options) — see "Session config options" | +| `session/set_config_option` | agent-scoped request target / `ctx.permission.set()` | per-session provider+model and permission-preset switching over [session config options](https://agentclientprotocol.com/protocol/session-config-options) — see "Session config options" | ## Multi-session @@ -41,7 +41,9 @@ Forward and reverse indexes route every event, prompt, cancel, and approval to o ## Session config options -When `ctx.permission` is composed, the bridge advertises one `permission` select in `session/new` and `session/load`. Options come from the deployment's preset table; the current value comes from the session fold, with switch-away-only `custom` for unmatched knobs. `session/set_config_option` accepts advertised presets and writes both sandbox-mode and approval-policy events through `PermissionService.set()`. Open-turn switches append immediately; idle switches overlay responses and anchor at the next `agent/prompt-submit`, before request assembly. A crash before anchoring restores the durable fold. See the [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), [`dsh-permission`](../permission/README.md), and [protocol matrix](acp-feature-support.md#6-session-config-options). +The bridge advertises a `model`-category select in `session/new` and `session/load` when the session has a complete target whose provider is registered. Values encode the complete provider/model pair, are grouped by provider when more than one group is available, and come from `ctx.llm.listProviders()` / `listModels()`. The configured or last-requested model is added when absent because catalogs are advisory and private adapters may accept unlisted ids. A selection changes only that ACP session. Agent-scoped prompt assembly snapshots the selected pair for one step, supplies matching `{{provider}}` / `{{model}}` variables, and the `agent/request` waterfall applies the same pair; a concurrent selection therefore takes effect on the next step instead of splitting prompt text from routing. The resulting request header is the durable record restored by `session/load`; a selection never used by a request remains in-memory only. + +When `ctx.permission` is composed, the bridge also advertises a `permission` select. Options come from the deployment's preset table; the current value comes from the session fold, with switch-away-only `custom` for unmatched knobs. `session/set_config_option` accepts advertised presets and writes both sandbox-mode and approval-policy events through `PermissionService.set()`. Open-turn switches append immediately; idle switches overlay responses and anchor at the next `agent/prompt-submit`, before request assembly. A crash before anchoring restores the durable fold. See the [model-catalog RFC](../../../docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md), [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md), [`dsh-permission`](../permission/README.md), and [protocol matrix](acp-feature-support.md#6-session-modes--config-options--models). Background bash tasks use the session id as an opaque owner token, so one session cannot inspect or stop another's task. That contract belongs to [`dsh-tool-bash`](../../bash/tool-bash/). @@ -108,6 +110,12 @@ The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loa **Token effect**: Zero direct tokens from the ACP option or the log-only `permission/preset` event. Downstream cost is limited to the owning plugins' policy prompt, conditional retained change notice, and any changed tool outcome. +### Model switches + +**What the model sees**: The ACP selector itself emits no message. The selected provider/model pair supplies the next step's `{{provider}}` / `{{model}}` prompt variables and request routing together; all other call-config fields continue through the `agent/request` waterfall unchanged. + +**Token effect**: The selector adds no direct tokens. A changed model may tokenize the same retained prompt/history differently, and any persona text that interpolates provider or model changes accordingly. + ### Loaded sessions **What the model sees**: `session/load` resumes the persisted log, after which the loop sends its reconstructed history and request header. Replaying that log to the editor is not an extra model message. @@ -118,6 +126,5 @@ The JSON-RPC frames go on stdout, so this plugin MUST run in an example that loa - **`additionalDirectories`** — rejected. A session operates in its single `cwd` (see Per-session cwd); widening the tool/filesystem scope to extra roots is a separate sandbox concern, not yet implemented. - **Prompt content is `text` + `resource_link` only** — image, audio, and embedded-resource blocks are rejected, as is a non-empty `mcpServers` list at `session/new`. -- **One configured `model` for every created session** — per-session model selection has no config or protocol surface here yet. - **Terminal cards render completed output** — live incremental streaming and command classification are named follow-ups of [the terminal-rendering RFC](../../../docs/rfc/implemented/feature/2026-06-18-acp-terminal-and-tool-rendering.md). - **Permission answers are one-shot only** — the bridge offers `allow_once` / `reject_once`; durable `allow_always` grants and their storage/revocation policy remain deferred to the approval seam. diff --git a/packages/ui/acp/acp-feature-support.md b/packages/ui/acp/acp-feature-support.md index 121af7cc2f..de390020c3 100644 --- a/packages/ui/acp/acp-feature-support.md +++ b/packages/ui/acp/acp-feature-support.md @@ -10,7 +10,7 @@ Legend: ✅ supported · ⚠️ partial / fallback · ❌ not yet · — n/a. Th ## At a glance -The bridge implements the **core prompt-turn loop** for N concurrent sessions: initialize, session new/load, prompt, cancel, streamed assistant/thought chunks, tool-call rendering (including Zed terminal cards), resumable session replay, one-shot permission prompts, and per-session permission presets. The largest **unbuilt** areas are **MCP passthrough**, runtime model selection, **slash commands**, and **agent plans**, plus the client **filesystem** and **terminal** method families (which the adapters mostly do NOT drive either — see rows 43-49). See [Gap summary](#gap-summary). +The bridge implements the **core prompt-turn loop** for N concurrent sessions: initialize, session new/load, prompt, cancel, streamed assistant/thought chunks, tool-call rendering (including Zed terminal cards), resumable session replay, one-shot permission prompts, per-session model selection, and permission presets. The largest **unbuilt** areas are **MCP passthrough**, **slash commands**, and **agent plans**, plus the client **filesystem** and **terminal** method families (which the adapters mostly do NOT drive either — see rows 43-49). See [Gap summary](#gap-summary). ## 1. Agent methods (client → agent) @@ -26,8 +26,8 @@ The bridge implements the **core prompt-turn loop** for N concurrent sessions: i | `session/prompt` | S | ✅ | ✅ | ✅ | Maps to `agent.send`; one in-flight prompt per session; settles on the owning turn's end. | | `session/cancel` | S | ✅ | ✅ | ✅ | Queue-aware `agent.cancel`; settles the in-flight prompt `cancelled`, scoped to the one session. | | `session/set_mode` | S | ❌ | ✅ | ✅ | Session modes deliberately skipped: config options are the spec's replacement and modes are slated for removal in ACP v2 (see [§6](#6-session-modes--config-options--models)). | -| `session/set_config_option` | S | ✅ | ✅ | ✅ | One `permission` select when `ctx.permission` is composed; values come from the deployment preset table, a switch writes its preset event through to both knob events, and the response carries the complete refreshed state ([sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)). | -| model selection | S | ❌ | ✅ | ✅ | No distinct stable `session/set_model` — model is the `model`-category `session/set_config_option`. The bridge fixes the model per-bridge via config; no runtime switch. Codex still uses the legacy `unstable_setSessionModel` ext method. | +| `session/set_config_option` | S | ✅ | ✅ | ✅ | A provider/model select is present for a complete registered target; one `permission` select is added when `ctx.permission` is composed. Every response carries the complete refreshed state. | +| model selection | S | ✅ | ✅ | ✅ | No distinct stable `session/set_model` — model is the `model`-category `session/set_config_option`. Values preserve the provider/model pair, catalogs come from `ctx.llm`, selection is per session, and `session/load` restores the last requested pair. Codex also supports the legacy `unstable_setSessionModel` ext method. | | `session/list` | S | ❌ | ✅ | ✅ | Gated by `sessionCapabilities.list`. The harness HAS `sessionPersistence.list()` (used internally for load-cwd validation) but does not expose it over ACP. | | `session/delete` | S | ❌ | ✅ | ✅ | Gated by `sessionCapabilities.delete`. | | `session/fork` | U | ❌ | ✅ | ❌ | Claude ships `unstable_forkSession`; Codex does not. | @@ -111,7 +111,7 @@ Tool-call presentation is **owned by each tool** (`presentCall` / `presentResult ## 6. Session modes / config options / models -Config options ✅ (the [sandbox RFC § Per-session mode switching](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)): when `ctx.permission` is composed, the bridge advertises one `permission` select whose values come from the deployment preset table and whose current value derives from the session log; `session/set_config_option` switches the preset end to end, with idle switches anchoring at the next `agent/prompt-submit` inside its open turn. Session modes stay deliberately unmodeled because config options replace them in ACP v2. Runtime model selection is still not modeled — the harness fixes the model per bridge via `AcpConfig.model` (both reference adapters ship a model selector). +Config options ✅: the bridge advertises a `model` select from the advisory LLM provider/model catalog, preserving each provider/model pair in an opaque value and grouping multiple providers. A selected pair is isolated to one session, snapshotted with the prompt for each step, applied through `agent/request`, and restored from the logged request header on load. When `ctx.permission` is composed, the bridge also advertises one `permission` select whose values come from the deployment preset table and whose current value derives from the session log; idle permission switches anchor at the next `agent/prompt-submit` inside its open turn. Session modes stay deliberately unmodeled because config options replace them in ACP v2. See the [model-catalog RFC](../../../docs/rfc/implemented/architecture/2026-07-15-llm-model-catalog-and-acp-selection.md) and [sandbox RFC](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md). ## 7. Content blocks @@ -141,13 +141,12 @@ The bridge rejects unsupported prompt blocks rather than silently dropping them Ranked by how commonly the reference adapters ship them and how much UX they unlock: 1. **Session lifecycle** — `session/list` + `session/delete` (the persistence layer already lists), then `session/resume` / `session/close`. -2. **Model selection** — sandbox and approval config options are implemented; selecting the bridge's model at runtime remains open. -3. **Agent plan** (`sessionUpdate: 'plan'`) — surface the loop's plan as structured entries. -4. **Slash commands** (`available_commands_update`). -5. **MCP passthrough** (`mcpServers` on `session/new` + `mcpCapabilities`). -6. **Richer prompt content** — image / embedded `resource` blocks (needs a multimodal model path). -7. **Usage reporting** (`usage_update`) — the harness already records token usage internally (on `assistant/message`). -8. **Editor filesystem delegation** (`fs/read_text_file` / `fs/write_text_file`) — lets the agent see unsaved buffers; lower priority since the harness has direct disk access. +2. **Agent plan** (`sessionUpdate: 'plan'`) — surface the loop's plan as structured entries. +3. **Slash commands** (`available_commands_update`). +4. **MCP passthrough** (`mcpServers` on `session/new` + `mcpCapabilities`). +5. **Richer prompt content** — image / embedded `resource` blocks (needs a multimodal model path). +6. **Usage reporting** (`usage_update`) — the harness already records token usage internally (on `assistant/message`). +7. **Editor filesystem delegation** (`fs/read_text_file` / `fs/write_text_file`) — lets the agent see unsaved buffers; lower priority since the harness has direct disk access. ## Out of scope diff --git a/packages/ui/acp/package.json b/packages/ui/acp/package.json index 71efc51a07..6d0e8ed1d3 100644 --- a/packages/ui/acp/package.json +++ b/packages/ui/acp/package.json @@ -34,6 +34,7 @@ "@deepseek-ai/dsh-sandbox": "^0.0.1", "@deepseek-ai/dsh-session": "^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", "@deepseek-ai/dsh-user-approval": "^0.0.1", "@deepseek-ai/dsh-user-interaction": "^0.0.1", diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 404384bda8..e8fb326d9b 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -34,13 +34,15 @@ import { type PromptRequest, type PromptResponse, type SessionConfigOption, + type SessionConfigSelectGroup, + type SessionConfigSelectOption, type SessionNotification, type SetSessionConfigOptionRequest, type SetSessionConfigOptionResponse, type Stream, type StopReason, } from '@agentclientprotocol/sdk' -import type { ContentBlock } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, LlmCallConfig, LlmModelInfo, LlmProviderInfo } from '@deepseek-ai/dsh-llm' import { assertNever, CallId } from '@deepseek-ai/dsh-llm' import type { Agent } from '@deepseek-ai/dsh-agent' import { AgentId } from '@deepseek-ai/dsh-agent' @@ -52,6 +54,9 @@ import type { ToolCallView, ToolRegistry, ToolResultView, TerminalResultView } f // Side-effect type import: declaration-merges `ctx.sessionPersistence` onto // Context (the bridge injects it and reads `list()` for load cwd validation). import type {} from '@deepseek-ai/dsh-session-persistence' +// Side-effect type import: declaration-merges prompt assembly onto Context and +// the scoped waterfall used to keep persona variables aligned with requests. +import type {} from '@deepseek-ai/dsh-system-prompt' // Side-effect type import: declaration-merges the `approval/request` waterfall // the bridge answers for its own agents (see the approval answerer below). import type {} from '@deepseek-ai/dsh-user-approval' @@ -73,7 +78,7 @@ import { export const name = 'acp' // Interface services back advertised loading, tool-owned presentation with a generic fallback, and interaction. // TODO(acp-session-inject): remove `sessions`; the bridge never reads it, and ownership is already behind `agents`. -export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction'] +export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction', 'llm', 'systemPrompt'] /** Build an ACP invalid-params error with visible human detail. */ function invalidParams(detail: string): RequestError { @@ -214,6 +219,31 @@ export const Config: Schema = Schema.object({ model: Schema.string(), }) +/** Provider/model pair selected for one ACP session. */ +interface LlmTarget { + provider: string + model: string +} + +/** Mutable target shared by one agent's scoped assembly and request listeners. */ +interface LlmTargetRef { + current: LlmTarget | undefined + /** Step snapshot captured by prompt assembly so target switches cannot split prompt and request. */ + assembled: LlmTarget | undefined +} + +/** One resolved ACP model selector plus its opaque value lookup. */ +interface ModelDirectory { + option: Extract | undefined + targets: ReadonlyMap +} + +/** One provider and its adapter-advertised models, detached for one RPC. */ +interface ModelCatalogEntry { + provider: LlmProviderInfo + models: LlmModelInfo[] +} + /** Per-session bridge state keyed by ACP session id. */ interface SessionRecord { sessionId: SessionId @@ -224,6 +254,8 @@ interface SessionRecord { presenter: ToolPresenter /** Session-creation snapshot of terminal-card support for call/result consistency. */ terminalEnabled: boolean + /** Session-local provider/model selection and the current step snapshot. */ + target: LlmTargetRef /** In-flight prompt and its captured turn number for exact settlement. */ inflight: { resolve: (reason: StopReason) => void @@ -246,6 +278,7 @@ interface SessionRecord { export function apply(ctx: Context, config: AcpConfig): void { // Handlers run later outside this injection scope, so capture services now. const agents = ctx.agents + const llm = ctx.llm const sessionPersistence = ctx.sessionPersistence const logger = ctx.logger const tools = ctx.tools @@ -253,6 +286,101 @@ export function apply(ctx: Context, config: AcpConfig): void { // Presenter failures are logged and contained per session or replay. const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent) + /** Resolve a complete target only; partial config remains available to other request listeners. */ + const configuredTarget = (): LlmTarget | undefined => config.provider !== undefined && config.model !== undefined + ? { provider: config.provider, model: config.model } + : undefined + + /** Install the ACP target as an agent-scoped prompt/request override. */ + const installTarget = (agentCtx: Context, target: LlmTargetRef): void => { + const agent = agentCtx.agent + /* v8 ignore next -- setup is invoked only with the freshly created agent's scoped context. */ + if (agent === undefined) throw new Error('acp: agent setup has no scoped agent') + const logged = agent.session.requestHeader()?.config + if (logged !== undefined) target.current = { provider: logged.provider, model: logged.model } + + // Capture once at assembly entry and apply the same pair after downstream + // prompt listeners. A selector change during async assembly therefore takes + // effect on the following step instead of splitting {{model}} from routing. + agentCtx.on('system-prompt/assemble', async (_assembly, _context, next) => { + const selected = target.current + const assembled = await next() + target.assembled = selected + if (selected === undefined) return assembled + return { + ...assembled, + variables: { + ...assembled.variables, + provider: selected.provider, + model: selected.model, + }, + } + }) + agentCtx.on('agent/request', async (_agent, _turn, _step, _callConfig, next): Promise => { + const resolved = await next() + const selected = target.assembled + return selected === undefined ? resolved : { + ...resolved, + provider: selected.provider, + model: selected.model, + } + }) + } + + /** Opaque ACP value preserving both routing dimensions. */ + const targetValue = (target: LlmTarget): string => JSON.stringify([target.provider, target.model]) + + /** Read one detached advisory catalog snapshot before mutating session state. */ + const readModelCatalog = async (): Promise => Promise.all( + llm.listProviders().map(async provider => ({ + provider, + models: await llm.listModels(provider.id), + })), + ) + + /** Resolve one catalog snapshot into the ACP model selector for a session. */ + const modelDirectory = (catalog: readonly ModelCatalogEntry[], current: LlmTarget | undefined): ModelDirectory => { + if (current === undefined) return { option: undefined, targets: new Map() } + const models = catalog.map(entry => ({ provider: entry.provider, models: [...entry.models] })) + const currentProvider = models.find(entry => entry.provider.id === current.provider) + if (currentProvider === undefined) return { option: undefined, targets: new Map() } + if (!currentProvider.models.some(model => model.id === current.model)) { + currentProvider.models = [...currentProvider.models, { + provider: current.provider, + id: current.model, + name: current.model, + }] + } + + const targets = new Map() + const groups = models.flatMap(({ provider, models: entries }) => { + if (entries.length === 0) return [] + const options = entries.map((model): SessionConfigSelectOption => { + const target = { provider: model.provider, model: model.id } + const value = targetValue(target) + targets.set(value, target) + return { + value, + name: model.name, + ...model.description === undefined ? {} : { description: model.description }, + } + }) + return [{ group: provider.id, name: provider.name, options } satisfies SessionConfigSelectGroup] + }) + return { + option: { + id: 'model', + name: 'Model', + description: 'Sets this session\'s provider and model.', + category: 'model', + type: 'select', + currentValue: targetValue(current), + options: groups.length === 1 ? groups.flatMap(group => group.options) : groups, + }, + targets, + } + } + // TODO(derive-acp-session-id): derive event ids from `agent.session`, verify ownership, then remove the reverse map. // Agent events currently carry only the Agent, so retain `SessionRecord.sessionId` and update both indexes together. // Dropping the forward record lets the weak reverse entry expire. @@ -436,16 +564,17 @@ export function apply(ctx: Context, config: AcpConfig): void { // --- The ACP Agent method surface ----------------------------------------- - /** - * Build the single Permissions option when `ctx.permission` is composed. - * Its value comes from the session log, overlaid by an unanchored idle - * switch, so `session/load` needs no catch-up state. - */ - const configOptionsFor = (agent: Agent, pending: SessionRecord['pendingSwitches'] = {}): SessionConfigOption[] => { + /** Build every ACP session option from the model directory and live services. */ + const configOptionsFor = ( + agent: Agent, + directory: ModelDirectory, + pending: SessionRecord['pendingSwitches'] = {}, + ): SessionConfigOption[] => { + const options = directory.option === undefined ? [] : [directory.option] const presets = ctx.get('permission') - if (presets === undefined) return [] + if (presets === undefined) return options const currentValue = pending.preset ?? presets.current(agent.session.events) - return [{ + return [...options, { id: 'permission', name: 'Permissions', description: 'Sets this session\'s sandbox and approval behavior.', @@ -544,11 +673,15 @@ export function apply(ctx: Context, config: AcpConfig): void { validateWorkspaceParams(params) validateMcpServers(params) const sessionId = SessionId(randomUUID()) + const target: LlmTargetRef = { current: configuredTarget(), assembled: undefined } + const directory = modelDirectory(await readModelCatalog(), target.current) + assertOpen() const handle = await agents.create({ agentId: AgentId(sessionId), sessionId, meta: { cwd: params.cwd }, agentOptions: agentOptions(config), + setup: (agentCtx) => { installTarget(agentCtx, target) }, }) // Creation awaits the unpublished setup transaction. A client disconnect // can therefore close this bridge @@ -567,10 +700,11 @@ export function apply(ctx: Context, config: AcpConfig): void { dispose: () => handle.dispose(), presenter: makePresenter(handle.agent), terminalEnabled: terminalOutputCap, + target, inflight: undefined, pendingSwitches: {}, }) - const configOptions = configOptionsFor(handle.agent) + const configOptions = configOptionsFor(handle.agent, directory) return { sessionId, ...configOptions.length > 0 ? { configOptions } : {} } }, @@ -615,10 +749,14 @@ export function apply(ctx: Context, config: AcpConfig): void { throw invalidParams(`session ${sessionId} cwd mismatch: persisted ${persistedCwd}, requested ${params.cwd}`) } } + const catalog = await readModelCatalog() + assertOpen() + const target: LlmTargetRef = { current: configuredTarget(), assembled: undefined } const handle = await agents.resume({ agentId: AgentId(sessionId), resumeSessionId: sessionId, agentOptions: agentOptions(config), + setup: (agentCtx) => { installTarget(agentCtx, target) }, }) // The bridge may have torn down (disposal / client disconnect) while // resume() was pending. Its listeners are gone, so installing a record @@ -634,6 +772,7 @@ export function apply(ctx: Context, config: AcpConfig): void { await handle.dispose() throw invalidParams('connection closed during session/load') } + const directory = modelDirectory(catalog, target.current) const agent = handle.agent bySession.set(agent, sessionId) // Snapshot the terminal capability ONCE for this session (used by both @@ -646,6 +785,7 @@ export function apply(ctx: Context, config: AcpConfig): void { dispose: () => handle.dispose(), presenter: makePresenter(agent), terminalEnabled, + target, inflight: undefined, pendingSwitches: {}, } @@ -671,7 +811,7 @@ export function apply(ctx: Context, config: AcpConfig): void { for (const event of agent.session.events) { streamSessionEventUpdate(sessionId, event, notify, replayPresenter, replayTerminal) } - const configOptions = configOptionsFor(agent) + const configOptions = configOptionsFor(agent, directory) return configOptions.length > 0 ? { configOptions } : {} } finally { loadingIds.delete(sessionId) @@ -725,18 +865,35 @@ export function apply(ctx: Context, config: AcpConfig): void { return Promise.resolve() }, - setSessionConfigOption(params: SetSessionConfigOptionRequest): Promise { + async setSessionConfigOption(params: SetSessionConfigOptionRequest): Promise { assertOpen() const rec = requireSession(SessionId(params.sessionId)) - // The advertised option is a select, so the boolean-shaped variant of - // the request is a protocol misuse regardless of configId. + // Every advertised option is a select, so the boolean-shaped variant + // is a protocol misuse regardless of configId. if (typeof params.value !== 'string') { throw invalidParams(`config option ${params.configId} is a select; boolean values are not accepted`) } + let directory = modelDirectory(await readModelCatalog(), rec.target.current) // Open-turn switches append immediately; idle switches wait for the // next prompt-submit. Only values advertised by this composition are // accepted, and the session log remains the durable store. switch (params.configId) { + case 'model': { + const target = directory.targets.get(params.value) + if (target === undefined) { + throw invalidParams(`unknown model value ${JSON.stringify(params.value)}`) + } + rec.target.current = { ...target } + const option = directory.option + /* v8 ignore next -- `targets` is populated only while constructing + this selector; a found target therefore proves it exists. */ + if (option === undefined) throw internalError('model directory target has no selector') + directory = { + ...directory, + option: { ...option, currentValue: params.value }, + } + break + } case 'permission': { const presets = ctx.get('permission') if (presets === undefined) { @@ -758,7 +915,7 @@ export function apply(ctx: Context, config: AcpConfig): void { } // The spec requires the COMPLETE refreshed config state in the response // (a change may cascade); ours are independent, but the contract holds. - return Promise.resolve({ configOptions: configOptionsFor(rec.agent, rec.pendingSwitches) }) + return { configOptions: configOptionsFor(rec.agent, directory, rec.pendingSwitches) } }, } } diff --git a/packages/ui/acp/tests/config-options.spec.ts b/packages/ui/acp/tests/config-options.spec.ts index f914004e8b..806aaa3ab6 100644 --- a/packages/ui/acp/tests/config-options.spec.ts +++ b/packages/ui/acp/tests/config-options.spec.ts @@ -40,6 +40,26 @@ function permissionOption(currentValue: string): object { } } +function modelValue(provider = 'mock', model = 'mock'): string { + return JSON.stringify([provider, model]) +} + +function modelOption(currentValue = modelValue()): object { + return { + id: 'model', + name: 'Model', + description: 'Sets this session\'s provider and model.', + category: 'model', + type: 'select', + currentValue, + options: [{ value: modelValue(), name: 'Mock' }], + } +} + +function optionsWithPermission(currentValue: string): object[] { + return [modelOption(), permissionOption(currentValue)] +} + describe('acp bridge — session config options', () => { let storageDir: string let h: BridgeHarness | undefined @@ -64,19 +84,111 @@ describe('acp bridge — session config options', () => { return harness } - it('advertises no configOptions without the permission service — even with both knobs composed', async () => { + it('advertises the model selector without requiring the permission service', async () => { h = await makeBridgeHarness({ storageDir }) await h.ctx.plugin(SandboxedLocalExecutor, { timeoutMs: 10_000 }) await h.ctx.plugin(ApprovalService) await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toBeUndefined() + expect(res.configOptions).toEqual([modelOption()]) + }) + + it('groups models by provider and switches routing plus prompt variables as one session target', async () => { + h = await makeBridgeHarness({ + storageDir, + script: [textResponse('ok')], + config: { provider: 'alpha', model: 'a1' }, + persona: 'Route {{provider}} / {{model}}', + catalog: { + providers: [{ id: 'alpha', name: 'Alpha' }, { id: 'beta', name: 'Beta' }], + models: [ + { provider: 'alpha', id: 'a1', name: 'Alpha One', description: 'Fast' }, + { provider: 'beta', id: 'b1', name: 'Beta One' }, + ], + }, + }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const created = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + expect(created.configOptions).toEqual([{ + id: 'model', + name: 'Model', + description: 'Sets this session\'s provider and model.', + category: 'model', + type: 'select', + currentValue: modelValue('alpha', 'a1'), + options: [ + { group: 'alpha', name: 'Alpha', options: [{ value: modelValue('alpha', 'a1'), name: 'Alpha One', description: 'Fast' }] }, + { group: 'beta', name: 'Beta', options: [{ value: modelValue('beta', 'b1'), name: 'Beta One' }] }, + ], + }]) + + const switched = await h.client.setSessionConfigOption({ + sessionId: created.sessionId, + configId: 'model', + value: modelValue('beta', 'b1'), + }) + expect(switched.configOptions?.[0]).toMatchObject({ currentValue: modelValue('beta', 'b1') }) + await h.client.prompt({ sessionId: created.sessionId, prompt: [{ type: 'text', text: 'use beta' }] }) + expect(h.adapter.requests[0]).toMatchObject({ + provider: 'beta', + model: 'b1', + }) + expect(h.adapter.requests[0]?.system).toContain('Route beta / b1') + expect(h.ctx.agents.list()[0]?.session.requestHeader()?.config).toMatchObject({ provider: 'beta', model: 'b1' }) + }) + + it('adds the configured private model to an advisory catalog and ignores empty non-current groups', async () => { + h = await makeBridgeHarness({ + storageDir, + config: { provider: 'alpha', model: 'private-model' }, + catalog: { + providers: [{ id: 'alpha', name: 'Alpha' }, { id: 'empty', name: 'Empty' }], + models: [{ provider: 'alpha', id: 'public-model', name: 'Public Model' }], + }, + }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + expect(res.configOptions?.[0]).toMatchObject({ + currentValue: modelValue('alpha', 'private-model'), + options: [ + { value: modelValue('alpha', 'public-model'), name: 'Public Model' }, + { value: modelValue('alpha', 'private-model'), name: 'private-model' }, + ], + }) + }) + + it('omits model selection without a complete or registered current target', async () => { + h = await makeBridgeHarness({ storageDir, config: { model: undefined } }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const missing = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + expect(missing.configOptions).toBeUndefined() + await h.dispose() + + h = await makeBridgeHarness({ storageDir, config: { provider: 'unregistered', model: 'm' } }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const unknown = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + expect(unknown.configOptions).toBeUndefined() + }) + + it('leaves model-less agents available to another agent/request supplier', async () => { + h = await makeBridgeHarness({ storageDir, config: { model: undefined }, script: [textResponse('ok')] }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + const agent = h.ctx.agents.list()[0] + if (agent === undefined) throw new Error('expected an agent') + agent.ctx.on('agent/request', async (_agent, _turn, _step, callConfig, _next) => ({ + ...callConfig, + provider: 'mock', + model: 'mock', + })) + await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'supplied elsewhere' }] }) + expect(h.adapter.requests[0]).toMatchObject({ provider: 'mock', model: 'mock' }) }) it('advertises the Permissions select with the default preset current', async () => { h = await presetStack() const res = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toEqual([permissionOption('workspace-write')]) + expect(res.configOptions).toEqual(optionsWithPermission('workspace-write')) }) it('an idle switch is pending (overlaid, not yet logged), then anchors inside the next prompt\'s turn', async () => { @@ -84,7 +196,7 @@ describe('acp bridge — session config options', () => { const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const after = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) - expect(after.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(after.configOptions).toEqual(optionsWithPermission('danger-full-access')) const session = h.ctx.agents.list()[0]?.session expect(session?.events.some(e => e.type === 'permission/preset' || e.type === 'bash/sandbox-mode' || e.type === 'approval/policy')).toBe(false) @@ -105,7 +217,7 @@ describe('acp bridge — session config options', () => { const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) const again = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) - expect(again.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(again.configOptions).toEqual(optionsWithPermission('danger-full-access')) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = h.ctx.agents.list()[0]?.session.events ?? [] expect(events.filter(e => e.type === 'permission/preset')).toHaveLength(1) @@ -119,7 +231,7 @@ describe('acp bridge — session config options', () => { const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) const back = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'workspace-write' }) - expect(back.configOptions).toEqual([permissionOption('workspace-write')]) + expect(back.configOptions).toEqual(optionsWithPermission('workspace-write')) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = h.ctx.agents.list()[0]?.session.events ?? [] expect(events.some(e => e.type === 'permission/preset' || e.type === 'bash/sandbox-mode' || e.type === 'approval/policy')).toBe(false) @@ -129,10 +241,10 @@ describe('acp bridge — session config options', () => { h = await presetStack({ script: [textResponse('ok')] }) const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) const echo = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'workspace-write' }) - expect(echo.configOptions).toEqual([permissionOption('workspace-write')]) + expect(echo.configOptions).toEqual(optionsWithPermission('workspace-write')) await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) const repeat = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) - expect(repeat.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(repeat.configOptions).toEqual(optionsWithPermission('danger-full-access')) await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'anchor' }] }) const events = h.ctx.agents.list()[0]?.session.events ?? [] expect(events.filter(e => e.type === 'permission/preset').map(e => e.data)).toEqual([{ preset: 'danger-full-access' }]) @@ -167,6 +279,8 @@ describe('acp bridge — session config options', () => { // This composition never advertised `permission`. await expect(h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' })) .rejects.toThrow(/unknown permission value/) + await expect(h.client.setSessionConfigOption({ sessionId, configId: 'model', value: modelValue('mock', 'missing') })) + .rejects.toThrow(/unknown model value/) await expect(h.client.setSessionConfigOption({ sessionId, configId: 'permission', type: 'boolean', value: true })) .rejects.toThrow(/select; boolean values are not accepted/) }) @@ -184,9 +298,31 @@ describe('acp bridge — session config options', () => { const b = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'permission', value: 'danger-full-access' }) const bAfter = await h.client.setSessionConfigOption({ sessionId: b.sessionId, configId: 'permission', value: 'workspace-write' }) - expect(bAfter.configOptions).toEqual([permissionOption('workspace-write')]) + expect(bAfter.configOptions).toEqual(optionsWithPermission('workspace-write')) const aAfter = await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'permission', value: 'danger-full-access' }) - expect(aAfter.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(aAfter.configOptions).toEqual(optionsWithPermission('danger-full-access')) + }) + + it('keeps model targets isolated across concurrent sessions', async () => { + h = await makeBridgeHarness({ + storageDir, + script: [textResponse('a'), textResponse('b')], + config: { provider: 'mock', model: 'one' }, + catalog: { + providers: [{ id: 'mock', name: 'Mock' }], + models: [ + { provider: 'mock', id: 'one', name: 'One' }, + { provider: 'mock', id: 'two', name: 'Two' }, + ], + }, + }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const a = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + const b = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + await h.client.setSessionConfigOption({ sessionId: a.sessionId, configId: 'model', value: modelValue('mock', 'two') }) + await h.client.prompt({ sessionId: a.sessionId, prompt: [{ type: 'text', text: 'a' }] }) + await h.client.prompt({ sessionId: b.sessionId, prompt: [{ type: 'text', text: 'b' }] }) + expect(h.adapter.requests.map(request => request.model)).toEqual(['two', 'one']) }) it('a knob drifted outside the table derives a visible-but-untargetable custom current', async () => { @@ -199,12 +335,12 @@ describe('acp bridge — session config options', () => { agent.session.append('bash/sandbox-mode', { mode: 'read-only' }) agent.session.append('turn/end', { turn: 1, reason: { kind: 'completed' } }) const echo = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'custom' }) - const option = echo.configOptions?.[0] + const option = echo.configOptions?.find(entry => entry.id === 'permission') expect(option).toMatchObject({ currentValue: 'custom' }) if (option === undefined || !('options' in option)) throw new Error('expected a select option') expect(option.options.map(o => 'value' in o ? o.value : o)).toEqual(['workspace-write', 'danger-full-access', 'custom']) const away = await h.client.setSessionConfigOption({ sessionId, configId: 'permission', value: 'danger-full-access' }) - const afterOption = away.configOptions?.[0] + const afterOption = away.configOptions?.find(entry => entry.id === 'permission') expect(afterOption).toMatchObject({ currentValue: 'danger-full-access' }) if (afterOption === undefined || !('options' in afterOption)) throw new Error('expected a select option') expect(afterOption.options.map(o => 'value' in o ? o.value : o)).toEqual(['workspace-write', 'danger-full-access']) @@ -223,6 +359,52 @@ describe('acp bridge — session config options', () => { loader = await presetStack() const res = await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }) - expect(res.configOptions).toEqual([permissionOption('danger-full-access')]) + expect(res.configOptions).toEqual(optionsWithPermission('danger-full-access')) + }) + + it('session/load restores the last requested provider/model from the request header', async () => { + const catalog = { + providers: [{ id: 'mock', name: 'Mock' }], + models: [ + { provider: 'mock', id: 'one', name: 'One' }, + { provider: 'mock', id: 'two', name: 'Two' }, + ], + } + h = await makeBridgeHarness({ + storageDir, + script: [textResponse('ok')], + config: { provider: 'mock', model: 'one' }, + catalog, + }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + await h.client.setSessionConfigOption({ sessionId, configId: 'model', value: modelValue('mock', 'two') }) + await h.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'persist target' }] }) + await h.dispose() + h = undefined + + loader = await makeBridgeHarness({ storageDir, config: { provider: 'mock', model: 'one' }, catalog }) + await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const loaded = await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }) + expect(loaded.configOptions?.find(option => option.id === 'model')).toMatchObject({ + currentValue: modelValue('mock', 'two'), + }) + }) + + it('session/load omits config options when the persisted session has no target or permission service', async () => { + h = await makeBridgeHarness({ storageDir, config: { model: undefined } }) + await h.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const { sessionId } = await h.client.newSession({ cwd: process.cwd(), mcpServers: [] }) + const agent = h.ctx.agents.list()[0] + if (agent === undefined) throw new Error('expected an agent') + agent.inject([{ type: 'text', text: 'checkpoint' }], { source: { kind: 'plugin', plugin: 'test' } }) + await agent.whenIdle() + await h.dispose() + h = undefined + + loader = await makeBridgeHarness({ storageDir, config: { model: undefined } }) + await loader.client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) + const loaded = await loader.client.loadSession({ sessionId, cwd: process.cwd(), mcpServers: [] }) + expect(loaded.configOptions).toBeUndefined() }) }) diff --git a/packages/ui/acp/tests/harness.ts b/packages/ui/acp/tests/harness.ts index a667243a7d..38ff7d515c 100644 --- a/packages/ui/acp/tests/harness.ts +++ b/packages/ui/acp/tests/harness.ts @@ -5,7 +5,7 @@ */ import { Context } from 'cordis' -import LlmService, { CallId, type GenerateOptions, type StreamChunk } from '@deepseek-ai/dsh-llm' +import LlmService, { CallId, type GenerateOptions, type LlmModelInfo, type LlmProviderInfo, type StreamChunk } from '@deepseek-ai/dsh-llm' import { LlmAdapter } from '@deepseek-ai/dsh-llm' import SessionStore from '@deepseek-ai/dsh-session' import SystemPrompt from '@deepseek-ai/dsh-system-prompt' @@ -39,10 +39,24 @@ import { type AcpConfig } from '../src/index.ts' /** A scripted mock adapter (mirrors the agent-loop test adapter). */ class MockAdapter extends LlmAdapter { requests: GenerateOptions[] = [] - constructor(private script: (StreamChunk[] | 'hang')[]) { + constructor( + private script: (StreamChunk[] | 'hang')[], + private readonly providers: readonly LlmProviderInfo[], + private readonly models: readonly LlmModelInfo[], + ) { super() } + override providerInfo(provider: string): LlmProviderInfo { + const info = this.providers.find(entry => entry.id === provider) + if (info === undefined) throw new Error(`MockAdapter: unknown provider ${provider}`) + return info + } + + override listModels(provider: string): Promise { + return Promise.resolve(this.models.filter(model => model.provider === provider)) + } + async * stream(options: GenerateOptions): AsyncIterable { this.requests.push(options) const entry = this.script.shift() @@ -142,6 +156,9 @@ export interface BridgeHarness { storageDir: string } +/** Test-only overrides preserve explicit undefined to suppress harness defaults. */ +type AcpConfigOverrides = { [K in keyof AcpConfig]?: AcpConfig[K] | undefined } + /** * Build the bridge + a connected client over an in-memory transport pair. * @@ -155,7 +172,9 @@ export interface BridgeHarness { */ export async function makeBridgeHarness(options: { script?: (StreamChunk[] | 'hang')[] - config?: Partial + config?: AcpConfigOverrides + /** Provider-neutral directory exposed to ACP model-selection tests. */ + catalog?: { providers: LlmProviderInfo[]; models: LlmModelInfo[] } /** Deployment persona for the tree (the system-prompt plugin's config). */ persona?: string storageDir: string @@ -185,7 +204,11 @@ export async function makeBridgeHarness(options: { withFs?: boolean fsCwd?: string } = { storageDir: '' }): Promise { - const adapter = new MockAdapter(options.script ?? []) + const catalog = options.catalog ?? { + providers: [{ id: 'mock', name: 'Mock' }], + models: [{ provider: 'mock', id: 'mock', name: 'Mock' }], + } + const adapter = new MockAdapter(options.script ?? [], catalog.providers, catalog.models) const ctx = new Context() await ctx.plugin(LlmService) @@ -211,7 +234,7 @@ export async function makeBridgeHarness(options: { await ctx.plugin(FsPolicy) await ctx.plugin(ToolFs) } - ctx.llm.registerAdapter(['mock'], adapter) + ctx.llm.registerAdapter(catalog.providers.map(provider => provider.id), adapter) // Two identity byte pipes cross-wired into the two ndJsonStreams: bytes the agent writes flow // to the client's reader and vice versa. (ndJsonStream takes (output, input): the agent @@ -272,7 +295,7 @@ export async function makeBridgeHarness(options: { }) // Default route fields only when the caller omitted them; explicit undefined values must survive. - const cfg: AcpConfig = { stream: agentStream, ...options.config } + const cfg = { stream: agentStream, ...options.config } as AcpConfig if (!(options.config && 'provider' in options.config)) cfg.provider = 'mock' if (!(options.config && 'model' in options.config)) cfg.model = 'mock' // Mount the bridge the way production does: as a cordis plugin (via `ctx.plugin` with the diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 6f25f53ffc..2b3646c731 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -262,6 +262,6 @@ export class HarnessSdkServer { } private hasAdapterFor(provider: string): boolean { - return this.ctx.get('llm')?.providers().includes(provider) ?? false + return this.ctx.get('llm')?.listProviders().some(entry => entry.id === provider) ?? false } } diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 28d1eda0f8..1dbeecb68a 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -399,7 +399,7 @@ describe('HarnessSdkServer', () => { expect(inspect.hasAdapterFor('missing-provider')).toBe(false) await server.initialize({ cwd: storageDir, provider: 'deepseek', model: 'preinstalled-model' }) - expect(ctx.get('llm')?.providers().filter(provider => provider === 'deepseek')).toEqual(['deepseek']) + expect(ctx.get('llm')?.listProviders().filter(provider => provider.id === 'deepseek')).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) await server.shutdown() } finally { await ctx.fiber.dispose() @@ -418,7 +418,7 @@ describe('HarnessSdkServer', () => { await expect(server.initialize({ cwd: storageDir, provider: 'private', model: 'new-model' })) .rejects.toThrow('no adapter registered for provider "private"') - expect(ctx.get('llm')?.providers()).toEqual(['deepseek']) + expect(ctx.get('llm')?.listProviders()).toEqual([{ id: 'deepseek', name: 'DeepSeek' }]) await server.shutdown() } finally { await ctx.fiber.dispose() @@ -519,7 +519,7 @@ describe('HarnessSdkServer', () => { const ctx = { on: vi.fn(() => () => undefined), agents: { create, get: () => undefined }, - get: () => ({ providers: () => ['mock'] }), + get: () => ({ listProviders: () => [{ id: 'mock', name: 'Mock' }] }), } as unknown as Context const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as { initialize(params: { cwd: string; provider: string; model: string }): Promise diff --git a/scripts/type-equiv.manifest.json b/scripts/type-equiv.manifest.json index d7324a8712..745362f3c2 100644 --- a/scripts/type-equiv.manifest.json +++ b/scripts/type-equiv.manifest.json @@ -7,6 +7,8 @@ { "doc": "docs/core-data-structures/core.md", "symbol": "Message", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "MessageSourceMap", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "FinishReasonMap", "source": "packages/llm/llm/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "LlmProviderInfo", "source": "packages/llm/llm/src/types.ts" }, + { "doc": "docs/core-data-structures/core.md", "symbol": "LlmModelInfo", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "GenerateOptions", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "ToolSchema", "source": "packages/llm/llm/src/types.ts" }, { "doc": "docs/core-data-structures/core.md", "symbol": "LlmCallConfig", "source": "packages/llm/llm/src/call-config.ts" }, From f689fde0bfec5091fb424e3604bfd04a20284d03 Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 13:39:56 +0800 Subject: [PATCH 5/9] test(acp): cover model selector in keyless e2e --- examples/acp-agent/tests/escalation.e2e.ts | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/examples/acp-agent/tests/escalation.e2e.ts b/examples/acp-agent/tests/escalation.e2e.ts index 1a690367aa..e3e20524ff 100644 --- a/examples/acp-agent/tests/escalation.e2e.ts +++ b/examples/acp-agent/tests/escalation.e2e.ts @@ -63,7 +63,7 @@ function spawnAcpAgent(cwd: string, answer: 'allow-once' | 'reject-once'): Spawn // A dummy key lets the deepseek adapter boot keyless (presence-checked at // apply, used only on a real model call); the with-key tests carry the // real key, so the fallback is inert there. - env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY ?? 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig }, + env: { ...process.env, DEEPSEEK_API_KEY: process.env.DEEPSEEK_API_KEY || 'sk-dummy-for-boot', TSX_TSCONFIG_PATH: repoTsconfig }, stdio: ['pipe', 'pipe', 'pipe'], }, ) @@ -115,15 +115,16 @@ describe('default sandbox composition keyless smoke (real cordis.yml via the Loa expect(sessionId.length).toBeGreaterThan(0) }, 30_000) - it('advertises the Permissions select and honors a switch end to end (no key, no model)', async () => { + it('advertises model and Permissions selects and honors a permission switch without a model call', async () => { workdir = await mkdtemp(join(tmpdir(), 'sandbox-acp-config-')) spawned = spawnAcpAgent(workdir, 'reject-once') const { client } = spawned await client.initialize({ protocolVersion: PROTOCOL_VERSION, clientCapabilities: {} }) const created = await client.newSession({ cwd: workdir, mcpServers: [] }) const advertised = created.configOptions ?? [] + const modelValue = JSON.stringify(['deepseek', 'deepseek-v4-flash']) expect(advertised.map(option => [option.id, 'currentValue' in option ? option.currentValue : undefined])) - .toEqual([['permission', 'workspace-write']]) + .toEqual([['model', modelValue], ['permission', 'workspace-write']]) const afterFullAccess = await client.setSessionConfigOption({ sessionId: created.sessionId, configId: 'permission', value: 'danger-full-access', }) @@ -133,7 +134,7 @@ describe('default sandbox composition keyless smoke (real cordis.yml via the Loa sessionId: created.sessionId, configId: 'permission', value: 'danger-full-access', }) expect((again.configOptions ?? []).map(option => [option.id, 'currentValue' in option ? option.currentValue : undefined])) - .toEqual([['permission', 'danger-full-access']]) + .toEqual([['model', modelValue], ['permission', 'danger-full-access']]) await expect(client.setSessionConfigOption({ sessionId: created.sessionId, configId: 'permission', value: 'plan', })).rejects.toThrow(/unknown permission value/) From d3f8cb0f23b6cf074c214aac9fb3051977193c0d Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 13:45:19 +0800 Subject: [PATCH 6/9] fix: harden replay and pi-ai request boundaries --- packages/core/agent-loop/src/loop.ts | 12 ++++++----- .../tests/contract-regressions.spec.ts | 20 +++++++++++++++++++ packages/llm/llm-pi-ai/src/adapter.ts | 12 ++++++++++- packages/llm/llm-pi-ai/src/config.ts | 10 +++++----- packages/llm/llm-pi-ai/tests/adapter.spec.ts | 16 ++++++++++++++- 5 files changed, 58 insertions(+), 12 deletions(-) diff --git a/packages/core/agent-loop/src/loop.ts b/packages/core/agent-loop/src/loop.ts index 501c673577..ebae2c898e 100644 --- a/packages/core/agent-loop/src/loop.ts +++ b/packages/core/agent-loop/src/loop.ts @@ -6,7 +6,7 @@ */ import type { Context } from 'cordis' -import type { FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm' +import type { ContentBlock, FinishReason, GenerateOptions, LlmCallConfig, Message } from '@deepseek-ai/dsh-llm' import { isDeepStrictEqual } from 'node:util' import { BlockAssembler, HarnessError, deepFreeze } from '@deepseek-ai/dsh-llm' import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent' @@ -529,20 +529,22 @@ async function runStep( if (assembler.finish.kind === 'max-tokens') { const assembled = assembler.message() + const assembledContent = structuredClone(assembled.content) let message: Message = withoutToolCalls(assembled) message = withoutToolCalls(await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message))) // Preserve usage even when max-token truncation produced no content. - recordAssistantMessage(session, turn, step, header.config, assembled, message, assembler, chunkSeqs) + recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs) return { hadToolCalls: false, finish: assembler.finish } } // Record the post-waterfall message that tool dispatch uses. const assembled = assembler.message() + const assembledContent = structuredClone(assembled.content) let message: Message = assembled message = await events.waterfall('agent/step-result', turn, step, message, () => Promise.resolve(message)) // Empty messages exist only to carry usage; the helper also omits empty chunk provenance. - recordAssistantMessage(session, turn, step, header.config, assembled, message, assembler, chunkSeqs) + recordAssistantMessage(session, turn, step, header.config, assembledContent, message, assembler, chunkSeqs) // Tool execution stays sequential; recheck abort around each normalized result. const toolCalls = message.content.filter(block => block.type === 'tool-call') @@ -600,7 +602,7 @@ function recordAssistantMessage( turn: number, step: number, config: LlmCallConfig, - assembled: Message, + assembledContent: ContentBlock[], message: Message, assembler: BlockAssembler, chunkSeqs: number[], @@ -615,7 +617,7 @@ function recordAssistantMessage( provenance: assistantProvenance( config, assembler.replayState, - isDeepStrictEqual(message.content, assembled.content), + isDeepStrictEqual(message.content, assembledContent), ), ...assembler.usage === undefined ? {} : { usage: assembler.usage }, }, diff --git a/packages/core/agent-loop/tests/contract-regressions.spec.ts b/packages/core/agent-loop/tests/contract-regressions.spec.ts index 746113a0e5..5ee3f563a7 100644 --- a/packages/core/agent-loop/tests/contract-regressions.spec.ts +++ b/packages/core/agent-loop/tests/contract-regressions.spec.ts @@ -110,6 +110,26 @@ describe('session log records what agent/step-result actually produced', () => { provider: 'mock', model: 'next-model', replayState, }) }) + + it('drops adapter replay state when step-result mutates assembled content in place', async () => { + const response = textResponse('original') + response[response.length - 1] = { type: 'finish', reason: { kind: 'stop' }, replayState: { private: 'state' } } + const adapter = new MockAdapter([response]) + const ctx = await harness(adapter) + ctx.on('agent/step-result', async (_agent, _turn, _step, message) => { + const block = message.content[0] + if (block?.type === 'text') block.text = 'mutated' + return message + }) + const agent = ctx.agentLoop.create(AgentId('mutated-replay-state'), { provider: 'mock', model: 'next-model' }) + + send(agent, 'go') + await waitForIdle(ctx, agent) + + const recorded = agent.session.events.find(event => event.type === 'assistant/message') + expect(recorded?.type === 'assistant/message' && recorded.data.content).toEqual([{ type: 'text', text: 'mutated' }]) + expect(recorded?.type === 'assistant/message' && recorded.data.provenance.replayState).toBeUndefined() + }) }) describe('abort during tool execution ends the turn', () => { diff --git a/packages/llm/llm-pi-ai/src/adapter.ts b/packages/llm/llm-pi-ai/src/adapter.ts index 8eb37cfb4f..26e28ecd1f 100644 --- a/packages/llm/llm-pi-ai/src/adapter.ts +++ b/packages/llm/llm-pi-ai/src/adapter.ts @@ -53,6 +53,16 @@ function profileOptions(profile: PiAiProviderProfile): SimpleStreamOptions { } } +/** Merge deployment headers while removing case-insensitive attribution collisions. */ +function requestHeaders(headers: Readonly> | undefined): Record { + const attribution = attributionHeaders() + const reserved = new Set(Object.keys(attribution).map(name => name.toLowerCase())) + return { + ...Object.fromEntries(Object.entries(headers ?? {}).filter(([name]) => !reserved.has(name.toLowerCase()))), + ...attribution, + } +} + /** * pi-ai-backed multi-provider adapter. Model descriptors are resolved for each * request, so models need not be registered during the Cordis lifecycle. @@ -103,7 +113,7 @@ export class PiAiAdapter extends LlmAdapter { signal: controller.signal, // Profile headers are deployment-owned; attribution names are // Harness-owned and therefore win collisions. - headers: { ...profile.headers, ...attributionHeaders() }, + headers: requestHeaders(profile.headers), }) yield* toStreamChunks(events) } finally { diff --git a/packages/llm/llm-pi-ai/src/config.ts b/packages/llm/llm-pi-ai/src/config.ts index b41ca2dd61..f7570aff64 100644 --- a/packages/llm/llm-pi-ai/src/config.ts +++ b/packages/llm/llm-pi-ai/src/config.ts @@ -58,10 +58,10 @@ const profile = z.object({ thinkingBudgets, cacheRetention: z.union(['none', 'short', 'long']), transport: z.union(['sse', 'websocket', 'websocket-cached', 'auto']), - timeoutMs: z.number(), - websocketConnectTimeoutMs: z.number(), - maxRetries: z.number(), - maxRetryDelayMs: z.number(), + timeoutMs: z.natural(), + websocketConnectTimeoutMs: z.natural(), + maxRetries: z.natural(), + maxRetryDelayMs: z.natural(), }) /** Runtime schema for {@link Config}. */ @@ -83,7 +83,7 @@ export function resolveProfiles(profiles: readonly PiAiProviderProfile[]): PiAiP if (source.provider.length === 0) throw new Error('llm-pi-ai: provider names must be non-empty') if (!supported.has(source.provider)) throw new Error(`llm-pi-ai: unknown pi-ai provider "${source.provider}"`) if (seen.has(source.provider)) throw new Error(`llm-pi-ai: duplicate provider profile "${source.provider}"`) - if (source.apiKey !== undefined && source.apiKey.length === 0) { + if (source.apiKey !== undefined && source.apiKey.trim().length === 0) { throw new Error(`llm-pi-ai: provider "${source.provider}" has an empty apiKey; omit it to use ambient authentication`) } if (source.baseURL !== undefined && source.baseURL.length === 0) { diff --git a/packages/llm/llm-pi-ai/tests/adapter.spec.ts b/packages/llm/llm-pi-ai/tests/adapter.spec.ts index 5cb065cb48..1767447d7d 100644 --- a/packages/llm/llm-pi-ai/tests/adapter.spec.ts +++ b/packages/llm/llm-pi-ai/tests/adapter.spec.ts @@ -90,7 +90,7 @@ describe('PiAiAdapter provider routing', () => { it('merges profile headers with Harness attribution winning', async () => { const server = await mockServer([{ events: textEvents }]) const ctx = await harness(server.url, { - headers: { 'x-company': 'private', 'user-agent': 'wrong' }, + headers: { 'x-company': 'private', 'User-Agent': 'wrong' }, }) await assemble(ctx, { model: 'deepseek-v4-flash', messages: [] }) expect(server.headers[0]?.['x-company']).toBe('private') @@ -219,9 +219,23 @@ describe('provider profile lifecycle', () => { expect(() => resolveProfiles([{ provider: 'not-real' }])).toThrow(/unknown/) expect(() => resolveProfiles([{ provider: 'openai' }, { provider: 'openai' }])).toThrow(/duplicate/) expect(() => resolveProfiles([{ provider: 'openai', apiKey: '' }])).toThrow(/empty apiKey/) + expect(() => resolveProfiles([{ provider: 'openai', apiKey: ' ' }])).toThrow(/empty apiKey/) expect(() => resolveProfiles([{ provider: 'openai', baseURL: '' }])).toThrow(/empty baseURL/) }) + it('rejects negative or fractional stream tunables at schema validation', () => { + const invalid = [ + { timeoutMs: -1 }, + { websocketConnectTimeoutMs: -1 }, + { maxRetries: -1 }, + { maxRetries: 0.5 }, + { maxRetryDelayMs: -1 }, + ] + for (const entry of invalid) { + expect(() => new LlmPiAi.Config({ providers: [{ provider: 'openai', ...entry }] })).toThrow() + } + }) + it('constructs the adapter directly and rejects routes it does not own', async () => { const adapter = new PiAiAdapter({ profiles: [{ provider: 'openai' }] }) await expect(adapter.listModels('anthropic')).rejects.toMatchObject({ code: 'NO_ADAPTER' }) From 634840d406237c88e19aa5170494e160f520b9bc Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Wed, 15 Jul 2026 15:26:03 +0800 Subject: [PATCH 7/9] fix(llm-pi-ai): validate replay provenance --- packages/llm/llm-pi-ai/README.md | 2 +- packages/llm/llm-pi-ai/src/replay.ts | 3 ++ packages/llm/llm-pi-ai/tests/convert.spec.ts | 30 +++++++++++++++++--- 3 files changed, 30 insertions(+), 5 deletions(-) diff --git a/packages/llm/llm-pi-ai/README.md b/packages/llm/llm-pi-ai/README.md index e5e9439713..bb63d82010 100644 --- a/packages/llm/llm-pi-ai/README.md +++ b/packages/llm/llm-pi-ai/README.md @@ -36,7 +36,7 @@ The selected pi-ai catalog descriptor supplies the protocol implementation. This Successful assistant responses store a versioned, lossless-JSON replay state beside their durable provider/model provenance. At request time, `LlmService` passes replay state only when the historical provider route and target provider route are currently owned by this same `PiAiAdapter` instance. The adapter validates the state and restores pi-ai response ids and provider signatures even when the target provider or model changes; pi-ai then decides which metadata its target API can reuse. History without replay state is translated as foreign provider-neutral content and never impersonates a native pi-ai response. -If a listener rewrites assembled assistant content, the loop drops replay state before logging the message because its provider metadata no longer describes the content. Invalid versions, malformed metadata, and content/block mismatches fail explicitly with `LlmError('INVALID_REPLAY_STATE')`. +If a listener rewrites assembled assistant content, the loop drops replay state before logging the message because its provider metadata no longer describes the content. Invalid versions, malformed metadata, provenance provider/model mismatches, and content/block mismatches fail explicitly with `LlmError('INVALID_REPLAY_STATE')`. ## Vocabulary differences diff --git a/packages/llm/llm-pi-ai/src/replay.ts b/packages/llm/llm-pi-ai/src/replay.ts index 665b236bfe..4e4fe679a5 100644 --- a/packages/llm/llm-pi-ai/src/replay.ts +++ b/packages/llm/llm-pi-ai/src/replay.ts @@ -156,6 +156,9 @@ function foreignAssistant(message: Message): AssistantMessage { /** Recombine durable Harness content with validated pi-ai replay metadata. */ function replayedAssistant(message: Message, rawState: unknown): AssistantMessage { const state = readReplayState(rawState) + const provenance = message.provenance + if (state.provider !== provenance?.provider) return invalidReplay('provider does not match assistant provenance') + if (state.model !== provenance.model) return invalidReplay('model does not match assistant provenance') if (state.blocks.length !== message.content.length) return invalidReplay('block count does not match assistant content') const content: AssistantMessage['content'] = message.content.map((block, index) => { const replay = state.blocks[index] diff --git a/packages/llm/llm-pi-ai/tests/convert.spec.ts b/packages/llm/llm-pi-ai/tests/convert.spec.ts index cf8e07de5c..50955f0607 100644 --- a/packages/llm/llm-pi-ai/tests/convert.spec.ts +++ b/packages/llm/llm-pi-ai/tests/convert.spec.ts @@ -255,7 +255,7 @@ describe('toPiContext', () => { { type: 'text', text: 'calling' }, { type: 'tool-call', id: CallId('c1'), name: 'f', arguments: '{"a":1}' }, ], - provenance: { provider: 'deepseek', model: 'old-model', replayState: state }, + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState: state }, }], }) @@ -302,7 +302,7 @@ describe('toPiContext', () => { messages: [{ role: 'assistant', content: [{ type: 'reasoning', text: 'done' }], - provenance: { provider: 'deepseek', model: 'old', replayState: state }, + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState: state }, }], })).toThrow(/block 0 does not match assistant content/) }) @@ -315,7 +315,7 @@ describe('toPiContext', () => { messages: [{ role: 'assistant', content: [{ type: 'text', text: 'done' }], - provenance: { provider: 'deepseek', model: 'old', replayState: state }, + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState: state }, }], })).toThrow(/block count does not match assistant content/) }) @@ -330,6 +330,28 @@ describe('toPiContext', () => { blocks: [{ type: 'text' }], } + it.each([ + ['provider', { ...validReplay, provider: 'openai' }], + ['model', { ...validReplay, model: 'deepseek-v4-pro' }], + ])('rejects replay metadata whose %s differs from assistant provenance', (field, replayState) => { + try { + toPiContext({ + provider: 'deepseek', + model: 'next-model', + messages: [{ + role: 'assistant', + content: [{ type: 'text', text: 'done' }], + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState }, + }], + }) + expect.fail('expected invalid replay state') + } catch (error: unknown) { + expect(error).toBeInstanceOf(LlmError) + expect((error as LlmError).code).toBe('INVALID_REPLAY_STATE') + expect((error as Error).message).toContain(`${field} does not match assistant provenance`) + } + }) + it.each([ ['number state', 1, 'expected an object'], ['null state', null, 'expected an object'], @@ -355,7 +377,7 @@ describe('toPiContext', () => { messages: [{ role: 'assistant', content: [{ type: 'text', text: 'done' }], - provenance: { provider: 'deepseek', model: 'old', replayState }, + provenance: { provider: 'deepseek', model: 'deepseek-v4-flash', replayState }, }], })).toThrow(message) }) From 182c622eab436569bbfac4db0cb1d4117f67a6de Mon Sep 17 00:00:00 2001 From: Yichen Jiang Date: Thu, 16 Jul 2026 16:42:04 +0800 Subject: [PATCH 8/9] docs: stay within architecture word budget --- docs/architecture.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/architecture.md b/docs/architecture.md index 16f3ee0541..0e1a3238a7 100644 --- a/docs/architecture.md +++ b/docs/architecture.md @@ -127,7 +127,7 @@ Durability is a plugin concern. Persistence backends buffer synchronous `session Messages are arrays of typed content blocks (`text`, `reasoning`, `tool-call`, `tool-result`). The union derives from the merge-extensible `ContentBlockMap`; the same pattern types `MessageSource`, `FinishReason`, `TurnTrigger`, and `TurnEndReason`. New block types are coordinated across adapters, UI bridges, compaction pricing, and persistence, so block types remain a repo-wide contract. -Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing assistant provider/model provenance plus replay state. An `LlmAdapter` implements `stream()`, registers provider routes, and may expose advisory selector metadata; the adapter still resolves and validates model ids. Replay state reaches a target only when both routes map to the same adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). +Streaming uses raw chunks (`block-start` through `finish`) and `BlockAssembler`. The loop logs and assembles chunks, storing provider/model provenance plus replay state. An `LlmAdapter` implements `stream()`, registers provider routes, and may expose selector metadata; it resolves and validates model ids. Replay state reaches targets only when both routes map to one adapter instance, which owns validation and conversion. The contract lives in [llm-streaming.md](core-data-structures/llm-streaming.md). ## Extension And Composition From cfa5d60ccb8c89aabc6a6fc770f98bd10fb2befa Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Fri, 17 Jul 2026 22:02:54 +0800 Subject: [PATCH 9/9] docs(website): align LLM references with provider routing --- website/zh-CN/api/harness/agent-loop.md | 6 ++-- website/zh-CN/api/harness/events.md | 28 ++++++++-------- website/zh-CN/api/harness/llm.md | 44 ++++++++++++++++--------- website/zh-CN/api/harness/sessions.md | 18 +++++----- website/zh-CN/develop/basic/config.md | 9 +++-- 5 files changed, 61 insertions(+), 44 deletions(-) diff --git a/website/zh-CN/api/harness/agent-loop.md b/website/zh-CN/api/harness/agent-loop.md index bf7492639b..9c99b81fc6 100644 --- a/website/zh-CN/api/harness/agent-loop.md +++ b/website/zh-CN/api/harness/agent-loop.md @@ -22,7 +22,7 @@ Create an agent on a fresh per-run session, owned by the accessing fiber. Constr **Returns** the published running agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L389) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L391) ### ctx.agentLoop.createAgent(ownerCtx, options) @@ -37,7 +37,7 @@ Create an owned agent on a caller-supplied session id. **Returns** the published handle. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L412) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L414) ### ctx.agentLoop.resume(ownerCtx, options) @@ -52,4 +52,4 @@ Resume an owned agent from the configured persistence service. **Returns** the published handle. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L443) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent-loop/src/index.ts#L445) diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index e1d4aca11d..794deb3571 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -18,7 +18,7 @@ A fully configured agent and live session were published. Setup is composition-o - `agent` — the newly registered agent with its live session and completed setup. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L151) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L153) ### agent/disposed @@ -32,7 +32,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence but bef - `agent` — the exact agent removed from the registry. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L160) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L162) ### agent/error @@ -49,7 +49,7 @@ A step or turn errored. The loop reports a failure here (plus the logger) even w - `step` — the step at which the failure surfaced. - `error` — the failure, verbatim. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L295) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L297) ### agent/pre-step @@ -68,7 +68,7 @@ Awaited serial checkpoint for session-surface mutation after prompt assembly and - `sessionPrefix` — the frozen request prefix. - `signal` — the turn abort signal. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L214) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L216) ### agent/prompt-submit @@ -84,7 +84,7 @@ Allow, rewrite, or block one drained prompt before it becomes a user message. Ca - `content` — the drained message's blocks, as queued. - `source` — the message's resolved source. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L224) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L226) ### agent/queued @@ -100,7 +100,7 @@ Detached, frozen content entered the agent's inbox. Source defaults have already - `content` — the accepted content blocks retained by the inbox. - `info` — the accepted source plus whether it entered as steering. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L179) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L181) ### agent/request @@ -117,7 +117,7 @@ Replace the frozen call configuration. Model-visible content must use logged cha - `step` — the step whose request this is. - `config` — the config the loop would use (frozen); return a replacement to switch. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L236) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L238) ### agent/session-prefix @@ -133,7 +133,7 @@ Compose request-only messages placed before derived history. The frozen result i - `prefix` — the frozen seed; return an extended replacement. - `signal` — aborts composition when the step is torn down. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L251) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L253) ### agent/session-start @@ -148,7 +148,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to - `agent` — the agent whose session lifecycle began. - `source` — why the session started (fresh startup, resume, …). Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L192) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L194) ### agent/status @@ -163,7 +163,7 @@ Agent status changed (`idle` ⇄ `running`, or → `disposed`). `send()` does no - `agent` — the agent whose status flipped. - `status` — the status just entered (the transition's destination). Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L169) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L171) ### agent/step-result @@ -180,7 +180,7 @@ Waterfall: post-process the assembled assistant Message before tool dispatch (va - `step` — the step that produced the message. - `message` — the assistant message as assembled from the stream. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L262) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L264) ### agent/turn-continuation @@ -196,7 +196,7 @@ Override whether the turn continues. The default continues after tool calls or s - `turn` — the turn being continued or stopped. - `defaultDecision` — what the loop would do absent an override. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L272) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L274) ### agent/turn-stop @@ -211,7 +211,7 @@ Monotonic terminal-stop checkpoint after continuation and steering are folded; a - `agent` — the agent whose composed continuation outcome may be stopped. - `turn` — the turn at its terminal-stop checkpoint. Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L282) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/agent/src/types.ts#L284) ## approval/* @@ -291,7 +291,7 @@ Waterfall around every streaming model call (retry, replay, routing). Bound to t - `options` — the full request. A LOOP-built request arrives deep-frozen (mutation throws): its content is a pure function of the session log (the reconstructability RFC), so listeners read it, never rewrite it. A hand-built one-shot (compaction summarize) is the caller's own object and stays mutable here. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L39) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L40) ## session/* diff --git a/website/zh-CN/api/harness/llm.md b/website/zh-CN/api/harness/llm.md index 65c622e9f9..200e926d15 100644 --- a/website/zh-CN/api/harness/llm.md +++ b/website/zh-CN/api/harness/llm.md @@ -6,34 +6,48 @@ The abstract `llm` service: an adapter registry plus a streaming model-call surface, interceptable via the `llm/stream` waterfall. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L75) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L96) -### ctx.llm.registerAdapter(models, adapter) +### ctx.llm.registerAdapter(providers, adapter) ```ts website-api -registerAdapter(models: string[], adapter: LlmAdapter): () => void +registerAdapter(providers: string[], adapter: LlmAdapter): () => void ``` -Register an adapter for the given model names. Throws `LlmError` with code `DUPLICATE_ADAPTER` if any model already has an adapter (all-or-nothing). Disposed with the fiber. +Register an adapter for the given provider routes. Throws `LlmError` with code `DUPLICATE_ADAPTER` if any provider already has an adapter (all-or-nothing). Disposed with the fiber. -- `models` — every model name this adapter should serve. -- `adapter` — the adapter that streams calls for those models. +- `providers` — every provider route this adapter should serve. +- `adapter` — the adapter that streams calls for those providers. **Returns** the disposer that unregisters all of them. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L90) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L111) -### ctx.llm.models() +### ctx.llm.listProviders() ```ts website-api -models(): string[] +listProviders(): LlmProviderInfo[] ``` -Model names with a registered adapter. +Describe provider routes with a registered adapter. -**Returns** the registered names, in registration order. +**Returns** detached provider metadata in registration order. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L111) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L142) + +### ctx.llm.listModels(provider) + +```ts website-api +async listModels(provider: string): Promise +``` + +Discover models advertised by one registered provider. Catalog membership is advisory and never changes routing or request validation. + +- `provider` — registered provider route to inspect. + +**Returns** detached model metadata in adapter-preferred order. + +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L152) ### ctx.llm.stream(options) @@ -41,10 +55,10 @@ Model names with a registered adapter. stream(options: GenerateOptions): AsyncIterable ``` -Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with code `NO_ADAPTER` if no adapter is registered for `options.model`. Dispatches through the `llm/stream` waterfall. +Stream one model call as raw chunks (token-level deltas). Throws `LlmError` with code `NO_ADAPTER` if no adapter is registered for `options.provider`. Replay state is retained only when the same adapter instance owns its historical provider and the target provider. Dispatches through the `llm/stream` waterfall. -- `options` — the full request; `options.model` selects the adapter. +- `options` — the full request; `options.provider` selects the adapter. **Returns** the chunk stream, possibly wrapped by `llm/stream` listeners. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L128) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/llm/llm/src/index.ts#L210) diff --git a/website/zh-CN/api/harness/sessions.md b/website/zh-CN/api/harness/sessions.md index 5ff551f947..a83deb044a 100644 --- a/website/zh-CN/api/harness/sessions.md +++ b/website/zh-CN/api/harness/sessions.md @@ -7,7 +7,7 @@ In-memory session store (`ctx.sessions`). Persistence is intentionally not implemented here — persistence plugins subscribe to `session/event` and flush on `session/flush` / dispose. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L540) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L567) ### ctx.sessions.create(id?, options?) @@ -23,7 +23,7 @@ For an agent whose session must be torn down IN ORDER with its loop (so the loop **Returns** the live session, already entered and announced. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L569) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L596) ### ctx.sessions.prepare(id?, options?) @@ -38,7 +38,7 @@ Build a session WITHOUT entering it into the store — validate the id/cwd and c **Returns** the constructed session, NOT yet in the store. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L598) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L625) ### ctx.sessions.enter(session) @@ -53,7 +53,7 @@ Re-checks the id for a duplicate: `prepare` and `enter` are public cross-package **Returns** the detach disposer (publication hooks + store removal). When called from a synchronous `session/created` listener, removal and disposal wait until that creation dispatch unwinds. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L642) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L669) ### ctx.sessions.announce(session) @@ -65,7 +65,7 @@ Emit `session/created` exactly once for an entered session (with the carrier ent - `session` — the entered session to announce to listeners. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L697) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L724) ### ctx.sessions.flush(session) @@ -79,7 +79,7 @@ Dispatch the awaited `session/flush` durability checkpoint for `session`, with t **Returns** resolves when every flush listener has settled; after all settle, rejects with the first registered listener failure if any listener failed. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L749) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L776) ### ctx.sessions.get(id) @@ -93,7 +93,7 @@ Look up a live session. **Returns** the session, or undefined when no live session has that id. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L781) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L808) ### ctx.sessions.list() @@ -105,7 +105,7 @@ All live sessions, in creation order. **Returns** a fresh array; mutating it does not affect the store. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L789) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L816) ### ctx.sessions.fork(source, boundary?, childSessionId?) @@ -121,4 +121,4 @@ Create a live child session from a turn-enclosed prefix of a live source. `bound **Returns** The created live child session. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L806) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/core/session/src/index.ts#L833) diff --git a/website/zh-CN/develop/basic/config.md b/website/zh-CN/develop/basic/config.md index 8b1edf385f..c912f49111 100644 --- a/website/zh-CN/develop/basic/config.md +++ b/website/zh-CN/develop/basic/config.md @@ -83,23 +83,26 @@ export interface Config { ### 配置错误要响亮 -如果配置引用了不存在的东西（比如一个不存在的模型名），应该尽早报错，而不是静默跳过： +如果配置引用了不存在的东西（比如一个未注册的 LLM 提供方路由），应该尽早报错，而不是静默跳过： ```ts import type { Context } from 'cordis' import type {} from '@deepseek-ai/dsh-llm' export interface Config { + provider: string model: string } export function apply(ctx: Context, config: Config) { - if (!ctx.llm.models().includes(config.model)) { - throw new Error(`Model "${config.model}" is not registered by any LLM adapter`) + if (!ctx.llm.listProviders().some(provider => provider.id === config.provider)) { + throw new Error(`LLM provider "${config.provider}" is not registered`) } } ``` +模型目录只用于发现；适配器可能接受目录之外的模型 ID，因此不能把 `listModels()` 当作请求白名单。 + ## 配合 HMR 配置变更会触发插件热替换：修改 `cordis.yml` 中某个插件的 `config`，框架会卸载旧实例、加载新实例。由于注册都是效果（自动清理），这个过程是安全的。