From 61136b22bbfabae49227843f924cc4832a07fe51 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:09:09 +0800 Subject: [PATCH 01/33] refactor: remove UI identity translations --- docs/config-catalog.md | 4 +- docs/rfc/INDEX.md | 2 +- .../architecture/2026-06-20-branded-ids.md | 4 +- .../2026-06-20-unify-agent-and-session-id.md | 38 ++++++++++++++ .../2026-06-20-unify-agent-and-session-id.md | 38 -------------- packages/ui/acp/README.md | 4 +- packages/ui/acp/src/index.ts | 52 ++++++++----------- packages/ui/acp/tests/approval.spec.ts | 9 ++-- packages/ui/acp/tests/bridge.spec.ts | 3 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 34 ++++-------- packages/ui/jsonrpc/tests/server.spec.ts | 20 ++++--- 12 files changed, 100 insertions(+), 110 deletions(-) create mode 100644 docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md delete mode 100644 docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 94d613bc4e..4ae020f0be 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` · `sessionPersistence` · `tools` · `userInteraction` ```ts config-catalog /** Plugin config: the agent template ACP sessions are created from. */ @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:249`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:246`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-agent` diff --git a/docs/rfc/INDEX.md b/docs/rfc/INDEX.md index a5334a63e1..5ed8c6ae6d 100644 --- a/docs/rfc/INDEX.md +++ b/docs/rfc/INDEX.md @@ -17,7 +17,6 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | Title | First proposed | |---|---| -| [Unify the agent id and the session id](proposed/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Prune dead public and result surface](proposed/simplification/2026-07-04-prune-dead-core-spine-surface.md) | 2026-07-04 | | [Drop unconsumed skill provider events](proposed/simplification/2026-07-12-drop-unconsumed-skill-provider-events.md) | 2026-07-12 | | [Prune unused web seam fields](proposed/simplification/2026-07-12-prune-unused-web-seam-fields.md) | 2026-07-12 | @@ -87,6 +86,7 @@ Generated by `pnpm run gen-rfc-index` from the RFC tree — never edit by hand; | [Prune dead methods from the persistence seam](implemented/simplification/2026-06-20-prune-dead-seam-methods.md) | 2026-06-20 | | [Keep one public stop primitive](implemented/simplification/2026-06-20-public-agent-stop-surface.md) | 2026-06-20 | | [Stop mirroring durable boundaries as agent events](implemented/simplification/2026-06-20-remove-agent-boundary-mirror-events.md) | 2026-06-20 | +| [Unify the agent id and the session id](implemented/simplification/2026-06-20-unify-agent-and-session-id.md) | 2026-06-20 | | [Split the filesystem seam — provider text mutations plus the `dsh-fs-policy` plugin](implemented/simplification/2026-06-26-fsspec-style-fs-seam.md) | 2026-06-26 | | [Stop mirroring the token stream as an agent event](implemented/simplification/2026-07-02-remove-stream-chunk-mirror.md) | 2026-07-02 | | [Drop the `image` content block until a path can honor it](implemented/simplification/2026-07-04-drop-image-content-block.md) | 2026-07-04 | diff --git a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md index 5fe8224644..4fe7f58168 100644 --- a/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md +++ b/docs/rfc/implemented/architecture/2026-06-20-branded-ids.md @@ -8,7 +8,7 @@ The harness brands `CallId` (`packages/llm/llm/src/brand.ts`) and the shared age **Gap 1 — unbranded cross-boundary IDs in the bash seam.** The background-task id is a plain `string`: `BashTask.id: string` (`packages/bash/bash/src/types.ts`), carried as `string` through the whole executor seam (`BashExecutor.get`/`ownerOf`/`readOutput`/`kill(id: string)` in `packages/bash/bash/src/index.ts`) and validated/passed as `string` by the model-facing tools (`validateTaskId`, `assertTaskAccess`, the `task_id` schema arg in `packages/bash/tool-bash/src/index.ts`). It is generated by a per-executor counter — `` `bash-${this.nextTaskId++}` `` in `packages/bash/bash-local/src/index.ts` — which gives it **exactly the same `name-N` shape as `SessionId`'s default** (`` `session-${++counter}` `` in `packages/core/session/src/index.ts`). A bash task id and a session id are trivially swappable at a call site and the compiler says nothing. This is the headline case the user asked about, and it is a model-facing id (the model passes `task_id` back to `bash_output`/`bash_kill`), so a confusion here is reachable from untrusted input. -The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias that the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal calls the "bash owner-token alias hole". +The bash **owner token** is the related sub-case: `BashExecRequest.owner?: string` and `BashExecSpec.owner: string | undefined` (`packages/bash/bash/src/types.ts`) are documented as a deliberately *opaque* isolation key, but in every live caller the value IS the owning agent's `session.header.id` (`callerToken = (exec) => exec.agent?.session.header.id` in `packages/bash/tool-bash/src/index.ts`) — i.e. a `SessionId` wearing a `string` disguise. It is compared for access control (`owner !== callerToken(exec)`), so a mismatched-but-well-typed string here is a cross-session isolation bug the type system currently cannot catch. This is the same `session.header.id`-as-owner alias covered by the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md). **Gap 2 — brand erosion at the seams of the *already-branded* IDs.** Even `CallId` and `SessionId` decay back to bare `string` at exactly the places confusion is most likely: registry/store key types and public method params. Representative sites include the session store, the agent registry (both keyed by the shared `SessionId`), `ToolPresenter`'s call-id map, ACP's session-id records and loading set, and the persistence coordinator. A brand that is dropped at a collection key buys nothing on lookups — the value of the existing brands is partly unrealized. @@ -62,6 +62,6 @@ The landed invariants: `BashTaskId` and `OwnerToken` are defined in `dsh-bash` a ## Consequences -- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unify-the-agent-id-and-the-session-id](../../proposed/simplification/2026-06-20-unify-agent-and-session-id.md) proposal (both touch the session-id / owner-token boundary); if that proposal lands, `OwnerToken` still stays distinct from the unified id for the decoupling reason above. +- **Mechanical churn across two surfaces.** Propagating brands touches the bash seam (interface + impl + consumer) and the ACP session-id surface plus the persistence coordinator. The churn is broad but low-severity: a missed site is a compile error, not a silent bug. The change is observably type-only — no snapshot or e2e behavioral diff. It sits next to the [unified agent/session identity decision](../simplification/2026-06-20-unify-agent-and-session-id.md) because both touch the session-id / owner-token boundary; `OwnerToken` stays distinct from the unified id for the decoupling reason above. - **Brands do not validate.** A brand is a confusability guard, not a correctness proof: a *wrong* session id that is still a well-formed string passes the type checker exactly as before. This RFC does not close that gap (see Out of scope) — it only stops the *category* error of passing the wrong *kind* of id. - **The "where to stop" line stays a judgment call.** Branding `BashTaskId` but not `ToolName`, `OwnerToken` but not `ModelId`, is a taste call about which strings "could plausibly be confused." Reasonable reviewers may want more or fewer; the policy in `brand.ts` is the tie-breaker, and this RFC errs toward the ids that are model-facing or used for access control. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md new file mode 100644 index 0000000000..79d7332553 --- /dev/null +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -0,0 +1,38 @@ +# RFC: Unify the agent id and the session id + +Status: implemented + +## Problem + +The agent factory previously carried two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` took both; `ResumeAgentOptions` took `agentId` plus `resumeSessionId`; in-process subagents minted two independent UUIDs despite recording lineage separately. + +ACP already used the same value for both identities. Where they diverged, stdio kept `labelBySession` solely to recover an agent label from session events, and hooks exposed both values for authors to reconcile. No production path reattached one live agent object to several sessions or drove one session through several agent ids. + +The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) had no reservation side tables: create and resume used one `AgentCreationTransaction`, and agent/session entries used the same final-entry collision rule. Separate ids therefore did not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification was only an API and representation simplification: it deleted one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. + +Session itself repeated the same fact as `Session.id` and `Session.header.id`. Construction rejected a header whose id differed, so the aliases were constrained equal; the durable boundary nevertheless had to validate the duplicate, and production consumers chose between its two homes. + +## Decision + +An agent's registry id equals its session id. `CreateAgentOptions` accepts one `sessionId` used for both final registry entries; resume registers the agent under `resumeSessionId`; subagent creation mints one combined id; and `Session.id` derives from `header.id`. The existing creation transaction, final-entry collision checks, and exact-entry detach semantics remain; maps and fields whose sole job was translating between the ids are gone. + +The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. + +`agent/created` and `agent/disposed` remain. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. + +## Alternatives considered + +**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. + +## Verification + +- Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. +- The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. ACP verifies exact `Agent` ownership from the forward session map; JSON-RPC caches only disposable-child parent lineage. +- The config-driven resume-or-create policy is explicit and covered across a durable restart. +- A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. +- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. + +## Consequences + +This forecloses latent multi-session-actor and session-handoff designs and makes persisted client-chosen session identity the registry identity. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md deleted file mode 100644 index 6e3eea1515..0000000000 --- a/docs/rfc/proposed/simplification/2026-06-20-unify-agent-and-session-id.md +++ /dev/null @@ -1,38 +0,0 @@ -# RFC: Unify the agent id and the session id - -Status: proposed - -## Problem - -The agent factory carries two ids for each live agent/session pair: `agentId`, the `AgentRegistry` routing handle, and `sessionId`, the event-sourced/persisted-log identity. `CreateAgentOptions` takes both; `ResumeAgentOptions` takes `agentId` plus `resumeSessionId`; in-process subagents mint two independent UUIDs despite recording lineage separately. - -ACP already uses the same value for both identities. Where they diverge, stdio keeps `labelBySession` solely to recover an agent label from session events, and hooks expose both values for authors to reconcile. No production path reattaches one live agent object to several sessions or drives one session through several agent ids. - -The [agent-scope runtime](../../implemented/architecture/2026-07-12-agent-scope-runtime-design.md) has no reservation side tables: create and resume use one `AgentCreationTransaction`, and agent/session entries use the same final-entry collision rule. Separate ids therefore do not duplicate asynchronous liveness, rollback, or quiescence machinery. Identity unification is only an API and representation simplification: it deletes one caller-supplied id, one UUID per in-process child, and the remaining translation paths without changing the transaction lifecycle. - -Session itself repeats the same fact as `Session.id` and `Session.header.id`. Construction rejects a header whose id differs, so the aliases are constrained equal; the durable boundary must nevertheless validate the duplicate, and production consumers choose between its two homes. - -## Proposal - -Make an agent's registry id equal its session id. `CreateAgentOptions` accepts one id used for both final registry entries; resume registers the agent under the resumed session id; subagent creation mints one combined id; Session keeps one identity home by deriving `id` from `header.id` or removing the alias. Keep the existing creation transaction, final-entry collision checks, and exact-entry detach semantics; remove only maps and fields whose sole job is translating between the ids. - -The config-driven path keeps `agents[].id` as a stable configuration label, not a live routing identity. A fresh start mints the combined id `${label}-session-${randomUUID()}` so durable restarts do not collide; `resumeSessionId` instead supplies the exact combined identity to load and register. Logs may use the stable label while all live and durable lookups use the one `SessionId`. - -`agent/created` and `agent/disposed` remain outside this proposal. They are paired publication lifecycle events, not identity aliases; any later consumer-free removal needs its own proposal after a fresh search. - -## Alternatives considered - -**Keep separate routing and log identities.** A stable configured label plus a fresh durable conversation is useful, but it does not require two live identities: the label can remain configuration/display metadata while the combined per-run `SessionId` owns routing and persistence. Keeping two ids would preserve translation maps and permit impossible pairings without adding lifecycle capability. - -## Acceptance criteria - -- Agent create/resume and subagent creation carry one identity; `Session` stores it in one place. -- The existing creation transaction keeps final-entry collision, exact-entry detach, rollback, and quiescence guarantees without adding identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage need no agent/session id translation. -- The config-driven resume-or-create policy is explicit and covered across a durable restart. -- `agent/created`/`agent/disposed` are removed only if a post-change production search finds no listener; otherwise they and their publication semantics stay. -- Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. - -## Risks - -This forecloses latent multi-session-actor and session-handoff designs, makes persisted client-chosen session identity the registry identity, and touches every factory fixture. If separate routing identity becomes a real requirement, it needs an explicit lifecycle design rather than an unconstrained caller-supplied pair. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index f4947e5d25..31a865c068 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,7 +8,7 @@ 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. -`inject: ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session. +`inject: ['agents', 'sessionPersistence', 'tools', 'userInteraction']` — programs against the interface packages only (never `dsh-agent-loop`). `sessionPersistence` is required because `initialize` advertises `loadSession: true`; `tools` lets a tool own how its calls render (`presentCall`/`presentResult`) — the bridge looks the definition up by name and falls back to a generic presentation when a tool declares none (see Tool-call presentation). `userInteraction` lets agent-owned `ask_user_question` calls become ACP form elicitations routed to the owning session. ### Config @@ -36,7 +36,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: ## Multi-session -The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map` (forward) with a `WeakMap` reverse map so agent-scoped approval events demultiplex in O(1). Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership: the `approval/request` answerer resolves the owning session through the reverse map and prompts only there. +The bridge multiplexes N sessions over one connection. Live sessions are held in a `Map` keyed by the shared agent/session id. Agent-scoped events derive that id from `agent.session.id` and verify the record owns the exact agent object, so a foreign same-id object cannot claim the bridge's session. Every `session/event` is routed strictly to its owning record, so concurrent sessions never cross-settle or interleave their `session/update` notifications. State is per session: one in-flight prompt each, `session/cancel` aborts and settles only its own agent/prompt, and disposal drains every live session in parallel to quiescence. Permission prompts follow the same ownership and prompt only the matching session. ## Session config options diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index e795c7e177..369c8ae166 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -18,12 +18,11 @@ * turn about to start) + settle the in-flight prompt * * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by id in `sessions` (forward) with an - * `agent→sessionId` reverse map for O(1) demux of `agent/*` events; every - * `session/event` and `agent/*` event is routed strictly to its owning session - * record, so two sessions streaming at once never interleave their - * `session/update` notifications. Permission prompts ride the same ownership - * map: the bridge answers `approval/request` for its own agents over + * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; + * every `session/event` and `agent/*` event is routed strictly to its owning + * session record, so two sessions streaming at once never interleave their + * `session/update` notifications. Permission prompts use the same identity: the + * bridge answers `approval/request` for its own agents over * `session/request_permission` (see the approval answerer below) — whether a * call ASKS is policy (a hook or plugin returning `ask`), not the bridge's. * @@ -106,9 +105,7 @@ export const name = 'acp' // because `initialize` advertises `loadSession: true`. `tools` lets a tool own // how its calls render (`presentCall`/`presentResult`); the bridge looks up the // definition by name and falls back to a generic presentation when absent. -// TODO(acp-session-inject): drop `sessions`; this bridge never reads -// ctx.sessions, and agent/session ownership is already behind ctx.agents. -export const inject = ['agents', 'sessions', 'sessionPersistence', 'tools', 'userInteraction'] +export const inject = ['agents', 'sessionPersistence', 'tools', 'userInteraction'] /** * Build an ACP "invalid params" error whose human detail rides in the message. @@ -268,7 +265,6 @@ export const Config: Schema = Schema.object({ * map keyed by id (RFC 011 multi-session). */ interface SessionRecord { - sessionId: SessionId agent: Agent /** * The owned-agent disposer (from the {@link AgentHandle} the factory returned). @@ -353,15 +349,8 @@ export function apply(ctx: Context, config: AcpConfig): void { // this warn sink so a throwing tool presenter is logged, not propagated. const makePresenter = (agent?: Agent): ToolPresenter => new ToolPresenter(tools, (message) => { logger.warn(message) }, agent) - // TODO(derive-acp-session-id): derive an event's id from agent.session and - // verify sessions.get(id)?.agent === agent; then remove this reverse map and - // SessionRecord.sessionId, whose sole read duplicates the same identity. - // Live sessions keyed by id (RFC 011 multi-session), plus an agent→sessionId - // reverse map so `agent/*` events (which carry only the Agent) demux in O(1). - // The forward record and weak reverse entry are installed together; removing - // the record releases its strong Agent reference, so the WeakMap entry expires. + // Live sessions keyed by their shared agent/session id (RFC 011 multi-session). const sessions = new Map() - const bySession = new WeakMap() // Session ids whose `session/load` is mid-`resume()` (the slot is reserved // before the async resume so a pipelined load/new for the SAME id can't create // two agents). Distinct ids load concurrently; a given id loads once at a time. @@ -382,20 +371,26 @@ export function apply(ctx: Context, config: AcpConfig): void { // `notify` never observes it unset — no undefined guard needed. let conn: AgentSideConnection + /** Return the bridge-owned record for an agent, rejecting same-id impostors. */ + const ownedRecord = (agent: Agent): SessionRecord | undefined => { + const rec = sessions.get(agent.session.id) + return rec?.agent === agent ? rec : undefined + } + userInteraction.registerProvider({ async ask(request: AskUserQuestionRequest): Promise { if (request.agent === undefined) { throw new UserInteractionError('ACP user questions must come from an agent-owned request', 'NO_AGENT') } - const sessionId = bySession.get(request.agent) - if (sessionId === undefined) { + const rec = ownedRecord(request.agent) + if (rec === undefined) { throw new UserInteractionError('ACP user question has no matching session', 'NO_SESSION') } const answers: AskUserQuestionAnswerItem[] = [] for (const question of request.questions) { const options = question.options ?? [] const response = await withAbort(conn.unstable_createElicitation( - elicitationForQuestion(sessionId, question, options), + elicitationForQuestion(rec.agent.session.id, question, options), ), request.signal).catch((error: unknown) => { if (error instanceof UserInteractionError) throw error throw new UserInteractionError('ACP elicitation request failed', 'ASK_FAILED', { cause: error }) @@ -496,7 +491,7 @@ export function apply(ctx: Context, config: AcpConfig): void { const rec = sessions.get(session.header.id) if (rec === undefined) return try { - streamSessionEventUpdate(rec.sessionId, event, notify, rec.presenter, { + streamSessionEventUpdate(rec.agent.session.id, event, notify, rec.presenter, { enabled: rec.terminalEnabled, cwd: session.header.cwd, }, { includeUserMessages: false }) @@ -527,12 +522,12 @@ export function apply(ctx: Context, config: AcpConfig): void { // allow_always is a grant-storage design the approval RFC defers, so the // prompt never offers a durable grant the harness could not honor. ctx.on('approval/request', (req, next) => { - const sessionId = bySession.get(req.agent) + const rec = ownedRecord(req.agent) // The protocol requires `toolCall` (the prompt renders attached to it), so // a request without a callId has nothing to attach to — delegate. - if (sessionId === undefined || req.callId === undefined) return next() + if (rec === undefined || req.callId === undefined) return next() return conn.requestPermission({ - sessionId, + sessionId: rec.agent.session.id, toolCall: { toolCallId: req.callId }, options: [ { optionId: 'allow-once', name: 'Allow once', kind: 'allow_once' }, @@ -639,8 +634,7 @@ export function apply(ctx: Context, config: AcpConfig): void { // turn) leaves the switch pending — it runs no step, so nothing executes // or assembles under a stale value. ctx.on('agent/prompt-submit', (agent, _content, _source, next) => { - const sessionId = bySession.get(agent) - const rec = sessionId === undefined ? undefined : sessions.get(sessionId) + const rec = ownedRecord(agent) if (rec !== undefined) flushPendingSwitches(rec) return next() }) @@ -699,9 +693,7 @@ export function apply(ctx: Context, config: AcpConfig): void { await handle.dispose() throw internalError('connection closed during session/new') } - bySession.set(handle.agent, sessionId) sessions.set(sessionId, { - sessionId, agent: handle.agent, dispose: () => handle.dispose(), presenter: makePresenter(handle.agent), @@ -773,13 +765,11 @@ export function apply(ctx: Context, config: AcpConfig): void { throw invalidParams('connection closed during session/load') } const agent = handle.agent - bySession.set(agent, sessionId) // Snapshot the terminal capability ONCE for this session (used by both // the replay below and the post-load live stream) so a later // `initialize` can't desync the call/result of a tool card. const terminalEnabled = terminalOutputCap const record: SessionRecord = { - sessionId, agent, dispose: () => handle.dispose(), presenter: makePresenter(agent), diff --git a/packages/ui/acp/tests/approval.spec.ts b/packages/ui/acp/tests/approval.spec.ts index 36846ac728..65679cd905 100644 --- a/packages/ui/acp/tests/approval.spec.ts +++ b/packages/ui/acp/tests/approval.spec.ts @@ -90,9 +90,12 @@ describe('acp bridge — approval answerer', () => { await harness.ctx.plugin(ApprovalService) harness.onPermission = () => ({ outcome: { outcome: 'selected', optionId: 'allow-once' } }) - // Not created through the bridge: no bySession entry, so the answerer must - // call next() — nobody else answers, so the seam fails closed. - const foreign = { session: { events: [{ type: 'turn/start' }], append: () => ({}) } } as unknown as Agent + const { agent } = await ownedAgentRequest(harness) + // Even an impostor that claims the bridge-owned session id must delegate: + // ownership requires the exact Agent object stored in the session record. + const foreign = { + session: { id: agent.session.id, events: [{ type: 'turn/start' }], append: () => ({}) }, + } as unknown as Agent await expect(harness.ctx.approval.request({ agent: foreign, toolName: 'echo', callId: CallId('c') })) .resolves.toBe('unavailable') expect(harness.permissionRequests).toHaveLength(0) diff --git a/packages/ui/acp/tests/bridge.spec.ts b/packages/ui/acp/tests/bridge.spec.ts index 7e780348ba..e7170c380f 100644 --- a/packages/ui/acp/tests/bridge.spec.ts +++ b/packages/ui/acp/tests/bridge.spec.ts @@ -205,7 +205,8 @@ describe('acp bridge', () => { await expect(harness.ctx.userInteraction.ask({ questions: [{ id: 'x', question: 'No agent?' }] })) .rejects.toMatchObject({ name: 'UserInteractionError', code: 'NO_AGENT' }) - await expect(harness.ctx.userInteraction.ask({ agent: { id: 'other' } as typeof agent, questions: [{ id: 'x', question: 'No session?' }] })) + const impostor = { session: { id: agent.session.id } } as typeof agent + await expect(harness.ctx.userInteraction.ask({ agent: impostor, questions: [{ id: 'x', question: 'No session?' }] })) .rejects.toMatchObject({ code: 'NO_SESSION' }) harness.onElicitation = () => ({ action: 'cancel' }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 007bd1a5f1..933023a2d9 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`). A subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. 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`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 4dbfeb0fa2..cfa083c394 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -58,11 +58,6 @@ interface SessionRecord { activePrompt: boolean } -interface SubagentRecord { - childSessionId: string - parentSessionId: string | undefined -} - /** * The SDK server over a booted harness context. Constructing it subscribes to * the context's `session/event`, `session/created`, `agent/created`, and @@ -76,7 +71,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly subagentSessions = new Map() + private readonly subagentParents = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -100,29 +95,22 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache agent → session lineage on creation: by the time `subagent/end` - // fires the child agent may already be disposed and gone from the registry. + // Cache parent lineage on creation: by the time `subagent/end` fires the + // child agent may already be disposed and gone from the registry. The child + // session id needs no cache because it is the shared agent/session id. this.disposers.push(ctx.on('agent/created', (agent) => { - this.subagentSessions.set(String(agent.id), { - childSessionId: String(agent.session.id), - parentSessionId: agent.session.header.parentSession === undefined - ? undefined - : String(agent.session.header.parentSession), - }) + const parentSessionId = agent.session.header.parentSession + if (parentSessionId !== undefined) this.subagentParents.set(agent.id, parentSessionId) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { - const rec = this.subagentSessions.get(String(info.id)) const agent = this.ctx.agents.get(info.id) - const childSessionId = rec?.childSessionId ?? (agent === undefined ? undefined : String(agent.session.id)) - const parentSessionId = rec?.parentSessionId ?? ( - agent?.session.header.parentSession === undefined ? undefined : String(agent.session.header.parentSession) - ) - if (childSessionId === undefined) return + const parentSessionId = this.subagentParents.get(info.id) ?? agent?.session.header.parentSession + this.subagentParents.delete(info.id) this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), - ...(parentSessionId === undefined ? {} : { parentSessionId }), - childSessionId, + ...(parentSessionId === undefined ? {} : { parentSessionId: String(parentSessionId) }), + childSessionId: String(info.id), status: info.stopReason === 'completed' ? 'ok' : 'error', stopReason: info.stopReason, ...(info.lastAssistantMessage === undefined ? {} : { lastAssistantMessage: info.lastAssistantMessage }), @@ -195,7 +183,7 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.subagentSessions.clear() + this.subagentParents.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 9260a59aae..433119e046 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -272,6 +272,9 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + // The backend may dispose the child before publishing its run outcome; + // only the cached parent lineage should be needed at this point. + await handle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), @@ -292,7 +295,6 @@ describe('HarnessSdkServer', () => { }, }) - await handle.dispose() await parentHandle.dispose() await server.shutdown() } finally { @@ -301,7 +303,7 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live agent lineage for uncached subagent end events', async () => { + it('falls back to live lineage and treats the shared id as the child session id', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -365,10 +367,16 @@ describe('HarnessSdkServer', () => { stopReason: 'error', }, }) - expect(transport.notifications.some(n => - n.method === 'subagent.finished' - && n.params?.agentId === 'missing-child-agent', - )).toBe(false) + expect(transport.notifications).toContainEqual({ + method: 'subagent.finished', + params: { + provider: 'fork', + agentId: 'missing-child-agent', + childSessionId: 'missing-child-agent', + status: 'error', + stopReason: 'error', + }, + }) await server.shutdown() } finally { From 9ebb40b84b404b3568a53cd6fab1b966e2c82c74 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 02:28:04 +0800 Subject: [PATCH 02/33] fix: keep SDK subagent notifications local --- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 8 +++++++- packages/ui/jsonrpc/tests/server.spec.ts | 16 +++++----------- 4 files changed, 14 insertions(+), 14 deletions(-) diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 10521447e0..bb77717e3b 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only disposable-child parent lineage. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend uses the child server's returned session id as its run id; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only local disposable-child parent lineage while leaving remote runs outside its local-session notification pair. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 933023a2d9..2324227ff7 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`). A subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. Runs from remote providers are not reported through this local-session notification pair because they create no local `session/created`/`subagent.started` edge. 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`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index cfa083c394..3c803a6c8c 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -104,8 +104,14 @@ export class HarnessSdkServer { })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const parentSessionId = this.subagentParents.get(info.id) ?? agent?.session.header.parentSession + const cachedParentSessionId = this.subagentParents.get(info.id) this.subagentParents.delete(info.id) + // This protocol reports LOCAL child sessions, paired with the + // session/created-driven subagent.started notification above. A remote + // provider may use a real remote SessionId for its run, but that session + // does not exist in this harness and therefore has no paired start event. + if (cachedParentSessionId === undefined && agent === undefined) return + const parentSessionId = cachedParentSessionId ?? agent?.session.header.parentSession this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 433119e046..e7f591b88f 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -303,7 +303,7 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live lineage and treats the shared id as the child session id', async () => { + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -367,16 +367,10 @@ describe('HarnessSdkServer', () => { stopReason: 'error', }, }) - expect(transport.notifications).toContainEqual({ - method: 'subagent.finished', - params: { - provider: 'fork', - agentId: 'missing-child-agent', - childSessionId: 'missing-child-agent', - status: 'error', - stopReason: 'error', - }, - }) + expect(transport.notifications.some(n => + n.method === 'subagent.finished' + && n.params?.agentId === 'missing-child-agent', + )).toBe(false) await server.shutdown() } finally { From e9d1e1cdda70eedb49a12f9adce2afb18caa4c00 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 06:19:24 +0800 Subject: [PATCH 03/33] docs: update ACP ownership routing --- .../rfc/implemented/feature/2026-06-14-acp-multi-session.md | 4 ++-- .../rfc/implemented/feature/2026-06-25-ask-user-question.md | 2 +- docs/rfc/implemented/feature/2026-07-06-approval-seam.md | 6 +++--- packages/ui/acp/README.md | 2 +- 4 files changed, 7 insertions(+), 7 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md b/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md index 77fa2b4669..64961bee89 100644 --- a/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md +++ b/docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md @@ -8,11 +8,11 @@ An ACP editor can keep several conversations alive over one agent subprocess. A ## Decision -The ACP bridge stores live sessions in `Map` and keeps a `WeakMap` reverse index for agent-scoped callbacks. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently. +The ACP bridge stores live sessions in `Map`. Agent-scoped callbacks use `ownedRecord`: look up `agent.session.id` in that forward map and accept the record only when it owns the exact agent object, so a foreign same-id object cannot claim the session. A record owns its agent handle, in-flight prompt, live tool-call presentation state, pending idle config switches, session cwd, and client capability snapshot. A separate loading-id set reserves each id before asynchronous resume so two pipelined loads cannot construct duplicate agents; distinct ids may load concurrently. Every `session/event` and `agent/status` callback resolves the owning record before sending or settling anything. Each session permits one in-flight prompt independently. The prompt records a log watermark, captures its own `turn/start`, and settles only on the matching `turn/end`; a late end from a cancelled prior turn cannot resolve a newer prompt. `session/cancel` addresses one record and calls only that agent's queue-aware cancel path. -Permission ownership uses the same reverse index. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them. +Permission ownership uses the same exact-agent check against the forward map. The ACP `approval/request` answerer prompts only the editor session that owns the requesting agent and delegates foreign requests. User-interaction elicitations likewise route by agent ownership. Per-session sandbox and approval config values fold only that session's events, with pending idle switches stored on that record until the next turn anchors them. Background bash tasks carry an opaque owner token equal to the owning session id. `bash_output` and `bash_kill` compare the caller's token with the executor's task ownership before reading or killing; a predictable task id alone grants no access. Ownership is stored with the executor task, so a tool plugin reload does not erase it. diff --git a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md b/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md index 9320189de1..42e5d9a7ab 100644 --- a/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md +++ b/docs/rfc/implemented/feature/2026-06-25-ask-user-question.md @@ -22,7 +22,7 @@ Providers return `{ answers: [{ id, selected, custom? }] }`. `selected` is alway `dsh-stdio-agent`'s in-package readline module renders each question, shows each option's `description` on the next line, supports comma/space-separated numeric choices for `multi_select`, accepts free-form custom answers, and rejects pending questions on abort, provider disposal, or stdin EOF. A batched request is asked in order and resolved as one answer object. The stdio provider serializes simultaneous requests with an internal queue so only one prompt owns stdin at a time. -`dsh-acp` provides the same seam for ACP sessions. It routes an ask request from the calling `Agent` through the bridge's `agent→sessionId` reverse map and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s. +`dsh-acp` provides the same seam for ACP sessions. It resolves the calling `Agent` through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, and calls ACP `unstable_createElicitation` with a session-scoped form for each question. Single-select options become a `choice` string enum; `multi_select` options become a `choice` array enum; optionless questions use a required `custom` text field. If the client returns both `choice` and non-empty `custom`, the custom answer wins. ACP `decline`/`cancel`, a missing answer, a missing session, and a client without elicitation support all become structured `UserInteractionError`s. The ACP mapping deliberately uses elicitation, not `session/request_permission`. `request_permission` is still reserved for the separate permission gate: it is a yes/no-or-policy authorization protocol around tool execution. `ask_user_question` is a general information-gathering tool with optional free-form answers, so ACP form elicitation is the closer protocol fit. The bridge's session routing is shared with the future permission gate, but the user intent is different. diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 5d82226a96..c5d61b0edb 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -65,9 +65,9 @@ The seam also owns the session-scoped approval policy — the approval knob of t #### The ACP answerer -The bridge registers the first real answerer: it resolves the owning session through its existing `WeakMap` reverse map, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. +The bridge registers the first real answerer: it resolves the owning session through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. -The answerer routes through the bridge's reverse-map ownership seam described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). +The answerer routes through the bridge's exact-agent ownership check described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). #### Audit, and what the model sees @@ -137,5 +137,5 @@ In-repo precedents this design copies or contrasts with: - The `fs/write-intent` gate (`packages/fs/fs/`) — the documented single-occupancy decision-slot waterfall semantics (first answer wins, delegate via `next()`) the answerer contract reuses. - `hook/invoked`/`hook/result` — the log-only audit-pair precedent `approval/asked`/`approval/decided` follows; [the hook-bridges RFC](2026-06-30-hook-bridges.md) ships `permissionDecision: ask`, the first producer. - [The interception-seams RFC](2026-06-30-interception-seams.md) — the `tools/pre-execute` `allow`/`deny`/`ask` vocabulary whose `ask` this seam services. -- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the `WeakMap` ownership seam the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. +- [The ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md) — the exact-agent ownership check against the forward session map that the answerer routes through; [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md) — the per-session permission-ownership blocker this implements. - The opportunistic `ctx.get()` consumption pattern (`tool-bash`'s owner-token lookup, the loop's persistence probe) — how `dsh-tools` consumes the seam without gating its fiber on it. diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 31a865c068..4b9a278707 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -75,7 +75,7 @@ A `session/prompt` resolves or rejects exactly once from the canonical `session/ ## Permission prompts -The bridge registers an `approval/request` waterfall listener — the ACP answerer of the [user-approval seam](../user-approval/README.md). When `ctx.approval` routes an `ask` for an agent the bridge owns, the listener resolves the owning session through the reverse map and issues `session/request_permission` with the request's `callId` as the `toolCall` reference (the editor attaches the prompt to the already-streamed call) and the one-shot options `allow_once`/`reject_once` (`allow_always` is deferred to the approval RFC's grant-storage question). Outcomes map `allow-once → allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled → cancelled`. A request for an agent the bridge does NOT own — or one without a `callId` to attach to — delegates via `next()` so another answerer or the seam's fail-closed `unavailable` default takes it. A rejected `requestPermission` RPC (client gone mid-prompt) propagates to the ApprovalService, which contains it as `unavailable`. Whether a call asks at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment; without such policy, tools keep the executor's full authority. +The bridge registers an `approval/request` waterfall listener — the ACP answerer of the [user-approval seam](../user-approval/README.md). When `ctx.approval` routes an `ask` for an agent the bridge owns, the listener resolves the owning `SessionRecord` through `ownedRecord`, which looks up `agent.session.id` in the forward session map and requires the record to own that exact agent object. It then issues `session/request_permission` with the request's `callId` as the `toolCall` reference (the editor attaches the prompt to the already-streamed call) and the one-shot options `allow_once`/`reject_once` (`allow_always` is deferred to the approval RFC's grant-storage question). Outcomes map `allow-once → allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled → cancelled`. A request for an agent the bridge does NOT own — or one without a `callId` to attach to — delegates via `next()` so another answerer or the seam's fail-closed `unavailable` default takes it. A rejected `requestPermission` RPC (client gone mid-prompt) propagates to the ApprovalService, which contains it as `unavailable`. Whether a call asks at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment; without such policy, tools keep the executor's full authority. ## Disposal & disconnect From 03f91a547183919422aeb1d699af58d678a8984d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 07:29:40 +0800 Subject: [PATCH 04/33] fix: retain local subagent completion identity --- .../cordis/tool-cordis/src/api-catalog.ts | 3 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 34 +++++++++++-------- packages/ui/jsonrpc/tests/server.spec.ts | 23 ++++++++++++- 4 files changed, 45 insertions(+), 17 deletions(-) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 5721bd97d9..ff27f51067 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -69,10 +69,11 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'async create(options: CreateAgentOptions): Promise', 'async resume(options: ResumeAgentOptions): Promise', 'register(agent: Agent): () => void', - 'enter(agent: Agent): () => void', + 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', 'list(): Agent[]', + 'roots(): Agent[]', ], }, { diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 2324227ff7..735cfead0a 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches only parent lineage because the child may be disposed before `subagent/end`. Runs from remote providers are not reported through this local-session notification pair because they create no local `session/created`/`subagent.started` edge. 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage because the child may be disposed before `subagent/end`, and the provider contract does not require lineage. Runs from remote providers are not reported because they create no local agent. 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`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 3c803a6c8c..bf21f7fc2d 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -58,6 +58,11 @@ interface SessionRecord { activePrompt: boolean } +/** Runtime-local agent identity plus optional durable fork lineage. */ +interface LocalAgentRecord { + parentSessionId?: SessionId +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * the context's `session/event`, `session/created`, `agent/created`, and @@ -71,7 +76,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly subagentParents = new Map() + private readonly localAgents = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -95,23 +100,24 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache parent lineage on creation: by the time `subagent/end` fires the - // child agent may already be disposed and gone from the registry. The child - // session id needs no cache because it is the shared agent/session id. + // Cache runtime-local identity and optional lineage on creation: by the + // time `subagent/end` fires the child agent may already be disposed and + // gone from the registry. Parent lineage is not required by the provider + // contract, so an empty record remains a load-bearing locality marker. this.disposers.push(ctx.on('agent/created', (agent) => { const parentSessionId = agent.session.header.parentSession - if (parentSessionId !== undefined) this.subagentParents.set(agent.id, parentSessionId) + this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const cachedParentSessionId = this.subagentParents.get(info.id) - this.subagentParents.delete(info.id) - // This protocol reports LOCAL child sessions, paired with the - // session/created-driven subagent.started notification above. A remote - // provider may use a real remote SessionId for its run, but that session - // does not exist in this harness and therefore has no paired start event. - if (cachedParentSessionId === undefined && agent === undefined) return - const parentSessionId = cachedParentSessionId ?? agent?.session.header.parentSession + const cachedLocalAgent = this.localAgents.get(info.id) + this.localAgents.delete(info.id) + // This protocol reports LOCAL child sessions. A lineage-bearing child + // has the session/created-driven start notification above; a parentless + // local provider still gets its terminal notification. A remote provider + // has neither a cached creation nor a live local agent and is ignored. + if (cachedLocalAgent === undefined && agent === undefined) return + const parentSessionId = cachedLocalAgent?.parentSessionId ?? agent?.session.header.parentSession this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), @@ -189,7 +195,7 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.subagentParents.clear() + this.localAgents.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index e7f591b88f..163aee4c0c 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -272,15 +272,26 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + const parentlessHandle = await ctx.agents.create({ + sessionId: SessionId('parentless-child-session'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) // The backend may dispose the child before publishing its run outcome; - // only the cached parent lineage should be needed at this point. + // cached locality must survive with or without optional parent lineage. await handle.dispose() + await parentlessHandle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }) + await settleSubagent(ctx, parentHandle.agent, { + provider: 'spawn', + id: SessionId('parentless-child-session'), + stopReason: 'error', + }) expect(transport.notifications).toContainEqual({ method: 'subagent.finished', @@ -294,6 +305,16 @@ describe('HarnessSdkServer', () => { lastAssistantMessage: [{ type: 'text', text: 'child done' }], }, }) + expect(transport.notifications).toContainEqual({ + method: 'subagent.finished', + params: { + provider: 'spawn', + agentId: 'parentless-child-session', + childSessionId: 'parentless-child-session', + status: 'error', + stopReason: 'error', + }, + }) await parentHandle.dispose() await server.shutdown() From cb80277e60c17ac5238dc7ee740ae315ee3521ff Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:11:13 +0800 Subject: [PATCH 05/33] fix: retain JSON-RPC subagent locality per run --- docs/event-producer-consumer.md | 4 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 45 +++++++++++---- packages/ui/jsonrpc/tests/server.spec.ts | 73 ++++++++++++++++++++---- 4 files changed, 98 insertions(+), 26 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 80389608cc..04aff464a9 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -8,7 +8,7 @@ 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:304`](../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:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | | `agent/error` | `emit` | [`packages/core/agent/src/types.ts:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../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:444`](../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) | @@ -34,7 +34,7 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:91`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | | `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:67`](../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:73`](../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) | +| `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), [`jsonrpc`](../packages/ui/jsonrpc) | | `system-prompt/assemble` | `waterfall` | [`packages/core/system-prompt/src/index.ts:49`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`waterfall`) | - | | `system-prompt/change` | `emit` | [`packages/core/system-prompt/src/index.ts:59`](../packages/core/system-prompt/src/index.ts) | [`system-prompt`](../packages/core/system-prompt) (`emit`) | - | | `tools/change` | `emit` | [`packages/core/tools/src/index.ts:173`](../packages/core/tools/src/index.ts) | [`tools`](../packages/core/tools) (`emit`) | - | diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 735cfead0a..95d7d7c7d7 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage because the child may be disposed before `subagent/end`, and the provider contract does not require lineage. Runs from remote providers are not reported because they create no local agent. 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and snapshots it per run, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Runs from remote providers are not reported because they create no local agent. 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`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index bf21f7fc2d..12bf82de3c 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -17,7 +17,7 @@ import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { AgentHandle } from '@deepseek-ai/dsh-agent' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' -import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' +import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -65,10 +65,11 @@ interface LocalAgentRecord { /** * The SDK server over a booted harness context. Constructing it subscribes to - * the context's `session/event`, `session/created`, `agent/created`, and - * `subagent/end` events and forwards them to the host as notifications; the - * subscriptions live until {@link shutdown}. One instance serves one transport - * peer for the process lifetime — there is no re-`initialize`. + * session, agent, and subagent lifecycle events, forwarding durable session + * events and SDK-facing completion notifications while retaining local-run + * identity across child disposal. The subscriptions live until + * {@link shutdown}. One instance serves one transport peer for the process + * lifetime — there is no re-`initialize`. */ export class HarnessSdkServer { private cwd = process.cwd() @@ -77,6 +78,7 @@ export class HarnessSdkServer { private readonly sessions = new Map() private readonly sessionCreations = new Map>() private readonly localAgents = new Map() + private readonly localRuns = new Map() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -100,18 +102,38 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache runtime-local identity and optional lineage on creation: by the - // time `subagent/end` fires the child agent may already be disposed and - // gone from the registry. Parent lineage is not required by the provider - // contract, so an empty record remains a load-bearing locality marker. + // Cache runtime-local identity and optional lineage for each agent lifetime. + // Parent lineage is not required by the provider contract, so an empty + // record remains a load-bearing locality marker. this.disposers.push(ctx.on('agent/created', (agent) => { const parentSessionId = agent.session.header.parentSession this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) })) - this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { + this.disposers.push(ctx.on('agent/disposed', (agent) => { + this.localAgents.delete(agent.id) + })) + // Snapshot locality per run. A provider may settle one run, continue the + // same live child in another run, and dispose that child before the later + // result settles. Consuming an agent-lifetime marker at the first end would + // lose the later notification; this queue pairs each start with one end. + this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { const agent = this.ctx.agents.get(info.id) const cachedLocalAgent = this.localAgents.get(info.id) - this.localAgents.delete(info.id) + const localAgent = cachedLocalAgent ?? (agent === undefined + ? undefined + : agent.session.header.parentSession === undefined + ? {} + : { parentSessionId: agent.session.header.parentSession }) + if (localAgent === undefined) return + const runs = this.localRuns.get(info.id) ?? [] + runs.push(localAgent) + this.localRuns.set(info.id, runs) + })) + this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { + const agent = this.ctx.agents.get(info.id) + const runs = this.localRuns.get(info.id) + const cachedLocalAgent = runs?.shift() + if (runs?.length === 0) this.localRuns.delete(info.id) // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider @@ -196,6 +218,7 @@ export class HarnessSdkServer { const records = [...this.sessions.values()] this.sessions.clear() this.localAgents.clear() + this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 163aee4c0c..d56f3000f6 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -11,7 +11,7 @@ import { SessionId } from '@deepseek-ai/dsh-session' import * as agentCore from '@deepseek-ai/dsh-agent-core' import SessionPersistenceJsonl from '@deepseek-ai/dsh-session-persistence-jsonl' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' -import SubagentService, { type SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' +import SubagentService, { type SubagentResult, type SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import { HarnessSdkServer, type JsonRpcTransportPeer } from '../src/index.ts' class FakeTransport implements JsonRpcTransportPeer { @@ -67,7 +67,13 @@ async function makeHarness(storageDir: string) { } /** Drive the owning service so test lifecycle events carry the real parent scope. */ -async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndInfo): Promise { +async function settleSubagent( + ctx: Context, + parent: Agent, + info: SubagentRunEndInfo, + beforeSettle?: () => Promise, +): Promise { + const result = Promise.withResolvers() const disposeProvider = ctx.subagents.registerProvider({ name: info.provider, capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, @@ -75,9 +81,7 @@ async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndI async start() { return { id: info.id, - result: info.lastAssistantMessage === undefined - ? Promise.reject(new Error('synthetic infrastructure failure')) - : Promise.resolve({ output: info.lastAssistantMessage, stopReason: info.stopReason }), + result: result.promise, dispose: () => Promise.resolve(), } }, @@ -88,6 +92,12 @@ async function settleSubagent(ctx: Context, parent: Agent, info: SubagentRunEndI prompt: [], signal: new AbortController().signal, }) + await beforeSettle?.() + if (info.lastAssistantMessage === undefined) { + result.reject(new Error('synthetic infrastructure failure')) + } else { + result.resolve({ output: info.lastAssistantMessage, stopReason: info.stopReason }) + } await run.result.then(() => undefined, () => undefined) await run.dispose() } finally { @@ -277,21 +287,17 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - // The backend may dispose the child before publishing its run outcome; - // cached locality must survive with or without optional parent lineage. - await handle.dispose() - await parentlessHandle.dispose() await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], - }) + }, () => handle.dispose()) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('parentless-child-session'), stopReason: 'error', - }) + }, () => parentlessHandle.dispose()) expect(transport.notifications).toContainEqual({ method: 'subagent.finished', @@ -324,6 +330,49 @@ describe('HarnessSdkServer', () => { } }) + it('retains locality across continuation runs on one live child', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-continuation-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parentHandle = await ctx.agents.create({ + sessionId: SessionId('continuation-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const childHandle = await ctx.agents.create({ + sessionId: SessionId('continuation-child'), + meta: { cwd: storageDir, parentSession: SessionId('continuation-parent') }, + agentOptions: { model: 'deepseek' }, + }) + + await settleSubagent(ctx, parentHandle.agent, { + provider: 'continuation', + id: SessionId('continuation-child'), + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'first' }], + }) + await settleSubagent(ctx, parentHandle.agent, { + provider: 'continuation', + id: SessionId('continuation-child'), + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'second' }], + }, () => childHandle.dispose()) + + expect(transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'continuation-child', + )).toHaveLength(2) + + await parentHandle.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) @@ -585,6 +634,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(4) + expect(on).toHaveBeenCalledTimes(6) }) }) From d898d1faf0739e4e4f2edd5b6f7a156f54ed2d25 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:25:52 +0800 Subject: [PATCH 06/33] fix: avoid FIFO subagent lineage attribution --- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 49 ++++++--- packages/ui/jsonrpc/tests/server.spec.ts | 123 ++++++++++++++++++++++- 3 files changed, 158 insertions(+), 16 deletions(-) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 95d7d7c7d7..5ff7eb7f8e 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and snapshots it per run, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Runs from remote providers are not reported because they create no local agent. 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and counts pending runs per provider/id, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Settlement order is not assumed: if concurrent ID reuse makes parent lineage ambiguous, the completion remains local but omits the optional `parentSessionId` rather than attributing the wrong parent. Runs from remote providers are not reported because they create no local agent. 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`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 12bf82de3c..ce0ac9c75a 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -63,6 +63,13 @@ interface LocalAgentRecord { parentSessionId?: SessionId } +/** Pending local runs that share one provider/id correlation key. */ +interface PendingLocalRuns { + count: number + parentSessionId?: SessionId + parentAmbiguous: boolean +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * session, agent, and subagent lifecycle events, forwarding durable session @@ -78,7 +85,7 @@ export class HarnessSdkServer { private readonly sessions = new Map() private readonly sessionCreations = new Map>() private readonly localAgents = new Map() - private readonly localRuns = new Map() + private readonly localRuns = new Map>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -112,10 +119,12 @@ export class HarnessSdkServer { this.disposers.push(ctx.on('agent/disposed', (agent) => { this.localAgents.delete(agent.id) })) - // Snapshot locality per run. A provider may settle one run, continue the - // same live child in another run, and dispose that child before the later - // result settles. Consuming an agent-lifetime marker at the first end would - // lose the later notification; this queue pairs each start with one end. + // Snapshot locality per provider/id run key. A provider may settle one run, + // continue the same live child in another run, and dispose that child before + // the later result settles. Counts preserve every completion without + // assuming settlement order. If id reuse produces disagreeing lineage, the + // optional parent is omitted until that pending group drains rather than + // attributed to the wrong completion. this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { const agent = this.ctx.agents.get(info.id) const cachedLocalAgent = this.localAgents.get(info.id) @@ -125,21 +134,35 @@ export class HarnessSdkServer { ? {} : { parentSessionId: agent.session.header.parentSession }) if (localAgent === undefined) return - const runs = this.localRuns.get(info.id) ?? [] - runs.push(localAgent) - this.localRuns.set(info.id, runs) + const providerRuns = this.localRuns.get(info.provider) ?? new Map() + const pending = providerRuns.get(info.id) + if (pending === undefined) { + providerRuns.set(info.id, localAgent.parentSessionId === undefined + ? { count: 1, parentAmbiguous: false } + : { count: 1, parentSessionId: localAgent.parentSessionId, parentAmbiguous: false }) + } else { + pending.count += 1 + if (pending.parentSessionId !== localAgent.parentSessionId) pending.parentAmbiguous = true + } + this.localRuns.set(info.provider, providerRuns) })) this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { const agent = this.ctx.agents.get(info.id) - const runs = this.localRuns.get(info.id) - const cachedLocalAgent = runs?.shift() - if (runs?.length === 0) this.localRuns.delete(info.id) + const providerRuns = this.localRuns.get(info.provider) + const pending = providerRuns?.get(info.id) + if (pending !== undefined) { + pending.count -= 1 + if (pending.count === 0) providerRuns?.delete(info.id) + if (providerRuns?.size === 0) this.localRuns.delete(info.provider) + } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider // has neither a cached creation nor a live local agent and is ignored. - if (cachedLocalAgent === undefined && agent === undefined) return - const parentSessionId = cachedLocalAgent?.parentSessionId ?? agent?.session.header.parentSession + if (pending === undefined && agent === undefined) return + const parentSessionId = pending === undefined + ? agent?.session.header.parentSession + : pending.parentAmbiguous ? undefined : pending.parentSessionId this.transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index d56f3000f6..48b8c4b1be 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -373,6 +373,100 @@ describe('HarnessSdkServer', () => { } }) + it('omits ambiguous lineage when one local id is reused and runs settle out of order', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-reuse-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const oldParent = await ctx.agents.create({ + sessionId: SessionId('old-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const oldChild = await ctx.agents.create({ + sessionId: SessionId('reused-child'), + meta: { cwd: storageDir, parentSession: SessionId('old-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const first = Promise.withResolvers() + const sameLifetime = Promise.withResolvers() + const replacement = Promise.withResolvers() + const results = [first.promise, sameLifetime.promise, replacement.promise] + let starts = 0 + const disposeProvider = ctx.subagents.registerProvider({ + name: 'reused', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + const result = results[starts] + starts += 1 + if (result === undefined) throw new Error('unexpected fourth reused-id run') + return Promise.resolve({ id: SessionId('reused-child'), result, dispose: () => Promise.resolve() }) + }, + }) + + const firstRun = await ctx.subagents.start('reused', { + parent: oldParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + const sameLifetimeRun = await ctx.subagents.start('reused', { + parent: oldParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + sameLifetime.resolve({ output: [{ type: 'text', text: 'same lifetime' }], stopReason: 'completed' }) + await sameLifetimeRun.result + await oldChild.dispose() + const newParent = await ctx.agents.create({ + sessionId: SessionId('new-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const newChild = await ctx.agents.create({ + sessionId: SessionId('reused-child'), + meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const secondRun = await ctx.subagents.start('reused', { + parent: newParent.agent, + prompt: [], + signal: new AbortController().signal, + }) + + replacement.resolve({ output: [{ type: 'text', text: 'new lifetime' }], stopReason: 'completed' }) + await secondRun.result + first.resolve({ output: [{ type: 'text', text: 'old lifetime' }], stopReason: 'completed' }) + await firstRun.result + await Promise.resolve() + + const finished = transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'reused-child', + ) + expect(finished.map(notification => notification.params?.lastAssistantMessage)).toEqual([ + [{ type: 'text', text: 'same lifetime' }], + [{ type: 'text', text: 'new lifetime' }], + [{ type: 'text', text: 'old lifetime' }], + ]) + expect(finished[0]?.params?.parentSessionId).toBe('old-parent') + expect(finished.slice(1).every(notification => !Object.hasOwn(notification.params ?? {}, 'parentSessionId'))).toBe(true) + + await firstRun.dispose() + await sameLifetimeRun.dispose() + await secondRun.dispose() + disposeProvider() + await newChild.dispose() + await oldParent.dispose() + await newParent.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('falls back to live lineage and ignores runs without a local child session', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) @@ -395,13 +489,38 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) + const missedStartResult = Promise.withResolvers() + const disposeMissedStartProvider = ctx.subagents.registerProvider({ + name: 'fork', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: true, + start: () => Promise.resolve({ + id: SessionId('fallback-child-session'), + result: missedStartResult.promise, + dispose: () => Promise.resolve(), + }), + }) + // Start before the server subscribes, so the terminal fallback must use + // the still-live registry entry rather than a cached start record. + const missedStartRun = await ctx.subagents.start('fork', { + parent: parentHandle.agent, + prompt: [], + signal: new AbortController().signal, + }) const transport = new FakeTransport() const server = new HarnessSdkServer(ctx, transport) + missedStartResult.resolve({ output: [], stopReason: 'max-tokens' }) + await missedStartRun.result + await Promise.resolve() + await missedStartRun.dispose() + disposeMissedStartProvider() + // The server also missed this agent's creation, but observes the start; + // recover its lineage from the still-live registry entry. await settleSubagent(ctx, parentHandle.agent, { - provider: 'fork', + provider: 'fork-live-fallback', id: SessionId('fallback-child-session'), - stopReason: 'max-tokens', + stopReason: 'completed', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { From 45e3997efcecf48c57e171a7d77401b1c914ea32 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:41:31 +0800 Subject: [PATCH 07/33] fix: correlate subagent completion by parent scope --- docs/event-producer-consumer.md | 4 +- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 101 ++++++++--------------- packages/ui/jsonrpc/tests/server.spec.ts | 13 ++- 4 files changed, 47 insertions(+), 73 deletions(-) diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 04aff464a9..bc1c0d38d0 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -7,8 +7,8 @@ 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:304`](../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:319`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`jsonrpc`](../packages/ui/jsonrpc), [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/created` | `emit` | [`packages/core/agent/src/types.ts:304`](../packages/core/agent/src/types.ts) | [`agent`](../packages/core/agent) (`events.dispatch`) | [`stdio-agent`](../packages/ui/stdio-agent) | +| `agent/disposed` | `emit` | [`packages/core/agent/src/types.ts:319`](../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:593`](../packages/core/agent/src/types.ts) | [`agent-loop`](../packages/core/agent-loop) (`emit`) | - | | `agent/pre-step` | `serial` | [`packages/core/agent/src/types.ts:426`](../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:444`](../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) | diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 5ff7eb7f8e..ffbd7a1288 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server caches runtime-local identity plus optional parent lineage for the agent lifetime and counts pending runs per provider/id, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. Settlement order is not assumed: if concurrent ID reuse makes parent lineage ambiguous, the completion remains local but omits the optional `parentSessionId` rather than attributing the wrong parent. Runs from remote providers are not reported because they create no local agent. 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server counts local starts by provider/id and the exact delegating-parent carrier, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported because they create no local agent. 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`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index ce0ac9c75a..352563f7f2 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -15,8 +15,10 @@ import type { Context } from 'cordis' import { resolve } from 'node:path' import type { ContentBlock } from '@deepseek-ai/dsh-llm' -import type { AgentHandle } from '@deepseek-ai/dsh-agent' +import type { Agent, AgentHandle } from '@deepseek-ai/dsh-agent' +import { carrierKeyOf, type Scoped } from '@deepseek-ai/dsh-scope' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' +import type SubagentService from '@deepseek-ai/dsh-subagent' import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -58,21 +60,14 @@ interface SessionRecord { activePrompt: boolean } -/** Runtime-local agent identity plus optional durable fork lineage. */ -interface LocalAgentRecord { - parentSessionId?: SessionId -} - -/** Pending local runs that share one provider/id correlation key. */ -interface PendingLocalRuns { - count: number - parentSessionId?: SessionId - parentAmbiguous: boolean +/** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ +function subagentParentOf(carrier: Scoped): Agent { + return carrierKeyOf(carrier) as Agent } /** * The SDK server over a booted harness context. Constructing it subscribes to - * session, agent, and subagent lifecycle events, forwarding durable session + * session and subagent lifecycle events, forwarding durable session * events and SDK-facing completion notifications while retaining local-run * identity across child disposal. The subscriptions live until * {@link shutdown}. One instance serves one transport peer for the process @@ -84,8 +79,7 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly localAgents = new Map() - private readonly localRuns = new Map>() + private readonly localRuns = new Map>>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -109,64 +103,40 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // Cache runtime-local identity and optional lineage for each agent lifetime. - // Parent lineage is not required by the provider contract, so an empty - // record remains a load-bearing locality marker. - this.disposers.push(ctx.on('agent/created', (agent) => { - const parentSessionId = agent.session.header.parentSession - this.localAgents.set(agent.id, parentSessionId === undefined ? {} : { parentSessionId }) + // In-process providers publish the child before start. Count those starts by + // the exact delegating-parent carrier so later completions remain local after + // child disposal and reused ids need no settlement-order assumption. + const localRuns = this.localRuns + this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { + if (ctx.agents.get(info.id) === undefined) return + const parent = subagentParentOf(this) + const providerRuns = localRuns.get(info.provider) ?? new Map>() + const parentRuns = providerRuns.get(info.id) ?? new Map() + parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) + providerRuns.set(info.id, parentRuns) + localRuns.set(info.provider, providerRuns) })) - this.disposers.push(ctx.on('agent/disposed', (agent) => { - this.localAgents.delete(agent.id) - })) - // Snapshot locality per provider/id run key. A provider may settle one run, - // continue the same live child in another run, and dispose that child before - // the later result settles. Counts preserve every completion without - // assuming settlement order. If id reuse produces disagreeing lineage, the - // optional parent is omitted until that pending group drains rather than - // attributed to the wrong completion. - this.disposers.push(ctx.on('subagent/start', (info: SubagentRunInfo) => { - const agent = this.ctx.agents.get(info.id) - const cachedLocalAgent = this.localAgents.get(info.id) - const localAgent = cachedLocalAgent ?? (agent === undefined - ? undefined - : agent.session.header.parentSession === undefined - ? {} - : { parentSessionId: agent.session.header.parentSession }) - if (localAgent === undefined) return - const providerRuns = this.localRuns.get(info.provider) ?? new Map() - const pending = providerRuns.get(info.id) - if (pending === undefined) { - providerRuns.set(info.id, localAgent.parentSessionId === undefined - ? { count: 1, parentAmbiguous: false } - : { count: 1, parentSessionId: localAgent.parentSessionId, parentAmbiguous: false }) - } else { - pending.count += 1 - if (pending.parentSessionId !== localAgent.parentSessionId) pending.parentAmbiguous = true - } - this.localRuns.set(info.provider, providerRuns) - })) - this.disposers.push(ctx.on('subagent/end', (info: SubagentRunEndInfo) => { - const agent = this.ctx.agents.get(info.id) - const providerRuns = this.localRuns.get(info.provider) - const pending = providerRuns?.get(info.id) - if (pending !== undefined) { - pending.count -= 1 - if (pending.count === 0) providerRuns?.delete(info.id) - if (providerRuns?.size === 0) this.localRuns.delete(info.provider) + this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { + const agent = ctx.agents.get(info.id) + const parent = subagentParentOf(this) + const providerRuns = localRuns.get(info.provider) + const parentRuns = providerRuns?.get(info.id) + const pendingCount = parentRuns?.get(parent) + if (pendingCount !== undefined) { + if (pendingCount === 1) parentRuns?.delete(parent) + else parentRuns?.set(parent, pendingCount - 1) + if (parentRuns?.size === 0) providerRuns?.delete(info.id) + if (providerRuns?.size === 0) localRuns.delete(info.provider) } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above; a parentless // local provider still gets its terminal notification. A remote provider - // has neither a cached creation nor a live local agent and is ignored. - if (pending === undefined && agent === undefined) return - const parentSessionId = pending === undefined - ? agent?.session.header.parentSession - : pending.parentAmbiguous ? undefined : pending.parentSessionId - this.transport.notify('subagent.finished', { + // has neither a pending local start nor a live local agent and is ignored. + if (pendingCount === undefined && agent === undefined) return + transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), - ...(parentSessionId === undefined ? {} : { parentSessionId: String(parentSessionId) }), + parentSessionId: String(parent.session.id), childSessionId: String(info.id), status: info.stopReason === 'completed' ? 'ok' : 'error', stopReason: info.stopReason, @@ -240,7 +210,6 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.localAgents.clear() this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 48b8c4b1be..427a190c36 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -316,6 +316,7 @@ describe('HarnessSdkServer', () => { params: { provider: 'spawn', agentId: 'parentless-child-session', + parentSessionId: 'main', childSessionId: 'parentless-child-session', status: 'error', stopReason: 'error', @@ -373,7 +374,7 @@ describe('HarnessSdkServer', () => { } }) - it('omits ambiguous lineage when one local id is reused and runs settle out of order', async () => { + it('correlates reused local ids by parent scope when runs settle out of order', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-reuse-')) const ctx = await makeHarness(storageDir) try { @@ -450,8 +451,11 @@ describe('HarnessSdkServer', () => { [{ type: 'text', text: 'new lifetime' }], [{ type: 'text', text: 'old lifetime' }], ]) - expect(finished[0]?.params?.parentSessionId).toBe('old-parent') - expect(finished.slice(1).every(notification => !Object.hasOwn(notification.params ?? {}, 'parentSessionId'))).toBe(true) + expect(finished.map(notification => notification.params?.parentSessionId)).toEqual([ + 'old-parent', + 'new-parent', + 'old-parent', + ]) await firstRun.dispose() await sameLifetimeRun.dispose() @@ -551,6 +555,7 @@ describe('HarnessSdkServer', () => { params: { provider: 'fork', agentId: 'failed-child-session', + parentSessionId: 'fallback-parent', childSessionId: 'failed-child-session', status: 'error', stopReason: 'error', @@ -753,6 +758,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(6) + expect(on).toHaveBeenCalledTimes(4) }) }) From c6cb9f4210d9303c197ac985fca7a4dc3b11cb88 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:55:38 +0800 Subject: [PATCH 08/33] fix: share scope carrier across built JSON-RPC --- AGENTS.md | 2 +- docs/testing.md | 2 +- packages/ui/jsonrpc/package.json | 2 + .../jsonrpc/tests/built-scope-carrier.e2e.ts | 121 ++++++++++++++++++ pnpm-lock.yaml | 3 + scripts/run-gates.ts | 1 + 6 files changed, 129 insertions(+), 2 deletions(-) create mode 100644 packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts diff --git a/AGENTS.md b/AGENTS.md index 4dfbedb97b..1494d3fcf8 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -76,7 +76,7 @@ printf '%s\n' "$out" | grep -q '\[tool call\] echo({"text":"ci smoke"})' printf '%s\n' "$out" | grep -q '\[tool result\] ECHO: CI SMOKE' test -n "$(find .sessions -path '.sessions/cwd-*/main-session-*.jsonl' -type f -print -quit)" rm -rf .sessions -pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts +pnpm exec vitest run --config vitest.e2e.config.ts packages/ui/stdio-agent/tests/built-bin.e2e.ts packages/ui/acp-agent/tests/built-bin.e2e.ts packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts packages/workflow/workflow-workerthread/tests/built-worker.e2e.ts packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts ``` `test:coverage`, not `test`, is the gating run ([why](docs/testing.md)); a sign-off counts only for commands actually run. diff --git a/docs/testing.md b/docs/testing.md index 23cca651fe..a1a841296a 100644 --- a/docs/testing.md +++ b/docs/testing.md @@ -25,7 +25,7 @@ An e2e assertion re-runs the command or re-reads the file externally; a keyword - A plugin shipped via `cordis.yml` needs at least one test through the REAL Loader path: hand-built `ctx.plugin({...})` mounts bypass `unwrapExports` and cannot catch a broken export shape ([postmortem 0001](postmortem/0001-acp-default-export-drops-inject.md); export-shape rules in [packages/AGENTS.md](../packages/AGENTS.md)). - A guard only guards if the regression actually fails it. For a plugin without `inject` (bundle/composition plugins), a Loader smoke stays green under a broken export shape — add an explicit `expect('default' in mod).toBe(false)` plus an `unwrapExports` round-trip assertion, and prove it: introduce the regression, watch red, revert. -- "Real entry path" means the published artifact: the package `bin` points at built `lib/bin.js` under plain `node`, which tsx masks (settle races, module resolution, a swallowed load failure exiting 0). The same applies to any non-index runtime entry the built package resolves at run time (the worker-thread runtime's sibling `lib/worker.cjs`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. +- "Real entry path" means the published artifact: a package `bin` runs built `lib/bin.js` under plain `node`, exposing failures tsx masks (settle races, module resolution, swallowed load failures). The same applies to non-index runtime entries (the worker-thread sibling `lib/worker.cjs`) and singleton modules shared across bundles (`packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts`). Keep the built-artifact smokes green (`packages/ui/*/tests/built-bin.e2e.ts`, `packages/code-runtime/code-runtime-worker/tests/built-lib.e2e.ts`), and assert a genuinely-missing config exits non-zero. - An e2e that spawns an example from a temp cwd sets `TSX_TSCONFIG_PATH` to the repo-root tsconfig, or it silently falls back to stale built `lib/` ([examples/AGENTS.md](../examples/AGENTS.md)). ## When a snapshot test is required diff --git a/packages/ui/jsonrpc/package.json b/packages/ui/jsonrpc/package.json index be19ab7217..bf4fe39118 100644 --- a/packages/ui/jsonrpc/package.json +++ b/packages/ui/jsonrpc/package.json @@ -28,6 +28,7 @@ "@deepseek-ai/dsh-agent": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-llm-deepseek": "^0.0.1", + "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", "@deepseek-ai/dsh-subagent": "^0.0.1", "cordis": "^4.0.0-rc.6" @@ -38,6 +39,7 @@ "@deepseek-ai/dsh-agent-core": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-llm-deepseek": "workspace:^", + "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", "@deepseek-ai/dsh-session-persistence-jsonl": "workspace:^", "@deepseek-ai/dsh-subagent": "workspace:^", diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts new file mode 100644 index 0000000000..159600e49c --- /dev/null +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -0,0 +1,121 @@ +/** + * Built-artifact guard for the scope carrier shared by `dsh-subagent` and + * `dsh-jsonrpc`. The carrier registry is module-local, so both bundles must + * externalize `dsh-scope`; source-mode tests cannot expose an accidentally + * inlined second registry. This test runs the real `lib/index.js` bundles in a + * plain Node subprocess, disposes the child before settlement, and requires the + * SDK completion notification to retain the delegating parent. + */ + +import { execFile } from 'node:child_process' +import { existsSync } from 'node:fs' +import { fileURLToPath } from 'node:url' +import { promisify } from 'node:util' +import { describe, expect, it } from 'vitest' + +const repoRoot = fileURLToPath(new URL('../../../../', import.meta.url)) +const jsonrpcBundle = fileURLToPath(new URL('../lib/index.js', import.meta.url)) +const execFileAsync = promisify(execFile) + +const builtRuntimeProbe = String.raw` +import { mkdtemp, rm } from "node:fs/promises"; +import { tmpdir } from "node:os"; +import { join, resolve } from "node:path"; +import { pathToFileURL } from "node:url"; + +const load = (path) => import(pathToFileURL(resolve(path)).href); +const [ + { Context }, + agentCore, + { default: SubagentService }, + { default: SessionPersistenceJsonl }, + { HarnessSdkServer }, + { SessionId }, +] = await Promise.all([ + load("vendor/cordis/lib/index.js"), + load("packages/core/agent-core/lib/index.js"), + load("packages/subagent/subagent/lib/index.js"), + load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), + load("packages/ui/jsonrpc/lib/index.js"), + load("packages/core/session/lib/index.js"), +]); + +const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); +const ctx = new Context(); +try { + await ctx.plugin(agentCore); + await ctx.plugin(SubagentService); + await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); + await new Promise((ready) => setTimeout(ready, 50)); + + const notifications = []; + const server = new HarnessSdkServer(ctx, { + request() { return Promise.reject(new Error("unexpected host request")); }, + notify(method, params) { notifications.push({ method, params }); }, + }); + const parent = await ctx.agents.create({ + sessionId: SessionId("built-parent"), + meta: { cwd: storageRoot }, + agentOptions: { model: "test" }, + }); + const child = await ctx.agents.create({ + sessionId: SessionId("built-child"), + meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, + agentOptions: { model: "test" }, + }); + const result = Promise.withResolvers(); + const unregister = ctx.subagents.registerProvider({ + name: "built-local", + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start() { + return Promise.resolve({ + id: child.agent.id, + result: result.promise, + dispose() { return Promise.resolve(); }, + }); + }, + }); + const run = await ctx.subagents.start("built-local", { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }); + await child.dispose(); + result.resolve({ output: [], stopReason: "completed" }); + await run.result; + await Promise.resolve(); + + console.log(JSON.stringify(notifications.filter(({ method }) => method === "subagent.finished"))); + await run.dispose(); + unregister(); + await parent.dispose(); + await server.shutdown(); +} finally { + await ctx.fiber.dispose(); + await rm(storageRoot, { recursive: true, force: true }); +} +` + +describe.skipIf(!existsSync(jsonrpcBundle))('dsh-jsonrpc BUILT scope carrier', () => { + it('preserves parent-scoped completion after child disposal', async () => { + const { stdout, stderr } = await execFileAsync(process.execPath, ['--input-type=module', '-e', builtRuntimeProbe], { + cwd: repoRoot, + timeout: 15_000, + }) + + expect(stderr).not.toContain('listener threw') + expect(JSON.parse(stdout) as unknown).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'built-local', + agentId: 'built-child', + parentSessionId: 'built-parent', + childSessionId: 'built-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [], + }, + }]) + }) +}) diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index 6214564eae..dec8c3024f 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1288,6 +1288,9 @@ importers: '@deepseek-ai/dsh-llm-deepseek': specifier: workspace:^ version: link:../../llm/llm-deepseek + '@deepseek-ai/dsh-scope': + specifier: workspace:^ + version: link:../../core/scope '@deepseek-ai/dsh-session': specifier: workspace:^ version: link:../../core/session diff --git a/scripts/run-gates.ts b/scripts/run-gates.ts index 131501abb0..e1c41149ca 100644 --- a/scripts/run-gates.ts +++ b/scripts/run-gates.ts @@ -332,6 +332,7 @@ function builtBinSmokeGate(): Gate { 'vitest.e2e.config.ts', 'packages/ui/stdio-agent/tests/built-bin.e2e.ts', 'packages/ui/acp-agent/tests/built-bin.e2e.ts', + 'packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts', // The worker-entry packages' built bundles: the only automated proof // that lib/index.js resolves its sibling lib/worker.cjs under plain node // (the e2e lane runs unbuilt, so these files self-skip there). From 151d6387e03b9f41b553e7f079588f76d7317516 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:57:46 +0800 Subject: [PATCH 09/33] docs: refresh module dependency graph --- docs/module-graph.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index 8ac71b11cc..864f39359f 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -293,6 +293,7 @@ flowchart TD pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek + pkg_jsonrpc --> pkg_scope pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent pkg_workflow_workerthread --> pkg_agent @@ -389,7 +390,7 @@ flowchart TD | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | -| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | | [`subagent-fork`](../packages/subagent/subagent-fork) | `subagent` | [`agent`](../packages/core/agent), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | | [`subagent-spawn`](../packages/subagent/subagent-spawn) | `subagent` | [`subagent`](../packages/subagent/subagent), [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | From 82c0d1fb7cc291196bc3fd5733dfec867d84dac7 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 08:59:33 +0800 Subject: [PATCH 10/33] test: register JSON-RPC artifact smoke --- knip.json | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/knip.json b/knip.json index 825980f205..fe2366e3fa 100644 --- a/knip.json +++ b/knip.json @@ -77,13 +77,17 @@ "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, - "packages/ui/stdio-agent": { + "packages/ui/jsonrpc": { "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] }, "packages/ui/jsonrpc-agent": { "project": ["src/**/*.ts"] }, + "packages/ui/stdio-agent": { + "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], + "project": ["src/**/*.ts", "tests/**/*.ts"] + }, "packages/subagent/subagent-spawn": { "entry": ["tests/**/*.spec.ts", "tests/**/*.e2e.ts"], "project": ["src/**/*.ts", "tests/**/*.ts"] From 1bb9995128f75474eeec9933e2bab6fc69a8b60e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:28:41 +0800 Subject: [PATCH 11/33] docs: state subagent carrier invariant --- packages/ui/jsonrpc/src/server.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 352563f7f2..fe605a8536 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -62,6 +62,7 @@ interface SessionRecord { /** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ function subagentParentOf(carrier: Scoped): Agent { + // SubagentService emits this lifecycle pair only through scopeTarget(this, parent). return carrierKeyOf(carrier) as Agent } From 2333ab19e3b03bc84cf050b16e897b830b2dfdf2 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 09:46:05 +0800 Subject: [PATCH 12/33] fix: verify JSON-RPC child ownership --- docs/cordis-catalog/services.md | 1 + packages/core/agent/README.md | 1 + packages/core/agent/src/index.ts | 12 ++++++ packages/core/agent/tests/agent.spec.ts | 4 ++ packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 11 +++-- packages/ui/jsonrpc/tests/server.spec.ts | 51 ++++++++++++++++++++---- 7 files changed, 68 insertions(+), 14 deletions(-) diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 1366fcf6f6..6a40f88a23 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -33,6 +33,7 @@ register(agent: Agent): () => void enter(agent: Agent, owner: Agent | undefined): () => void announce(agent: Agent): void get(id: SessionId): Agent | undefined +isOwnedBy(id: SessionId, owner: Agent): boolean list(): Agent[] roots(): Agent[] ``` diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index a45603f191..941f46baf0 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -13,6 +13,7 @@ The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh- - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. - Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` +- `ctx.agents.isOwnedBy(id: SessionId, owner: Agent): boolean` — whether the exact live entry was created through that parent agent's scoped context; runtime ownership is independent of durable session lineage. - `ctx.agents.list(): Agent[]` - `ctx.agents.roots(): Agent[]` — live agents created without an owning agent context; a resumed lineage-bearing session can still be a runtime root. diff --git a/packages/core/agent/src/index.ts b/packages/core/agent/src/index.ts index abafa38e45..8a9ed68ab6 100644 --- a/packages/core/agent/src/index.ts +++ b/packages/core/agent/src/index.ts @@ -440,6 +440,18 @@ export class AgentRegistry extends Service { return this.store.get(id)?.agent } + /** + * Test whether a live agent was created through one exact parent agent's + * scoped context. Runtime ownership is independent of durable session + * lineage and remains unambiguous when unrelated providers reuse an id. + * @param id - the candidate child agent's shared agent/session id. + * @param owner - the expected runtime creator agent. + * @returns true only while the exact child entry is live under that owner. + */ + isOwnedBy(id: SessionId, owner: Agent): boolean { + return this.store.get(id)?.owner === owner + } + /** * All live agents, in registration order. * @returns a fresh array; mutating it does not affect the registry. diff --git a/packages/core/agent/tests/agent.spec.ts b/packages/core/agent/tests/agent.spec.ts index d2866cacb3..5d79d1a91f 100644 --- a/packages/core/agent/tests/agent.spec.ts +++ b/packages/core/agent/tests/agent.spec.ts @@ -72,8 +72,12 @@ describe('AgentRegistry', () => { expect(ctx.agents.list()).toEqual([root, child]) expect(ctx.agents.roots()).toEqual([root]) + expect(ctx.agents.isOwnedBy(child.id, root)).toBe(true) + expect(ctx.agents.isOwnedBy(root.id, root)).toBe(false) + expect(ctx.agents.isOwnedBy(SessionId('missing'), root)).toBe(false) detachChild() + expect(ctx.agents.isOwnedBy(child.id, root)).toBe(false) detachRoot() }) diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index ffbd7a1288..df612ac263 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server counts local starts by provider/id and the exact delegating-parent carrier, because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported because they create no local agent. 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` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server verifies that the live child is owned by the exact delegating parent, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$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`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index fe605a8536..d78f24b5ab 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -109,8 +109,8 @@ export class HarnessSdkServer { // child disposal and reused ids need no settlement-order assumption. const localRuns = this.localRuns this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { - if (ctx.agents.get(info.id) === undefined) return const parent = subagentParentOf(this) + if (!ctx.agents.isOwnedBy(info.id, parent)) return const providerRuns = localRuns.get(info.provider) ?? new Map>() const parentRuns = providerRuns.get(info.id) ?? new Map() parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) @@ -118,7 +118,6 @@ export class HarnessSdkServer { localRuns.set(info.provider, providerRuns) })) this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { - const agent = ctx.agents.get(info.id) const parent = subagentParentOf(this) const providerRuns = localRuns.get(info.provider) const parentRuns = providerRuns?.get(info.id) @@ -130,10 +129,10 @@ export class HarnessSdkServer { if (providerRuns?.size === 0) localRuns.delete(info.provider) } // This protocol reports LOCAL child sessions. A lineage-bearing child - // has the session/created-driven start notification above; a parentless - // local provider still gets its terminal notification. A remote provider - // has neither a pending local start nor a live local agent and is ignored. - if (pendingCount === undefined && agent === undefined) return + // has the session/created-driven start notification above. A remote run + // has neither a cached owned start nor a live child owned by this exact + // parent; an unrelated local agent with the same id never makes it local. + if (pendingCount === undefined && !ctx.agents.isOwnedBy(info.id, parent)) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 427a190c36..c97bd1a6e1 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -277,12 +277,12 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const handle = await ctx.agents.create({ + const handle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) - const parentlessHandle = await ctx.agents.create({ + const parentlessHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('parentless-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, @@ -331,6 +331,43 @@ describe('HarnessSdkServer', () => { } }) + it('ignores a remote run id that collides with an unrelated local agent', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-remote-collision-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parentHandle = await ctx.agents.create({ + sessionId: SessionId('collision-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const unrelatedHandle = await ctx.agents.create({ + sessionId: SessionId('remote-run-id'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + + await settleSubagent(ctx, parentHandle.agent, { + provider: 'remote', + id: SessionId('remote-run-id'), + stopReason: 'completed', + lastAssistantMessage: [], + }, () => unrelatedHandle.dispose()) + + expect(transport.notifications.some(notification => + notification.method === 'subagent.finished' + && notification.params?.agentId === 'remote-run-id', + )).toBe(false) + + await parentHandle.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + it('retains locality across continuation runs on one live child', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-continuation-')) const ctx = await makeHarness(storageDir) @@ -342,7 +379,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const childHandle = await ctx.agents.create({ + const childHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('continuation-child'), meta: { cwd: storageDir, parentSession: SessionId('continuation-parent') }, agentOptions: { model: 'deepseek' }, @@ -385,7 +422,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const oldChild = await ctx.agents.create({ + const oldChild = await oldParent.agent.ctx.agents.create({ sessionId: SessionId('reused-child'), meta: { cwd: storageDir, parentSession: SessionId('old-parent') }, agentOptions: { model: 'deepseek' }, @@ -425,7 +462,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const newChild = await ctx.agents.create({ + const newChild = await newParent.agent.ctx.agents.create({ sessionId: SessionId('reused-child'), meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, agentOptions: { model: 'deepseek' }, @@ -483,12 +520,12 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - handle = await ctx.agents.create({ + handle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('fallback-child-session'), meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { model: 'deepseek' }, }) - failedHandle = await ctx.agents.create({ + failedHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, From 00462f80a6ff59604e44b71446bb9b2427a212c8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:01:36 +0800 Subject: [PATCH 13/33] docs: expose agent ownership in Cordis catalog --- packages/cordis/tool-cordis/src/api-catalog.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index ff27f51067..ede7935f8e 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -72,6 +72,7 @@ export const SERVICE_API: readonly ServiceApiEntry[] = [ 'enter(agent: Agent, owner: Agent | undefined): () => void', 'announce(agent: Agent): void', 'get(id: SessionId): Agent | undefined', + 'isOwnedBy(id: SessionId, owner: Agent): boolean', 'list(): Agent[]', 'roots(): Agent[]', ], From db3e97fc17a0f96fda7a2ecee94af86e7fad2102 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:05:19 +0800 Subject: [PATCH 14/33] test: create built probe child in parent scope --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index 159600e49c..bc6642263e 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -58,7 +58,7 @@ try { meta: { cwd: storageRoot }, agentOptions: { model: "test" }, }); - const child = await ctx.agents.create({ + const child = await parent.agent.ctx.agents.create({ sessionId: SessionId("built-child"), meta: { cwd: storageRoot, parentSession: SessionId("built-parent") }, agentOptions: { model: "test" }, From cf21e252fa8fd7e66c4b0c6a5acface4821d4712 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:32:02 +0800 Subject: [PATCH 15/33] fix: recognize provider-owned local subagents --- packages/subagent/subagent/README.md | 2 ++ packages/subagent/subagent/src/types.ts | 6 +++++- packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 22 ++++++++++++++++------ packages/ui/jsonrpc/tests/server.spec.ts | 5 ++++- 5 files changed, 28 insertions(+), 9 deletions(-) diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index 413bbbdafc..016d363d78 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -50,6 +50,8 @@ Runtime features are optional methods on `SubagentRun`: `sendMessage?` steers a `SubagentRun.result` resolves to `{ output, structured?, stopReason }`. Child-level failures resolve with a non-`completed` reason; only an infrastructure fault that the seam cannot represent may reject. `dispose()` is idempotent, cancels remaining work, and waits for the child resources to quiesce. +A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, and records `request.parent.session.id` in the child's `parentSession` header. The child may be owned by the parent scope or by a provider/root scope; durable lineage is the transport-neutral local-child relation. Remote providers instead mint a parent-scoped lifecycle id without publishing a local child. + The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. In-process start observers can resolve the published child through `ctx.agents.get(info.id)`; remote providers need not publish a local agent. Run events are scoped to the delegating parent. Every listener is independently contained: a synchronous throw or rejected returned promise is logged without starving peer listeners or changing the run. diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 827c2db7a7..37e0b28323 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -147,7 +147,11 @@ export interface SubagentResult { * presence of the method IS the capability — narrow before calling. */ export interface SubagentRun { - /** Parent-scoped run id. Local runs use the published child session id; remote providers mint an id unique in the parent namespace. */ + /** + * Parent-scoped run id. A local run publishes a child session whose + * `parentSession` records `request.parent`; a remote provider mints an id + * unique in the parent namespace. + */ readonly id: SessionId /** * Resolves with the child's terminal {@link SubagentResult} when the run diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index df612ac263..4ef9e86ffc 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`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server verifies that the live child is owned by the exact delegating parent, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. 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` / `$DEEPSEEK_BASE_URL`) — a config-registered adapter for the model wins. Everything else — persistence, the tool stacks, the adapter set — comes from the surrounding `cordis.yml`. +`inject: ['agents']` — the server creates one agent per SDK `sessionId` (get-or-create on `session/prompt`). A local subagent's shared agent/session id supplies `subagent.finished.childSessionId` directly; the server recognizes a live child through either exact delegating-parent runtime ownership or matching durable `parentSession` lineage, then counts local starts by provider/id and that parent carrier because a continuation may reuse one child and the child may be disposed before a later `subagent/end`. The paired event carrier preserves parent correlation even when reused ids settle out of order. Runs from remote providers are not reported even when their parent-scoped run id collides with an unrelated local agent. The LLM seam is read opportunistically via `ctx.get('llm')` (not injected): when `initialize.model` has no registered adapter, the plugin mounts `dsh-llm-deepseek` for it (credentials from `$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`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index d78f24b5ab..723f2eb4eb 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -66,6 +66,15 @@ function subagentParentOf(carrier: Scoped): Agent { return carrierKeyOf(carrier) as Agent } +/** Whether the live id names a local child related to this exact delegating parent. */ +function isLocalChild(ctx: Context, id: SessionId, parent: Agent): boolean { + const child = ctx.agents.get(id) + return child !== undefined && ( + ctx.agents.isOwnedBy(id, parent) + || child.session.header.parentSession === parent.session.id + ) +} + /** * The SDK server over a booted harness context. Constructing it subscribes to * session and subagent lifecycle events, forwarding durable session @@ -104,13 +113,14 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // In-process providers publish the child before start. Count those starts by - // the exact delegating-parent carrier so later completions remain local after - // child disposal and reused ids need no settlement-order assumption. + // In-process providers publish the child before start. Count starts related + // by exact runtime ownership or durable parent lineage so provider-owned + // roots remain local, completions survive child disposal, and reused ids + // need no settlement-order assumption. const localRuns = this.localRuns this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { const parent = subagentParentOf(this) - if (!ctx.agents.isOwnedBy(info.id, parent)) return + if (!isLocalChild(ctx, info.id, parent)) return const providerRuns = localRuns.get(info.provider) ?? new Map>() const parentRuns = providerRuns.get(info.id) ?? new Map() parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) @@ -130,9 +140,9 @@ export class HarnessSdkServer { } // This protocol reports LOCAL child sessions. A lineage-bearing child // has the session/created-driven start notification above. A remote run - // has neither a cached owned start nor a live child owned by this exact + // has neither a cached local start nor a live child related to this // parent; an unrelated local agent with the same id never makes it local. - if (pendingCount === undefined && !ctx.agents.isOwnedBy(info.id, parent)) return + if (pendingCount === undefined && !isLocalChild(ctx, info.id, parent)) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index c97bd1a6e1..3861a6729d 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -277,11 +277,14 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const handle = await parentHandle.agent.ctx.agents.create({ + // A custom in-process provider may own its child at the provider/root + // scope while preserving durable parent lineage. + const handle = await ctx.agents.create({ sessionId: SessionId('child-session'), meta: { cwd: storageDir, parentSession: SessionId('main') }, agentOptions: { model: 'deepseek' }, }) + expect(ctx.agents.roots()).toContain(handle.agent) const parentlessHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('parentless-child-session'), meta: { cwd: storageDir }, From 288023dac182c407c296571f3730ff3a89a0696a Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 10:51:36 +0800 Subject: [PATCH 16/33] docs: define local subagent lineage --- docs/core-data-structures/subagent.md | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 883c33020a..7b57789a7c 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -76,6 +76,8 @@ interface SubagentRun { } ``` +A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope; `parentSession` is the durable transport-neutral lineage. A remote provider instead returns a parent-scoped lifecycle id and does not publish a local child. + ## The provider seam: `SubagentProvider` One transport for running a child agent. Implementations register under a unique name via `SubagentService.registerProvider`; multiple coexist in one context. The service validates every requested start-time capability before calling `start`, so an implementation may assume e.g. `request.maxDepth` is honorable when present. `inheritsParentContext` is a DESCRIPTIVE fact beside the capabilities (nothing validates against it): whether a child sees the parent conversation (`fork`: true, `spawn`/`acp`: false) — the model-facing consumer derives truthful tool wording from it. It describes conversation history only, not tool registrations, injected services, or authority inheritance. From 5409452cc705804386fe029908f14b31840efe96 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 19:30:29 +0800 Subject: [PATCH 17/33] test: refresh snapshots after master merge --- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/stdout.golden.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/stdout.golden.jsonl | 2 +- .../tests/snapshots/both-mode-turn/system-prompt.golden.md | 2 +- .../acp-agent/tests/snapshots/cancel/stdout.golden.jsonl | 2 +- .../tests/snapshots/code-mode-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/code-mode-turn/system-prompt.golden.md | 2 +- .../tests/snapshots/config-options/stdout.golden.jsonl | 6 +++--- .../tests/snapshots/error-finish/stdout.golden.jsonl | 2 +- .../tests/snapshots/escalation-approved/session.jsonl | 4 ++-- .../tests/snapshots/escalation-approved/stdout.golden.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/session.jsonl | 4 ++-- .../tests/snapshots/escalation-rejected/stdout.golden.jsonl | 4 ++-- .../acp-agent/tests/snapshots/fs-edit/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-policy-reject/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-read-window/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/fs-read/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-terminal-card/stdout.golden.jsonl | 2 +- .../tests/snapshots/fs-write-overwrite/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/fs-write/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/handshake/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-posttool-block/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-posttool-context/stdout.golden.jsonl | 2 +- .../tests/snapshots/hook-cc-pretool-ask/session.jsonl | 4 ++-- .../tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-pretool-deny/stdout.golden.jsonl | 2 +- .../hook-cc-promptsubmit-block/stdout.golden.jsonl | 2 +- .../hook-cc-promptsubmit-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-cc-stop-continue/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-posttool-block/stdout.golden.jsonl | 2 +- .../hook-codex-posttool-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-pretool-block/stdout.golden.jsonl | 2 +- .../hook-codex-promptsubmit-block/stdout.golden.jsonl | 2 +- .../hook-codex-promptsubmit-context/stdout.golden.jsonl | 2 +- .../snapshots/hook-codex-stop-continue/stdout.golden.jsonl | 2 +- .../tests/snapshots/multi-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/permission-switching/session.jsonl | 2 +- .../snapshots/permission-switching/stdout.golden.jsonl | 6 +++--- .../tests/snapshots/repeat-tool-guard/stdout.golden.jsonl | 2 +- examples/acp-agent/tests/snapshots/skill-load/session.jsonl | 2 +- .../tests/snapshots/skill-load/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-fork/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-mixed/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-multi/stdout.golden.jsonl | 2 +- .../tests/snapshots/subagent-spawn/stdout.golden.jsonl | 2 +- examples/acp-agent/tests/snapshots/text-turn/session.jsonl | 2 +- .../acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl | 2 +- .../acp-agent/tests/snapshots/todo-plan/stdout.golden.jsonl | 2 +- .../tests/snapshots/tool-call-turn/stdout.golden.jsonl | 2 +- .../tests/snapshots/workflow-run/stdout.golden.jsonl | 2 +- .../tests/snapshots/workspace-edit/stdout.golden.jsonl | 2 +- 55 files changed, 64 insertions(+), 64 deletions(-) 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 991806d74b..cdc09c92c0 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":{"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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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 a6a3371913..79d9b94ad9 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":{"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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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 c6213cd558..7155b1c2a6 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":{"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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/advanced-toolchain/stdout.golden.jsonl index bc4da17bb0..80a9cc9339 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/advanced-toolchain/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/advanced-toolchain/system-prompt.golden.md index 5ad12cddff..6e8f157ace 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 @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** 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. */ + /** 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. */ bash(args: { /** The bash command to execute. */ command: 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 a68bb37f9f..66cdecedfb 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`. 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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/both-mode-turn/stdout.golden.jsonl index 577f10445b..c9d2c87c27 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/both-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/both-mode-turn/system-prompt.golden.md index ed60d52258..98b4f97fee 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 @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** 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. */ + /** 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. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/cancel/stdout.golden.jsonl index 60235cac75..1f8c0ca024 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..5fe0944ac7 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/code-mode-turn/system-prompt.golden.md b/examples/acp-agent/tests/snapshots/code-mode-turn/system-prompt.golden.md index ed60d52258..98b4f97fee 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 @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** 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. */ + /** 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. */ bash(args: { /** The bash command to execute. */ command: string; 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..7c85717676 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..99e00460c6 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/session.jsonl index 8aac1627bc..74fbed6ee3 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\"}"}],"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":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","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":"3b0efb0e-5b4a-4911-87cf-9914bd346c17","outcome":"allowed-once"}} +{"type":"approval/asked","seq":132,"time":1783962245386,"data":{"id":"daa6d214-9e99-4cb6-b4f7-7f6086379133","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":"daa6d214-9e99-4cb6-b4f7-7f6086379133","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-approved/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-approved/stdout.golden.jsonl index f438444dc4..5c63764aae 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/session.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/session.jsonl index 7c0a743413..bf86999cd9 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\"}"}],"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":"9e6c7946-af56-4535-9cce-993e0165c2f9","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":"9e6c7946-af56-4535-9cce-993e0165c2f9","outcome":"rejected"}} +{"type":"approval/asked","seq":156,"time":1783962246275,"data":{"id":"71281495-1503-47de-bbdf-11d5de1e5f06","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":"71281495-1503-47de-bbdf-11d5de1e5f06","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/escalation-rejected/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/escalation-rejected/stdout.golden.jsonl index b926355bd7..07e48d9e22 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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 acc193ad1e..919c0f169e 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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 5aa75c026c..c27544a176 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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 05832400c8..8b75c30e8c 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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 19abb7f418..30aa0d2460 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..e045c7b228 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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 4801d9410d..f554fa3123 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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 d5b3ca5d15..d04def6af2 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..312569a491 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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 0a93b649da..36f050a694 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..bbc16779ba 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/session.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/session.jsonl index b975c54aac..faed620b4c 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":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} -{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"da1d1e2e-c13f-4e70-8039-a42ae8f84fd5","outcome":"rejected"}} +{"type":"approval/asked","seq":56,"time":1783962235813,"data":{"id":"7b519d67-ef63-4ba2-9b37-1493e1525329","toolName":"bash","callId":"call_00_6k0oGSliVHxGSgqBmMEO4311","reason":"bash requires manual approval in this session"}} +{"type":"approval/decided","seq":57,"time":1783962235813,"data":{"id":"7b519d67-ef63-4ba2-9b37-1493e1525329","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/hook-cc-pretool-ask/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/hook-cc-pretool-ask/stdout.golden.jsonl index 3905e82ca7..db38650167 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..f0c5e005d9 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..5d88350cad 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..ac203d50cc 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..01297aa39d 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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 cbaec45f9f..57b297ccfc 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..faa1255a32 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..11b47d6e58 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..5d88350cad 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..116a8ebbbd 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..d231f60e0a 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/multi-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/multi-turn/stdout.golden.jsonl index 1d9d45954a..b45d9e947c 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index 0d8e018ae5..a30f9e4a46 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":{"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?, 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"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"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"]}},{"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"]}}]},"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/permission-switching/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/stdout.golden.jsonl index 651897e850..9c3c78be5c 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..876f6c490a 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/session.jsonl b/examples/acp-agent/tests/snapshots/skill-load/session.jsonl index 9a26fa2efe..1c85ee81ba 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`. 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?, 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"]}}],"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":{"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?, 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"]}}],"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/skill-load/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/skill-load/stdout.golden.jsonl index 10198918d6..b5f25f2c07 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..e390bda86a 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..db5f28fa79 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..4c0c7d2601 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..ce114fccf0 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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/session.jsonl b/examples/acp-agent/tests/snapshots/text-turn/session.jsonl index 0643740e4f..c66f5676cc 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`. 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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/text-turn/stdout.golden.jsonl index 1059a9cc6c..8de447de6d 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..a947ed4997 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..9d06e9d6ac 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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..56b8f3537a 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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 23f13ff3c2..513a02a6af 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":"permission","name":"Permissions","description":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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"}}}} From 5a1194bf301ecd9f2ab007a599a2e121e57b72e6 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Tue, 14 Jul 2026 20:18:24 +0800 Subject: [PATCH 18/33] test: refresh snapshots after bash guidance merge --- .../tests/snapshots/advanced-toolchain/session.1.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/session.2.jsonl | 2 +- .../acp-agent/tests/snapshots/advanced-toolchain/session.jsonl | 2 +- .../tests/snapshots/advanced-toolchain/system-prompt.golden.md | 2 +- examples/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/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 +- 10 files changed, 10 insertions(+), 10 deletions(-) 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 cdc09c92c0..991806d74b 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":{"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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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 79d9b94ad9..a6a3371913 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":{"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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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 7155b1c2a6..c6213cd558 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":{"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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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 6e8f157ace..5ad12cddff 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 @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** 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. */ + /** 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. */ bash(args: { /** The bash command to execute. */ command: 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 66cdecedfb..a68bb37f9f 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`. 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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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 98b4f97fee..ed60d52258 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 @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** 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. */ + /** 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. */ bash(args: { /** The bash command to execute. */ command: 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 98b4f97fee..ed60d52258 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 @@ -25,7 +25,7 @@ The available tools: ```ts declare const tools: { - /** 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. */ + /** 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. */ bash(args: { /** The bash command to execute. */ command: string; diff --git a/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl b/examples/acp-agent/tests/snapshots/permission-switching/session.jsonl index 1f33766ec9..07cd6233b3 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":{"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?, 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"]}}]},"reason":"initial"}} +{"type":"request/header","seq":6,"time":1783962244580,"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"]}},{"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"]}}]},"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 1c85ee81ba..9a26fa2efe 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`. 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?, 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"]}}],"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":{"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?, 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"]}}],"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 c66f5676cc..0643740e4f 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`. 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?, 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"]}}]},"reason":"initial"}} +{"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`. 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?, 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"]}}]},"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"}}} From f6350ac553dc9f34b7c397eb62991e2566f1ca6b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:10:46 +0800 Subject: [PATCH 19/33] Keep root instructions within budget --- AGENTS.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/AGENTS.md b/AGENTS.md index 0c5272b105..4209b0f95c 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -59,7 +59,7 @@ pnpm run demo:cordis # self-referential demo: the agent modifies its own runt pnpm run demo:acp # ACP server agent (needs DEEPSEEK_API_KEY) ``` -### Run the CI gates locally before marking a PR ready +### Run CI gates locally before marking a PR ready Run narrow checks during implementation and this CI-equivalent sequence before marking a PR ready. Fresh worktrees need `pnpm run build` before publint and NodeNext inspect `lib/`: From cdeec6fc1d984adfdbd645d1a481dd0a2a9fdba8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 17:36:51 +0800 Subject: [PATCH 20/33] Update built JSON-RPC probe path --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index bc6642263e..ed4dfbb9db 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -33,7 +33,7 @@ const [ { SessionId }, ] = await Promise.all([ load("vendor/cordis/lib/index.js"), - load("packages/core/agent-core/lib/index.js"), + load("packages/examples/agent-spine-demo/lib/index.js"), load("packages/subagent/subagent/lib/index.js"), load("packages/session-persistence/session-persistence-jsonl/lib/index.js"), load("packages/ui/jsonrpc/lib/index.js"), From 419b0bcf7dfd9c0e88bc15ecf303c9576a92b43f Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Wed, 15 Jul 2026 23:51:45 +0800 Subject: [PATCH 21/33] docs: refresh module graph for UI identity --- docs/module-graph.md | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/docs/module-graph.md b/docs/module-graph.md index baa714bad1..83f98d734e 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -321,6 +321,7 @@ flowchart TD pkg_jsonrpc --> pkg_agent pkg_jsonrpc --> pkg_llm pkg_jsonrpc --> pkg_llm_deepseek + pkg_jsonrpc --> pkg_scope pkg_jsonrpc --> pkg_session pkg_jsonrpc --> pkg_subagent pkg_stdio --> pkg_agent @@ -443,7 +444,7 @@ flowchart TD | [`tool-subagent`](../packages/subagent/tool-subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`subagent`](../packages/subagent/subagent), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) | | [`hooks-claude`](../packages/hooks/hooks-claude) | `hooks` | [`agent`](../packages/core/agent), [`hook-protocol`](../packages/hooks/hook-protocol), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools) | | [`subagent-mock`](../packages/support/subagent-mock) | `support` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | -| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | +| [`jsonrpc`](../packages/ui/jsonrpc) | `ui` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`llm-deepseek`](../packages/llm/llm-deepseek), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent) | | [`stdio`](../packages/ui/stdio) | `ui` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`user-interaction`](../packages/ui/user-interaction) | | [`agent-spine-demo`](../packages/examples/agent-spine-demo) | `examples` | [`agent`](../packages/core/agent), [`agent-loop`](../packages/core/agent-loop), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`skill`](../packages/skill/skill), [`skill-local`](../packages/skill/skill-local), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tool-bash`](../packages/bash/tool-bash), [`tool-skill`](../packages/skill/tool-skill), [`tool-tasks`](../packages/tasks/tool-tasks), [`tools`](../packages/core/tools) | | [`workflow-workerthread`](../packages/workflow/workflow-workerthread) | `workflow` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) | From 336f4e51ba0b7fe0c79abbd7d617f6597f0fd7fb Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 00:51:52 +0800 Subject: [PATCH 22/33] docs(acp): align identity routing contract --- packages/ui/acp/README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/ui/acp/README.md b/packages/ui/acp/README.md index 3650cf27d4..923c0178fa 100644 --- a/packages/ui/acp/README.md +++ b/packages/ui/acp/README.md @@ -8,7 +8,7 @@ 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`, `sessionPersistence`, `tools`, and `userInteraction`, never the concrete loop. Persistence backs `session/load`; tool definitions own presentation; user interaction maps agent questions to ACP forms. ### Config @@ -36,7 +36,7 @@ The `initialize` handshake reports a fixed server identity (`agentInfo: { name: ## Multi-session -Forward and reverse indexes route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). +One id-keyed record map plus exact agent-object checks route every event, prompt, cancel, and approval to one session. Each session permits one in-flight prompt; teardown drains all sessions in parallel. See the [multi-session RFC](../../../docs/rfc/implemented/feature/2026-06-14-acp-multi-session.md). ## Session config options From 1a111654ae13b9dd448cc7166499c45247e20731 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 01:17:26 +0800 Subject: [PATCH 23/33] docs(subagent): restore local run identity contract --- packages/subagent/subagent/src/types.ts | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index 67fcc99600..b0f228da96 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -134,9 +134,9 @@ export interface SubagentResult { */ export interface SubagentRun { /** - * Parent-scoped run id. A local run publishes a child session whose - * `parentSession` records `request.parent`; a remote provider mints an id - * unique in the parent namespace. + * Parent-scoped run id. For a local run, this MUST equal the published child + * session id, whose `parentSession` records `request.parent`; a remote + * provider mints an id unique in the parent namespace. */ readonly id: SessionId /** From 70c6c0ac39aacf14ab0b627319b192fd1ca6f03b Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:04:04 +0800 Subject: [PATCH 24/33] docs(approval): qualify audit guarantees --- .../implemented/feature/2026-07-06-approval-seam.md | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 9f4968c3a4..0945228593 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -25,7 +25,7 @@ One `cordis.yml` entry mounts the seam. Not loading it is the fail-closed opt-ou The entry alone provides mechanism, not a channel: with no answerer composed, every ask resolves `unavailable` and the asking tool call denies — fail-closed needs no configuration. Composing the ACP app (`@deepseek-ai/dsh-acp-demo`, as in [the acp-agent example's default tree](../../../../examples/acp-agent/README.md)) completes the loop: its bridge registers an answerer that prompts the owning editor session via `session/request_permission`, so a hook's `ask` or an escalation request surfaces as a one-shot Allow/Reject prompt attached to the already-streamed tool call. `policy: never` is the unattended stance — every ask auto-rejects deterministically, stated in the system prompt, no human in the loop. `policy` is validated against the closed list at plugin load; anything else throws. -What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; every ask lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. +What a composed deployment observes: `allowed-once` lets exactly that call proceed; rejection, dismissal, and channel absence deny with three distinct reasons the model can tell apart; a successful in-turn request lands a durable `approval/asked`/`approval/decided` pair on the asking agent's session log; nothing about a grant persists past the call that asked. An idle request or audit append failure rejects instead of returning an unaudited decision. One ask under this composition, verbatim from the sandbox example's recorded `escalation-approved` scenario — the model requests a sandbox escalation, the gate asks, the bridge prompts the owning editor, the user clicks Allow once: @@ -71,7 +71,7 @@ The answerer routes through the bridge's exact-agent ownership check described b #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. One `decided` lands per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. +`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. #### Entities and dependencies @@ -105,7 +105,7 @@ The implemented contract is pinned by the suites in Testing: - With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. - A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). - Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; post-append observer failures cannot split the pair. +- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. - Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. - A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. @@ -113,7 +113,7 @@ Costs and accepted limits: - **Two decide-eager answerers race for the slot.** Sibling-plugin listener order is not deterministic, so the seam cannot referee competing terminal answerers — mitigated by convention (one terminal answerer per deployment; `prepend` only for decide-or-delegate gates) rather than a priority mechanism the event bus does not have. - **Production exercise rests on one composition.** `ask` has two producer families — the hook bridges through `tools/pre-execute`, and sandbox escalation through its own gate — with the wire recorded in the sandbox example's snapshot suite, so the seam's real-world coverage is that one composition until more deployments compose it. -- **Ownership keys on `Agent` object identity.** The answerer resolves sessions through the bridge's existing WeakMap; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need session-id matching instead. +- **Ownership keys on `Agent` object identity.** The answerer resolves the forward session-map record at `agent.session.id`, then requires that record to own the exact agent object; every current path hands the same object through the loop and the seams, but a future boundary that clones or proxies agents would make the bridge delegate and fail closed — safe, but silently UI-less — and would need a different ownership contract. ## FAQ @@ -123,10 +123,10 @@ Behavioral and usage questions only — every "why not X?" design question lives - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. - **Who decides whether a call asks in the first place?** Policy producers: a hook returning `permissionDecision: ask`, any `tools/pre-execute` listener, or the sandbox escalation gate. The seam and the bridge only route and answer; neither injects its own judgment about what deserves a prompt. -- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer — one audit pair either way, never two. +- **What happens when the user dismisses the prompt, or the turn aborts mid-ask?** Dismissal maps to `cancelled` with its own deny text. An already-aborted signal settles `cancelled` without dispatching; an abort during the ask discards the late answer. When both audit appends commit, either path records one pair, never two. - **What if the client answers with an option the harness never offered?** Any selection other than the offered `allow_once` maps to `rejected` — an unknown optionId from a non-conforming client can never grant. - **How do subagents' approvals route?** An agent no answerer owns delegates through the whole waterfall and fails closed — in-process subagents are deliberately unanswerable. `subagent-acp`'s child-side auto-answer is separate; routing a child's asks to the parent's editor is deferred (§ Deferred). -- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; the audit pair still lands for every auto-rejection. +- **What does `policy: 'never'` actually change at runtime?** The service resolves every ask for that session to `rejected` before dispatching any answerer (in-service, so no registration order can bypass it); the system prompt states the policy; switches are narrated at boundaries; each successful auto-rejection records the audit pair. - **What happens across a hot reload, or when the UI plugin unloads mid-session?** Answerers dispose with their owning fiber, so the next ask degrades to `unavailable` instead of hanging on a dead channel; remounting re-registers the answerer with no catch-up state. - **Where does the user see what they are approving?** On the tool call itself: the prompt attaches to the already-streamed call via `callId` — arguments included — and adds the asker's human-readable `reason`; the request carries no argument copy of its own. From 69c36e4fb5a6bceff4f44a8ba81ee8deb68fc1e8 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:31:20 +0800 Subject: [PATCH 25/33] docs(subagent): name parent session lineage --- packages/subagent/subagent/src/types.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index b0f228da96..e5ba8fd84d 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -135,8 +135,8 @@ export interface SubagentResult { export interface SubagentRun { /** * Parent-scoped run id. For a local run, this MUST equal the published child - * session id, whose `parentSession` records `request.parent`; a remote - * provider mints an id unique in the parent namespace. + * session id, whose `parentSession` records `request.parent.session.id`; a + * remote provider mints an id unique in the parent namespace. */ readonly id: SessionId /** From 9366baf39fd84f169e1df7f42048088b5cc0c790 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:31:26 +0800 Subject: [PATCH 26/33] docs(acp): describe session terminal rendering --- packages/ui/acp/src/index.ts | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 8bb25df579..d9c53cebf0 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -1049,7 +1049,7 @@ function validateMcpServers(params: { mcpServers?: unknown[] }): void { * zero or more times per event (best-effort UI feed, never load-bearing). * @param presenter - resolves tool-owned render intent for tool events; * defaults to the generic-fallback {@link nullToolPresenter}. - * @param terminal - the connection's terminal-rendering context; defaults to + * @param terminal - the session's terminal-rendering context; defaults to * disabled (the plain-text console-block fallback). * @param options - `includeUserMessages` (default `true`): live streaming * passes `false` so a prompt the client just sent is not echoed back. @@ -1122,7 +1122,7 @@ export function todosToPlan(todos: TodoItem[]): Plan { } /** - * Per-connection terminal-rendering context threaded into + * Per-session terminal-rendering context threaded into * {@link streamSessionEventUpdate}: whether the client advertised the * `_meta.terminal_output` capability, and the session's workspace cwd (the * default terminal-card header when a tool doesn't supply its own). Kept out of From 4c08629b58ef493da1a02e0dcff9eed4d4eb1980 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:56:12 +0800 Subject: [PATCH 27/33] docs(acp): describe concurrent update routing --- packages/ui/acp/src/index.ts | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index d9c53cebf0..7b5cb11324 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -20,11 +20,12 @@ * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; * every `session/event` and `agent/*` event is routed strictly to its owning - * session record, so two sessions streaming at once never interleave their - * `session/update` notifications. Permission prompts use the same identity: the - * bridge answers `approval/request` for its own agents over - * `session/request_permission` (see the approval answerer below) — whether a - * call ASKS is policy (a hook or plugin returning `ask`), not the bridge's. + * session record, and each `session/update` carries that id. Concurrent updates + * may alternate on the shared connection without crossing session attribution. + * Permission prompts use the same identity: the bridge answers + * `approval/request` for its own agents over `session/request_permission` (see + * the approval answerer below) — whether a call ASKS is policy (a hook or + * plugin returning `ask`), not the bridge's. * * stdout is the protocol: this plugin must run in an example that loads NO * stdout logger (the console logger writes to stdout and would corrupt the @@ -483,8 +484,8 @@ export function apply(ctx: Context, config: AcpConfig): void { // whose end arrives late is ignored (see // SessionRecord.inflight). A turn that ends `error` REJECTS the prompt (ACP // has no error stop reason); other reasons resolve via the codec. Demux - // strictly by session id: a `session/event` is routed to its own record, so - // two sessions streaming at once never cross-settle or interleave updates. + // strictly by session id: concurrent updates may alternate on the shared + // connection, but they retain the owning id and never cross-settle. ctx.on('session/event', (session, event: SessionEvent) => { const rec = sessions.get(session.header.id) if (rec === undefined) return From 486362d2f8a6de1aee998cee320046d5c3db1a8d Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 02:57:32 +0800 Subject: [PATCH 28/33] docs(catalog): refresh ACP config source link --- docs/config-catalog.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 4300404cfb..cb5aebbdf8 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -31,7 +31,7 @@ export interface AcpConfig { Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:244`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:245`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-demo` From f7af6a87dcf06397bb66b91fd851572e31385815 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Thu, 16 Jul 2026 03:25:21 +0800 Subject: [PATCH 29/33] docs(acp): describe terminal capability lifetime --- packages/ui/acp/src/index.ts | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 7b5cb11324..a12249d0b5 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -359,10 +359,10 @@ export function apply(ctx: Context, config: AcpConfig): void { // await and NOT install a record (which would resurrect a live agent/listeners // after the bridge closed). Checked after every load await. let closed = false - // Whether the client advertised the Zed `_meta.terminal_output` capability in - // `initialize`. When true, a tool's terminal presentation is rendered as a - // terminal card (content + `_meta.terminal_*`); when false, the bridge uses - // the tool's text fallback. Set once in `initialize`, read on every tool event. + // Connection-level terminal capability from the latest `initialize`; false + // before initialization. Each `session/new` or `session/load` snapshots it in + // `SessionRecord.terminalEnabled`, so later initialization affects only future + // sessions. let terminalOutputCap = false // Assigned at the bottom, before any agent event can fire (a session only From 0f85ae0a9df15ad0a356087715afebba12ff41b4 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 14:26:14 +0800 Subject: [PATCH 30/33] fix(subagent): identify lifecycle runs explicitly --- docs/config-catalog.md | 2 +- docs/cordis-catalog/events.md | 8 +- docs/cordis-catalog/services.md | 2 +- docs/core-data-structures/subagent.md | 5 +- docs/event-producer-consumer.md | 8 +- docs/module-graph.md | 3 +- .../cordis/tool-cordis/src/api-catalog.ts | 2 +- .../hooks/hooks-claude/tests/bridge.spec.ts | 7 +- .../hooks-claude/tests/coverage-cases.ts | 9 +- packages/subagent/subagent-acp/src/run.ts | 1 + .../subagent/subagent-inprocess/src/index.ts | 1 + packages/subagent/subagent/README.md | 4 +- packages/subagent/subagent/package.json | 2 + packages/subagent/subagent/src/index.ts | 25 +++- packages/subagent/subagent/src/types.ts | 19 +++ .../subagent/subagent/tests/service.spec.ts | 25 +++- .../tool-subagent/tests/tool-subagent.spec.ts | 15 ++ packages/support/subagent-mock/src/index.ts | 1 + packages/ui/jsonrpc/README.md | 2 +- packages/ui/jsonrpc/src/server.ts | 45 +----- .../jsonrpc/tests/built-scope-carrier.e2e.ts | 1 + packages/ui/jsonrpc/tests/server.spec.ts | 130 ++++++++++++++++-- .../tests/workflow-workerthread.spec.ts | 8 ++ pnpm-lock.yaml | 3 + website/zh-CN/api/harness/events.md | 8 +- website/zh-CN/api/harness/subagents.md | 10 +- 26 files changed, 253 insertions(+), 93 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index a0cbac6789..f07dfcf18a 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -918,7 +918,7 @@ export interface Config { Depends on: [`SubagentCapabilities`](../packages/subagent/subagent/src/index.ts) · [`SubagentStopReason`](../packages/subagent/subagent/src/index.ts) -Source: [`packages/support/subagent-mock/src/index.ts:86`](../packages/support/subagent-mock/src/index.ts) +Source: [`packages/support/subagent-mock/src/index.ts:87`](../packages/support/subagent-mock/src/index.ts) ## `@deepseek-ai/dsh-subagent-spawn` diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index 820a453ceb..d0ff7002b0 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -301,7 +301,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c 'subagent/end'(this: Scoped, info: SubagentRunEndInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:109`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:112`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-added` — emit @@ -311,7 +311,7 @@ A provider became resolvable in the registry. 'subagent/provider-added'(provider: SubagentProvider): void ``` -Source: [`packages/subagent/subagent/src/index.ts:83`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:86`](../../packages/subagent/subagent/src/index.ts) ### `subagent/provider-removed` — emit @@ -321,7 +321,7 @@ A provider left the registry. Accepted runs remain holder-owned. 'subagent/provider-removed'(name: string): void ``` -Source: [`packages/subagent/subagent/src/index.ts:89`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:92`](../../packages/subagent/subagent/src/index.ts) ### `subagent/start` — emit @@ -331,7 +331,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( 'subagent/start'(this: Scoped, info: SubagentRunInfo): void ``` -Source: [`packages/subagent/subagent/src/index.ts:100`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:103`](../../packages/subagent/subagent/src/index.ts) ## `system-prompt/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index 52f9cdf131..ee953e37c7 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -264,7 +264,7 @@ list(): string[] async start(name: string, request: SubagentStartRequest): Promise ``` -Source: [`packages/subagent/subagent/src/index.ts:142`](../../packages/subagent/subagent/src/index.ts) +Source: [`packages/subagent/subagent/src/index.ts:153`](../../packages/subagent/subagent/src/index.ts) ## `ctx.systemPrompt` — `SystemPrompt` diff --git a/docs/core-data-structures/subagent.md b/docs/core-data-structures/subagent.md index 18cb22c32d..815438f215 100644 --- a/docs/core-data-structures/subagent.md +++ b/docs/core-data-structures/subagent.md @@ -69,6 +69,7 @@ interface SubagentStopReasonMap { ```ts type-equiv interface SubagentRun { readonly id: SessionId + readonly localAgent: Agent | undefined readonly result: Promise dispose(): Promise sendMessage?(content: ContentBlock[]): void @@ -76,7 +77,7 @@ interface SubagentRun { } ``` -A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope; `parentSession` is the durable transport-neutral lineage. A remote provider instead returns a parent-scoped lifecycle id and does not publish a local child. +A local run MUST publish an ordinary child agent/session before `start()` fulfills, return that child session id as `SubagentRun.id`, expose the exact child as `localAgent`, and record `request.parent.session.id` in the child's `parentSession` header. Runtime ownership may place the child under the parent, provider, or root scope. A remote provider instead returns a parent-scoped lifecycle id and `localAgent: undefined`. ## The provider seam: `SubagentProvider` @@ -91,7 +92,7 @@ interface SubagentProvider { } ``` -`start()` fulfills only with a ready run. The service observes its result, emits `subagent/start`, and returns the same run; rejection implies provider cleanup and emits no lifecycle pair. In-process children are discoverable through `ctx.agents`, while remote children need not be. `subagent/end` reports final output or infrastructure failure. Both events are observe-only and contain listener exceptions. +`start()` fulfills only with a ready run. The service mints a unique `runId`, snapshots `local` from the provider's exact `localAgent`, observes the result, emits `subagent/start`, and returns the same run; rejection implies provider cleanup and emits no lifecycle pair. The paired `subagent/end` carries the same identity and the final output or infrastructure failure. Both events are observe-only and contain listener exceptions. ## In-process backends: depth and seed diff --git a/docs/event-producer-consumer.md b/docs/event-producer-consumer.md index 6d75d54f3d..49e8d778cf 100644 --- a/docs/event-producer-consumer.md +++ b/docs/event-producer-consumer.md @@ -30,10 +30,10 @@ This matrix shows which packages dispatch each harness-owned event and which pac | `session/disposed` | `emit` | [`packages/core/session/src/index.ts:56`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`agent-loop`](../packages/core/agent-loop), [`session-persistence`](../packages/session-persistence/session-persistence) | | `session/event` | `emit` | [`packages/core/session/src/index.ts:68`](../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`](../packages/ui/stdio), [`token-meter`](../packages/llm/token-meter), [`workspace-context`](../packages/context/workspace-context) | | `session/flush` | `parallel` | [`packages/core/session/src/index.ts:78`](../packages/core/session/src/index.ts) | [`session`](../packages/core/session) (`events.dispatch`) | [`session-persistence`](../packages/session-persistence/session-persistence) | -| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:109`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | -| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:83`](../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:89`](../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:100`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/end` | `emit` | [`packages/subagent/subagent/src/index.ts:112`](../packages/subagent/subagent/src/index.ts) | [`subagent`](../packages/subagent/subagent) (`events.dispatch`) | [`hooks-claude`](../packages/hooks/hooks-claude), [`jsonrpc`](../packages/ui/jsonrpc) | +| `subagent/provider-added` | `emit` | [`packages/subagent/subagent/src/index.ts:86`](../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:92`](../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:103`](../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`) | [`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`) | - | diff --git a/docs/module-graph.md b/docs/module-graph.md index 604aa7cf7f..f49092f99d 100644 --- a/docs/module-graph.md +++ b/docs/module-graph.md @@ -279,6 +279,7 @@ flowchart TD pkg_tool_skill --> pkg_skill pkg_tool_skill --> pkg_tools pkg_subagent --> pkg_agent + pkg_subagent --> pkg_brand pkg_subagent --> pkg_llm pkg_subagent --> pkg_scope pkg_subagent --> pkg_session @@ -493,7 +494,7 @@ flowchart TD | [`tool-fs`](../packages/fs/tool-fs) | `fs` | [`fs`](../packages/fs/fs), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-fs-search`](../packages/fs/tool-fs-search) | `fs` | [`bash`](../packages/bash/bash), [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools) | | [`tool-skill`](../packages/skill/tool-skill) | `skill` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`skill`](../packages/skill/skill), [`tools`](../packages/core/tools) | -| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | +| [`subagent`](../packages/subagent/subagent) | `subagent` | [`agent`](../packages/core/agent), [`brand`](../packages/util/brand), [`llm`](../packages/llm/llm), [`scope`](../packages/core/scope), [`session`](../packages/core/session), [`tools`](../packages/core/tools) | | [`tool-web`](../packages/web/tool-web) | `web` | [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`web`](../packages/web/web) | | [`spill-policy`](../packages/spill/spill-policy) | `spill` | [`llm`](../packages/llm/llm), [`retention`](../packages/util/retention), [`session`](../packages/core/session), [`spill`](../packages/spill/spill), [`tools`](../packages/core/tools) | | [`timeout-policy`](../packages/timeout/timeout-policy) | `timeout` | [`llm`](../packages/llm/llm), [`timeout`](../packages/util/timeout), [`tools`](../packages/core/tools) | diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 71640498c9..ed5c0babe9 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -1028,7 +1028,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'SubagentRun', - declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', + declaration: 'export interface SubagentRun {\n readonly id: SessionId;\n readonly localAgent: Agent | undefined;\n readonly result: Promise;\n dispose(): Promise;\n sendMessage?(content: ContentBlock[]): void;\n resume?(content: ContentBlock[]): Promise;\n}', }, { name: 'SubagentStartRequest', diff --git a/packages/hooks/hooks-claude/tests/bridge.spec.ts b/packages/hooks/hooks-claude/tests/bridge.spec.ts index 136ee893c6..7bb4c0b4ea 100644 --- a/packages/hooks/hooks-claude/tests/bridge.spec.ts +++ b/packages/hooks/hooks-claude/tests/bridge.spec.ts @@ -9,6 +9,7 @@ import { defineTool } from '@deepseek-ai/dsh-tools' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import { SubagentRunId } from '@deepseek-ai/dsh-subagent' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -288,8 +289,8 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => // Drive the observe-only lifecycle events directly (no real child needed — the // bridge just listens). No child agent is registered, so SubagentStart's // child lookup yields undefined and it simply runs the hook. - ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) - ctx.emit('subagent/end', { provider: 'inproc', id: SessionId('child-1'), stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-1'), provider: 'inproc', id: SessionId('child-1'), local: false }) + ctx.emit('subagent/end', { runId: SubagentRunId('run-1'), provider: 'inproc', id: SessionId('child-1'), local: false, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'done' }] }) // Both hooks run async (detached .then); poll for their marker files rather // than a fixed sleep that flakes under load. @@ -324,7 +325,7 @@ describe('hooks-claude bridge — SubagentStart / SubagentStop (observe)', () => const { ctx, hooks } = await harnessWithFiber(dir, new MockAdapter([])) const warn = vi.fn() ctx.logger.warn = warn as never - ctx.emit('subagent/start', { provider: 'inproc', id: SessionId('child-1') }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-1'), provider: 'inproc', id: SessionId('child-1'), local: false }) await waitFor(() => existsSync(marker)) const pid = Number(readFileSync(pidFile, 'utf8').trim()) await hooks.dispose() diff --git a/packages/hooks/hooks-claude/tests/coverage-cases.ts b/packages/hooks/hooks-claude/tests/coverage-cases.ts index 9d4004c1ff..0431486d57 100644 --- a/packages/hooks/hooks-claude/tests/coverage-cases.ts +++ b/packages/hooks/hooks-claude/tests/coverage-cases.ts @@ -9,6 +9,7 @@ import { defineTool } from '@deepseek-ai/dsh-tools' import AgentLoop, { type ReactLoopAgent } from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local' +import { SubagentRunId } from '@deepseek-ai/dsh-subagent' import * as HooksClaude from '@deepseek-ai/dsh-hooks-claude' import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts' @@ -231,7 +232,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const injected: string[] = [] const child = { id: SessionId('child-x'), inject: (content: { type: string; text?: string }[]) => { injected.push(content.map(b => b.text ?? '').join('')) }, session: { id: SessionId('child-x'), header: { id: 'child-x' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-x') }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-x'), provider: 'p', id: SessionId('child-x'), local: true }) await waitFor(() => injected.includes('child guidance')) expect(injected).toContain('child guidance') }) @@ -247,7 +248,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const warn = vi.fn(); ctx.logger.warn = warn as never const child = { id: SessionId('child-y'), inject: () => { throw new Error('inject boom') }, session: { id: SessionId('child-y'), header: { id: 'child-y' } } } as unknown as Parameters[0] ctx.agents.register(child) - ctx.emit('subagent/start', { provider: 'p', id: SessionId('child-y') }) + ctx.emit('subagent/start', { runId: SubagentRunId('run-y'), provider: 'p', id: SessionId('child-y'), local: true }) await waitFor(() => warn.mock.calls.some(c => String(c[0]).includes('SubagentStart hook failed'))) expect(warn).toHaveBeenCalledWith(expect.stringContaining('SubagentStart hook failed')) }) @@ -291,7 +292,7 @@ export function defineCoverageCases(group: CoverageGroup): void { const s = sh(d, 'stop.sh', `#!/usr/bin/env bash\ntouch "${marker}"\n`) const path = hooks(d, { SubagentStop: [{ hooks: [{ type: 'command', command: s }] }] }) const ctx = await harness(path, new MockAdapter([])) - ctx.emit('subagent/end', { provider: 'p', id: SessionId('child-z'), stopReason: 'completed' }) + ctx.emit('subagent/end', { runId: SubagentRunId('run-z'), provider: 'p', id: SessionId('child-z'), local: false, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) }) @@ -691,7 +692,7 @@ export function defineCoverageCases(group: CoverageGroup): void { // 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({ 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' }) + ctx.emit('subagent/end', { runId: SubagentRunId('run-stop'), provider: 'inproc', id: childHandle.agent.id, local: true, stopReason: 'completed' }) await waitFor(() => existsSync(marker)) expect(existsSync(marker)).toBe(true) // the marker landed in the CHILD dir diff --git a/packages/subagent/subagent-acp/src/run.ts b/packages/subagent/subagent-acp/src/run.ts index b7b10ecb97..a10a87a940 100644 --- a/packages/subagent/subagent-acp/src/run.ts +++ b/packages/subagent/subagent-acp/src/run.ts @@ -294,6 +294,7 @@ export async function startAcpRun(request: SubagentStartRequest, spec: AcpRunSpe let disposal: Promise | undefined return { id, + localAgent: undefined, result, dispose(): Promise { if (disposal !== undefined) return disposal diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index 018f93051f..c5c85ec232 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -175,6 +175,7 @@ export async function startInProcessRun( return { id: childId, + localAgent: child, result, dispose(): Promise { request.signal.removeEventListener('abort', onAbort) diff --git a/packages/subagent/subagent/README.md b/packages/subagent/subagent/README.md index 45e0976ed7..17edd0e3c7 100644 --- a/packages/subagent/subagent/README.md +++ b/packages/subagent/subagent/README.md @@ -50,9 +50,9 @@ Runtime features are optional methods on `SubagentRun`: `sendMessage?` steers a `SubagentRun.result` resolves to `{ output, structured?, stopReason }`. Child-level failures resolve with a non-`completed` reason; only an infrastructure fault that the seam cannot represent may reject. `dispose()` is idempotent, cancels remaining work, and waits for the child resources to quiesce. -A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, and records `request.parent.session.id` in the child's `parentSession` header. The child may be owned by the parent scope or by a provider/root scope; durable lineage is the transport-neutral local-child relation. Remote providers instead mint a parent-scoped lifecycle id without publishing a local child. +A local run publishes an ordinary child agent/session before `start()` fulfills, returns that shared session id as `SubagentRun.id`, exposes the exact child as `SubagentRun.localAgent`, and records `request.parent.session.id` in the child's `parentSession` header. Remote providers instead mint a parent-scoped lifecycle id and return `localAgent: undefined`. -The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. In-process start observers can resolve the published child through `ctx.agents.get(info.id)`; remote providers need not publish a local agent. +The service emits `subagent/start` only after `start()` has fulfilled. It attaches the result observer before that synchronous notification, so even an already-settled child still produces `subagent/start` before `subagent/end`. The pair shares a service-minted `runId`; its `local` flag is snapshotted from the provider's exact `localAgent`, so observers never infer run identity or locality from reusable provider/session names. Run events are scoped to the delegating parent. Every listener is independently contained: a synchronous throw or rejected returned promise is logged without starving peer listeners or changing the run. diff --git a/packages/subagent/subagent/package.json b/packages/subagent/subagent/package.json index 84d2c963d5..aea05553e4 100644 --- a/packages/subagent/subagent/package.json +++ b/packages/subagent/subagent/package.json @@ -23,6 +23,7 @@ "license": "BSD-3-Clause", "peerDependencies": { "@deepseek-ai/dsh-agent": "^0.0.1", + "@deepseek-ai/dsh-brand": "^0.0.1", "@deepseek-ai/dsh-llm": "^0.0.1", "@deepseek-ai/dsh-scope": "^0.0.1", "@deepseek-ai/dsh-session": "^0.0.1", @@ -31,6 +32,7 @@ }, "devDependencies": { "@deepseek-ai/dsh-agent": "workspace:^", + "@deepseek-ai/dsh-brand": "workspace:^", "@deepseek-ai/dsh-llm": "workspace:^", "@deepseek-ai/dsh-scope": "workspace:^", "@deepseek-ai/dsh-session": "workspace:^", diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 00762cc413..8f3549ac7c 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -28,6 +28,7 @@ * @module @deepseek-ai/dsh-subagent */ +import { randomUUID } from 'node:crypto' import { Context, Service } from 'cordis' import { scopeTarget } from '@deepseek-ai/dsh-scope' import type { Scoped } from '@deepseek-ai/dsh-scope' @@ -43,7 +44,9 @@ import type { SubagentRun, SubagentStartRequest, } from './types.ts' +import { SubagentRunId } from './types.ts' +export { SubagentRunId } from './types.ts' export type { SubagentCapabilities, SubagentProvider, @@ -112,18 +115,26 @@ declare module 'cordis' { /** Observe-only identifying detail for a ready subagent run. */ export interface SubagentRunInfo { + /** Unique identity shared with the paired terminal event. */ + readonly runId: SubagentRunId /** The provider that established the run. */ readonly provider: string /** The child agent's id. */ readonly id: SessionId + /** Whether the provider exposed an exact published in-process child. */ + readonly local: boolean } /** Observe-only outcome detail for a settled subagent run. */ export interface SubagentRunEndInfo { + /** Unique identity shared with the paired start event. */ + readonly runId: SubagentRunId /** The provider that ran it. */ readonly provider: string /** The child agent's id. */ readonly id: SessionId + /** Whether the provider exposed an exact published in-process child. */ + readonly local: boolean /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] /** The child's final assistant output, absent on infrastructure rejection. */ @@ -208,22 +219,28 @@ export class SubagentService extends Service { const parent = request.parent const run = await provider.start(request) + const runId = SubagentRunId(randomUUID()) + const lifecycleIdentity = { + runId, + provider: name, + id: run.id, + local: run.localAgent !== undefined, + } // Attach the terminal observer before dispatching start. Promise reactions // still run after this synchronous start emission, preserving start → end. void run.result.then( (result) => { this.emitLifecycle('subagent/end', { - provider: name, - id: run.id, + ...lifecycleIdentity, stopReason: result.stopReason, lastAssistantMessage: result.output, }, parent) }, () => { - this.emitLifecycle('subagent/end', { provider: name, id: run.id, stopReason: 'error' }, parent) + this.emitLifecycle('subagent/end', { ...lifecycleIdentity, stopReason: 'error' }, parent) }, ) - this.emitLifecycle('subagent/start', { provider: name, id: run.id }, parent) + this.emitLifecycle('subagent/start', lifecycleIdentity, parent) return run } diff --git a/packages/subagent/subagent/src/types.ts b/packages/subagent/subagent/src/types.ts index e5ba8fd84d..1b1645d89b 100644 --- a/packages/subagent/subagent/src/types.ts +++ b/packages/subagent/subagent/src/types.ts @@ -7,10 +7,23 @@ */ import type { Agent, AgentOptions } from '@deepseek-ai/dsh-agent' +import type { Branded } from '@deepseek-ai/dsh-brand' import type { ContentBlock } from '@deepseek-ai/dsh-llm' import type { SessionId } from '@deepseek-ai/dsh-session' import type { StructuredOutputSchema, ToolRestriction } from '@deepseek-ai/dsh-tools' +/** Identifies one accepted subagent run across its lifecycle event pair. */ +export type SubagentRunId = Branded<'SubagentRunId'> + +/** + * Brand a string as a {@link SubagentRunId}. + * @param id - the raw id string (the service mints UUIDs; tests may pass fixtures). + * @returns the same string, branded. + */ +export function SubagentRunId(id: string): SubagentRunId { + return id as SubagentRunId +} + /** * Which START-TIME features a provider supports. Checked by the service before delegating to * {@link SubagentProvider.start}: a request that needs a capability the chosen provider lacks @@ -139,6 +152,12 @@ export interface SubagentRun { * remote provider mints an id unique in the parent namespace. */ readonly id: SessionId + /** + * The exact published in-process child, or `undefined` for a remote run. + * When present, its id is {@link id}; the provider retains no ownership + * implication beyond the run's ordinary {@link dispose} contract. + */ + readonly localAgent: Agent | undefined /** * Resolves with the child's terminal {@link SubagentResult} when the run * settles. Does NOT reject on a child-level failure — a model/transport diff --git a/packages/subagent/subagent/tests/service.spec.ts b/packages/subagent/subagent/tests/service.spec.ts index ad7dbaafff..66008a923b 100644 --- a/packages/subagent/subagent/tests/service.spec.ts +++ b/packages/subagent/subagent/tests/service.spec.ts @@ -48,6 +48,7 @@ class StubProvider implements SubagentProvider { this.startCount += 1 return { id: SessionId(`child:${this.name}:${request.parent.id}`), + localAgent: undefined, result: Promise.resolve(this.outcome), async dispose() {}, } @@ -137,13 +138,14 @@ describe('SubagentService', () => { const parent = fakeParent('delegator') const events: string[] = [] const keys: unknown[] = [] - ctx.on('subagent/start', function () { events.push('start'); keys.push(carrierKeyOf(this)) }) - ctx.on('subagent/end', function () { events.push('end'); keys.push(carrierKeyOf(this)) }) + const runIds: string[] = [] + ctx.on('subagent/start', function (info) { events.push('start'); keys.push(carrierKeyOf(this)); runIds.push(info.runId) }) + ctx.on('subagent/end', function (info) { events.push('end'); keys.push(carrierKeyOf(this)); runIds.push(info.runId) }) const starting = subagents.start('deferred', baseRequest({ parent })) await Promise.resolve() expect(events).toEqual([]) - ready.resolve({ id: SessionId('child'), result: result.promise, async dispose() {} }) + ready.resolve({ id: SessionId('child'), localAgent: undefined, result: result.promise, async dispose() {} }) const run = await starting expect(events).toEqual(['start']) result.resolve({ output: [{ type: 'text', text: 'answer' }], stopReason: 'completed' }) @@ -151,6 +153,21 @@ describe('SubagentService', () => { await Promise.resolve() expect(events).toEqual(['start', 'end']) expect(keys).toEqual([parent, parent]) + expect(runIds[0]).toBe(runIds[1]) + }) + + it('mints distinct lifecycle identities when provider and child ids repeat', async () => { + const { ctx, subagents } = await service() + subagents.registerProvider(new StubProvider('reused')) + const runIds: string[] = [] + ctx.on('subagent/start', info => void runIds.push(info.runId)) + + const first = await subagents.start('reused', baseRequest()) + const second = await subagents.start('reused', baseRequest()) + await Promise.all([first.result, second.result]) + + expect(runIds).toHaveLength(2) + expect(new Set(runIds).size).toBe(2) }) it('emits no run lifecycle when provider startup rejects', async () => { @@ -192,7 +209,7 @@ describe('SubagentService', () => { capabilities: NO_CAPS, inheritsParentContext: false, async start() { - return { id: SessionId('infra-child'), result: failure.promise, async dispose() {} } + return { id: SessionId('infra-child'), localAgent: undefined, result: failure.promise, async dispose() {} } }, }) const failedRun = await subagents.start('infra', baseRequest()) diff --git a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts index 27a603049e..dbb78812d4 100644 --- a/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts +++ b/packages/subagent/tool-subagent/tests/tool-subagent.spec.ts @@ -144,6 +144,7 @@ describe('dsh-tool-subagent', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('weird-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'partial' }], stopReason: 'frobnicated' as never }), dispose: async () => {}, }), @@ -171,6 +172,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -200,6 +202,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('bare-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -327,6 +330,7 @@ describe('dsh-tool-subagent', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('spy-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => void disposed(), }), @@ -349,6 +353,7 @@ describe('dsh-tool-subagent', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('spy-child'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'error' as const }), dispose: async () => void disposed(), }), @@ -380,6 +385,7 @@ describe('dsh-tool-subagent', () => { }, { once: true }) return { id: SessionId('spy-child'), + localAgent: undefined, result, dispose: async () => {}, } @@ -472,6 +478,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture2-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -529,6 +536,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture3-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -558,6 +566,7 @@ describe('dsh-tool-subagent', () => { seen = request return { id: SessionId('capture4-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'ok' }], stopReason: 'completed' as const }), dispose: async () => {}, } @@ -732,6 +741,7 @@ describe('dsh-tool-subagent background mode', () => { }, { once: true }) return { id, + localAgent: undefined, result, dispose: () => Promise.resolve(), } @@ -771,6 +781,7 @@ describe('dsh-tool-subagent background mode', () => { const order: string[] = [] const completed = await settleRun({ id: SessionId('child-1'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text' as const, text: 'ok' }], stopReason: 'completed' as const }), dispose() { order.push('dispose'); return Promise.resolve() }, }) @@ -782,6 +793,7 @@ describe('dsh-tool-subagent background mode', () => { let disposed = false const failed = await settleRun({ id: SessionId('child-2'), + localAgent: undefined, result: Promise.reject(new Error('transport gone')), dispose() { disposed = true; return Promise.resolve() }, }) @@ -790,6 +802,7 @@ describe('dsh-tool-subagent background mode', () => { const disposeFailed = await settleRun({ id: SessionId('child-3'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'completed' }), dispose: () => Promise.reject(new Error('reap failed')), }) @@ -797,6 +810,7 @@ describe('dsh-tool-subagent background mode', () => { const bothFailed = await settleRun({ id: SessionId('child-4'), + localAgent: undefined, result: Promise.reject(new Error('result failed')), dispose: () => Promise.reject(new Error('reap failed')), }) @@ -832,6 +846,7 @@ describe('background preflight failure (no orphaned child, by construction)', () starts += 1 return { id: SessionId('probe-child'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'completed' as const }), dispose: () => Promise.resolve(), } diff --git a/packages/support/subagent-mock/src/index.ts b/packages/support/subagent-mock/src/index.ts index c2e94c521f..4ea30d166a 100644 --- a/packages/support/subagent-mock/src/index.ts +++ b/packages/support/subagent-mock/src/index.ts @@ -69,6 +69,7 @@ class MockSubagentProvider implements SubagentProvider { }) return { id, + localAgent: undefined, result, dispose(): Promise { flags.cancelled = true diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 6d9f007e66..3d19b601c4 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 gets or creates one agent per `sessionId` from the `initialize.provider`/`initialize.model` pair. It classifies subagent completions through live parent ownership or durable parent lineage and retains parent-scoped provider/id counts after child disposal. A registered owner for the provider route wins; an unowned `deepseek` route mounts `dsh-llm-deepseek` using `$DEEPSEEK_API_KEY` and `$DEEPSEEK_BASE_URL`, while any other unowned provider fails initialization. Persistence, tools, and other adapters come from the surrounding `cordis.yml`. +`inject: ['agents']`. The server gets or creates one agent per `sessionId` from the `initialize.provider`/`initialize.model` pair. It forwards subagent completions only when the lifecycle payload's `local` flag was snapshotted from the provider's exact in-process child; reusable provider names, child ids, and durable lineage never establish locality. A registered owner for the provider route wins; an unowned `deepseek` route mounts `dsh-llm-deepseek` using `$DEEPSEEK_API_KEY` and `$DEEPSEEK_BASE_URL`, while any other unowned provider fails initialization. Persistence, tools, and other adapters come from the surrounding `cordis.yml`. ## Config diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 91cc49571a..5246795a31 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -19,7 +19,7 @@ import type { Agent, AgentHandle } from '@deepseek-ai/dsh-agent' import { carrierKeyOf, type Scoped } from '@deepseek-ai/dsh-scope' import { SessionId, type TurnEndReason } from '@deepseek-ai/dsh-session' import type SubagentService from '@deepseek-ai/dsh-subagent' -import type { SubagentRunEndInfo, SubagentRunInfo } from '@deepseek-ai/dsh-subagent' +import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' @@ -68,15 +68,6 @@ function subagentParentOf(carrier: Scoped): Agent { return carrierKeyOf(carrier) as Agent } -/** Whether the live id names a local child related to this exact delegating parent. */ -function isLocalChild(ctx: Context, id: SessionId, parent: Agent): boolean { - const child = ctx.agents.get(id) - return child !== undefined && ( - ctx.agents.isOwnedBy(id, parent) - || child.session.header.parentSession === parent.session.id - ) -} - /** * The SDK server over a booted harness context. Constructing it subscribes to * session and subagent lifecycle events, forwarding durable session @@ -92,7 +83,6 @@ export class HarnessSdkServer { private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() - private readonly localRuns = new Map>>() private readonly disposers: (() => void)[] = [] private shutdownTask: Promise> | undefined private shuttingDown = false @@ -116,36 +106,12 @@ export class HarnessSdkServer { childSessionId: String(session.id), }) })) - // In-process providers publish the child before start. Count starts related - // by exact runtime ownership or durable parent lineage so provider-owned - // roots remain local, completions survive child disposal, and reused ids - // need no settlement-order assumption. - const localRuns = this.localRuns - this.disposers.push(ctx.on('subagent/start', function (this: Scoped, info: SubagentRunInfo) { - const parent = subagentParentOf(this) - if (!isLocalChild(ctx, info.id, parent)) return - const providerRuns = localRuns.get(info.provider) ?? new Map>() - const parentRuns = providerRuns.get(info.id) ?? new Map() - parentRuns.set(parent, (parentRuns.get(parent) ?? 0) + 1) - providerRuns.set(info.id, parentRuns) - localRuns.set(info.provider, providerRuns) - })) this.disposers.push(ctx.on('subagent/end', function (this: Scoped, info: SubagentRunEndInfo) { const parent = subagentParentOf(this) - const providerRuns = localRuns.get(info.provider) - const parentRuns = providerRuns?.get(info.id) - const pendingCount = parentRuns?.get(parent) - if (pendingCount !== undefined) { - if (pendingCount === 1) parentRuns?.delete(parent) - else parentRuns?.set(parent, pendingCount - 1) - if (parentRuns?.size === 0) providerRuns?.delete(info.id) - if (providerRuns?.size === 0) localRuns.delete(info.provider) - } - // This protocol reports LOCAL child sessions. A lineage-bearing child - // has the session/created-driven start notification above. A remote run - // has neither a cached local start nor a live child related to this - // parent; an unrelated local agent with the same id never makes it local. - if (pendingCount === undefined && !isLocalChild(ctx, info.id, parent)) return + // This protocol reports only in-process child sessions. The service + // snapshots the provider's exact run provenance through child disposal; + // matching ids or parent lineage alone never establishes locality. + if (!info.local) return transport.notify('subagent.finished', { provider: info.provider, agentId: String(info.id), @@ -223,7 +189,6 @@ export class HarnessSdkServer { this.sessionCreations.clear() const records = [...this.sessions.values()] this.sessions.clear() - this.localRuns.clear() const failures: unknown[] = [] while (this.disposers.length > 0) { try { diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index ed4dfbb9db..54727f571b 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -71,6 +71,7 @@ try { start() { return Promise.resolve({ id: child.agent.id, + localAgent: child.agent, result: result.promise, dispose() { return Promise.resolve(); }, }); diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 3fe73c904e..5b9259dd85 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -70,7 +70,7 @@ async function makeHarness(storageDir: string) { async function settleSubagent( ctx: Context, parent: Agent, - info: SubagentRunEndInfo, + info: Omit & { localAgent: Agent | undefined }, beforeSettle?: () => Promise, ): Promise { const result = Promise.withResolvers() @@ -81,6 +81,7 @@ async function settleSubagent( async start() { return { id: info.id, + localAgent: info.localAgent, result: result.promise, dispose: () => Promise.resolve(), } @@ -294,12 +295,14 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('child-session'), + localAgent: handle.agent, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'child done' }], }, () => handle.dispose()) await settleSubagent(ctx, parentHandle.agent, { provider: 'spawn', id: SessionId('parentless-child-session'), + localAgent: parentlessHandle.agent, stopReason: 'error', }, () => parentlessHandle.dispose()) @@ -335,7 +338,7 @@ describe('HarnessSdkServer', () => { } }) - it('ignores a remote run id that collides with an unrelated local agent', async () => { + it('ignores a remote run id that collides with a local child of the same parent', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-remote-collision-')) const ctx = await makeHarness(storageDir) try { @@ -346,24 +349,26 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir }, agentOptions: { model: 'deepseek' }, }) - const unrelatedHandle = await ctx.agents.create({ + const collidingChild = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('remote-run-id'), - meta: { cwd: storageDir }, + meta: { cwd: storageDir, parentSession: SessionId('collision-parent') }, agentOptions: { model: 'deepseek' }, }) await settleSubagent(ctx, parentHandle.agent, { provider: 'remote', id: SessionId('remote-run-id'), + localAgent: undefined, stopReason: 'completed', lastAssistantMessage: [], - }, () => unrelatedHandle.dispose()) + }) expect(transport.notifications.some(notification => notification.method === 'subagent.finished' && notification.params?.agentId === 'remote-run-id', )).toBe(false) + await collidingChild.dispose() await parentHandle.dispose() await server.shutdown() } finally { @@ -392,12 +397,14 @@ describe('HarnessSdkServer', () => { await settleSubagent(ctx, parentHandle.agent, { provider: 'continuation', id: SessionId('continuation-child'), + localAgent: childHandle.agent, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'first' }], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'continuation', id: SessionId('continuation-child'), + localAgent: childHandle.agent, stopReason: 'completed', lastAssistantMessage: [{ type: 'text', text: 'second' }], }, () => childHandle.dispose()) @@ -436,6 +443,7 @@ describe('HarnessSdkServer', () => { const replacement = Promise.withResolvers() const results = [first.promise, sameLifetime.promise, replacement.promise] let starts = 0 + let currentLocalAgent = oldChild.agent const disposeProvider = ctx.subagents.registerProvider({ name: 'reused', capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, @@ -444,7 +452,7 @@ describe('HarnessSdkServer', () => { const result = results[starts] starts += 1 if (result === undefined) throw new Error('unexpected fourth reused-id run') - return Promise.resolve({ id: SessionId('reused-child'), result, dispose: () => Promise.resolve() }) + return Promise.resolve({ id: SessionId('reused-child'), localAgent: currentLocalAgent, result, dispose: () => Promise.resolve() }) }, }) @@ -471,6 +479,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('new-parent') }, agentOptions: { model: 'deepseek' }, }) + currentLocalAgent = newChild.agent const secondRun = await ctx.subagents.start('reused', { parent: newParent.agent, prompt: [], @@ -512,7 +521,99 @@ describe('HarnessSdkServer', () => { } }) - it('falls back to live lineage and ignores runs without a local child session', async () => { + it('keeps locality bound to the accepted run across provider re-registration', async () => { + const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-provider-reuse-')) + const ctx = await makeHarness(storageDir) + try { + const transport = new FakeTransport() + const server = new HarnessSdkServer(ctx, transport) + const parent = await ctx.agents.create({ + sessionId: SessionId('provider-reuse-parent'), + meta: { cwd: storageDir }, + agentOptions: { model: 'deepseek' }, + }) + const child = await parent.agent.ctx.agents.create({ + sessionId: SessionId('provider-reuse-child'), + meta: { cwd: storageDir, parentSession: SessionId('provider-reuse-parent') }, + agentOptions: { model: 'deepseek' }, + }) + const localResult = Promise.withResolvers() + const remoteResult = Promise.withResolvers() + const unregisterLocal = ctx.subagents.registerProvider({ + name: 'reused-provider', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start: () => Promise.resolve({ + id: SessionId('provider-reuse-child'), + localAgent: child.agent, + result: localResult.promise, + dispose: () => Promise.resolve(), + }), + }) + const localRun = await ctx.subagents.start('reused-provider', { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }) + unregisterLocal() + + const unregisterRemote = ctx.subagents.registerProvider({ + name: 'reused-provider', + capabilities: { outputSchema: false, depthLimit: false, toolFilter: false, persona: false }, + inheritsParentContext: false, + start: () => Promise.resolve({ + id: SessionId('provider-reuse-child'), + localAgent: undefined, + result: remoteResult.promise, + dispose: () => Promise.resolve(), + }), + }) + const remoteRun = await ctx.subagents.start('reused-provider', { + parent: parent.agent, + prompt: [], + signal: new AbortController().signal, + }) + + remoteResult.resolve({ output: [{ type: 'text', text: 'remote' }], stopReason: 'completed' }) + await remoteRun.result + await Promise.resolve() + expect(transport.notifications.some(notification => + notification.method === 'subagent.finished' + && notification.params?.lastAssistantMessage !== undefined, + )).toBe(false) + + await child.dispose() + localResult.resolve({ output: [{ type: 'text', text: 'local' }], stopReason: 'completed' }) + await localRun.result + await Promise.resolve() + expect(transport.notifications.filter(notification => + notification.method === 'subagent.finished' + && notification.params?.childSessionId === 'provider-reuse-child', + )).toEqual([{ + method: 'subagent.finished', + params: { + provider: 'reused-provider', + agentId: 'provider-reuse-child', + parentSessionId: 'provider-reuse-parent', + childSessionId: 'provider-reuse-child', + status: 'ok', + stopReason: 'completed', + lastAssistantMessage: [{ type: 'text', text: 'local' }], + }, + }]) + + await localRun.dispose() + await remoteRun.dispose() + unregisterRemote() + await parent.dispose() + await server.shutdown() + } finally { + await ctx.fiber.dispose() + await rm(storageDir, { recursive: true, force: true }) + } + }) + + it('uses explicit local provenance when start was missed and ignores remote runs', async () => { const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-subagent-fallback-')) const ctx = await makeHarness(storageDir) let parentHandle: AgentHandle | undefined @@ -529,6 +630,7 @@ describe('HarnessSdkServer', () => { meta: { cwd: storageDir, parentSession: SessionId('fallback-parent') }, agentOptions: { provider: 'deepseek', model: 'deepseek' }, }) + const fallbackChild = handle.agent failedHandle = await parentHandle.agent.ctx.agents.create({ sessionId: SessionId('failed-child-session'), meta: { cwd: storageDir }, @@ -541,12 +643,13 @@ describe('HarnessSdkServer', () => { inheritsParentContext: true, start: () => Promise.resolve({ id: SessionId('fallback-child-session'), + localAgent: fallbackChild, result: missedStartResult.promise, dispose: () => Promise.resolve(), }), }) - // Start before the server subscribes, so the terminal fallback must use - // the still-live registry entry rather than a cached start record. + // Start before the server subscribes. The terminal payload still carries + // this run's exact local child without reconstructing it from ids. const missedStartRun = await ctx.subagents.start('fork', { parent: parentHandle.agent, prompt: [], @@ -560,22 +663,25 @@ describe('HarnessSdkServer', () => { await Promise.resolve() await missedStartRun.dispose() disposeMissedStartProvider() - // The server also missed this agent's creation, but observes the start; - // recover its lineage from the still-live registry entry. + // The server also missed this agent's creation but sees the exact child + // on the run lifecycle payload. await settleSubagent(ctx, parentHandle.agent, { provider: 'fork-live-fallback', id: SessionId('fallback-child-session'), + localAgent: fallbackChild, stopReason: 'completed', lastAssistantMessage: [], }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', id: SessionId('failed-child-session'), + localAgent: failedHandle.agent, stopReason: 'error', }) await settleSubagent(ctx, parentHandle.agent, { provider: 'fork', id: SessionId('missing-child-agent'), + localAgent: undefined, stopReason: 'error', }) @@ -800,6 +906,6 @@ describe('HarnessSdkServer', () => { const server = new HarnessSdkServer(ctx, new FakeTransport()) await expect(server.shutdown()).rejects.toBe(listenerFailure) - expect(on).toHaveBeenCalledTimes(4) + expect(on).toHaveBeenCalledTimes(3) }) }) diff --git a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts index 5905161e6a..2f52cd7b6b 100644 --- a/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts +++ b/packages/workflow/workflow-workerthread/tests/workflow-workerthread.spec.ts @@ -105,6 +105,7 @@ class StubProvider implements SubagentProvider { if (request.signal.aborted) throw new Error('child start aborted before publication') return { id: SessionId(`stub-child-${index}`), + localAgent: undefined, result: terminal.promise, dispose: () => { controlled.disposeCalls += 1 @@ -362,6 +363,7 @@ describe('dsh-workflow-workerthread', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('reject-child'), + localAgent: undefined, result: Promise.reject(new Error('backend exploded')), dispose: () => Promise.resolve(), }), @@ -396,6 +398,7 @@ describe('dsh-workflow-workerthread', () => { } as unknown as SubagentResult const start = vi.spyOn(ctx.subagents, 'start').mockResolvedValue({ id: SessionId('raw-invalid-child'), + localAgent: undefined, result: Promise.resolve(invalid), dispose: () => Promise.resolve(), }) @@ -419,6 +422,7 @@ describe('dsh-workflow-workerthread', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('bad-dispose-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, dispose: () => { throw new Error('dispose exploded') }, @@ -440,6 +444,7 @@ describe('dsh-workflow-workerthread', () => { inheritsParentContext: false, start: async () => ({ id: SessionId('trap-child'), + localAgent: undefined, result: Promise.resolve({ output: [{ type: 'text', text: 'fine' }], stopReason: 'completed' }), cancel: () => { /* settled already */ }, // The rejection VALUE's own coercion throws: a warn built with bare @@ -767,6 +772,7 @@ describe('dsh-workflow-workerthread', () => { }, { once: true }) return { id: SessionId('signal-only-child'), + localAgent: undefined, result, dispose: () => Promise.resolve(), } @@ -1088,6 +1094,7 @@ describe('dsh-workflow-workerthread', () => { ready.resolve({ id: SessionId('late-ready-child'), + localAgent: undefined, result: Promise.resolve({ output: [], stopReason: 'aborted' }), dispose: () => { disposeCalls += 1 @@ -1124,6 +1131,7 @@ describe('dsh-workflow-workerthread', () => { }, { once: true }) return { id: SessionId('doomed-child'), + localAgent: undefined, result: new Promise(() => { /* never settles; the reap is the teardown */ }), dispose: () => Promise.reject(new Error('dispose exploded during reap')), } diff --git a/pnpm-lock.yaml b/pnpm-lock.yaml index d7b3ab2b95..47d998fedc 100644 --- a/pnpm-lock.yaml +++ b/pnpm-lock.yaml @@ -1441,6 +1441,9 @@ importers: '@deepseek-ai/dsh-agent': specifier: workspace:^ version: link:../../core/agent + '@deepseek-ai/dsh-brand': + specifier: workspace:^ + version: link:../../util/brand '@deepseek-ai/dsh-llm': specifier: workspace:^ version: link:../../llm/llm diff --git a/website/zh-CN/api/harness/events.md b/website/zh-CN/api/harness/events.md index aafaf28484..1301a6a508 100644 --- a/website/zh-CN/api/harness/events.md +++ b/website/zh-CN/api/harness/events.md @@ -383,7 +383,7 @@ A ready child settled. Scope-filtered dispatch uses the same delegating parent c - `info` — the run identity and terminal outcome. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L109) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L112) ### subagent/provider-added @@ -397,7 +397,7 @@ A provider became resolvable in the registry. - `provider` — the registered provider. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L83) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L86) ### subagent/provider-removed @@ -411,7 +411,7 @@ A provider left the registry. Accepted runs remain holder-owned. - `name` — the provider name that no longer resolves. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L89) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L92) ### subagent/start @@ -425,7 +425,7 @@ A provider established a ready child. For in-process providers, `ctx.agents.get( - `info` — the provider and ready child identity. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L100) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L103) ## system-prompt/* diff --git a/website/zh-CN/api/harness/subagents.md b/website/zh-CN/api/harness/subagents.md index 54fe5aa76e..52632e820d 100644 --- a/website/zh-CN/api/harness/subagents.md +++ b/website/zh-CN/api/harness/subagents.md @@ -6,7 +6,7 @@ Named provider registry and capability-checked start surface. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L142) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L153) ### ctx.subagents.registerProvider(provider) @@ -20,7 +20,7 @@ Register a provider under its name. Registration is effect-scoped and HMR safe; **Returns** the exact Cordis effect disposer. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L156) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L167) ### ctx.subagents.getProvider(name) @@ -34,7 +34,7 @@ Look up a provider by name. **Returns** the provider, or undefined when absent. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L179) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L190) ### ctx.subagents.list() @@ -46,7 +46,7 @@ List registered provider names in insertion order. **Returns** the registered names. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L187) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L198) ### ctx.subagents.start(name, request) @@ -61,4 +61,4 @@ Establish a ready child on the named provider. Capability and semantic checks ru **Returns** the ready holder-owned run. -[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L200) +[Source](https://github.com/deepseek-harness/deepseek-harness/blob/master/packages/subagent/subagent/src/index.ts#L211) From 1febeb8428d1c1dd4d24f812567b792d3d3f79ea Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sat, 18 Jul 2026 14:26:48 +0800 Subject: [PATCH 31/33] test(jsonrpc): configure built scope probe --- packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts index 54727f571b..051b0eef20 100644 --- a/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts +++ b/packages/ui/jsonrpc/tests/built-scope-carrier.e2e.ts @@ -43,7 +43,7 @@ const [ const storageRoot = await mkdtemp(join(tmpdir(), "jsonrpc-built-scope-")); const ctx = new Context(); try { - await ctx.plugin(agentCore); + await ctx.plugin(agentCore, { workspaceContext: false }); await ctx.plugin(SubagentService); await ctx.plugin(SessionPersistenceJsonl, { root: storageRoot }); await new Promise((ready) => setTimeout(ready, 50)); From 3d19252e9643df4875b43669e7e22a32865ba857 Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 02:03:35 +0800 Subject: [PATCH 32/33] test: refresh parallel tool call permission snapshot --- .../tests/snapshots/parallel-tool-calls/stdout.golden.jsonl | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl b/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl index 6d7bc199e8..8680db3d30 100644 --- a/examples/acp-agent/tests/snapshots/parallel-tool-calls/stdout.golden.jsonl +++ b/examples/acp-agent/tests/snapshots/parallel-tool-calls/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":"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":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":"The session permission preset: each choice bundles a sandbox mode and an approval policy.","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_read_a","title":"Read a.txt","kind":"read","status":"in_progress","locations":[{"path":"a.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call","toolCallId":"call_read_b","title":"Read b.txt","kind":"read","status":"in_progress","locations":[{"path":"b.txt","line":1}]}}} {"jsonrpc":"2.0","method":"session/update","params":{"sessionId":"{{sessionId}}","update":{"sessionUpdate":"tool_call_update","toolCallId":"call_read_a","status":"completed","content":[{"type":"content","content":{"type":"text","text":"{{cwd}}/a.txt\nfile\n\n1: alpha\n\n(End of file - total 1 lines)\n"}}]}}} From 9f1a69366bb4644f781df1508cd2879d205f343e Mon Sep 17 00:00:00 2001 From: Tianyi Cui <53024+tianyicui@users.noreply.github.com> Date: Sun, 19 Jul 2026 02:18:59 +0800 Subject: [PATCH 33/33] docs: tighten identity bridge prose --- docs/config-catalog.md | 10 +- .../feature/2026-07-06-approval-seam.md | 32 +-- .../2026-06-20-unify-agent-and-session-id.md | 2 +- packages/subagent/subagent/src/index.ts | 4 +- packages/ui/acp/src/index.ts | 267 +++--------------- packages/ui/jsonrpc/README.md | 12 +- packages/ui/jsonrpc/src/server.ts | 59 ++-- 7 files changed, 86 insertions(+), 300 deletions(-) diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 3b3e034601..c8e1a04036 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -20,20 +20,14 @@ export interface AcpConfig { provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string - /** - * Transport stream override. Production omits this (the plugin wires - * `process.stdin`/`process.stdout` via `ndJsonStream`). Tests inject an - * in-memory `Stream` (e.g. an `ndJsonStream` over a `Duplex` pair) to drive - * the bridge without a subprocess. Not part of the schemastery `Config` — - * it is a runtime-only seam, never set from a `cordis.yml`. - */ + /** Runtime-only transport override; production uses stdio. */ stream?: Stream } ``` Depends on: `Stream` (`@agentclientprotocol/sdk`) -Source: [`packages/ui/acp/src/index.ts:247`](../packages/ui/acp/src/index.ts) +Source: [`packages/ui/acp/src/index.ts:206`](../packages/ui/acp/src/index.ts) ## `@deepseek-ai/dsh-acp-demo` diff --git a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md index 0945228593..81e60a726f 100644 --- a/docs/rfc/implemented/feature/2026-07-06-approval-seam.md +++ b/docs/rfc/implemented/feature/2026-07-06-approval-seam.md @@ -49,39 +49,39 @@ The `escalation-rejected` twin ends in `{"outcome": "rejected"}` instead: nothin #### The seam: mechanism and policy split -After request validation and a successful `approval/asked` append, the answerer phase always resolves to a closed `ApprovalOutcome` — `allowed-once` / `rejected` / `cancelled` / `unavailable`. `ApprovalRequest` is a readonly same-process contract, so the service borrows its routing identity and cancellation signal instead of copying the record or capturing a parallel callback bundle. It dispatches the `approval/request` waterfall, races the request signal (abort settles `cancelled`; a late answer is discarded, never double-audited), contains a throwing answerer as `unavailable`, normalizes a rogue non-vocabulary return to `unavailable`, and lands the log-only audit pair `approval/asked`/`approval/decided` (paired by the branded `ApprovalRequestId`) on the request agent's session log. Request acceptance and either pre-commit audit append may still reject; returning a decision that could not be logged would violate the pair. Session owns post-commit observer containment, so a callback failure cannot turn an authoritative audit append into a rejected request or suppress the matching event. Grants are one-shot by definition: `allowed-once` authorizes the single asked-about action, never a class of future ones, and the service stores nothing between requests. `request()` also throws before appending anything when the agent's session has no open turn — the audit pair must be turn-enclosed, the turn being the durable log's commit/replay boundary (a bare event between turns is dropped as crash tail on reload); every ask path runs mid-turn already, and idle asks are a deferred design. +After validation and a successful `approval/asked` append, the service resolves the `approval/request` waterfall to `allowed-once`, `rejected`, `cancelled`, or `unavailable`. It borrows the readonly request identity and signal, treats abort as `cancelled`, contains answerer failures and invalid returns as `unavailable`, discards late answers, and appends the paired `approval/decided` event. Pre-commit audit failures reject; post-append observer failures cannot undo an authoritative event. `allowed-once` authorizes only the asked action, and `request()` rejects outside an open turn so the audit pair remains inside the durable commit boundary. -Answerers are the policy, and they are `approval/request` waterfall listeners. The waterfall buys exactly what the seam needs: with zero listeners the dispatch falls through to the caller-supplied default — `unavailable`, so fail-closed needs no configuration and no code in any deployment; a listener that recognizes the request's agent answers by returning an outcome without calling `next()` (the decision slot is single-occupancy, first answer wins — the same documented semantics as the `fs/write-intent` gate); a listener that does not recognize the agent MUST delegate via `next()` so another answerer or the default gets the question; and listeners dispose with their owning fiber, so an unloaded UI plugin degrades the next ask to `unavailable` instead of leaving a dangling channel. Registration order across sibling plugins is not load-order deterministic (the loader starts siblings concurrently), so a deployment composes ONE terminal answerer and reserves `prepend` listeners for decide-or-delegate gates. +Answerers are `approval/request` waterfall listeners. Zero listeners fall through to `unavailable`; a recognizing listener occupies the first-wins decision slot, while an unrecognized agent must delegate with `next()`. Listeners dispose with their fibers, so an unloaded channel fails closed. Because sibling registration order is not deterministic, a deployment composes one terminal answerer and reserves `prepend` for decide-or-delegate gates. -`ApprovalRequest` carries the asking `agent` (routes the question; receives the audit events), the `toolName`, the optional exact `callId`, the asker's human-readable `reason`, and the optional `signal`. The caller retains ownership and honors the readonly contract for the duration of `request()`. The vocabulary is deliberately self-contained — it names the tool-call by the `CallId` brand from `dsh-llm` and never imports `dsh-tools` — because `dsh-tools` depends on `dsh-user-approval` (the ask routing) and a `ToolCallView` import would close a package cycle. It deliberately does NOT carry tool arguments: a UI answerer attaches the prompt to the already-streamed tool call via `callId` instead of re-rendering the call. +`ApprovalRequest` carries the asking `agent`, `toolName`, optional exact `callId`, human-readable `reason`, and optional `signal`. It uses the `CallId` brand without importing `dsh-tools`, which depends on this seam. Tool arguments stay on the already-streamed call that a UI references by `callId`. #### Ask routing in dsh-tools -`ToolRegistry.execute()` resolves an `ask` decision through the seam before the shared deny path: `allowed-once` proceeds to guards and dispatch, and the three non-grants deny with distinct reasons — "the user rejected…", "…was cancelled", "…no approval channel is available" — so the model can tell a human "no" from an absent channel. The seam is consumed opportunistically (`ctx.get('approval')`, the `tool-bash`/`agent-loop` pattern), not statically injected: with no ApprovalService, or after one unmounts, the next ask fails closed without gating the registry's fiber. An agent-less execution also fails closed — without an agent there is no session to audit to and no UI to route to. +`ToolRegistry.execute()` resolves `ask` before dispatch: `allowed-once` proceeds, while rejection, cancellation, and channel absence produce distinct deny reasons. Opportunistic `ctx.get('approval')` consumption lets an absent or unmounted service fail closed without gating the registry fiber. Agent-less execution also fails closed because it has neither an audit session nor a UI owner. #### The per-session policy tier -The seam also owns the session-scoped approval policy — the approval knob of the two-knob per-session switching design ([the sandbox RFC](2026-07-06-sandbox.md) § Per-session modes is the pattern's home: one log-only event per knob, a pure fold, THE write path, ACP config-option advertisement, and turn-anchoring). `ApprovalPolicy` is `'ask' | 'never'`, and `effectiveApprovalPolicy(events) ?? Config.policy` (default `'ask'`) decides every request BEFORE any interactive answerer: the service resolves a `'never'` session to `'rejected'` INSIDE `request()`, before dispatching the waterfall at all — no listener registration, including a later `prepend`, can sit ahead of it — while `'ask'` dispatches unchanged and falls through to fail-closed `'unavailable'` when nobody answers. Visibility follows the switching design's two layers with one asymmetry: the prompt section states ONLY `'never'` (deterministic, availability-independent — "you will be prompted" would overclaim in a composition with no answerer, and absence under a logged header is exactly how the narrator reads `'ask'` back), the narrator injects at most one coalesced notice per switch, and the audit pair still lands on every ask, including the policy's auto-rejections. +The seam also owns the session-scoped `'ask' | 'never'` policy described by [the sandbox RFC](2026-07-06-sandbox.md). Effective policy is folded from logged switches over the deployment default. `'never'` resolves to `rejected` inside `request()` before any answerer can run; `'ask'` dispatches and otherwise falls through to `unavailable`. The prompt states only deterministic `'never'`, switch narration is coalesced, and every request still records the audit pair. #### The ACP answerer -The bridge registers the first real answerer: it resolves the owning session through `ownedRecord`, requiring the forward session-map record at `agent.session.id` to own that exact agent object, issues `session/request_permission` with the request's `callId` as the `toolCall` reference and the one-shot options `allow_once`/`reject_once`, and maps the response — selected `allow-once` → `allowed-once`, any other selection → `rejected` (an unknown optionId from a non-conforming client never grants), client `cancelled` → `cancelled`. A request for a foreign agent — or one without a `callId`, since the protocol prompt must attach to a tool call — delegates via `next()`. A rejected RPC (client gone mid-prompt) propagates to the service, which contains it as `unavailable`. Whether a call ASKS at all is policy — a hook or `tools/pre-execute` plugin returning `ask` — never the bridge's own judgment. +The ACP bridge answers only for an exact agent object owned by its forward session map. It attaches `session/request_permission` to the existing `callId`, advertises one-shot allow/reject options, maps cancellation separately, and never grants an unknown option. Foreign or call-less requests delegate; a failed client RPC becomes `unavailable`. Hooks and `tools/pre-execute` decide whether a call asks at all. The answerer routes through the bridge's exact-agent ownership check described by [the ACP support RFC](../../implemented/feature/2026-06-14-acp-agent-client-protocol.md), implementing the per-session permission ownership required by [the multi-session RFC](../../implemented/feature/2026-06-14-acp-multi-session.md). #### Audit, and what the model sees -`approval/asked` / `approval/decided` are log-only session events (the `hook/invoked`/`hook/result` precedent): durable, replayable, never in the model transcript. The model's entire view of an approval is the tool result the asker derives from the outcome — reconstructability holds because that result is an ordinary logged `tool/result`. Successful request completion commits one `decided` per `asked`, whatever the outcome, including an already-aborted signal (settled `cancelled` without dispatching), a contained answerer failure, or a session observer that throws after either event is already appended. An idle request appends neither event; a pre-commit append failure rejects, and failure of the second append can leave the already-committed `asked` without a `decided`. +`approval/asked` and `approval/decided` are durable log-only events; the model sees only the ordinary tool result derived from the outcome. Successful completion commits one `decided` per `asked`, including cancellation and contained answerer failure. Idle requests append neither event; a pre-commit failure rejects, while failure of the second append can leave an already-committed `asked` unmatched. #### Entities and dependencies -One package, no cycles: `dsh-user-approval` peers on `cordis`, `dsh-session` (event-map merge + append), `dsh-agent` (the `Agent` type), `dsh-llm` (`CallId`, via `dsh-brand`). `dsh-tools` and `dsh-acp` each peer on it; the escalation phase's asker lives in `dsh-tool-bash` (see [the sandbox RFC](2026-07-06-sandbox.md) § Escalation), so the sandbox family keeps its ZERO-edge relation (the executor contributes the per-call override mechanism, and transport seams never ask humans questions). The seam is one package, not the capability-seam three: the service body (dispatch + audit) has no replaceable implementation — the replaceable part is the answerer listeners, and those live with their owners (the bridge; future terminal UIs; test scripts). `@cordisjs/plugin-capability` stays orthogonal (a static grant registry answers "is this already authorized", not "ask the user now"), and `subagent-acp`'s child-side `permission` auto-answer is untouched — routing a child's approvals to the parent session is deferred (§ Deferred). +`dsh-user-approval` depends on Cordis plus the session, agent, and branded-call contracts; `dsh-tools` and `dsh-acp` consume it. The sandbox executor stays independent because `dsh-tool-bash` owns escalation requests. The fixed dispatch-and-audit service remains one package; replaceable answerers live with their channel owners. Static capability grants and `subagent-acp` child-side permission answers remain separate concerns. ### Testing -Unit tier: the service's outcome branches (fail-closed default, first-wins slot, delegation, containment, rogue-value normalization, abort-before and abort-during with late-answer discard, fresh ids, fiber-disposal degradation), scoped routing, post-append observer throws on both audit events, and the policy tier (both values × dispatch/decide, a `'never'` decision unbypassable even by an answerer prepended AFTER the service, audit pair intact) in `dsh-user-approval`; the ask routing matrix (grant dispatches; three non-grant reasons pinned verbatim; unmounted and agent-less degrades; the registry's own exhaustiveness backstop against a non-conforming stand-in) in `dsh-tools`; the answerer (wire shape of the prompt, outcome mapping, unknown-option conservatism, foreign-agent and call-less delegation) driven through a real bridge + scripted client in `dsh-acp`. +Unit tests pin outcomes, first-wins delegation, containment, cancellation, scoped routing, audit pairing, the unbypassable `'never'` policy, tool deny reasons, and ACP ownership/outcome mapping through a real scripted bridge. -Snapshot tier: the harness accepts scripted permission answers (`permissionAnswers` in a scenario's `input.json`, consumed FIFO; an unscripted prompt answers `cancelled`, fail closed). The seam's wire is recorded end to end in the sandbox example's suite: both escalation branches drive `session/request_permission` through this seam over scripted answers (grant and rejection), and the recorded `mode-switching` scenario pins the `'never'` prompt sentence and the policy-switch notice ([the sandbox RFC](2026-07-06-sandbox.md) § Testing). +Snapshots record allowed and rejected sandbox escalation through `session/request_permission`, plus the `'never'` prompt and policy-switch notice. Unscripted permission prompts cancel and fail closed. ## Deferred @@ -102,12 +102,10 @@ Snapshot tier: the harness accepts scripted permission answers (`permissionAnswe The implemented contract is pinned by the suites in Testing: -- With an ApprovalService and an answerer composed, a hook's `ask` reaches a human and `allowed-once` dispatches the tool; every other outcome denies with its distinct reason. -- A `'never'` session auto-rejects every ask without prompting anyone, states the policy in its prompt, and narrates switches (the shared switching mechanics are pinned in [the sandbox RFC](2026-07-06-sandbox.md)). -- Every unanswerable path fails closed to `unavailable`: no service, no listener, a foreign or agent-less request, a throwing answerer, a rogue return value, or a dead client connection. -- Every successful `request()` routes through its readonly agent identity and lands exactly one `approval/asked`/`approval/decided` pair on that agent's log, replayable and invisible to the model transcript; idle and pre-commit failures reject, while post-append observer failures cannot split the pair. -- Prompts route per-session through the bridge's ownership map; one session's prompt can never reach another session's editor. -- A deployment with no ApprovalService emits no approval prompt or approval audit events and denies every `ask` request. +- `allowed-once` dispatches one action; every other outcome denies with a distinct reason, and `'never'` rejects before prompting. +- Missing, foreign, agent-less, throwing, invalid, and disconnected answer paths fail closed. +- Successful requests route by exact agent ownership and append one replayable, model-invisible audit pair; idle and pre-commit failures reject. +- ACP ownership keeps prompts inside their session, while a deployment without the service emits no prompt or audit events. Costs and accepted limits: @@ -117,8 +115,6 @@ Costs and accepted limits: ## FAQ -Behavioral and usage questions only — every "why not X?" design question lives in [Alternatives considered](#alternatives-considered), whose job is exactly that. - - **What happens in a deployment with no answerer at all (headless, CI)?** Every ask falls through the empty waterfall to `unavailable` and the tool call denies with the "no approval channel is available" reason. Fail-closed is the zero-listener default, not a configuration. - **Can a grant persist — "always allow this"?** No. `allowed-once` authorizes the single asked-about action and the service stores nothing between requests; `allow_always` is deliberately not advertised until grant storage is designed (§ Deferred). - **What does the model see of an approval?** Only the tool result the asker derives from the outcome — the audit pair never enters the transcript. The three non-grant reasons are distinct, so the model can tell a human "no" from a dismissed prompt from a missing channel. diff --git a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md index 896e019779..9084befad5 100644 --- a/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md +++ b/docs/rfc/implemented/simplification/2026-06-20-unify-agent-and-session-id.md @@ -28,7 +28,7 @@ The config-driven path keeps `agents[].id` as a stable configuration label, not - Agent create/resume and subagent creation carry one identity, and `Session` stores it in one place. - The creation transaction retains final-entry collision, exact-entry detach, rollback, and quiescence coverage without identity-specific lifecycle state. -- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC caches only local disposable-child parent lineage while leaving remote runs outside its local-session notification pair. +- ACP, stdio, hooks, bash ownership, persistence, and lineage use the shared `SessionId` directly. The ACP subagent backend mints its lifecycle id in the parent namespace because a child server's returned session id is only server-local; the ACP bridge verifies exact `Agent` ownership from the forward session map; and JSON-RPC forwards only lifecycle events whose service-snapshotted `local` flag is true, obtains the delegating parent from the scoped event carrier, and keeps no child identity or lineage cache. - The config-driven resume-or-create policy is explicit and covered across a durable restart. - A production listener search kept `agent/created`/`agent/disposed` and their publication semantics. - Typecheck, coverage, snapshots, doc-sync, module-graph verification, build, and hygiene pass. diff --git a/packages/subagent/subagent/src/index.ts b/packages/subagent/subagent/src/index.ts index 8f3549ac7c..19779f9137 100644 --- a/packages/subagent/subagent/src/index.ts +++ b/packages/subagent/subagent/src/index.ts @@ -121,7 +121,7 @@ export interface SubagentRunInfo { readonly provider: string /** The child agent's id. */ readonly id: SessionId - /** Whether the provider exposed an exact published in-process child. */ + /** Snapshot of whether `SubagentRun.localAgent` was present when start fulfilled. */ readonly local: boolean } @@ -133,7 +133,7 @@ export interface SubagentRunEndInfo { readonly provider: string /** The child agent's id. */ readonly id: SessionId - /** Whether the provider exposed an exact published in-process child. */ + /** Snapshot of whether `SubagentRun.localAgent` was present when start fulfilled. */ readonly local: boolean /** The terminal stop reason. */ readonly stopReason: SubagentResult['stopReason'] diff --git a/packages/ui/acp/src/index.ts b/packages/ui/acp/src/index.ts index 95c5abb0d6..e20cd40f10 100644 --- a/packages/ui/acp/src/index.ts +++ b/packages/ui/acp/src/index.ts @@ -1,36 +1,7 @@ /** - * The Agent Client Protocol (ACP) bridge: a client-driver / UI plugin that - * exposes the harness agent as an ACP server over JSON-RPC stdio, so editors - * (Zed and other ACP clients) can drive it. The structured analogue of the - * readline `stdio-chat` plugin. - * - * This is NOT a loop change and NOT an ADR-0009 capability seam: it consumes - * the existing `agent/*` event taxonomy, the `dsh-agent` create/resume factory, - * and `dsh-session-persistence` (for `session/load`). It maps: - * - * - `initialize` → protocol-version negotiation, text-only capabilities - * - `session/new` → `ctx.agents.create({ sessionId, meta:{cwd} })` - * - `session/load` → `ctx.agents.resume(...)` then replay the event log - * - `session/prompt` → `agent.send()`, settle on the owning turn's end (a turn - * that ends in `error` rejects the RPC) - * - `session/cancel` → `agent.cancel()` (the queue-aware cancel: aborts a - * running step, clears queued + steering work, and drops a - * turn about to start) + settle the in-flight prompt - * - * Multi-session (RFC 011): N concurrent sessions per connection, each mapped to - * its own `ReactLoopAgent`. Sessions are keyed by their shared agent/session id; - * every `session/event` and `agent/*` event is routed strictly to its owning - * session record, and each `session/update` carries that id. Concurrent updates - * may alternate on the shared connection without crossing session attribution. - * Permission prompts use the same identity: the bridge answers - * `approval/request` for its own agents over `session/request_permission` (see - * the approval answerer below) — whether a call ASKS is policy (a hook or - * plugin returning `ask`), not the bridge's. - * - * stdout is the protocol: this plugin must run in an example that loads NO - * stdout logger (the console logger writes to stdout and would corrupt the - * JSON-RPC frames). The guarantee is config-only — see the package README and - * RFC 010 § Risks. + * Multi-session ACP bridge over JSON-RPC stdio. Creates or resumes agents, + * routes session-scoped events and approvals, and settles prompts by turn. + * Stdout is reserved for protocol frames. * * @module @deepseek-ai/dsh-acp */ @@ -104,27 +75,15 @@ import { } from './codec.ts' 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`. +// Interface services back loading, presentation, interaction, and prompt assembly. export const inject = ['agents', 'sessionPersistence', 'tools', 'userInteraction', 'llm', 'systemPrompt'] -/** - * Build an ACP "invalid params" error whose human detail rides in the message. - * `RequestError.invalidParams(data, additionalMessage)` keeps the standard - * "Invalid params" message and appends `additionalMessage`, so we pass the - * detail as `additionalMessage` (and no structured `data`). - */ +/** Preserve invalid-parameter detail in the SDK wire error message. */ function invalidParams(detail: string): RequestError { return RequestError.invalidParams(undefined, detail) } -/** - * Build an ACP "internal error" whose human detail rides in the message. Used - * to reject a `session/prompt` whose turn ended in failure: a plain `Error` - * thrown from a method handler is flattened to a generic "Internal error" on - * the wire, so we wrap the detail in the SDK's `RequestError.internalError` - * (which appends `additionalMessage`) to surface *why* the turn failed. - */ +/** Preserve failed-turn detail; plain handler errors become a generic wire internal error. */ function internalError(detail: string): RequestError { return RequestError.internalError(undefined, detail) } @@ -249,13 +208,7 @@ export interface AcpConfig { provider?: string /** Model name for created agents (must have a registered adapter). */ model?: string - /** - * Transport stream override. Production omits this (the plugin wires - * `process.stdin`/`process.stdout` via `ndJsonStream`). Tests inject an - * in-memory `Stream` (e.g. an `ndJsonStream` over a `Duplex` pair) to drive - * the bridge without a subprocess. Not part of the schemastery `Config` — - * it is a runtime-only seam, never set from a `cordis.yml`. - */ + /** Runtime-only transport override; production uses stdio. */ stream?: Stream } @@ -292,30 +245,11 @@ interface ModelCatalogEntry { /** Per-session bridge state keyed by ACP session id. */ interface SessionRecord { agent: Agent - /** - * The owned-agent disposer (from the {@link AgentHandle} the factory returned). - * Teardown calls it to unregister this ONE agent, stop its loop, await - * quiescence, and remove its session — instead of leaving it for the bridge - * fiber to reclaim. - */ + /** Exact owned-agent disposer; resolves after registry, loop, and session teardown. */ dispose: () => Promise - /** - * Resolves tool-owned presentation for THIS session's tool calls and remembers - * each in-flight call's `(name, args)` so the matching `tool/result` can find - * its tool. Per-session so two concurrent sessions never cross their in-flight - * tool state. - */ + /** Per-session tool presentation and call/result correlation. */ presenter: ToolPresenter - /** - * Whether THIS session renders shell tools as terminal cards — snapshotted - * from the client's `_meta.terminal_output` capability at session creation - * (`session/new`/`session/load`), NOT re-read live. A capability snapshot per - * session means the `tool_call` (which registers the terminal) and the matching - * `tool_call_update` (which streams its output) ALWAYS agree, even if a later - * `initialize` mutates the connection-level capability between them — otherwise - * a re-`initialize` mid-call could orphan a `terminal_output` (call non-terminal, - * result terminal) or clobber the card (call terminal, result non-terminal). - */ + /** Terminal capability snapshot shared by matching call and result updates. */ terminalEnabled: boolean /** Session-local provider/model selection and the current step snapshot. */ target: LlmTargetRef @@ -325,18 +259,7 @@ interface SessionRecord { reject: (error: Error) => void turn: number | undefined } | undefined - /** - * Config switches accepted while the session was IDLE, not yet anchored in - * its log. The turn-enclosure contract makes a bare between-turns append - * invalid (the JSONL backend treats a post-`turn/end` tail as crash - * garbage, and dev invariants throw), so an idle switch waits here and is - * anchored at the next turn's prompt-submit — before anything in that - * turn assembles a prompt or runs a call, and last write - * per knob wins (an idle flip-flop anchors as one event). Until anchored, - * the switch lives only in bridge memory: the set/new/load responses - * overlay it truthfully, and a restart before the next turn reverts it — - * which `session/load` then reports honestly from the log's fold. - */ + /** Last idle switch per knob, anchored before the next prompt assembles. */ pendingSwitches: { preset?: string } } @@ -347,21 +270,15 @@ interface SessionRecord { * correlation in a `finally` so presentation failure cannot starve settlement. */ export function apply(ctx: Context, config: AcpConfig): void { - // Capture the injected services NOW, during apply(), while we are inside this - // plugin's fiber (where `inject` grants access). The ACP method handlers run - // LATER, from the AgentSideConnection's JSON-RPC read loop — a context that is - // NOT this fiber's injection scope — so reading `ctx.agents` / `ctx.logger` / - // `ctx.sessionPersistence` lazily inside a handler throws "cannot get property - // … without inject". Resolving the references here and closing over them keeps - // the handlers working regardless of which fiber later invokes them. + // ACP handlers execute outside this plugin's injection scope, so capture + // injected services during apply(); lazy service reads in a handler fail. const agents = ctx.agents const llm = ctx.llm const sessionPersistence = ctx.sessionPersistence const logger = ctx.logger const tools = ctx.tools const userInteraction = ctx.userInteraction - // A new ToolPresenter per session (and a throwaway per load replay), each given - // this warn sink so a throwing tool presenter is logged, not propagated. + // Presenter callbacks are contained so display failures cannot break protocol handling. 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. */ @@ -459,23 +376,12 @@ export function apply(ctx: Context, config: AcpConfig): void { } } - // 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. const sessions = new Map() - // Session ids whose `session/load` is mid-`resume()` (the slot is reserved - // before the async resume so a pipelined load/new for the SAME id can't create - // two agents). Distinct ids load concurrently; a given id loads once at a time. + // Reserve an id before resume so pipelined load/new requests cannot duplicate it. const loadingIds = new Set() - // Set once the bridge has torn down (disposal or client disconnect). An async - // `session/load` mid-`resume()` when teardown ran must observe this after its - // await and NOT install a record (which would resurrect a live agent/listeners - // after the bridge closed). Checked after every load await. + // Async creation checks this after awaits to avoid publishing after teardown. let closed = false - // Connection-level terminal capability from the latest `initialize`; false - // before initialization. Each `session/new` or `session/load` snapshots it in - // `SessionRecord.terminalEnabled`, so later initialization affects only future - // sessions. + // Each new or loaded session snapshots the latest connection capability. let terminalOutputCap = false // Assigned at the bottom, before any agent event can fire (a session only @@ -674,22 +580,13 @@ export function apply(ctx: Context, config: AcpConfig): void { currentValue, options: [ ...presets.names.map((name: string) => presets.optionOf(name)), - // The derived not-a-preset state: visible exactly while it IS the - // current value (a knob state outside the table), switchable FROM, - // never a target — set() below rejects it like any unknown name. + // `custom` echoes the current derived state but is never a target. ...currentValue === 'custom' ? [presets.optionOf('custom')] : [], ], }] } - /** - * Whether the session's log currently has an open turn — the last boundary - * event is a `turn/start`. Decides whether a config switch may append NOW - * (enclosed) or must wait for the next turn (see - * {@link SessionRecord.pendingSwitches}). Read from the LOG, not - * `agent.status`: status stays `running` across the gap between two queued - * turns, where a bare append would still land outside any turn. - */ + /** Whether the log has an open turn in which a config switch can be enclosed. */ const isTurnOpen = (agent: Agent): boolean => { const events = agent.session.events for (let index = events.length - 1; index >= 0; index -= 1) { @@ -700,12 +597,7 @@ export function apply(ctx: Context, config: AcpConfig): void { return false } - /** - * Anchor a record's pending switches into its (just-opened) turn, last - * write per knob — skipping a value the session already effectively has, - * so a net-zero idle flip-flop anchors NOTHING (the log records switches, - * not select clicks). - */ + /** Anchor last-write-wins idle switches into a just-opened turn. */ const flushPendingSwitches = (rec: SessionRecord): void => { const pending = rec.pendingSwitches rec.pendingSwitches = {} @@ -717,15 +609,8 @@ export function apply(ctx: Context, config: AcpConfig): void { presets.set(rec.agent.session, pending.preset) } - // Idle-accepted switches anchor at the next turn's prompt-submit: the turn - // is open (the seam fires inside it, per drained message — the first flush - // empties the slot, later ones no-op), the loop has not yet assembled - // anything for it, and — unlike appending from inside a `session/event` - // listener — this seam fires OUTSIDE any log emit, so peer listeners - // (the dev invariants, persistence) observe the anchored events in strict - // log order. A turn with no prompt (an idle inject's one-shot injection - // turn) leaves the switch pending — it runs no step, so nothing executes - // or assembles under a stale value. + // Prompt-submit is inside the new turn but before prompt assembly. Promptless + // injection turns leave the switch pending because they execute no request. ctx.on('agent/prompt-submit', (agent, _content, _source, next) => { const rec = ownedRecord(agent) if (rec !== undefined) flushPendingSwitches(rec) @@ -780,10 +665,8 @@ export function apply(ctx: Context, config: AcpConfig): void { agentOptions: agentOptions(config), setup: (agentCtx) => { installTarget(agentCtx, target) }, }) - // Creation is now asynchronous because it awaits the unpublished setup - // transaction. A client disconnect can therefore close this bridge - // after the entry check but before the handle resolves; never install a - // post-close record that quiesce() could not have seen. + // Agent creation may resolve after the bridge closes; dispose the handle + // instead of publishing a record that teardown could not observe. /* v8 ignore next 4 -- the in-memory transport rejects the in-flight RPC immediately on close; real stdio may let the handler resume */ if (closed) { @@ -991,10 +874,7 @@ export function apply(ctx: Context, config: AcpConfig): void { if (presets === undefined) { throw invalidParams(`unknown permission value ${JSON.stringify(params.value)}`) } - // A no-op switch (the value the session already shows — pending, - // else derived) is acknowledged FIRST and records nothing: - // clients re-push current selections on session start, and the - // derived 'custom' current is only ever valid as such an echo. + // A current-value echo is acknowledged without recording a switch. const current = rec.pendingSwitches.preset ?? presets.current(rec.agent.session.events) if (params.value === current) break if (!presets.names.includes(params.value)) { @@ -1236,27 +1116,16 @@ export function streamSessionEventUpdate( } /** - * Map a harness todo list to an ACP `plan` body. ACP's `PlanEntry` requires - * `content` + `priority` + `status`, but a {@link TodoItem} carries no priority, - * so synthesize a constant `'medium'` on every entry; `status` maps 1:1 (the - * harness status triple IS `PlanEntryStatus`). The ACP client REPLACES its whole - * plan on each `plan` update, matching the harness's whole-list-replace - * semantics, so no per-entry diffing is needed. - * @param todos - the harness todo list (the whole list, not a diff). - * @returns the ACP plan body, one entry per todo. + * Map a whole harness todo list to an ACP replacement plan, using medium + * priority because harness todos do not carry one. + * @param todos - complete harness todo list. + * @returns one ACP plan entry per todo. */ export function todosToPlan(todos: TodoItem[]): Plan { return { entries: todos.map((todo): PlanEntry => ({ content: todo.content, priority: 'medium', status: todo.status })) } } -/** - * Per-session terminal-rendering context threaded into - * {@link streamSessionEventUpdate}: whether the client advertised the - * `_meta.terminal_output` capability, and the session's workspace cwd (the - * default terminal-card header when a tool doesn't supply its own). Kept out of - * the pure translator's required params so the no-capability / no-presenter - * tests stay terse. - */ +/** Per-session terminal capability and workspace used while translating updates. */ export interface TerminalRendering { enabled: boolean /** The session workspace cwd (terminal-card header default); `undefined` when the session has none. */ @@ -1267,47 +1136,21 @@ export interface TerminalRendering { const noTerminalRendering: TerminalRendering = { enabled: false, cwd: undefined } /** - * Resolves tool-owned presentation for a session's tool-call events. A tool - * declares `presentCall`/`presentResult` (see `dsh-tools`) returning a - * `card`-tagged {@link ToolCallView}/{@link ToolResultView}; this looks them up - * by name in the registry and applies a generic fallback when a tool defines - * neither. The returned view is what {@link streamSessionEventUpdate} switches on. - * - * The `tool/result` session event does NOT carry the tool name or args — so to - * call a tool's `presentResult` (which needs both), the presenter remembers each - * `tool/call`'s `{ name, args, card }` keyed by callId and looks it up on the - * matching result. The map is bridge-LOCAL (not a change to the event schema or a - * core service): one presenter per live session - * (and a throwaway per `session/load` replay), and each entry is removed when its - * result arrives. In the normal loop a `tool/call` is always followed by a - * `tool/result` (the registry turns even a thrown tool into an isError result), - * so the map holds only currently-in-flight calls. The one exception is a step - * torn down mid-tool (an abort between `tool/call` and `tool/result`), which can - * leave a single stale entry per such call; this is bounded by the session - * lifetime (the whole presenter is dropped on teardown) and never affects - * correctness — a later result for a different callId is unaffected, and the - * stale entry's only cost is one map slot until the session ends. + * Resolve tool-owned call/result views with a generic fallback. Per-session + * state correlates results with call arguments; interrupted calls may retain an + * entry only until that session's presenter is discarded. */ export class ToolPresenter { private readonly pending = new Map() /** - * @param tools the registry to resolve tool definitions by name. - * @param onError invoked when a tool's `presentCall`/`presentResult` THROWS; - * the presenter swallows the error and falls back to the generic - * presentation so a buggy display callback can never fail a live turn or a - * `session/load` replay (docs/defensive-patterns.md "contain callback exceptions at the - * boundary"). Defaults to a no-op for callers that don't supply a logger. + * @param tools - registry used to resolve executing definitions. + * @param onError - contained presenter-error sink before generic fallback. + * @param agent - optional scoped registry view for the executing agent. */ constructor( private readonly tools: Pick, private readonly onError: (message: string) => void = () => {}, - /** - * The agent whose view resolves tool presentations: a scoped/shadowed - * tool presents with ITS OWN presentCall/presentResult — the same - * definition that executed — not a same-named global's. Absent (a replay - * with no live agent) the global view presents. - */ private readonly agent?: Agent, ) {} @@ -1316,10 +1159,8 @@ export class ToolPresenter { * for the matching result. * @param callId - the call id the matching `tool/result` will look up. * @param name - the tool name, resolved against the registry for `presentCall`. - * @param argsJson - the raw arguments JSON from the event; parsed for the view - * (a non-JSON string is surfaced raw). - * @returns the tool-owned view, or the generic fallback (title = tool name, - * kind `other`, parsed args as raw input) when the tool defines none or threw. + * @param argsJson - raw event arguments parsed for presentation. + * @returns the tool-owned view or generic fallback. */ call(callId: CallId, name: string, argsJson: string): ToolCallView { const args = parseToolArguments(argsJson) @@ -1331,10 +1172,7 @@ export class ToolPresenter { this.onError(`acp: tool "${name}" presentCall threw, using generic presentation: ${String(error)}`) present = undefined } - // No tool-owned presentation: fall back to the tool name as the title, the - // full parsed args as the raw input, and kind `other` (the generic card). - // The kind is never sniffed from the name — the bridge does not special-case - // tool names; a tool that wants a richer kind declares `presentCall`. + // Tool names never imply presentation kind; richer cards are tool-owned. const view: ToolCallView = present ?? { card: 'generic', title: name, kind: 'other', rawInput: args } this.pending.set(callId, { name, args, card: view.card }) return view @@ -1343,14 +1181,11 @@ export class ToolPresenter { /** * Completed-state render intent for a `tool/result`; consumes the remembered * `(name, args, card)`. - * @param callId - the id of the matching `tool/call`; an unknown or late id - * falls back to the raw content. - * @param content - the result's content blocks (the fallback and fill-in body). + * @param callId - matching call id; unknown or late ids use raw content. + * @param content - result content used by the fallback and fill-in body. * @param isError - whether the result is an error, forwarded to `presentResult`. * @param meta - the result's machine-readable meta, forwarded when present. - * @returns the tool-owned view — an orphaned `terminal` result (no terminal - * call side) and a content-less `generic` are normalized — or the raw-content - * generic card when the tool defines no `presentResult` or threw. + * @returns a normalized tool-owned view or raw-content fallback. */ result(callId: CallId, content: ContentBlock[], isError: boolean, meta?: unknown): ToolResultView { const call = this.pending.get(callId) @@ -1420,25 +1255,11 @@ type AcpToolCallContent = | { type: 'diff'; path: string; oldText: string | null; newText: string } | { type: 'terminal'; terminalId: string } -/** - * Relativize a file card's TITLE path against the session workspace cwd, so a - * card reads `Read src/foo.ts` rather than `/abs/proj/src/foo.ts` — matching the - * reference ACP adapter's `toDisplayPath`. Only the TITLE is relativized; the - * card's `locations`/`diff` paths stay RAW (the editor opens the real path). The - * pure tool presenter can't see the session cwd, so this happens here where the - * bridge knows it. The rewrite is an exact substring replace of the known raw - * path (a card carries the same path in `locations[0]`/`diffs[0]`), never a - * heuristic. A path outside the workspace, or an absent/relative session cwd, is - * left unchanged. - */ +/** Relativize only in-workspace title text; location and diff paths stay raw. */ function displayTitle(title: string, rawPath: string | undefined, sessionCwd: string | undefined): string { if (rawPath === undefined || sessionCwd === undefined || !isAbsolute(rawPath) || !isAbsolute(sessionCwd)) return title const rel = relativePath(sessionCwd, rawPath) - // Only relativize a target that stays INSIDE the workspace. `relative` prefixes - // a `..` SEGMENT for a target above the cwd — test for the segment (`..` alone - // or `..…`), NOT a bare `..` char prefix, so a sibling like `..cache/x` - // (a real in-workspace name) still relativizes. Never relativize to the empty - // string (rawPath === cwd — a non-file target). + // Test the `..` segment, not a character prefix: `..cache/x` is in-workspace. if (rel.length === 0 || rel === '..' || rel.startsWith(`..${pathSep}`)) return title return title.split(rawPath).join(rel) } diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 3d19b601c4..6666867598 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -1,26 +1,26 @@ # @deepseek-ai/dsh-jsonrpc -The **SDK server plugin** (`jsonrpc`): mounting it serves a stdio JSON-RPC server that lets an out-of-process SDK client (e.g. the Python `deepseek_harness` package) drive DeepSeek Harness agents without touching Cordis. The client speaks newline-delimited JSON-RPC on the process stdin/stdout ([`HarnessSdkServer`](src/server.ts): `initialize` → `session/prompt` → `shutdown`, with `session.event` / `session.finished` / `subagent.*` notifications over [`JsonRpcLineTransport`](src/transport.ts)). The SDK-client analogue of the [`acp`](../acp/README.md) bridge, split the same way: this package is the protocol plugin, while [`jsonrpc-demo`](../../examples/jsonrpc-demo/README.md) is the app bin that boots a `cordis.yml` around it — which process serves this protocol is a config decision, not a hardcoded bin. This plugin is the serving face of the [single-executable distribution plan](../../../docs/rfc/implemented/architecture/2026-07-10-single-file-executable-sdk-runtime-distribution.md). +The `jsonrpc` plugin serves newline-delimited JSON-RPC over stdio so out-of-process SDK clients can drive harness agents. [`HarnessSdkServer`](src/server.ts) owns the protocol methods and notifications; [`jsonrpc-demo`](../../examples/jsonrpc-demo/README.md) supplies the surrounding `cordis.yml` application. ## Wiring -`inject: ['agents']`. The server gets or creates one agent per `sessionId` from the `initialize.provider`/`initialize.model` pair. It forwards subagent completions only when the lifecycle payload's `local` flag was snapshotted from the provider's exact in-process child; reusable provider names, child ids, and durable lineage never establish locality. A registered owner for the provider route wins; an unowned `deepseek` route mounts `dsh-llm-deepseek` using `$DEEPSEEK_API_KEY` and `$DEEPSEEK_BASE_URL`, while any other unowned provider fails initialization. Persistence, tools, and other adapters come from the surrounding `cordis.yml`. +`inject: ['agents']`. The server gets or creates one agent per `sessionId`. It forwards subagent completions only when the service-snapshotted lifecycle `local` flag is true; provider names, child ids, and durable lineage never establish locality. A registered adapter wins, an unowned `deepseek` route mounts `dsh-llm-deepseek`, and any other unowned provider fails initialization. Other capabilities come from the surrounding `cordis.yml`. ## Config -No `cordis.yml`-settable keys. The `JsonRpcConfig` fields (`input`, `output`, `exit`) are runtime-only test seams so a spec can drive the server over in-memory streams without a subprocess or a killed test process; production always serves the process stdio and exits via `process.exit`. +There are no `cordis.yml` keys. `JsonRpcConfig.input`, `output`, and `exit` are runtime-only transport seams; production uses process stdio and `process.exit`. ## stdout is the protocol -The process stdout this plugin runs in carries only JSON-RPC frames. The tree that loads it must load NO stdout logger (a console logger corrupts the frames) — the guarantee is config-only, same as the ACP bridge. Diagnostics go to stderr. +Stdout carries only JSON-RPC frames. The deployment must not compose a stdout logger; diagnostics belong on stderr. ## Shutdown and exit semantics -The plugin owns the PROTOCOL-level exit: a `shutdown` request is answered first (the response frame flushes), then the plugin disposes its own fiber — running the effect disposer: an idempotent `server.shutdown()` (every SDK-created agent disposed to quiescence, event subscriptions detached) plus `transport.close()` — and exits the process with code 0. Own-fiber disposal is deliberate: the request's `server.shutdown()` already flushed all SDK-owned session state, and the process exit that follows is the teardown of the rest of the tree. Process-level exits (stdin EOF → 0, SIGTERM → 0, SIGINT → 130) belong to the app bin, which disposes the whole root context. Fiber disposal WITHOUT a `shutdown` request (HMR-style unload) just stops serving — it never exits the process. +The plugin answers `shutdown`, disposes SDK-owned agents and subscriptions to quiescence, closes the transport, then exits with code 0. EOF and signal exits belong to the app bin, which disposes the root context. Unloading only this plugin stops serving without exiting the process. ## Wire notes -`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime` (SDK clients key on it, independent of this package's name). A session accepts at most one in-flight `session/prompt`; an overlapping prompt for the same `sessionId` fails immediately through the standard handler-error response, while other sessions remain independent and the same session can be reused after the active prompt settles. Persistence roots and the deployment persona come from `cordis.yml`; the wire exposes only parameters the server applies. +`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime`. A session accepts one in-flight prompt; overlap fails immediately, other sessions remain independent, and the session is reusable after settlement. Persistence roots and persona come from `cordis.yml`. ## Model Experience diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 5246795a31..8949ccb06a 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -1,13 +1,6 @@ /** - * `HarnessSdkServer`: the JSON-RPC method surface the `dsh-jsonrpc` plugin - * serves to out-of-process SDK clients (e.g. the Python `deepseek_harness` - * package). Requests: `initialize` → `session/prompt`* → `shutdown`. - * Notifications pushed to the host: `session.event` (every durable session - * event, verbatim), `session.finished` (per prompt turn settle), - * `subagent.started` / `subagent.finished` (child-session lineage and run - * outcomes). The server owns only the SDK-facing session map — the harness - * itself is the context the plugin mounts in; plugins, persistence, and - * the LLM adapter set all come from the external `cordis.yml`. + * JSON-RPC method and notification surface for out-of-process harness SDKs. + * The surrounding context owns plugins, persistence, and configured adapters. * * @module @deepseek-ai/dsh-jsonrpc/server */ @@ -23,7 +16,7 @@ import type { SubagentRunEndInfo } from '@deepseek-ai/dsh-subagent' import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek' import type { JsonRpcTransportPeer } from './transport.ts' -/** Parameters of the `initialize` request (once per process, before any prompt). */ +/** Parameters for the process-wide SDK handshake. */ export interface InitializeParams { /** Working directory recorded on every SDK-created session's header. */ cwd: string @@ -33,16 +26,13 @@ export interface InitializeParams { model: string } -/** Result of the `initialize` request: the server's identity for the SDK handshake. */ +/** Wire-stable server identity returned by initialization. */ export interface InitializeResult { /** Wire-stable server identity (`deepseek-harness-sdk-runtime`) and version. */ serverInfo: { name: string; version: string } } -/** - * Parameters of a `session/prompt` request: one user turn on one SDK session, - * with at most one in flight per session. - */ +/** One user turn on one SDK session. */ export interface SessionPromptParams { /** The SDK-side session id; an unknown id lazily creates the agent+session pair. */ sessionId: string @@ -50,7 +40,7 @@ export interface SessionPromptParams { contentBlocks: ContentBlock[] } -/** Result of a `session/prompt` request: the prompt ran to turn settle (outcome rides on `session.finished`). */ +/** Prompt acceptance after turn settlement; outcome rides on `session.finished`. */ export interface SessionPromptResult { /** Always `true`; the turn outcome is the paired `session.finished` notification. */ accepted: true @@ -62,20 +52,12 @@ interface SessionRecord { activePrompt: boolean } -/** Recover the delegating parent carried by every service-owned subagent lifecycle event. */ +/** Recover the delegating parent from the service-owned scoped carrier. */ function subagentParentOf(carrier: Scoped): Agent { - // SubagentService emits this lifecycle pair only through scopeTarget(this, parent). return carrierKeyOf(carrier) as Agent } -/** - * The SDK server over a booted harness context. Constructing it subscribes to - * session and subagent lifecycle events, forwarding durable session - * events and SDK-facing completion notifications while retaining local-run - * identity across child disposal. The subscriptions live until - * {@link shutdown}. One instance serves one transport peer for the process - * lifetime — there is no re-`initialize`. - */ +/** SDK server whose subscriptions and created agents live until {@link shutdown}. */ export class HarnessSdkServer { private cwd = process.cwd() private provider = 'deepseek' @@ -125,10 +107,9 @@ export class HarnessSdkServer { } /** - * Record cwd and provider/model, mounting the DeepSeek adapter only when the - * `deepseek` provider route has no configured owner. - * @param params - the SDK handshake parameters. - * @returns the server identity for the handshake. + * Configure the SDK route, mounting the DeepSeek fallback only when unowned. + * @param params - SDK handshake parameters. + * @returns server identity for the handshake. */ async initialize(params: InitializeParams): Promise { this.cwd = resolve(params.cwd) @@ -142,13 +123,9 @@ export class HarnessSdkServer { } /** - * Handle `session/prompt`: get-or-create the session's agent, send the - * content as the user message, await turn settle (quiescence), then notify - * `session.finished` with the settled turn's outcome. A session accepts at - * most one prompt at a time; an overlapping request fails immediately while - * other sessions remain independent. - * @param params - the target session id and prompt content. - * @returns `{ accepted: true }` after the turn settled. + * Run one prompt to settlement; overlap on the same session fails. + * @param params - target session and user content. + * @returns acceptance after the turn settled. */ async prompt(params: SessionPromptParams): Promise { const rec = await this.getOrCreateSession(params.sessionId) @@ -171,11 +148,9 @@ export class HarnessSdkServer { } /** - * Handle `shutdown`: dispose every SDK-created agent handle (awaiting loop - * quiescence), unmount the adapter fiber this server mounted (if any), and - * detach the event subscriptions. The CONTEXT stays up — the bin disposes it - * as part of process exit. - * @returns an empty object (the JSON-RPC result). + * Dispose server-owned agents, adapter, and subscriptions to quiescence. + * The surrounding context remains running. + * @returns empty JSON-RPC result. */ shutdown(): Promise> { this.shutdownTask ??= this.performShutdown()