Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge master into codex/session-title

Browse Source
This commit is contained in:
Tianyi Cui
2026-07-21 22:59:41 +08:00
parent 3a895ce815 0cd8424d46
commit 3176d232b8
197 changed files with 3343 additions and 1227 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
packages/core/agent-loop/README.md
View File

@@ -60,7 +60,7 @@ The driver owns one agent for its lifetime and runs inside `ctx.agents.withIniti
Every provider call that reaches a successful finish appends exactly one `assistant/message` completion anchor, including content-less calls and `max-tokens` finishes. A successful `agent/step-result` stores its transformed content; a rejected result records empty content before the original failure continues. The anchor retains exact chunk provenance (`[]` for a stream with no chunks) and usage when available, while empty content stays out of derived message history.
Plugin failure ends the current turn, not the loop. Only final adapter dispatch/iteration failures and terminal in-band error or aborted finishes enter `agent/request-error`; middleware, result processing, tools, and `agent/post-step` remain ordinary turn failures. Recovery receives the exact live error, immutable provider facts, and immutable prior failures after the failed step closes. A retry rebuilds from the durable log in a new numbered step, success clears the consecutive history, and exhaustion records the structured failure once on `turn/end`. Effective cancellation resolves its reason and emits `agent/cancel-requested` before clearing pending work or aborting the current step; notification failures are contained, queued work added by an observer is included in the same broad clear, and idle cancellation emits nothing. Undispatched model tool calls receive synthetic `tool/call` and aborted result pairs. Terminal continuation stops remain authoritative through turn close and durability flush.
Plugin failure ends the current turn, not the loop. Only final adapter dispatch/iteration failures and terminal in-band error or aborted finishes enter `agent/request-error`; middleware, result processing, tools, and `agent/post-step` remain ordinary turn failures. Recovery receives the exact live error, immutable provider facts, and immutable prior failures after the failed step closes. A retry rebuilds from the durable log in a new numbered step, success clears the consecutive history, and exhaustion records the structured failure once on `turn/end`. AgentLoop privately owns one cancellation holder whose explicit signal spans prompt policy, assembly, every step, model and tool work, recovery, continuation, and terminal stop; it retires the holder immediately before publishing `turn/end`, while the driver may remain `running` through the durability flush. An effective `cancel()` emits the typed runtime-only `user | parent` cause before clearing pending work and cooperatively aborting the holder; notification failures cannot veto cancellation, work queued by a notification observer is cleared, work queued by a later abort observer belongs to the next turn, and idle cancellation emits nothing. Durable `turn/end` remains coarse `aborted`; undispatched model tool calls receive synthetic `tool/call` and `ABORTED_BEFORE_DISPATCH` result pairs. Disposal wins terminal classification, and work that ignores the signal must settle before quiescence. The [explicit-cancellation decision](../../../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md) owns the lifecycle and race contract. Terminal continuation stops remain authoritative through turn close and durability flush.
Within a step, exclusive calls form barriers; parallel-safe calls use a bounded rolling pool and are reclassified before start. Only dispatch/body overlaps. Policy, durable results, and result context remain model-ordered. Abort stops new calls, drains started results, then drains accepted batch context before the turn closes through the normal abort path.
@@ -109,7 +109,7 @@ Ordinary history growth is append-only and preserves reusable entries. A surface
#### What the model sees
If a later request replays an aborted step, each tool call that cancellation prevented from dispatching has the error result text `Error: tool call skipped because the step was aborted before execution`.
If a later request replays an aborted step, each tool call that cancellation prevented from dispatching has error code `ABORTED_BEFORE_DISPATCH` and result text `Error: tool call aborted before dispatch`.
#### Token effect

69
packages/core/agent-loop/src/agent.ts
View File

@@ -8,11 +8,12 @@
import type { Context } from 'cordis'
import { agentEvents } from '@deepseek-ai/dsh-agent'
import type { AgentOptions, AgentStatus, HookContext, InjectOptions, SendOptions } from '@deepseek-ai/dsh-agent'
import type { AgentCancelCause, AgentOptions, AgentStatus, HookContext, InjectOptions, SendOptions } from '@deepseek-ai/dsh-agent'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { deepFreeze, errorChain } from '@deepseek-ai/dsh-llm'
import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
import { snapshotJsonValue, type Session, type SessionId } from '@deepseek-ai/dsh-session'
import { DISPOSED_INTERRUPT_REASON, TurnCancellation } from './cancellation.ts'
import { Inbox, type InboxMessage } from './inbox.ts'
import { isTurnOpen, lastTurnNumber, runLoop } from './loop.ts'
@@ -95,7 +96,7 @@ export function bindReactLoopAgentContext(agent: ReactLoopAgent, ctx: Context):
/**
* The concrete {@link Agent} implementation owned by the agent-loop plugin.
*
* Owns the inbox (queued + steering FIFOs), the per-step AbortController, and
* Owns the inbox (queued + steering FIFOs), turn cancellation, and
* the loop driver. Everything observable happens through session events and
* the agent/* event taxonomy — plugins never need this class.
*/
@@ -120,21 +121,14 @@ export class ReactLoopAgent implements Agent {
}
private _status: AgentStatus = 'idle'
private currentAbort: AbortController | undefined
/** Active turn owner from pre-running publication through durability settlement. */
private turnCancellation: TurnCancellation | undefined
/** Whether runLoop has been installed into {@link done}. */
private driverStarted = false
/** Whether registry publication began and status disposal is externally visible. */
private published = false
/**
* Turn-scoped cancel marker, set by {@link cancel} and read/cleared by the
* driver loop (via the LoopHandle) at every point a turn could start or
* continue. Armed ONLY when there is something to cancel (a running turn, an
* in-flight step, or queued/steering work), so an idle no-op cancel cannot
* leave it set to wrongly drop a later prompt.
*/
private cancelRequested = false
/** Pending cancellation reason, preserved even outside an active step signal. */
private cancelReason = 'cancelled'
/** Cause-less marker for queued work cancelled before the driver installs a turn owner. */
private preRunCancelled = false
private disposed: Promise<void>
private resolveDisposed!: () => void
/** Resolves when the driver loop has fully exited (tests/disposal). */
@@ -330,29 +324,21 @@ export class ReactLoopAgent implements Agent {
}
}
cancel(reason?: string): void {
const resolvedReason = reason ?? 'cancelled'
// Arm only for current work; an idle marker would cancel the next prompt.
if (this._status === 'running' || this.currentAbort !== undefined || this.#inbox.hasQueued || this.#inbox.hasSteering) {
this.cancelRequested = true
// Capture the resolved reason for the marker-only windows (pre-step /
// continuation). The mid-step path reads it from abort.signal.reason
// below; the marker path reads it via the LoopHandle's cancelReason().
this.cancelReason = resolvedReason
cancel(cause?: AgentCancelCause): void {
const resolvedCause = cause ?? { kind: 'user' }
const cancellation = this.turnCancellation
const preRun = cancellation === undefined && (this.#inbox.hasQueued || this.#inbox.hasSteering)
if (cancellation !== undefined || preRun) {
if (preRun) this.preRunCancelled = true
// Coordination consumers must update their own state before this call
// clears the inbox or aborts the step. Notification failures are
// clears the inbox or aborts the turn. Notification failures are
// contained by the fused dispatcher and cannot veto cancellation.
agentEvents(this.loopCtx, this).emit('agent/cancel-requested', resolvedReason)
agentEvents(this.loopCtx, this).emit('agent/cancel-requested', resolvedCause)
}
// Drop all pending queued + steering work (un-started prompts never run; the
// cancelled turn's steering is not re-enqueued). Cleared directly even when
// the loop is parked in waitForQueued — there is no turn to stop and nothing
// left for the parked loop to run, so no wake is needed.
// Clear work already present before abort observers run. A replacement
// synchronously enqueued by an observer belongs to the next turn.
this.#inbox.clear()
// Interrupt an in-flight step immediately (the running turn observes the
// abort and ends `aborted`). The marker covers the windows where no step is
// running (pre-step, continuation).
this.currentAbort?.abort(resolvedReason)
cancellation?.request(resolvedCause)
}
/**
@@ -394,14 +380,21 @@ export class ReactLoopAgent implements Agent {
inbox: this.#inbox,
maxParallelToolCalls: this.maxParallelToolCalls,
setStatus: (status) => { this.setStatus(status) },
setAbort: controller => void (this.currentAbort = controller),
installTurnCancellation: () => {
const cancellation = new TurnCancellation()
this.turnCancellation = cancellation
return cancellation
},
clearTurnCancellation: (cancellation) => {
/* v8 ignore else -- the driver clears only the exact owner returned by its latest install. */
if (this.turnCancellation === cancellation) this.turnCancellation = undefined
},
disposed: this.disposed,
isDisposed: () => this._status === 'disposed',
isCancelled: () => this.cancelRequested,
cancelReason: () => this.cancelReason,
clearCancel: () => { this.cancelRequested = false },
isPreRunCancelled: () => this.preRunCancelled,
clearPreRunCancel: () => { this.preRunCancelled = false },
withToolBatch: run => this.withToolBatch(run),
// Pre-start cancellation settles queued-work waiters before publishing idle.
// Pre-run cancellation settles queued-work waiters before publishing idle.
settleIdle: () => { this.settleIdleWaiters() },
}))
}
@@ -419,7 +412,7 @@ export class ReactLoopAgent implements Agent {
// internal state that must settle even if a listener throws below. Each
// waiter chains `done`, so it resolves only once the loop actually exits.
this.settleIdleWaiters()
this.currentAbort?.abort('disposed')
this.turnCancellation?.request(DISPOSED_INTERRUPT_REASON)
// An unpublished rollback has no public status lifecycle to announce.
// Once publication begins, disposed is part of the agent/status contract.
if (this.published) {

31
packages/core/agent-loop/src/cancellation.ts Normal file
View File

@@ -0,0 +1,31 @@
/** Turn-scoped cancellation ownership for the concrete AgentLoop driver. @module dsh-agent-loop/cancellation */
import type { AgentCancelCause } from '@deepseek-ai/dsh-agent'
/** Stable runtime-only reason used when lifecycle teardown interrupts a turn. */
export const DISPOSED_INTERRUPT_REASON = Object.freeze({ kind: 'disposed' } as const)
/**
* Owns the single controller shared by every asynchronous boundary of one turn.
* The first request wins because a later caller must not rewrite the cause
* observed by earlier listeners.
*/
export class TurnCancellation {
readonly #controller = new AbortController()
/** The explicit signal passed through this turn's execution boundaries. */
get signal(): AbortSignal {
return this.#controller.signal
}
/**
* Abort the turn once.
* @param reason - a typed caller cause or lifecycle disposal marker.
* @returns whether this request established the signal reason.
*/
request(reason: AgentCancelCause | typeof DISPOSED_INTERRUPT_REASON): boolean {
if (this.signal.aborted) return false
this.#controller.abort(Object.freeze({ kind: reason.kind }))
return true
}
}

2
packages/core/agent-loop/src/inbox.ts
View File

@@ -29,7 +29,7 @@ export class Inbox {
return this.queuedMessages.length > 0
}
/** True while steering messages are pending — read by `cancel()`'s arm gate and the loop's stop-override check. */
/** True while steering messages are pending — read by cancellation and the loop's stop-override check. */
get hasSteering(): boolean {
return this.steeringMessages.length > 0
}

242
packages/core/agent-loop/src/loop.ts
View File

@@ -9,7 +9,7 @@ import type { Context } from 'cordis'
import type { ContentBlock, FinishReason, GenerateOptions, LlmCallConfig, LlmFailure, Message } from '@deepseek-ai/dsh-llm'
import { isDeepStrictEqual } from 'node:util'
import { BlockAssembler, HarnessError, LlmError, assertNever, deepFreeze, errorChain, llmFailureOf, markAgentLoopRequest } from '@deepseek-ai/dsh-llm'
import { agentEvents, assembleContextFor } from '@deepseek-ai/dsh-agent'
import { agentEvents, agentInterruptReasonOf, assembleContextFor } from '@deepseek-ai/dsh-agent'
import type { AgentEventDispatch, ContinuationDecision, HookContext, PromptDecision, RequestError, RequestErrorDecision } from '@deepseek-ai/dsh-agent'
import { canonicalHeader } from '@deepseek-ai/dsh-session'
import type { Session, TurnEndReason, TurnTrigger } from '@deepseek-ai/dsh-session'
@@ -20,6 +20,7 @@ import type { PromptAssembly } from '@deepseek-ai/dsh-system-prompt'
import type {} from '@deepseek-ai/dsh-tools'
import { executeToolCalls } from './tool-calls.ts'
import type { Inbox } from './inbox.ts'
import type { TurnCancellation } from './cancellation.ts'
/** Normalize thrown values while preserving an existing error code. */
function toError(error: unknown): RequestError {
@@ -88,6 +89,32 @@ function stepFinishReason(finish: FinishReason): TurnEndReason | undefined {
}
}
/** Internal control-flow sentinel; durable classification comes only from the turn signal. */
const TURN_INTERRUPTED = new Error('turn interrupted')
/** Stop at an explicit cooperative boundary without stringifying the runtime reason. */
function interruptionCheckpoint(signal: AbortSignal): void {
if (signal.aborted) throw TURN_INTERRUPTED
}
/** Classify a supported turn interruption, with lifecycle disposal taking precedence. */
function interruptionTurnEndReason(handle: LoopHandle, signal: AbortSignal): TurnEndReason | undefined {
if (handle.isDisposed()) return { kind: 'disposed' }
const reason = agentInterruptReasonOf(signal)
if (reason === undefined) return undefined
switch (reason.kind) {
case 'user':
case 'parent':
return { kind: 'aborted' }
/* v8 ignore next 2 -- the private holder requests disposed only after lifecycle state flips, which returns above. */
case 'disposed':
return { kind: 'disposed' }
/* v8 ignore next 2 -- AgentInterruptReason is closed and the public helper filters unsupported reasons. */
default:
return assertNever(reason, 'AgentInterruptReason')
}
}
/** Mutable agent controls supplied to the loop driver. */
export interface LoopHandle {
/** Native-private agent inbox handed to the driver only at internal startup. */
@@ -95,16 +122,17 @@ export interface LoopHandle {
/** Maximum parallel-safe calls allowed in one step. */
readonly maxParallelToolCalls: number
setStatus(status: 'idle' | 'running'): void
setAbort(controller: AbortController | undefined): void
/** Install a fresh active-turn owner before the running notification. */
installTurnCancellation(): TurnCancellation
/** Clear only the exact owner whose turn reached its terminal event boundary. */
clearTurnCancellation(cancellation: TurnCancellation): void
/** Resolves when the agent is disposed — unblocks the idle wait. */
disposed: Promise<void>
isDisposed(): boolean
/** Whether cancellation is pending for the current loop iteration. */
isCancelled(): boolean
/** Resolved pending-cancellation reason; meaningful only while {@link isCancelled} is true. */
cancelReason(): string
/** Clear the cancel marker (called once per iteration after the turn returns). */
clearCancel(): void
/** Whether queued work was cancelled before an active turn owner existed. */
isPreRunCancelled(): boolean
/** Clear the cause-less pre-run marker without affecting replacement work. */
clearPreRunCancel(): void
/** Settle idle waiters before pre-running cancellation publishes idle. */
settleIdle(): void
/** Run an active tool-call batch, accepting post-tool context into the FIFO drained before settlement. */
@@ -119,7 +147,7 @@ export interface LoopHandle {
* @param ctx - the plugin context the loop reaches its initiating Agent,
* events (agent/…, session/flush), and services (systemPrompt, llm, tools)
* through.
* @param handle - the bridge to the agent's mutable state: status/abort setters plus the disposal and cancel-marker reads.
* @param handle - the bridge to status, turn cancellation ownership, disposal, and pre-run cancellation state.
* @throws when no initiating Agent is active.
*/
export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
@@ -134,8 +162,8 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
while (!handle.isDisposed()) {
// An idle listener can enqueue and cancel replacement work before the next
// wait is installed. Consume that empty marker before parking the driver.
if (handle.isCancelled()) {
handle.clearCancel()
if (handle.isPreRunCancelled()) {
handle.clearPreRunCancel()
if (!handle.inbox.hasQueued) {
handle.settleIdle()
handle.setStatus('idle')
@@ -148,8 +176,8 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
// Cancellation between wake and `running` skips only the cancelled work;
// a replacement prompt still runs before the eventual idle transition.
if (handle.isCancelled()) {
handle.clearCancel()
if (handle.isPreRunCancelled()) {
handle.clearPreRunCancel()
if (!handle.inbox.hasQueued) {
// Settle before publishing idle: the already-idle path has no status
// transition, while an idle listener can register waiters for new work.
@@ -159,24 +187,29 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
}
}
let cancellation = handle.installTurnCancellation()
handle.setStatus('running')
if (handle.isDisposed()) break
if (handle.isDisposed()) {
handle.clearTurnCancellation(cancellation)
break
}
// A synchronous `running` listener can cancel before `runTurn`; balance the
// status only when no replacement prompt was queued by that listener.
if (handle.isCancelled()) {
handle.clearCancel()
if (cancellation.signal.aborted) {
handle.clearTurnCancellation(cancellation)
if (!handle.inbox.hasQueued) {
handle.setStatus('idle')
continue
}
cancellation = handle.installTurnCancellation()
}
// Idle injection can add a turn, so derive the next number from the log.
const turn = lastTurnNumber(session) + 1
let terminalStopped = false
try {
terminalStopped = await runTurn(ctx, events, handle, turn, transmission)
terminalStopped = await runTurn(ctx, events, handle, turn, transmission, cancellation)
} catch (error: unknown) {
// Pre-turn failure has no durable boundary to close; report it without appending outside a turn.
const err = toError(error)
@@ -184,11 +217,10 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
try {
events.emit('agent/error', turn, 0, err)
} catch { /* contained: a throwing agent/error listener must not kill the driver */ }
} finally {
handle.clearTurnCancellation(cancellation)
}
// Reset per iteration, including when a prompt arrives during the flush window.
handle.clearCancel()
// Late steering becomes queued input unless terminal policy stopped the turn.
for (const message of handle.inbox.drainSteering()) {
if (!terminalStopped) handle.inbox.enqueue(message)
@@ -200,9 +232,11 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
async function runTurn(
ctx: Context, events: AgentEventDispatch, handle: LoopHandle, turn: number, transmission: TransmissionLog,
cancellation: TurnCancellation,
): Promise<boolean> {
const agent = ctx.agents.requireInitiator()
const { session } = agent
const { signal } = cancellation
const drainSteering = (): boolean => {
const messages = handle.inbox.drainSteering()
for (const message of messages) {
@@ -246,8 +280,11 @@ async function runTurn(
}
}
// Pre-commit validation failure escapes rather than masquerading as a committed boundary.
// Retire cancellation authority before publishing the terminal event. The
// following durability flush is quiescent turn work, but no longer part of
// the cancellable turn lifetime.
const closeTurn = (): void => {
handle.clearTurnCancellation(cancellation)
session.append('turn/end', { turn, reason })
}
@@ -256,15 +293,17 @@ async function runTurn(
// matter what throws below; the catch + closeTurn guarantee it. A pre-commit
// veto leaves no turn/start in the log and therefore owes no turn/end.
session.append('turn/start', { turn, trigger })
interruptionCheckpoint(signal)
// The claimed message runs the `agent/prompt-submit` waterfall before it
// becomes a `user/message` — a hook can rewrite the prompt or block it.
// Recorded INSIDE the turn (after turn/start) so every event is turn-enclosed;
// turn/end is now owed, so a throwing prompt-submit listener (the waterfall
// throws) is caught below and the turn still closes.
const promptDecision = await events.waterfall(
'agent/prompt-submit', message.content, message.source,
'agent/prompt-submit', message.content, message.source, signal,
() => Promise.resolve<PromptDecision>({ kind: 'allow' }),
)
interruptionCheckpoint(signal)
if (promptDecision.kind === 'block') {
session.append('prompt/blocked', { content: message.content, source: message.source, reason: promptDecision.reason })
reason = { kind: 'rejected', reason: promptDecision.reason }
@@ -292,53 +331,28 @@ async function runTurn(
// the request.
drainSteering()
// The step's AbortController exists BEFORE any async pre-step work so a
// dispose() or cancel() — in a synchronous turn-start listener or an
// async listener whose effect fires before we block — always has an armed
// abort to cancel against. isDisposed below covers disposal, which does
// NOT set the cancel marker. Cleared on every exit path below.
const abort = new AbortController()
handle.setAbort(abort)
// Assemble once before pre-step so listener work and the request share one prompt value.
const assembly = await ctx.systemPrompt.assemble(assembleContextFor(agent))
const assembly = await ctx.systemPrompt.assemble(assembleContextFor(agent, signal))
interruptionCheckpoint(signal)
const fullSystemPrompt = renderPrompt(assembly)
// Cancellation or disposal during assembly ends the turn before any step opens.
if (handle.isCancelled() || handle.isDisposed()) {
handle.setAbort(undefined)
reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() }
break
}
// Compose the request-only prefix once per loop instance before the first
// request boundary. It precedes all derived history and is recorded only
// in the request header, not as session history.
if (transmission.sessionPrefix === undefined) {
const emptyPrefix: Message[] = deepFreeze([])
const composed = await events.waterfall(
'agent/session-prefix', emptyPrefix, abort.signal,
'agent/session-prefix', emptyPrefix, signal,
() => Promise.resolve(emptyPrefix),
)
// Never cache an interrupted composition; the next turn recomposes it.
if (handle.isCancelled() || handle.isDisposed()) {
handle.setAbort(undefined)
reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() }
break
}
interruptionCheckpoint(signal)
transmission.sessionPrefix = deepFreeze(structuredClone(composed))
}
// Await surface mutations outside the step before snapshotting history.
await events.serial('agent/pre-step', turn, step, abort.signal)
// Interruption landing during the pre-step seam: do not open an empty step.
if (handle.isCancelled() || handle.isDisposed()) {
handle.setAbort(undefined)
reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() }
break
}
await events.serial('agent/pre-step', turn, step, signal)
interruptionCheckpoint(signal)
// Snapshot the exact log prefix before step/start: the reconstruction
// boundary. Appends after this synchronous snapshot join the next request.
@@ -350,16 +364,8 @@ async function runTurn(
// are contained inside Session.append().
stepOpen = true
// Cancel landing in the step-start window: a synchronous `session/event`
// step/start listener can cancel after the step is already open. Check
// AFTER the step/start append and before `runStep`: drop the step, end the
// turn accordingly. closeStep balances the already-appended step/start.
if (handle.isCancelled() || handle.isDisposed()) {
handle.setAbort(undefined)
reason = handle.isDisposed() ? { kind: 'disposed' } : { kind: 'aborted', reason: handle.cancelReason() }
closeStep()
break
}
// A synchronous step/start observer can cancel after the step opened.
interruptionCheckpoint(signal)
let stepOutcome:
| { hadToolCalls: boolean; finish: FinishReason }
@@ -367,7 +373,7 @@ async function runTurn(
| { error: RequestError }
try {
stepOutcome = await runStep(
ctx, events, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, abort.signal)
ctx, events, handle, turn, step, assembly, fullSystemPrompt, boundaryMessages, transmission, signal)
} catch (error: unknown) {
if (error instanceof TerminalModelRequestFailure) {
stepOutcome = { requestError: error.requestError, failure: error.failure }
@@ -380,11 +386,9 @@ async function runTurn(
// Recovery observes a balanced failed step and the original provider
// error while the failed step's signal remains the active owner.
closeStep()
if (handle.isDisposed() || abort.signal.aborted) {
handle.setAbort(undefined)
reason = handle.isDisposed()
? { kind: 'disposed' }
: { kind: 'aborted', reason: String(abort.signal.reason) }
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted !== undefined) {
reason = interrupted
break
}
@@ -393,7 +397,7 @@ async function runTurn(
try {
recoveryDecision = await events.waterfall(
'agent/request-error', turn, step, stepOutcome.requestError,
stepOutcome.failure, requestFailureHistory, abort.signal,
stepOutcome.failure, requestFailureHistory, signal,
() => Promise.resolve(defaultDecision),
)
} catch (recoveryError: unknown) {
@@ -401,15 +405,11 @@ async function runTurn(
`agent "${agent.id}": request recovery failed at turn ${turn}, step ${step}: ${errorChain(recoveryError)}`,
)
}
handle.setAbort(undefined)
// Cancellation and disposal always win over either a recovery decision
// or a recovery-listener failure.
// eslint-disable-next-line @typescript-eslint/no-unnecessary-condition
if (handle.isDisposed() || abort.signal.aborted) {
reason = handle.isDisposed()
? { kind: 'disposed' }
: { kind: 'aborted', reason: String(abort.signal.reason) }
const recoveryInterrupted = interruptionTurnEndReason(handle, signal)
if (recoveryInterrupted !== undefined) {
reason = recoveryInterrupted
break
}
switch (recoveryDecision.action) {
@@ -431,17 +431,10 @@ async function runTurn(
// runLoop re-enqueues it as a queued message, so an abort-then-steer
// starts a fresh turn instead of being silently consumed.
closeStep()
handle.setAbort(undefined)
const { error } = stepOutcome
/* v8 ignore next -- narrow race: disposal while non-request step work throws. */
if (handle.isDisposed()) {
reason = { kind: 'disposed' }
} else if (abort.signal.aborted) {
/* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */
reason = { kind: 'aborted', reason: String(abort.signal.reason ?? 'aborted') }
} else {
failTurn(error)
}
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(error)
else reason = interrupted
break
}
@@ -455,48 +448,40 @@ async function runTurn(
const steered = drainSteering()
try {
await events.serial('agent/post-step', turn, step, abort.signal)
await events.serial('agent/post-step', turn, step, signal)
} catch (error: unknown) {
stepOutcome = { error: toError(error) }
}
if ('error' in stepOutcome) {
closeStep()
handle.setAbort(undefined)
/* v8 ignore next -- narrow race: disposal while a post-step listener throws. */
if (handle.isDisposed()) {
reason = { kind: 'disposed' }
} else if (abort.signal.aborted) {
/* v8 ignore next -- signal.reason always set by cancellation or disposal. */
reason = { kind: 'aborted', reason: String(abort.signal.reason ?? 'aborted') }
} else {
failTurn(stepOutcome.error)
}
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(stepOutcome.error)
else reason = interrupted
break
}
if (handle.isDisposed() || abort.signal.aborted) {
reason = handle.isDisposed()
? { kind: 'disposed' }
: { kind: 'aborted', reason: String(abort.signal.reason) }
const postStepInterrupted = interruptionTurnEndReason(handle, signal)
if (postStepInterrupted !== undefined) {
reason = postStepInterrupted
closeStep()
handle.setAbort(undefined)
break
}
closeStep()
handle.setAbort(undefined)
const defaultDecision: ContinuationDecision = { action: stepOutcome.hadToolCalls || steered ? 'continue' : 'stop' }
let decision: ContinuationDecision
try {
decision = await events.waterfall(
'agent/turn-continuation', turn, defaultDecision,
'agent/turn-continuation', turn, defaultDecision, signal,
() => Promise.resolve(defaultDecision),
)
interruptionCheckpoint(signal)
} catch (error: unknown) {
// A broken continuation plugin ends the turn, not the loop.
failTurn(toError(error))
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(toError(error))
else reason = interrupted
break
}
@@ -512,12 +497,15 @@ async function runTurn(
// Terminal policy is monotonic and runs after ordinary continuation folding.
let terminalStop = false
try {
const stop = await events.serial('agent/turn-stop', turn)
const stop = await events.serial('agent/turn-stop', turn, signal)
interruptionCheckpoint(signal)
terminalStop = stop !== undefined
} catch (error: unknown) {
// A broken terminal policy is an ordinary continuation failure: fail
// this turn closed while leaving the driver alive for later turns.
failTurn(toError(error))
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(toError(error))
else reason = interrupted
break
}
if (terminalStop) {
@@ -527,17 +515,7 @@ async function runTurn(
shouldContinue = false
}
// The marker catches cancellation after the step controller was cleared.
if (handle.isCancelled()) {
reason = { kind: 'aborted', reason: handle.cancelReason() }
break
}
if (!shouldContinue || handle.isDisposed()) {
/* v8 ignore next -- disposal during continuation-decision window is a narrow race; error-path disposal is covered elsewhere */
if (handle.isDisposed()) reason = { kind: 'disposed' }
break
}
if (!shouldContinue) break
}
// Normal / inline-error loop exit: close the turn.
@@ -547,12 +525,9 @@ async function runTurn(
const turnStartLogged = session.events.some(e => e.type === 'turn/start' && e.data.turn === turn)
if (!turnStartLogged) throw error
closeStep()
// Preserve an established disposal reason; otherwise report the failure.
if (handle.isDisposed() && !errorReported) { // eslint-disable-line @typescript-eslint/no-unnecessary-condition
reason = { kind: 'disposed' }
} else {
failTurn(toError(error))
}
const interrupted = interruptionTurnEndReason(handle, signal)
if (interrupted === undefined) failTurn(toError(error))
else reason = interrupted
closeTurn()
}
@@ -601,7 +576,10 @@ async function runStep(
: { provider: options.provider ?? '', model: options.model ?? '' }))
// Listener replacements are recorded in the request header before dispatch.
const config = await events.waterfall('agent/request', turn, step, seedConfig, () => Promise.resolve(seedConfig))
const config = await events.waterfall(
'agent/request', turn, step, seedConfig, signal, () => Promise.resolve(seedConfig),
)
interruptionCheckpoint(signal)
if (!config.provider || !config.model) {
throw new Error(`agent "${agent.id}" has no provider/model: set AgentOptions.provider and AgentOptions.model or supply both via the agent/request waterfall`)
}
@@ -638,8 +616,7 @@ async function runStep(
const stream = ctx.llm.stream(request)
try {
for await (const chunk of stream) {
/* v8 ignore next -- signal.reason always set: cancel()/disposal provide a default */
if (signal.aborted) throw new Error(String(signal.reason ?? 'aborted'))
interruptionCheckpoint(signal)
const chunkEvent = session.append('assistant/chunk', { turn, step, chunk })
chunkSeqs.push(chunkEvent.seq)
assembler.push(chunk)
@@ -649,6 +626,7 @@ async function runStep(
if (failure !== undefined && error instanceof Error) throw new TerminalModelRequestFailure(error, failure)
throw error
}
interruptionCheckpoint(signal)
// Normalize failure finish chunks into the same path as thrown stream errors.
const stepError = finishError(assembler.finish)
@@ -679,9 +657,11 @@ async function runStep(
// A rejected result still records the successful provider call without retaining rejected output.
const processStepResult = async (assembledContent: ContentBlock[], message: Message): Promise<Message> => {
try {
return await events.waterfall(
'agent/step-result', turn, step, message, () => Promise.resolve(message),
const processed = await events.waterfall(
'agent/step-result', turn, step, message, signal, () => Promise.resolve(message),
)
interruptionCheckpoint(signal)
return processed
} catch (error: unknown) {
recordAssistantMessage(assembledContent, { ...message, content: [] }, false)
throw error

6
packages/core/agent-loop/src/tool-calls.ts
View File

@@ -13,7 +13,7 @@ import type { Context } from 'cordis'
import { assertNever, type ToolCallBlock } from '@deepseek-ai/dsh-llm'
import type { HookContext } from '@deepseek-ai/dsh-agent'
import type { Session } from '@deepseek-ai/dsh-session'
import { TOOL_REGISTRY_SCHEDULER, type ToolExecutionInput, type ToolExecutionMode, type ToolExecutionResult, type ToolRunContext } from '@deepseek-ai/dsh-tools'
import { TOOL_ABORTED_BEFORE_DISPATCH, TOOL_REGISTRY_SCHEDULER, type ToolExecutionInput, type ToolExecutionMode, type ToolExecutionResult, type ToolRunContext } from '@deepseek-ai/dsh-tools'
/** One tool call after argument parsing, ready to schedule. */
interface PlannedCall {
@@ -217,9 +217,9 @@ async function runGroup(
function appendSkippedToolCall(session: Session, turn: number, step: number, block: ToolCallBlock): void {
const callSeq = appendToolCall(session, turn, step, block)
appendToolResult(session, turn, step, block, {
content: [{ type: 'text', text: 'Error: tool call skipped because the step was aborted before execution' }],
content: [{ type: 'text', text: 'Error: tool call aborted before dispatch' }],
isError: true,
error: { name: 'AbortError', code: 'ABORTED' },
error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH },
}, callSeq)
}

77
packages/core/agent-loop/tests/agent-initiator.spec.ts
View File

@@ -9,6 +9,8 @@ import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
const testToolSignal = new AbortController().signal
interface Harness {
ctx: Context
agentsFiber: Fiber
@@ -142,6 +144,80 @@ describe('AgentLoop initiator scope', () => {
await ctx.fiber.dispose()
})
it('keeps initiator identity minimal while one explicit signal spans each turn seam', async () => {
const adapter = new MockAdapter([
toolCallResponse('observe-call', 'observe', {}),
textResponse('first done'),
textResponse('second done'),
])
const { ctx } = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('signal-owner'), { provider: 'mock', model: 'mock' })
let signals: AbortSignal[] = []
const capture = (signal: AbortSignal | undefined): void => {
if (signal === undefined) throw new Error('turn seam omitted its explicit signal')
expect(ctx.agents.requireInitiator()).toBe(agent)
signals.push(signal)
}
ctx.on('system-prompt/assemble', async (_assembly, context, next) => {
if (context.agent === agent) capture(context.signal)
return next()
})
ctx.on('agent/prompt-submit', async (subject, _content, _source, signal, next) => {
if (subject === agent) capture(signal)
return next()
})
ctx.on('agent/session-prefix', async (subject, _prefix, signal, next) => {
if (subject === agent) capture(signal)
return next()
})
ctx.on('agent/pre-step', (subject, _turn, _step, signal) => {
if (subject === agent) capture(signal)
})
ctx.on('agent/request', async (subject, _turn, _step, _config, signal, next) => {
if (subject === agent) capture(signal)
return next()
})
ctx.on('agent/step-result', async (subject, _turn, _step, _message, signal, next) => {
if (subject === agent) capture(signal)
return next()
})
ctx.on('agent/turn-continuation', async (subject, _turn, _decision, signal, next) => {
if (subject === agent) capture(signal)
return next()
})
ctx.on('agent/turn-stop', (subject, _turn, signal) => {
if (subject === agent) capture(signal)
})
ctx.tools.register(defineTool({
name: 'observe',
description: 'observe explicit turn state',
parameters: {},
execute: async (_args, exec) => {
capture(exec.signal)
return [{ type: 'text', text: 'observed' }]
},
}))
const firstIdle = waitForIdle(ctx, agent)
send(agent, 'first')
await firstIdle
const firstSignal = signals[0]
expect(firstSignal).toBeDefined()
expect(new Set([...signals, ...adapter.requests.slice(0, 2).map(request => request.signal!)])).toEqual(new Set([firstSignal]))
signals = []
const secondIdle = waitForIdle(ctx, agent)
send(agent, 'second')
await secondIdle
const secondSignal = signals[0]
expect(secondSignal).toBeDefined()
expect(new Set([...signals, adapter.requests[2]!.signal!])).toEqual(new Set([secondSignal]))
expect(secondSignal).not.toBe(firstSignal)
expect(ctx.agents.currentInitiator()).toBeUndefined()
await ctx.fiber.dispose()
})
it('keeps child setup under the parent boundary and restores the parent while the child driver remains active', async () => {
const adapter = new MockAdapter([
toolCallResponse('spawn', 'spawn-child', {}),
@@ -239,6 +315,7 @@ describe('AgentLoop initiator scope', () => {
}))
const direct = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('direct'),
name: 'agentless-probe',
arguments: {},

2
packages/core/agent-loop/tests/agent.spec.ts
View File

@@ -345,7 +345,7 @@ describe('Agent', () => {
expect(settled).toBe(false)
await waitForStatus(ctx, agent, 'running')
agent.cancel('done')
agent.cancel({ kind: 'user' })
await idle
expect(settled).toBe(true)
expect(agent.status).toBe('idle')

316
packages/core/agent-loop/tests/cancel.spec.ts
View File

@@ -1,9 +1,8 @@
/**
* Tests for the queue-aware `Agent.cancel()` primitive. `cancel()` is the broad verb — it
* clears queued + steering work, aborts an in-flight step, and drops a turn about to start —
* whereas a bare step abort (the loop's private `AbortController`) kills only the current step
* and leaves the queue intact. The suite covers every landing window plus marker
* reset and `whenIdle()` quiescence.
* clears queued + steering work, aborts the active turn, and drops work not yet claimed by the
* driver without leaking cancellation into a replacement prompt. The suite covers every landing
* window plus signal reset and `whenIdle()` quiescence.
* @module dsh-agent-loop/tests/cancel
*/
@@ -12,7 +11,7 @@ import { Context } from 'cordis'
import LlmService, { type Message } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool } from '@deepseek-ai/dsh-tools'
import ToolRegistry, { defineTool, TOOL_ABORTED_BEFORE_DISPATCH } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse, toolCallResponse } from './mock-adapter.ts'
@@ -61,22 +60,22 @@ describe('Agent.cancel()', () => {
const agent = ctx.agentLoop.create(SessionId('cancel-event'), { provider: 'mock', model: 'mock' })
const warned = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => {})
const seen: string[] = []
ctx.on('agent/cancel-requested', (subject, reason) => {
ctx.on('agent/cancel-requested', (subject, cause) => {
if (subject !== agent) return
seen.push(`first:${reason}`)
seen.push(`first:${cause.kind}`)
subject.send([{ type: 'text', text: 'queued by cancel observer' }])
throw new Error('observer failed')
})
ctx.on('agent/cancel-requested', (subject, reason) => {
if (subject === agent) seen.push(`second:${reason}`)
ctx.on('agent/cancel-requested', (subject, cause) => {
if (subject === agent) seen.push(`second:${cause.kind}`)
})
send(agent, 'drop me')
agent.cancel()
await new Promise(resolve => setTimeout(resolve, 30))
agent.cancel('idle no-op')
agent.cancel({ kind: 'parent' })
expect(seen).toEqual(['first:cancelled', 'second:cancelled'])
expect(seen).toEqual(['first:user', 'second:user'])
expect(userTexts(agent)).toEqual([])
expect(adapter.requests).toHaveLength(0)
expect(warned).toHaveBeenCalledWith(expect.stringContaining('agent/cancel-requested'))
@@ -89,7 +88,7 @@ describe('Agent.cancel()', () => {
// The loop is parked at the idle wait with nothing queued. A cancel here must
// NOT arm the marker — otherwise the next legitimate prompt would be dropped.
agent.cancel('nothing to cancel')
agent.cancel({ kind: 'user' })
send(agent, 'real prompt')
await waitForIdle(ctx, agent)
@@ -108,7 +107,7 @@ describe('Agent.cancel()', () => {
// resumed). Cancel in that pre-step window: the queued turn must not run.
send(agent, 'drop me first')
send(agent, 'drop me second')
agent.cancel('pre-step')
agent.cancel({ kind: 'user' })
// Give the loop a chance to wake and process the cancel.
await new Promise(r => setTimeout(r, 30))
@@ -157,7 +156,7 @@ describe('Agent.cancel()', () => {
// drops the turn before it runs; the skip path must settle it directly.
send(agent, 'q')
const idle = agent.whenIdle()
agent.cancel('pre-step')
agent.cancel({ kind: 'user' })
// Must resolve (not hang). A timeout makes the failure a clear test failure.
await Promise.race([
@@ -186,7 +185,7 @@ describe('Agent.cancel()', () => {
// before its resolved waitForQueued continuation checks cancellation.
queueMicrotask(() => {
queueMicrotask(() => {
agent.cancel('between turns')
agent.cancel({ kind: 'user' })
cancelled.resolve(undefined)
})
})
@@ -236,7 +235,7 @@ describe('Agent.cancel()', () => {
ctx.on('agent/error', (subject, _turn, _step, error) => {
if (subject !== agent || error.message !== 'first flush failed') return
queueMicrotask(() => {
queueMicrotask(() => { agent.cancel('between turns') })
queueMicrotask(() => { agent.cancel({ kind: 'user' }) })
})
})
@@ -277,7 +276,7 @@ describe('Agent.cancel()', () => {
requests: adapter.requests.length,
turns: agent.session.events.filter(event => event.type === 'turn/start').length,
}))
agent.cancel('idle listener')
agent.cancel({ kind: 'user' })
replacementRegistered.resolve(undefined)
})
@@ -307,7 +306,7 @@ describe('Agent.cancel()', () => {
ctx.on('agent/status', (subject, status) => {
if (subject !== agent || status !== 'idle' || replacementIdle !== undefined) return
send(agent, 'cancelled replacement')
agent.cancel('idle listener')
agent.cancel({ kind: 'user' })
send(agent, 'surviving replacement')
replacementIdle = agent.whenIdle()
replacementRegistered.resolve(undefined)
@@ -334,16 +333,16 @@ describe('Agent.cancel()', () => {
await new Promise(r => setTimeout(r, 30))
expect(agent.status).toBe('running')
send(agent, 'queued tail')
agent.cancel('mid-step')
agent.cancel({ kind: 'user' })
await waitForIdle(ctx, agent)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'mid-step' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
expect(userTexts(agent)).toEqual(['go'])
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
expect(adapter.requests).toHaveLength(1)
})
it('cancel() with no reason defaults to "cancelled" when aborting an in-flight step', async () => {
it('cancel() with no cause defaults to user when aborting an active turn', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
@@ -353,10 +352,10 @@ describe('Agent.cancel()', () => {
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
agent.cancel() // no reason → default 'cancelled'
agent.cancel()
await waitForIdle(ctx, agent)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'cancelled' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
})
it('cancel from an assistant/message observer skips execution but balances replay', async () => {
@@ -378,7 +377,7 @@ describe('Agent.cancel()', () => {
const agent = ctx.agentLoop.create(SessionId('cancel-after-assistant-message'), { provider: 'mock', model: 'mock' })
const dispose = ctx.on('session/event', (session, event) => {
if (session === agent.session && event.type === 'assistant/message') {
agent.cancel('cancelled after assistant message')
agent.cancel({ kind: 'user' })
}
})
@@ -390,14 +389,14 @@ describe('Agent.cancel()', () => {
dispose()
expect(executions).toBe(0)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'cancelled after assistant message' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
const call = agent.session.events.find(event => event.type === 'tool/call')
const result = agent.session.events.find(event => event.type === 'tool/result')
expect(call?.type === 'tool/call' ? call.data.callId : undefined).toBe('c1')
expect(result?.type === 'tool/result' ? result.data : undefined).toMatchObject({
callId: 'c1',
isError: true,
error: { name: 'AbortError', code: 'ABORTED' },
error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH },
})
send(agent, 'continue safely')
@@ -407,7 +406,7 @@ describe('Agent.cancel()', () => {
.find(block => block.type === 'tool-result')
expect(replayedResult).toMatchObject({ toolCallId: 'c1', isError: true })
expect(reasons).toEqual([
{ kind: 'aborted', reason: 'cancelled after assistant message' },
{ kind: 'aborted' },
{ kind: 'completed' },
])
})
@@ -420,7 +419,7 @@ describe('Agent.cancel()', () => {
// First turn hangs; cancel it mid-step.
send(agent, 'first')
await new Promise(r => setTimeout(r, 30))
agent.cancel('cancel first')
agent.cancel({ kind: 'user' })
await waitForIdle(ctx, agent)
// The marker must have been reset after the cancelled turn — a fresh prompt
@@ -445,7 +444,7 @@ describe('Agent.cancel()', () => {
let streamed = false
ctx.on('session/event', (_s, event) => { if (event.type === 'assistant/chunk') streamed = true })
ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next) => {
agent.cancel('from prefix composition')
agent.cancel({ kind: 'user' })
return next()
})
@@ -456,7 +455,7 @@ describe('Agent.cancel()', () => {
await waitForIdle(ctx, agent)
expect(streamed).toBe(false)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'from prefix composition' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
})
it('disposal from inside the agent/session-prefix waterfall ends the turn disposed (prefix-composition window)', async () => {
@@ -508,7 +507,7 @@ describe('Agent.cancel()', () => {
ctx.on('agent/session-prefix', async (_agent, _prefix, _signal, next): Promise<Message[]> => {
compositions += 1
if (compositions === 1) {
agent.cancel('mid-composition')
agent.cancel({ kind: 'user' })
return next()
}
return [opener, ...await next()]
@@ -536,7 +535,7 @@ describe('Agent.cancel()', () => {
let streamed = false
ctx.on('session/event', (_s, event) => { if (event.type === 'assistant/chunk') streamed = true })
const dispose = ctx.on('session/event', (session, event) => {
if (session === agent.session && event.type === 'turn/start') agent.cancel('from turn-start')
if (session === agent.session && event.type === 'turn/start') agent.cancel({ kind: 'user' })
})
const reasons: TurnEndReason[] = []
@@ -547,10 +546,10 @@ describe('Agent.cancel()', () => {
dispose()
// No step streamed (the model never ran), and the turn ended aborted with
// the CALLER's reason — the marker carries `cancel(reason)` through even
// the caller's cause — the marker carries `cancel(cause)` through even
// though no AbortController observed it in this window.
expect(streamed).toBe(false)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'from turn-start' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
})
it('cancel from a synchronous step/start session-event listener drops the step (post-step-start window)', async () => {
@@ -565,7 +564,7 @@ describe('Agent.cancel()', () => {
let streamed = false
ctx.on('session/event', (_s, event) => { if (event.type === 'assistant/chunk') streamed = true })
const dispose = ctx.on('session/event', (session, event) => {
if (session === agent.session && event.type === 'step/start') agent.cancel('from step-start')
if (session === agent.session && event.type === 'step/start') agent.cancel({ kind: 'user' })
})
const reasons: TurnEndReason[] = []
@@ -575,10 +574,10 @@ describe('Agent.cancel()', () => {
await waitForIdle(ctx, agent)
dispose()
// No step streamed, the turn ended aborted with the caller's reason, and the
// No step streamed, the turn ended with the coarse aborted outcome, and the
// log is balanced (the open step was closed by the cancel branch).
expect(streamed).toBe(false)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'from step-start' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
const types = agent.session.events.map(e => e.type)
expect(types.filter(t => t === 'step/start').length).toBe(types.filter(t => t === 'step/end').length)
})
@@ -636,11 +635,11 @@ describe('Agent.cancel()', () => {
})
let continued = false
ctx.on('agent/turn-continuation', async (subject, _turn, _default, next) => {
ctx.on('agent/turn-continuation', async (subject, _turn, _default, _signal, next) => {
if (subject === agent && !continued) {
continued = true
agent.cancel('from continuation')
return { action: 'continue' as const } // vote to continue — the post-waterfall marker check must override
agent.cancel({ kind: 'user' })
return { action: 'continue' as const }
}
return next()
})
@@ -649,10 +648,9 @@ describe('Agent.cancel()', () => {
await waitForIdle(ctx, agent)
// Only ONE step ran (the second was cancelled in the continuation window),
// and the turn ended aborted with the CALLER's reason (carried by the
// marker, since the finished step's AbortController was already cleared).
// and the shared turn signal classified the durable outcome as aborted.
expect(steps).toBe(1)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'from continuation' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
})
it('cancel from a synchronous agent/status(running) listener drops the turn (window 2)', async () => {
@@ -665,7 +663,7 @@ describe('Agent.cancel()', () => {
let streamed = false
ctx.on('session/event', (_s, event) => { if (event.type === 'assistant/chunk') streamed = true })
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject === agent && status === 'running') agent.cancel('from running listener')
if (subject === agent && status === 'running') agent.cancel({ kind: 'user' })
})
send(agent, 'go')
@@ -688,7 +686,7 @@ describe('Agent.cancel()', () => {
const dispose = ctx.on('agent/status', (subject, status) => {
if (subject !== agent || status !== 'running' || replaced) return
replaced = true
agent.cancel('drop A')
agent.cancel({ kind: 'user' })
send(agent, 'B')
})
@@ -713,7 +711,7 @@ describe('Agent.cancel()', () => {
send(agent, 'A') // queues A (status still idle, loop microtask pending)
const idle = agent.whenIdle() // registers a waiter (idle + hasQueued → no fast path)
agent.cancel('drop A') // arms marker, clears A
agent.cancel({ kind: 'user' }) // arms marker, clears A
send(agent, 'B') // B races in before the loop resumes
// whenIdle() must resolve only after B's turn fully ran — by which point B's user message
@@ -736,7 +734,7 @@ describe('Agent.cancel()', () => {
// Steer (joins the running turn's steering FIFO), then cancel: the steering
// must be dropped, NOT re-enqueued as a new queued turn.
agent.steer([{ type: 'text', text: 'steer text' }])
agent.cancel('cancel with steering')
agent.cancel({ kind: 'user' })
await waitForIdle(ctx, agent)
// After the cancelled turn settles, the agent is idle with NO follow-up turn
@@ -752,4 +750,228 @@ describe('Agent.cancel()', () => {
.flatMap(b => b.type === 'text' ? [b.text] : [])
expect(flat).not.toContain('steer text')
})
it('keeps replacement work queued synchronously by an abort observer', async () => {
const adapter = new MockAdapter(['hang', textResponse('replacement reply')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('abort-observer-replacement'), { provider: 'mock', model: 'mock' })
send(agent, 'original')
await expect.poll(() => adapter.requests.length).toBe(1)
const signal = adapter.requests[0]?.signal
if (signal === undefined) throw new Error('model request omitted its turn signal')
signal.addEventListener('abort', () => { send(agent, 'replacement') }, { once: true })
const idle = waitForIdle(ctx, agent)
agent.cancel({ kind: 'user' })
await Promise.race([
idle,
new Promise((_resolve, reject) => {
setTimeout(() => {
reject(new Error(`replacement did not settle: ${JSON.stringify({
status: agent.status,
requests: adapter.requests.length,
users: userTexts(agent),
events: agent.session.events.map(event => event.type),
})}`))
}, 1000)
}),
])
expect(adapter.requests).toHaveLength(2)
expect(userTexts(agent)).toEqual(['original', 'replacement'])
const reasons = agent.session.events
.filter(event => event.type === 'turn/end')
.map(event => event.type === 'turn/end' ? event.data.reason : undefined)
expect(reasons).toEqual([{ kind: 'aborted' }, { kind: 'completed' }])
})
it('keeps the first typed cause for an active turn and detaches the runtime reason', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('typed-first-wins'), { provider: 'mock', model: 'mock' })
const supplied: { kind: 'parent' | 'user' } = { kind: 'parent' }
send(agent, 'go')
await expect.poll(() => adapter.requests.length).toBe(1)
agent.cancel(supplied)
supplied.kind = 'user'
agent.cancel({ kind: 'user' })
await waitForIdle(ctx, agent)
const runtimeReason: unknown = adapter.requests[0]?.signal?.reason
expect(runtimeReason).toEqual({ kind: 'parent' })
expect(runtimeReason).not.toBe(supplied)
expect(Object.isFrozen(runtimeReason)).toBe(true)
const turnEnd = agent.session.events.findLast(event => event.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted' })
})
it('retires turn cancellation before terminal publication and a blocked durability flush', async () => {
const adapter = new MockAdapter([textResponse('done')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('terminal-cancellation-authority'), { provider: 'mock', model: 'mock' })
const flushStarted = Promise.withResolvers<undefined>()
const releaseFlush = Promise.withResolvers<undefined>()
let abortedDuringTurnEnd: boolean | undefined
let cancelNotifications = 0
ctx.on('agent/cancel-requested', (subject) => {
if (subject === agent) cancelNotifications += 1
})
ctx.on('session/event', (session, event) => {
if (session !== agent.session || event.type !== 'turn/end') return
const signal = adapter.requests[0]?.signal
if (signal === undefined) throw new Error('model request omitted its turn signal')
agent.cancel({ kind: 'user' })
abortedDuringTurnEnd = signal.aborted
})
ctx.on('session/flush', async (session) => {
if (session !== agent.session) return
flushStarted.resolve(undefined)
await releaseFlush.promise
})
send(agent, 'finish before persistence drains')
await flushStarted.promise
const signal = adapter.requests[0]?.signal
if (signal === undefined) throw new Error('model request omitted its turn signal')
const idle = agent.whenIdle()
agent.cancel({ kind: 'user' })
expect(abortedDuringTurnEnd).toBe(false)
expect(signal.aborted).toBe(false)
expect(cancelNotifications).toBe(0)
expect(agent.session.events.findLast(event => event.type === 'turn/end')).toMatchObject({
data: { reason: { kind: 'completed' } },
})
releaseFlush.resolve(undefined)
await idle
expect(agent.status).toBe('idle')
})
it('records disposed when lifecycle teardown races an already-requested cancel', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
const handle = await ctx.agents.create({
sessionId: SessionId('cancel-dispose-race'),
agentOptions: { provider: 'mock', model: 'mock' },
})
const { agent } = handle
send(agent, 'go')
await expect.poll(() => adapter.requests.length).toBe(1)
agent.cancel({ kind: 'user' })
await handle.dispose()
const turnEnd = agent.session.events.findLast(event => event.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'disposed' })
})
it.each([
'prompt-submit',
'system-prompt',
'session-prefix',
'pre-step',
'request',
'step-result',
'post-step',
'turn-continuation',
'turn-stop',
'tool',
] as const)('lets a cooperative %s boundary settle from the explicit turn signal', async (stage) => {
const adapter = new MockAdapter(stage === 'tool'
? [toolCallResponse('blocked-tool', 'blocked', {})]
: [textResponse('done')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId(`cooperative-${stage}`), { provider: 'mock', model: 'mock' })
const started = Promise.withResolvers<undefined>()
const blockUntilAbort = async (signal: AbortSignal): Promise<void> => {
started.resolve(undefined)
if (signal.aborted) return
await new Promise<void>((resolve) => {
signal.addEventListener('abort', () => { resolve() }, { once: true })
})
}
switch (stage) {
case 'prompt-submit':
ctx.on('agent/prompt-submit', async (subject, _content, _source, signal, next) => {
if (subject === agent) await blockUntilAbort(signal)
return next()
})
break
case 'system-prompt':
ctx.on('system-prompt/assemble', async (_assembly, context, next) => {
if (context.agent === agent) {
if (context.signal === undefined) throw new Error('turn assembly omitted its signal')
await blockUntilAbort(context.signal)
}
return next()
})
break
case 'session-prefix':
ctx.on('agent/session-prefix', async (subject, _prefix, signal, next) => {
if (subject === agent) await blockUntilAbort(signal)
return next()
})
break
case 'pre-step':
ctx.on('agent/pre-step', async (subject, _turn, _step, signal) => {
if (subject === agent) await blockUntilAbort(signal)
})
break
case 'request':
ctx.on('agent/request', async (subject, _turn, _step, _config, signal, next) => {
if (subject === agent) await blockUntilAbort(signal)
return next()
})
break
case 'step-result':
ctx.on('agent/step-result', async (subject, _turn, _step, _message, signal, next) => {
if (subject === agent) await blockUntilAbort(signal)
return next()
})
break
case 'post-step':
ctx.on('agent/post-step', async (subject, _turn, _step, signal) => {
if (subject !== agent) return
await blockUntilAbort(signal)
throw new Error('post-step failed after cancellation')
})
break
case 'turn-continuation':
ctx.on('agent/turn-continuation', async (subject, _turn, _decision, signal, next) => {
if (subject === agent) await blockUntilAbort(signal)
return next()
})
break
case 'turn-stop':
ctx.on('agent/turn-stop', async (subject, _turn, signal) => {
if (subject === agent) await blockUntilAbort(signal)
})
break
case 'tool':
ctx.tools.register(defineTool({
name: 'blocked',
description: 'wait for cancellation',
parameters: {},
execute: async (_args, exec) => {
if (exec.signal === undefined) throw new Error('tool execution omitted its signal')
await blockUntilAbort(exec.signal)
return [{ type: 'text', text: 'cancelled' }]
},
}))
break
}
send(agent, 'go')
await started.promise
const idle = waitForIdle(ctx, agent)
agent.cancel({ kind: 'user' })
await idle
const turnEnd = agent.session.events.findLast(event => event.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted' })
await ctx.fiber.dispose()
})
})

77
packages/core/agent-loop/tests/contract-regressions.spec.ts
View File

@@ -3,7 +3,7 @@ import { Context } from 'cordis'
import LlmService, { CallId, ContentBlock, MessageSource, ProviderRequestId, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { Session, SessionEvent, SessionId, TurnEndReason } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry, { defineTool, type PostToolDecision } from '@deepseek-ai/dsh-tools'
import ToolRegistry, { defineTool, TOOL_ABORTED, TOOL_ABORTED_BEFORE_DISPATCH, type PostToolDecision } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent, type ContinuationDecision } from '@deepseek-ai/dsh-agent'
import AgentLoop, { DEFAULT_MAX_PARALLEL_TOOL_CALLS } from '@deepseek-ai/dsh-agent-loop'
import { prepareReactLoopAgent } from '../src/agent.ts'
@@ -73,7 +73,7 @@ describe('session log records what agent/step-result actually produced', () => {
// Plugin rewrites the message: replaces the text AND adds a tool call.
let rewritten = false
ctx.on('agent/step-result', async (_agent, _turn, _step, _message, next) => {
ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _signal, next) => {
if (rewritten) return next()
rewritten = true
return {
@@ -214,7 +214,7 @@ describe('successful provider completion survives agent/step-result failure', ()
})
describe('abort during tool execution ends the turn', () => {
it('balances an aborted tool batch through context, steering, and post-step before closing', async () => {
it('balances a cancelled tool batch through context and post-step before closing', async () => {
const adapter = new MockAdapter([
// model asks for two tool calls in one step
[
@@ -239,8 +239,7 @@ describe('abort during tool execution ends the turn', () => {
[{ type: 'text', text: 'steering before abort' }],
{ source: { kind: 'plugin', plugin: 'abort-test' } },
)
// Exercise bare step abort without `cancel()` clearing queued work.
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
agent.cancel({ kind: 'user' })
return [{ type: 'text', text: 'done' }]
},
}))
@@ -269,7 +268,10 @@ describe('abort during tool execution ends the turn', () => {
case 'assistant/message': order.push('assistant/message'); break
case 'tool/call': order.push(`tool/call:${event.data.callId}`); break
case 'tool/result': {
const outcome = event.data.error?.code === 'ABORTED' ? 'synthetic-aborted' : 'real'
const outcome = event.data.error?.code === TOOL_ABORTED
|| event.data.error?.code === TOOL_ABORTED_BEFORE_DISPATCH
? 'aborted'
: 'completed'
order.push(`tool/result:${event.data.callId}:${outcome}`)
break
}
@@ -300,25 +302,29 @@ describe('abort during tool execution ends the turn', () => {
expect(order).toEqual([
'assistant/message',
'tool/call:c1',
'tool/result:c1:real',
'tool/result:c1:aborted',
'tool/call:c2',
'tool/result:c2:synthetic-aborted',
'tool/result:c2:aborted',
'context/message',
'steering/message',
'agent/post-step',
'step/end',
'turn/end:aborted',
])
expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
const calls = agent.session.events.filter(event => event.type === 'tool/call')
const results = agent.session.events.filter(event => event.type === 'tool/result')
expect(calls.map(event => event.data.callId)).toEqual([CallId('c1'), CallId('c2')])
expect(results).toHaveLength(2)
expect(results[0]!.data).toMatchObject({ callId: CallId('c1'), isError: false })
expect(results[0]!.data).toMatchObject({
callId: CallId('c1'),
content: [{ type: 'text', text: 'Error: tool call aborted' }],
isError: true,
error: { name: 'AbortError', code: TOOL_ABORTED },
})
expect(results[1]!.data).toMatchObject({
callId: CallId('c2'),
isError: true,
error: { name: 'AbortError', code: 'ABORTED' },
error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH },
})
})
@@ -332,7 +338,7 @@ describe('abort during tool execution ends the turn', () => {
parameters: {},
async execute() {
agent.inject([{ type: 'text', text: 'accepted before abort' }], { source: { kind: 'plugin', plugin: 'test' } })
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
agent.cancel({ kind: 'user' })
return [{ type: 'text', text: 'done' }]
},
}))
@@ -385,7 +391,7 @@ describe('abort during tool execution ends the turn', () => {
description: '',
parameters: {},
async execute() {
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
agent.cancel({ kind: 'user' })
return [{ type: 'text', text: 'aborted' }]
},
}))
@@ -478,7 +484,7 @@ describe('abort during tool execution ends the turn', () => {
description: '',
parameters: {},
async execute() {
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
agent.cancel({ kind: 'user' })
return [{ type: 'text', text: 'done' }]
},
}))
@@ -517,7 +523,7 @@ describe('steering from late extension points is never stranded', () => {
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let steeredOnce = false
ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, next) => {
ctx.on('agent/turn-continuation', async (_agent, _turn, _decision, _signal, next) => {
if (!steeredOnce) {
steeredOnce = true
agent.steer([{ type: 'text', text: 'one more thing' }])
@@ -591,26 +597,6 @@ describe('steering from late extension points is never stranded', () => {
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('too late for this turn')
})
it('steering queued during an aborted step is re-delivered, not silently consumed', async () => {
const adapter = new MockAdapter(['hang', textResponse('recovered')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
agent.steer([{ type: 'text', text: 'redirect' }])
// Abort ONLY the in-flight step, via its AbortController directly — NOT
// cancel(), which clears the inbox and would drop the queued steering this
// test proves survives a step abort. There is no public step-only abort
// verb (cancel() is the only public stop primitive), so reach the private
// controller the loop registered.
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('user interrupt')
await waitForIdle(ctx, agent)
// a new turn ran with the steering content delivered as a message
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('redirect')
})
})
describe('plugin exceptions are contained', () => {
@@ -767,7 +753,7 @@ describe('adapter registration, routing, and accepted-input ownership', () => {
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), {}) // no model — router plugin decides
ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => {
ctx.on('agent/request', async (_agent, _turn, _step, config, _signal) => {
return { ...config, provider: 'mock', model: 'mock' }
})
@@ -1481,7 +1467,7 @@ describe('surface: assistant/message records exact empty provenance when no chun
await mountInvariants(ctx)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _next) => ({
ctx.on('agent/step-result', async (_agent, _turn, _step, _message, _signal) => ({
role: 'assistant' as const,
content: [{ type: 'text' as const, text: 'injected' }],
}))
@@ -1584,7 +1570,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
send(agent, 'go')
await new Promise(r => setTimeout(r, 50))
agent.cancel('user cancelled during assembly')
agent.cancel({ kind: 'user' })
releaseAssemble()
await waitForIdle(ctx, agent)
@@ -1596,15 +1582,12 @@ describe('disposal and cancellation during pre-step assembly', () => {
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
const turnEnd = e.findLast(x => x.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({
kind: 'aborted',
reason: 'user cancelled during assembly',
})
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted' })
expect(e.some(x => x.type === 'step/start')).toBe(false)
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
expect(e.some(x => x.type === 'assistant/message')).toBe(false)
expect(adapter.requests).toHaveLength(0)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'user cancelled during assembly' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
})
it('disposal during agent/pre-step seam ends the turn disposed', { timeout: 15000 }, async () => {
@@ -1689,7 +1672,7 @@ describe('disposal and cancellation during pre-step assembly', () => {
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
agent.cancel('user cancelled')
agent.cancel({ kind: 'user' })
releasePreStep()
await waitForIdle(ctx, agent)
@@ -1700,10 +1683,10 @@ describe('disposal and cancellation during pre-step assembly', () => {
expect(e.filter(x => x.type === 'turn/start')).toHaveLength(1)
expect(e.filter(x => x.type === 'turn/end')).toHaveLength(1)
const turnEnd = e.findLast(x => x.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted', reason: 'user cancelled' })
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted' })
expect(e.some(x => x.type === 'step/start')).toBe(false)
expect(e.some(x => x.type === 'assistant/chunk')).toBe(false)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'user cancelled' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
})
it('disposal during assembly does not leak an LLM call or append assistant/chunk', { timeout: 15000 }, async () => {

4
packages/core/agent-loop/tests/coverage-edges.spec.ts
View File

@@ -170,7 +170,7 @@ describe('toError normalization', () => {
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let threwOnce = false
ctx.on('agent/request', async (_agent, _turn, _step, _options, _next) => {
ctx.on('agent/request', async (_agent, _turn, _step, _options, _signal, _next) => {
if (!threwOnce) {
threwOnce = true
throw { code: 500 } // non-Error throw, goes through runStep catch
@@ -200,7 +200,7 @@ describe('coded error data emission', () => {
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let threwOnce = false
ctx.on('agent/request', async (_agent, _turn, _step, _options, next) => {
ctx.on('agent/request', async (_agent, _turn, _step, _options, _signal, next) => {
if (!threwOnce) {
threwOnce = true
throw new LlmError('server overloaded', 'RATE_LIMIT')

8
packages/core/agent-loop/tests/interception.spec.ts
View File

@@ -56,7 +56,7 @@ describe('agent/prompt-submit', () => {
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const seen: string[] = []
ctx.on('agent/prompt-submit', async (_agent, content, _source, next) => {
ctx.on('agent/prompt-submit', async (_agent, content, _source, _signal, next) => {
seen.push(content.map(b => (b.type === 'text' ? b.text : '')).join(''))
return next()
})
@@ -182,7 +182,7 @@ describe('agent/prompt-submit', () => {
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise<PromptDecision> => {
ctx.on('agent/prompt-submit', async (_agent, content, _source, _signal, next): Promise<PromptDecision> => {
const text = content.map(b => (b.type === 'text' ? b.text : '')).join('')
return text === 'secret' ? { kind: 'block', reason: 'policy: no secrets' } : next()
})
@@ -497,7 +497,7 @@ describe('agent/turn-continuation (ContinuationDecision)', () => {
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let forced = false
ctx.on('agent/turn-continuation', async (_agent, _turn, _default, next): Promise<ContinuationDecision> => {
ctx.on('agent/turn-continuation', async (_agent, _turn, _default, _signal, next): Promise<ContinuationDecision> => {
if (!forced) {
forced = true
return { action: 'continue', reason: { content: [{ type: 'text', text: 'keep going on the goal' }], source: { kind: 'plugin', plugin: 'goal' } } }
@@ -662,7 +662,7 @@ describe('worked example: a native hook plugin is just a cordis plugin on the se
)
})
// 2. PromptSubmit: block a forbidden prompt, annotate the rest.
ctx.on('agent/prompt-submit', async (_agent, content, _source, next): Promise<PromptDecision> => {
ctx.on('agent/prompt-submit', async (_agent, content, _source, _signal, next): Promise<PromptDecision> => {
const text = content.map(b => (b.type === 'text' ? b.text : '')).join('')
if (text.includes('rm -rf')) return { kind: 'block', reason: 'destructive prompt blocked' }
return next()

14
packages/core/agent-loop/tests/loop.spec.ts
View File

@@ -231,7 +231,7 @@ describe('agent loop', () => {
assembly.variables['model'] = 'mock'
return next()
})
ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => {
ctx.on('agent/request', async (_agent, _turn, _step, config, _signal, _next) => {
return { ...config, provider: 'mock', model: 'mock' }
})
const agent = ctx.agentLoop.create(SessionId('a-late-model'), {})
@@ -527,7 +527,7 @@ describe('agent loop', () => {
let steps = 0
ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ })
ctx.on('agent/turn-continuation', async (_agent, _turn, _defaultDecision, next) => {
ctx.on('agent/turn-continuation', async (_agent, _turn, _defaultDecision, _signal, next) => {
if (steps < 3) return { action: 'continue' as const }
return next()
})
@@ -566,7 +566,7 @@ describe('agent loop', () => {
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => {
ctx.on('agent/request', async (_agent, _turn, _step, config, _signal, _next) => {
// The seed is frozen — config is not a mutable per-call knob; a switch
// is proposed by returning a replacement, and the loop logs it.
expect(Object.isFrozen(config)).toBe(true)
@@ -692,10 +692,10 @@ describe('agent loop', () => {
// wait until the stream is hanging, then cancel
await new Promise(r => setTimeout(r, 30))
expect(agent.status).toBe('running')
agent.cancel('user interrupt')
agent.cancel({ kind: 'user' })
await waitForIdle(ctx, agent)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'user interrupt' }])
expect(reasons).toEqual([{ kind: 'aborted' }])
})
it('surfaces max-tokens as the turn-end reason when the last step is cut off', async () => {
@@ -732,7 +732,7 @@ describe('agent loop', () => {
ctx.on('session/event', (_session, event) => { if (event.type === 'step/end') steps++ })
// Force exactly one continuation (step 1 → step 2), then defer to default
// (step 2 is a plain stop with no tool calls → stops).
ctx.on('agent/turn-continuation', async (_agent, _turn, _defaultDecision, next) => {
ctx.on('agent/turn-continuation', async (_agent, _turn, _defaultDecision, _signal, next) => {
if (steps < 2) return { action: 'continue' as const }
return next()
})
@@ -884,7 +884,7 @@ describe('agent loop', () => {
]])
const ctx = await harness(adapter)
let stepResults = 0
ctx.on('agent/step-result', async (_agent, _turn, _step, message, next) => {
ctx.on('agent/step-result', async (_agent, _turn, _step, message, _signal, next) => {
stepResults += 1
expect(message.content).toEqual([{ type: 'text', text: 'partial text' }])
return next()

6
packages/core/agent-loop/tests/request-reconstruction.spec.ts
View File

@@ -167,7 +167,7 @@ describe('request stability across the loop', () => {
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let injected = false
ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => {
ctx.on('agent/request', async (_agent, _turn, _step, _config, _signal, next) => {
if (!injected) {
injected = true
agent.inject([{ type: 'text', text: '[late context]' }], { source: { kind: 'plugin', plugin: 'test' } })
@@ -243,7 +243,7 @@ describe('request stability across the loop', () => {
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('agent/request', async (_agent, _turn, _step, _config, next) => {
ctx.on('agent/request', async (_agent, _turn, _step, _config, _signal, next) => {
const config = await next()
// next() resolves the SAME frozen seed — in-place shaping after
// delegation is unrepresentable, so a "mutate what next() returned"
@@ -280,7 +280,7 @@ describe('request stability across the loop', () => {
send(agent, 'go')
await waitForIdle(ctx, agent)
ctx.systemPrompt.section({ name: 'extra', order: 2, text: 'now with guidance' })
ctx.on('agent/request', async (_agent, _turn, _step, config, _next) => ({ ...config, temperature: 0.5, maxTokens: 99, stop: ['<END>'] }))
ctx.on('agent/request', async (_agent, _turn, _step, config, _signal, _next) => ({ ...config, temperature: 0.5, maxTokens: 99, stop: ['<END>'] }))
send(agent, 'again')
await waitForIdle(ctx, agent)

8
packages/core/agent-loop/tests/request-recovery.spec.ts
View File

@@ -204,7 +204,7 @@ describe('agent post-step and request-error lifecycle', () => {
send(agent)
const idle = waitForIdle(ctx, agent)
await postStepEntered
agent.cancel('cancelled during max-tokens post-step')
agent.cancel({ kind: 'user' })
await idle
expect(agent.session.events.find(event => event.type === 'assistant/message')).toMatchObject({
@@ -212,7 +212,7 @@ describe('agent post-step and request-error lifecycle', () => {
})
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: { kind: 'aborted', reason: 'cancelled during max-tokens post-step' } },
data: { reason: { kind: 'aborted' } },
})
})
@@ -587,7 +587,7 @@ describe('agent post-step and request-error lifecycle', () => {
const idle = waitForIdle(ctx, agent)
await recoveryEntered
if (action === 'cancel') {
agent.cancel('cancelled during recovery')
agent.cancel({ kind: 'user' })
await idle
} else {
await ctx.fiber.dispose()
@@ -596,7 +596,7 @@ describe('agent post-step and request-error lifecycle', () => {
expect(adapter.requests).toHaveLength(1)
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: action === 'cancel' ? { kind: 'aborted', reason: 'cancelled during recovery' } : { kind: 'disposed' } },
data: { reason: action === 'cancel' ? { kind: 'aborted' } : { kind: 'disposed' } },
})
})
})

2
packages/core/agent-loop/tests/resume.spec.ts
View File

@@ -193,7 +193,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
order.push('agent/created')
})
ctx.on('agent/session-start', (agent) => {
expect(() => { agent.cancel('now live') }).not.toThrow()
expect(() => { agent.cancel({ kind: 'user' }) }).not.toThrow()
order.push('agent/session-start')
})

39
packages/core/agent-loop/tests/tool-calls.spec.ts
View File

@@ -9,7 +9,7 @@ import { CallId, StreamChunk } from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import LlmService from '@deepseek-ai/dsh-llm'
import ToolRegistry, { defineTool, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
import ToolRegistry, { defineTool, TOOL_ABORTED_BEFORE_DISPATCH, type PostToolDecision, type PreToolDecision } from '@deepseek-ai/dsh-tools'
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { MockAdapter, textResponse } from './mock-adapter.ts'
@@ -461,7 +461,7 @@ describe('tool-call scheduler: abort handling', () => {
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('session/event', (session, event) => {
if (session === agent.session && event.type === 'assistant/message') {
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('already aborted')
agent.cancel({ kind: 'user' })
}
})
@@ -476,12 +476,12 @@ describe('tool-call scheduler: abort handling', () => {
isError: e.data.isError,
error: e.data.error,
}))).toEqual([
{ callId: CallId('c1'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } },
{ callId: CallId('c2'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } },
{ callId: CallId('c1'), isError: true, error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } },
{ callId: CallId('c2'), isError: true, error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } },
])
})
it('stops starting siblings when abort fires during ordered pre-execute', async () => {
it('skips dispatch and stops starting siblings when abort fires during ordered pre-execute', async () => {
const adapter = new MockAdapter([
multiCall([{ id: 'c1', name: 'p', args: { id: '1' } }, { id: 'c2', name: 'p', args: { id: '2' } }]),
textResponse('should never be requested'),
@@ -492,24 +492,25 @@ describe('tool-call scheduler: abort handling', () => {
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
ctx.on('tools/pre-execute', async (exec, next): Promise<PreToolDecision> => {
if (exec.callId === CallId('c1')) {
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('pre cancelled')
agent.cancel({ kind: 'user' })
}
return next()
})
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 1)
await new Promise(r => setTimeout(r, 5))
expect(gated.started).toEqual(['1'])
gated.release('1')
await waitForIdle(ctx, agent)
expect(gated.started).toEqual([])
expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
.toEqual([CallId('c1'), CallId('c2')])
expect(events(agent).filter(e => e.type === 'tool/result').map(e => e.data.callId))
.toEqual([CallId('c1'), CallId('c2')])
expect(events(agent).filter(e => e.type === 'tool/result').at(-1)?.data)
.toMatchObject({ callId: CallId('c2'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } })
expect(events(agent).filter(e => e.type === 'tool/result').map(e => ({
callId: e.data.callId,
isError: e.data.isError,
error: e.data.error,
}))).toEqual([
{ callId: CallId('c1'), isError: true, error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } },
{ callId: CallId('c2'), isError: true, error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } },
])
})
it('stops replenishing after abort, commits started results, and drains accepted additional contexts', async () => {
@@ -528,7 +529,7 @@ describe('tool-call scheduler: abort handling', () => {
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 2)
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('stop now')
agent.cancel({ kind: 'user' })
gated.release('1')
gated.release('2')
await waitForIdle(ctx, agent)
@@ -540,8 +541,8 @@ describe('tool-call scheduler: abort handling', () => {
.toEqual([CallId('c1'), CallId('c2'), CallId('c3'), CallId('c4')])
expect(events(agent).filter(e => e.type === 'tool/result').slice(-2).map(e => e.data))
.toEqual([
expect.objectContaining({ callId: CallId('c3'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } }),
expect.objectContaining({ callId: CallId('c4'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } }),
expect.objectContaining({ callId: CallId('c3'), isError: true, error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } }),
expect.objectContaining({ callId: CallId('c4'), isError: true, error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } }),
])
const settled = events(agent).filter(e => e.type === 'tool/result' || e.type === 'context/message')
expect(settled.map(e => e.type))
@@ -574,7 +575,7 @@ describe('tool-call scheduler: abort handling', () => {
agent.send([{ type: 'text', text: 'go' }])
await until(() => gated.started.length === 2)
;(agent as unknown as { currentAbort?: AbortController }).currentAbort?.abort('stop before barrier')
agent.cancel({ kind: 'user' })
gated.release('1')
gated.release('2')
await waitForIdle(ctx, agent)
@@ -583,6 +584,6 @@ describe('tool-call scheduler: abort handling', () => {
expect(events(agent).filter(e => e.type === 'tool/call').map(e => e.data.callId))
.toEqual([CallId('c1'), CallId('c2'), CallId('c3')])
expect(events(agent).filter(e => e.type === 'tool/result').at(-1)?.data)
.toMatchObject({ callId: CallId('c3'), isError: true, error: { name: 'AbortError', code: 'ABORTED' } })
.toMatchObject({ callId: CallId('c3'), isError: true, error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH } })
})
})

2
packages/core/agent-loop/tests/turn-stop.spec.ts
View File

@@ -60,7 +60,7 @@ describe('agent/turn-stop', () => {
agent.ctx.on('agent/turn-stop', (): ContinuationStop => ({ action: 'stop' }))
let steered = false
ctx.on('agent/turn-continuation', async (subject, _turn, _default, next) => {
ctx.on('agent/turn-continuation', async (subject, _turn, _default, _signal, next) => {
const downstream = await next()
if (subject === agent && !steered) {
steered = true

4
packages/core/agent/README.md
View File

@@ -46,7 +46,7 @@ Agent *creation* is provided by the plugin implementing `AgentFactory` (`dsh-age
The lifecycle edges have two important local caveats. `agent/created` runs after scoped setup and after both session and agent registry entries exist. Setup is trusted composition-only code; the immediately following non-vetoing `agent/session-start` notification is the first supported startup injection point. `agent/disposed` always means the exact agent has left the registry. AgentLoop emits it after its driver is quiescent, while ordered teardown may still be detaching the session and unwinding the scope; custom agents registered directly own any stronger driver-ordering contract themselves.
Most interception points are cooperative waterfalls returning seam-specific decisions. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: it receives the exact error, normalized failure facts, immutable prior-retried facts, and signal after the failed step closes; a retry opens a new numbered step. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. Effective broad cancellation first emits the observe-only `agent/cancel-requested` with its resolved reason, then clears queues and aborts; notification failures are contained and cannot veto the stop. The full rationale for scoped dispatch and terminal settlement is in the [agent-scope runtime-design Agent Note](../../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way).
Most interception points are cooperative waterfalls returning seam-specific decisions. Turn-scoped asynchronous seams receive one explicit `AbortSignal`, with `signal` immediately before a waterfall's final `next`; listeners may cooperate but must not retain it as authority over another turn. The signal remains authoritative through terminal policy and is retired immediately before `turn/end` publication, so terminal observers and the following durability flush cannot cancel completed turn work. `agent/pre-step` and `agent/post-step` are serial checkpoints around a step's durable work, while `agent/request-error` is the failed-model-request recovery waterfall: it receives the exact error, normalized failure facts, immutable prior-retried facts, and signal after the failed step closes; a retry opens a new numbered step. `agent/turn-stop` is the terminal serial fold: it runs after ordinary continuation and steering folding, and a returned stop remains in force through turn close and flush so later steering cannot create an extra step or turn. Ordinary queued prompts remain intact. Effective broad cancellation first emits the observe-only `agent/cancel-requested` with its resolved typed cause, then clears queues and aborts; notification failures are contained and cannot veto the stop. The [explicit-cancellation decision](../../../.agents/notes/implemented/architecture/2026-07-16-explicit-turn-cancellation.md) owns signal lifetime; the [agent-scope runtime-design Agent Note](../../../.agents/notes/implemented/architecture/2026-07-12-agent-scope-runtime-design.md#three-execution-boundaries-are-deliberately-one-way) owns scoped dispatch and terminal settlement.
`PromptDecision.additionalContexts` is an array so every injected context keeps its own source and metadata. A `ContinuationDecision` reason is narrower: it becomes a `steering/message`, not a `context/message`, and therefore carries only content and source.
@@ -59,7 +59,7 @@ The handle every plugin programs against:
- `agent.send(content, options?)` — queue one independent FIFO item. If claimed, that item becomes the sole ordinary message in its turn; a claimed FIFO successor waits for that turn's checkpoint to settle. Broad cancellation, disposal, or a pre-start failure may instead drop it without a turn. Omitting `options.source` attests direct human input as `{ kind: 'user' }` and may authorize policy consumers, so plugins, schedulers, and other non-human producers provide their own source. Content and resolved source become one detached, deeply frozen lossless-JSON record before `agent/queued` and enqueue; invalid data throws synchronously, and caller or notification-listener in-place mutation cannot change the log or model input (`agent/prompt-submit` still rewrites by returning replacement content). The [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md) owns the rationale.
- `agent.steer(content, options?)` — submit steering while the agent is `running`. An open turn records it at the next steering checkpoint before a request or continuation decision; policy can still stop before another step. After turn close and its checkpoint, remaining steering becomes later queued input unless terminal turn policy, cancellation, or disposal discards it. The method uses the same synchronous snapshot-and-validation boundary as `send` and delegates to `send` when idle
- `agent.inject(content, options?)` — accept detached in-session context without running the model; the next request sees its `context/message` with `content` rendered verbatim as a user-role message. `options.meta` persists opaque JSON state without rendering it. While a turn is open it joins that turn, deferring FIFO while the current tool batch executes and draining before turn close if execution is interrupted; while idle it is wrapped in a one-shot `injection` turn and durability checkpoint ([the turn-enclosure invariant](../../../.agents/notes/implemented/architecture/2026-06-15-turn-enclosure-invariant.md)).
- `agent.cancel(reason?)` — cancel ALL pending work: an effective call emits `agent/cancel-requested` before it clears the queued + steering FIFOs, aborts the in-flight step, and drops a turn about to start (the pre-step window). Observers may synchronize their own state but cannot veto cancellation. A UI/ACP `session/cancel` maps to this. The single public stop primitive. Idle with nothing pending → a safe no-op with no notification.
- `agent.cancel(cause?)` — cancel ALL pending work: an omitted cause means `{ kind: 'user' }`; TypeScript restricts callers to the `user | parent` union, and an active holder copies its discriminant into a detached frozen signal reason before aborting. An effective call emits `agent/cancel-requested` with the cause before clearing queued and steering work; observers may synchronize state but cannot veto cancellation. The same-process typed seam adds no runtime validation or compatibility fallback for untyped callers. Repeated active-turn cancellation is first-wins for the signal, and idle cancellation is a safe no-op with no notification. ACP maps to `user`, while in-process parent propagation maps to `parent`. The cause is runtime-only; durable `turn/end` stays coarse `aborted`.
- `agent.whenIdle()` — resolve once the agent reaches quiescence after settling out of `running` (idle → immediately; disposed → awaits the loop exit). A non-owner's quiescence-observation hook: it observes the work settling WITHOUT tearing the agent down. Teardown is separate — a lifecycle owner stops and unregisters via `AgentHandle.dispose()`, which awaits the loop exit directly.
- `agent.session`, `agent.status`, `agent.options`, `agent.id`

30
packages/core/agent/src/cancellation.ts Normal file
View File

@@ -0,0 +1,30 @@
/** Runtime reason inspection for explicit turn cancellation. @module @deepseek-ai/dsh-agent/cancellation */
import type { AgentInterruptReason } from './types.ts'
/**
* Read a supported agent interruption from an explicitly supplied signal.
* Unknown reasons return `undefined`; ambient initiator identity does not grant
* cancellation authority.
* @param signal - the current turn's explicit control signal.
* @returns its canonical reason, or `undefined` while live or unsupported.
*/
export function agentInterruptReasonOf(signal: AbortSignal): AgentInterruptReason | undefined {
if (!signal.aborted) return undefined
const reason: unknown = signal.reason
if (typeof reason !== 'object' || reason === null || Array.isArray(reason)) return undefined
const prototype = Object.getPrototypeOf(reason) as unknown
const keys = Reflect.ownKeys(reason)
if ((prototype !== Object.prototype && prototype !== null)
|| keys.length !== 1 || keys[0] !== 'kind') return undefined
switch ((reason as { readonly kind?: unknown }).kind) {
case 'user':
return Object.freeze({ kind: 'user' })
case 'parent':
return Object.freeze({ kind: 'parent' })
case 'disposed':
return Object.freeze({ kind: 'disposed' })
default:
return undefined
}
}

5
packages/core/agent/src/dispatch.ts
View File

@@ -115,8 +115,9 @@ export function agentEvents(ctx: Context, agent: Agent): AgentEventDispatch {
* Build the prompt assembly context with agent and scope set together, so
* agent-scoped prompt and tool contributions cannot be silently omitted.
* @param agent - the agent the assembly is for.
* @param signal - the current turn's explicit control signal, when assembly belongs to a turn.
* @returns the context to pass to `assemble()`.
*/
export function assembleContextFor(agent: Agent): AssembleContext {
return { agent, scope: agent }
export function assembleContextFor(agent: Agent, signal?: AbortSignal): AssembleContext {
return { agent, scope: agent, ...signal === undefined ? {} : { signal } }
}

1
packages/core/agent/src/index.ts
View File

@@ -15,6 +15,7 @@ import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
import type { Agent, AgentOptions } from './types.ts'
export * from './types.ts'
export { agentInterruptReasonOf } from './cancellation.ts'
export * from './llm-target.ts'
export { agentEvents, assembleContextFor } from './dispatch.ts'
export type { AgentEventDispatch, AgentSubjectEvent } from './dispatch.ts'

2
packages/core/agent/src/llm-target.ts
View File

@@ -49,7 +49,7 @@ export function installAgentLlmTarget(agentCtx: Context, target: AgentLlmTargetR
})
const disposeRequest = agentCtx.on(
'agent/request',
async (_agent, _turn, _step, _config, next): Promise<LlmCallConfig> => {
async (_agent, _turn, _step, _config, _signal, next): Promise<LlmCallConfig> => {
const resolved = await next()
const selected = target.assembled
return selected === undefined ? resolved : {

48
packages/core/agent/src/types.ts
View File

@@ -86,6 +86,14 @@ export type ContinuationStop = Extract<ContinuationDecision, { action: 'stop' }>
/** Why a session lifecycle began; seeded creates are `startup`, while persisted loads are `resume`. */
export type SessionStartSource = 'startup' | 'resume' | 'clear' | 'compact'
/** Stable runtime cause accepted by {@link Agent.cancel}. */
export type AgentCancelCause =
| { readonly kind: 'user' }
| { readonly kind: 'parent' }
/** Runtime reason carried by the signal that controls one live turn. */
export type AgentInterruptReason = AgentCancelCause | { readonly kind: 'disposed' }
/** Public agent handle; its concrete implementation is internal to `@deepseek-ai/dsh-agent-loop`. */
export interface Agent {
/** The single identity shared with {@link session}. */
@@ -125,12 +133,14 @@ export interface Agent {
/**
* Clear all queued and steering work, including items waiting to start, and
* abort the active step. An effective call first emits `agent/cancel-requested`
* with the resolved reason. That reason is preserved across pre-step and active
* cancellation windows, and `whenIdle()` resolves after cancellation reaches
* quiescence. Idle cancellation is a no-op and does not arm a later cancel.
* abort the active turn. An effective call first emits
* `agent/cancel-requested` with the resolved typed cause. The first cause wins
* for the active turn, and `whenIdle()` resolves after cancellation reaches
* quiescence. Omission means `{ kind: 'user' }`. Idle cancellation is a no-op
* and does not arm later work. The active turn snapshots and freezes the cause.
* @param cause - the stable caller intent carried by the current turn signal.
*/
cancel(reason?: string): void
cancel(cause?: AgentCancelCause): void
/** Resolve at idle quiescence; disposal waits for driver exit rather than only the status transition. */
whenIdle(): Promise<void>
@@ -181,14 +191,14 @@ declare module 'cordis' {
'agent/queued'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], info: { source: MessageSource; steering: boolean }): void
/**
* Effective broad cancellation was requested, before queued/steering work
* is cleared or the active step is aborted. This observe-only notification
* is cleared or the active turn is aborted. This observe-only notification
* cannot veto cancellation; listener failures are contained.
* @param agent - the agent whose current work is being cancelled.
* @param reason - resolved cancellation reason, including the default.
* @param cause - resolved typed cancellation cause, including the default.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode emit
*/
'agent/cancel-requested'(this: Scoped<Agent>, agent: Agent, reason: string): void
'agent/cancel-requested'(this: Scoped<Agent>, agent: Agent, cause: AgentCancelCause): void
// ---- session lifecycle (emit) ----
/**
@@ -220,14 +230,17 @@ declare module 'cordis' {
'agent/pre-step'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, signal: AbortSignal): Promise<void> | void
/**
* Allow, rewrite, or block one claimed prompt before it becomes a user
* message. Call `next()` for the unchanged default.
* message. Call `next()` for the unchanged default. The signal controls only
* this turn; listeners may cooperate with it but must not retain it to
* control another turn.
* @param agent - the agent whose turn claimed the message.
* @param content - the claimed message's blocks, as queued.
* @param source - the message's resolved source.
* @param signal - the current turn's explicit abort signal.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode waterfall
*/
'agent/prompt-submit'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], source: MessageSource, next: () => Promise<PromptDecision>): Promise<PromptDecision>
'agent/prompt-submit'(this: Scoped<Agent>, agent: Agent, content: ContentBlock[], source: MessageSource, signal: AbortSignal, next: () => Promise<PromptDecision>): Promise<PromptDecision>
/**
* Replace the frozen call configuration. Model-visible content must use
* logged channels; this seam cannot mutate messages. Injection here joins
@@ -236,10 +249,12 @@ declare module 'cordis' {
* @param turn - the open turn number.
* @param step - the step whose request this is.
* @param config - the config the loop would use (frozen); return a replacement to switch.
* @param signal - the current turn's explicit abort signal; ambient
* initiator identity does not imply liveness or cancellation authority.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode waterfall
*/
'agent/request'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, config: LlmCallConfig, next: () => Promise<LlmCallConfig>): Promise<LlmCallConfig>
'agent/request'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, config: LlmCallConfig, signal: AbortSignal, next: () => Promise<LlmCallConfig>): Promise<LlmCallConfig>
/**
* Compose request-only messages placed before derived history. The frozen
* result is computed once per loop instance, logged on its anchoring request
@@ -251,7 +266,7 @@ declare module 'cordis' {
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @param agent - the agent whose session prefix is being composed.
* @param prefix - the frozen seed; return an extended replacement.
* @param signal - aborts composition when the step is torn down.
* @param signal - the current turn's explicit abort signal.
* @mode waterfall
*/
'agent/session-prefix'(this: Scoped<Agent>, agent: Agent, prefix: Message[], signal: AbortSignal, next: () => Promise<Message[]>): Promise<Message[]>
@@ -262,10 +277,11 @@ declare module 'cordis' {
* @param turn - the open turn number.
* @param step - the step that produced the message.
* @param message - the assistant message as assembled from the stream.
* @param signal - the current turn's explicit abort signal.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode waterfall
*/
'agent/step-result'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, message: Message, next: () => Promise<Message>): Promise<Message>
'agent/step-result'(this: Scoped<Agent>, agent: Agent, turn: number, step: number, message: Message, signal: AbortSignal, next: () => Promise<Message>): Promise<Message>
/**
* Awaited serial checkpoint after the response, real or synthetic tool
* results, injected context, and steering are durable but before `step/end`.
@@ -299,20 +315,22 @@ declare module 'cordis' {
* @param agent - the agent deciding whether to run another step.
* @param turn - the turn being continued or stopped.
* @param defaultDecision - what the loop would do absent an override.
* @param signal - the current turn's explicit abort signal.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode waterfall
*/
'agent/turn-continuation'(this: Scoped<Agent>, agent: Agent, turn: number, defaultDecision: ContinuationDecision, next: () => Promise<ContinuationDecision>): Promise<ContinuationDecision>
'agent/turn-continuation'(this: Scoped<Agent>, agent: Agent, turn: number, defaultDecision: ContinuationDecision, signal: AbortSignal, next: () => Promise<ContinuationDecision>): Promise<ContinuationDecision>
/**
* Monotonic terminal-stop checkpoint after continuation and steering are
* folded; a stop remains authoritative through turn close and flush:
* steering queued in that window is discarded, while ordinary sends survive.
* @param agent - the agent whose composed continuation outcome may be stopped.
* @param turn - the turn at its terminal-stop checkpoint.
* @param signal - the current turn's explicit abort signal.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent.
* @mode serial
*/
'agent/turn-stop'(this: Scoped<Agent>, agent: Agent, turn: number): ContinuationStop | undefined
'agent/turn-stop'(this: Scoped<Agent>, agent: Agent, turn: number, signal: AbortSignal): Promise<ContinuationStop | undefined> | ContinuationStop | undefined
// ---- error notifications (emit) ----
/**

47
packages/core/agent/tests/agent.spec.ts
View File

@@ -2,9 +2,12 @@ import { describe, expect, expectTypeOf, it } from 'vitest'
import { Context, Service, symbols } from 'cordis'
import type { Events } from 'cordis'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent'
import AgentRegistry, {
agentEvents,
agentInterruptReasonOf,
} from '@deepseek-ai/dsh-agent'
import type { Agent, AgentFactory, ContinuationStop, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent'
import type { Agent, AgentCancelCause, AgentFactory, ContinuationStop, CreateAgentOptions, ResumeAgentOptions } from '@deepseek-ai/dsh-agent'
function stubAgent(rawId: string): Agent {
const id = SessionId(rawId)
@@ -23,12 +26,12 @@ function stubAgent(rawId: string): Agent {
}
describe('AgentRegistry', () => {
it('keeps terminal stop decisions synchronous', () => {
it('allows terminal stop policy to cooperate asynchronously with turn cancellation', () => {
type TurnStopListener = Events['agent/turn-stop']
type AsyncTurnStopListener = () => Promise<ContinuationStop | undefined>
expectTypeOf<AsyncTurnStopListener>().not.toExtend<TurnStopListener>()
expectTypeOf<ReturnType<TurnStopListener>>().toEqualTypeOf<ContinuationStop | undefined>()
expectTypeOf<AsyncTurnStopListener>().toExtend<TurnStopListener>()
expectTypeOf<Awaited<ReturnType<TurnStopListener>>>().toEqualTypeOf<ContinuationStop | undefined>()
})
it('registers exact entries, emits lifecycle events, and unregisters on owner disposal', async () => {
@@ -182,6 +185,40 @@ describe('agentEvents()', () => {
})
})
describe('explicit cancellation helpers', () => {
it('exposes the closed typed cancellation cause at the Agent seam', () => {
expectTypeOf<Parameters<Agent['cancel']>[0]>().toEqualTypeOf<AgentCancelCause | undefined>()
expectTypeOf<Parameters<Events['agent/cancel-requested']>[1]>().toEqualTypeOf<AgentCancelCause>()
})
it('reads only supported reasons from an explicit signal', () => {
const read = (reason: unknown) => {
const controller = new AbortController()
controller.abort(reason)
return agentInterruptReasonOf(controller.signal)
}
const live = new AbortController()
expect(agentInterruptReasonOf(live.signal)).toBeUndefined()
expect(read({ kind: 'user' })).toEqual({ kind: 'user' })
expect(read({ kind: 'parent' })).toEqual({ kind: 'parent' })
const disposed = new AbortController()
disposed.abort(Object.assign(Object.create(null) as object, { kind: 'disposed' }))
const disposedReason = agentInterruptReasonOf(disposed.signal)
expect(disposedReason).toEqual({ kind: 'disposed' })
expect(Object.isFrozen(disposedReason)).toBe(true)
expect(read(null)).toBeUndefined()
expect(read([])).toBeUndefined()
expect(read('private runtime reason')).toBeUndefined()
expect(read(new Error('private runtime reason'))).toBeUndefined()
expect(read({ kind: 'user', detail: true })).toBeUndefined()
expect(read({ other: 'user' })).toBeUndefined()
expect(read({ kind: 'timeout' })).toBeUndefined()
})
})
describe('AgentRegistry factory seam', () => {
function stubFactory() {
const calls: {

9
packages/core/agent/tests/llm-target.spec.ts
View File

@@ -17,28 +17,29 @@ describe('installAgentLlmTarget()', () => {
const dispose = installAgentLlmTarget(ctx, target)
const agent = {} as Agent
const seed: LlmCallConfig = { provider: 'seed', model: 'seed', temperature: 0.2 }
const signal = new AbortController().signal
expect((await ctx.systemPrompt.assemble()).variables).toEqual({})
await expect(agentEvents(ctx, agent).waterfall(
'agent/request', 1, 0, seed, () => Promise.resolve(seed),
'agent/request', 1, 0, seed, signal, () => Promise.resolve(seed),
)).resolves.toBe(seed)
target.current = { provider: 'alpha', model: 'a1' }
expect((await ctx.systemPrompt.assemble()).variables).toMatchObject({ provider: 'alpha', model: 'a1' })
target.current = { provider: 'beta', model: 'b1' }
await expect(agentEvents(ctx, agent).waterfall(
'agent/request', 1, 0, seed, () => Promise.resolve(seed),
'agent/request', 1, 0, seed, signal, () => Promise.resolve(seed),
)).resolves.toEqual({ provider: 'alpha', model: 'a1', temperature: 0.2 })
expect((await ctx.systemPrompt.assemble()).variables).toMatchObject({ provider: 'beta', model: 'b1' })
await expect(agentEvents(ctx, agent).waterfall(
'agent/request', 1, 1, seed, () => Promise.resolve(seed),
'agent/request', 1, 1, seed, signal, () => Promise.resolve(seed),
)).resolves.toEqual({ provider: 'beta', model: 'b1', temperature: 0.2 })
dispose()
expect((await ctx.systemPrompt.assemble()).variables).toEqual({})
await expect(agentEvents(ctx, agent).waterfall(
'agent/request', 2, 0, seed, () => Promise.resolve(seed),
'agent/request', 2, 0, seed, signal, () => Promise.resolve(seed),
)).resolves.toBe(seed)
await ctx.fiber.dispose()
})

46
packages/core/scope/tests/invariant.spec.ts
View File

@@ -1,5 +1,7 @@
import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import type { Events } from 'cordis'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { scopeTarget } from '@deepseek-ai/dsh-scope'
import * as ScopeInvariant from '@deepseek-ai/dsh-scope/invariant'
import InvariantService from '@deepseek-ai/dsh-invariants'
@@ -18,6 +20,9 @@ function emit(ctx: Context, receiver: object | undefined, event: string, args: u
}
describe('scoped-dispatch invariants', () => {
type AgentEventName = Extract<keyof Events, `agent/${string}`>
type EventArgs<K extends keyof Events> = Events[K] extends (...args: infer Args) => unknown ? Args : never
it('ignores ordinary events and rejects a scoped dispatch without a carrier', async () => {
const ctx = await setup()
expect(() => { emit(ctx, undefined, 'ordinary/event', []) }).not.toThrow()
@@ -28,24 +33,31 @@ describe('scoped-dispatch invariants', () => {
it('checks every generated subject resolver against the carrier key', async () => {
const ctx = await setup()
const agent = { id: 'a1' }
const other = { id: 'a2' }
const agent = { id: 'a1' } as unknown as Agent
const other = { id: 'a2' } as unknown as Agent
const signal = new AbortController().signal
const config = { provider: 'p', model: 'm' }
const message = { role: 'assistant' as const, content: [] }
const agentRows = {
'agent/created': [agent],
'agent/disposed': [agent],
'agent/status': [agent, 'idle'],
'agent/queued': [agent, [], { source: { kind: 'user' }, steering: false }],
'agent/cancel-requested': [agent, { kind: 'user' }],
'agent/session-start': [agent, 'startup'],
'agent/pre-step': [agent, 1, 1, signal],
'agent/post-step': [agent, 1, 1, signal],
'agent/prompt-submit': [agent, [], { kind: 'user' }, signal, () => Promise.resolve({ kind: 'allow' })],
'agent/request': [agent, 1, 1, config, signal, () => Promise.resolve(config)],
'agent/request-error': [agent, 1, 1, new Error('request failed'), { message: 'request failed', code: 'UNKNOWN' }, [], signal, () => Promise.resolve({ action: 'fail' })],
'agent/session-prefix': [agent, [], signal, () => Promise.resolve([])],
'agent/step-result': [agent, 1, 1, message, signal, () => Promise.resolve(message)],
'agent/turn-continuation': [agent, 1, { action: 'stop' }, signal, () => Promise.resolve({ action: 'stop' })],
'agent/turn-stop': [agent, 1, signal],
'agent/error': [agent, 1, 0, new Error('x')],
} satisfies { [K in AgentEventName]: EventArgs<K> }
const rows: Array<[string, unknown[]]> = [
['agent/created', [agent]],
['agent/disposed', [agent]],
['agent/error', [agent, 1, 0, new Error('x')]],
['agent/post-step', [agent, 1, 1]],
['agent/pre-step', [agent, 1, 1, new AbortController().signal]],
['agent/prompt-submit', [agent, [], { kind: 'user' }, () => Promise.resolve({ kind: 'allow' })]],
['agent/queued', [agent, [], { source: { kind: 'user' }, steering: false }]],
['agent/request', [agent, 1, 1, { model: 'm' }, () => Promise.resolve({ model: 'm' })]],
['agent/request-error', [agent, 1, 1, new Error('x')]],
['agent/session-prefix', [agent, [], new AbortController().signal, () => Promise.resolve([])]],
['agent/session-start', [agent, 'startup']],
['agent/status', [agent, 'idle']],
['agent/step-result', [agent, 1, 1, { role: 'assistant', content: [] }, () => Promise.resolve({ role: 'assistant', content: [] })]],
['agent/turn-continuation', [agent, 1, { action: 'stop' }, () => Promise.resolve({ action: 'stop' })]],
['agent/turn-stop', [agent, 1]],
...Object.entries(agentRows),
['approval/request', [{ agent, toolName: 'echo' }, () => Promise.resolve('unavailable')]],
['goal/changed', [agent, { operation: 'create', ref: { id: 'goal-a', revision: 1 } }]],
['system-prompt/assemble', [[], { scope: agent }]],

4
packages/core/session/README.md
View File

@@ -70,6 +70,8 @@ Merge-extensible via `SessionEventMap` — a plugin declaration-merges its own t
Also defines `TurnTriggerMap` and `TurnEndReasonMap` (merge-extensible sum types for typed turn boundaries — `kind`-tagged instead of strings). A final model-request error retains one structured `LlmFailure`; other turn errors retain message/code, and both identify the failed step.
An interrupted live turn ends with the coarse `{ kind: 'aborted' }` outcome. Caller identity belongs to the Agent's runtime cancellation signal rather than the durable transcript; disposal remains the separate `{ kind: 'disposed' }` terminal state.
Every `SessionEvent` carries two optional top-level fields (structural metadata):
- `sourceEventSeqs?: number[]` — seq numbers of provenance sources (e.g., the `assistant/chunk` seqs behind an `assistant/message`, or the shadowed entries behind a compaction replacement entry). On `assistant/message`, a present `[]` records a known empty provider stream, while omission means legacy or otherwise unrecorded provenance; other surface events require a non-empty list when this field is present.
@@ -82,7 +84,7 @@ Every `SessionEvent` carries two optional top-level fields (structural metadata)
### Extension points
- Persistence plugins: subscribe to `session/event` (write-behind) and drain on `session/flush` (awaited) and fiber dispose. A durable backend reads the log and reloads it into a live session; the metadata seam (`SessionHeader`, `session.header`) is what such a backend stores beside the log.
- Replay/fork: `create(id, { seed })` validates and freezes a contiguous current-format log and rebuilds its surface; request headers require provider/model and assistant messages require provider/model provenance. `fork(source, boundary?, childSessionId?)` selects a completed-turn prefix and records lineage.
- Replay/fork: `create(id, { seed })` validates and freezes a contiguous current-format log and rebuilds its surface; request headers require provider/model, assistant messages require provider/model provenance, and a coarse aborted outcome must contain only `{ kind: 'aborted' }` (legacy reason-bearing records are rejected). `fork(source, boundary?, childSessionId?)` selects a completed-turn prefix and records lineage.
- Compaction: `dsh-compact-basic` appends a `user/message` replacement for summary checkpoints, while `dsh-compact-tool-result-prune` appends a content-only `tool/result` replacement. Tool-pairing boundary policy and its cache belong to the [`dsh-compact` seam](../../compact/compact/README.md), while this package owns ordered surface membership, replacement validation, and `replaceGeneration`.
## Model Experience

17
packages/core/session/src/index.ts
View File

@@ -158,6 +158,7 @@ function assertSessionEventEnvelope(value: Record<string, unknown>, index: numbe
throw new Error(`seed event at index ${index} has an invalid event envelope`)
}
assertCurrentLlmShape(event, index)
assertCurrentTurnEndShape(event, index)
}
/** Reject pre-provider request headers and assistant messages at the seed/load boundary. */
@@ -175,6 +176,22 @@ function assertCurrentLlmShape(event: Record<string, unknown>, index: number): v
}
}
/** Reject legacy aborted outcomes that persisted caller-owned reason detail. */
function assertCurrentTurnEndShape(event: Record<string, unknown>, index: number): void {
if (event['type'] !== 'turn/end') return
const data = event['data']
/* v8 ignore next -- this migration recognizes only the legacy object shape; format-wide payload validation is separate. */
if (typeof data !== 'object' || data === null) return
const reason = (data as Record<string, unknown>)['reason']
/* v8 ignore next -- non-object reasons cannot carry the legacy aborted detail this migration removes. */
if (typeof reason !== 'object' || reason === null || Array.isArray(reason)) return
const record = reason as Record<string, unknown>
if (record['kind'] === 'aborted'
&& (Object.keys(record).length !== 1 || !Object.hasOwn(record, 'kind'))) {
throw new Error(`seed turn/end at index ${index} uses unsupported reason-bearing aborted format`)
}
}
/** Whether an unknown value carries the current provider/model pair. */
function hasProviderModel(value: unknown): boolean {
if (typeof value !== 'object' || value === null) return false

3
packages/core/session/src/types.ts
View File

@@ -101,7 +101,8 @@ export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap]
*/
export interface TurnEndReasonMap {
completed: { kind: 'completed' }
aborted: { kind: 'aborted'; reason?: string }
/** A cancellation request interrupted the live turn. */
aborted: { kind: 'aborted' }
/**
* The turn failed: a step threw or the model reported a failure. `step` is the
* step number the failure occurred on (the operational error's location — the

2
packages/core/session/tests/fork.spec.ts
View File

@@ -102,7 +102,7 @@ describe('SessionStore.fork', () => {
const { ctx, sessions } = await setup()
const reasons: TurnEndReason[] = [
{ kind: 'completed' },
{ kind: 'aborted', reason: 'cancelled by user' },
{ kind: 'aborted' },
{ kind: 'error', step: 1, message: 'model failed', code: 'MODEL' },
{ kind: 'disposed' },
{ kind: 'max-tokens' },

26
packages/core/session/tests/session.spec.ts
View File

@@ -90,6 +90,32 @@ describe('Session', () => {
expect(findLastMessageTurnEnd(session.events)).toBe(messageEnd)
})
it('round-trips the coarse aborted turn outcome', () => {
const session = new Session(SessionId('aborted'))
session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
session.append('turn/end', { turn: 1, reason: { kind: 'aborted' } })
const replayed = new Session(SessionId('aborted-replay'), structuredClone(session.events))
expect(replayed.events).toEqual(session.events)
const turnEnd = replayed.events.findLast(event => event.type === 'turn/end')
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'aborted' })
})
it('rejects legacy reason-bearing aborted outcomes at the seed/load boundary', () => {
const legacy = [
{
type: 'turn/start', seq: 0, time: 1,
data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } },
},
{
type: 'turn/end', seq: 1, time: 2,
data: { turn: 1, reason: { kind: 'aborted', reason: 'legacy cancellation detail' } },
},
] as unknown as SessionEvent[]
expect(() => new Session(SessionId('legacy-aborted'), legacy))
.toThrow('seed turn/end at index 1 uses unsupported reason-bearing aborted format')
})
it('renders context and steering messages as plain user content', () => {
const session = new Session(SessionId('s2'))
session.append('context/message', {

4
packages/core/system-prompt/README.md
View File

@@ -16,7 +16,7 @@ System prompt assembly registry. Plugins contribute ordered sections, tool schem
- `ctx.systemPrompt.section(section: PromptSection): () => void` Contribute a section. The layer is the calling context's scope: `agent.ctx` contributes to that agent alone, shadowing a same-named global section there. Duplicate names within one layer and non-finite orders throw. Disposed with the calling fiber.
- `ctx.systemPrompt.tools(provider: (context: AssembleContext) => ToolProviderResult): () => void` Contribute tool schemas, evaluated at each assembly with that assembly's context. `ToolProviderResult` = `{ schemas, knownNames? }`: `schemas` is the post-restriction visible set; `knownNames` is the pre-restriction universe used by `toolOrder`. A provider must not return a schema named `TOOL_ORDER_REST`. Scoped providers are consulted only for their scope's assemblies. Disposed with the calling fiber.
- `ctx.systemPrompt.variable(name: string, provider: (context) => string | undefined): () => void` Contribute a prompt variable, referenced from section text as `{{name}}`. Scoped variables shadow a same-named global for that agent. Duplicate-in-layer or unreferenceable names throw; `undefined` means "no value for this assembly". Disposed with the calling fiber.
- `ctx.systemPrompt.assemble(context?: AssembleContext): Promise<PromptAssembly>` Assemble the prompt for one caller: the global layer merged with `context.scope`'s layer, with tool schemas detached before the transform seam. Runs through the scope-filtered `system-prompt/assemble` waterfall and returns its authoritative result. Rejects when a configured `toolOrder` names a tool outside the providers' `knownNames` universe, or when a provider returns the reserved rest-entry name.
- `ctx.systemPrompt.assemble(context?: AssembleContext): Promise<PromptAssembly>` Assemble the prompt for one caller: the global layer merged with `context.scope`'s layer, with tool schemas detached before the transform seam. Runs through the scope-filtered `system-prompt/assemble` waterfall and returns its authoritative result. An optional `context.signal` explicitly controls this assembly request; providers and listeners may cooperate with it but must not retain it for another turn. Rejects when a configured `toolOrder` names a tool outside the providers' `knownNames` universe, or when a provider returns the reserved rest-entry name.
### Live events
@@ -24,7 +24,7 @@ System prompt assembly registry. Plugins contribute ordered sections, tool schem
### Key types
- `AssembleContext` — what one `assemble()` call is FOR. Merge-extensible; declares `scope?: ScopeKey` (the layer selector) here, and `dsh-agent` declares `agent?: Agent` (the typed DX field — never set without `scope`; use `assembleContextFor(agent)`). Providers must tolerate absent fields (a bare `assemble()` carries an empty, scope-less context).
- `AssembleContext` — what one `assemble()` call is FOR. Merge-extensible; declares `scope?: ScopeKey` (the layer selector) and `signal?: AbortSignal` (the explicit request control capability) here, while `dsh-agent` declares `agent?: Agent` (the typed DX field — never set without `scope`; use `assembleContextFor(agent, signal)`). Providers must tolerate absent fields because a bare `assemble()` carries an empty, scope-less, signal-less context. `signal` is a request value, not part of the ambient Agent execution frame.
- `PromptSection` — `{ name, order, text }`. Sections are concatenated in ascending `order`. Order bands: `-100` is the harness identity, `0` the deployment persona, tool guidance uses `100–199`.
- `PromptAssembly` — `{ sections: AssembledSection[], tools: ToolSchema[], variables: Record<string, string | undefined> }`. Section texts arrive resolved but not yet interpolated; `variables` holds every registered variable resolved against the context. Tool schemas are part of the assembly by design: "what the model is told it can do" is one coherent thing, even though adapters transmit schemas as a separate wire field.
- `renderPrompt(assembly)` — interpolates `{{variable}}` references in each section, drops empty sections, joins with blank lines. STRICT: an unknown reference (`Object.hasOwn` lookup — prototype names like `{{constructor}}` are unknown), a registered-but-valueless reference, a malformed complete `{{…}}` group, or a `{{` that opens no complete group while a `}}` still follows (`{{{model}}}`) throws — fail loud beats shipping a malformed prompt. A lone `{{` with no `}}` anywhere after it passes through verbatim; substituted values are never re-scanned.

4
packages/core/system-prompt/src/index.ts
View File

@@ -20,6 +20,8 @@ declare module 'cordis' {
* Expert waterfall over the assembled sections, tools, and variables.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): scoped listeners
* receive only that scope's assemblies. The returned value is authoritative.
* A supplied signal controls only this explicit assembly request and must not
* be retained to control later turns.
* @param assembly - the mutable assembly built from registered providers.
* @param context - the caller's per-assembly context.
* @mode waterfall
@@ -41,6 +43,8 @@ export interface AssembleContext {
* only global providers and subject-less listeners participate.
*/
scope?: ScopeKey
/** Explicit control signal for the turn that requested this assembly, when any. */
signal?: AbortSignal
}
/** One contributed section of the system prompt (registry input). */

16
packages/core/tools/README.md
View File

@@ -20,24 +20,28 @@ tools:
- `ctx.tools.get(name: string, scope?: ScopeKey): ToolDefinition | undefined` Resolution as one scope sees it (shadowing applied; a restricted-away global reads as absent) — presenters pass the calling agent so the card matches what executed.
- `ctx.tools.schemas(scope?: ScopeKey): ToolSchema[]` Schemas of everything the scope can see (without the `execute` functions). The shipped tools' schemas are catalogued in [docs/tool-catalog.md](../../../docs/tool-catalog.md), generated by booting each tool plugin and harvesting this method (see [the tool-schema-catalog Agent Note](../../../.agents/notes/implemented/process/2026-07-02-tool-schema-catalog.md)).
- `ctx.tools.guard(guard: ToolGuard): () => void` Register a monotonic synchronous execution guard after `tools/pre-execute`: returning a reason denies the call, while `undefined` leaves it unchanged. A plain-context guard applies globally; an `agent.ctx` guard applies only to that agent. Later waterfall listeners cannot turn a guard denial back into permission. Disposed with the calling fiber.
- `ctx.tools.execute(exec)` losslessly snapshots and freezes arguments, assigns an opaque token, runs the complete policy/dispatch/result pipeline, then independently snapshots the authoritative outcome before final observation. Invalid arguments use the same result path without reaching policy or the body; around wrappers may replace only `signal`.
- `ctx.tools.execute(exec)` losslessly snapshots and freezes arguments, assigns an opaque token, runs the complete policy/dispatch/result pipeline, then independently snapshots the authoritative outcome before final observation. Invalid arguments use the same result path without reaching policy or the body. Around wrappers may replace only `signal`; the registry re-fuses the original caller signal immediately before the body.
- `ctx.tools.executionMode(exec)` returns `parallel` only when the visible definition's `isConcurrencySafe(exec.arguments)` classifier returns exactly `true`; unknown, hidden, undeclared, invalid, or throwing classifications are exclusive.
### Injected services
`SystemPrompt` — the registry automatically feeds its tool schemas into the system-prompt assembly via `ctx.systemPrompt.tools()`. The approval seam is consumed opportunistically instead (`ctx.get('approval')`, no static inject): a deployment without it keeps the ask→deny degrade, and the registry stays active either way.
### Cancellation
Cancellation is cooperative and quiescent. Every typed invocation supplies a caller-owned `AbortSignal`; tool bodies receive it as required readonly `exec.signal`, while only `tools/execute` wrappers may temporarily replace the required signal. The registry preserves caller cancellation through replacement and never races away from a started same-process promise. Cancellation before body invocation is `ABORTED_BEFORE_DISPATCH`; cancellation after invocation can replace only a successful outcome with `ABORTED`. A denial, wrapper failure, tool failure, post-policy failure, or timeout-owned `TOOL_TIMEOUT` remains more specific. A pre-aborted entry materializes and freezes arguments, then skips every policy and dispatch phase and publishes one result. Every async tool must observe or forward the signal and settle only after owned work stops. The [tool-cancellation Agent Note](../../../.agents/notes/implemented/architecture/2026-07-19-cooperative-tool-cancellation.md) owns the full contract and hard-termination limit.
### Live events
The live registry pipeline has three transformable waterfalls followed by the observe-only `tools/result` boundary; registry changes are deliberately unfiltered shared-state notifications. Exact signatures, dispatch modes, scope filtering, and failure-containment contracts live in the generated [Cordis event catalog](../../../docs/cordis-catalog/events.md), while the complete ordering is visualized in the generated [tool execution pipeline](../../../docs/tool-execution-pipeline.md). `tools/result` is live; the similarly named `tool/result` is the durable session event the agent loop appends afterwards.
### Key types
- `ToolDefinition` — `ToolSchema` + `execute(args, exec)`, optional presentation callbacks, cooperative `timeoutMs`, and optional per-call `isConcurrencySafe(args)` classification.
- `ToolExecutionInput` — the caller-supplied call description: `{ callId, name, arguments, agent?, parent?, signal? }`; callers may pass an enclosing execution's opaque token as `parent` but never choose the new execution's own token.
- `ToolDefinition` — `ToolSchema` + `execute(args, exec)`, whose async work must cooperatively stop through `exec.signal`, plus optional presentation callbacks, cooperative `timeoutMs`, and optional per-call `isConcurrencySafe(args)` classification.
- `ToolExecutionInput` — the caller-supplied call description: `{ callId, name, arguments, signal, agent?, parent? }`; `signal` is required and readonly, callers may pass an enclosing execution's opaque token as `parent`, and callers never choose the new execution's own token.
- `ToolExecutionToken` — a fresh branded `Symbol` assigned by the registry. It supports equality correlation only and never crosses a model, log, or worker boundary.
- `ToolExecution` — the pipeline-owned call: immutable `{ token, callId, name, arguments, agent?, parent? }` identity plus optional operational `signal`, which an around wrapper may add, replace, remove, and restore. A nested call's `parent` is a `ToolExecutionToken`, not an execution object.
- `ToolRunContext` — the execution passed to a tool body, extending `ToolExecution` with `deferContext(context)`. Composite tools use it to ferry context produced by nested dispatches to the outer result even when the tool later throws; it never injects immediately.
- `ToolExecution` — the readonly pipeline view: immutable `{ token, callId, name, arguments, signal, agent?, parent? }`; the registry separately retains and re-fuses the original caller signal. `ToolDispatchExecution` is the `tools/execute`-only view whose required signal is mutable, so a wrapper may replace and restore it but cannot delete it. A nested call's `parent` is a `ToolExecutionToken`, not an execution object.
- `ToolRunContext` — the execution passed to a tool body, extending `ToolExecution` with `deferContext(context)`. Composite tools use it to ferry context produced by nested dispatches to the outer result even when the tool later throws or cancellation wins; it never injects immediately.
- `ToolExecutionResult` — losslessly JSON-serializable outcome: `{ content, isError, error?, additionalContexts?, meta? }`. Call identity stays on the immutable `ToolExecution` supplied alongside the result instead of being duplicated on the outcome. The registry materializes and freezes the complete post-policy value before final observation. On failure with a `HarnessError`, `error: { name, code }` carries the structured failure class alongside the model-facing text. `additionalContexts` preserves each deferred or post-execute `HookContext` with its own source and durable JSON metadata; the loop buffers the array and appends each entry as a `context/message` after all `tool/result`s in the step.
- `PreToolDecision` — `{kind:'allow'}` | `{kind:'deny', reason}` | `{kind:'ask', reason?}`. Input rewrite is deliberately not offered; `ask` is serviced by [`ctx.approval`](../../ui/user-approval/README.md) when mounted and otherwise degrades to deny.
- `PostToolDecision` — `{kind:'accept', content?, additionalContexts?}` (keep the call successful, optionally replacing the model-facing content) | `{kind:'block', feedback, additionalContexts?}` (turn it into an `isError` whose content is the corrective feedback). Accept preserves tool-deferred contexts before decision contexts; block discards tool-deferred contexts and exposes only contexts explicitly supplied by the blocking decision.
@@ -74,7 +78,7 @@ ctx.tools.register(defineTool({
},
async execute(args, exec) {
// args is typed: { path: string; offset?: number; limit?: number }
const text = await readFile(args.path, 'utf8')
const text = await readFile(args.path, { encoding: 'utf8', signal: exec.signal })
return [{ type: 'text', text }]
},
}))

7
packages/core/tools/src/code-mode.ts
View File

@@ -160,9 +160,8 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () =>
// (its executor kills on this signal) instead of orphaned, and
// queued-unstarted dispatches are abandoned.
const runController = new AbortController()
const onOuterAbort = (): void => { runController.abort(exec.signal?.reason) }
if (exec.signal?.aborted) onOuterAbort()
exec.signal?.addEventListener('abort', onOuterAbort, { once: true })
const onOuterAbort = (): void => { runController.abort(exec.signal.reason) }
exec.signal.addEventListener('abort', onOuterAbort, { once: true })
let dispatches = 0
// The per-run serialization queue: every binding call chains onto the tail, so even
@@ -273,7 +272,7 @@ export function createRunCodeTool(registry: ToolRegistry, requireRuntime: () =>
meta,
}
} finally {
exec.signal?.removeEventListener('abort', onOuterAbort)
exec.signal.removeEventListener('abort', onOuterAbort)
}
},
// ACP execute cards use the program as their visible title.

290
packages/core/tools/src/index.ts
View File

@@ -72,7 +72,9 @@ declare module 'cordis' {
interface Events {
/**
* Allow, deny, or ask before dispatch. `next()` delegates to allow; missing
* approval support turns `ask` into denial.
* approval support turns `ask` into denial. Async gates must observe
* `exec.signal`; the registry rechecks cancellation after they settle but
* never abandons their promise.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.
* @param exec - the pending call (name, parsed arguments, caller agent).
* @mode waterfall
@@ -81,15 +83,20 @@ declare module 'cordis' {
/**
* Around-dispatch waterfall for timeout, retry, or metrics. `next()` returns
* a normalized result; wrappers may change only `exec.signal`, while call
* identity remains immutable.
* identity remains immutable. The registry re-fuses the original caller
* signal before the body, so replacement cannot detach caller cancellation;
* wrappers must still restore their signal and reach quiescence.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.
* @param exec - the allowed call about to dispatch (name, parsed arguments, caller agent, signal).
* @mode waterfall
*/
'tools/execute'(this: Scoped<ToolRegistry>, exec: ToolExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>
'tools/execute'(this: Scoped<ToolRegistry>, exec: ToolDispatchExecution, next: () => Promise<ToolExecutionResult>): Promise<ToolExecutionResult>
/**
* Accept, replace, enrich, or block a normalized dispatch result. `next()`
* accepts it unchanged; thrown tools still reach this seam as errors.
* accepts it unchanged; thrown tools still reach this seam as errors. Async
* listeners must observe `exec.signal`; after they settle, caller
* cancellation replaces only a successful accepted outcome with the code
* selected by whether the tool body was invoked.
* Scope-filtered dispatch (`@deepseek-ai/dsh-scope`): agent-scoped listeners receive only that agent's calls.
* @param exec - the call that just ran (name, parsed arguments, caller agent).
* @param result - the dispatch outcome a listener may accept, replace, or block.
@@ -122,6 +129,15 @@ export type ToolExecuteReturn = ContentBlock[] | { content: ContentBlock[]; meta
/** A registered tool: its schema plus the execution function. */
export interface ToolDefinition extends ToolSchema {
/**
* Run one accepted call. Async work must observe or forward `exec.signal` and
* settle only after its owned work reaches quiescence. The registry preserves
* caller cancellation through around-dispatch signal replacement and does
* not abandon this promise, but it cannot hard-kill same-process code.
* @param args - losslessly snapshotted, frozen model arguments.
* @param exec - execution identity, cancellation signal, and context deferral.
* @returns model-facing content plus optional private presentation metadata.
*/
execute(args: unknown, exec: ToolRunContext): Promise<ToolExecuteReturn>
/**
* Cooperative tool-call timeout budget in milliseconds. Omit for no deadline.
@@ -203,7 +219,8 @@ export interface ToolExecutionInput {
* the outer `run_code` outcome without receiving its live mutable execution.
*/
readonly parent?: ToolExecutionToken
signal?: AbortSignal
/** Required caller-owned cancellation for this invocation. */
readonly signal: AbortSignal
}
/**
@@ -217,15 +234,25 @@ export type ToolExecutionMode =
/**
* One pending tool call inside the registry pipeline. Parsed arguments cross
* one lossless-JSON materialization boundary before policy and are deep-frozen;
* call identity and the registry-assigned {@link token} are readonly. An
* around-dispatch wrapper may set, replace, or remove `signal`. The registry
* freezes the complete object before `tools/result` observers run.
* call identity, the caller signal, and the registry-assigned {@link token} are
* readonly. The registry freezes the complete object before `tools/result`
* observers run.
*/
export interface ToolExecution extends ToolExecutionInput {
/** Registry-assigned identity shared with nested calls only as their opaque `parent` token. */
readonly token: ToolExecutionToken
}
/**
* Around-dispatch view of a {@link ToolExecution}. A `tools/execute` wrapper
* may replace the signal for its delegated lifetime, but it cannot remove it.
* The registry fuses every replacement with the captured caller signal.
*/
export interface ToolDispatchExecution extends Omit<ToolExecution, 'signal'> {
/** Cancellation signal visible to the next wrapper or tool body. */
signal: AbortSignal
}
/**
* Runtime context handed to a tool implementation after the registry has
* accepted a {@link ToolExecution}. A composite tool uses
@@ -241,6 +268,9 @@ export interface ToolRunContext extends ToolExecution {
deferContext(context: HookContext): void
}
/** Registry-owned live execution object; public pipeline views stay readonly. */
type MutableToolRunContext = Omit<ToolRunContext, 'signal'> & { signal: AbortSignal }
/**
* Scheduler-only result after ordered pre-execute and guards. A `post-result`
* still receives post-execute; a `final-result` bypasses it.
@@ -282,6 +312,13 @@ export interface ToolRegistryScheduler {
* @internal
*/
export const TOOL_REGISTRY_SCHEDULER: unique symbol = Symbol('@deepseek-ai/dsh-tools.scheduler')
/** Canonical error code for cancellation after a tool body was invoked. */
export const TOOL_ABORTED = 'ABORTED'
/** Canonical error code for cancellation before a tool body was invoked. */
export const TOOL_ABORTED_BEFORE_DISPATCH = 'ABORTED_BEFORE_DISPATCH'
/** Structured error metadata for a failed tool call (alongside the model-facing text). */
export interface ToolErrorInfo {
name: string
@@ -431,6 +468,24 @@ interface ToolGuardRegistration {
guard: ToolGuard
}
/** Approval decision plus whether the approval channel reported cancellation. */
interface ToolAskResolution {
readonly decision: Extract<PreToolDecision, { kind: 'allow' | 'deny' }>
readonly approvalCancelled: boolean
}
/** Caller cancellation and dispatch state kept outside the around-wrapper view. */
interface ToolCancellationState {
readonly callerSignal: AbortSignal
bodyInvoked: boolean
}
/** One dispatch-scoped fused signal plus listener cleanup after the body settles. */
interface FusedToolSignal {
readonly signal: AbortSignal
dispose(): void
}
/**
* Tool registry and execution pipeline. Scoped registrations shadow globals;
* one visibility resolver feeds presentation, lookup, and dispatch.
@@ -452,6 +507,8 @@ export class ToolRegistry extends Service {
/** Context deferred by a running tool body, keyed by its scheduler-owned execution. */
private deferredContexts = new WeakMap<ToolRunContext, HookContext[]>()
/** Original caller cancellation, kept outside the wrapper-mutable execution object. */
private cancellationStates = new WeakMap<ToolRunContext, ToolCancellationState>()
private global = new Map<string, ToolDefinition>()
private scoped = new Map<ScopeKey, Map<string, ToolDefinition>>()
/** Compiled restriction filters, per scope (see {@link restrict}). */
@@ -774,7 +831,11 @@ export class ToolRegistry extends Service {
* Execute through pre-policy, guards, around-dispatch, post-policy, and final
* notification. Tool and listener failures resolve as materialized error
* results; an invisible tool reports `UNKNOWN_TOOL`. The returned outcome is
* the same lossless, frozen snapshot final observers receive.
* the same lossless, frozen snapshot final observers receive. Cancellation
* arriving after entry and before final result materialization skips a
* not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a
* successful started outcome with `ABORTED`; already-started work is still
* drained and may retain a tool-owned structured error.
* @param exec - the typed same-process call input. The registry assigns its
* correlation token before policy begins.
* @returns the materialized final result.
@@ -801,7 +862,7 @@ export class ToolRegistry extends Service {
}
}
private createExecution(exec: ToolExecutionInput): ScheduledToolPreparation | { kind: 'ready'; exec: ToolRunContext } {
private createExecution(exec: ToolExecutionInput): ScheduledToolPreparation | { kind: 'ready'; exec: MutableToolRunContext } {
const deferredContexts: HookContext[] = []
const token = createExecutionToken()
const callId = exec.callId
@@ -813,9 +874,9 @@ export class ToolRegistry extends Service {
token,
callId,
name,
signal,
...agent !== undefined ? { agent } : {},
...parent !== undefined ? { parent } : {},
...signal !== undefined ? { signal } : {},
deferContext(context: HookContext): void {
deferredContexts.push(context)
},
@@ -825,11 +886,15 @@ export class ToolRegistry extends Service {
if (detached === undefined) {
throw new TypeError('tool execution arguments must be losslessly JSON-serializable')
}
const execution: ToolRunContext = { ...base, arguments: deepFreeze(detached) }
const execution: MutableToolRunContext = { ...base, arguments: deepFreeze(detached) }
this.deferredContexts.set(execution, deferredContexts)
this.cancellationStates.set(execution, {
callerSignal: signal,
bodyInvoked: false,
})
return { kind: 'ready', exec: execution }
} catch (error: unknown) {
const execution: ToolRunContext = { ...base, arguments: undefined }
const execution: MutableToolRunContext = { ...base, arguments: undefined }
return { kind: 'final-result', exec: execution, result: toolErrorResult(error) }
}
}
@@ -851,13 +916,22 @@ export class ToolRegistry extends Service {
const created = this.createExecution(input)
if (created.kind !== 'ready') return next(created)
const exec = created.exec
if (this.callerCancelled(exec)) {
return next({ kind: 'final-result', exec, result: toolAbortedBeforeDispatchResult() })
}
try {
const carrier = scopeTarget(this, exec.agent)
const gate = await this.ctx.waterfall(
carrier, 'tools/pre-execute', exec,
() => Promise.resolve<PreToolDecision>({ kind: 'allow' }),
)
const decision = gate.kind === 'ask' ? await this.serviceAsk(exec, gate) : gate
const askResolution: ToolAskResolution = gate.kind === 'ask'
? await this.serviceAsk(exec, gate)
: { decision: gate, approvalCancelled: false }
const { decision } = askResolution
if (this.callerCancelled(exec) && askResolution.approvalCancelled) {
return await next({ kind: 'post-result', exec, result: toolAbortedBeforeDispatchResult() })
}
const denialReason = decision.kind === 'allow'
? this.guardReason(exec)
: decision.reason
@@ -871,12 +945,74 @@ export class ToolRegistry extends Service {
},
})
}
if (this.callerCancelled(exec)) {
return await next({ kind: 'post-result', exec, result: toolAbortedBeforeDispatchResult() })
}
return await next({ kind: 'dispatch', exec })
} catch (error: unknown) {
return next({ kind: 'final-result', exec, result: toolErrorResult(error) })
}
}
/** Whether the original caller signal is currently aborted. */
private callerCancelled(exec: ToolRunContext): boolean {
const state = this.cancellationStates.get(exec)
/* v8 ignore next -- only registry-minted executions reach the staged scheduler methods */
if (state === undefined) throw new Error('tool registry scheduler invariant violated: missing cancellation state')
return state.callerSignal.aborted
}
/** Canonical cancellation outcome selected by whether the tool body started. */
private cancellationResult(exec: ToolRunContext, prior?: ToolExecutionResult): ToolExecutionResult {
const state = this.cancellationStates.get(exec)
/* v8 ignore next -- only registry-minted executions reach the staged scheduler methods */
if (state === undefined) throw new Error('tool registry scheduler invariant violated: missing cancellation state')
return state.bodyInvoked
? toolAbortedResult(prior)
: toolAbortedBeforeDispatchResult(prior)
}
/**
* Dispatch the registered body with the original caller signal fused back
* into any around-wrapper replacement. Cancellation never abandons the body:
* a started promise reaches quiescence before its outcome becomes `ABORTED`.
*/
private async dispatchToolBody(exec: MutableToolRunContext): Promise<ToolExecutionResult> {
const state = this.cancellationStates.get(exec)
/* v8 ignore next -- only registry-minted executions reach the staged scheduler methods */
if (state === undefined) throw new Error('tool registry scheduler invariant violated: missing cancellation state')
const wrapperSignal = exec.signal
const fused = fuseToolSignals(state.callerSignal, wrapperSignal)
const signal = fused.signal
if (isAborted(signal)) {
fused.dispose()
return toolAbortedBeforeDispatchResult()
}
exec.signal = signal
try {
const tool = this.get(exec.name, exec.agent)
if (!tool) throw new ToolNotFoundError(exec.name)
state.bodyInvoked = true
const returned = await tool.execute(exec.arguments, exec)
const content = Array.isArray(returned) ? returned : returned.content
const meta = Array.isArray(returned) ? undefined : returned.meta
const result: ToolExecutionResult = {
content,
isError: false,
...meta !== undefined ? { meta } : {},
}
return isAborted(signal)
? toolAbortedResult(result)
: result
} catch (error: unknown) {
return toolErrorResult(error)
} finally {
fused.dispose()
exec.signal = wrapperSignal
}
}
/**
* Run around-dispatch and the tool body. Tool and unknown-tool failures still
* receive post-execute; pipeline failures are already final.
@@ -886,21 +1022,11 @@ export class ToolRegistry extends Service {
*/
private async dispatchScheduledExecution(exec: ToolRunContext): Promise<ScheduledToolDispatch> {
try {
const mutableExec = exec as MutableToolRunContext
const carrier = scopeTarget(this, exec.agent)
const result = await this.ctx.waterfall(
carrier, 'tools/execute', exec,
async (): Promise<ToolExecutionResult> => {
try {
const tool = this.get(exec.name, exec.agent)
if (!tool) throw new ToolNotFoundError(exec.name)
const returned = await tool.execute(exec.arguments, exec)
const content = Array.isArray(returned) ? returned : returned.content
const meta = Array.isArray(returned) ? undefined : returned.meta
return { content, isError: false, ...meta !== undefined ? { meta } : {} }
} catch (error: unknown) {
return toolErrorResult(error)
}
},
carrier, 'tools/execute', mutableExec,
() => this.dispatchToolBody(mutableExec),
)
const deferredContexts = this.deferredContexts.get(exec)
/* v8 ignore next -- dispatch only receives executions minted by this registry's prepare stage */
@@ -914,7 +1040,12 @@ export class ToolRegistry extends Service {
...result.additionalContexts ?? [],
],
}
return { kind: 'post-result', result: resultWithDeferredContexts }
return {
kind: 'post-result',
result: this.callerCancelled(exec) && !resultWithDeferredContexts.isError
? this.cancellationResult(exec, resultWithDeferredContexts)
: resultWithDeferredContexts,
}
} catch (error: unknown) {
return { kind: 'final-result', result: toolErrorResult(error) }
}
@@ -929,7 +1060,13 @@ export class ToolRegistry extends Service {
*/
private async finalizeScheduledExecution(exec: ToolRunContext, result: ToolExecutionResult): Promise<ToolExecutionResult> {
try {
return this.finishScheduledExecution(exec, await this.postExecute(exec, result))
const postResult = await this.postExecute(exec, result)
return this.finishScheduledExecution(
exec,
this.callerCancelled(exec) && !postResult.isError
? this.cancellationResult(exec, postResult)
: postResult,
)
} catch (error: unknown) {
return this.finishScheduledExecution(exec, toolErrorResult(error))
}
@@ -955,8 +1092,8 @@ export class ToolRegistry extends Service {
/** Notify observers without exposing a mutation or error channel into the outcome. */
private notifyResult(exec: ToolExecution, result: ToolExecutionResult): void {
// Freeze the remaining mutable signal slot before observers receive the
// shared WeakMap-keyable execution object.
// Freeze the registry's live object before observers receive its readonly
// WeakMap-keyable view.
Object.freeze(exec)
const { name: toolName, callId } = exec
const reportFailure = (error: unknown): void => {
@@ -989,26 +1126,41 @@ export class ToolRegistry extends Service {
private async serviceAsk(
exec: ToolExecution,
ask: Extract<PreToolDecision, { kind: 'ask' }>,
): Promise<Extract<PreToolDecision, { kind: 'allow' | 'deny' }>> {
): Promise<ToolAskResolution> {
const approval = this.ctx.get('approval')
if (approval === undefined) {
return { kind: 'deny', reason: ask.reason ?? `tool "${exec.name}" requires approval (not yet supported)` }
return {
decision: { kind: 'deny', reason: ask.reason ?? `tool "${exec.name}" requires approval (not yet supported)` },
approvalCancelled: false,
}
}
if (exec.agent === undefined) {
return { kind: 'deny', reason: `tool "${exec.name}" requires approval, but the call has no agent to route it through` }
return {
decision: { kind: 'deny', reason: `tool "${exec.name}" requires approval, but the call has no agent to route it through` },
approvalCancelled: false,
}
}
const outcome = await approval.request({
agent: exec.agent,
toolName: exec.name,
callId: exec.callId,
...ask.reason !== undefined ? { reason: ask.reason } : {},
...exec.signal !== undefined ? { signal: exec.signal } : {},
signal: exec.signal,
})
switch (outcome) {
case 'allowed-once': return { kind: 'allow' }
case 'rejected': return { kind: 'deny', reason: `the user rejected tool "${exec.name}"` }
case 'cancelled': return { kind: 'deny', reason: `approval for tool "${exec.name}" was cancelled` }
case 'unavailable': return { kind: 'deny', reason: `tool "${exec.name}" requires approval, but no approval channel is available` }
case 'allowed-once': return { decision: { kind: 'allow' }, approvalCancelled: false }
case 'rejected': return {
decision: { kind: 'deny', reason: `the user rejected tool "${exec.name}"` },
approvalCancelled: false,
}
case 'cancelled': return {
decision: { kind: 'deny', reason: `approval for tool "${exec.name}" was cancelled` },
approvalCancelled: true,
}
case 'unavailable': return {
decision: { kind: 'deny', reason: `tool "${exec.name}" requires approval, but no approval channel is available` },
approvalCancelled: false,
}
default: return assertNever(outcome, 'ApprovalOutcome')
}
}
@@ -1074,4 +1226,64 @@ function toolErrorResult(error: unknown): ToolExecutionResult {
}
}
/** Read live abort state across an await without treating it as synchronously immutable. */
function isAborted(signal: AbortSignal): boolean {
return signal.aborted
}
/**
* Fuse caller and wrapper cancellation without nesting `AbortSignal.any`.
* Keeping the relay dispatch-scoped also removes listeners when work settles.
*/
function fuseToolSignals(caller: AbortSignal, wrapper: AbortSignal): FusedToolSignal {
if (caller === wrapper) return { signal: caller, dispose() {} }
const controller = new AbortController()
let listening = false
const dispose = (): void => {
if (!listening) return
listening = false
caller.removeEventListener('abort', abortFromCaller)
wrapper.removeEventListener('abort', abortFromWrapper)
}
const abortFrom = (source: AbortSignal): void => {
const reason: unknown = source.reason
controller.abort(reason)
dispose()
}
const abortFromCaller = (): void => { abortFrom(caller) }
const abortFromWrapper = (): void => { abortFrom(wrapper) }
if (wrapper.aborted) abortFromWrapper()
else if (caller.aborted) abortFromCaller()
else {
listening = true
caller.addEventListener('abort', abortFromCaller, { once: true })
wrapper.addEventListener('abort', abortFromWrapper, { once: true })
}
return { signal: controller.signal, dispose }
}
/** Canonical result when cancellation supersedes success after body invocation. */
function toolAbortedResult(prior?: ToolExecutionResult): ToolExecutionResult {
const additionalContexts = prior?.additionalContexts ?? []
return {
content: [{ type: 'text', text: 'Error: tool call aborted' }],
isError: true,
error: { name: 'AbortError', code: TOOL_ABORTED },
...additionalContexts.length > 0 ? { additionalContexts } : {},
}
}
/** Canonical result when cancellation prevents tool body invocation. */
function toolAbortedBeforeDispatchResult(prior?: ToolExecutionResult): ToolExecutionResult {
const additionalContexts = prior?.additionalContexts ?? []
return {
content: [{ type: 'text', text: 'Error: tool call aborted before dispatch' }],
isError: true,
error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH },
...additionalContexts.length > 0 ? { additionalContexts } : {},
}
}
export default ToolRegistry

28
packages/core/tools/tests/code-mode.spec.ts
View File

@@ -6,12 +6,14 @@ import type { Scope } from '@deepseek-ai/dsh-scope'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
import type { CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
import ToolRegistry, { CodeRunFailedError, RUN_CODE_NAME, defineTool } from '@deepseek-ai/dsh-tools'
import ToolRegistry, { CodeRunFailedError, RUN_CODE_NAME, TOOL_ABORTED_BEFORE_DISPATCH, defineTool } from '@deepseek-ai/dsh-tools'
import type { Config, PostToolDecision, ToolExecutionResult } from '@deepseek-ai/dsh-tools'
import type { Agent } from '@deepseek-ai/dsh-agent'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
import type { SessionEventMap } from '@deepseek-ai/dsh-session'
const testToolSignal = new AbortController().signal
/**
* Code Mode unit tier (per the Agent Note's plan): provider contribution per mode,
* misconfiguration rejections, the run_code dispatch bridge (serialization,
@@ -95,6 +97,7 @@ function fakeAgent(options: { cwd?: string } = { cwd: '/workspace' }): { agent:
/** Dispatch run_code through the registry pipeline, as the loop would. */
async function runCode(ctx: Context, code: string, extras: { agent?: Agent; signal?: AbortSignal } = {}): Promise<ToolExecutionResult> {
return ctx.tools.execute({
signal: testToolSignal,
callId: CallId('call-1'),
name: RUN_CODE_NAME,
arguments: { code },
@@ -357,8 +360,7 @@ describe('the run_code dispatch bridge', () => {
const previous = exec.signal
exec.signal = new AbortController().signal
const result = await next()
if (previous === undefined) delete exec.signal
else exec.signal = previous
exec.signal = previous
return result
})
ctx.on('tools/result', (exec) => {
@@ -574,7 +576,7 @@ describe('the run_code dispatch bridge', () => {
seen.push(args.id)
await new Promise<void>((resolve) => {
const timer = setTimeout(resolve, 500)
exec.signal?.addEventListener('abort', () => { sawAbort = true; clearTimeout(timer); resolve() }, { once: true })
exec.signal.addEventListener('abort', () => { sawAbort = true; clearTimeout(timer); resolve() }, { once: true })
})
return [{ type: 'text' as const, text: args.id }]
},
@@ -610,7 +612,7 @@ describe('the run_code dispatch bridge', () => {
started()
await new Promise<void>((resolve) => {
const timer = setTimeout(resolve, 500)
exec.signal?.addEventListener('abort', () => { sawAbort = true; clearTimeout(timer); resolve() }, { once: true })
exec.signal.addEventListener('abort', () => { sawAbort = true; clearTimeout(timer); resolve() }, { once: true })
})
return [{ type: 'text' as const, text: args.id }]
},
@@ -838,7 +840,7 @@ describe('the run_code dispatch bridge', () => {
expect((result.content[0] as { text: string }).text).toBe('{ n: 42 }')
})
it('reports a pre-aborted outer signal as the run failure without dispatching anything', async () => {
it('short-circuits a pre-aborted outer signal before the code runtime', async () => {
const { ctx, runtime } = await setup({ mode: 'code' })
const calls = registerEcho(ctx)
runtime.behavior = (request) => {
@@ -850,11 +852,16 @@ describe('the run_code dispatch bridge', () => {
controller.abort('too-late')
const result = await runCode(ctx, 'program', { signal: controller.signal })
expect(result.isError).toBe(true)
expect((result.content[0] as { text: string }).text).toContain('code run failed (abort)')
expect(result).toEqual({
content: [{ type: 'text', text: 'Error: tool call aborted before dispatch' }],
isError: true,
error: { name: 'AbortError', code: TOOL_ABORTED_BEFORE_DISPATCH },
})
expect(runtime.lastRequest).toBeUndefined()
expect(calls).toEqual([])
})
it('rejects a binding invoked after the run is over without dispatching it', async () => {
it('reports cancellation after rejecting a late binding without dispatching it', async () => {
const { ctx, runtime } = await setup({ mode: 'code' })
const calls = registerEcho(ctx)
const controller = new AbortController()
@@ -865,8 +872,9 @@ describe('the run_code dispatch bridge', () => {
return { logs: [], value: message }
}
const result = await runCode(ctx, 'program', { signal: controller.signal })
expect(result.isError).toBe(false)
expect((result.content[0] as { text: string }).text).toContain('not dispatched')
expect(result.isError).toBe(true)
expect(result.error).toEqual({ name: 'AbortError', code: 'ABORTED' })
expect((result.content[0] as { text: string }).text).toBe('Error: tool call aborted')
expect(calls).toEqual([])
})

4
packages/core/tools/tests/execution-mode.spec.ts
View File

@@ -11,6 +11,8 @@ import ToolRegistry, {
type ToolExecutionMode,
} from '@deepseek-ai/dsh-tools'
const testToolSignal = new AbortController().signal
async function setup() {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
@@ -19,7 +21,7 @@ async function setup() {
}
function exec(name: string, args: unknown): ToolExecutionInput {
return { callId: CallId('c1'), name, arguments: args }
return { signal: testToolSignal, callId: CallId('c1'), name, arguments: args }
}
describe('ToolRegistry.executionMode', () => {

100
packages/core/tools/tests/execution-signal-types.spec.ts Normal file
View File

@@ -0,0 +1,100 @@
import { describe, expectTypeOf, it } from 'vitest'
import type { Context } from 'cordis'
import { CallId } from '@deepseek-ai/dsh-llm'
import { defineTool } from '@deepseek-ai/dsh-tools'
import type {
ToolDispatchExecution,
ToolExecution,
ToolExecutionInput,
ToolRunContext,
} from '@deepseek-ai/dsh-tools'
function inputAndExecutionContracts(
input: ToolExecutionInput,
execution: ToolExecution,
run: ToolRunContext,
): void {
// @ts-expect-error -- every typed invocation must supply a caller-owned signal.
const missingSignal: ToolExecutionInput = { callId: CallId('missing'), name: 'probe', arguments: {} }
void missingSignal
// @ts-expect-error -- caller input is readonly after construction.
input.signal = new AbortController().signal
// @ts-expect-error -- required readonly properties cannot be deleted.
delete input.signal
// @ts-expect-error -- required signals cannot become undefined.
input.signal = undefined
// @ts-expect-error -- pipeline observers receive a readonly execution view.
execution.signal = new AbortController().signal
// @ts-expect-error -- pipeline observers cannot remove the required signal.
delete execution.signal
// @ts-expect-error -- tool bodies receive a readonly run context.
run.signal = new AbortController().signal
// @ts-expect-error -- tool bodies cannot remove the required signal.
delete run.signal
// @ts-expect-error -- tool bodies cannot replace the required signal with undefined.
run.signal = undefined
}
void inputAndExecutionContracts
function observerContracts(ctx: Context): void {
ctx.on('tools/pre-execute', (exec, next) => {
// @ts-expect-error -- pre-policy sees a readonly signal.
exec.signal = new AbortController().signal
// @ts-expect-error -- pre-policy cannot remove the required signal.
delete exec.signal
// @ts-expect-error -- pre-policy cannot replace the required signal with undefined.
exec.signal = undefined
return next()
})
ctx.on('tools/post-execute', (exec, _result, next) => {
// @ts-expect-error -- post-policy sees a readonly signal.
exec.signal = new AbortController().signal
// @ts-expect-error -- post-policy sees a readonly signal.
delete exec.signal
// @ts-expect-error -- post-policy cannot replace the required signal with undefined.
exec.signal = undefined
return next()
})
ctx.on('tools/result', (exec) => {
// @ts-expect-error -- result observers see a readonly signal.
exec.signal = new AbortController().signal
// @ts-expect-error -- result observers cannot remove the required signal.
delete exec.signal
// @ts-expect-error -- result observers see a readonly signal.
exec.signal = undefined
})
ctx.on('tools/execute', (exec, next) => {
exec.signal = new AbortController().signal
// @ts-expect-error -- around-dispatch may replace but not remove the signal.
delete exec.signal
// @ts-expect-error -- around-dispatch cannot replace the required signal with undefined.
exec.signal = undefined
return next()
})
}
void observerContracts
const inferredTool = defineTool({
name: 'signal-inference',
description: 'Pins contextual signal inference.',
parameters: {},
async execute(_args, exec) {
expectTypeOf(exec.signal).toEqualTypeOf<AbortSignal>()
// @ts-expect-error -- defineTool contextually exposes a readonly signal.
exec.signal = new AbortController().signal
return []
},
})
void inferredTool
describe('tool execution signal types', () => {
it('requires an exact AbortSignal at every readonly tool view', () => {
expectTypeOf<ToolExecutionInput['signal']>().toEqualTypeOf<AbortSignal>()
expectTypeOf<ToolExecution['signal']>().toEqualTypeOf<AbortSignal>()
expectTypeOf<ToolRunContext['signal']>().toEqualTypeOf<AbortSignal>()
expectTypeOf<ToolDispatchExecution['signal']>().toEqualTypeOf<AbortSignal>()
expectTypeOf<typeof inferredTool.execute>().toBeFunction()
})
})

3
packages/core/tools/tests/invariant.spec.ts
View File

@@ -6,6 +6,8 @@ import type { ToolExecution, ToolExecutionResult, ToolExecutionToken } from '@de
import * as ToolsInvariant from '@deepseek-ai/dsh-tools/invariant'
import InvariantService from '@deepseek-ai/dsh-invariants'
const testToolSignal = new AbortController().signal
async function setup(): Promise<Context> {
const ctx = new Context()
await ctx.plugin(InvariantService)
@@ -19,6 +21,7 @@ const execution = (overrides: Partial<ToolExecution> = {}): ToolExecution => ({
name: 'echo',
arguments: Object.freeze({ text: 'hi' }),
...overrides,
signal: overrides.signal ?? testToolSignal,
})
const outcome = (): ToolExecutionResult => Object.freeze({

15
packages/core/tools/tests/scoped.spec.ts
View File

@@ -12,6 +12,8 @@ import { CallId } from '@deepseek-ai/dsh-llm'
import type { ContentBlock } from '@deepseek-ai/dsh-llm'
import type { SessionId } from '@deepseek-ai/dsh-session'
const testToolSignal = new AbortController().signal
/** Mount the registry (with its systemPrompt dependency) on a fresh context. */
async function mount(): Promise<Context> {
const ctx = new Context()
@@ -43,6 +45,7 @@ function tool(name: string, reply = `ran:${name}`): ToolDefinition {
async function run(ctx: Context, name: string, agent?: Agent): Promise<string> {
const result = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('c1'),
name,
arguments: {},
@@ -305,6 +308,7 @@ describe('scoped execution dispatch', () => {
expect(await run(ctx, 'danger', key)).toBe('Error: danger denied')
const callerArguments = { source: true }
const safeResult = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('safe-call'),
name: 'safe',
arguments: callerArguments,
@@ -348,7 +352,7 @@ describe('scoped execution dispatch', () => {
if (exec.name === 'parent') parent = exec.token
return next()
})
await ctx.tools.execute({ callId: CallId('parent'), name: 'parent', arguments: {} })
await ctx.tools.execute({ signal: testToolSignal, callId: CallId('parent'), name: 'parent', arguments: {} })
stopCapture()
policyCalls = 0
const signal = new AbortController().signal
@@ -372,6 +376,7 @@ describe('scoped execution dispatch', () => {
signal,
})
const subjectlessResult = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('non-cloneable-subjectless'),
name: 't',
arguments: { invalid: () => undefined },
@@ -414,6 +419,7 @@ describe('scoped execution dispatch', () => {
callId: CallId('stateful-parent'),
name: 't',
arguments: {},
signal: testToolSignal,
get parent(): ToolExecutionToken | undefined {
parentReads += 1
return parentReads === 1 ? undefined : forged
@@ -438,7 +444,7 @@ describe('scoped execution dispatch', () => {
if (exec.name === 'parent') parent = exec.token
return next()
})
await ctx.tools.execute({ callId: CallId('parent'), name: 'parent', arguments: {} })
await ctx.tools.execute({ signal: testToolSignal, callId: CallId('parent'), name: 'parent', arguments: {} })
stopCapture()
const acceptedSignal = new AbortController().signal
const driftSignal = new AbortController().signal
@@ -485,6 +491,7 @@ describe('scoped execution dispatch', () => {
const input = {
callId: CallId('throwing-arguments'),
name: 't',
signal: testToolSignal,
get arguments(): unknown {
argumentReads += 1
throw new Error('getter exploded')
@@ -525,6 +532,7 @@ describe('scoped execution dispatch', () => {
})
const result = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('bad-arguments'), name: 't', arguments: argumentsValue,
})
@@ -545,6 +553,7 @@ describe('scoped execution dispatch', () => {
})
const result = await ctx.tools.execute({
signal: testToolSignal,
callId: CallId('unstable-arguments'), name: 't', arguments: argumentsValue,
})
@@ -585,7 +594,7 @@ describe('scoped execution dispatch', () => {
ctx.on('tools/result', () => Promise.reject(new Error('async observer failure')) as never)
ctx.on('tools/result', (_exec, result) => { seen.push(result.isError) })
const result = await ctx.tools.execute({ callId: CallId('final'), name: 't', arguments: {}, agent: key })
const result = await ctx.tools.execute({ signal: testToolSignal, callId: CallId('final'), name: 't', arguments: {}, agent: key })
await Promise.resolve()
expect(result).toMatchObject({ isError: true, content: [{ type: 'text', text: 'outer failure' }] })
expect(seen).toEqual([true, true])

692
packages/core/tools/tests/tools.spec.ts
View File

File diff suppressed because it is too large Load Diff