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

Merge branch 'codex/goal-tools' into codex/goal-session

Browse Source 
# Conflicts:
#	.agents/notes/implemented/feature/2026-07-19-persisted-same-session-goal-domain.i18n.yaml
#	docs/cordis-catalog/events.md
#	docs/core-data-structures/core.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	examples/package.json
#	packages/core/agent/README.md
#	packages/core/agent/src/types.ts
#	website/zh-CN/api/harness/events.md
This commit is contained in:
Tianyi Cui
2026-07-20 20:35:15 +08:00
parent df7be480e1 1dcfc63a78
commit eb5ae54a79
462 changed files with 13121 additions and 8781 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -46,7 +46,9 @@ Configured agents start automatically. A model call requires both `provider` and
### Internal concrete driver
The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. The concrete `send()`, running `steer()`, and open-turn `inject()` materialize content plus resolved source once as detached, deeply frozen lossless JSON; malformed data throws before enqueue or append. An injection that arrives while the current step executes assistant tool calls stays in a FIFO until the batch settles; successful batches place it after the complete result batch, and interrupted batches drain it before the turn closes. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy.
The concrete `Agent` class, its `Inbox`, `runLoop`, and instance-bound publication/start controls are package-internal. The package root exports only the plugin/service/config contract, and the package exports map exposes no `./src/*` escape hatch; lifecycle owners create agents through `ctx.agents` rather than naming, constructing, or starting driver internals. One prepared session can be claimed by only one concrete driver, and everything observable happens through session events and the `agent/*` event taxonomy.
Each concrete `send()` materializes content plus resolved source once as a detached, deeply frozen lossless-JSON FIFO item. If claimed, it is the sole ordinary message in its turn; a successor waits for the preceding ordinary turn's checkpoint to settle, while cancellation, disposal, or a pre-start failure may drop it without a turn. Running `steer()` enters the steering FIFO: an open turn records it at the next steering checkpoint before a request or continuation decision, but policy can still stop before another step; steering left after turn close and its checkpoint becomes later queued input unless terminal turn policy, cancellation, or disposal discards it. Open-turn `inject()` uses the same accepted-value boundary but defers in a FIFO while the current step executes assistant tool calls; successful batches place it after all results, and interrupted batches drain it before turn close. Malformed data throws before enqueue or append.
### Loop lifecycle (`loop.ts`)

3
packages/core/agent-loop/src/agent.ts
View File

@@ -252,7 +252,6 @@ export class ReactLoopAgent implements Agent {
const context = {
content,
source,
...options?.envelope !== undefined ? { envelope: options.envelope } : {},
...options?.meta !== undefined ? { meta: options.meta } : {},
}
if (isTurnOpen(this.session)) {
@@ -403,7 +402,7 @@ export class ReactLoopAgent implements Agent {
cancelReason: () => this.cancelReason,
clearCancel: () => { this.cancelRequested = false },
withToolBatch: run => this.withToolBatch(run),
// Pre-step cancellation re-parks without emitting a status transition.
// Pre-start cancellation settles queued-work waiters before publishing idle.
settleIdle: () => { this.settleIdleWaiters() },
}))
}

12
packages/core/agent-loop/src/inbox.ts
View File

@@ -15,7 +15,7 @@ export interface InboxMessage {
}
/**
* Per-agent inbox: a queued FIFO (drained at turn start) and a steering FIFO
* Per-agent inbox: a queued FIFO (dequeued once per turn start) and a steering FIFO
* (drained between steps of a running turn). Purely an in-memory mechanism of
* the loop — the public surface is `Agent.send()` / `Agent.steer()`.
*/
@@ -54,11 +54,11 @@ export class Inbox {
}
/**
* Drain all queued messages (turn start).
* @returns the drained messages in arrival order; the queued FIFO is left empty.
* Remove the oldest queued message for one turn start.
* @returns the oldest message, or `undefined` when the queued FIFO is empty.
*/
drainQueued(): InboxMessage[] {
return this.queuedMessages.splice(0)
dequeueQueued(): InboxMessage | undefined {
return this.queuedMessages.shift()
}
/**
@@ -72,7 +72,7 @@ export class Inbox {
/**
* Discard all pending messages (queued + steering) without delivering them —
* used by `cancel()`, which drops un-started work rather than draining it into
* a turn. Unlike `drainQueued`/`drainSteering`, the messages are thrown away.
* a turn. Unlike `dequeueQueued`/`drainSteering`, the messages are thrown away.
*/
clear(): void {
this.queuedMessages.length = 0

7
packages/core/agent-loop/src/index.ts
View File

@@ -620,12 +620,7 @@ export class AgentLoop extends Service implements AgentFactory {
transaction.assertActive()
const session = this.runtime.ctx.sessions.prepare(options.resumeSessionId, {
seed: loaded.events,
meta: {
createdAt: loaded.meta.createdAt,
...loaded.meta.cwd === undefined ? {} : { cwd: loaded.meta.cwd },
...loaded.meta.parentSession === undefined ? {} : { parentSession: loaded.meta.parentSession },
...loaded.meta.seedLength === undefined ? {} : { seedLength: loaded.meta.seedLength },
},
meta: loaded.meta,
})
const agent = transaction.prepare(agentOptions, session, this.maxParallelToolCalls)
await transaction.waitFor(options.setup?.(agent.ctx))

92
packages/core/agent-loop/src/loop.ts
View File

@@ -91,16 +91,16 @@ export interface LoopHandle {
cancelReason(): string
/** Clear the cancel marker (called once per iteration after the turn returns). */
clearCancel(): void
/** Settle idle waiters when pre-running cancellation skips a turn, without emitting `agent/status`. */
/** 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. */
readonly withToolBatch: <T>(run: (acceptContext: (context: HookContext) => void) => Promise<T>) => Promise<T>
}
/**
* Drive queued batches as durable turns until disposal. Plugin failures end the
* current turn without terminating the driver. The caller establishes the
* `ctx.agents.withInitiator()` boundary before entry; package-private
* Drive queued messages as independent durable turns until disposal. Plugin
* failures end the current turn without terminating the driver. The caller
* establishes the `ctx.agents.withInitiator()` boundary before entry; package-private
* orchestration recovers that exact Agent and captures its Session locally.
* @param ctx - the plugin context the loop reaches its initiating Agent,
* events (agent/…, session/flush), and services (systemPrompt, llm, tools)
@@ -118,20 +118,35 @@ export async function runLoop(ctx: Context, handle: LoopHandle): Promise<void> {
const events = agentEvents(ctx, agent)
while (!handle.isDisposed()) {
await handle.inbox.waitForQueued(handle.disposed)
if (handle.isDisposed()) break
// Cancellation between wake and `running` skips only the cancelled work;
// a replacement prompt still runs and owns the eventual idle transition.
// 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.inbox.hasQueued) {
handle.settleIdle()
handle.setStatus('idle')
continue
}
}
await handle.inbox.waitForQueued(handle.disposed)
if (handle.isDisposed()) break
// 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.inbox.hasQueued) {
// Settle before publishing idle: the already-idle path has no status
// transition, while an idle listener can register waiters for new work.
handle.settleIdle()
handle.setStatus('idle')
continue
}
}
handle.setStatus('running')
if (handle.isDisposed()) break
// A synchronous `running` listener can cancel before `runTurn`; balance the
// status only when no replacement prompt was queued by that listener.
@@ -182,12 +197,11 @@ async function runTurn(
return messages.length > 0
}
// Drain before opening the turn, but append only after `turn/start`.
const queued = handle.inbox.drainQueued()
const first = queued[0]
// Claim one queued message before opening its turn, but append it only after `turn/start`.
const message = handle.inbox.dequeueQueued()
/* v8 ignore next 3 -- invariant guard: runLoop only calls runTurn when hasQueued */
if (!first) throw new Error('runTurn invariant violated: no queued message at turn start')
const trigger: TurnTrigger = { kind: 'message', source: first.source }
if (!message) throw new Error('runTurn invariant violated: no queued message at turn start')
const trigger: TurnTrigger = { kind: 'message', source: message.source }
let reason: TurnEndReason = { kind: 'completed' }
let step = 0
@@ -226,56 +240,36 @@ 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 })
// Each drained queued message runs the `agent/prompt-submit` waterfall before
// it becomes a `user/message` — a hook can rewrite the prompt or block it.
// 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.
let anyAllowed = false
// Seeded with a floor (only observable if the batch were empty, which
// runTurn never allows — it is called with ≥1 queued message); each `block`
// decision carries a required `reason` and overwrites it, so a fully-blocked
// batch always reports the last vetoing reason.
let lastBlockReason = 'prompt blocked by hook'
for (const message of queued) {
const decision = await events.waterfall(
'agent/prompt-submit', message.content, message.source,
() => Promise.resolve<PromptDecision>({ kind: 'allow' }),
)
if (decision.kind === 'block') {
lastBlockReason = decision.reason
// Record the veto durably: `PromptDecision.reason` is the durable record
// of why a prompt was blocked, but a fully-blocked batch's `rejected`
// turn/end only preserves the LAST reason, and a MIXED batch (this prompt
// blocked, another allowed) does not end `rejected` at all — so without
// this append a blocked prompt would vanish from the log whenever any
// sibling prompt is allowed. `prompt/blocked` sits in the open turn in
// place of the `user/message` this prompt would have become.
session.append('prompt/blocked', { content: message.content, source: message.source, reason: decision.reason })
continue
}
anyAllowed = true
const promptDecision = await events.waterfall(
'agent/prompt-submit', message.content, message.source,
() => Promise.resolve<PromptDecision>({ kind: 'allow' }),
)
if (promptDecision.kind === 'block') {
session.append('prompt/blocked', { content: message.content, source: message.source, reason: promptDecision.reason })
reason = { kind: 'rejected', reason: promptDecision.reason }
} else {
// `allow.content` REPLACES the prompt bytes (a rewrite); absent keeps them.
const content = decision.content ?? message.content
const content = promptDecision.content ?? message.content
session.append('user/message', { content, source: message.source }, { surfaceOp: 'append' })
// Every `allow.additionalContexts` entry is a separate context/message the
// next request also sees. The turn is open, so inject() appends each one
// into THIS turn without flattening provenance, framing, or metadata.
for (const context of decision.additionalContexts ?? []) {
// into THIS turn without flattening provenance or metadata.
for (const context of promptDecision.additionalContexts ?? []) {
agent.inject(context.content, {
source: context.source,
...context.envelope !== undefined ? { envelope: context.envelope } : {},
...context.meta !== undefined ? { meta: context.meta } : {},
})
}
}
while (true) {
// A fully blocked batch closes its zero-step turn as rejected.
if (!anyAllowed) {
reason = { kind: 'rejected', reason: lastBlockReason }
break
}
// A blocked prompt closes its zero-step turn as rejected.
if (promptDecision.kind === 'block') break
step += 1
// Steering from the previous round's continuation listeners joins before

193
packages/core/agent-loop/tests/cancel.spec.ts
View File

@@ -106,7 +106,8 @@ describe('Agent.cancel()', () => {
// send() queues synchronously (status still idle, loop microtask not yet
// resumed). Cancel in that pre-step window: the queued turn must not run.
send(agent, 'drop me')
send(agent, 'drop me first')
send(agent, 'drop me second')
agent.cancel('pre-step')
// Give the loop a chance to wake and process the cancel.
@@ -118,6 +119,35 @@ describe('Agent.cancel()', () => {
expect(agent.status).toBe('idle')
})
it('disposal from the running notification drops queued work before turn start', async () => {
const adapter = new MockAdapter([textResponse('should not run')])
const ctx = await harness(adapter)
const handle = await ctx.agents.create({
sessionId: SessionId('dispose-running-session'),
agentOptions: { provider: 'mock', model: 'mock' },
})
const agent = handle.agent
const running = Promise.withResolvers<undefined>()
let disposalDone: Promise<void> | undefined
ctx.on('agent/status', (subject, status) => {
if (subject !== agent || status !== 'running') return
disposalDone = handle.dispose()
running.resolve(undefined)
})
send(agent, 'drop before claim')
await running.promise
if (disposalDone === undefined) throw new Error('running listener did not start disposal')
await disposalDone
await driverDone(agent)
expect(agent.status).toBe('disposed')
expect(agent.session.events.some(event => event.type === 'turn/start')).toBe(false)
expect(userTexts(agent)).toEqual([])
expect(adapter.requests).toHaveLength(0)
})
it('a whenIdle() waiter registered BEFORE a pre-step cancel resolves (F1 hang guard)', async () => {
const adapter = new MockAdapter([textResponse('x')])
const ctx = await harness(adapter)
@@ -137,7 +167,162 @@ describe('Agent.cancel()', () => {
expect(agent.status).toBe('idle')
})
it('cancel() mid-step aborts the in-flight model call; the turn ends aborted', async () => {
it('cancel() between consecutive turns restores idle and leaves idle steer usable', async () => {
const adapter = new MockAdapter([textResponse('first reply'), textResponse('steer reply')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('between-turn-cancel'), { provider: 'mock', model: 'mock' })
let rejectFirstFlush = true
ctx.on('session/flush', (session) => {
if (session !== agent.session || !rejectFirstFlush) return
rejectFirstFlush = false
throw new Error('first flush failed')
})
const cancelled = Promise.withResolvers<undefined>()
ctx.on('agent/error', (subject, _turn, _step, error) => {
if (subject !== agent || error.message !== 'first flush failed') return
// The first hop runs before runLoop resumes from runTurn; the second lands
// before its resolved waitForQueued continuation checks cancellation.
queueMicrotask(() => {
queueMicrotask(() => {
agent.cancel('between turns')
cancelled.resolve(undefined)
})
})
})
const statuses: string[] = []
ctx.on('agent/status', (subject, status) => {
if (subject === agent) statuses.push(status)
})
send(agent, 'first')
send(agent, 'queued tail')
await cancelled.promise
expect(agent.status).toBe('idle')
expect(statuses).toEqual(['running', 'idle'])
expect(adapter.requests).toHaveLength(1)
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
expect(userTexts(agent)).toEqual(['first'])
let idleResolved = false
void agent.whenIdle().then(() => { idleResolved = true })
await Promise.resolve()
expect(idleResolved).toBe(true)
const idle = waitForIdle(ctx, agent)
agent.steer([{ type: 'text', text: 'idle steer' }])
await idle
expect(statuses).toEqual(['running', 'idle', 'running', 'idle'])
expect(adapter.requests).toHaveLength(2)
expect(userTexts(agent)).toEqual(['first', 'idle steer'])
})
it('an idle-listener replacement keeps whenIdle pending until the replacement turn finishes', async () => {
const adapter = new MockAdapter([textResponse('first reply'), textResponse('replacement reply')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('between-turn-idle-listener'), { provider: 'mock', model: 'mock' })
let rejectFirstFlush = true
ctx.on('session/flush', (session) => {
if (session !== agent.session || !rejectFirstFlush) return
rejectFirstFlush = false
throw new Error('first flush failed')
})
ctx.on('agent/error', (subject, _turn, _step, error) => {
if (subject !== agent || error.message !== 'first flush failed') return
queueMicrotask(() => {
queueMicrotask(() => { agent.cancel('between turns') })
})
})
const replacementRegistered = Promise.withResolvers<undefined>()
let replacementObservation: Promise<{ status: string; requests: number; turns: number }> | undefined
ctx.on('agent/status', (subject, status) => {
if (subject !== agent || status !== 'idle' || replacementObservation !== undefined) return
send(agent, 'replacement')
replacementObservation = agent.whenIdle().then(() => ({
status: agent.status,
requests: adapter.requests.length,
turns: agent.session.events.filter(event => event.type === 'turn/start').length,
}))
replacementRegistered.resolve(undefined)
})
send(agent, 'first')
send(agent, 'cancelled tail')
await replacementRegistered.promise
if (replacementObservation === undefined) throw new Error('idle listener did not register replacement work')
await expect(replacementObservation).resolves.toEqual({ status: 'idle', requests: 2, turns: 2 })
expect(userTexts(agent)).toEqual(['first', 'replacement'])
})
it('idle-listener cancellation settles its waiter without cancelling later work', async () => {
const adapter = new MockAdapter([textResponse('first reply'), textResponse('later reply')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('idle-listener-cancel'), { provider: 'mock', model: 'mock' })
const replacementRegistered = Promise.withResolvers<undefined>()
let replacementObservation: Promise<{ status: string; requests: number; turns: number }> | undefined
ctx.on('agent/status', (subject, status) => {
if (subject !== agent || status !== 'idle' || replacementObservation !== undefined) return
send(agent, 'cancelled replacement')
replacementObservation = agent.whenIdle().then(() => ({
status: agent.status,
requests: adapter.requests.length,
turns: agent.session.events.filter(event => event.type === 'turn/start').length,
}))
agent.cancel('idle listener')
replacementRegistered.resolve(undefined)
})
send(agent, 'first')
await replacementRegistered.promise
if (replacementObservation === undefined) throw new Error('idle listener did not register replacement work')
await expect(Promise.race([
replacementObservation,
new Promise((_resolve, reject) => setTimeout(() => { reject(new Error('whenIdle hung after idle-listener cancel')) }, 1000)),
])).resolves.toEqual({ status: 'idle', requests: 1, turns: 1 })
const idle = waitForIdle(ctx, agent)
send(agent, 'later')
await idle
expect(adapter.requests).toHaveLength(2)
expect(userTexts(agent)).toEqual(['first', 'later'])
})
it('replacement work queued after idle-listener cancellation still runs', async () => {
const adapter = new MockAdapter([textResponse('first reply'), textResponse('replacement reply')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('idle-listener-post-cancel-send'), { provider: 'mock', model: 'mock' })
const replacementRegistered = Promise.withResolvers<undefined>()
let replacementIdle: Promise<void> | undefined
ctx.on('agent/status', (subject, status) => {
if (subject !== agent || status !== 'idle' || replacementIdle !== undefined) return
send(agent, 'cancelled replacement')
agent.cancel('idle listener')
send(agent, 'surviving replacement')
replacementIdle = agent.whenIdle()
replacementRegistered.resolve(undefined)
})
send(agent, 'first')
await replacementRegistered.promise
if (replacementIdle === undefined) throw new Error('idle listener did not register replacement work')
await replacementIdle
expect(adapter.requests).toHaveLength(2)
expect(userTexts(agent)).toEqual(['first', 'surviving replacement'])
})
it('cancel() mid-step aborts the active turn and drops every queued tail item', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
@@ -148,10 +333,14 @@ describe('Agent.cancel()', () => {
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
expect(agent.status).toBe('running')
send(agent, 'queued tail')
agent.cancel('mid-step')
await waitForIdle(ctx, agent)
expect(reasons).toEqual([{ kind: 'aborted', reason: 'mid-step' }])
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 () => {

40
packages/core/agent-loop/tests/contract-regressions.spec.ts
View File

@@ -632,15 +632,20 @@ describe('plugin exceptions are contained', () => {
expect(agent.status).toBe('idle')
})
it('a rejecting session/flush listener is reported but does not kill the agent', async () => {
it('a rejecting first-turn flush settles before the queued tail starts', async () => {
const adapter = new MockAdapter([textResponse('one'), textResponse('two')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let rejectedOnce = false
ctx.on('session/flush', async () => {
if (!rejectedOnce) {
rejectedOnce = true
const firstFlush = Promise.withResolvers<undefined>()
const releaseFirstFlush = Promise.withResolvers<undefined>()
let flushes = 0
ctx.on('session/flush', async (session) => {
if (session !== agent.session) return
flushes += 1
if (flushes === 1) {
firstFlush.resolve(undefined)
await releaseFirstFlush.promise
throw new Error('disk full')
}
})
@@ -648,18 +653,25 @@ describe('plugin exceptions are contained', () => {
const errors: Error[] = []
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
const idle = waitForIdle(ctx, agent)
send(agent, 'first')
await waitForIdle(ctx, agent)
expect(errors.map(e => e.message)).toEqual(['disk full'])
send(agent, 'second')
await waitForIdle(ctx, agent)
await firstFlush.promise
expect(adapter.requests).toHaveLength(1)
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
releaseFirstFlush.resolve(undefined)
await idle
expect(errors.map(e => e.message)).toEqual(['disk full'])
expect(adapter.requests).toHaveLength(2)
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
})
})
describe('disposed status is part of the agent/status contract', () => {
it('disposing the fiber emits agent/status(disposed) and ends the turn with reason disposed', async () => {
it('disposing the fiber ends the active turn and never starts its queued tail', async () => {
const adapter = new MockAdapter(['hang'])
const ctx = await harness(adapter)
@@ -675,11 +687,19 @@ describe('disposed status is part of the agent/status contract', () => {
send(agent, 'go')
await new Promise(r => setTimeout(r, 30))
send(agent, 'queued tail')
await fiber.dispose()
await driverDone(agent)
expect(statuses).toEqual(['running', 'disposed'])
expect(reasons).toEqual([{ kind: 'disposed' }])
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(1)
const messages = agent.session.events
.filter(event => event.type === 'user/message')
.flatMap(event => event.data.content)
.flatMap(block => block.type === 'text' ? [block.text] : [])
expect(messages).toEqual(['go'])
expect(adapter.requests).toHaveLength(1)
})
it('a throwing agent/status listener cannot break disposal or leak the registry entry', async () => {

16
packages/core/agent-loop/tests/coverage-edges.spec.ts
View File

@@ -146,12 +146,22 @@ describe('toError normalization', () => {
const errors: Error[] = []
ctx.on('agent/error', (_agent, _turn, _step, error) => void errors.push(error))
send(agent, 'go')
send(agent, 'fails before turn start')
send(agent, 'survives as the next item')
await waitForIdle(ctx, agent)
expect(errors).toHaveLength(1)
expect(errors[0]).toMatchObject({ message: 'naked string error', code: 'UNKNOWN' })
expect(adapter.requests).toEqual([])
expect(agent.session.events.some(event => event.type === 'turn/start' || event.type === 'turn/end')).toBe(false)
expect(adapter.requests).toHaveLength(1)
const starts = agent.session.events.filter(event => event.type === 'turn/start')
const ends = agent.session.events.filter(event => event.type === 'turn/end')
const messages = agent.session.events.filter(event => event.type === 'user/message')
expect(starts).toHaveLength(1)
expect(starts[0]?.type === 'turn/start' && starts[0].data.turn).toBe(1)
expect(ends).toHaveLength(1)
expect(messages).toHaveLength(1)
expect(messages[0]?.type === 'user/message' && messages[0].data.content).toEqual([
{ type: 'text', text: 'survives as the next item' },
])
})
it('normalizes non-Error throws from agent/request waterfall via inline toError in runStep catch', async () => {

10
packages/core/agent-loop/tests/inbox.spec.ts
View File

@@ -8,17 +8,17 @@ function resolverPair() {
}
describe('Inbox', () => {
it('enqueues and drains queued messages in FIFO order', () => {
it('dequeues one queued message at a time in FIFO order', () => {
const inbox = new Inbox()
inbox.enqueue({ content: [{ type: 'text', text: 'first' }], source: { kind: 'user' } })
inbox.enqueue({ content: [{ type: 'text', text: 'second' }], source: { kind: 'user' } })
expect(inbox.hasQueued).toBe(true)
const drained = inbox.drainQueued()
expect(drained).toHaveLength(2)
expect(drained[0]!.content[0]).toMatchObject({ text: 'first' })
expect(drained[1]!.content[0]).toMatchObject({ text: 'second' })
expect(inbox.dequeueQueued()?.content[0]).toMatchObject({ text: 'first' })
expect(inbox.hasQueued).toBe(true)
expect(inbox.dequeueQueued()?.content[0]).toMatchObject({ text: 'second' })
expect(inbox.hasQueued).toBe(false)
expect(inbox.dequeueQueued()).toBeUndefined()
})
it('pushes and drains steering messages separately from queued', () => {

55
packages/core/agent-loop/tests/interception.spec.ts
View File

@@ -99,7 +99,6 @@ describe('agent/prompt-submit', () => {
additionalContexts: [{
content: [{ type: 'text', text: '<system-reminder>extra ctx</system-reminder>' }],
source: { kind: 'plugin', plugin: 'test' },
envelope: 'raw',
meta,
}],
}))
@@ -113,7 +112,6 @@ describe('agent/prompt-submit', () => {
expect(userMsg).toBeDefined()
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.content).toEqual([{ type: 'text', text: '<system-reminder>extra ctx</system-reminder>' }])
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.source).toEqual({ kind: 'plugin', plugin: 'test' })
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.envelope).toBe('raw')
expect(ctxMsg?.type === 'context/message' && ctxMsg.data.meta).toEqual(meta)
const sent = JSON.stringify(adapter.requests[0]!.messages)
expect(sent).toContain('extra ctx')
@@ -179,9 +177,7 @@ describe('agent/prompt-submit', () => {
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason).toEqual({ kind: 'rejected', reason: 'blocked by policy' })
})
it('a mixed batch records a prompt/blocked for the vetoed prompt while the allowed one runs', async () => {
// Blocking one prompt in a mixed batch must persist its reason even though
// the allowed prompt keeps the turn from ending rejected.
it('adjacent blocked and allowed prompts keep independent turn outcomes', async () => {
const adapter = new MockAdapter([textResponse('ran once')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
@@ -194,13 +190,13 @@ describe('agent/prompt-submit', () => {
const reasons: TurnEndReason[] = []
ctx.on('session/event', (_s, event: SessionEvent) => { if (event.type === 'turn/end') reasons.push(event.data.reason) })
// both sends land before the loop drains → one batched turn
// Both sends land before the driver wakes, but each remains its own turn.
send(agent, 'secret')
send(agent, 'safe')
await waitForIdle(ctx, agent)
const log = events(agent)
// the allowed prompt became a user/message and drove exactly one model call
// The allowed prompt became a user/message and drove exactly one model call.
const userMsgs = log.filter(e => e.type === 'user/message')
expect(userMsgs).toHaveLength(1)
expect(userMsgs[0]?.type === 'user/message' && userMsgs[0].data.content).toEqual([{ type: 'text', text: 'safe' }])
@@ -212,12 +208,14 @@ describe('agent/prompt-submit', () => {
content: [{ type: 'text', text: 'secret' }],
reason: 'policy: no secrets',
})
// the turn did NOT reject — a sibling was allowed — so the boundary reason
// alone would not have preserved the block
expect(reasons.some(r => r.kind === 'rejected')).toBe(false)
expect(log.filter(e => e.type === 'turn/start')).toHaveLength(2)
expect(reasons).toEqual([
{ kind: 'rejected', reason: 'policy: no secrets' },
{ kind: 'completed' },
])
})
it('a throwing prompt-submit listener ends the turn balanced (error), loop survives', async () => {
it('a throwing prompt-submit listener ends its turn balanced while an adjacent message survives', async () => {
const adapter = new MockAdapter([textResponse('after')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
@@ -228,20 +226,31 @@ describe('agent/prompt-submit', () => {
return { kind: 'allow' as const }
})
const errors: Error[] = []
const reasons: TurnEndReason[] = []
const statuses: string[] = []
ctx.on('agent/error', (_a, _t, _s, error) => void errors.push(error))
ctx.on('agent/status', (subject, status) => { if (subject === agent) statuses.push(status) })
ctx.on('session/event', (session, event) => {
if (session === agent.session && event.type === 'turn/end') reasons.push(event.data.reason)
})
const idle = waitForIdle(ctx, agent)
send(agent, 'first')
await waitForIdle(ctx, agent)
expect(errors.map(e => e.message)).toEqual(['prompt hook broke'])
// turn balanced
const log = events(agent)
expect(log.filter(e => e.type === 'turn/start')).toHaveLength(1)
expect(log.filter(e => e.type === 'turn/end')).toHaveLength(1)
// loop survives: a second prompt runs normally
send(agent, 'second')
await waitForIdle(ctx, agent)
expect(adapter.requests.length).toBeGreaterThanOrEqual(1)
await idle
expect(errors.map(e => e.message)).toEqual(['prompt hook broke'])
// The failed prompt forms one balanced error turn; the adjacent prompt forms
// the following normal turn without an intermediate idle transition.
const log = events(agent)
expect(log.filter(e => e.type === 'turn/start')).toHaveLength(2)
expect(log.filter(e => e.type === 'turn/end')).toHaveLength(2)
expect(reasons).toEqual([
{ kind: 'error', step: 0, message: 'prompt hook broke' },
{ kind: 'completed' },
])
expect(statuses).toEqual(['running', 'idle'])
expect(adapter.requests).toHaveLength(1)
expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('second')
})
})
@@ -556,7 +565,6 @@ describe('tool additionalContexts buffering across a step', () => {
additionalContexts: [{
content: [{ type: 'text', text: `ctx-${exec.callId}` }],
source: { kind: 'plugin', plugin: 'p' },
envelope: 'raw',
meta: { callId: exec.callId },
}],
}))
@@ -580,7 +588,6 @@ describe('tool additionalContexts buffering across a step', () => {
.map(b => (b.type === 'text' ? b.text : ''))
expect(ctxTexts).toEqual(['ctx-c1', 'ctx-c2'])
const contextEvents = events(agent).filter(e => e.type === 'context/message')
expect(contextEvents.map(e => e.type === 'context/message' && e.data.envelope)).toEqual(['raw', 'raw'])
expect(contextEvents.map(e => e.type === 'context/message' && e.data.meta)).toEqual([{ callId: 'c1' }, { callId: 'c2' }])
})
@@ -591,7 +598,7 @@ describe('tool additionalContexts buffering across a step', () => {
name: 'composite', description: 'composite', parameters: {},
async execute(_args, exec) {
exec.deferContext({ content: [{ type: 'text', text: 'nested-a' }], source: { kind: 'plugin', plugin: 'a' }, meta: { order: 1 } })
exec.deferContext({ content: [{ type: 'text', text: 'nested-b' }], source: { kind: 'plugin', plugin: 'b' }, envelope: 'raw', meta: { order: 2 } })
exec.deferContext({ content: [{ type: 'text', text: 'nested-b' }], source: { kind: 'plugin', plugin: 'b' }, meta: { order: 2 } })
return [{ type: 'text', text: 'outer result' }]
},
}))

204
packages/core/agent-loop/tests/loop.spec.ts
View File

@@ -354,14 +354,24 @@ describe('agent loop', () => {
expect(flat).toContain('change of plans')
})
it('steering while idle behaves like send (starts a turn)', async () => {
const adapter = new MockAdapter([textResponse('ok')])
it('same-tick idle steering inherits one-send-one-turn FIFO behavior', async () => {
const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agent.steer([{ type: 'text', text: 'hello' }])
await waitForIdle(ctx, agent)
expect(agent.session.events.some(e => e.type === 'user/message')).toBe(true)
const idle = waitForIdle(ctx, agent)
agent.steer([{ type: 'text', text: 'first idle steer' }])
agent.steer([{ type: 'text', text: 'second idle steer' }])
await idle
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
expect(agent.session.events
.filter(event => event.type === 'user/message')
.map(event => event.data.content)).toEqual([
[{ type: 'text', text: 'first idle steer' }],
[{ type: 'text', text: 'second idle steer' }],
])
expect(adapter.requests).toHaveLength(2)
})
it('inject() while idle wraps context in a one-shot turn, visible to the next request', async () => {
@@ -385,10 +395,10 @@ describe('agent loop', () => {
await waitForIdle(ctx, agent)
const flat = JSON.stringify(adapter.requests[0]!.messages)
expect(flat).toContain('file changed: a.ts')
expect(flat).toContain('<context source=\\"plugin\\">')
expect(flat).not.toContain('<context source=')
})
it('inject() can persist raw structured context without the generic context envelope', async () => {
it('inject() persists structured context content verbatim with durable hidden meta', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('raw-context'), { provider: 'mock', model: 'mock' })
@@ -401,14 +411,13 @@ describe('agent loop', () => {
agent.inject([{ type: 'text', text }], {
source: { kind: 'plugin', plugin: 'workspace-context' },
envelope: 'raw',
meta,
})
send(agent, 'go')
await waitForIdle(ctx, agent)
const contextEvent = agent.session.events.find(event => event.type === 'context/message')
expect(contextEvent?.type === 'context/message' && contextEvent.data).toMatchObject({ envelope: 'raw', meta })
expect(contextEvent?.type === 'context/message' && contextEvent.data).toMatchObject({ meta })
const requestText = JSON.stringify(adapter.requests[0]!.messages)
expect(requestText).toContain('Additional instructions from: pkg/AGENTS.md')
expect(requestText).not.toContain('<context source=')
@@ -432,7 +441,6 @@ describe('agent loop', () => {
const first = { type: 'text' as const, text: 'mid-turn notice' }
agent.inject([first], {
source: { kind: 'plugin', plugin: 'x' },
envelope: 'raw',
meta,
})
first.text = 'mutated after inject'
@@ -458,7 +466,6 @@ describe('agent loop', () => {
expect(contexts).toHaveLength(2)
expect(result.seq).toBeLessThan(contexts[0]!.seq)
expect(contexts[0]?.type === 'context/message' && contexts[0].data).toMatchObject({
envelope: 'raw',
meta,
})
expect(contexts.flatMap(event => event.type === 'context/message' ? event.data.content : []))
@@ -925,7 +932,149 @@ describe('agent loop', () => {
expect(turnEnd?.type === 'turn/end' && turnEnd.data.reason.kind).toBe('completed')
})
it('chains queued messages into consecutive turns', async () => {
it('keeps same-tick sends in separate turns and checkpoints before the next starts', async () => {
const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const firstFlush = Promise.withResolvers<undefined>()
const releaseFirstFlush = Promise.withResolvers<undefined>()
let flushes = 0
ctx.on('session/flush', async (session) => {
if (session !== agent.session) return
flushes += 1
if (flushes === 1) {
firstFlush.resolve(undefined)
await releaseFirstFlush.promise
}
})
const turns: number[] = []
ctx.on('session/event', (session, event) => {
if (session === agent.session && event.type === 'turn/start') turns.push(event.data.turn)
})
const idle = waitForIdle(ctx, agent)
send(agent, 'first message')
send(agent, 'second message')
await firstFlush.promise
expect(turns).toEqual([1])
expect(adapter.requests).toHaveLength(1)
releaseFirstFlush.resolve(undefined)
await idle
expect(turns).toEqual([1, 2])
expect(flushes).toBe(2)
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first answer')
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('second message')
})
it('holds a turn-end listener send behind the closing turn checkpoint', async () => {
const adapter = new MockAdapter([textResponse('first answer'), textResponse('second answer')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const firstFlush = Promise.withResolvers<undefined>()
const releaseFirstFlush = Promise.withResolvers<undefined>()
let flushes = 0
ctx.on('session/flush', async (session) => {
if (session !== agent.session) return
flushes += 1
if (flushes === 1) {
firstFlush.resolve(undefined)
await releaseFirstFlush.promise
}
})
const turns: number[] = []
const statuses: string[] = []
ctx.on('agent/status', (subject, status) => {
if (subject === agent) statuses.push(status)
})
ctx.on('session/event', (session, event) => {
if (session !== agent.session) return
if (event.type === 'turn/start') turns.push(event.data.turn)
if (event.type === 'turn/end' && event.data.turn === 1) send(agent, 'turn-end listener message')
})
const idle = waitForIdle(ctx, agent)
send(agent, 'first message')
await firstFlush.promise
expect(turns).toEqual([1])
expect(adapter.requests).toHaveLength(1)
releaseFirstFlush.resolve(undefined)
await idle
expect(turns).toEqual([1, 2])
expect(statuses).toEqual(['running', 'idle'])
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first answer')
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('turn-end listener message')
})
it('keeps a reentrant agent/queued send as the next independent turn', async () => {
const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
let nested = false
ctx.on('agent/queued', (subject) => {
if (subject !== agent || nested) return
nested = true
send(agent, 'queued listener message')
})
const idle = waitForIdle(ctx, agent)
send(agent, 'outer message')
await idle
const turns = agent.session.events.filter(event => event.type === 'turn/start')
const messages = agent.session.events
.filter(event => event.type === 'user/message')
.map(event => event.data.content)
expect(turns).toHaveLength(2)
expect(messages).toEqual([
[{ type: 'text', text: 'outer message' }],
[{ type: 'text', text: 'queued listener message' }],
])
})
it('preserves independent turn sources across an adjacent microtask send', async () => {
const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
const idle = waitForIdle(ctx, agent)
agent.send([{ type: 'text', text: 'user message' }])
await Promise.resolve()
agent.send(
[{ type: 'text', text: 'plugin message' }],
{ source: { kind: 'plugin', plugin: 'test' } },
)
await idle
const triggers = agent.session.events
.filter(event => event.type === 'turn/start')
.map(event => event.data.trigger)
const sources = agent.session.events
.filter(event => event.type === 'user/message')
.map(event => event.data.source)
expect(triggers).toEqual([
{ kind: 'message', source: { kind: 'user' } },
{ kind: 'message', source: { kind: 'plugin', plugin: 'test' } },
])
expect(sources).toEqual([
{ kind: 'user' },
{ kind: 'plugin', plugin: 'test' },
])
})
it('keeps a session-listener send after dequeue in the following turn', async () => {
const adapter = new MockAdapter([textResponse('first'), textResponse('second')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
@@ -948,6 +1097,37 @@ describe('agent loop', () => {
expect(turns).toEqual([1, 2])
expect(adapter.requests).toHaveLength(2)
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('first')
expect(JSON.stringify(adapter.requests[1]!.messages)).toContain('second message')
})
it('keeps a model-adapter callback send in the following turn', async () => {
const agentRef: { current?: Agent } = {}
const adapter = new MockAdapter([
() => {
const agent = agentRef.current
if (agent === undefined) throw new Error('model callback ran before agent setup')
send(agent, 'model callback message')
return textResponse('first')
},
textResponse('second'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('a1'), { provider: 'mock', model: 'mock' })
agentRef.current = agent
const idle = waitForIdle(ctx, agent)
send(agent, 'outer message')
await idle
const messages = agent.session.events
.filter(event => event.type === 'user/message')
.map(event => event.data.content)
expect(agent.session.events.filter(event => event.type === 'turn/start')).toHaveLength(2)
expect(messages).toEqual([
[{ type: 'text', text: 'outer message' }],
[{ type: 'text', text: 'model callback message' }],
])
})
it('awaits session/flush at turn end (persistence checkpoint)', async () => {

41
packages/core/agent-loop/tests/properties.spec.ts
View File

@@ -81,6 +81,21 @@ function turnNumbers(agent: Agent): number[] {
.map(e => (e.data as { turn: number }).turn)
}
function turnEndNumbers(agent: Agent): number[] {
return agent.session.events
.filter(e => e.type === 'turn/end')
.map(e => (e.data as { turn: number }).turn)
}
function userMessageCountsByTurn(agent: Agent): number[] {
const counts: number[] = []
for (const event of agent.session.events) {
if (event.type === 'turn/start') counts.push(0)
if (event.type === 'user/message') counts[counts.length - 1]! += 1
}
return counts
}
/** Assert a status trace is a legal run: idle/running alternating, ending idle. */
function assertLegalStatusTrace(trace: string[]): void {
for (let i = 1; i < trace.length; i++) {
@@ -90,7 +105,7 @@ function assertLegalStatusTrace(trace: string[]): void {
}
describe('agent loop scheduling properties', () => {
it('a synchronous burst loses no message and uses strictly increasing turns', async () => {
it('a synchronous burst gives every message its own strictly increasing turn', async () => {
await fc.assert(fc.asyncProperty(
fc.array(fc.string({ minLength: 1 }), { minLength: 1, maxLength: 6 }),
async (texts) => {
@@ -105,8 +120,11 @@ describe('agent loop scheduling properties', () => {
// No message lost: every send appears as a user/message, in order.
expect(userMessageTexts(agent)).toEqual(texts)
// A synchronous burst batches into exactly one turn.
expect(turnNumbers(agent)).toEqual([1])
// This failure-free fixture maps every item to an independent turn.
expect(turnNumbers(agent)).toEqual(texts.map((_, i) => i + 1))
expect(turnEndNumbers(agent)).toEqual(texts.map((_, i) => i + 1))
expect(userMessageCountsByTurn(agent)).toEqual(texts.map(() => 1))
expect(trace).toEqual(['running', 'idle'])
assertLegalStatusTrace(trace)
} finally {
await ctx.fiber.dispose()
@@ -137,9 +155,9 @@ describe('agent loop scheduling properties', () => {
), { numRuns: 20, timeout: 2000 })
})
it('mixed schedule (send, optionally settle) loses no message and orders turns', async () => {
// Each step is a (text, settle?) pair: settle=true awaits idle before the
// next send (own turn); settle=false sends in the same tick (batches).
it('mixed settled and same-tick sends preserve one turn per message', async () => {
// Each step optionally waits for idle before the next send; that scheduling
// choice must not change the ordinary message-to-turn mapping.
const stepArb = fc.record({ text: fc.string({ minLength: 1 }), settle: fc.boolean() })
await fc.assert(fc.asyncProperty(
fc.array(stepArb, { minLength: 1, maxLength: 6 }),
@@ -158,14 +176,13 @@ describe('agent loop scheduling properties', () => {
}
await lastIdle
// No message lost or reordered, regardless of batching.
// No message is lost or reordered, regardless of driver timing.
expect(userMessageTexts(agent)).toEqual(steps.map(s => s.text))
// Turn numbers are a strictly increasing 1..N prefix (N = turn count).
// Every item forms one FIFO-ordered turn containing only that message.
const turns = turnNumbers(agent)
expect(turns).toEqual(turns.map((_, i) => i + 1))
// Every message landed in some turn; turns never exceed messages.
expect(turns.length).toBeLessThanOrEqual(steps.length)
expect(turns.length).toBeGreaterThanOrEqual(1)
expect(turns).toEqual(steps.map((_, i) => i + 1))
expect(turnEndNumbers(agent)).toEqual(turns)
expect(userMessageCountsByTurn(agent)).toEqual(steps.map(() => 1))
} finally {
await ctx.fiber.dispose()
}

7
packages/core/agent-loop/tests/resume.spec.ts
View File

@@ -411,7 +411,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
await ctx.fiber.dispose()
})
it('resume of a forked session preserves the parentSession lineage and seed boundary in the header', async () => {
it('resume of a forked session preserves the lineage, seed boundary, and delegation depth in the header', async () => {
// Lifecycle 1: persist a FORKED session (carries parentSession + seedLength
// in its header) by creating it with a complete-turn seed — the write path
// materializes the fork (header + seed) on disk.
@@ -423,7 +423,7 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
const { ctx: ctx1, root } = await persistentHarness(adapter1)
const forked = ctx1.sessions.create(SessionId('forked-sess'), {
seed,
meta: { cwd: '/w', parentSession: SessionId('parent-sess'), seedLength: seed.length },
meta: { cwd: '/w', parentSession: SessionId('parent-sess'), seedLength: seed.length, delegationDepth: 1 },
})
await ctx1.parallel('session/flush', forked)
await ctx1.fiber.dispose()
@@ -447,6 +447,9 @@ describe('the session-persistence Agent Note: AgentLoop factory create/resume',
expect(a2.session.header.parentSession).toBe('parent-sess')
expect(a2.session.header.cwd).toBe('/w')
expect(a2.session.header.seedLength).toBe(seed.length)
// The recursion budget survives resume — a dropped depth would let a
// resumed child delegate as if it were top-level.
expect(a2.session.header.delegationDepth).toBe(1)
await ctx2.fiber.dispose()
})