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

feat(agent-loop): give each send its own turn

Browse Source
This commit is contained in:
pku-xht
2026-07-17 17:14:52 +08:00
parent 97c5ca940d
commit aa4e629874
26 changed files with 372 additions and 209 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
packages/core/agent-loop/tests/cancel.spec.ts
View File

@@ -75,7 +75,8 @@ 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.
@@ -106,7 +107,7 @@ 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() 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(AgentId('a1'), { model: 'mock' })
@@ -117,10 +118,14 @@ 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

@@ -276,15 +276,20 @@ 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(AgentId('a1'), { 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')
}
})
@@ -292,18 +297,25 @@ 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)
@@ -319,11 +331,19 @@ 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 agent.done
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

@@ -141,12 +141,22 @@ 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', () => {

38
packages/core/agent-loop/tests/interception.spec.ts
View File

@@ -182,9 +182,7 @@ 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(AgentId('a1'), { model: 'mock' })
@@ -197,13 +195,13 @@ 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' }])
@@ -215,12 +213,14 @@ 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(AgentId('a1'), { model: 'mock' })
@@ -233,18 +233,18 @@ describe('agent/prompt-submit', () => {
const errors: Error[] = []
ctx.on('agent/error', (_a, _t, _s, error) => void errors.push(error))
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 owns one balanced error turn; the adjacent prompt owns
// 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(adapter.requests).toHaveLength(1)
expect(JSON.stringify(adapter.requests[0]!.messages)).toContain('second')
})
})

130
packages/core/agent-loop/tests/loop.spec.ts
View File

@@ -827,7 +827,104 @@ 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(AgentId('a1'), { 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('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(AgentId('a1'), { 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(AgentId('a1'), { 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(AgentId('a1'), { model: 'mock' })
@@ -850,6 +947,37 @@ 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?: ReactLoopAgent } = {}
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(AgentId('a1'), { 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

@@ -75,6 +75,21 @@ function turnNumbers(agent: ReactLoopAgent): number[] {
.map(e => (e.data as { turn: number }).turn)
}
function turnEndNumbers(agent: ReactLoopAgent): number[] {
return agent.session.events
.filter(e => e.type === 'turn/end')
.map(e => (e.data as { turn: number }).turn)
}
function userMessageCountsByTurn(agent: ReactLoopAgent): 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++) {
@@ -84,7 +99,7 @@ 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) => {
@@ -99,8 +114,11 @@ 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])
// Every successful send owns an independent turn even before the driver wakes.
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()
@@ -131,9 +149,9 @@ 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 }),
@@ -152,14 +170,13 @@ 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 send owns exactly one turn, numbered in FIFO order.
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()
}