feat(compact): recover context overflow (PR3 phase 2)

This commit is contained in:
Hypatia May
2026-07-15 16:50:44 +08:00
parent e8d066f750
commit 12484104c8
46 changed files with 913 additions and 242 deletions

View File

@@ -58,7 +58,7 @@ Plugin failure ends the current turn, not the loop. Only final adapter dispatch/
Everything that goes beyond "call the model, run the tools, repeat" belongs to plugins listening on the event taxonomy:
- Hooks and policy: the relevant `agent/*` checkpoints plus the guarded `tools/pre-execute` → `tools/execute` → `tools/post-execute` → `tools/result` pipeline; exact signatures and modes live in the [generated event catalog](../../../docs/cordis-catalog/events.md)
- Compaction: `agent/pre-step`
- Compaction: pressure on `agent/post-step`; canonical context overflow on `agent/request-error`
- Sandbox, permission, plan mode: `tools/pre-execute` for extensible deny/ask, `tools.guard()` for monotonic owner policy, `tools/post-execute` for result decisions, and `tools/result` for final observation
- Sub-agents: implemented outside the loop as `ctx.subagents` providers; in-process providers use `ctx.agents.create()` and owned `AgentHandle` teardown, while child streaming/progress and background/poll collection remain deferred.
- Persistence: `session/event` + `session/flush`

View File

@@ -276,7 +276,7 @@ async function runTurn(
const abort = new AbortController()
handle.setAbort(abort)
// Assemble once before pre-step so pressure checks and the request share the same prompt.
// Assemble once before pre-step so listener work and the request share one prompt value.
const assembly = await ctx.systemPrompt.assemble(assembleContextFor(agent))
const fullSystemPrompt = renderPrompt(assembly)
@@ -287,9 +287,9 @@ async function runTurn(
break
}
// Compose the request-only prefix once per loop instance before pressure
// checks. It precedes all derived history and is recorded only in the
// request header, not as session history.
// 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(
@@ -306,8 +306,8 @@ async function runTurn(
transmission.sessionPrefix = deepFreeze(structuredClone(composed))
}
// Await surface mutations outside the step; pressure checks receive the pending prefix.
await events.serial('agent/pre-step', turn, step, fullSystemPrompt, transmission.sessionPrefix, abort.signal)
// 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()) {

View File

@@ -118,7 +118,7 @@ describe('agent/prompt-submit', () => {
it('a prompt-submit rewrite + additionalContext is VISIBLE to the agent/pre-step seam (merged ordering)', async () => {
// Prompt rewrites and injected context land before `agent/pre-step`, so a
// compaction listener measures the current surface before the single derive.
// surface listener sees the current state before the single derive.
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
@@ -130,8 +130,7 @@ describe('agent/prompt-submit', () => {
additionalContext: { content: [{ type: 'text', text: 'injected ctx' }], source: { kind: 'plugin', plugin: 'test' } },
}))
// The pre-step seam (where compaction lives) derives the surface it would act
// on. Capture what it sees on the first step.
// Capture the surface visible at the generic pre-step seam on the first step.
let preStepDerived: string | undefined
ctx.on('agent/pre-step', (subject, _turn, step) => {
if (subject === agent && step === 1) preStepDerived = JSON.stringify(subject.session.deriveMessages())
@@ -375,7 +374,7 @@ describe('agent/session-prefix', () => {
expect(agent.session.deriveMessages()[0]).toEqual({ role: 'user', content: [{ type: 'text', text: 'go' }] })
})
it('composes before the first pre-step and hands the prefix to the seam (pressure gates see the real value)', async () => {
it('composes before the first pre-step and records the prefix on the request header', async () => {
const adapter = new MockAdapter([textResponse('ok')])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
@@ -386,20 +385,15 @@ describe('agent/session-prefix', () => {
order.push('compose')
return [reminder, ...await next()]
})
const seen: (readonly Message[])[] = []
ctx.on('agent/pre-step', (_agent, _turn, _step, _system, sessionPrefix) => {
ctx.on('agent/pre-step', () => {
order.push('pre-step')
seen.push(sessionPrefix)
})
send(agent, 'hi')
await waitForIdle(ctx, agent)
// Composition precedes the pre-step seam, and the seam receives THIS
// instance's composed prefix — a token-pressure gate (compaction) counts
// what the request will actually carry, never a stale logged prefix.
expect(order).toEqual(['compose', 'pre-step'])
expect(seen[0]).toEqual([reminder])
expect(agent.session.requestHeader()?.messagePrefix).toEqual([reminder])
})
it('the canonical prepend pattern composes contributions in registration order', async () => {

View File

@@ -486,9 +486,8 @@ describe('agent loop', () => {
it('agent/pre-step fires once per step before the step is opened', async () => {
// Two steps (a tool call, then a final text turn) → two model calls → two
// pre-step fires, each carrying the assembled full system prompt, BEFORE
// the step is opened and its request is derived (the request the adapter
// sees reflects any surface state at fire time).
// pre-step fires BEFORE the step is opened and its request is derived (the
// request the adapter sees reflects any surface state at fire time).
const adapter = new MockAdapter([
toolCallResponse('c1', 'echo', {}, 'calling echo'),
textResponse('done'),
@@ -500,21 +499,19 @@ describe('agent loop', () => {
}))
const agent = ctx.agentLoop.create(AgentId('a1'), { model: 'mock' })
const fires: { turn: number; step: number; fullSystemPrompt: string }[] = []
ctx.on('agent/pre-step', (subject, turn, step, fullSystemPrompt) => {
if (subject === agent) fires.push({ turn, step, fullSystemPrompt })
const fires: { turn: number; step: number; signal: AbortSignal }[] = []
ctx.on('agent/pre-step', (subject, turn, step, signal) => {
if (subject === agent) fires.push({ turn, step, signal })
})
send(agent, 'go')
await waitForIdle(ctx, agent)
// One fire per step, in order, each with the assembled system prompt
// (here just the loop's own harness-identity section — no persona set).
const HARNESS = 'You are an AI agent powered by the DeepSeek Harness SDK.'
expect(fires).toEqual([
{ turn: 1, step: 1, fullSystemPrompt: HARNESS },
{ turn: 1, step: 2, fullSystemPrompt: HARNESS },
expect(fires.map(({ turn, step }) => ({ turn, step }))).toEqual([
{ turn: 1, step: 1 },
{ turn: 1, step: 2 },
])
expect(fires.every(({ signal }) => signal instanceof AbortSignal)).toBe(true)
})
it('agent/pre-step fires BEFORE the step it precedes opens (events land outside the step)', async () => {

View File

@@ -219,6 +219,48 @@ describe('agent post-step and request-error lifecycle', () => {
})
})
it('closes the successful step as disposed when disposal lands during post-step', async () => {
const adapter = new FailureScriptAdapter([
toolCallResponse('dispose-call', 'work', {}),
textResponse('must not continue'),
])
const ctx = await harness(adapter)
ctx.tools.register(defineTool({
name: 'work',
description: 'do work',
parameters: {},
async execute() { return [{ type: 'text', text: 'worked' }] },
}))
const agent = ctx.agentLoop.create(AgentId('dispose-post-step'), { model: 'mock' })
let entered!: () => void
const postStepEntered = new Promise<void>((resolve) => { entered = resolve })
ctx.on('agent/post-step', async (_agent, turn, step, signal) => {
expect({ turn, step }).toEqual({ turn: 1, step: 1 })
entered()
await new Promise<void>((resolve) => {
signal.addEventListener('abort', () => { resolve() }, { once: true })
})
})
send(agent)
await postStepEntered
await ctx.fiber.dispose()
expect(adapter.requests).toHaveLength(1)
const boundaries = agent.session.events.filter(event =>
event.type === 'step/start' || event.type === 'step/end',
)
expect(boundaries.map(event => event.type)).toEqual(['step/start', 'step/end'])
expect(boundaries.map(event => event.data)).toEqual([
{ turn: 1, step: 1 },
{ turn: 1, step: 1 },
])
expect(agent.session.events.at(-1)).toMatchObject({
type: 'turn/end',
data: { reason: { kind: 'disposed' } },
})
})
it.each([
['thrown', contextError()],
['in-band', [{ type: 'finish', reason: { kind: 'error', message: 'too large', code: CONTEXT_WINDOW_EXCEEDED_CODE } }] satisfies StreamChunk[]],