fix(session): contain post-commit observers

This commit is contained in:
Tianyi Cui
2026-07-12 18:57:42 +08:00
parent 50873b8bd0
commit e8fed4fb66
31 changed files with 1166 additions and 475 deletions

View File

@@ -160,7 +160,7 @@ describe('acp bridge — disposal & HMR safety', () => {
// The teardown-ORDER guarantee: a per-agent dispose must stop the loop,
// AWAIT its exit (so the loop's final `turn/end` + `session/flush` fire
// through the still-attached store observer → `session/event`), and only
// THEN detach that observer + remove the session. If the order were inverted
// THEN remove its publication hooks and session entry. If the order were inverted
// (detach first), the closing events would never reach persistence. Drive a
// CLEAN turn to completion, dispose JUST the bridge, then re-load the
// persisted log from disk and assert the closing turn/end is on disk — the
@@ -190,7 +190,7 @@ describe('acp bridge — disposal & HMR safety', () => {
// produced BY the dispose itself. Here the model stream HANGS, so the turn is
// still open when teardown runs: the composite agent effect stops the loop,
// the loop unwinds and appends `turn/end {disposed}` + runs its final
// `session/flush` — all while the store-owned append observer is still attached (the session
// `session/flush` — all while the store-owned publication hooks are still attached (the session
// detach is the LAST disposer in the same effect's LIFO chain) — and only
// THEN is the session detached. If the order were inverted (or the session
// were a racing SIBLING effect), the abort-produced `turn/end` would never
@@ -255,7 +255,7 @@ describe('acp bridge — disposal & HMR safety', () => {
// into ONE composite effect whose disposers run as a `.then()` chain. The
// register disposer emits `agent/disposed`; if a listener throws and the
// emit is UNCONTAINED, the rejected chain skips the LATER session-detach
// disposer — stranding the session in the store with its append observer attached (a
// disposer — stranding the session in the store with its publication hooks attached (a
// leak AND a durability hole, since the new design relies on detach
// running). The emit must be contained. Register a throwing listener, drive
// a clean turn, dispose, and assert the session was STILL removed.

View File

@@ -3,7 +3,7 @@ import { mkdtemp, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { defineTool } from '@deepseek-ai/dsh-tools'
import { AgentId } from '@deepseek-ai/dsh-agent'
import { AgentId, agentEvents } from '@deepseek-ai/dsh-agent'
import { PROTOCOL_VERSION } from '@agentclientprotocol/sdk'
import {
errorResponse,
@@ -235,12 +235,9 @@ describe('acp bridge — turn outcomes', () => {
expect(failed).toHaveLength(1)
})
it('settles via the log fallback when a prior session/event listener throws (starvation)', async () => {
// A peer session/event listener that runs BEFORE the bridge's listener
// throws on turn/end (prepend: true puts it first). cordis emit stops at the
// throw, so the bridge's session/event listener never sees turn/end and
// cannot settle there. The agent/status idle-fallback must reconcile the
// prompt from the log so the RPC settles instead of hanging.
it('settles successfully when an earlier turn/end observer throws', async () => {
// Session contains each post-commit observer failure, so a prepended peer
// cannot starve the bridge's live turn/end delivery.
harness = await makeBridgeHarness({ storageDir, script: [textResponse('answer')] })
harness.ctx.on('session/event', (_s, event) => {
if (event.type === 'turn/end') throw new Error('peer listener boom')
@@ -250,9 +247,7 @@ describe('acp bridge — turn outcomes', () => {
expect(res.stopReason).toBe('end_turn')
})
it('log fallback REJECTS when the starved turn ended in error', async () => {
// Same starvation as above, but the turn fails: the idle-fallback must
// reject the RPC from the logged turn/end{error}, not resolve.
it('still rejects a failed turn when an earlier turn/end observer throws', async () => {
harness = await makeBridgeHarness({ storageDir, script: [errorResponse('starved boom')] })
harness.ctx.on('session/event', (_s, event) => {
if (event.type === 'turn/end') throw new Error('peer listener boom')
@@ -262,21 +257,49 @@ describe('acp bridge — turn outcomes', () => {
.rejects.toThrow(/turn failed: starved boom/)
})
it('log fallback infers the owning turn when turn/START capture is starved', async () => {
// A peer listener throws on turn/START (not turn/end): the bridge never
it('captures and settles the owning turn when an earlier turn-start observer throws', async () => {
// Turn correlation still reaches the bridge after the throwing peer and
// captures inflight.turn via the live stream. A throwing turn/start listener
// also FAILS the turn (the throw is recorded as the turn's error). Without
// the watermark inference the fallback would resolve `cancelled` (the bug);
// with it, it infers the owning turn from the log and REJECTS from that
// turn's error turn/end. (The model's own error is never reached — the turn
// failed at start — so the rejection carries the listener's failure.)
harness = await makeBridgeHarness({ storageDir, script: [textResponse('never runs')] })
// Session contains post-commit callbacks independently.
// The model request and normal turn outcome therefore still occur.
harness = await makeBridgeHarness({ storageDir, script: [textResponse('answer')] })
harness.ctx.on('session/event', (_s, event) => {
if (event.type === 'turn/start') throw new Error('peer listener boom on start')
}, { prepend: true })
const sessionId = await newSession(harness)
await expect(harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] }))
.rejects.toThrow(/turn failed:/)
const result = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
expect(result.stopReason).toBe('end_turn')
})
it('status reconciliation infers the owning message turn when teardown wins after turn/start', async () => {
harness = await makeBridgeHarness({ storageDir, script: [textResponse('background completion')] })
const sessionId = await newSession(harness)
const agent = harness.ctx.agents.get(AgentId(sessionId))!
harness.ctx.on('session/event', (session, event) => {
if (session !== agent.session || event.type !== 'turn/start') return
// Inject the signal ordering the defensive fallback handles: disposal
// status after turn/start commits but before ACP's later live observer.
// This is event-level simulation; it does not mutate the test agent.
agentEvents(harness!.ctx, agent).emit('agent/status', 'disposed')
}, { prepend: true })
const result = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
expect(result.stopReason).toBe('cancelled')
})
it('status reconciliation can settle from a committed turn/end before live delivery', async () => {
harness = await makeBridgeHarness({ storageDir, script: [textResponse('answer')] })
const sessionId = await newSession(harness)
const agent = harness.ctx.agents.get(AgentId(sessionId))!
harness.ctx.on('session/event', (session, event) => {
if (session !== agent.session || event.type !== 'turn/end') return
// Inject a reentrant status signal after the boundary commits to exercise
// the defensive log path before ACP's captured callback runs.
agentEvents(harness!.ctx, agent).emit('agent/status', 'idle')
}, { prepend: true })
const result = await harness.client.prompt({ sessionId, prompt: [{ type: 'text', text: 'go' }] })
expect(result.stopReason).toBe('end_turn')
})
it('a between-turn injection does not settle the prompt early (message-trigger correlation)', async () => {