feat(ai-chat): durable detached agent runs (#184 phase 1)
Make an agent turn a first-class, server-side RUN that keeps executing and persisting its steps after the browser window closes, and that a later client can reconnect to — the core invariant of #184. Phase 1 only; the full proposal (cross-process BullMQ runner, resumable live-tail transport, autonomy triggers, budgets, history compaction) is explicitly deferred. What lands: - `ai_chat_runs` lifecycle table + repo: the run as a persistent object (status pending->running->succeeded|failed|aborted, trigger, createdBy, assistantMessageId projection link, error, step_count, timings). A partial unique index enforces ONE ACTIVE run per chat; a startup sweep recovers dangling runs (mirrors #183's sweepStreaming). - AiChatRunService: owns the run lifecycle + an in-memory abort registry. The abort is governed by the RUN (an explicit user stop), NOT the HTTP socket — so a browser disconnect no longer ends the turn. Reuses #183's socket- independent durable write path (consumeStream + flushAssistant) unchanged. - Controller, behind `settings.ai.autonomousRuns`: /stream wraps the turn in a run and does NOT abort on disconnect (logs only); a clean 409 rejects a concurrent run on the same chat; new POST /ai-chat/stop (explicit stop) and POST /ai-chat/run (reconnect -> latest persisted run + its projection). The runId is surfaced on the streamed start metadata. Flag OFF = byte-for-byte legacy behavior. Tests: AiChatRunService unit spec (lifecycle, disconnect != stop, explicit stop aborts the signal, best-effort sweeps); ai_chat_runs integration spec (one-active-run index, detached persist+reconnect with no subscriber, explicit stop, stale-run sweep). Server tsc + build clean; touched jest green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
committed by
claude_code
parent
106df7c907
commit
95781d80e1
275
apps/server/test/integration/ai-chat-run.int-spec.ts
Normal file
275
apps/server/test/integration/ai-chat-run.int-spec.ts
Normal file
@@ -0,0 +1,275 @@
|
||||
import { Kysely } from 'kysely';
|
||||
import { AiChatRunRepo } from '@docmost/db/repos/ai-chat/ai-chat-run.repo';
|
||||
import { AiChatMessageRepo } from '@docmost/db/repos/ai-chat/ai-chat-message.repo';
|
||||
import { AiChatRunService } from '../../src/core/ai-chat/ai-chat-run.service';
|
||||
import {
|
||||
getTestDb,
|
||||
destroyTestDb,
|
||||
createWorkspace,
|
||||
createUser,
|
||||
createChat,
|
||||
} from './db';
|
||||
|
||||
/**
|
||||
* Integration coverage for the #184 phase-1 durable agent run: real SQL against
|
||||
* docmost_test. Proves the core invariant primitives — a run is a first-class
|
||||
* lifecycle row, at most one is active per chat, a detached run's progress
|
||||
* survives with NO subscriber, an explicit stop settles it as aborted, a
|
||||
* reconnect read returns the persisted state, and a crash sweep recovers
|
||||
* dangling runs.
|
||||
*/
|
||||
describe('AiChatRun durable lifecycle [integration]', () => {
|
||||
let db: Kysely<any>;
|
||||
let runRepo: AiChatRunRepo;
|
||||
let messageRepo: AiChatMessageRepo;
|
||||
let service: AiChatRunService;
|
||||
let workspaceId: string;
|
||||
let otherWorkspaceId: string;
|
||||
let userId: string;
|
||||
let chatId: string;
|
||||
|
||||
beforeAll(async () => {
|
||||
db = getTestDb();
|
||||
runRepo = new AiChatRunRepo(db as any);
|
||||
messageRepo = new AiChatMessageRepo(db as any);
|
||||
service = new AiChatRunService(runRepo);
|
||||
workspaceId = (await createWorkspace(db)).id;
|
||||
otherWorkspaceId = (await createWorkspace(db)).id;
|
||||
userId = (await createUser(db, workspaceId)).id;
|
||||
chatId = (await createChat(db, { workspaceId, creatorId: userId })).id;
|
||||
});
|
||||
|
||||
afterAll(async () => {
|
||||
await destroyTestDb();
|
||||
});
|
||||
|
||||
// Each test that creates an active run settles it (or uses its own chat) so the
|
||||
// partial unique index does not bleed across tests.
|
||||
|
||||
it('insert + findById round-trips a run row, defaulting status/trigger', async () => {
|
||||
const run = await runRepo.insert({
|
||||
chatId,
|
||||
workspaceId,
|
||||
createdBy: userId,
|
||||
});
|
||||
expect(run.status).toBe('pending');
|
||||
expect(run.trigger).toBe('user');
|
||||
expect(run.stepCount).toBe(0);
|
||||
|
||||
const found = await runRepo.findById(run.id, workspaceId);
|
||||
expect(found!.id).toBe(run.id);
|
||||
// Workspace-scoped: a foreign workspace sees nothing.
|
||||
expect(await runRepo.findById(run.id, otherWorkspaceId)).toBeUndefined();
|
||||
|
||||
// settle so it does not occupy the active slot
|
||||
await runRepo.update(run.id, workspaceId, {
|
||||
status: 'succeeded',
|
||||
finishedAt: new Date(),
|
||||
});
|
||||
});
|
||||
|
||||
it('enforces ONE ACTIVE run per chat (partial unique index rejects a second)', async () => {
|
||||
const activeChat = (
|
||||
await createChat(db, { workspaceId, creatorId: userId })
|
||||
).id;
|
||||
const first = await runRepo.insert({
|
||||
chatId: activeChat,
|
||||
workspaceId,
|
||||
createdBy: userId,
|
||||
status: 'running',
|
||||
});
|
||||
// A second pending/running run on the SAME chat must be rejected by the DB.
|
||||
await expect(
|
||||
runRepo.insert({
|
||||
chatId: activeChat,
|
||||
workspaceId,
|
||||
createdBy: userId,
|
||||
status: 'running',
|
||||
}),
|
||||
).rejects.toThrow();
|
||||
|
||||
// findActiveByChat returns exactly the one active run.
|
||||
const active = await runRepo.findActiveByChat(activeChat, workspaceId);
|
||||
expect(active!.id).toBe(first.id);
|
||||
|
||||
// Once it settles, the slot frees and a new run may start.
|
||||
await runRepo.update(first.id, workspaceId, {
|
||||
status: 'succeeded',
|
||||
finishedAt: new Date(),
|
||||
});
|
||||
expect(
|
||||
await runRepo.findActiveByChat(activeChat, workspaceId),
|
||||
).toBeUndefined();
|
||||
const second = await runRepo.insert({
|
||||
chatId: activeChat,
|
||||
workspaceId,
|
||||
createdBy: userId,
|
||||
status: 'running',
|
||||
});
|
||||
expect(second.id).not.toBe(first.id);
|
||||
await runRepo.update(second.id, workspaceId, {
|
||||
status: 'aborted',
|
||||
finishedAt: new Date(),
|
||||
});
|
||||
});
|
||||
|
||||
it('DETACHED run: persists + finalizes succeeded with NO subscriber, reconnect returns state', async () => {
|
||||
// A dedicated chat so the active-run slot is clean.
|
||||
const runChat = (
|
||||
await createChat(db, { workspaceId, creatorId: userId })
|
||||
).id;
|
||||
|
||||
// beginRun = the runner starts the turn (registers an in-memory controller).
|
||||
const handle = await service.beginRun({
|
||||
chatId: runChat,
|
||||
workspaceId,
|
||||
userId,
|
||||
});
|
||||
expect(handle.signal.aborted).toBe(false);
|
||||
expect(service.isLocallyActive(handle.runId)).toBe(true);
|
||||
|
||||
// The assistant projection row (#183) is seeded + linked.
|
||||
const seeded = await messageRepo.insert({
|
||||
chatId: runChat,
|
||||
workspaceId,
|
||||
userId,
|
||||
role: 'assistant',
|
||||
content: '',
|
||||
status: 'streaming',
|
||||
metadata: { parts: [] } as never,
|
||||
});
|
||||
await service.linkAssistantMessage(handle.runId, workspaceId, seeded.id);
|
||||
|
||||
// Progress is persisted as steps finish — NO HTTP socket involved here at all.
|
||||
await service.recordStep(handle.runId, workspaceId, 1);
|
||||
await messageRepo.update(seeded.id, workspaceId, {
|
||||
content: 'partial work',
|
||||
metadata: { parts: [{ type: 'text', text: 'partial work' }] },
|
||||
});
|
||||
|
||||
// The turn completes; finalize the projection then the run.
|
||||
await messageRepo.update(seeded.id, workspaceId, {
|
||||
content: 'final answer',
|
||||
status: 'completed',
|
||||
});
|
||||
await service.finalizeRun(handle.runId, workspaceId, 'completed');
|
||||
|
||||
expect(service.isLocallyActive(handle.runId)).toBe(false);
|
||||
|
||||
// Reconnect: the latest run for the chat + its projected message, from the DB.
|
||||
const run = await service.getLatestForChat(runChat, workspaceId);
|
||||
expect(run!.status).toBe('succeeded');
|
||||
expect(run!.stepCount).toBe(1);
|
||||
expect(run!.assistantMessageId).toBe(seeded.id);
|
||||
expect(run!.finishedAt).toBeTruthy();
|
||||
const message = await messageRepo.findById(seeded.id, workspaceId);
|
||||
expect(message!.status).toBe('completed');
|
||||
expect(message!.content).toBe('final answer');
|
||||
});
|
||||
|
||||
it('EXPLICIT stop aborts the run signal, marks the row, and settles as aborted', async () => {
|
||||
const runChat = (
|
||||
await createChat(db, { workspaceId, creatorId: userId })
|
||||
).id;
|
||||
const handle = await service.beginRun({
|
||||
chatId: runChat,
|
||||
workspaceId,
|
||||
userId,
|
||||
});
|
||||
|
||||
// User presses Stop.
|
||||
const stopped = await service.requestStop(handle.runId, workspaceId);
|
||||
expect(stopped).toBe(true);
|
||||
expect(handle.signal.aborted).toBe(true);
|
||||
|
||||
// The row carries the stop request (distinct from a disconnect, which would
|
||||
// leave stop_requested_at NULL).
|
||||
const afterStop = await runRepo.findById(handle.runId, workspaceId);
|
||||
expect(afterStop!.stopRequestedAt).toBeTruthy();
|
||||
|
||||
// The terminal callback (onAbort) settles the run.
|
||||
await service.finalizeRun(handle.runId, workspaceId, 'aborted');
|
||||
const run = await service.getLatestForChat(runChat, workspaceId);
|
||||
expect(run!.status).toBe('aborted');
|
||||
});
|
||||
|
||||
it('markStopRequested is a no-op on an already-settled run (returns undefined)', async () => {
|
||||
const runChat = (
|
||||
await createChat(db, { workspaceId, creatorId: userId })
|
||||
).id;
|
||||
const run = await runRepo.insert({
|
||||
chatId: runChat,
|
||||
workspaceId,
|
||||
createdBy: userId,
|
||||
status: 'running',
|
||||
});
|
||||
await runRepo.update(run.id, workspaceId, {
|
||||
status: 'succeeded',
|
||||
finishedAt: new Date(),
|
||||
});
|
||||
const marked = await runRepo.markStopRequested(run.id, workspaceId);
|
||||
expect(marked).toBeUndefined();
|
||||
});
|
||||
|
||||
it('sweepRunning aborts STALE dangling runs but not fresh or settled ones', async () => {
|
||||
const sweepChat1 = (
|
||||
await createChat(db, { workspaceId, creatorId: userId })
|
||||
).id;
|
||||
const sweepChat2 = (
|
||||
await createChat(db, { workspaceId, creatorId: userId })
|
||||
).id;
|
||||
const sweepChat3 = (
|
||||
await createChat(db, { workspaceId, creatorId: userId })
|
||||
).id;
|
||||
|
||||
const stale = await runRepo.insert({
|
||||
chatId: sweepChat1,
|
||||
workspaceId,
|
||||
createdBy: userId,
|
||||
status: 'running',
|
||||
});
|
||||
const fresh = await runRepo.insert({
|
||||
chatId: sweepChat2,
|
||||
workspaceId,
|
||||
createdBy: userId,
|
||||
status: 'running',
|
||||
});
|
||||
const settled = await runRepo.insert({
|
||||
chatId: sweepChat3,
|
||||
workspaceId,
|
||||
createdBy: userId,
|
||||
status: 'running',
|
||||
});
|
||||
await runRepo.update(settled.id, workspaceId, {
|
||||
status: 'succeeded',
|
||||
finishedAt: new Date(),
|
||||
});
|
||||
// Backdate the stale run's updatedAt past the 10-minute staleness window.
|
||||
await db
|
||||
.updateTable('aiChatRuns')
|
||||
.set({ updatedAt: new Date(Date.now() - 20 * 60 * 1000) })
|
||||
.where('id', '=', stale.id)
|
||||
.execute();
|
||||
|
||||
const swept = await runRepo.sweepRunning();
|
||||
expect(swept).toBeGreaterThanOrEqual(1);
|
||||
|
||||
expect((await runRepo.findById(stale.id, workspaceId))!.status).toBe(
|
||||
'aborted',
|
||||
);
|
||||
// Fresh (recently-updated) running run survives — a sibling replica may still
|
||||
// be executing it.
|
||||
expect((await runRepo.findById(fresh.id, workspaceId))!.status).toBe(
|
||||
'running',
|
||||
);
|
||||
expect((await runRepo.findById(settled.id, workspaceId))!.status).toBe(
|
||||
'succeeded',
|
||||
);
|
||||
|
||||
// cleanup active fresh run
|
||||
await runRepo.update(fresh.id, workspaceId, {
|
||||
status: 'aborted',
|
||||
finishedAt: new Date(),
|
||||
});
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user