Files
gitmost/apps/server/test/integration/ai-chat-message-status.int-spec.ts
claude code agent 227 ae6faf3abc fix(ai-chat): guard step-update vs finalize race with WHERE status='streaming' (#183 review)
Review caught a real race: onStepFinish fires `updateStreaming()` fire-and-
forget (not awaited), so the FINAL step's streaming UPDATE and the terminal
`finalizeAssistant` UPDATE run as two concurrent statements on different pool
connections — commit order is not guaranteed. If the late streaming update
lands AFTER finalize, the completed row is clobbered back to status='streaming'
with no usage/finishReason, and the next startup sweep then mis-marks the
finished turn 'aborted'. Green unit/integration tests don't reproduce a
cross-connection race.

Fix: scope the per-step update with `onlyIfStreaming` → SQL `WHERE
status='streaming'`. Once finalize has set a terminal status the late update
matches zero rows and no-ops, regardless of commit order; finalize runs
unguarded so it always wins. A cheap `if (finalized) return` short-circuit
avoids most wasted queries, but the SQL guard is the authoritative fix (the
flag can be set after a query is already in flight).

Integration test: finalize to 'completed', then a late onlyIfStreaming update
is a no-op — status/content/usage preserved.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-25 06:14:02 +03:00

185 lines
6.2 KiB
TypeScript

import { Kysely } from 'kysely';
import { AiChatMessageRepo } from '@docmost/db/repos/ai-chat/ai-chat-message.repo';
import {
getTestDb,
destroyTestDb,
createWorkspace,
createUser,
createChat,
createMessage,
} from './db';
/**
* Integration coverage for the #183 step-granular durability primitives on
* AiChatMessageRepo: `update` (in-place patch by id+workspace, bumps updatedAt,
* returns the row) and `sweepStreaming` (crash recovery: flip dangling
* 'streaming' rows to 'aborted'). Real SQL against docmost_test, not a mock.
*/
describe('AiChatMessageRepo.update + sweepStreaming [integration]', () => {
let db: Kysely<any>;
let repo: AiChatMessageRepo;
let workspaceId: string;
let otherWorkspaceId: string;
let userId: string;
let chatId: string;
let otherChatId: string;
beforeAll(async () => {
db = getTestDb();
repo = new AiChatMessageRepo(db as any);
workspaceId = (await createWorkspace(db)).id;
otherWorkspaceId = (await createWorkspace(db)).id;
userId = (await createUser(db, workspaceId)).id;
chatId = (await createChat(db, { workspaceId, creatorId: userId })).id;
const otherUser = await createUser(db, otherWorkspaceId);
otherChatId = (
await createChat(db, {
workspaceId: otherWorkspaceId,
creatorId: otherUser.id,
})
).id;
});
afterAll(async () => {
await destroyTestDb();
});
it('update patches content/status/metadata and bumps updatedAt', async () => {
const seeded = await repo.insert({
chatId,
workspaceId,
userId,
role: 'assistant',
content: '',
status: 'streaming',
metadata: { parts: [] } as never,
});
const before = seeded.updatedAt;
// Ensure a measurable timestamp delta.
await new Promise((r) => setTimeout(r, 5));
const updated = await repo.update(seeded.id, workspaceId, {
content: 'final answer',
status: 'completed',
metadata: { parts: [{ type: 'text', text: 'final answer' }] },
});
expect(updated).toBeDefined();
expect(updated!.content).toBe('final answer');
expect(updated!.status).toBe('completed');
expect((updated!.metadata as any).parts).toHaveLength(1);
expect(new Date(updated!.updatedAt).getTime()).toBeGreaterThanOrEqual(
new Date(before).getTime(),
);
});
it('onlyIfStreaming update is a NO-OP once the row is finalized (race guard)', async () => {
// Reproduce the step-update-vs-finalize race (#183 review): the row is
// finalized to 'completed', then a LATE per-step 'streaming' update lands.
// With `onlyIfStreaming` it must match nothing and leave the finalized row
// untouched (no clobber back to 'streaming', no lost usage).
const seeded = await repo.insert({
chatId,
workspaceId,
userId,
role: 'assistant',
content: 'partial',
status: 'streaming',
});
// Terminal finalize (unguarded) wins.
await repo.update(seeded.id, workspaceId, {
content: 'final answer',
status: 'completed',
metadata: { usage: { totalTokens: 42 } } as never,
});
// A straggler per-step update arrives AFTER finalize.
const late = await repo.update(
seeded.id,
workspaceId,
{ content: 'partial', status: 'streaming', metadata: {} as never },
{ onlyIfStreaming: true },
);
expect(late).toBeUndefined(); // matched no 'streaming' row -> no-op
const rows = await repo.findAllByChat(chatId, workspaceId);
const row = rows.find((r) => r.id === seeded.id)!;
expect(row.status).toBe('completed'); // NOT clobbered back to streaming
expect(row.content).toBe('final answer');
expect((row.metadata as any).usage.totalTokens).toBe(42); // usage preserved
});
it('update is workspace-scoped: a foreign workspace id matches nothing', async () => {
const seeded = await repo.insert({
chatId,
workspaceId,
userId,
role: 'assistant',
content: 'orig',
status: 'streaming',
});
const res = await repo.update(seeded.id, otherWorkspaceId, {
status: 'completed',
});
expect(res).toBeUndefined();
// The row in the real workspace is untouched.
const rows = await repo.findAllByChat(chatId, workspaceId);
const stillThere = rows.find((r) => r.id === seeded.id);
expect(stillThere!.status).toBe('streaming');
// Clean up so it does not pollute the sweep test below.
await repo.update(seeded.id, workspaceId, { status: 'completed' });
});
it('sweepStreaming flips dangling streaming rows to aborted and counts them', async () => {
// Two dangling streaming rows in our workspace + one in another workspace.
const a = await createMessage(db, {
workspaceId,
chatId,
role: 'assistant',
status: 'streaming',
});
const b = await createMessage(db, {
workspaceId,
chatId,
role: 'assistant',
status: 'streaming',
});
// A settled row must NOT be touched.
const done = await createMessage(db, {
workspaceId,
chatId,
role: 'assistant',
status: 'completed',
});
// A legacy NULL-status row must NOT be touched.
const legacy = await createMessage(db, {
workspaceId,
chatId,
role: 'assistant',
status: null,
});
await createMessage(db, {
workspaceId: otherWorkspaceId,
chatId: otherChatId,
role: 'assistant',
status: 'streaming',
});
const swept = await repo.sweepStreaming();
// At least the 3 streaming rows we created (2 here + 1 in the other ws).
expect(swept).toBeGreaterThanOrEqual(3);
const rows = await repo.findAllByChat(chatId, workspaceId);
const byId = new Map(rows.map((r) => [r.id, r]));
expect(byId.get(a.id)!.status).toBe('aborted');
expect(byId.get(b.id)!.status).toBe('aborted');
expect(byId.get(done.id)!.status).toBe('completed');
expect(byId.get(legacy.id)!.status).toBeNull();
// Idempotent: a second sweep finds nothing left in our seeded set.
const again = await repo.sweepStreaming();
const rows2 = await repo.findAllByChat(chatId, workspaceId);
// Our two rows stay aborted regardless of `again`'s global count.
expect(rows2.find((r) => r.id === a.id)!.status).toBe('aborted');
expect(again).toBeGreaterThanOrEqual(0);
});
});