fix(ai): show live reindex progress in semantic-search settings
The "Indexed X of Y pages" counter stayed stuck at "478 of 478" during a
manual "Reindex now" run instead of resetting to 0 and climbing. The status
reports indexedPages = countIndexedPages (DISTINCT pages with >=1 embedding
row), but reindex hard-replaces each page in its OWN small transaction, so
nearly all pages always have rows -> the count never drops.
Add a per-workspace live reindex-progress record in Redis (reusing the
existing global ioredis client via RedisService, no new Redis config):
- EmbeddingReindexProgressService: start/increment/clear/get over a Redis hash
with a 1h TTL self-clean; all best-effort/cosmetic so a Redis failure degrades
to the existing DB-count behavior.
- AiSettingsService.reindex seeds {total, done:0, startedAt} at enqueue time so
the very first poll already reports done=0.
- EmbeddingIndexerService.reindexWorkspace overwrites total with the real page
count at start, increments done per processed page (success or handled
failure), and clears the record in a finally (covers success, fatal abort,
and the unconfigured early-return) so a failed run never sticks.
- AiSettingsService.getMasked returns the live run numbers when a progress
record is active (plus an optional reindexing flag), else falls back to
countIndexedPages/countEmbeddablePages.
Per-page edits (reindexPage) never touch the workspace progress record, and no
mass up-front delete is introduced (search availability preserved).
Tests: indexer sets/increments/clears progress (incl. fatal abort and
unconfigured early-return); status reports run progress when active and falls
back when not.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -3,6 +3,8 @@ import { PageRepo } from '@docmost/db/repos/page/page.repo';
|
||||
import { PageEmbeddingRepo } from '@docmost/db/repos/ai-chat/page-embedding.repo';
|
||||
import { KyselyDB } from '@docmost/db/types/kysely.types';
|
||||
import { AiService } from '../../../integrations/ai/ai.service';
|
||||
import { EmbeddingReindexProgressService } from '../../../integrations/ai/embedding-reindex-progress.service';
|
||||
import { AiEmbeddingNotConfiguredException } from '../../../integrations/ai/ai-embedding-not-configured.exception';
|
||||
|
||||
/**
|
||||
* Unit tests for EmbeddingIndexerService.reindexWorkspace's batch control flow.
|
||||
@@ -30,15 +32,24 @@ describe('EmbeddingIndexerService.reindexWorkspace fail-fast', () => {
|
||||
const aiService = {
|
||||
getEmbeddingModel: jest.fn().mockResolvedValue('some-model'),
|
||||
};
|
||||
// Progress is a best-effort cosmetic store; mock its async methods so the
|
||||
// batch control flow can be tested without Redis.
|
||||
const reindexProgress = {
|
||||
start: jest.fn().mockResolvedValue(undefined),
|
||||
increment: jest.fn().mockResolvedValue(undefined),
|
||||
clear: jest.fn().mockResolvedValue(undefined),
|
||||
get: jest.fn().mockResolvedValue(null),
|
||||
};
|
||||
const db = {};
|
||||
|
||||
const service = new EmbeddingIndexerService(
|
||||
pageRepo as unknown as PageRepo,
|
||||
pageEmbeddingRepo as unknown as PageEmbeddingRepo,
|
||||
aiService as unknown as AiService,
|
||||
reindexProgress as unknown as EmbeddingReindexProgressService,
|
||||
db as unknown as KyselyDB,
|
||||
);
|
||||
return { service, pageRepo, aiService };
|
||||
return { service, pageRepo, aiService, reindexProgress };
|
||||
}
|
||||
|
||||
it('aborts after the first page on a FATAL (401) provider error', async () => {
|
||||
@@ -78,3 +89,100 @@ describe('EmbeddingIndexerService.reindexWorkspace fail-fast', () => {
|
||||
expect(reindexPage).toHaveBeenCalledTimes(3);
|
||||
});
|
||||
});
|
||||
|
||||
/**
|
||||
* Live reindex-progress reporting: reindexWorkspace must publish a per-workspace
|
||||
* progress record (total at start, done incremented per processed page) and ALWAYS
|
||||
* clear it in a finally — including on a fatal abort and an unconfigured early
|
||||
* return — so the settings status can show the counter climb without ever getting
|
||||
* stuck in a "reindexing" state.
|
||||
*/
|
||||
describe('EmbeddingIndexerService.reindexWorkspace progress', () => {
|
||||
const WORKSPACE_ID = 'ws-1';
|
||||
|
||||
function makeService(pageIds: string[] = ['p1', 'p2', 'p3']) {
|
||||
const pageRepo = {
|
||||
getIdsByWorkspace: jest.fn().mockResolvedValue(pageIds),
|
||||
};
|
||||
const pageEmbeddingRepo = {};
|
||||
const aiService = {
|
||||
getEmbeddingModel: jest.fn().mockResolvedValue('some-model'),
|
||||
};
|
||||
const reindexProgress = {
|
||||
start: jest.fn().mockResolvedValue(undefined),
|
||||
increment: jest.fn().mockResolvedValue(undefined),
|
||||
clear: jest.fn().mockResolvedValue(undefined),
|
||||
get: jest.fn().mockResolvedValue(null),
|
||||
};
|
||||
const db = {};
|
||||
const service = new EmbeddingIndexerService(
|
||||
pageRepo as unknown as PageRepo,
|
||||
pageEmbeddingRepo as unknown as PageEmbeddingRepo,
|
||||
aiService as unknown as AiService,
|
||||
reindexProgress as unknown as EmbeddingReindexProgressService,
|
||||
db as unknown as KyselyDB,
|
||||
);
|
||||
return { service, pageRepo, aiService, reindexProgress };
|
||||
}
|
||||
|
||||
it('sets total at start, increments done per page, and clears in finally', async () => {
|
||||
const { service, reindexProgress } = makeService(['p1', 'p2', 'p3']);
|
||||
jest.spyOn(service, 'reindexPage').mockResolvedValue(undefined);
|
||||
|
||||
await service.reindexWorkspace(WORKSPACE_ID);
|
||||
|
||||
expect(reindexProgress.start).toHaveBeenCalledWith(WORKSPACE_ID, 3);
|
||||
// One increment per processed page.
|
||||
expect(reindexProgress.increment).toHaveBeenCalledTimes(3);
|
||||
expect(reindexProgress.increment).toHaveBeenCalledWith(WORKSPACE_ID);
|
||||
// Cleared exactly once on completion.
|
||||
expect(reindexProgress.clear).toHaveBeenCalledTimes(1);
|
||||
expect(reindexProgress.clear).toHaveBeenCalledWith(WORKSPACE_ID);
|
||||
});
|
||||
|
||||
it('counts a handled (non-fatal) per-page failure as processed', async () => {
|
||||
const { service, reindexProgress } = makeService(['p1', 'p2', 'p3']);
|
||||
// No statusCode -> non-fatal -> isolate and continue; each counts as done.
|
||||
jest.spyOn(service, 'reindexPage').mockRejectedValue(new Error('boom'));
|
||||
|
||||
await service.reindexWorkspace(WORKSPACE_ID);
|
||||
|
||||
expect(reindexProgress.increment).toHaveBeenCalledTimes(3);
|
||||
expect(reindexProgress.clear).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
it('clears progress in finally even when a FATAL provider error aborts the batch', async () => {
|
||||
const { service, reindexProgress } = makeService(['p1', 'p2', 'p3']);
|
||||
// A 401 aborts on the first page (re-thrown) — the finally must still clear.
|
||||
jest
|
||||
.spyOn(service, 'reindexPage')
|
||||
.mockRejectedValue({ statusCode: 401, message: 'User not found' });
|
||||
|
||||
await expect(service.reindexWorkspace(WORKSPACE_ID)).rejects.toMatchObject({
|
||||
statusCode: 401,
|
||||
});
|
||||
|
||||
expect(reindexProgress.start).toHaveBeenCalledWith(WORKSPACE_ID, 3);
|
||||
// Aborted page is NOT counted as processed.
|
||||
expect(reindexProgress.increment).not.toHaveBeenCalled();
|
||||
// But progress is still cleared so the run never gets stuck.
|
||||
expect(reindexProgress.clear).toHaveBeenCalledTimes(1);
|
||||
});
|
||||
|
||||
it('clears the enqueue-seeded progress on an unconfigured early return', async () => {
|
||||
const { service, aiService, reindexProgress } = makeService();
|
||||
// Embeddings not configured: reindexWorkspace returns early WITHOUT starting
|
||||
// a fresh record, but the finally must still clear the enqueue-time seed.
|
||||
aiService.getEmbeddingModel = jest
|
||||
.fn()
|
||||
.mockRejectedValue(new AiEmbeddingNotConfiguredException());
|
||||
|
||||
await expect(
|
||||
service.reindexWorkspace(WORKSPACE_ID),
|
||||
).resolves.toBeUndefined();
|
||||
|
||||
expect(reindexProgress.start).not.toHaveBeenCalled();
|
||||
expect(reindexProgress.clear).toHaveBeenCalledTimes(1);
|
||||
expect(reindexProgress.clear).toHaveBeenCalledWith(WORKSPACE_ID);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -9,6 +9,7 @@ import { KyselyDB } from '@docmost/db/types/kysely.types';
|
||||
import { InjectKysely } from 'nestjs-kysely';
|
||||
import { executeTx } from '@docmost/db/utils';
|
||||
import { AiService } from '../../../integrations/ai/ai.service';
|
||||
import { EmbeddingReindexProgressService } from '../../../integrations/ai/embedding-reindex-progress.service';
|
||||
import { AiEmbeddingNotConfiguredException } from '../../../integrations/ai/ai-embedding-not-configured.exception';
|
||||
import {
|
||||
describeProviderError,
|
||||
@@ -48,6 +49,7 @@ export class EmbeddingIndexerService {
|
||||
private readonly pageRepo: PageRepo,
|
||||
private readonly pageEmbeddingRepo: PageEmbeddingRepo,
|
||||
private readonly aiService: AiService,
|
||||
private readonly reindexProgress: EmbeddingReindexProgressService,
|
||||
@InjectKysely() private readonly db: KyselyDB,
|
||||
) {}
|
||||
|
||||
@@ -194,69 +196,89 @@ export class EmbeddingIndexerService {
|
||||
* the batch.
|
||||
*/
|
||||
async reindexWorkspace(workspaceId: string): Promise<void> {
|
||||
// The whole run is wrapped so the per-workspace progress record is ALWAYS
|
||||
// cleared in the finally — on success, on a fatal-provider abort, on an
|
||||
// unconfigured early-return, or on any unexpected throw — so a failed run
|
||||
// never leaves a stuck "reindexing" state (the status then falls back to the
|
||||
// steady-state DB coverage count). A placeholder record may already exist
|
||||
// (seeded at enqueue time); the finally cleans that too.
|
||||
try {
|
||||
await this.aiService.getEmbeddingModel(workspaceId);
|
||||
} catch (err) {
|
||||
if (err instanceof AiEmbeddingNotConfiguredException) {
|
||||
this.logger.log(
|
||||
`reindexWorkspace: embeddings not configured for workspace ${workspaceId}, skipping`,
|
||||
);
|
||||
return;
|
||||
}
|
||||
throw err;
|
||||
}
|
||||
|
||||
const pageIds = await this.pageRepo.getIdsByWorkspace(workspaceId);
|
||||
const total = pageIds.length;
|
||||
const startedAt = Date.now();
|
||||
this.logger.log(
|
||||
`reindexWorkspace: starting reindex of ${total} page(s) for workspace ${workspaceId}`,
|
||||
);
|
||||
|
||||
let failed = 0;
|
||||
for (let i = 0; i < total; i++) {
|
||||
const pageId = pageIds[i];
|
||||
const position = i + 1;
|
||||
// Log BEFORE the await: if the embedding call hangs, this is the last line
|
||||
// in the log and it names the exact page that is stuck.
|
||||
this.logger.log(
|
||||
`reindexWorkspace: [${position}/${total}] indexing page ${pageId} (workspace ${workspaceId})`,
|
||||
);
|
||||
const pageStartedAt = Date.now();
|
||||
try {
|
||||
await this.reindexPage(pageId);
|
||||
const elapsed = Date.now() - pageStartedAt;
|
||||
if (elapsed >= SLOW_PAGE_MS) {
|
||||
this.logger.warn(
|
||||
`reindexWorkspace: [${position}/${total}] page ${pageId} took ${elapsed}ms`,
|
||||
);
|
||||
}
|
||||
await this.aiService.getEmbeddingModel(workspaceId);
|
||||
} catch (err) {
|
||||
// A fatal provider error (invalid/missing key, no credits) recurs
|
||||
// identically on EVERY remaining page. Abort the whole batch instead of
|
||||
// issuing hundreds of doomed requests against the provider.
|
||||
if (isFatalProviderError(err)) {
|
||||
this.logger.error(
|
||||
`reindexWorkspace: aborting at [${position}/${total}] for workspace ` +
|
||||
`${workspaceId} — fatal provider error, remaining pages would fail ` +
|
||||
`identically: ${describeProviderError(err)}`,
|
||||
if (err instanceof AiEmbeddingNotConfiguredException) {
|
||||
this.logger.log(
|
||||
`reindexWorkspace: embeddings not configured for workspace ${workspaceId}, skipping`,
|
||||
);
|
||||
throw err;
|
||||
return;
|
||||
}
|
||||
// Per-page isolation: one non-fatal failure (incl. an embedding timeout)
|
||||
// must not abort the whole batch.
|
||||
failed++;
|
||||
this.logger.error(
|
||||
`reindexWorkspace: [${position}/${total}] failed to reindex page ${pageId} ` +
|
||||
`after ${Date.now() - pageStartedAt}ms: ${describeProviderError(err)}`,
|
||||
);
|
||||
throw err;
|
||||
}
|
||||
}
|
||||
|
||||
this.logger.log(
|
||||
`reindexWorkspace: done for workspace ${workspaceId}: ` +
|
||||
`${total - failed}/${total} indexed, ${failed} failed in ${Date.now() - startedAt}ms`,
|
||||
);
|
||||
const pageIds = await this.pageRepo.getIdsByWorkspace(workspaceId);
|
||||
const total = pageIds.length;
|
||||
const startedAt = Date.now();
|
||||
// Publish the live run progress (overwrites the enqueue-time placeholder
|
||||
// with the real page count, done back to 0) so the settings status can
|
||||
// report done climbing 0 -> total while this reindex runs.
|
||||
await this.reindexProgress.start(workspaceId, total);
|
||||
this.logger.log(
|
||||
`reindexWorkspace: starting reindex of ${total} page(s) for workspace ${workspaceId}`,
|
||||
);
|
||||
|
||||
let failed = 0;
|
||||
for (let i = 0; i < total; i++) {
|
||||
const pageId = pageIds[i];
|
||||
const position = i + 1;
|
||||
// Log BEFORE the await: if the embedding call hangs, this is the last line
|
||||
// in the log and it names the exact page that is stuck.
|
||||
this.logger.log(
|
||||
`reindexWorkspace: [${position}/${total}] indexing page ${pageId} (workspace ${workspaceId})`,
|
||||
);
|
||||
const pageStartedAt = Date.now();
|
||||
try {
|
||||
await this.reindexPage(pageId);
|
||||
// Count this page as processed (matches the [position/total] log).
|
||||
await this.reindexProgress.increment(workspaceId);
|
||||
const elapsed = Date.now() - pageStartedAt;
|
||||
if (elapsed >= SLOW_PAGE_MS) {
|
||||
this.logger.warn(
|
||||
`reindexWorkspace: [${position}/${total}] page ${pageId} took ${elapsed}ms`,
|
||||
);
|
||||
}
|
||||
} catch (err) {
|
||||
// A fatal provider error (invalid/missing key, no credits) recurs
|
||||
// identically on EVERY remaining page. Abort the whole batch instead of
|
||||
// issuing hundreds of doomed requests against the provider. Do NOT count
|
||||
// it as processed — the run aborts here (the finally clears progress).
|
||||
if (isFatalProviderError(err)) {
|
||||
this.logger.error(
|
||||
`reindexWorkspace: aborting at [${position}/${total}] for workspace ` +
|
||||
`${workspaceId} — fatal provider error, remaining pages would fail ` +
|
||||
`identically: ${describeProviderError(err)}`,
|
||||
);
|
||||
throw err;
|
||||
}
|
||||
// Per-page isolation: one non-fatal failure (incl. an embedding timeout)
|
||||
// must not abort the whole batch. A handled failure still advances the
|
||||
// counter (matches the [position/total] log, so done reaches total).
|
||||
failed++;
|
||||
await this.reindexProgress.increment(workspaceId);
|
||||
this.logger.error(
|
||||
`reindexWorkspace: [${position}/${total}] failed to reindex page ${pageId} ` +
|
||||
`after ${Date.now() - pageStartedAt}ms: ${describeProviderError(err)}`,
|
||||
);
|
||||
}
|
||||
}
|
||||
|
||||
this.logger.log(
|
||||
`reindexWorkspace: done for workspace ${workspaceId}: ` +
|
||||
`${total - failed}/${total} indexed, ${failed} failed in ${Date.now() - startedAt}ms`,
|
||||
);
|
||||
} finally {
|
||||
// Always remove the progress record so the status reverts to the DB count.
|
||||
await this.reindexProgress.clear(workspaceId);
|
||||
}
|
||||
}
|
||||
|
||||
/** Purge ALL embeddings for a workspace (WORKSPACE_DELETE_EMBEDDINGS). */
|
||||
|
||||
Reference in New Issue
Block a user