feat(queue): adapter queue overhaul — pause/resume, error capture, scheduling

- Pause/resume persisted in queue_state; drain loop checks isPaused() and skips
- Error capture: every failed/backoff attempt logged to queue_errors with the
  full stack trace; admin queue page expands a failed job to stream it
- Retry controls: retryJob(key), retrySource(kind), clearDone(olderThanMs)
- Per-source scheduling: queue_schedules table + 30s enqueueDueSchedules loop
  (seed defaults sec-fetch 24h, yfinance 5min); admin UI lists/adds/deletes
- Startup recovery: interrupted in_flight jobs reset to pending on boot
- fix(edgar): archive URLs use the filer CIK (accession-number prefix), not the
  company CIK — resolves Cloudflare 429 that left SEC backfills sparse/empty
- Migration: add queue_errors, queue_schedules, queue_state tables plus error/
  scheduled_for columns on adapter_queue (idempotent ALTER on startup)

Verified: full sec-fetch backfill now succeeds for all watched symbols
(NVDA 14,675 institution filings, CIFR 274 insider txns, TSLA 6,011, etc.).
503 backend tests pass.

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Investor Flow Build
2026-07-12 12:55:59 -04:00
co-authored by Claude
parent 55f07e6b42
commit ca385c1960
10 changed files with 1345 additions and 141 deletions
+30 -5
View File
@@ -5,17 +5,31 @@ import { fetchRequestHandler } from '@trpc/server/adapters/fetch';
import { db } from './db/client.ts';
import { createCacheRepository, type SourceKind } from './cache/CacheRepository.ts';
import { YFinanceAdapter } from './adapters/YFinanceAdapter.ts';
import { SecFetchAdapter } from './adapters/SecFetchAdapter.ts';
import type { SourceFetch } from './adapters/SourceAdapter.ts';
import { AdapterQueue } from './queue/AdapterQueue.ts';
import { makeCreateContext } from './trpc/context.ts';
import { appRouter } from './trpc/router.ts';
const PORT = Number(process.env.PORT ?? 3001);
const database = db();
const adapters = new Map<SourceKind, YFinanceAdapter>([['yfinance', new YFinanceAdapter()]]);
const adapters: Map<SourceKind, SourceFetch> = new Map([
['yfinance', new YFinanceAdapter()],
['sec-fetch', new SecFetchAdapter(database)],
]);
const queue = new AdapterQueue({ db: database, adapters });
const cache = createCacheRepository({ db: database, scheduler: queue });
queue.cache = cache; // break the cache<->scheduler cycle
const createContext = makeCreateContext({ db: database, cache });
// Seed default schedules (noop if already seeded)
queue.seedDefaultSchedules();
// Startup recovery: any job left 'in_flight' was interrupted by a restart/crash.
// Reset to 'pending' so the drain loop reprocesses it.
const recovered = database.prepare("UPDATE adapter_queue SET status='pending', error=NULL, retry_count=0 WHERE status='in_flight'").run();
if (Number(recovered.changes) > 0) console.log(`[investor-flow] recovered ${recovered.changes} interrupted in_flight jobs`);
const createContext = makeCreateContext({ db: database, cache, queue });
// Background drain: stale-while-revalidate refreshes are queued by CacheRepository.get;
// this loop drains them (fetch via adapter -> write to cache), deduped + backed off.
@@ -23,6 +37,11 @@ const DRAIN_MS = Number(process.env.IFLOW_DRAIN_MS ?? 2000);
const drainTimer = setInterval(() => { queue.drain().catch((e) => console.error('[drain error]', e)); }, DRAIN_MS);
drainTimer.unref();
// Auto-scheduler: every 30s, enqueue refreshes for due schedules
const SCHEDULE_MS = 30_000;
const scheduleTimer = setInterval(() => { queue.enqueueDueSchedules().catch((e) => console.error('[schedule error]', e)); }, SCHEDULE_MS);
scheduleTimer.unref();
function readBody(req: IncomingMessage): Promise<string> {
return new Promise((resolve, reject) => {
let data = '';
@@ -44,7 +63,12 @@ const server = createServer(async (req, res) => {
for (const [k, v] of Object.entries(req.headers)) if (v != null) headers.set(k, Array.isArray(v) ? v.join(', ') : String(v));
const method = req.method ?? 'GET';
const body = method === 'GET' || method === 'HEAD' ? undefined : await readBody(req);
const request = new Request(`http://localhost:${PORT}${url.pathname}${url.search}`, { method, headers, body });
const requestUrl = `http://localhost:${PORT}${url.pathname}${url.search}`;
const init: RequestInit = { method, headers };
if (body) {
init.body = new Blob([body], { type: 'application/json' });
}
const request = new Request(requestUrl, init);
try {
const response = await fetchRequestHandler({ router: appRouter, createContext, endpoint: '/api/trpc', req: request });
const buf = Buffer.from(await response.arrayBuffer());
@@ -61,6 +85,7 @@ const server = createServer(async (req, res) => {
res.end(JSON.stringify({ error: 'not found' }));
});
server.listen(PORT, () => {
console.log(`[investor-flow] backend on http://localhost:${PORT} (tRPC /api/trpc, health /health, drain every ${DRAIN_MS}ms)`);
const HOST = process.env.HOST ?? '0.0.0.0';
server.listen(PORT, HOST, () => {
console.log(`[investor-flow] backend on http://${HOST}:${PORT} (tRPC /api/trpc, health /health, drain every ${DRAIN_MS}ms)`);
});