Files
worldmonitor/scripts/seed-market-quotes.mjs
Elie Habib 9b07fc8d8a feat(yahoo): _yahoo-fetch helper with curl-only Decodo proxy fallback + 4 seeder migrations (#3120)
* feat(_yahoo-fetch): curl-only Decodo proxy fallback helper

Yahoo Finance throttles Railway egress IPs aggressively. 4 seeders
(seed-commodity-quotes, seed-etf-flows, seed-gulf-quotes, seed-market-quotes)
duplicated the same fetchYahooWithRetry block with no proxy fallback.
This helper consolidates them and adds the proxy fallback.

Yahoo-specific: CURL-ONLY proxy strategy. Probed 2026-04-16:
  query1.finance.yahoo.com via CONNECT (httpsProxyFetchRaw): HTTP 404
  query1.finance.yahoo.com via curl    (curlFetch):          HTTP 200
Yahoo's edge blocks Decodo's CONNECT egress IPs but accepts the curl
egress IPs. Helper deliberately omits the CONNECT leg — adding it
would burn time on guaranteed-404 attempts. Production defaults expose
ONLY curlProxyResolver + curlFetcher.

All learnings from PR #3118 + #3119 reviews baked in:
- lastDirectError accumulator across the loop, embedded in final throw +
  Error.cause chain
- catch block uses break (NOT throw) so thrown errors also reach proxy
- DI seams (_curlProxyResolver, _proxyCurlFetcher) for hermetic tests
- _PROXY_DEFAULTS exported for production-default lock tests
- Sync curlFetch wrapped with await Promise.resolve() to future-proof
  against an async refactor (Greptile P2 from #3119)

Tests (tests/yahoo-fetch.test.mjs, 11 cases):
- Production defaults: curl resolver/fetcher reference equality
- Production defaults: NO CONNECT leg present (regression guard)
- 200 OK passthrough, never touches proxy
- 429 with no proxy → throws exhausted with HTTP 429 in message
- Retry-After header parsed correctly
- 429 + curl proxy succeeds → returns proxy data
- Thrown fetch error on final retry → proxy fallback runs (P1 guard)
- 429 + proxy ALSO fails → both errors visible in message + cause chain
- Proxy malformed JSON → throws exhausted
- Non-retryable 500 → no extra direct retry, falls to proxy
- parseRetryAfterMs unit (exported sanity check)

Verification: 11/11 helper tests pass. node --check clean.

Phase 1 of 2 — seeder migrations follow.

* feat(yahoo-seeders): migrate 4 seeders to _yahoo-fetch helper

Removes the duplicated fetchYahooWithRetry function (4 byte-identical
copies across seed-commodity-quotes, seed-etf-flows, seed-gulf-quotes,
seed-market-quotes) and routes all Yahoo Finance fetches through the
new scripts/_yahoo-fetch.mjs helper. Each seeder gains the curl-only
Decodo proxy fallback baked into the helper.

Per-seeder changes (mechanical):
- import { fetchYahooJson } from './_yahoo-fetch.mjs'
- delete the local fetchYahooWithRetry function
- replace 'const resp = await fetchYahooWithRetry(url, label); if (!resp)
  return X; const json = await resp.json()' with
  'let json; try { json = await fetchYahooJson(url, { label }); }
  catch { return X; }'
- prune now-unused CHROME_UA/sleep imports where applicable

Latent bugs fixed in passing:
- seed-etf-flows.mjs:23 and seed-market-quotes.mjs:38 referenced
  CHROME_UA without importing it (would throw ReferenceError at
  runtime if the helper were called). Now the call site is gone in
  etf-flows; in market-quotes CHROME_UA is properly imported because
  Finnhub call still uses it.

seed-commodity-quotes also has fetchYahooChart1y (separate non-retry
function for gold history). Migrated to use fetchYahooJson under the
hood — preserves return shape, adds proxy fallback automatically.

Verification:
- node --check clean on all 4 modified seeders
- npm run typecheck:all clean
- npm run test:data: 5374/5374 pass

Phase 2 of 2.

* fix(_yahoo-fetch): log success AFTER parse + add _sleep DI seam for honest Retry-After test

Greptile P2: "[YAHOO] proxy (curl) succeeded" was logged BEFORE
JSON.parse(text). On malformed proxy JSON, Railway logs would show:

  [YAHOO] proxy (curl) succeeded for AAPL
  throw: Yahoo retries exhausted ...

Contradictory + breaks the post-deploy log-grep verification this PR
relies on ("look for [YAHOO] proxy (curl) succeeded"). Fix: parse
first; success log only fires when parse succeeds AND the value is
about to be returned.

Greptile P3: 'Retry-After header parsed correctly' test used header
value '0', but parseRetryAfterMs() treats non-positive seconds as null
→ helper falls through to default linear backoff. So the test was
exercising the wrong branch despite its name.

Fix: added _sleep DI opt seam to the helper. New test injects a sleep
spy and asserts the captured duration:

  Retry-After: '7' → captured sleep == [7000]   (Retry-After branch)
  no Retry-After  → captured sleep == [10]      (default backoff = retryBaseMs * 1)

Two paired tests lock both branches separately so a future regression
that collapses them is caught.

Also added a log-ordering regression test: malformed proxy JSON must
NOT emit the 'succeeded' log. Captures console.log into an array and
asserts no 'proxy (curl) succeeded' line appeared before the throw.

Verification:
- tests/yahoo-fetch.test.mjs: 13/13 (was 11, +2)
- npm run test:data: 5376/5376 (+2)
- npm run typecheck:all: clean

Followup commits on PR #3120.
2026-04-16 09:25:06 +04:00

136 lines
4.8 KiB
JavaScript

#!/usr/bin/env node
import { loadEnvFile, loadSharedConfig, sleep, CHROME_UA, runSeed, parseYahooChart, writeExtraKey } from './_seed-utils.mjs';
import { fetchYahooJson } from './_yahoo-fetch.mjs';
import { fetchAvBulkQuotes } from './_shared-av.mjs';
const stocksConfig = loadSharedConfig('stocks.json');
loadEnvFile(import.meta.url);
const CANONICAL_KEY = 'market:stocks-bootstrap:v1';
const CACHE_TTL = 1800;
const YAHOO_DELAY_MS = 200;
const MARKET_SYMBOLS = stocksConfig.symbols.map(s => s.symbol);
const YAHOO_ONLY = new Set(stocksConfig.yahooOnly);
async function fetchFinnhubQuote(symbol, apiKey) {
try {
const url = `https://finnhub.io/api/v1/quote?symbol=${encodeURIComponent(symbol)}`;
const resp = await fetch(url, {
headers: { 'User-Agent': CHROME_UA, 'X-Finnhub-Token': apiKey },
signal: AbortSignal.timeout(10_000),
});
if (!resp.ok) return null;
const data = await resp.json();
if (data.c === 0 && data.h === 0 && data.l === 0) return null;
return { symbol, name: symbol, display: symbol, price: data.c, change: data.dp, sparkline: [] };
} catch (err) {
console.warn(` [Finnhub] ${symbol} error: ${err.message}`);
return null;
}
}
async function fetchYahooQuote(symbol) {
try {
const url = `https://query1.finance.yahoo.com/v8/finance/chart/${encodeURIComponent(symbol)}`;
const chart = await fetchYahooJson(url, { label: symbol });
return parseYahooChart(chart, symbol);
} catch (err) {
console.warn(` [Yahoo] ${symbol} error: ${err.message}`);
return null;
}
}
async function fetchMarketQuotes() {
const quotes = [];
const avKey = process.env.ALPHA_VANTAGE_API_KEY;
const finnhubKey = process.env.FINNHUB_API_KEY;
// --- Primary: Alpha Vantage REALTIME_BULK_QUOTES ---
if (avKey) {
// AV doesn't support Indian NSE symbols or Yahoo-only indices — skip those
const avSymbols = MARKET_SYMBOLS.filter((s) => !YAHOO_ONLY.has(s) && !s.endsWith('.NS'));
const avResults = await fetchAvBulkQuotes(avSymbols, avKey);
for (const [sym, q] of avResults) {
const meta = stocksConfig.symbols.find(s => s.symbol === sym);
quotes.push({ symbol: sym, name: meta?.name || sym, display: meta?.display || sym, price: q.price, change: q.change, sparkline: [] });
console.log(` [AV] ${sym}: $${q.price} (${q.change > 0 ? '+' : ''}${q.change.toFixed(2)}%)`);
}
}
const covered = new Set(quotes.map((q) => q.symbol));
// --- Secondary: Finnhub (for any stocks not covered by AV or if AV key not set) ---
if (finnhubKey) {
const finnhubSymbols = MARKET_SYMBOLS.filter((s) => !covered.has(s) && !YAHOO_ONLY.has(s));
for (let i = 0; i < finnhubSymbols.length; i++) {
if (i > 0 && i % 10 === 0) await sleep(100);
const r = await fetchFinnhubQuote(finnhubSymbols[i], finnhubKey);
if (r) {
quotes.push(r);
covered.add(r.symbol);
console.log(` [Finnhub] ${r.symbol}: $${r.price} (${r.change > 0 ? '+' : ''}${r.change}%)`);
}
}
}
// --- Fallback: Yahoo (for remaining symbols including Yahoo-only and Indian markets) ---
const allYahoo = MARKET_SYMBOLS.filter((s) => !covered.has(s));
for (let i = 0; i < allYahoo.length; i++) {
const s = allYahoo[i];
if (i > 0) await sleep(YAHOO_DELAY_MS);
const q = await fetchYahooQuote(s);
if (q) {
const meta = stocksConfig.symbols.find(x => x.symbol === s);
quotes.push({ ...q, symbol: s, name: meta?.name || s, display: meta?.display || s });
covered.add(s);
console.log(` [Yahoo] ${s}: $${q.price} (${q.change > 0 ? '+' : ''}${q.change}%)`);
}
}
if (quotes.length === 0) {
throw new Error('All market quote fetches failed');
}
return {
quotes,
finnhubSkipped: !finnhubKey && !avKey,
skipReason: (!finnhubKey && !avKey) ? 'ALPHA_VANTAGE_API_KEY and FINNHUB_API_KEY not configured' : '',
rateLimited: false,
};
}
function validate(data) {
return Array.isArray(data?.quotes) && data.quotes.length >= 1;
}
export function declareRecords(data) {
return Array.isArray(data?.quotes) ? data.quotes.length : 0;
}
let seedData = null;
async function fetchAndStash() {
seedData = await fetchMarketQuotes();
return seedData;
}
runSeed('market', 'quotes', CANONICAL_KEY, fetchAndStash, {
validateFn: validate,
ttlSeconds: CACHE_TTL,
sourceVersion: 'alphavantage+finnhub+yahoo',
declareRecords,
schemaVersion: 1,
maxStaleMin: 30,
}).then(async (result) => {
if (result?.skipped || !seedData) return;
const rpcKey = `market:quotes:v1:${[...MARKET_SYMBOLS].sort().join(',')}`;
await writeExtraKey(rpcKey, seedData, CACHE_TTL);
}).catch((err) => {
const _cause = err.cause ? ` (cause: ${err.cause.message || err.cause.code || err.cause})` : ''; console.error('FATAL:', (err.message || err) + _cause);
process.exit(1);
});