Files
vyndr/src/routes/internal.js
T
builtbykev 2bfae804da Verify off-box presence by reading the remote dir back
Exit 0 from the backup script is deliberately tied to ON-BOX durability,
so it is not proof the off-box copy landed. GET /api/internal/backup/offbox
runs rsync --list-only against BACKUP_REMOTE using the SAME pinned
known_hosts as the push (checking never disabled) and returns the dumps
actually present, with size and timestamp — so off-box presence is a
verified fact rather than an inference from an exit code.

Needed because the dev box cannot authenticate to the Storage Box: the
authorized key installed there is Kev's ~/vyndr-backup-key, not the
keypair generated in-session, so independent verification has to run from
the container that does hold working credentials.

Suite 280/3338 green, build exit 0.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01SmNjJAwEnqHPtXbvSZR8kA
2026-07-20 01:14:38 -04:00

405 lines
16 KiB
JavaScript

'use strict';
/**
* Internal ops endpoints (Session 18).
*
* Reachable only with the shared `VYNDR_INTERNAL_KEY` — never
* exposed to end users. The admin dashboard wires the Tank01
* prefetch button to POST here through the Next.js server (the
* key never touches a browser).
*
* Deviation from spec: the spec suggested `execSync('node scripts/tank01-prefetch.js')`.
* We import the module instead — same behavior, but in-process and
* testable. The module already exposes `main(argv)` which returns
* the same summary object the spec expected to parse out of stdout.
*/
const express = require('express');
const { requireInternalAuth } = require('../middleware/internalAuth');
const tank01Prefetch = require('../../scripts/tank01-prefetch');
const quotaTracker = require('../services/quotaTracker');
const router = express.Router();
router.use(requireInternalAuth({ loopbackOnly: false }));
/**
* GET /api/internal/quota (Session 20)
*
* Snapshot of every configured provider's current quota counter.
* Consumed by the admin dashboard's "Provider Quotas" tile. Cached
* for 5s so a refresh-button mash doesn't flood Redis.
*/
router.get('/quota', async (req, res) => {
try {
const providers = await quotaTracker.getAllQuotaStatuses();
res.set('Cache-Control', 'private, max-age=5');
return res.json({ ok: true, providers });
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/quota] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* POST /api/internal/quota/test-alert (quota guard)
*
* Test-fires the quota pager end-to-end through the REAL opsNotify path so
* "does the 80% alert actually deliver?" is verifiable on demand (the reason
* the 500/500 drain went unnoticed was a counting blind spot, not delivery —
* this proves the delivery leg). Sends one ntfy to vyndr-pipeline-kev2026.
* Does NOT touch the real counter. Body: { pct? } (default 0.85).
*/
router.post('/quota/test-alert', async (req, res) => {
try {
const notify = require('../utils/opsNotify').notify;
const pct = Number.isFinite(Number(req.body && req.body.pct)) ? Number(req.body.pct) : 0.85;
const out = await notify(
`TEST — odds-api quota alert delivery check (${Math.round(pct * 100)}%). If you can read this, the quota pager path works.`,
{ title: 'VYNDR quota (test)', priority: 'high', tags: ['warning', 'chart_decreasing'] },
);
return res.json({ ok: true, delivery: out });
} catch (err) {
const message = err && err.message ? err.message : String(err);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* POST /api/internal/prefetch/tank01
*
* Body (all optional):
* { max?: number, sports?: string[]|string, dryRun?: boolean }
*
* Builds an argv array equivalent to the CLI form and hands it to
* the prefetch module. Returns the module's summary on success.
*/
router.post('/prefetch/tank01', async (req, res) => {
const body = (req.body && typeof req.body === 'object') ? req.body : {};
// Build argv. `main()` parses its own args, so all the validation
// (numeric bounds, allowed sports) stays in one place — we just
// translate JSON shapes into CLI flags.
const argv = ['node', 'scripts/tank01-prefetch.js'];
if (Number.isFinite(body.max) && body.max > 0) {
argv.push(`--max=${Math.floor(body.max)}`);
}
if (body.dryRun === true) {
argv.push('--dry-run');
}
if (body.sports) {
const sportsList = Array.isArray(body.sports)
? body.sports.join(',')
: String(body.sports);
argv.push(`--sports=${sportsList}`);
}
try {
const summary = await tank01Prefetch.main(argv);
return res.json({ ok: true, summary });
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/prefetch/tank01] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* POST /api/internal/snapshot/:sport (Session 45)
*
* Trigger one snapshot cycle for a sport (pre-grade the slate, lock grades,
* compute deltas, emit ticker events). Internal-only (requireInternalAuth at the
* router root). This is what the cron / n8n schedule calls — never public, so a
* bad actor can't drain the PropLine quota by spamming it.
*/
/** POST /api/internal/snapshot/all — every active sport, sequentially.
* Registered BEFORE /snapshot/:sport so "all" isn't captured as a sport. */
router.post('/snapshot/all', async (req, res) => {
const snapshot = require('../services/snapshotService');
try {
const results = await snapshot.runAllSnapshots();
return res.json({ ok: true, results });
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/snapshot/all] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* GET /api/internal/snapshot/status (Session 52) — verification probe. Reports
* whether the in-process cron is armed, the freshest snapshot per sport, which
* pipeline Redis keys exist, and the ticker item count. Read-only; safe to poll.
* GET vs the POST /snapshot/:sport below — no route collision.
*/
router.get('/snapshot/status', async (req, res) => {
const { cacheGet } = require('../utils/redis');
const { HOURS_UTC, isSnapshotOverdue } = require('../snapshotScheduler');
const SPORTS = ['mlb', 'nba', 'wnba'];
try {
const redis_keys = {};
const last_snapshot = {};
for (const sp of SPORTS) {
const latestKey = `snapshot:${sp}:latest`;
const prevKey = `snapshot:${sp}:previous`;
const gradesKey = `grades:${sp}`;
const [latest, prev, grades] = await Promise.all([cacheGet(latestKey), cacheGet(prevKey), cacheGet(gradesKey)]);
redis_keys[latestKey] = !!latest;
redis_keys[prevKey] = !!prev;
redis_keys[gradesKey] = !!grades;
if (latest) {
last_snapshot[sp] = {
updated_at: latest.updated_at || null,
gradeCount: Array.isArray(latest.grades) ? latest.grades.length : 0,
deltaCount: Array.isArray(latest.deltas) ? latest.deltas.length : 0,
};
}
}
const ticker = await cacheGet('ticker:items');
redis_keys['ticker:items'] = !!ticker;
// Session 56 — surface the missed-cron signal in the health probe.
const mlbTs = last_snapshot.mlb && last_snapshot.mlb.updated_at;
return res.json({
cron_armed: process.env.SNAPSHOT_CRON === '1',
cron_hours_utc: HOURS_UTC,
last_snapshot,
overdue: isSnapshotOverdue(mlbTs),
redis_keys,
ticker_count: Array.isArray(ticker) ? ticker.length : 0,
});
} catch (err) {
return res.status(500).json({ ok: false, error: err.message });
}
});
router.post('/snapshot/:sport', async (req, res) => {
const snapshot = require('../services/snapshotService');
try {
const summary = await snapshot.runSnapshot(req.params.sport);
return res.json({ ok: true, summary });
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/snapshot] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* POST /api/internal/outcomes/all (Session 55) — settle every sport's latest
* snapshot against real results + recompute the overall accuracy record. This
* is the self-learning loop's write path (the public /api/accuracy is read-only).
* Registered BEFORE /outcomes/:sport so "all" isn't captured as a sport.
*/
router.post('/outcomes/all', async (req, res) => {
const outcomes = require('../services/outcomeService');
try {
const results = await outcomes.settleAllOutcomes();
return res.json({ ok: true, results });
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/outcomes/all] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* POST /api/internal/ghost/drafts (Session 63 / A1-S4d) — assemble today's
* desk pack and save the slate-preview + settle drafts to Ghost. DRAFTS
* ONLY; Kev publishes from the Ghost admin. Env-gated no-op without Ghost.
*/
router.post('/ghost/drafts', async (req, res) => {
try {
const { assembleDeskPack } = require('../services/deskService');
const ghost = require('../services/ghostPublisher');
const pack = await assembleDeskPack();
const result = await ghost.saveDailyDrafts(pack);
return res.json({ ok: result.ok, result });
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/ghost/drafts] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* POST /api/internal/refresh/all (Session 60, Phase 2.5) — manual intraday
* odds-only refresh: STEAM/VALUE movement, public revisions, closing
* capture. Same behavior as the in-process 20-min cadence.
*/
router.post('/refresh/all', async (req, res) => {
const refresh = require('../services/intradayRefreshService');
try {
const results = await refresh.runAllIntradayRefreshes();
return res.json({ ok: true, results });
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/refresh/all] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* POST /api/internal/backup/run (Session 64) — fire ONE real database backup
* now: pg_dump → validate (`pg_restore --list` must contain ledger_entries) →
* off-box rsync to the Storage Box.
*
* Exists because the backup can only run where SUPABASE_DB_URL and the Supabase
* network route live — inside this container — and there was previously no way
* to trigger or observe it without a shell on the box. Returns the script's
* exit code and output tail so a real run can be VERIFIED, not assumed.
*/
router.post('/backup/run', async (req, res) => {
const { runBackup, durabilityWarning } = require('../backupScheduler');
try {
const started = Date.now();
const result = await runBackup();
// Session 64 Phase 2b — off-box is REQUIRED now, so its outcome is reported
// SEPARATELY from the exit code. The script deliberately still exits 0 on a
// failed push (a durable on-box dump must not raise a false total-failure
// alarm) — so without this field a failed off-box push reads as success.
const tail = result.tail || '';
const offboxOk = /OFFBOX_OK=1/.test(tail) ? true
: (/OFFBOX_OK=0/.test(tail) ? false : null); // null = deferred/not attempted
return res.json({
ok: result.ok,
offbox_ok: offboxOk,
exit_code: result.code,
duration_ms: Date.now() - started,
durability_warning: durabilityWarning() || null,
remote_configured: !!process.env.BACKUP_REMOTE,
ssh_key_configured: !!process.env.BACKUP_SSH_KEY,
output_tail: result.tail || result.error || null,
});
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/backup/run] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* GET /api/internal/backup/verify (Session 64) — prove the newest dump on the
* persistent volume actually CONTAINS the data, by counting `ledger_entries`
* rows out of the archive with pg_restore. A backup nobody has read back is a
* hope, not a backup.
*/
router.get('/backup/verify', async (req, res) => {
const { latestDump, countRowsInDump } = require('../backupScheduler');
try {
const dir = process.env.BACKUP_DIR || '/var/backups/vyndr';
// Report identity + writability: a mounted-but-unwritable volume is the
// exact failure we hit (Coolify mounts root-owned; the container runs as
// the non-root `vyndr` user), and the fix needs the real uid/gid.
const fs = require('fs');
let writable = false;
let dirErr = null;
try {
fs.accessSync(dir, fs.constants.W_OK);
writable = true;
} catch (e) { dirErr = e.code || e.message; }
const identity = {
uid: typeof process.getuid === 'function' ? process.getuid() : null,
gid: typeof process.getgid === 'function' ? process.getgid() : null,
backup_dir_writable: writable,
backup_dir_error: dirErr,
};
const dump = latestDump(dir);
if (!dump) {
return res.json({ ok: false, backup_dir: dir, ...identity, error: 'no dump found in BACKUP_DIR' });
}
const table = String(req.query.table || 'ledger_entries');
const counted = await countRowsInDump(dump.path, table);
return res.json({
ok: counted.ok,
backup_dir: dir,
...identity,
dump: dump.file,
dump_bytes: dump.size,
table,
rows_in_dump: counted.rows,
error: counted.error || null,
});
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/backup/verify] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* GET /api/internal/backup/offbox — list the dumps actually present ON the
* Storage Box. Exit 0 from the backup is not proof the file landed; this reads
* the remote directory back so off-box presence is verified, not inferred.
*/
router.get('/backup/offbox', async (req, res) => {
const { listOffbox } = require('../backupScheduler');
try {
const result = await listOffbox();
return res.json(result);
} catch (err) {
const message = err && err.message ? err.message : String(err);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* POST /api/internal/ledger/settle (Session 58, Phase 1) — settle the
* persistent ledger (outcome + actual_value + CLV) across every sport.
* Idempotent — safe to re-run; already-settled rows are never touched.
*/
router.post('/ledger/settle', async (req, res) => {
const ledger = require('../services/ledgerService');
try {
const results = await ledger.settleAllLedgers();
return res.json({ ok: true, results });
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/ledger/settle] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
/**
* POST /api/internal/newsletter/send (Session S7, a1) — assemble today's
* VYNDR REPORT from the pipeline (snapshot signals + streak lens + the
* ledger record) and send it as a Listmonk campaign to the opted-in list.
*
* DELIBERATELY UNSCHEDULED: nothing calls this on a timer. The operator
* (or a future n8n cron, once Kev arms it) triggers the send. Env-gated —
* without LISTMONK_* config it's a calm no-op; an empty report (zero
* signals AND zero streaks) refuses to send.
*
* Body (optional): { sports?: string[] } — defaults to ['mlb', 'wnba'].
*/
router.post('/newsletter/send', async (req, res) => {
const newsletter = require('../services/newsletterService');
const body = (req.body && typeof req.body === 'object') ? req.body : {};
const sports = Array.isArray(body.sports) && body.sports.length > 0 ? body.sports : undefined;
try {
const result = await newsletter.sendDailyReport({ sports });
return res.json(result);
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/newsletter/send] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
router.post('/outcomes/:sport', async (req, res) => {
const outcomes = require('../services/outcomeService');
try {
const summary = await outcomes.settleSnapshot(req.params.sport);
await outcomes.recomputeOverall();
return res.json({ ok: true, summary: { sport: summary.sport, settled: summary.settled, pending: summary.pending, accuracy: summary.accuracy } });
} catch (err) {
const message = err && err.message ? err.message : String(err);
console.error('[internal/outcomes] failed:', message);
return res.status(500).json({ ok: false, error: message });
}
});
module.exports = router;