timmy-talking-turd/tests/release-dashboard.test.js
Timmy ad8c8a9f4c
All checks were successful
Quality gates / quality (pull_request) Successful in 1m44s
feat(ops): release observability dashboard and incident-response flow
Implements issue #41 acceptance criteria without touching the live host:

- src/release-observability.js: sanitizeEvidence() allowlists bounded,
  privacy-safe evidence (release tag, commit, UTC time, per-check
  id/boundary/status/failure-class/latency/counters) and drops session
  identifiers, credentials, environment dumps, photo payloads, base64,
  image hashes, note text, emails, and any oversized/suspicious value.
- buildDashboard(): app/api/queue/model boundary rollups, failure-class
  counts, manual-fallback state; evaluateAlerts() with owner, threshold,
  severity, and runbook anchor per rule.
- scripts/release_dashboard.mjs: local operator CLI over sanitized
  evidence files or a loopback drill fixture; never contacts a live
  host and exits nonzero without echoing rejected input.
- docs/RELEASE-OBSERVABILITY.md: alert inventory, evidence schema,
  simulated worker-outage drill, incident flow, privacy boundary.
- Tests: sanitizer hostile-payload coverage, dashboard/alert rules,
  end-to-end loopback outage drill asserting exactly one actionable
  page alert plus graceful manual fallback, runbook/package contract.
2026-08-22 20:33:10 +00:00

110 lines
5.0 KiB
JavaScript

import test from 'node:test';
import assert from 'node:assert/strict';
import { sanitizeEvidence, buildDashboard, evaluateAlerts, DEFAULT_ALERT_RULES } from '../src/release-observability.js';
const healthyEvidence = () => sanitizeEvidence({
schemaVersion: 1,
releaseTag: 'daily-2026-08-22.1',
commit: 'ca31e6d38bec649407f63880504554c59f2878ae',
generatedAtUtc: '2026-08-22T12:00:00Z',
checks: [
{ id: 'app.healthz', boundary: 'app', status: 'pass', latencyMs: 12 },
{ id: 'api.analyze', boundary: 'api', status: 'pass', counters: { ok: 40, fail: 0 } },
{ id: 'queue.depth', boundary: 'queue', status: 'pass', counters: { depth: 0 } === undefined ? {} : { ok: 30, fail: 0 } },
{ id: 'model.inference', boundary: 'model', status: 'pass', latencyMs: 900, counters: { ok: 25, fail: 0, abstain: 3 } },
],
}).evidence;
test('dashboard separates app, api, queue, and model boundaries', () => {
const dashboard = buildDashboard(healthyEvidence());
assert.equal(dashboard.ok, true);
assert.deepEqual(Object.keys(dashboard.boundaries).sort(), ['api', 'app', 'model', 'queue']);
assert.equal(dashboard.boundaries.app.pass, 1);
assert.equal(dashboard.boundaries.model.pass, 1);
assert.equal(dashboard.boundaries.model.latencyMs, 900);
assert.equal(dashboard.totals.checks, 4);
assert.equal(dashboard.totals.fail, 0);
assert.deepEqual(dashboard.failureClasses, {});
assert.equal(dashboard.identity.releaseTag, 'daily-2026-08-22.1');
assert.equal(dashboard.identity.commit, 'ca31e6d38bec649407f63880504554c59f2878ae');
});
test('dashboard summarizes privacy-safe failure classes without any payload text', () => {
const evidence = sanitizeEvidence({
schemaVersion: 1,
releaseTag: 'daily-2026-08-22.1',
commit: 'ca31e6d38bec649407f63880504554c59f2878ae',
generatedAtUtc: '2026-08-22T12:00:00Z',
checks: [
{ id: 'api.analyze', boundary: 'api', status: 'degraded', failureClass: 'vision.timeout' },
{ id: 'model.inference', boundary: 'model', status: 'fail', failureClass: 'model.error' },
{ id: 'model.inference.warmup', boundary: 'model', status: 'fail', failureClass: 'model.error' },
],
}).evidence;
const dashboard = buildDashboard(evidence);
assert.deepEqual(dashboard.failureClasses, { 'vision.timeout': 1, 'model.error': 2 });
assert.equal(dashboard.totals.fail, 2);
assert.equal(dashboard.totals.degraded, 1);
assert.equal(JSON.stringify(dashboard).includes('note'), false);
});
test('simulated worker outage fires exactly one actionable alert with owner, threshold, and runbook', () => {
const evidence = sanitizeEvidence({
schemaVersion: 1,
releaseTag: 'daily-2026-08-22.1',
commit: 'ca31e6d38bec649407f63880504554c59f2878ae',
generatedAtUtc: '2026-08-22T12:00:00Z',
checks: [
{ id: 'app.healthz', boundary: 'app', status: 'pass', latencyMs: 11 },
{ id: 'api.analyze', boundary: 'api', status: 'fail', failureClass: 'worker.unavailable' },
{ id: 'queue.depth', boundary: 'queue', status: 'fail', failureClass: 'worker.unavailable', counters: { depth: 17 } },
{ id: 'model.inference', boundary: 'model', status: 'fail', failureClass: 'worker.unavailable', counters: { timeout: 4 } },
],
}).evidence;
const dashboard = buildDashboard(evidence);
const alerts = evaluateAlerts(dashboard, DEFAULT_ALERT_RULES);
assert.equal(alerts.length, 1, `expected exactly one alert, got ${JSON.stringify(alerts)}`);
const alert = alerts[0];
assert.equal(alert.id, 'worker.outage');
assert.equal(alert.severity, 'page');
assert.equal(alert.owner, 'release-operator');
assert.match(alert.runbook, /docs\/RELEASE-OBSERVABILITY\.md#simulate-a-worker-outage/);
assert.match(alert.message, /worker\.unavailable/);
assert.match(alert.message, /daily-2026-08-22\.1/);
assert.equal(alert.count, 3);
assert.equal(alert.threshold, 1);
});
test('healthy evidence raises no alerts and every default rule carries owner, threshold, and runbook', () => {
assert.deepEqual(evaluateAlerts(buildDashboard(healthyEvidence()), DEFAULT_ALERT_RULES), []);
for (const rule of DEFAULT_ALERT_RULES) {
assert.ok(rule.owner && rule.owner.length > 0);
assert.ok(Number.isInteger(rule.threshold) && rule.threshold >= 1);
assert.match(rule.runbook, /^docs\/RELEASE-OBSERVABILITY\.md#/);
assert.ok(['page', 'warn'].includes(rule.severity));
}
});
test('manual fallback stays available whenever any non-app check is unhealthy', () => {
const healthy = buildDashboard(healthyEvidence());
assert.deepEqual(healthy.manualFallback, { available: true, reason: 'none-required' });
const outage = buildDashboard(sanitizeEvidence({
schemaVersion: 1,
releaseTag: 'daily-2026-08-22.1',
commit: 'ca31e6d38bec649407f63880504554c59f2878ae',
generatedAtUtc: '2026-08-22T12:00:00Z',
checks: [
{ id: 'app.healthz', boundary: 'app', status: 'pass' },
{ id: 'queue.depth', boundary: 'queue', status: 'fail', failureClass: 'worker.unavailable' },
],
}).evidence);
assert.deepEqual(outage.manualFallback, {
available: true,
reason: 'local-journal',
});
});