Merge PR #2630: feat(autopilot): wire the nightly conversation-parser probe into the loop

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

test/audit-parser-probe.serial.test.ts

@@ -0,0 +1,102 @@
+/**
+ * Tests for the parser-probe audit trail + the 24h rate-limit gate.
+ *
+ * Uses GBRAIN_AUDIT_DIR override pointed at a tmpdir for hermeticity
+ * (same pattern as audit-slug-fallback.serial.test.ts). Serial because
+ * the env override is process-global.
+ */
+import { afterEach, beforeEach, describe, expect, test } from 'bun:test';
+import { mkdtempSync, rmSync, readdirSync } from 'node:fs';
+import { tmpdir } from 'node:os';
+import { join } from 'node:path';
+
+import {
+  computeParserProbeAuditFilename,
+  logParserProbeEvent,
+  parserProbeRanWithin,
+  readRecentParserProbeEvents,
+  type ParserProbeAuditEvent,
+} from '../src/core/audit-parser-probe.ts';
+
+let auditDir: string;
+let savedEnv: string | undefined;
+
+beforeEach(() => {
+  auditDir = mkdtempSync(join(tmpdir(), 'parser-probe-audit-'));
+  savedEnv = process.env.GBRAIN_AUDIT_DIR;
+  process.env.GBRAIN_AUDIT_DIR = auditDir;
+});
+
+afterEach(() => {
+  if (savedEnv === undefined) delete process.env.GBRAIN_AUDIT_DIR;
+  else process.env.GBRAIN_AUDIT_DIR = savedEnv;
+  rmSync(auditDir, { recursive: true, force: true });
+});
+
+function makeEvent(overrides: Partial<ParserProbeAuditEvent> = {}): ParserProbeAuditEvent {
+  return {
+    schema_version: 1,
+    ts: new Date().toISOString(),
+    outcome: 'pass',
+    fixtures_total: 12,
+    fixtures_passed: 12,
+    recall_mean: 0.98,
+    participants_recall_mean: 0.97,
+    adversarial_false_positives: 0,
+    failed_fixture_ids: [],
+    ...overrides,
+  };
+}
+
+describe('parser-probe audit trail', () => {
+  test('log + readRecent round-trip', () => {
+    logParserProbeEvent(makeEvent({ outcome: 'fail', reason: '2 fixture(s) failed' }));
+    const events = readRecentParserProbeEvents(7);
+    expect(events.length).toBe(1);
+    expect(events[0]!.outcome).toBe('fail');
+    expect(events[0]!.reason).toBe('2 fixture(s) failed');
+    const files = readdirSync(auditDir);
+    expect(files.length).toBe(1);
+    expect(files[0]).toMatch(/^parser-probe-\d{4}-W\d{2}\.jsonl$/);
+  });
+
+  test('filename uses ISO-week rotation with the parser-probe prefix', () => {
+    // Year-boundary edge pinned by the shared writer's own tests; here we
+    // pin the prefix wiring.
+    expect(computeParserProbeAuditFilename(new Date('2026-07-06T12:00:00Z'))).toBe(
+      'parser-probe-2026-W28.jsonl',
+    );
+  });
+
+  test('readRecent filters by window', () => {
+    const old = new Date(Date.now() - 10 * 86400000).toISOString();
+    logParserProbeEvent(makeEvent({ ts: old }));
+    expect(readRecentParserProbeEvents(7).length).toBe(0);
+  });
+});
+
+describe('parserProbeRanWithin — 24h rate-limit gate', () => {
+  const DAY_MS = 24 * 60 * 60 * 1000;
+
+  test('false when no runs are audited', () => {
+    expect(parserProbeRanWithin(DAY_MS)).toBe(false);
+  });
+
+  test('true when a run landed within the window', () => {
+    logParserProbeEvent(makeEvent({ ts: new Date(Date.now() - 60_000).toISOString() }));
+    expect(parserProbeRanWithin(DAY_MS)).toBe(true);
+  });
+
+  test('false when the last run is older than the window', () => {
+    logParserProbeEvent(makeEvent({ ts: new Date(Date.now() - 25 * 3600_000).toISOString() }));
+    expect(parserProbeRanWithin(DAY_MS)).toBe(false);
+  });
+
+  test('non-pass outcomes also hold the window (mirrors quality-probe semantics)', () => {
+    logParserProbeEvent(makeEvent({
+      outcome: 'no_embedding_key',
+      ts: new Date(Date.now() - 3600_000).toISOString(),
+    }));
+    expect(parserProbeRanWithin(DAY_MS)).toBe(true);
+  });
+});

test/autopilot-parser-probe-wiring.test.ts

@@ -0,0 +1,77 @@
+/**
+ * Source-shape regression tests for the autopilot wiring of
+ * `runConversationParserNightlyProbe` (step 4.6).
+ *
+ * Same rationale as autopilot-nightly-probe-wiring.test.ts: the loop is
+ * hard to drive end-to-end, so these pin the structural protections —
+ * the dual-plane flag read, the D10 tokenmax mode-gate, the package-root
+ * fixture resolution, the audit-flood guard, and the try/catch posture.
+ *
+ * The probe's own gate/scoring logic is pinned by the module's unit
+ * tests; the audit trail by audit-parser-probe.serial.test.ts.
+ */
+
+import { describe, test, expect } from 'bun:test';
+import { readFileSync } from 'node:fs';
+import { resolve } from 'node:path';
+
+const AUTOPILOT_SRC = resolve('src/commands/autopilot.ts');
+const SOURCE = readFileSync(AUTOPILOT_SRC, 'utf-8');
+
+describe('autopilot wiring: conversation-parser probe', () => {
+  test('invokes the phase module and the audit trail', () => {
+    expect(SOURCE).toContain(`runConversationParserNightlyProbe`);
+    expect(SOURCE).toContain(`conversation-parser/nightly-probe`);
+    expect(SOURCE).toContain(`logParserProbeEvent`);
+    expect(SOURCE).toContain(`audit-parser-probe`);
+  });
+
+  test('flag reads dual-plane: DB row (gbrain config set) wins, file plane fallback', () => {
+    expect(SOURCE).toContain(`getConfig('autopilot.conversation_parser_probe.enabled')`);
+    expect(SOURCE).toContain(`cfg?.autopilot?.conversation_parser_probe?.enabled === true`);
+  });
+
+  test('D10 mode-gate present: tokenmax brains run the probe by default', () => {
+    expect(SOURCE).toMatch(/parserEnabled \|\| searchMode === 'tokenmax'/);
+  });
+
+  test('fixtures resolve from the gbrain package root, NOT the brain repoPath', () => {
+    // The committed fixtures live in the gbrain source tree; resolving
+    // them against sync.repo_path would point into the user's brain repo.
+    expect(SOURCE).toMatch(/fileURLToPath\(new URL\('\.\.\/\.\.', import\.meta\.url\)\)/);
+    expect(SOURCE).toContain(`'conversation-formats', 'all.jsonl'`);
+    expect(SOURCE).toContain(`'conversation-formats', 'adversarial.jsonl'`);
+  });
+
+  test('missing fixtures skip quietly (no audit row, once-per-process stderr note)', () => {
+    // Compiled-binary installs carry no source tree; writing failure rows
+    // would flip doctor to WARN on every binary install.
+    expect(SOURCE).toContain(`parserProbeFixtureWarned`);
+  });
+
+  test('rate_limited outcomes are NOT audit-logged (flood guard)', () => {
+    expect(SOURCE).toMatch(/outcome !== 'rate_limited'\) logParserProbeEvent\(result\)/);
+  });
+
+  test('rate-limit gate delegates to the audit module, not inline event reads', () => {
+    expect(SOURCE).toContain(`parserProbeRanWithin(24 * 60 * 60 * 1000)`);
+  });
+
+  test('LLM-key gate reads gateway.isAvailable("chat") in-process', () => {
+    expect(SOURCE).toContain(`isAvailable('chat')`);
+  });
+
+  test('probe call wrapped in try/catch that does NOT bump consecutiveErrors', () => {
+    expect(SOURCE).toMatch(/catch[\s\S]*?autopilot\.parser_probe[\s\S]*?do NOT bump consecutiveErrors/);
+  });
+
+  test('DI shape: the exact 7 fields of the parser probe NightlyProbeDeps', () => {
+    expect(SOURCE).toContain(`isEnabled:`);
+    expect(SOURCE).toContain(`searchMode:`);
+    expect(SOURCE).toContain(`hasLlmKey:`);
+    expect(SOURCE).toContain(`resolveFixturePath:`);
+    expect(SOURCE).toContain(`resolveAdversarialPath:`);
+    expect(SOURCE).toContain(`shouldSkipForRateLimit:`);
+    expect(SOURCE).toContain(`now:`);
+  });
+});

test/doctor-parser-probe-check.test.ts

@@ -0,0 +1,51 @@
+/**
+ * Tests for computeConversationParserProbeHealthCheck — the pure function
+ * behind doctor's conversation_parser_probe_health check, which replaced
+ * the v0.41.13.0 hardcoded "Skipped" stub when the autopilot wiring
+ * landed. Mirrors the branch coverage style of the quality-probe check.
+ */
+import { describe, expect, test } from 'bun:test';
+
+import { computeConversationParserProbeHealthCheck } from '../src/commands/doctor.ts';
+
+const ev = (outcome: string, reason?: string, ts = new Date().toISOString()) => ({
+  outcome,
+  ts,
+  ...(reason !== undefined ? { reason } : {}),
+});
+
+describe('computeConversationParserProbeHealthCheck', () => {
+  test('disabled + no events → ok with paste-ready enable hint', () => {
+    const check = computeConversationParserProbeHealthCheck(false, []);
+    expect(check.status).toBe('ok');
+    expect(check.message).toContain('gbrain config set autopilot.conversation_parser_probe.enabled true');
+  });
+
+  test('enabled + no events yet → ok, next run by autopilot', () => {
+    const check = computeConversationParserProbeHealthCheck(true, []);
+    expect(check.status).toBe('ok');
+    expect(check.message).toContain('no probe events');
+  });
+
+  test('disabled flag but events exist (tokenmax mode-gate ran it) → events win over the hint', () => {
+    const check = computeConversationParserProbeHealthCheck(false, [ev('pass')]);
+    expect(check.status).toBe('ok');
+    expect(check.message).toContain('all pass');
+  });
+
+  test('any non-pass outcome in the window → warn, latest surfaced with reason', () => {
+    const check = computeConversationParserProbeHealthCheck(true, [
+      ev('pass'),
+      ev('adversarial_false_positive', '1 adversarial fixture(s) parsed to non-empty'),
+    ]);
+    expect(check.status).toBe('warn');
+    expect(check.message).toContain('adversarial_false_positive');
+    expect(check.message).toContain('parsed to non-empty');
+  });
+
+  test('all pass → ok with run count', () => {
+    const check = computeConversationParserProbeHealthCheck(true, [ev('pass'), ev('pass')]);
+    expect(check.status).toBe('ok');
+    expect(check.message).toContain('2 probe run(s)');
+  });
+});