Files
gbrain/test/audit-parser-probe.serial.test.ts
b91350d778 fix(autopilot,eval): nightly quality probe enable path + conversation-parser probe wire-up (takeover of #2629, #2630) (#3094)
* fix(autopilot,eval): nightly quality probe enable path works end-to-end + wire conversation-parser probe

Takeover of #2629 and #2630 (rebased onto master; dropped the
test/engine-find-trajectory.test.ts hunk both PRs carried — master
already ships the equivalent gateway-dims fix).

#2629 — nightly quality probe enable path:
- autopilot + doctor read the probe flag dual-plane (DB config row from
  'gbrain config set' wins, ~/.gbrain/config.json fallback) via new
  resolveProbeEnabled/resolveProbeMaxUsd helpers
- resolveRepoRoot prefers the gbrain package root where the committed
  fixture lives, not the brain repoPath
- rate_limited skips no longer write an audit row every autopilot cycle
- eval-longmemeval strips 'provider:' recipe ids before raw Anthropic SDK
  calls and emits the gold answer for downstream judges
- cross-modal batch folds the gold answer into the judge task; probe
  passes QA-shaped dimensions instead of the agent-response rubric
- DEFAULT_SLOTS slot A moves to openai:gpt-5.2 (gpt-4o left the recipe);
  new consistency test pins every default slot to its recipe

#2630 — conversation-parser nightly probe wire-up:
- autopilot step 4.6 invokes runConversationParserNightlyProbe (dual-plane
  flag + D10 tokenmax mode-gate, package-root fixtures, 24h gate, audit
  trail via new src/core/audit-parser-probe.ts)
- doctor's conversation_parser_probe_health replaces the hardcoded
  'Skipped' stub with a real pure-function check over the audit trail

Co-authored-by: p3ob7o <p3ob7o@users.noreply.github.com>
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(pricing): add openai:gpt-5.2 canonical entry for the new default slot A

DEFAULT_SLOTS slot A moved to openai:gpt-5.2, which had no CANONICAL_PRICING
entry — estimateCost silently dropped slot A from the --max-usd pre-flight
and est_cost_usd audit rows (~1/3 under-count on the default panel). Rates
from the OpenAI recipe chat touchpoint (verified 2026-04-20). Also refresh
the --slot-a-model help text default and pin a pricing-presence assertion
in the DEFAULT_SLOTS consistency test.

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

---------

Co-authored-by: Sinabina <sinabina@Sinabinas-MacBook-Pro-4.local>
Co-authored-by: p3ob7o <p3ob7o@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Garry Tan <garrytan@gmail.com>
2026-07-23 12:26:33 -07:00

103 lines
3.4 KiB
TypeScript

/**
* 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);
});
});