Files
gbrain/test/conversation-parser/llm-fallback.test.ts
T
9bf96db807 v0.42.51.0 fix(sync): contention-free clock + checkpoint integrity + honest sync freshness (#2255)
* fix(sync): contention-free page-generation clock — sequence swap

The page-generation clock backed the query-cache Layer-1 bookmark via a
FOR EACH STATEMENT trigger running `UPDATE page_generation_clock SET
value=value+1 WHERE id=1`. That took a transaction-length RowExclusiveLock
on one tuple, so every concurrent page writer serialized on the prior
writer's COMMIT — sync ran at ~0.8 cores regardless of worker count.

Swap to a SEQUENCE bumped by nextval() (a microsecond LWLock, never a row
lock). The clock's only contract is monotonic advancement on any page
INSERT/UPDATE/DELETE; last_value is non-transactional, so rolled-back or
concurrent-uncommitted writers only OVER-invalidate the cache (lose a hit),
never serve stale.

- migration v118: CREATE SEQUENCE + load-bearing 2-arg setval (is_called=
  true, floor 1, seeded >= old clock and MAX(generation)) + repoint the
  trigger function body + DELETE query_cache so no old-clock bookmark
  survives the swap. v107 left immutable.
- query-cache-gate.ts: 3 readers -> SELECT last_value FROM page_generation_clock_seq.
- schema.sql + pglite-schema.ts (+ regenerated schema-embedded.ts) ship the
  sequence on fresh install; table + trigger names retained.
- tests: clockValue reads last_value; mechanism proof (trigger fn uses
  nextval not the row UPDATE); rollback-advances-clock safety pin; real
  PGLite sequence round-trip (is_called gotcha); shape test requires _seq.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(sync): op_checkpoints array-shape guard — CHECK + repair + defensive loader

completed_keys is JSONB and the checkpoint loader runs
jsonb_array_elements_text over it. A non-array (scalar) value makes that
throw "cannot extract elements from a scalar", which takes down the whole
UNION load — including the valid op_checkpoint_paths child rows — and loses
all checkpoint progress for that key. No current writer produces a scalar,
but an older binary / external script / future bug could.

Make the corruption class structurally impossible and self-healing:

- migration v119: LOCK TABLE (so an out-of-band scalar can't land between
  repair and constrain; no-op on single-connection PGLite), repair any
  pre-existing scalar to '[]' (op_checkpoint_paths child rows are the
  append-only source of truth, so the reset loses nothing), then add the
  named CHECK (jsonb_typeof(completed_keys) = 'array') via a pg_constraint
  IF NOT EXISTS guard. A DB-enforced always-on guard — the correct pattern
  vs a migration verify-hook, which never runs on already-stamped brains.
- schema.sql + pglite-schema.ts (+ regenerated schema-embedded.ts) ship the
  same NAMED inline CHECK so fresh installs match migrated brains and v119
  skips the duplicate.
- op-checkpoint.ts loader: gate the legacy arm on jsonb_typeof = 'array' so
  a scalar parent is skipped (children still load) instead of throwing the
  whole union, and log a specific corruption warning when one is seen.
- tests: CHECK rejects a scalar (exactly one constraint, no blob+migration
  dupe); loader survives a scalar parent and returns the children; v119
  repair converts a scalar to '[]'.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(doctor): report actively-running sync via live lock, not stale freshness

A slow source that makes partial progress every cycle but never fully
completes used to read as permanently "stale" / "never synced" because
last_sync_at only advances on a full successful sync. The naive fix
(treat recent checkpoint banking as "in progress") is unsafe: a blocked
sync banks the good files then writes no anchor, so banking can't tell
in-progress from wedged.

Use the only honest signal: a LIVE, non-expired per-source sync lock
(inspectLock + syncLockId against gbrain_cycle_locks). Every non-skipLock
sync holds it and refreshes it; a blocked/failed sync's process has exited
(no lock row) and a wedged holder stops refreshing (TTL lapses), so either
correctly falls through to the stale path and is NEVER masked. An
actively-syncing source (including a never-synced source doing its first
sync) counts as synced_recently, preserving the pinned 3-bucket invariant.
The lock lookup reuses doctor's existing dynamic db-lock import and swallows
any throw (stub engine, pre-lock-table brain) to false, so it can only ADD
an in-progress verdict, never suppress a real stale one.

Tests (real PGLiteEngine + real lock rows): stale+no-lock -> fail;
stale+live-lock -> ok; never-synced+live-lock -> ok; never-synced+no-lock
-> fail; expired-TTL lock -> fail (wedged not masked); blocked source with
banked checkpoint rows but no lock -> still fail.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(sync): honest --force-break-lock diagnostic when no lock is held

--force-break-lock used to emit the same terse "Lock ... is not held
(nothing to break)" line and exit 0 even when a sync was genuinely wedged,
sending the operator down a dead end — the wedge was not a held lock. Keep
rc=0 (breaking a non-existent lock is idempotently successful; flipping the
exit code would break automation), but under --force say plainly that
nothing was broken and point at the real next step (gbrain sync / gbrain
doctor) plus a `wedge_hint` field in --json output. The non-force path is
byte-for-byte unchanged.

runBreakLock is exported for the test. Tests: force+no-lock -> wedge_hint
JSON + human hint, rc 0; non-force+no-lock -> unchanged terse line, no hint.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(doctor): surface the in-progress sync holder in the freshness message

Plan-completion follow-up to the BUG 4 live-lock signal: when a source is
actively syncing, name the holder (pid + host) in the check message instead
of silently folding it into synced_recently. The note is appended only when
something is in progress, so steady-state messages stay byte-for-byte
unchanged (the pinned exact-message + 3-bucket-invariant tests still pass).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(sync): pre-landing review fixes — monotonic clock seed, scoped CHECK guard

Adversarial (codex) review of the implementation diff caught three:

- P1 (correctness): the fresh-schema setval was not monotonic. initSchema
  replays the schema blob, and the unconditional setval(MAX(generation))
  could move page_generation_clock_seq.last_value BACKWARD on an
  already-upgraded brain, letting a stored query_cache bookmark serve stale
  rows. Seed via GREATEST over the sequence's OWN last_value (+ old table
  value + MAX(generation)) in all 3 fresh schemas and migration v118, so a
  replay is idempotent — mirrors the old table's ON CONFLICT DO NOTHING.
  Pinned by a new monotonic regression test.
- P2: v119's CHECK-exists guard keyed on conname only (not globally unique).
  Scope it to conrelid = 'op_checkpoints'::regclass.
- P3: in-progress note ran into the prior sentence in fail/warn doctor
  messages; separate it with '. '.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* test: make Anthropic/ZE no-key tests hermetic against a dev config key

These "no key" tests cleared only ANTHROPIC_API_KEY / ZEROENTROPY_API_KEY
from the env, but hasAnthropicKey() and checkZeEmbeddingHealth() also read
the key from ~/.gbrain/config.json. On a dev machine whose real config holds
a key, the no-key assertions flipped and the tests failed locally (they
passed only in key-less CI). Add a shared with-env emptyHome() helper and
point GBRAIN_HOME at an empty dir in every no-key path so loadConfig finds
nothing — matching the already-hermetic anthropic-key / gateway-probe tests.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* chore: bump version and changelog (v0.44.1.0)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* docs(key-files): sync doctor + op-checkpoint entries to v0.44.1.0 truth

checkSyncFreshness now reports an actively-running sync via the live
per-source lock (names holder pid+host, counts as synced_recently) instead
of flagging it stale; loadOpCheckpoint gates the legacy union arm on
jsonb_typeof = 'array' so a scalar parent can't take down the whole load,
and migration v119's CHECK constraint makes the corruption class
structurally impossible. Reference docs describe current behavior only —
both entries updated in place, no release-clause appends. Guard + llms
freshness test green.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* chore: re-version to v0.42.51.0 (natural next-off-master)

Maintainer override of the queue allocator's leap to 0.44.1.0 (it jumped past
in-flight sibling PR claims at 0.42.50/0.43.0/0.44.0). Take the natural next
slot in the 0.42.x line above the immediate sibling claim (0.42.50.0); a
merge re-bump resolves any collision if a cathedral PR lands first.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* ci(e2e): bound + retry the OpenClaw install so a transient npm hang can't burn the Tier 2 budget

The Tier 2 (LLM Skills) job failed at 30m16s — the `npm install -g
openclaw@2026.4.9` step hung on a transient npm/registry stall (orphan
`npm install openclaw` was still running at cancel time) and consumed the
entire 30m job budget that v0.42.50.0 (#2254) introduced. The install
normally finishes in under a minute (Tier 2 is ~4m end to end on master),
so this is flaky-install infra, not a test failure.

Wrap the install in `timeout 120` + a 3-attempt retry loop with an 8-minute
step backstop: a hung attempt is killed in 2 min and retried instead of
eating the whole job. Same bound-the-hang philosophy as #2254's job timeouts.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-17 14:02:47 -07:00

130 lines
4.5 KiB
TypeScript

/**
* v0.41.16.0 — LLM fallback unit tests.
*
* Hermetic via the `chatTransport` test seam.
*
* Pins:
* - Happy path: parses LLM-returned JSON array
* - Adversarial input: LLM returns [] → parser returns [] (skip page)
* - Malformed LLM output → fail-open null
* - Provider unavailable → null
* - Cache hit: doesn't re-call
*/
import { describe, expect, test, beforeEach } from 'bun:test';
import { withEnv, emptyHome } from '../helpers/with-env.ts';
import { runLlmFallback } from '../../src/core/conversation-parser/llm-fallback.ts';
import { _resetLlmCacheForTests } from '../../src/core/conversation-parser/llm-base.ts';
import { makeChatResult } from './helpers.ts';
beforeEach(() => {
_resetLlmCacheForTests();
});
describe('runLlmFallback', () => {
test('happy path: parses LLM JSON output', async () => {
await withEnv({ ANTHROPIC_API_KEY: 'sk-test' }, async () => {
const result = await runLlmFallback({
modelStr: 'claude-haiku-4-5',
body: 'some-novel-chat-format',
chatTransport: async () =>
makeChatResult(
JSON.stringify([
{ speaker: 'Alice', timestamp: '2024-03-15T18:37:00Z', text: 'hello' },
{ speaker: 'Bob', timestamp: '2024-03-15T18:38:00Z', text: 'world' },
]),
{ input_tokens: 10, output_tokens: 30 },
),
});
expect(result).not.toBeNull();
expect(result).toHaveLength(2);
expect(result![0].speaker).toBe('Alice');
expect(result![1].text).toBe('world');
});
});
test('adversarial input: LLM returns [] → empty array', async () => {
await withEnv({ ANTHROPIC_API_KEY: 'sk-test' }, async () => {
const result = await runLlmFallback({
modelStr: 'claude-haiku-4-5',
body: 'This is just a recipe for cookies. Not a chat log.',
chatTransport: async () => makeChatResult('[]', { input_tokens: 10, output_tokens: 1 }),
});
expect(result).toEqual([]);
});
});
test('malformed output → fail-open null', async () => {
await withEnv({ ANTHROPIC_API_KEY: 'sk-test' }, async () => {
const result = await runLlmFallback({
modelStr: 'claude-haiku-4-5',
body: 'something',
chatTransport: async () =>
makeChatResult(
'I think this might be a chat log but I am not sure.',
{ input_tokens: 10, output_tokens: 12 },
),
});
expect(result).toBeNull();
});
});
test('provider unavailable: returns null without calling transport', async () => {
await withEnv(
{ ANTHROPIC_API_KEY: undefined as unknown as string, GBRAIN_HOME: emptyHome() },
async () => {
let calls = 0;
const result = await runLlmFallback({
modelStr: 'claude-haiku-4-5',
body: 'whatever',
chatTransport: async () => {
calls++;
return makeChatResult('[]', { input_tokens: 1, output_tokens: 1 });
},
});
expect(result).toBeNull();
expect(calls).toBe(0);
},
);
});
test('cache hit: second call doesnt re-invoke transport', async () => {
await withEnv({ ANTHROPIC_API_KEY: 'sk-test' }, async () => {
let calls = 0;
const opts = {
modelStr: 'claude-haiku-4-5',
body: 'stable-body-for-cache',
chatTransport: async () => {
calls++;
return makeChatResult('[{"speaker":"A","timestamp":"2024-01-01T00:00:00Z","text":"x"}]', { input_tokens: 1, output_tokens: 1 });
},
};
await runLlmFallback(opts);
await runLlmFallback(opts);
expect(calls).toBe(1);
});
});
test('strips invalid items from array', async () => {
await withEnv({ ANTHROPIC_API_KEY: 'sk-test' }, async () => {
const result = await runLlmFallback({
modelStr: 'claude-haiku-4-5',
body: 'something',
chatTransport: async () =>
makeChatResult(
JSON.stringify([
{ speaker: 'Alice', timestamp: '2024-03-15T18:37:00Z', text: 'good' },
{ speaker: 42, timestamp: 'x', text: 'bad shape' }, // speaker not string
{ timestamp: '2024-03-15T18:38:00Z', text: 'missing speaker' },
{ speaker: 'Bob', timestamp: '2024-03-15T18:39:00Z', text: 'good2' },
]),
{ input_tokens: 10, output_tokens: 30 },
),
});
expect(result).toHaveLength(2);
expect(result![0].speaker).toBe('Alice');
expect(result![1].speaker).toBe('Bob');
});
});
});