GitNexus/gitnexus/test/unit/embeddings-sync-command.test.ts
Gergő Magyar 7bbaf6b73b
fix(review): fail closed on foreign embedding identity and vector-width drift (#3260)
Applied from a ce-code-review pass over this branch (run 20260911-053832-b49f88d6).

- `embeddings sync` now gates EVERY checkpoint kind on embedding identity.
  `unverified-count` was exempted, but `decideEmbeddingResume` abandons that
  kind before it compares identity, so the exemption was the only thing
  keeping a foreign model from filling holes beside the old model's vectors —
  two vector spaces in one CodeEmbedding table, reported healthy. The test
  that asserted this run succeeds now asserts the refusal.

- `embeddings sync` refuses when the index's recorded vector width differs
  from this run's. The column is FLOAT[N] fixed at build time and the pipeline
  deletes each batch's stale rows immediately before inserting, so a width
  change deleted rows it could not re-insert. `analyze` already forces a
  rebuild on the same mismatch; only a rebuild can retype the column.

- `GITNEXUS_EMBEDDING_RETRY_TIMEOUTS` parses with the repo's truthy convention
  (`1`/`true`/`yes`). The integer parser threw on `true`, so the conventional
  spelling hard-failed every embedding call rather than enabling the flag or
  leaving it off. README names the accepted spellings.

- One `persistMeta` write path replaces three inlined metadata
  read-modify-writes; #2790 traced two production drifts to hand-copied
  writers of these exact fields.

- Tests: the pipeline mock now invokes `onCheckpointWindowStart`/`onCheckpoint`,
  so the resume contract actually executes under test. Added coverage for the
  incomplete-index refusal, the partial-checkpoint branch, and the body-read
  timeout retry site that the existing opt-in test never reached.

Verified: tsc --noEmit clean; 99 tests pass across the three affected suites;
prettier clean.

Co-authored-by: Gergo Magyar <gergomagyar0@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-11 07:37:08 +00:00

361 lines
12 KiB
TypeScript

/**
* Tests for `gitnexus embeddings sync` writer-safety contracts (#3065 review):
* index lock, missing-DB preflight, identity fail-closed, tri-state count,
* closeLbug masking, and hash-only cache load.
*/
import { mkdtemp, mkdir, rm, writeFile } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import path from 'node:path';
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
const {
acquireIndexLockMock,
releaseMock,
getStoragePathsMock,
loadMetaMock,
saveMetaMock,
initLbugMock,
closeLbugMock,
executeQueryMock,
executeWithReusedStatementMock,
fetchExistingEmbeddingHashesMock,
runEmbeddingPipelineMock,
resolveEmbeddingIdentityMock,
} = vi.hoisted(() => ({
acquireIndexLockMock: vi.fn(),
releaseMock: vi.fn(),
getStoragePathsMock: vi.fn(),
loadMetaMock: vi.fn(),
saveMetaMock: vi.fn(),
initLbugMock: vi.fn(),
closeLbugMock: vi.fn(),
executeQueryMock: vi.fn(),
executeWithReusedStatementMock: vi.fn(),
fetchExistingEmbeddingHashesMock: vi.fn(),
runEmbeddingPipelineMock: vi.fn(),
resolveEmbeddingIdentityMock: vi.fn(),
}));
vi.mock('../../src/storage/git.js', () => ({
getGitRoot: () => '/tmp/emb-sync-repo',
}));
vi.mock('../../src/storage/index-lock.js', () => ({
acquireIndexLock: (...args: unknown[]) => acquireIndexLockMock(...args),
}));
vi.mock('../../src/storage/repo-manager.js', () => ({
getStoragePaths: (...args: unknown[]) => getStoragePathsMock(...args),
loadMeta: (...args: unknown[]) => loadMetaMock(...args),
saveMeta: (...args: unknown[]) => saveMetaMock(...args),
}));
vi.mock('../../src/core/lbug/lbug-adapter.js', () => ({
initLbug: (...args: unknown[]) => initLbugMock(...args),
closeLbug: (...args: unknown[]) => closeLbugMock(...args),
executeQuery: (...args: unknown[]) => executeQueryMock(...args),
executeWithReusedStatement: (...args: unknown[]) => executeWithReusedStatementMock(...args),
fetchExistingEmbeddingHashes: (...args: unknown[]) => fetchExistingEmbeddingHashesMock(...args),
}));
vi.mock('../../src/core/embeddings/embedding-pipeline.js', () => ({
runEmbeddingPipeline: (...args: unknown[]) => runEmbeddingPipelineMock(...args),
}));
vi.mock('../../src/core/embeddings/embedding-identity.js', () => ({
resolveEmbeddingIdentity: () => resolveEmbeddingIdentityMock(),
}));
const IDENTITY = { model: 'test-model', dimensions: 768, provider: 'local' } as const;
const BASE_META = {
repoPath: '/tmp/emb-sync-repo',
lastCommit: 'abc123',
indexedAt: '2026-01-01T00:00:00.000Z',
stats: { embeddings: 1 },
};
const lockHandle = (release: () => void = releaseMock) => ({
record: {
v: 1 as const,
pid: 1,
hostname: 'h',
startTime: null,
token: 't',
invocationId: 'i',
acquiredAt: '',
},
release,
});
async function run(inputPath = '/tmp/emb-sync-repo') {
const { embeddingsSyncCommand } = await import('../../src/cli/embeddings-sync.js');
await embeddingsSyncCommand(inputPath);
}
describe('embeddingsSyncCommand writer safety (#3065)', () => {
const tmpDirs: string[] = [];
async function store(kind: 'file' | 'missing' | 'dir' = 'file') {
const dir = await mkdtemp(path.join(tmpdir(), 'emb-sync-'));
tmpDirs.push(dir);
const lbugPath = path.join(dir, 'lbug');
const metaPath = path.join(dir, 'gitnexus.json');
if (kind === 'file') await writeFile(lbugPath, 'db');
if (kind === 'dir') await mkdir(lbugPath);
getStoragePathsMock.mockReturnValue({ lbugPath, metaPath });
return { dir, lbugPath, metaPath };
}
beforeEach(() => {
vi.resetModules();
acquireIndexLockMock.mockReset().mockResolvedValue(lockHandle());
releaseMock.mockReset();
getStoragePathsMock.mockReset();
loadMetaMock.mockReset().mockResolvedValue({ ...BASE_META });
saveMetaMock.mockReset().mockResolvedValue(undefined);
initLbugMock.mockReset().mockResolvedValue(undefined);
closeLbugMock.mockReset().mockResolvedValue(undefined);
executeQueryMock.mockReset().mockResolvedValue([{ cnt: 2 }]);
executeWithReusedStatementMock.mockReset();
fetchExistingEmbeddingHashesMock.mockReset().mockResolvedValue(new Map([['n1', 'hash-1']]));
runEmbeddingPipelineMock.mockReset().mockResolvedValue({
nodesProcessed: 2,
chunksProcessed: 2,
failedNodeIds: [],
});
resolveEmbeddingIdentityMock.mockReset().mockReturnValue({ ...IDENTITY });
});
afterEach(async () => {
await Promise.all(tmpDirs.splice(0).map((dir) => rm(dir, { recursive: true, force: true })));
});
it('acquires the index lock before re-reading metadata and releases it in finally', async () => {
const { dir } = await store();
const order: string[] = [];
acquireIndexLockMock.mockImplementation(async () => {
order.push('lock');
return lockHandle(() => {
order.push('release');
releaseMock();
});
});
loadMetaMock.mockImplementation(async () => {
order.push('loadMeta');
return { ...BASE_META };
});
initLbugMock.mockImplementation(async () => {
order.push('init');
});
await run();
expect(acquireIndexLockMock).toHaveBeenCalledWith(dir);
expect(order[0]).toBe('lock');
expect(order.indexOf('loadMeta')).toBeGreaterThan(order.indexOf('lock'));
expect(order.indexOf('init')).toBeGreaterThan(order.indexOf('loadMeta'));
expect(order.at(-1)).toBe('release');
});
it('refuses to create a new database when the LadybugDB file is missing', async () => {
const { lbugPath } = await store('missing');
await expect(run()).rejects.toThrow(
`The LadybugDB graph store at ${lbugPath} is missing. Run gitnexus analyze first.`,
);
expect(initLbugMock).not.toHaveBeenCalled();
expect(releaseMock).toHaveBeenCalled();
});
it('refuses to open a LadybugDB path that is not a regular file', async () => {
const { lbugPath } = await store('dir');
await expect(run()).rejects.toThrow(
`The LadybugDB graph store at ${lbugPath} is not a usable database file. Run gitnexus analyze first.`,
);
expect(initLbugMock).not.toHaveBeenCalled();
expect(releaseMock).toHaveBeenCalled();
});
it('fails closed on an identity-mismatched partial checkpoint', async () => {
await store();
loadMetaMock.mockResolvedValue({
...BASE_META,
embeddingCheckpoint: {
at: '2026-01-01T00:00:00.000Z',
nodesProcessed: 1,
totalNodes: 2,
chunksProcessed: 1,
model: 'old-model',
dimensions: 768,
provider: 'local',
kind: 'partial',
pendingNodeIds: ['n2'],
},
});
resolveEmbeddingIdentityMock.mockReturnValue({
model: 'new-model',
dimensions: 768,
provider: 'http:deadbeef',
});
await expect(run()).rejects.toThrow(/Cannot sync embeddings: the index checkpoint was written/);
expect(initLbugMock).not.toHaveBeenCalled();
expect(releaseMock).toHaveBeenCalled();
});
it('fails closed on an identity-mismatched unverified-count checkpoint', async () => {
// `decideEmbeddingResume` abandons this kind before comparing identity, so
// the command's own gate is the only thing that keeps a foreign model from
// filling the remaining holes beside the old model's vectors.
await store();
loadMetaMock.mockResolvedValue({
...BASE_META,
embeddingCheckpoint: {
at: '2026-01-01T00:00:00.000Z',
nodesProcessed: 2,
totalNodes: 2,
chunksProcessed: 2,
model: 'old-model',
dimensions: 768,
provider: 'local',
kind: 'unverified-count',
pendingNodeIds: [],
},
});
resolveEmbeddingIdentityMock.mockReturnValue({
model: 'new-model',
dimensions: 768,
provider: 'http:deadbeef',
});
await expect(run()).rejects.toThrow(/Cannot sync embeddings: the index checkpoint was written/);
expect(initLbugMock).not.toHaveBeenCalled();
expect(runEmbeddingPipelineMock).not.toHaveBeenCalled();
expect(releaseMock).toHaveBeenCalled();
});
it('refuses to sync when the recorded vector width differs from this run', async () => {
await store();
loadMetaMock.mockResolvedValue({ ...BASE_META, embeddingDims: 1 });
await expect(run()).rejects.toThrow(/Cannot sync embeddings: this index stores FLOAT\[1\]/);
expect(initLbugMock).not.toHaveBeenCalled();
expect(releaseMock).toHaveBeenCalled();
});
it('refuses to sync while the structural index is incomplete', async () => {
await store();
loadMetaMock.mockResolvedValue({
...BASE_META,
incrementalInProgress: { startedAt: '2026-01-01T00:00:00.000Z', toWriteCount: 3 },
});
await expect(run()).rejects.toThrow(
'The structural index is incomplete. Run gitnexus analyze --force first.',
);
expect(initLbugMock).not.toHaveBeenCalled();
expect(saveMetaMock).not.toHaveBeenCalled();
expect(releaseMock).toHaveBeenCalled();
});
it('persists an interrupted checkpoint from the pipeline checkpoint callbacks', async () => {
// The resume contract lives in these callbacks; a mock that never invokes
// them leaves the whole save path unexecuted.
await store();
runEmbeddingPipelineMock.mockImplementation(
async (
_executeQuery: unknown,
_executeWithReusedStatement: unknown,
_onProgress: unknown,
_config: unknown,
_signal: unknown,
_existing: unknown,
options: {
onCheckpointWindowStart: (checkpoint: Record<string, unknown>) => Promise<void>;
onCheckpoint: (checkpoint: Record<string, unknown>) => Promise<void>;
},
) => {
await options.onCheckpointWindowStart({
nodeIds: ['n2', 'n3'],
nodesProcessed: 1,
totalNodes: 3,
chunksProcessed: 1,
});
await options.onCheckpoint({ nodesProcessed: 3, totalNodes: 3, chunksProcessed: 3 });
return { nodesProcessed: 3, chunksProcessed: 3, failedNodeIds: [] };
},
);
await run();
type SavedMeta = {
stats?: { embeddings?: number };
embeddingCheckpoint?: { pendingNodeIds?: string[] };
};
const windowStart = saveMetaMock.mock.calls[0]?.[1] as SavedMeta;
expect(windowStart.embeddingCheckpoint?.pendingNodeIds).toEqual(['n2', 'n3']);
// The window marker carries no count, so the last known one must survive.
expect(windowStart.stats?.embeddings).toBe(1);
const windowEnd = saveMetaMock.mock.calls[1]?.[1] as SavedMeta;
expect(windowEnd.embeddingCheckpoint?.pendingNodeIds).toEqual([]);
expect(windowEnd.stats?.embeddings).toBe(2);
});
it('keeps a partial checkpoint when some nodes failed to embed', async () => {
await store();
runEmbeddingPipelineMock.mockResolvedValue({
nodesProcessed: 2,
chunksProcessed: 2,
failedNodeIds: ['n9'],
});
await run();
const saved = saveMetaMock.mock.calls.at(-1)?.[1] as {
embeddingCheckpoint?: { pendingNodeIds?: string[] };
};
expect(saved.embeddingCheckpoint).toBeDefined();
expect(saved.embeddingCheckpoint?.pendingNodeIds).toEqual(['n9']);
});
it('does not publish a missing count cell as zero', async () => {
await store();
executeQueryMock.mockResolvedValue([{}]);
await expect(run()).rejects.toThrow('Could not verify persisted embedding count.');
expect(saveMetaMock).toHaveBeenCalledTimes(1);
const saved = saveMetaMock.mock.calls[0]?.[1] as {
stats?: { embeddings?: number };
embeddingCheckpoint?: { kind?: string; pendingNodeIds?: string[] };
};
expect(saved.stats?.embeddings).toBe(1);
expect(saved.embeddingCheckpoint?.kind).toBe('unverified-count');
expect(saved.embeddingCheckpoint?.pendingNodeIds).toEqual([]);
expect(releaseMock).toHaveBeenCalled();
});
it('keeps the pipeline error when closeLbug also rejects', async () => {
await store();
runEmbeddingPipelineMock.mockRejectedValue(new Error('pipeline boom'));
closeLbugMock.mockRejectedValue(new Error('close boom'));
await expect(run()).rejects.toThrow('pipeline boom');
expect(releaseMock).toHaveBeenCalled();
});
it('loads existing hashes without materializing cached vectors', async () => {
await store();
const hashes = new Map([
['n1', 'h1'],
['n2', 'h2'],
]);
fetchExistingEmbeddingHashesMock.mockResolvedValue(hashes);
await run();
expect(fetchExistingEmbeddingHashesMock).toHaveBeenCalledTimes(1);
const existingArg = runEmbeddingPipelineMock.mock.calls[0]?.[5];
expect(existingArg).toBe(hashes);
});
});