mirror of
https://github.com/abhigyanpatwari/GitNexus.git
synced 2026-09-21 00:21:30 +00:00
* Initial plan * fix(analyze): add WAL auto-checkpoint CLI control and default-off behavior * test(analyze): share lbug auto-checkpoint parsing and align validation * fix(analyze): always enable lbug auto-checkpoint and expose threshold control * refactor(lbug): inline always-on auto-checkpoint constructor arg * fix(analyze): guide checkpoint-threshold on Ladybug WAL checkpoint IO failures * test(analyze): cover checkpoint IO guidance and add integration guard * fix(analyze): tighten checkpoint IO detection and remove test hook * fix(analyze): remove checkpoint test hook and tighten error matching * fix(analyze): rename to wal-checkpoint-threshold, raise default, add manual checkpoint driver with retry Address review feedback on PR #1772: - Rename CLI flag, env var, AnalyzeOptions field, recovery-hint tag, and parser/constants from lbug-* to engine-neutral wal-* (matches the existing WAL_RECOVERY_SUGGESTION / isWalCorruptionError convention). - Raise default threshold from -1 (Ladybug stock ~16 MiB) to 64 MiB so users on the default config no longer hit the original rename/remove race. - Align both READMEs to publish 67108864 (64 MiB) instead of 65536 (which would have made the crash more frequent). - Add wal-checkpoint-driver.ts: a periodic manual CHECKPOINT driver wrapped in a 3-attempt jittered retry (50/200/500 ms), driven from runFullAnalysis. Opt-out via GITNEXUS_WAL_MANUAL_CHECKPOINT=0. Moves the race window into a JS-controllable retry surface while keeping native auto-checkpoint on. - Move LBUG_CHECKPOINT_RENAME_RE / REMOVE_RE plus the predicate (renamed to isLbugCheckpointIoError) into lbug-config.ts alongside isWalCorruptionError. Predicate is now exported. Add a permissive fallback matcher and pin the matched Ladybug version in comments. - Warn instead of silently defaulting when GITNEXUS_WAL_CHECKPOINT_THRESHOLD is set to a non-empty unparseable value (closes the CLI-vs-env asymmetry). - Add a typed RecoveryHint string-literal union in cli-message.ts so future hint tags can't drift. - Add a real integration test under test/integration/ that triggers a Ladybug checkpoint IO failure via a pre-existing directory at the rename target (portable across platforms; no test-only injection hook). - Add small-disk / CI caveat (32 MiB secondary suggestion) to the recovery hint and README env-var rows. - Document CLI/env precedence in the analyze --help block. - Help placeholder: <value> -> <bytes>. - Rename analyze-lbug-auto-checkpoint.test.ts to use the new wal-* token. * chore(lbug): remove dead jitteredDelay helper and apply prettier - Drop unused `jitteredDelay` function flagged by CodeQL in PR #1772; the retry loop already inlines the same calculation with the injectable `randomImpl` so the helper was dead. Move the non-cryptographic-by-design comment next to the actual jitter site. - Apply `prettier --write` to wal-checkpoint-driver.ts and the new integration test to absorb the PR autofix bot's formatting findings. --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: Gergő Magyar <gergomagyar@icloud.com> Co-authored-by: Test <test@example.com>
215 lines
7.6 KiB
TypeScript
215 lines
7.6 KiB
TypeScript
/**
|
|
* Tests for WAL corruption error handling in the `analyzeCommand` CLI.
|
|
*
|
|
* Before this fix, a WAL corruption error surfaced as a raw stack-trace dump.
|
|
* After the fix, it is caught before the generic error path and rendered as
|
|
* a clean, actionable message telling the user to run `gitnexus analyze --force`.
|
|
*
|
|
* Mirrors the test shape of analyze-worker-timeout.test.ts:
|
|
* - vi.mock the heavy dependencies so no real DB / git is touched
|
|
* - drive `analyzeCommand` with a mocked `runFullAnalysis` that throws
|
|
* - assert on process.exitCode and the logged output
|
|
*/
|
|
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
|
|
|
const runFullAnalysisMock = vi.fn();
|
|
|
|
vi.mock('../../src/core/run-analyze.js', () => ({
|
|
runFullAnalysis: runFullAnalysisMock,
|
|
}));
|
|
|
|
vi.mock('../../src/core/lbug/lbug-adapter.js', () => ({
|
|
closeLbug: vi.fn(async () => undefined),
|
|
}));
|
|
|
|
vi.mock('../../src/storage/repo-manager.js', () => ({
|
|
getStoragePaths: vi.fn(() => ({ storagePath: '.gitnexus', lbugPath: '.gitnexus/lbug' })),
|
|
getGlobalRegistryPath: vi.fn(() => 'registry.json'),
|
|
RegistryNameCollisionError: class RegistryNameCollisionError extends Error {},
|
|
AnalysisNotFinalizedError: class AnalysisNotFinalizedError extends Error {},
|
|
assertAnalysisFinalized: vi.fn(async () => undefined),
|
|
}));
|
|
|
|
vi.mock('../../src/storage/git.js', () => ({
|
|
getGitRoot: vi.fn(() => '/repo'),
|
|
hasGitDir: vi.fn(() => true),
|
|
}));
|
|
|
|
vi.mock('../../src/core/ingestion/utils/max-file-size.js', () => ({
|
|
getMaxFileSizeBannerMessage: vi.fn(() => null),
|
|
}));
|
|
|
|
// analyze.ts imports isHfDownloadFailure from hf-env.js, which in turn imports
|
|
// from gitnexus-shared (not linked in dev). Mock the module to break the chain.
|
|
vi.mock('../../src/core/embeddings/hf-env.js', () => ({
|
|
isHfDownloadFailure: vi.fn(() => false),
|
|
}));
|
|
|
|
// ─── Tests ───────────────────────────────────────────────────────────────────
|
|
|
|
describe('analyzeCommand WAL corruption error handling', () => {
|
|
beforeEach(() => {
|
|
vi.resetModules();
|
|
runFullAnalysisMock.mockReset();
|
|
process.exitCode = undefined;
|
|
// Ensure ensureHeap() short-circuits (heap already at target size)
|
|
process.env.NODE_OPTIONS = `${process.env.NODE_OPTIONS ?? ''} --max-old-space-size=8192`.trim();
|
|
});
|
|
|
|
it('surfaces a clean recovery message on a re-wrapped WAL corruption error', async () => {
|
|
// This error shape is what lbug-adapter throws after detecting WAL corruption
|
|
// in doInitLbug and re-wrapping it with the recovery suggestion.
|
|
const walError = new Error(
|
|
'LadybugDB WAL corruption detected at /repo/.gitnexus/lbug. ' +
|
|
'Run `gitnexus analyze` to rebuild the index.\n' +
|
|
' Original error: Runtime exception: Corrupted wal file.',
|
|
);
|
|
runFullAnalysisMock.mockRejectedValue(walError);
|
|
|
|
const { _captureLogger } = await import('../../src/core/logger.js');
|
|
const cap = _captureLogger();
|
|
const { analyzeCommand } = await import('../../src/cli/analyze.js');
|
|
|
|
await analyzeCommand(undefined, {});
|
|
|
|
expect(process.exitCode).toBe(1);
|
|
|
|
const records = cap.records();
|
|
const walRecord = records.find(
|
|
(r) => typeof r.msg === 'string' && r.msg.includes('gitnexus analyze --force'),
|
|
);
|
|
expect(walRecord).toBeDefined();
|
|
|
|
// Raw stack trace must NOT appear via cliError
|
|
const stackRecord = records.find(
|
|
(r) => typeof r.msg === 'string' && r.msg.includes('at analyzeCommand'),
|
|
);
|
|
expect(stackRecord).toBeUndefined();
|
|
|
|
cap.restore();
|
|
});
|
|
|
|
it('surfaces a clean recovery message when the native WAL error fires directly', async () => {
|
|
// isWalCorruptionError fires on the native engine message before re-wrapping.
|
|
const nativeWalError = new Error(
|
|
'Runtime exception: Corrupted wal file. Read out invalid WAL record type.',
|
|
);
|
|
runFullAnalysisMock.mockRejectedValue(nativeWalError);
|
|
|
|
const { _captureLogger } = await import('../../src/core/logger.js');
|
|
const cap = _captureLogger();
|
|
const { analyzeCommand } = await import('../../src/cli/analyze.js');
|
|
|
|
await analyzeCommand(undefined, {});
|
|
|
|
expect(process.exitCode).toBe(1);
|
|
|
|
const records = cap.records();
|
|
const walRecord = records.find(
|
|
(r) => typeof r.msg === 'string' && r.msg.includes('gitnexus analyze --force'),
|
|
);
|
|
expect(walRecord).toBeDefined();
|
|
|
|
cap.restore();
|
|
});
|
|
|
|
it('does NOT route non-WAL errors through the WAL handler', async () => {
|
|
const genericError = new Error('Some unexpected failure unrelated to WAL');
|
|
runFullAnalysisMock.mockRejectedValue(genericError);
|
|
|
|
const { _captureLogger } = await import('../../src/core/logger.js');
|
|
const cap = _captureLogger();
|
|
const { analyzeCommand } = await import('../../src/cli/analyze.js');
|
|
|
|
await analyzeCommand(undefined, {});
|
|
|
|
expect(process.exitCode).toBe(1);
|
|
|
|
// The WAL recovery message must NOT appear for unrelated errors
|
|
const records = cap.records();
|
|
const walRecord = records.find(
|
|
(r) => typeof r.msg === 'string' && r.msg.includes('gitnexus analyze --force'),
|
|
);
|
|
expect(walRecord).toBeUndefined();
|
|
|
|
cap.restore();
|
|
});
|
|
|
|
it('recommends --wal-checkpoint-threshold on Ladybug checkpoint I/O failures', async () => {
|
|
runFullAnalysisMock.mockRejectedValue(
|
|
new Error(
|
|
'Runtime exception: IO exception: Error renaming file /repo/.gitnexus/lbug.wal to /repo/.gitnexus/lbug.wal.checkpoint. ErrorMessage: Permission denied',
|
|
),
|
|
);
|
|
|
|
const { _captureLogger } = await import('../../src/core/logger.js');
|
|
const cap = _captureLogger();
|
|
const { analyzeCommand } = await import('../../src/cli/analyze.js');
|
|
|
|
await analyzeCommand(undefined, {});
|
|
|
|
expect(process.exitCode).toBe(1);
|
|
const records = cap.records();
|
|
expect(
|
|
records.some(
|
|
(r) =>
|
|
typeof r.msg === 'string' &&
|
|
r.msg.includes('gitnexus analyze --wal-checkpoint-threshold'),
|
|
),
|
|
).toBe(true);
|
|
|
|
cap.restore();
|
|
});
|
|
|
|
it('also recommends threshold on .wal.checkpoint remove failures', async () => {
|
|
runFullAnalysisMock.mockRejectedValue(
|
|
new Error(
|
|
'Runtime exception: IO exception: Error removing directory or file /repo/.gitnexus/lbug.wal.checkpoint. Error Message: Permission denied',
|
|
),
|
|
);
|
|
|
|
const { _captureLogger } = await import('../../src/core/logger.js');
|
|
const cap = _captureLogger();
|
|
const { analyzeCommand } = await import('../../src/cli/analyze.js');
|
|
|
|
await analyzeCommand(undefined, {});
|
|
|
|
expect(process.exitCode).toBe(1);
|
|
const records = cap.records();
|
|
expect(
|
|
records.some(
|
|
(r) =>
|
|
typeof r.msg === 'string' &&
|
|
r.msg.includes('gitnexus analyze --wal-checkpoint-threshold'),
|
|
),
|
|
).toBe(true);
|
|
|
|
cap.restore();
|
|
});
|
|
|
|
it('does not recommend threshold for non-checkpoint IO exceptions', async () => {
|
|
runFullAnalysisMock.mockRejectedValue(
|
|
new Error(
|
|
'Runtime exception: IO exception: Error renaming file /repo/.gitnexus/data.tmp to /repo/.gitnexus/data.tmp.bak. ErrorMessage: Permission denied',
|
|
),
|
|
);
|
|
|
|
const { _captureLogger } = await import('../../src/core/logger.js');
|
|
const cap = _captureLogger();
|
|
const { analyzeCommand } = await import('../../src/cli/analyze.js');
|
|
|
|
await analyzeCommand(undefined, {});
|
|
|
|
expect(process.exitCode).toBe(1);
|
|
const records = cap.records();
|
|
expect(
|
|
records.some(
|
|
(r) =>
|
|
typeof r.msg === 'string' &&
|
|
r.msg.includes('gitnexus analyze --wal-checkpoint-threshold'),
|
|
),
|
|
).toBe(false);
|
|
|
|
cap.restore();
|
|
});
|
|
});
|