feat(MULTIVERSION-0001): wire trueref.json into pipeline + per-version rules

- Add migration 0003: recreate repository_configs with nullable version_id
  column and two partial unique indexes (repo-wide: version_id IS NULL,
  per-version: (repository_id, version_id) WHERE version_id IS NOT NULL)
- Update schema.ts to reflect the new composite structure with uniqueIndex
  partial constraints via drizzle-orm sql helper
- IndexingPipeline: parse trueref.json / context7.json after crawl, apply
  excludeFiles filter before diff computation, update totalFiles accordingly
- IndexingPipeline: persist repo-wide rules (version_id=null) and
  version-specific rules (when versionId set) via upsertRepoConfig helper
- Add matchesExcludePattern static helper supporting plain filename,
  glob prefix (docs/legacy*), and exact path patterns
- context endpoint: split getRules into repo-wide + version-specific lookup
  with dedup merge; pass versionId at call site
- Update test DB loaders to include migration 0003
- Add pipeline tests for excludeFiles, repo-wide rules persistence, and
  per-version rules persistence
- Add integration tests for merged rules, repo-only rules, and dedup logic

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Giancarmine Salucci
2026-03-28 10:44:30 +01:00
parent 255838dcc0
commit 666ec7d55f
7 changed files with 418 additions and 32 deletions

View File

@@ -26,7 +26,8 @@ function createTestDb(): Database.Database {
for (const migrationFile of [
'0000_large_master_chief.sql',
'0001_quick_nighthawk.sql',
'0002_silky_stellaris.sql'
'0002_silky_stellaris.sql',
'0003_multiversion_config.sql'
]) {
const migrationSql = readFileSync(join(migrationsFolder, migrationFile), 'utf-8');
@@ -771,4 +772,117 @@ describe('IndexingPipeline', () => {
ref: undefined
});
});
it('excludes files matching excludeFiles patterns from trueref.json', async () => {
const truerefConfig = JSON.stringify({
excludeFiles: ['migration-guide.md', 'docs/legacy*']
});
const files = [
{
path: 'trueref.json',
content: truerefConfig,
sha: 'sha-config',
language: 'json'
},
{
path: 'README.md',
content: '# Hello\n\nThis is documentation.',
sha: 'sha-readme',
language: 'markdown'
},
{
path: 'migration-guide.md',
content: '# Migration Guide\n\nThis should be excluded.',
sha: 'sha-migration',
language: 'markdown'
},
{
path: 'docs/legacy-api.md',
content: '# Legacy API\n\nShould be excluded by glob prefix.',
sha: 'sha-legacy',
language: 'markdown'
}
];
const pipeline = makePipeline({ files, totalFiles: files.length });
const job = makeJob();
await pipeline.run(job as never);
const docs = db
.prepare(`SELECT file_path FROM documents ORDER BY file_path`)
.all() as { file_path: string }[];
const filePaths = docs.map((d) => d.file_path);
// migration-guide.md and docs/legacy-api.md must be absent.
expect(filePaths).not.toContain('migration-guide.md');
expect(filePaths).not.toContain('docs/legacy-api.md');
// README.md must still be indexed.
expect(filePaths).toContain('README.md');
});
it('persists repo-wide rules from trueref.json to repository_configs after indexing', async () => {
const truerefConfig = JSON.stringify({
rules: ['Always use TypeScript strict mode', 'Prefer async/await over callbacks']
});
const files = [
{
path: 'trueref.json',
content: truerefConfig,
sha: 'sha-config',
language: 'json'
}
];
const pipeline = makePipeline({ files, totalFiles: files.length });
const job = makeJob();
await pipeline.run(job as never);
const row = db
.prepare(
`SELECT rules FROM repository_configs WHERE repository_id = '/test/repo' AND version_id IS NULL`
)
.get() as { rules: string } | undefined;
expect(row).toBeDefined();
const rules = JSON.parse(row!.rules);
expect(rules).toEqual(['Always use TypeScript strict mode', 'Prefer async/await over callbacks']);
});
it('persists version-specific rules under (repositoryId, versionId) when job has versionId', async () => {
const versionId = insertVersion(db, { tag: 'v2.0.0', state: 'pending' });
const truerefConfig = JSON.stringify({
rules: ['This is v2. Use the new Builder API.']
});
const files = [
{
path: 'trueref.json',
content: truerefConfig,
sha: 'sha-config',
language: 'json'
}
];
const pipeline = makePipeline({ files, totalFiles: files.length });
const job = makeJob('/test/repo', versionId);
await pipeline.run(job as never);
// Repo-wide row (version_id IS NULL) must exist.
const repoRow = db
.prepare(
`SELECT rules FROM repository_configs WHERE repository_id = '/test/repo' AND version_id IS NULL`
)
.get() as { rules: string } | undefined;
expect(repoRow).toBeDefined();
// Version-specific row must also exist.
const versionRow = db
.prepare(
`SELECT rules FROM repository_configs WHERE repository_id = '/test/repo' AND version_id = ?`
)
.get(versionId) as { rules: string } | undefined;
expect(versionRow).toBeDefined();
const rules = JSON.parse(versionRow!.rules);
expect(rules).toEqual(['This is v2. Use the new Builder API.']);
});
});