fix(MULTIVERSION-0001): prevent version jobs from overwriting repo-wide NULL rules entry

Version jobs now write rules only to the version-specific (repo, versionId)
row. Previously every version job unconditionally wrote to the (repo, NULL)
row as well, causing whichever version indexed last to contaminate the
repo-wide rules that the context API merges into every query response.

Adds a regression test (Bug5b) that indexes the main branch, then indexes a
version with different rules, and asserts the NULL row still holds the
main-branch rules.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Giancarmine Salucci
2026-03-29 01:15:58 +01:00
parent cd4ea7112c
commit bbc67f8064
2 changed files with 75 additions and 7 deletions

View File

@@ -869,15 +869,17 @@ describe('IndexingPipeline', () => {
await pipeline.run(job as never);
// Repo-wide row (version_id IS NULL) must exist.
// Repo-wide row (version_id IS NULL) must NOT be written by a version job —
// writing it here would contaminate the NULL entry with version-specific rules
// (Bug 5b regression guard).
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();
expect(repoRow).toBeUndefined();
// Version-specific row must also exist.
// Version-specific row must exist with the correct rules.
const versionRow = db
.prepare(
`SELECT rules FROM repository_configs WHERE repository_id = '/test/repo' AND version_id = ?`
@@ -888,6 +890,69 @@ describe('IndexingPipeline', () => {
expect(rules).toEqual(['This is v2. Use the new Builder API.']);
});
it('regression(Bug5b): version job does not overwrite the repo-wide NULL rules entry', async () => {
// Arrange: index the main branch first to establish a repo-wide rules entry.
const mainBranchRules = ['Always use TypeScript strict mode.'];
const mainPipeline = makePipeline({
files: [
{
path: 'trueref.json',
content: JSON.stringify({ rules: mainBranchRules }),
sha: 'sha-main-config',
language: 'json'
}
],
totalFiles: 1
});
const mainJob = makeJob('/test/repo'); // no versionId → main-branch job
await mainPipeline.run(mainJob as never);
// Confirm the repo-wide entry was written.
const afterMain = db
.prepare(
`SELECT rules FROM repository_configs WHERE repository_id = '/test/repo' AND version_id IS NULL`
)
.get() as { rules: string } | undefined;
expect(afterMain).toBeDefined();
expect(JSON.parse(afterMain!.rules)).toEqual(mainBranchRules);
// Act: index a version with different rules.
const versionId = insertVersion(db, { tag: 'v3.0.0', state: 'pending' });
const versionRules = ['v3 only: use the streaming API.'];
const versionPipeline = makePipeline({
files: [
{
path: 'trueref.json',
content: JSON.stringify({ rules: versionRules }),
sha: 'sha-v3-config',
language: 'json'
}
],
totalFiles: 1
});
const versionJob = makeJob('/test/repo', versionId);
await versionPipeline.run(versionJob as never);
// Assert: the repo-wide NULL entry must still contain the main-branch rules,
// not the version-specific ones.
const afterVersion = db
.prepare(
`SELECT rules FROM repository_configs WHERE repository_id = '/test/repo' AND version_id IS NULL`
)
.get() as { rules: string } | undefined;
expect(afterVersion).toBeDefined();
expect(JSON.parse(afterVersion!.rules)).toEqual(mainBranchRules);
// And the version-specific row must contain the version rules.
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();
expect(JSON.parse(versionRow!.rules)).toEqual(versionRules);
});
it('persists rules from CrawlResult.config even when trueref.json is absent from files (folders allowlist bug)', async () => {
// Regression test for MULTIVERSION-0001:
// When trueref.json specifies a `folders` allowlist (e.g. ["src/"]),