feat(TRUEREF-0021): implement differential tag indexing

This commit is contained in:
U811073
2026-03-30 13:12:50 +02:00
committed by Giancarmine Salucci
parent e63279fcf6
commit f4fe8c6043
10 changed files with 1281 additions and 9 deletions

View File

@@ -13,6 +13,7 @@ import { JobQueue } from './job-queue.js';
import { IndexingPipeline } from './indexing.pipeline.js';
import { recoverStaleJobs } from './startup.js';
import { EmbeddingService } from '$lib/server/embeddings/embedding.service.js';
import * as diffStrategy from './differential-strategy.js';
// ---------------------------------------------------------------------------
// Test DB factory
@@ -1019,3 +1020,290 @@ describe('IndexingPipeline', () => {
expect(rules).toEqual(['v3: use the streaming API.']);
});
});
// ---------------------------------------------------------------------------
// differential indexing
// ---------------------------------------------------------------------------
describe('differential indexing', () => {
let db: Database.Database;
beforeEach(() => {
db = createTestDb();
insertRepo(db, { source: 'local', source_url: '/tmp/test-repo' });
});
function insertDocument(
localDb: Database.Database,
overrides: Partial<Record<string, unknown>> = {}
): string {
const id = crypto.randomUUID();
localDb
.prepare(
`INSERT INTO documents (id, repository_id, version_id, file_path, title, language, token_count, checksum, indexed_at)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)`
)
.run(
(overrides.id as string) ?? id,
(overrides.repository_id as string) ?? '/test/repo',
(overrides.version_id as string | null) ?? null,
(overrides.file_path as string) ?? 'README.md',
null,
'markdown',
100,
(overrides.checksum as string) ?? 'abc123',
Math.floor(Date.now() / 1000)
);
return (overrides.id as string) ?? id;
}
function insertSnippet(
localDb: Database.Database,
documentId: string,
overrides: Partial<Record<string, unknown>> = {}
): string {
const id = crypto.randomUUID();
localDb
.prepare(
`INSERT INTO snippets (id, document_id, repository_id, version_id, type, title, content, language, breadcrumb, token_count, created_at)
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)`
)
.run(
(overrides.id as string) ?? id,
documentId,
(overrides.repository_id as string) ?? '/test/repo',
(overrides.version_id as string | null) ?? null,
'info',
null,
'content',
'markdown',
null,
10,
Math.floor(Date.now() / 1000)
);
return (overrides.id as string) ?? id;
}
type PipelineInternals = IndexingPipeline & {
cloneFromAncestor: (
ancestorVersionId: string,
targetVersionId: string,
repositoryId: string,
unchangedPaths: Set<string>
) => void;
};
it('cloneFromAncestor inserts documents and snippets into the target version', () => {
const ancestorVersionId = insertVersion(db, { tag: 'v1.0.0', state: 'indexed' });
const targetVersionId = insertVersion(db, { tag: 'v1.1.0', state: 'pending' });
const doc1Id = insertDocument(db, {
repository_id: '/test/repo',
version_id: ancestorVersionId,
file_path: 'README.md',
checksum: 'sha-readme'
});
const doc2Id = insertDocument(db, {
repository_id: '/test/repo',
version_id: ancestorVersionId,
file_path: 'src/index.ts',
checksum: 'sha-index'
});
insertSnippet(db, doc1Id, { repository_id: '/test/repo', version_id: ancestorVersionId });
insertSnippet(db, doc2Id, { repository_id: '/test/repo', version_id: ancestorVersionId });
const pipeline = new IndexingPipeline(
db,
vi.fn() as never,
{ crawl: vi.fn() } as never,
null
);
(pipeline as unknown as PipelineInternals).cloneFromAncestor(
ancestorVersionId,
targetVersionId,
'/test/repo',
new Set(['README.md', 'src/index.ts'])
);
const targetDocs = db
.prepare(`SELECT * FROM documents WHERE version_id = ?`)
.all(targetVersionId) as { id: string; file_path: string }[];
expect(targetDocs).toHaveLength(2);
expect(targetDocs.map((d) => d.file_path).sort()).toEqual(
['README.md', 'src/index.ts'].sort()
);
// New IDs must differ from ancestor doc IDs.
const targetDocIds = targetDocs.map((d) => d.id);
expect(targetDocIds).not.toContain(doc1Id);
expect(targetDocIds).not.toContain(doc2Id);
const targetSnippets = db
.prepare(`SELECT * FROM snippets WHERE version_id = ?`)
.all(targetVersionId) as { id: string }[];
expect(targetSnippets).toHaveLength(2);
});
it('cloneFromAncestor silently skips paths absent from the ancestor', () => {
const ancestorVersionId = insertVersion(db, { tag: 'v1.0.0', state: 'indexed' });
const targetVersionId = insertVersion(db, { tag: 'v1.1.0', state: 'pending' });
insertDocument(db, {
repository_id: '/test/repo',
version_id: ancestorVersionId,
file_path: 'src/main.ts',
checksum: 'sha-main'
});
const pipeline = new IndexingPipeline(
db,
vi.fn() as never,
{ crawl: vi.fn() } as never,
null
);
(pipeline as unknown as PipelineInternals).cloneFromAncestor(
ancestorVersionId,
targetVersionId,
'/test/repo',
new Set(['src/main.ts', 'MISSING.md'])
);
const targetDocs = db
.prepare(`SELECT * FROM documents WHERE version_id = ?`)
.all(targetVersionId) as { id: string; file_path: string }[];
expect(targetDocs).toHaveLength(1);
expect(targetDocs[0].file_path).toBe('src/main.ts');
});
it('falls back to full crawl when no indexed ancestor exists', async () => {
const targetVersionId = insertVersion(db, { tag: 'v1.0.0', state: 'pending' });
const files = [
{
path: 'README.md',
content: '# Hello\n\nThis is documentation.',
sha: 'sha-readme',
language: 'markdown'
},
{
path: 'src/index.ts',
content: 'export const x = 1;',
sha: 'sha-index',
language: 'typescript'
}
];
const mockLocalCrawl = vi.fn().mockResolvedValue({
files,
totalFiles: 2,
skippedFiles: 0,
branch: 'main',
commitSha: 'abc'
});
const pipeline = new IndexingPipeline(
db,
vi.fn() as never,
{ crawl: mockLocalCrawl } as never,
null
);
const jobId = insertJob(db, {
repository_id: '/test/repo',
version_id: targetVersionId,
status: 'queued'
});
const job = db.prepare(`SELECT * FROM indexing_jobs WHERE id = ?`).get(jobId) as never;
await pipeline.run(job);
const updatedJob = db
.prepare(`SELECT status FROM indexing_jobs WHERE id = ?`)
.get(jobId) as { status: string };
expect(updatedJob.status).toBe('done');
const docs = db
.prepare(`SELECT * FROM documents WHERE version_id = ?`)
.all(targetVersionId) as { id: string }[];
expect(docs.length).toBeGreaterThanOrEqual(2);
});
it('cloned unchanged documents survive the diff/replace stage', async () => {
// 1. Set up ancestor and target versions.
const ancestorVersionId = insertVersion(db, { tag: 'v1.0.0', state: 'indexed' });
const targetVersionId = insertVersion(db, { tag: 'v1.1.0', state: 'pending' });
// 2. Insert ancestor doc + snippet for unchanged.md.
const ancestorDocId = insertDocument(db, {
repository_id: '/test/repo',
version_id: ancestorVersionId,
file_path: 'unchanged.md',
checksum: 'sha-unchanged'
});
insertSnippet(db, ancestorDocId, {
repository_id: '/test/repo',
version_id: ancestorVersionId
});
// 3. Crawl returns ONLY changed.md (unchanged.md is absent — differential only).
const mockLocalCrawl = vi.fn().mockResolvedValue({
files: [
{
path: 'changed.md',
content: '# Changed\n\nThis file was added.',
sha: 'sha-changed',
language: 'markdown'
}
],
totalFiles: 1,
skippedFiles: 0,
branch: 'main',
commitSha: 'abc'
});
// 4. Mock buildDifferentialPlan to return a plan with the two paths.
const mockPlan = {
ancestorVersionId,
ancestorTag: 'v1.0.0',
changedPaths: new Set(['changed.md']),
deletedPaths: new Set<string>(),
unchangedPaths: new Set(['unchanged.md'])
};
const spy = vi
.spyOn(diffStrategy, 'buildDifferentialPlan')
.mockResolvedValueOnce(mockPlan);
const pipeline = new IndexingPipeline(
db,
vi.fn() as never,
{ crawl: mockLocalCrawl } as never,
null
);
// 5. Run pipeline for the target version job.
const jobId = insertJob(db, {
repository_id: '/test/repo',
version_id: targetVersionId,
status: 'queued'
});
const job = db.prepare(`SELECT * FROM indexing_jobs WHERE id = ?`).get(jobId) as never;
await pipeline.run(job);
spy.mockRestore();
// 6. Assert job completed and both docs exist under the target version.
const finalJob = db
.prepare(`SELECT status FROM indexing_jobs WHERE id = ?`)
.get(jobId) as { status: string };
expect(finalJob.status).toBe('done');
const targetDocs = db
.prepare(`SELECT file_path FROM documents WHERE version_id = ?`)
.all(targetVersionId) as { file_path: string }[];
const filePaths = targetDocs.map((d) => d.file_path);
// unchanged.md was cloned and must NOT have been deleted by computeDiff.
expect(filePaths).toContain('unchanged.md');
// changed.md was crawled and indexed in this run.
expect(filePaths).toContain('changed.md');
});
});