fix(MULTIVERSION-0001): surface pre-parsed config in CrawlResult to fix rules persistence

When trueref.json specifies a `folders` allowlist (e.g. ["src/"]),
shouldIndexFile() excludes trueref.json itself because it lives at the
repo root. The indexing pipeline then searches crawlResult.files for the
config file, finds nothing, and never writes rules to repository_configs.

Fix (Option B): add a `config` field to CrawlResult so LocalCrawler
returns the pre-parsed config directly. The indexing pipeline now reads
crawlResult.config first instead of scanning files[], which resolves the
regression for all repos with a folders allowlist.

- Add `config?: RepoConfig` to CrawlResult in crawler/types.ts
- Return `config` from LocalCrawler.crawlDirectory()
- Update IndexingPipeline.crawl() to propagate CrawlResult.config
- Update IndexingPipeline.run() to prefer crawlResult.config over files
- Add regression tests covering the folders-allowlist exclusion scenario

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/lib/server/pipeline/indexing.pipeline.test.ts

@@ -268,6 +268,8 @@ describe('IndexingPipeline', () => {
 		crawlResult: {
 			files: Array<{ path: string; content: string; sha: string; language: string }>;
 			totalFiles: number;
+			/** Optional pre-parsed config — simulates LocalCrawler returning CrawlResult.config. */
+			config?: Record<string, unknown>;
 		} = { files: [], totalFiles: 0 },
 		embeddingService: EmbeddingService | null = null
 	) {
@@ -885,4 +887,70 @@ describe('IndexingPipeline', () => {
 		const rules = JSON.parse(versionRow!.rules);
 		expect(rules).toEqual(['This is v2. Use the new Builder API.']);
 	});
+
+	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/"]),
+		// shouldIndexFile() excludes trueref.json itself because it lives at the
+		// repo root. The LocalCrawler now carries the pre-parsed config in
+		// CrawlResult.config so the pipeline no longer needs to find the file in
+		// crawlResult.files[].
+		const pipeline = makePipeline({
+			// trueref.json is NOT in files — simulates it being excluded by folders allowlist.
+			files: [
+				{
+					path: 'src/index.ts',
+					content: 'export const x = 1;',
+					sha: 'sha-src',
+					language: 'typescript'
+				}
+			],
+			totalFiles: 1,
+			// The pre-parsed config is carried here instead (set by LocalCrawler).
+			config: { rules: ['Use strict TypeScript.', 'Avoid any.'] }
+		});
+		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(['Use strict TypeScript.', 'Avoid any.']);
+	});
+
+	it('persists version-specific rules from CrawlResult.config when trueref.json is excluded by folders allowlist', async () => {
+		const versionId = insertVersion(db, { tag: 'v3.0.0', state: 'pending' });
+
+		const pipeline = makePipeline({
+			files: [
+				{
+					path: 'src/index.ts',
+					content: 'export const x = 1;',
+					sha: 'sha-src',
+					language: 'typescript'
+				}
+			],
+			totalFiles: 1,
+			config: { rules: ['v3: use the streaming API.'] }
+		});
+		const job = makeJob('/test/repo', versionId);
+
+		await pipeline.run(job as never);
+
+		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(['v3: use the streaming API.']);
+	});
 });