Merge branch 'fix/MULTIVERSION-0001-trueref-config-crawl-result'

src/hooks.server.ts

@@ -24,7 +24,12 @@ import type { Handle } from '@sveltejs/kit';
 
 try {
 	initializeDatabase();
+} catch (err) {
+	console.error('[hooks.server] FATAL: database initialisation failed:', err);
+	process.exit(1);
+}
 
+try {
 	const db = getClient();
 	const activeProfileRow = db
 		.prepare<[], EmbeddingProfileEntityProps>(
@@ -46,7 +51,8 @@ try {
 	console.log('[hooks.server] Indexing pipeline initialised.');
 } catch (err) {
 	console.error(
-		`[hooks.server] Failed to initialise server: ${err instanceof Error ? err.message : String(err)}`
+		'[hooks.server] Failed to initialise pipeline:',
+		err instanceof Error ? err.message : String(err)
 	);
 }
 

src/lib/components/IndexingProgress.svelte

@@ -1,13 +1,14 @@
 <script lang="ts">
 	import type { IndexingJob } from '$lib/types';
 
-	let { jobId }: { jobId: string } = $props();
+	let { jobId, oncomplete }: { jobId: string; oncomplete?: () => void } = $props();
 
 	let job = $state<IndexingJob | null>(null);
 
 	$effect(() => {
 		job = null;
 		let stopped = false;
+		let completeFired = false;
 
 		async function poll() {
 			if (stopped) return;
@@ -16,6 +17,10 @@
 				if (res.ok) {
 					const data = await res.json();
 					job = data.job;
+					if (!completeFired && (job?.status === 'done' || job?.status === 'failed')) {
+						completeFired = true;
+						oncomplete?.();
+					}
 				}
 			} catch {
 				// ignore transient errors

src/lib/components/RepositoryCard.svelte.test.ts

@@ -5,7 +5,7 @@ import RepositoryCard from './RepositoryCard.svelte';
 
 describe('RepositoryCard.svelte', () => {
 	it('encodes slash-bearing repository ids in the details href', async () => {
-		render(RepositoryCard, {
+		const { container } = await render(RepositoryCard, {
 			repo: {
 				id: '/facebook/react',
 				title: 'React',
@@ -26,7 +26,8 @@ describe('RepositoryCard.svelte', () => {
 			.element(page.getByRole('link', { name: 'Details' }))
 			.toHaveAttribute('href', '/repos/%2Ffacebook%2Freact');
 
-		await expect.element(page.getByText('1,200 embeddings')).toBeInTheDocument();
+		const text = container.textContent ?? '';
-		await expect.element(page.getByText('Indexed: main, v18.3.0')).toBeInTheDocument();
+		expect(text).toMatch(/1[,.\u00a0\u202f]?200 embeddings/);
+		expect(text).toContain('Indexed: main, v18.3.0');
 	});
 });

src/lib/server/crawler/local.crawler.test.ts

@@ -413,6 +413,59 @@ describe('LocalCrawler.crawl() — config file detection', () => {
 		const result = await crawlRoot();
 		expect(result.files.some((f) => f.path === 'src/index.ts')).toBe(true);
 	});
+
+	it('populates CrawlResult.config with the parsed trueref.json even when folders allowlist excludes the root', async () => {
+		// Regression test for MULTIVERSION-0001:
+		// When folders: ["src/"] is set, trueref.json at the root is excluded from
+		// files[] by shouldIndexFile(). The config must still be returned in
+		// CrawlResult.config so the indexing pipeline can persist rules.
+		root = await makeTempRepo({
+			'trueref.json': JSON.stringify({
+				folders: ['src/'],
+				rules: ['Always document public APIs.']
+			}),
+			'src/index.ts': 'export {};',
+			'docs/guide.md': '# Guide'
+		});
+		const result = await crawlRoot();
+
+		// trueref.json must NOT appear in files (excluded by folders allowlist).
+		expect(result.files.some((f) => f.path === 'trueref.json')).toBe(false);
+		// docs/guide.md must NOT appear (outside src/).
+		expect(result.files.some((f) => f.path === 'docs/guide.md')).toBe(false);
+		// src/index.ts must appear (inside src/).
+		expect(result.files.some((f) => f.path === 'src/index.ts')).toBe(true);
+		// CrawlResult.config must carry the parsed config.
+		expect(result.config).toBeDefined();
+		expect(result.config?.rules).toEqual(['Always document public APIs.']);
+	});
+
+	it('populates CrawlResult.config with the parsed context7.json', async () => {
+		root = await makeTempRepo({
+			'context7.json': JSON.stringify({ rules: ['Rule from context7.'] }),
+			'src/index.ts': 'export {};'
+		});
+		const result = await crawlRoot();
+		expect(result.config).toBeDefined();
+		expect(result.config?.rules).toEqual(['Rule from context7.']);
+	});
+
+	it('CrawlResult.config is undefined when no config file is present', async () => {
+		root = await makeTempRepo({ 'src/index.ts': 'export {};' });
+		const result = await crawlRoot();
+		expect(result.config).toBeUndefined();
+	});
+
+	it('CrawlResult.config is undefined when caller supplies config (caller-provided takes precedence, no auto-detect)', async () => {
+		root = await makeTempRepo({
+			'trueref.json': JSON.stringify({ rules: ['From file.'] }),
+			'src/index.ts': 'export {};'
+		});
+		// Caller-supplied config prevents auto-detection; CrawlResult.config
+		// should carry the caller config (not the file content).
+		const result = await crawlRoot({ config: { rules: ['From caller.'] } });
+		expect(result.config?.rules).toEqual(['From caller.']);
+	});
 });
 
 // ---------------------------------------------------------------------------

src/lib/server/crawler/local.crawler.ts

@@ -230,7 +230,11 @@ export class LocalCrawler {
 			totalFiles: filteredPaths.length,
 			skippedFiles: allRelPaths.length - filteredPaths.length,
 			branch,
-			commitSha
+			commitSha,
+			// Surface the pre-parsed config so the indexing pipeline can read rules
+			// without needing to find trueref.json inside crawledFiles (which fails
+			// when a `folders` allowlist excludes the repo root).
+			config: config ?? undefined
 		};
 	}
 

src/lib/server/crawler/types.ts

@@ -35,6 +35,13 @@ export interface CrawlResult {
 	branch: string;
 	/** HEAD commit SHA */
 	commitSha: string;
+	/**
+	 * Pre-parsed trueref.json / context7.json configuration found at the repo
+	 * root during crawling. Carried here so the indexing pipeline can consume it
+	 * directly without having to locate the config file in `files` — which fails
+	 * when a `folders` allowlist excludes the repo root.
+	 */
+	config?: RepoConfig;
 }
 
 export interface CrawlOptions {

src/lib/server/db/index.ts

@@ -30,6 +30,7 @@ const __dirname = dirname(fileURLToPath(import.meta.url));
  */
 export function initializeDatabase(): void {
 	const migrationsFolder = join(__dirname, 'migrations');
+	console.log(`[db] Running migrations from ${migrationsFolder}...`);
 	migrate(db, { migrationsFolder });
 
 	// Apply FTS5 virtual table and trigger DDL (not expressible via Drizzle).

src/lib/server/db/migrations/meta/0003_snapshot.json

@@ -0,0 +1,835 @@
+{
+	"version": "6",
+	"dialect": "sqlite",
+	"id": "a7c2e4f8-3b1d-4e9a-8f0c-6d5e2a1b9c7f",
+	"prevId": "31531dab-a199-4fc5-a889-1884940039cd",
+	"tables": {
+		"documents": {
+			"name": "documents",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "text",
+					"primaryKey": true,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"repository_id": {
+					"name": "repository_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"version_id": {
+					"name": "version_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"file_path": {
+					"name": "file_path",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"title": {
+					"name": "title",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"language": {
+					"name": "language",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"token_count": {
+					"name": "token_count",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"checksum": {
+					"name": "checksum",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"indexed_at": {
+					"name": "indexed_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {
+				"documents_repository_id_repositories_id_fk": {
+					"name": "documents_repository_id_repositories_id_fk",
+					"tableFrom": "documents",
+					"tableTo": "repositories",
+					"columnsFrom": ["repository_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				},
+				"documents_version_id_repository_versions_id_fk": {
+					"name": "documents_version_id_repository_versions_id_fk",
+					"tableFrom": "documents",
+					"tableTo": "repository_versions",
+					"columnsFrom": ["version_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"checkConstraints": {}
+		},
+		"embedding_profiles": {
+			"name": "embedding_profiles",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "text",
+					"primaryKey": true,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"provider_kind": {
+					"name": "provider_kind",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"title": {
+					"name": "title",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"enabled": {
+					"name": "enabled",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false,
+					"default": true
+				},
+				"is_default": {
+					"name": "is_default",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false,
+					"default": false
+				},
+				"model": {
+					"name": "model",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"dimensions": {
+					"name": "dimensions",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"config": {
+					"name": "config",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"updated_at": {
+					"name": "updated_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"checkConstraints": {}
+		},
+		"indexing_jobs": {
+			"name": "indexing_jobs",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "text",
+					"primaryKey": true,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"repository_id": {
+					"name": "repository_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"version_id": {
+					"name": "version_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"status": {
+					"name": "status",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false,
+					"default": "'queued'"
+				},
+				"progress": {
+					"name": "progress",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"total_files": {
+					"name": "total_files",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"processed_files": {
+					"name": "processed_files",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"error": {
+					"name": "error",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"started_at": {
+					"name": "started_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"completed_at": {
+					"name": "completed_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {
+				"indexing_jobs_repository_id_repositories_id_fk": {
+					"name": "indexing_jobs_repository_id_repositories_id_fk",
+					"tableFrom": "indexing_jobs",
+					"tableTo": "repositories",
+					"columnsFrom": ["repository_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"checkConstraints": {}
+		},
+		"repositories": {
+			"name": "repositories",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "text",
+					"primaryKey": true,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"title": {
+					"name": "title",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"description": {
+					"name": "description",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"source": {
+					"name": "source",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"source_url": {
+					"name": "source_url",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"branch": {
+					"name": "branch",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": "'main'"
+				},
+				"state": {
+					"name": "state",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false,
+					"default": "'pending'"
+				},
+				"total_snippets": {
+					"name": "total_snippets",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"total_tokens": {
+					"name": "total_tokens",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"trust_score": {
+					"name": "trust_score",
+					"type": "real",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"benchmark_score": {
+					"name": "benchmark_score",
+					"type": "real",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"stars": {
+					"name": "stars",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"github_token": {
+					"name": "github_token",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"last_indexed_at": {
+					"name": "last_indexed_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"updated_at": {
+					"name": "updated_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"checkConstraints": {}
+		},
+		"repository_configs": {
+			"name": "repository_configs",
+			"columns": {
+				"repository_id": {
+					"name": "repository_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"version_id": {
+					"name": "version_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"project_title": {
+					"name": "project_title",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"description": {
+					"name": "description",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"folders": {
+					"name": "folders",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"exclude_folders": {
+					"name": "exclude_folders",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"exclude_files": {
+					"name": "exclude_files",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"rules": {
+					"name": "rules",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"previous_versions": {
+					"name": "previous_versions",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"updated_at": {
+					"name": "updated_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				}
+			},
+			"indexes": {
+				"uniq_repo_config_base": {
+					"name": "uniq_repo_config_base",
+					"columns": ["repository_id"],
+					"isUnique": true,
+					"where": "`version_id` IS NULL"
+				},
+				"uniq_repo_config_version": {
+					"name": "uniq_repo_config_version",
+					"columns": ["repository_id", "version_id"],
+					"isUnique": true,
+					"where": "`version_id` IS NOT NULL"
+				}
+			},
+			"foreignKeys": {
+				"repository_configs_repository_id_repositories_id_fk": {
+					"name": "repository_configs_repository_id_repositories_id_fk",
+					"tableFrom": "repository_configs",
+					"tableTo": "repositories",
+					"columnsFrom": ["repository_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"checkConstraints": {}
+		},
+		"repository_versions": {
+			"name": "repository_versions",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "text",
+					"primaryKey": true,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"repository_id": {
+					"name": "repository_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"tag": {
+					"name": "tag",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"title": {
+					"name": "title",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"commit_hash": {
+					"name": "commit_hash",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"state": {
+					"name": "state",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false,
+					"default": "'pending'"
+				},
+				"total_snippets": {
+					"name": "total_snippets",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"indexed_at": {
+					"name": "indexed_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {
+				"repository_versions_repository_id_repositories_id_fk": {
+					"name": "repository_versions_repository_id_repositories_id_fk",
+					"tableFrom": "repository_versions",
+					"tableTo": "repositories",
+					"columnsFrom": ["repository_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"checkConstraints": {}
+		},
+		"settings": {
+			"name": "settings",
+			"columns": {
+				"key": {
+					"name": "key",
+					"type": "text",
+					"primaryKey": true,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"value": {
+					"name": "value",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"updated_at": {
+					"name": "updated_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"checkConstraints": {}
+		},
+		"snippet_embeddings": {
+			"name": "snippet_embeddings",
+			"columns": {
+				"snippet_id": {
+					"name": "snippet_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"profile_id": {
+					"name": "profile_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"model": {
+					"name": "model",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"dimensions": {
+					"name": "dimensions",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"embedding": {
+					"name": "embedding",
+					"type": "blob",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {
+				"snippet_embeddings_snippet_id_snippets_id_fk": {
+					"name": "snippet_embeddings_snippet_id_snippets_id_fk",
+					"tableFrom": "snippet_embeddings",
+					"tableTo": "snippets",
+					"columnsFrom": ["snippet_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				},
+				"snippet_embeddings_profile_id_embedding_profiles_id_fk": {
+					"name": "snippet_embeddings_profile_id_embedding_profiles_id_fk",
+					"tableFrom": "snippet_embeddings",
+					"tableTo": "embedding_profiles",
+					"columnsFrom": ["profile_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {
+				"snippet_embeddings_snippet_id_profile_id_pk": {
+					"columns": ["snippet_id", "profile_id"],
+					"name": "snippet_embeddings_snippet_id_profile_id_pk"
+				}
+			},
+			"uniqueConstraints": {},
+			"checkConstraints": {}
+		},
+		"snippets": {
+			"name": "snippets",
+			"columns": {
+				"id": {
+					"name": "id",
+					"type": "text",
+					"primaryKey": true,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"document_id": {
+					"name": "document_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"repository_id": {
+					"name": "repository_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"version_id": {
+					"name": "version_id",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"type": {
+					"name": "type",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"title": {
+					"name": "title",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"content": {
+					"name": "content",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				},
+				"language": {
+					"name": "language",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"breadcrumb": {
+					"name": "breadcrumb",
+					"type": "text",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false
+				},
+				"token_count": {
+					"name": "token_count",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": false,
+					"autoincrement": false,
+					"default": 0
+				},
+				"created_at": {
+					"name": "created_at",
+					"type": "integer",
+					"primaryKey": false,
+					"notNull": true,
+					"autoincrement": false
+				}
+			},
+			"indexes": {},
+			"foreignKeys": {
+				"snippets_document_id_documents_id_fk": {
+					"name": "snippets_document_id_documents_id_fk",
+					"tableFrom": "snippets",
+					"tableTo": "documents",
+					"columnsFrom": ["document_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				},
+				"snippets_repository_id_repositories_id_fk": {
+					"name": "snippets_repository_id_repositories_id_fk",
+					"tableFrom": "snippets",
+					"tableTo": "repositories",
+					"columnsFrom": ["repository_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				},
+				"snippets_version_id_repository_versions_id_fk": {
+					"name": "snippets_version_id_repository_versions_id_fk",
+					"tableFrom": "snippets",
+					"tableTo": "repository_versions",
+					"columnsFrom": ["version_id"],
+					"columnsTo": ["id"],
+					"onDelete": "cascade",
+					"onUpdate": "no action"
+				}
+			},
+			"compositePrimaryKeys": {},
+			"uniqueConstraints": {},
+			"checkConstraints": {}
+		}
+	},
+	"views": {},
+	"enums": {},
+	"schemas": {},
+	"sequences": {},
+	"_meta": {
+		"schemas": {},
+		"tables": {},
+		"columns": {}
+	},
+	"internal": {
+		"indexes": {}
+	}
+}

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
 	) {
@@ -867,15 +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 = ?`
@@ -885,4 +889,133 @@ describe('IndexingPipeline', () => {
 		const rules = JSON.parse(versionRow!.rules);
 		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/"]),
+		// 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.']);
+	});
 });

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

@@ -15,14 +15,14 @@
 
 import { createHash, randomUUID } from 'node:crypto';
 import type Database from 'better-sqlite3';
-import type { Document, NewDocument, NewSnippet } from '$lib/types';
+import type { Document, NewDocument, NewSnippet, TrueRefConfig } from '$lib/types';
 import type { crawl as GithubCrawlFn } from '$lib/server/crawler/github.crawler.js';
 import type { LocalCrawler } from '$lib/server/crawler/local.crawler.js';
 import type { EmbeddingService } from '$lib/server/embeddings/embedding.service.js';
 import { RepositoryMapper } from '$lib/server/mappers/repository.mapper.js';
 import { IndexingJob } from '$lib/server/models/indexing-job.js';
 import { Repository, RepositoryEntity } from '$lib/server/models/repository.js';
-import { resolveConfig } from '$lib/server/config/config-parser.js';
+import { resolveConfig, type ParsedConfig } from '$lib/server/config/config-parser.js';
 import { parseFile } from '$lib/server/parser/index.js';
 import { computeTrustScore } from '$lib/server/search/trust-score.js';
 import { computeDiff } from './diff.js';
@@ -101,13 +101,25 @@ export class IndexingPipeline {
 				: undefined;
 			const crawlResult = await this.crawl(repo, versionTag);
 
-			// Parse trueref.json / context7.json if present in the crawl results.
+			// Resolve trueref.json / context7.json configuration.
+			// Prefer the pre-parsed config carried in the CrawlResult (set by
+			// LocalCrawler so it is available even when a `folders` allowlist
+			// excludes the repo root and trueref.json never appears in files[]).
+			// Fall back to locating the file in crawlResult.files for GitHub crawls
+			// which do not yet populate CrawlResult.config.
+			let parsedConfig: ReturnType<typeof resolveConfig> | null = null;
+			if (crawlResult.config) {
+				// Config was pre-parsed by the crawler — wrap it in a ParsedConfig
+				// shell so the rest of the pipeline can use it uniformly.
+				parsedConfig = { config: crawlResult.config, source: 'trueref.json', warnings: [] } satisfies ParsedConfig;
+			} else {
 				const configFile = crawlResult.files.find(
 					(f) => f.path === 'trueref.json' || f.path === 'context7.json'
 				);
-			const parsedConfig = configFile
+				parsedConfig = configFile
 					? resolveConfig([{ filename: configFile.path, content: configFile.content }])
 					: null;
+			}
 			const excludeFiles: string[] = parsedConfig?.config.excludeFiles ?? [];
 
 			// Filter out excluded files before diff computation.
@@ -264,10 +276,13 @@ export class IndexingPipeline {
 
 			// ---- Stage 6: Persist rules from config ----------------------------
 			if (parsedConfig?.config.rules?.length) {
-				// Repo-wide rules (versionId = null).
+				if (!normJob.versionId) {
+					// Main-branch job: write the repo-wide entry only.
 					this.upsertRepoConfig(repo.id, null, parsedConfig.config.rules);
-				// Version-specific rules stored separately when indexing a version.
+				} else {
-				if (normJob.versionId) {
+					// Version job: write only the version-specific entry.
+					// Writing to the NULL row here would overwrite repo-wide rules
+					// with whatever the last-indexed version happened to carry.
 					this.upsertRepoConfig(repo.id, normJob.versionId, parsedConfig.config.rules);
 				}
 			}
@@ -304,6 +319,8 @@ export class IndexingPipeline {
 	private async crawl(repo: Repository, ref?: string): Promise<{
 		files: Array<{ path: string; content: string; sha: string; size: number; language: string }>;
 		totalFiles: number;
+		/** Pre-parsed trueref.json / context7.json, or undefined when absent. */
+		config?: TrueRefConfig;
 	}> {
 		if (repo.source === 'github') {
 			// Parse owner/repo from the canonical ID: "/owner/repo"
@@ -330,7 +347,7 @@ export class IndexingPipeline {
 				ref: ref ?? (repo.branch !== 'main' ? (repo.branch ?? undefined) : undefined)
 			});
 
-			return { files: result.files, totalFiles: result.totalFiles };
+			return { files: result.files, totalFiles: result.totalFiles, config: result.config };
 		}
 	}
 

src/routes/api/v1/api-contract.integration.test.ts

@@ -446,7 +446,11 @@ describe('API contract integration', () => {
 		const repositoryId = seedRepo(db);
 		const versionId = seedVersion(db, repositoryId, 'v18.3.0');
 		const documentId = seedDocument(db, repositoryId, versionId);
-		seedRules(db, repositoryId, ['Prefer hooks over classes']);
+		// Insert version-specific rules (versioned queries no longer inherit the NULL row).
+		db.prepare(
+			`INSERT INTO repository_configs (repository_id, version_id, rules, updated_at)
+			 VALUES (?, ?, ?, ?)`
+		).run(repositoryId, versionId, JSON.stringify(['Prefer hooks over classes']), NOW_S);
 		seedSnippet(db, {
 			documentId,
 			repositoryId,
@@ -497,12 +501,12 @@ describe('API contract integration', () => {
 		});
 	});
 
-	it('GET /api/v1/context returns merged repo-wide and version-specific rules', async () => {
+	it('GET /api/v1/context returns only version-specific rules for versioned queries (no NULL row contamination)', async () => {
 		const repositoryId = seedRepo(db);
 		const versionId = seedVersion(db, repositoryId, 'v2.0.0');
 		const documentId = seedDocument(db, repositoryId, versionId);
 
-		// Insert repo-wide rules (version_id IS NULL).
+		// Insert repo-wide rules (version_id IS NULL) — these must NOT appear in versioned queries.
 		db.prepare(
 			`INSERT INTO repository_configs (repository_id, version_id, rules, updated_at)
 			 VALUES (?, NULL, ?, ?)`
@@ -529,8 +533,8 @@ describe('API contract integration', () => {
 
 		expect(response.status).toBe(200);
 		const body = await response.json();
-		// Both repo-wide and version-specific rules should appear (deduped).
+		// Only the version-specific rule should appear — NULL row must not contaminate.
-		expect(body.rules).toEqual(['Repo-wide rule', 'Version-specific rule']);
+		expect(body.rules).toEqual(['Version-specific rule']);
 	});
 
 	it('GET /api/v1/context returns only repo-wide rules when no version is requested', async () => {
@@ -556,12 +560,13 @@ describe('API contract integration', () => {
 		expect(body.rules).toEqual(['Repo-wide rule only']);
 	});
 
-	it('GET /api/v1/context deduplicates rules that appear in both repo-wide and version config', async () => {
+	it('GET /api/v1/context versioned query returns only the version-specific rules row', async () => {
 		const repositoryId = seedRepo(db);
 		const versionId = seedVersion(db, repositoryId, 'v3.0.0');
 		const documentId = seedDocument(db, repositoryId, versionId);
 
 		const sharedRule = 'Use TypeScript strict mode';
+		// Insert repo-wide NULL row — must NOT bleed into versioned query results.
 		db.prepare(
 			`INSERT INTO repository_configs (repository_id, version_id, rules, updated_at)
 			 VALUES (?, NULL, ?, ?)`
@@ -582,10 +587,35 @@ describe('API contract integration', () => {
 
 		expect(response.status).toBe(200);
 		const body = await response.json();
-		// sharedRule appears once, version-only rule appended.
+		// Returns only the version-specific row as stored — no NULL row merge.
 		expect(body.rules).toEqual([sharedRule, 'Version-only rule']);
 	});
 
+	it('GET /api/v1/context versioned query returns empty rules when only NULL row exists (no NULL contamination)', async () => {
+		const repositoryId = seedRepo(db);
+		const versionId = seedVersion(db, repositoryId, 'v1.0.0');
+		const documentId = seedDocument(db, repositoryId, versionId);
+
+		// Only a repo-wide NULL row exists — no version-specific config.
+		db.prepare(
+			`INSERT INTO repository_configs (repository_id, version_id, rules, updated_at)
+			 VALUES (?, NULL, ?, ?)`
+		).run(repositoryId, JSON.stringify(['HEAD rules that must not contaminate v1']), NOW_S);
+
+		seedSnippet(db, { documentId, repositoryId, versionId, content: 'v1 content' });
+
+		const response = await getContext({
+			url: new URL(
+				`http://test/api/v1/context?libraryId=${encodeURIComponent(`${repositoryId}/v1.0.0`)}&query=${encodeURIComponent('v1 content')}`
+			)
+		} as never);
+
+		expect(response.status).toBe(200);
+		const body = await response.json();
+		// No version-specific config row → empty rules. NULL row must not bleed in.
+		expect(body.rules).toEqual([]);
+	});
+
 	it('GET /api/v1/context returns 404 with VERSION_NOT_FOUND when version does not exist', async () => {
 		const repositoryId = seedRepo(db);
 

src/routes/api/v1/context/+server.ts

@@ -69,35 +69,25 @@ function getRules(
 	repositoryId: string,
 	versionId?: string
 ): string[] {
-	// Repo-wide rules (version_id IS NULL).
+	if (!versionId) {
-	const repoRow = db
+		// Unversioned query: return repo-wide (HEAD) rules only.
+		const row = db
 			.prepare<
 				[string],
 				RawRepoConfig
 			>(`SELECT rules FROM repository_configs WHERE repository_id = ? AND version_id IS NULL`)
 			.get(repositoryId);
+		return parseRulesJson(row?.rules);
+	}
 
-	const repoRules = parseRulesJson(repoRow?.rules);
+	// Versioned query: return only version-specific rules (no NULL row merge).
-
+	const row = db
-	if (!versionId) return repoRules;
-
-	// Version-specific rules.
-	const versionRow = db
 		.prepare<
 			[string, string],
 			RawRepoConfig
 		>(`SELECT rules FROM repository_configs WHERE repository_id = ? AND version_id = ?`)
 		.get(repositoryId, versionId);
-
+	return parseRulesJson(row?.rules);
-	const versionRules = parseRulesJson(versionRow?.rules);
-
-	// Merge: repo-wide first, then version-specific (deduped by content).
-	const seen = new Set(repoRules);
-	const merged = [...repoRules];
-	for (const r of versionRules) {
-		if (!seen.has(r)) merged.push(r);
-	}
-	return merged;
 }
 
 interface RawRepoState {

src/routes/repos/[id]/+page.svelte

@@ -524,6 +524,29 @@
 							</button>
 						</div>
 					</div>
+					{#if version.totalSnippets > 0 || version.commitHash || version.indexedAt}
+						{@const metaParts = (
+							[
+								version.totalSnippets > 0
+									? { text: `${version.totalSnippets} snippets`, mono: false }
+									: null,
+								version.commitHash
+									? { text: version.commitHash.slice(0, 8), mono: true }
+									: null,
+								version.indexedAt
+									? { text: formatDate(version.indexedAt), mono: false }
+									: null
+							] as Array<{ text: string; mono: boolean } | null>
+						).filter((p): p is { text: string; mono: boolean } => p !== null)}
+						<div class="mt-1 flex items-center gap-1.5">
+							{#each metaParts as part, i (i)}
+								{#if i > 0}
+									<span class="text-xs text-gray-300">·</span>
+								{/if}
+								<span class="text-xs text-gray-400{part.mono ? ' font-mono' : ''}">{part.text}</span>
+							{/each}
+						</div>
+					{/if}
 					{#if !!activeVersionJobs[version.tag]}
 						<IndexingProgress
 							jobId={activeVersionJobs[version.tag]!}