feat(mcpedia): Phase 3 — async indexing (BullMQ), git-sync webhook, revisions, MCP Resources

- packages/queue: ioredis singleton + BullMQ Queue/Worker (prefix mcpedia:
  on shared imrnes Redis :6379); apps/worker runs startWorker()
- @mcpedia/core: indexContentFile/runFullIndex (single indexing entry point
  shared by script/worker/hook) + revision.service (list/get/restore)
- document_revisions table (migration 0002) — snapshots only on body change
- apps/api: POST /hooks/reindex + /hooks/index webhooks; tRPC revisions,
  getRevision, restoreRevision, jobStatus, queueStatus
- apps/mcp: register MCP Resources mcpedia://docs{/,+slug/chunks/revisions}
  ({+slug} RFC6570 reserved expansion for slugs containing /)
- apps/mcp zod pinned to ^4 to match MCP SDK 1.30 compiled types
  (resolves registerTool TS2589/ShapeOutput skew)
- scripts/enqueue.ts one-shot job enqueue helper; indexer refactored to runFullIndex
- PHASES.md/README/.env.example/docs updated

scripts/indexer.ts

@@ -1,67 +1,14 @@
-import { db } from "@mcpedia/db";
-import { documents } from "@mcpedia/db/schema";
-import { parseFile } from "@mcpedia/parser";
-import { CONTENT_ROOT } from "@mcpedia/config";
-import { listContentFiles, indexChunks } from "@mcpedia/core";
-import { join } from "node:path";
+import { runFullIndex } from "@mcpedia/core";
 
+// Phase 3: the indexer now goes through `runFullIndex`, the single indexing
+// entry point shared with the BullMQ worker and the git-sync hook. It parses
+// each content file, upserts `documents`, chunks+embeds, and snapshots a
+// revision when the body changed.
 async function main() {
-  const files = listContentFiles();
-  let indexed = 0;
-  let chunked = 0;
-  for (const rel of files) {
-    const abs = join(CONTENT_ROOT, rel);
-    const { meta, body } = parseFile(abs, rel);
-    const nowIso =
-      meta.updatedAt && meta.updatedAt !== ""
-        ? meta.updatedAt
-        : new Date().toISOString();
-    await db
-      .insert(documents)
-      .values({
-        id: meta.id,
-        slug: meta.slug,
-        title: meta.title,
-        type: meta.type,
-        section: meta.section,
-        status: meta.status,
-        author: meta.author,
-        tags: meta.tags,
-        path: meta.path,
-        body,
-        createdAt: new Date(meta.createdAt || nowIso),
-        updatedAt: new Date(nowIso),
-      })
-      .onConflictDoUpdate({
-        target: documents.slug,
-        set: {
-          title: meta.title,
-          type: meta.type,
-          section: meta.section,
-          status: meta.status,
-          author: meta.author,
-          tags: meta.tags,
-          path: meta.path,
-          body,
-          updatedAt: new Date(nowIso),
-        },
-      });
-    indexed++;
-    console.log(`  indexed ${rel}`);
-
-    // Phase 2: chunk + embed for semantic search.
-    try {
-      const n = await indexChunks(meta.slug, body);
-      chunked += n;
-      console.log(`    embedded ${n} chunks`);
-    } catch (err) {
-      console.error(
-        `    embed FAILED for ${meta.slug}: ${err instanceof Error ? err.message : err}`,
-      );
-      // Don't abort the whole index over one doc's embedding failure.
-    }
-  }
-  console.log(`indexed ${indexed} documents, ${chunked} chunks embedded`);
+  const reason = process.argv[2] && process.argv[2].startsWith("--reason=")
+    ? process.argv[2].slice("--reason=".length)
+    : "index";
+  await runFullIndex(reason);
 }
 
 main()