feat: add query/retrieval FlowProcessor services and missing runner scripts

Wire up the query and retrieval side of the pipeline so the agent can
answer questions from stored knowledge:

- Triples query service (FalkorDB) — all SPO pattern queries via NATS
- Graph embeddings query service (Qdrant) — entity vector similarity
- Document embeddings query service (Qdrant) — chunk vector similarity
- Graph RAG service — full concept→entity→traverse→score→synthesize pipeline
- Document RAG service — embed→find chunks→synthesize pipeline
- Runner scripts for chunker, extractor, embeddings (missing from Phase 5)
- Add DocumentEmbeddingsRequest/Response schema types
- Add RAG prompt templates (extract-concepts, edge-scoring, synthesize)
- Add graph/doc embeddings query topics to seed config + flow manager
- Add all pipeline/query/retrieval services to docker-compose
- 8 new runner scripts, 8 new pnpm script aliases

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

ts/packages/flow/src/flow-manager/service.ts

@@ -82,6 +82,12 @@ const DEFAULT_BLUEPRINT: Blueprint = {
     // Embeddings
     "embeddings-request": "tg.flow.embeddings-request",
     "embeddings-response": "tg.flow.embeddings-response",
+    // Graph embeddings query
+    "graph-embeddings-request": "tg.flow.graph-embeddings-request",
+    "graph-embeddings-response": "tg.flow.graph-embeddings-response",
+    // Document embeddings query
+    "document-embeddings-request": "tg.flow.document-embeddings-request",
+    "document-embeddings-response": "tg.flow.document-embeddings-response",
     // Librarian RPC (for PDF decoder)
     "librarian-request": "tg.flow.librarian-request",
     "librarian-response": "tg.flow.librarian-response",