feat: add document pipeline — PDF decoder, Ollama LLM, storage services

Add end-to-end document processing pipeline:
- PDF decoder service (pdfjs-dist) extracts text per page from librarian docs
- Ollama native LLM service for local model inference
- FalkorDB triples store FlowProcessor consumer
- Qdrant graph embeddings store FlowProcessor consumer
- Fix spec name collisions in chunker/extractor (input→chunk-input, etc.)
- Gateway /load endpoint to trigger document processing
- Align flow manager blueprint and seed config with full pipeline topics
- Add runner scripts and test coverage for document load

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

ts/packages/flow/src/gateway/dispatch/manager.ts

@@ -235,6 +235,18 @@ export class DispatcherManager {
     });
   }
 
+  // ---------- Fire-and-forget publish ----------
+
+  /**
+   * Publish a single message to an arbitrary topic (no request/response).
+   * Used for injecting documents into the processing pipeline.
+   */
+  async publishToTopic(topic: string, message: unknown): Promise<void> {
+    const producer = await this.pubsub.createProducer<unknown>({ topic });
+    await producer.send(message);
+    await producer.close();
+  }
+
   // ---------- Static introspection ----------
 
   static get flowServiceNames(): readonly string[] {