feat: Hybrid RAG knowledge base, sentence-aware chunking, MeshMonitor HTTP sync

Knowledge Base:
- Hybrid FTS5 + vector search using sqlite-vec and bge-small-en-v1.5
- Reciprocal Rank Fusion for result merging
- Domain-aware query construction handles typos
- Configurable weights for keyword vs semantic matching

Message Chunking:
- Sentence-aware splitting respects message boundaries
- Continuation prompts for long responses
- Natural follow-up detection (yes, ok, continue, more, etc.)
- Per-user continuation state management

MeshMonitor Integration:
- HTTP API trigger sync (replaces file-based triggers.json)
- Dynamic refresh interval
- Trigger injection into LLM prompt

Other:
- Updated system prompt for better response length control
- Simplified responder to handle message lists
- Updated README with new features and architecture diagram
- Cleaned up config.example.yaml

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

docker-compose.yml

@@ -14,12 +14,12 @@
 services:
   meshai:
     # Pull from GitHub Container Registry
-    image: ghcr.io/zvx-echo6/meshai:latest
+    # image: ghcr.io/zvx-echo6/meshai:latest
 
     # Uncomment to build locally instead of pulling
-    # build:
-    #   context: .
-    #   dockerfile: Dockerfile
+    build:
+      context: .
+      dockerfile: Dockerfile
     #   args:
     #     UID: ${UID:-1000}
     #     GID: ${GID:-1000}
@@ -52,7 +52,7 @@ services:
     deploy:
       resources:
         limits:
-          memory: 256M
+          memory: 3G
         reservations:
           memory: 64M
 
@@ -69,6 +69,7 @@ services:
         max-size: "10m"
         max-file: "3"
 
+
 volumes:
   meshai_data:
     name: meshai_data