Add three-tier model routing with VRAM management and benchmark suite

- Three-tier routing: light (router answers directly ~3s), medium (qwen3:4b
  + tools ~60s), complex (/think prefix → qwen3:8b + subagents ~140s)
- Router: qwen2.5:1.5b, temp=0, regex pre-classifier + raw-text LLM classify
- VRAMManager: explicit flush/poll/prewarm to prevent Ollama CPU-spill bug
- agent_factory: build_medium_agent and build_complex_agent using deepagents
  (TodoListMiddleware + SubAgentMiddleware with research/memory subagents)
- Fix: split Telegram replies >4000 chars into multiple messages
- Benchmark: 30 questions (easy/medium/hard) — 10/10/10 verified passing
  easy→light, medium→medium, hard→complex with VRAM flush confirmed

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

adolf/docker-compose.yml

@@ -0,0 +1,43 @@
+services:
+  deepagents:
+    build: .
+    container_name: deepagents
+    ports:
+      - "8000:8000"
+    environment:
+      - PYTHONUNBUFFERED=1
+      - OLLAMA_BASE_URL=http://host.docker.internal:11436
+      - DEEPAGENTS_MODEL=qwen3:4b
+      - DEEPAGENTS_COMPLEX_MODEL=qwen3:8b
+      - DEEPAGENTS_ROUTER_MODEL=qwen2.5:1.5b
+      - SEARXNG_URL=http://host.docker.internal:11437
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    depends_on:
+      - openmemory
+      - grammy
+    restart: unless-stopped
+
+  openmemory:
+    build: ./openmemory
+    container_name: openmemory
+    ports:
+      - "8765:8765"
+    environment:
+      # Extraction LLM (qwen2.5:1.5b) runs on GPU after reply — fast 2-5s extraction
+      - OLLAMA_GPU_URL=http://host.docker.internal:11436
+      # Embedding (nomic-embed-text) runs on CPU — fast enough for search (50-150ms)
+      - OLLAMA_CPU_URL=http://host.docker.internal:11435
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    restart: unless-stopped
+
+  grammy:
+    build: ./grammy
+    container_name: grammy
+    ports:
+      - "3001:3001"
+    environment:
+      - TELEGRAM_BOT_TOKEN=${TELEGRAM_BOT_TOKEN}
+      - DEEPAGENTS_URL=http://deepagents:8000
+    restart: unless-stopped