refactor: split openai/ into ollama/, openwebui/, searxng/

Move services out of the monolithic openai/docker-compose.yml:
- ollama/ — ollama GPU + CPU inference servers
- openwebui/ — open-webui chat UI (uses env var for ANTHROPIC_API_KEY)
- searxng/ — SearXNG container + searxng-mcp MCP server (port 3102)

openai/ now contains only: litellm, langfuse, qdrant, faster-whisper,
silero-tts, pipecat.

searxng-mcp exposes a single searxng_search tool via MCP HTTP on :3102.
Registered in ~/.claude.json as the "searxng" MCP server.

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

openai/docker-compose.yml

@@ -1,65 +1,4 @@
 services:
-  ollama:
-    image: ollama/ollama
-    container_name: ollama
-    ports:
-      - "11436:11434"
-    volumes:
-      - /mnt/ssd/ai/ollama:/root/.ollama
-      - /mnt/ssd/ai/open-webui:/app/backend/data
-    restart: always
-    environment:
-      # Allow qwen3:8b + qwen2.5:1.5b to coexist in VRAM (~6.7-7.7 GB on 8 GB GPU)
-      - OLLAMA_MAX_LOADED_MODELS=2
-      # One GPU inference at a time — prevents compute contention between models
-      - OLLAMA_NUM_PARALLEL=1
-      # Force all layers to GPU — fail instead of falling back to CPU
-      - OLLAMA_NUM_GPU=999
-    runtime: nvidia
-    mem_limit: 4g
-
-  ollama-cpu:
-    image: ollama/ollama
-    container_name: ollama-cpu
-    ports:
-      - "11435:11434"
-    volumes:
-      - /mnt/ssd/ai/ollama-cpu:/root/.ollama
-    restart: always
-   
-  open-webui:
-    image: ghcr.io/open-webui/open-webui:main
-    container_name: open-webui
-    ports:
-      - "3125:8080"
-    volumes:
-      - /mnt/ssd/ai/open-webui:/app/backend/data
-    extra_hosts:
-      - "host.docker.internal:host-gateway"
-    restart: always
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: all
-              capabilities: [gpu]
-    environment:
-      - ANTHROPIC_API_KEY=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
-      - OPENAI_API_BASE_URL=http://host.docker.internal:4000/v1
-      - OPENAI_API_KEY=dummy
-      # STT — Faster-Whisper large-v3-turbo
-      - AUDIO_STT_ENGINE=openai
-      - AUDIO_STT_OPENAI_API_BASE_URL=http://host.docker.internal:8880/v1
-      - AUDIO_STT_OPENAI_API_KEY=dummy
-      - AUDIO_STT_MODEL=deepdml/faster-whisper-large-v3-turbo-ct2
-      # TTS — Silero v4
-      - AUDIO_TTS_ENGINE=openai
-      - AUDIO_TTS_OPENAI_API_BASE_URL=http://host.docker.internal:8881/v1
-      - AUDIO_TTS_OPENAI_API_KEY=dummy
-      - AUDIO_TTS_MODEL=silero
-      - AUDIO_TTS_VOICE=onyx
-
   litellm-db:
     image: postgres:16-alpine
     container_name: litellm-db
@@ -119,16 +58,6 @@ services:
       - langfuse-db
     restart: always
 
-  searxng:
-    image: docker.io/searxng/searxng:latest
-    container_name: searxng
-    volumes:
-      - /mnt/ssd/ai/searxng/config/:/etc/searxng/
-      - /mnt/ssd/ai/searxng/data/:/var/cache/searxng/
-    restart: always
-    ports:
-      - "11437:8080"
-
   qdrant:
     image: qdrant/qdrant
     container_name: qdrant