feat: eager vLLM warmup and smart page titles in paginate stage

- Add warmup() to LlmProvider interface for eager subprocess startup
- ManagedVllmProvider.warmup() starts vLLM in background on project load
- ProviderRegistry.warmupAll() triggers all managed providers
- NamedProvider proxies warmup() to inner provider
- paginate stage generates LLM-powered descriptive page titles when
  available, cached by content hash, falls back to generic "Page N"
- project-mcp-endpoint calls warmupAll() on router creation so vLLM
  is loading while the session initializes

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

deploy/Dockerfile.python-runner

@@ -0,0 +1,12 @@
+# Base container for Python/uvx-based MCP servers (STDIO transport).
+# mcpd uses this image to run `uvx <packageName>` when a server
+# has packageName with runtime=python but no dockerImage.
+FROM python:3.12-slim
+
+WORKDIR /mcp
+
+# Install uv (which provides uvx)
+RUN pip install --no-cache-dir uv
+
+# Default entrypoint — overridden by mcpd via container command
+ENTRYPOINT ["uvx"]

deploy/docker-compose.yml

@@ -31,6 +31,7 @@ services:
       MCPD_HOST: "0.0.0.0"
       MCPD_LOG_LEVEL: info
       MCPD_NODE_RUNNER_IMAGE: mcpctl-node-runner:latest
+      MCPD_PYTHON_RUNNER_IMAGE: mcpctl-python-runner:latest
       MCPD_MCP_NETWORK: mcp-servers
     depends_on:
       postgres:
@@ -60,6 +61,16 @@ services:
       - build
     entrypoint: ["echo", "Image built successfully"]
 
+  # Base image for Python/uvx-based MCP servers (built once, used by mcpd)
+  python-runner:
+    build:
+      context: ..
+      dockerfile: deploy/Dockerfile.python-runner
+    image: mcpctl-python-runner:latest
+    profiles:
+      - build
+    entrypoint: ["echo", "Image built successfully"]
+
   postgres-test:
     image: postgres:16-alpine
     container_name: mcpctl-postgres-test