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"]