forked from cardosofelipe/fast-next-template
feat(llm-gateway): implement LLM Gateway MCP Server (#56)
Implements complete LLM Gateway MCP Server with: - FastMCP server with 4 tools: chat_completion, list_models, get_usage, count_tokens - LiteLLM Router with multi-provider failover chains - Circuit breaker pattern for fault tolerance - Redis-based cost tracking per project/agent - Comprehensive test suite (209 tests, 92% coverage) Model groups defined per ADR-004: - reasoning: claude-opus-4 → gpt-4.1 → gemini-2.5-pro - code: claude-sonnet-4 → gpt-4.1 → deepseek-coder - fast: claude-haiku → gpt-4.1-mini → gemini-2.0-flash 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
53
mcp-servers/llm-gateway/Dockerfile
Normal file
53
mcp-servers/llm-gateway/Dockerfile
Normal file
@@ -0,0 +1,53 @@
|
||||
# Syndarix LLM Gateway MCP Server
|
||||
# Multi-stage build for minimal image size
|
||||
|
||||
# Build stage
|
||||
FROM python:3.12-slim AS builder
|
||||
|
||||
# Install uv for fast package management
|
||||
COPY --from=ghcr.io/astral-sh/uv:latest /uv /usr/local/bin/uv
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# Copy dependency files
|
||||
COPY pyproject.toml ./
|
||||
|
||||
# Create virtual environment and install dependencies
|
||||
RUN uv venv /app/.venv
|
||||
ENV PATH="/app/.venv/bin:$PATH"
|
||||
RUN uv pip install -e .
|
||||
|
||||
# Runtime stage
|
||||
FROM python:3.12-slim AS runtime
|
||||
|
||||
# Create non-root user for security
|
||||
RUN groupadd --gid 1000 appgroup && \
|
||||
useradd --uid 1000 --gid appgroup --shell /bin/bash --create-home appuser
|
||||
|
||||
WORKDIR /app
|
||||
|
||||
# Copy virtual environment from builder
|
||||
COPY --from=builder /app/.venv /app/.venv
|
||||
ENV PATH="/app/.venv/bin:$PATH"
|
||||
|
||||
# Copy application code
|
||||
COPY --chown=appuser:appgroup . .
|
||||
|
||||
# Switch to non-root user
|
||||
USER appuser
|
||||
|
||||
# Environment variables
|
||||
ENV LLM_GATEWAY_HOST=0.0.0.0
|
||||
ENV LLM_GATEWAY_PORT=8001
|
||||
ENV PYTHONUNBUFFERED=1
|
||||
ENV PYTHONDONTWRITEBYTECODE=1
|
||||
|
||||
# Expose port
|
||||
EXPOSE 8001
|
||||
|
||||
# Health check
|
||||
HEALTHCHECK --interval=30s --timeout=10s --start-period=5s --retries=3 \
|
||||
CMD python -c "import httpx; httpx.get('http://localhost:8001/health').raise_for_status()" || exit 1
|
||||
|
||||
# Run the server
|
||||
CMD ["python", "server.py"]
|
||||
Reference in New Issue
Block a user