Dockerization and Fixes for Gemini chunk issues

.dockerignore

@@ -0,0 +1,39 @@
+# Git
+.git
+.gitignore
+
+# Environment
+.env
+.env.example
+
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+env/
+venv/
+ENV/
+*.egg-info/
+dist/
+build/
+
+# Docker
+Dockerfile
+docker-compose.yml
+.dockerignore
+
+# Tests
+tests.py
+
+# Documentation
+README.md
+CLAUDE.md
+*.png
+
+# Editor files
+.vscode/
+.idea/
+*.swp
+*.swo

.gitattributes

@@ -0,0 +1,5 @@
+# Shell scripts require LF
+*.sh    text eol=lf
+# Batch scripts require CRLF
+*.bat   text eol=crlf
+*.cmd   text eol=crlf

CLAUDE.md

@@ -0,0 +1,87 @@
+# CLAUDE.md
+
+This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
+
+## Project Overview
+
+This project is a proxy server that allows you to use Anthropic clients (like Claude Code) with Gemini or OpenAI backends via LiteLLM. It translates API requests between Anthropic's format and OpenAI/Gemini formats, enabling Claude clients to use non-Anthropic models.
+
+## Key Commands
+
+### Running the Server
+
+```bash
+# Start the server with hot reloading (for development)
+uv run uvicorn server:app --host 0.0.0.0 --port 8082 --reload
+
+# Start the server without hot reloading (for production)
+uv run uvicorn server:app --host 0.0.0.0 --port 8082
+```
+
+### Running Tests
+
+```bash
+# Run all tests
+python tests.py
+
+# Skip streaming tests
+python tests.py --no-streaming
+
+# Run only simple tests (no tools)
+python tests.py --simple
+
+# Run only tool-related tests
+python tests.py --tools-only
+
+# Run only streaming tests
+python tests.py --streaming-only
+```
+
+## Dependencies and Setup
+
+This project uses Python 3.10+ and manages dependencies with `uv`. Key dependencies include:
+
+- fastapi: Web framework
+- uvicorn: ASGI server
+- httpx: HTTP client
+- pydantic: Data validation
+- litellm: LLM API abstraction for model mapping
+- python-dotenv: Environment variable management
+
+## Configuration
+
+For detailed configuration instructions, including environment variables and model settings, please refer to the "Setup" and "Model Mapping" sections in [README.md](README.md).
+
+## Architecture
+
+The proxy server works by:
+
+1. Receiving requests in Anthropic's API format
+2. Translating the requests to OpenAI/Gemini format via LiteLLM
+3. Sending the translated request to the target provider
+4. Converting the response back to Anthropic format
+5. Returning the formatted response to the client
+
+Key components:
+
+- `server.py`: Main FastAPI application with all proxy logic
+- `tests.py`: Test suite for verifying proxy functionality
+## Development Patterns
+
+When working on this project, follow these guidelines:
+
+1. Use type hints and Pydantic models for data validation
+2. Log important events for debugging
+3. Handle errors gracefully and provide informative error messages
+4. Write tests for new functionality
+5. Maintain backward compatibility with the Anthropic API
+6. Keep model mappings updated as new models are released
+
+## Code Style Guidelines
+
+1. DO NOT add inline comments for code that is self-explanatory
+2. Only add comments for complex logic that requires explanation
+3. Keep code clean and readable without relying on comments
+4. Use descriptive variable and function names instead of comments
+5. Use comments sparingly and only when they add genuine value
+6. For Docker and shell scripts, avoid obvious comments - the commands should be self-explanatory

Dockerfile

@@ -0,0 +1,24 @@
+FROM python:3.10-slim
+
+RUN useradd -m appuser
+
+WORKDIR /app
+RUN chown -R appuser:appuser /app
+
+RUN pip install --no-cache-dir uv
+
+COPY pyproject.toml ./
+COPY server.py ./
+
+RUN chown -R appuser:appuser /app
+
+USER appuser
+
+RUN uv venv && . .venv/bin/activate && uv pip install -e .
+
+EXPOSE 8082
+
+ENV PYTHONUNBUFFERED=1
+ENV PATH="/app/.venv/bin:$PATH"
+
+CMD ["/app/.venv/bin/uvicorn", "server:app", "--host", "0.0.0.0", "--port", "8082"]

README.md

@@ -17,6 +17,41 @@ A proxy server that lets you use Anthropic clients with Gemini or OpenAI models
 
 ### Setup 🛠️
 
+You can set up the proxy server either manually or using the provided setup script.
+
+#### Option 1: Using Setup Script (Recommended)
+
+1. **Clone this repository**:
+   ```bash
+   git clone https://github.com/1rgs/claude-code-openai.git
+   cd claude-code-openai
+   ```
+
+2. **Run the setup script**:
+   ```bash
+   ./setup.sh
+   ```
+
+   This script will:
+   - Check your Python version
+   - Install uv if not already installed
+   - Create and activate a virtual environment
+   - Install all dependencies
+   - Create a .env file if one doesn't exist
+
+3. **Update your API keys**:
+   Edit the `.env` file with your API keys.
+
+   Note: The `.env.example` file must always be present in the project root directory.
+
+4. **Run the server**:
+   ```bash
+   source venv/bin/activate
+   python -m uvicorn server:app --host 0.0.0.0 --port 8082 --reload
+   ```
+
+#### Option 2: Manual Setup
+
 1. **Clone this repository**:
    ```bash
    git clone https://github.com/1rgs/claude-code-openai.git
@@ -153,6 +188,54 @@ This proxy works by:
 
 The proxy handles both streaming and non-streaming responses, maintaining compatibility with all Claude clients. 🌊
 
+## Docker Deployment 🐳
+
+You can run the proxy server using Docker for easier deployment:
+
+### Using Docker Compose
+
+1. **Configure Environment**:
+   ```bash
+   cp .env.example .env
+   ```
+   Edit `.env` with your API keys as described in the Setup section.
+
+2. **Build and Run**:
+   ```bash
+   docker compose up -d
+   ```
+
+3. **Connect**:
+   ```bash
+   ANTHROPIC_BASE_URL=http://localhost:8082 claude
+   ```
+
+### Manual Docker Build
+
+1. **Build the Docker image**:
+   ```bash
+   docker build -t claude-code-proxy .
+   ```
+
+2. **Run the container**:
+   ```bash
+   docker run -d \
+     -p 8082:8082 \
+     -e OPENAI_API_KEY="your-openai-key" \
+     -e PREFERRED_PROVIDER="openai" \
+     --name claude-code-proxy \
+     claude-code-proxy
+   ```
+
+   Alternatively, use environment variables from your .env file:
+   ```bash
+   docker run -d \
+     -p 8082:8082 \
+     --env-file .env \
+     --name claude-code-proxy \
+     claude-code-proxy
+   ```
+
 ## Contributing 🤝
 
 Contributions are welcome! Please feel free to submit a Pull Request. 🎁

docker-build.sh

@@ -0,0 +1,23 @@
+#!/bin/bash
+[ "$1" = -x ] && shift && set -x
+DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+set -e
+
+cd "${DIR}"
+
+TAG=$1
+
+if [[ -z "${TAG}" ]]; then
+  TAG=${CLAUDE_CODE_PROXY_DOCKER_TAG}
+fi
+
+if [[ -z "${TAG}" ]]; then
+  TAG=latest
+fi
+
+LOCAL_DOCKER_IMG=claude-code-proxy:${TAG}
+
+set -e
+
+docker build -t "${LOCAL_DOCKER_IMG}" .

docker-compose-start.sh

@@ -0,0 +1,13 @@
+#!/bin/bash
+[ "$1" = -x ] && shift && set -x
+DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+set -e
+
+cd "${DIR}"
+
+docker compose build
+
+docker compose up -d
+
+docker compose logs -f claude-code-proxy

docker-compose.yml

@@ -0,0 +1,23 @@
+services:
+  claude-code-proxy:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    ports:
+      - "8082:8082"
+    environment:
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - GEMINI_API_KEY=${GEMINI_API_KEY}
+      - ANTHROPIC_API_KEY=${ANTHROPIC_API_KEY}
+      - PREFERRED_PROVIDER=${PREFERRED_PROVIDER:-openai}
+      - BIG_MODEL=${BIG_MODEL:-gpt-4.1}
+      - SMALL_MODEL=${SMALL_MODEL:-gpt-4.1-mini}
+    volumes:
+      - ./.env:/app/.env:ro
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8082/"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 5s

docker-push.sh

@@ -0,0 +1,33 @@
+#!/bin/bash
+[ "$1" = -x ] && shift && set -x
+DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
+
+set -e
+
+cd "${DIR}"
+
+TAG=$1
+
+if [[ -z "${TAG}" ]]; then
+  TAG=${CLAUDE_CODE_PROXY_DOCKER_TAG}
+fi
+
+if [[ -z "${TAG}" ]]; then
+  TAG=latest
+fi
+
+LOCAL_DOCKER_IMG=claude-code-proxy:${TAG}
+
+if [[ -z "${DOCKER_REMOTE_REGISTRY}" ]]; then
+  echo "DOCKER_REMOTE_REGISTRY is not set" >&2
+
+  exit 1
+fi
+
+REMOTE_DOCKER_IMG=${DOCKER_REMOTE_REGISTRY}/${LOCAL_DOCKER_IMG}
+
+set -e
+
+docker tag "${LOCAL_DOCKER_IMG}" "${REMOTE_DOCKER_IMG}"
+
+docker push "${REMOTE_DOCKER_IMG}"