github actions for container, CLAUDE_MODELS_OVERRIDE, bump sdk

.env.example

@@ -13,6 +13,8 @@ CLAUDE_CLI_PATH=claude
 
 # Server Configuration
 PORT=8000
+# Maximum number of concurrent CLI processes allowed (default: 3)
+# MAX_CONCURRENT_PROCESSES=3
 # Host binding address - use 127.0.0.1 for local-only access, 0.0.0.0 for all interfaces
 # CLAUDE_WRAPPER_HOST=0.0.0.0
 # Maximum request body size in bytes (default: 10MB)
@@ -21,12 +23,18 @@ PORT=8000
 # Timeout Configuration (milliseconds)
 MAX_TIMEOUT=600000
 
+# Prewarming Configuration
+# Prompt to use during startup for prewarming the CLI backends (default: Hello)
+# PREWARM_PROMPT=Hello
+
 # CORS Configuration
 CORS_ORIGINS=["*"]
 
 # Model Configuration
 # Default Claude model to use when none specified in request
-DEFAULT_MODEL=claude-sonnet-4-5-20250929
+DEFAULT_MODEL=claude-sonnet-4-6
+# Fast Claude model for speed/cost-optimized paths
+FAST_MODEL=claude-haiku-4-5-20251001
 
 # Rate Limiting Configuration
 RATE_LIMIT_ENABLED=true
@@ -35,4 +43,14 @@ RATE_LIMIT_CHAT_PER_MINUTE=10
 RATE_LIMIT_DEBUG_PER_MINUTE=2
 RATE_LIMIT_AUTH_PER_MINUTE=10
 RATE_LIMIT_SESSION_PER_MINUTE=15
-RATE_LIMIT_HEALTH_PER_MINUTE=30
+RATE_LIMIT_HEALTH_PER_MINUTE=30
+
+# Security Configuration
+# Comma-separated list of trusted proxy IPs (for X-Forwarded-For rate limiting)
+# TRUSTED_PROXIES=10.0.0.1,10.0.0.2
+# Base directory for CLAUDE_CWD sandboxing (default: system temp dir)
+# CLAUDE_CWD_ALLOWED_BASE=/tmp
+# Maximum concurrent sessions (default: 1000)
+# MAX_SESSIONS=1000
+# Maximum messages per session history (default: 100)
+# MAX_SESSION_MESSAGES=100

.github/workflows/ci.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: ["3.10", "3.11", "3.12"]
+        python-version: ["3.12"]
 
     steps:
       - uses: actions/checkout@v4
@@ -52,14 +52,14 @@ jobs:
         run: poetry run bandit -r src/ -ll -x tests
 
       - name: Dependency vulnerability scan
-        run: poetry run safety check || true
+        run: poetry run safety scan || true
         continue-on-error: true
 
       - name: Run tests
         run: poetry run pytest tests/ -v --cov=src --cov-report=xml --cov-report=term-missing
 
       - name: Upload coverage to Codecov
-        if: matrix.python-version == '3.11'
+        if: matrix.python-version == '3.12'
         uses: codecov/codecov-action@v4
         with:
           files: ./coverage.xml

.github/workflows/docker.yml

@@ -0,0 +1,50 @@
+name: Build and push container image to GHCR
+
+on:
+  push:
+    branches:
+      - main
+  workflow_dispatch:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: read
+      packages: write
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Docker meta
+        id: meta
+        uses: docker/metadata-action@v5
+        with:
+          images: ghcr.io/${{ github.repository }}
+          tags: |
+            type=sha
+            type=raw,value=latest
+
+      - name: Build and push
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          push: true
+          platforms: linux/amd64
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max

.gitignore

@@ -40,6 +40,7 @@ logs/
 # Testing
 .coverage
 .pytest_cache/
+.hypothesis/
 htmlcov/
 
 # Claude Code
@@ -57,4 +58,5 @@ test_debug_*.py
 test_performance_*.py
 test_user_*.py
 test_new_*.py
-test_roocode_compatibility.py
+test_roocode_compatibility.py
+.worktrees/

Dockerfile

@@ -1,30 +1,58 @@
-FROM python:3.12-slim
+# Stage 1: Builder — install Poetry and dependencies
+FROM python:3.12-slim AS builder
 
-# Install system deps (curl for Poetry installer)
 RUN apt-get update && apt-get install -y \
     curl \
     && rm -rf /var/lib/apt/lists/*
 
-# Install Poetry globally
 RUN curl -sSL https://install.python-poetry.org | python3 -
-
-# Add Poetry to PATH
 ENV PATH="/root/.local/bin:${PATH}"
 
-# Note: Claude Code CLI is bundled with claude-agent-sdk >= 0.1.8
-# No separate Node.js/npm installation required
+WORKDIR /app
+
+# Copy dependency files first (cache-friendly)
+COPY pyproject.toml poetry.lock ./
 
-# Copy the app code
-COPY . /app
+# Install dependencies into a virtualenv
+RUN poetry config virtualenvs.in-project true && \
+    poetry install --no-root --no-interaction
+
+# Copy application code
+COPY . .
+
+# Install the project itself
+RUN poetry install --no-interaction
+
+
+# Stage 2: Runtime — minimal image with non-root user
+FROM python:3.12-slim
+
+# Install Node.js (required by Claude Agent SDK bundled CLI)
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    curl \
+    && curl -fsSL https://deb.nodesource.com/setup_22.x | bash - \
+    && apt-get install -y --no-install-recommends nodejs \
+    && rm -rf /var/lib/apt/lists/*
+
+# Create non-root user
+RUN groupadd --gid 1000 appuser && \
+    useradd --uid 1000 --gid appuser --create-home appuser
 
-# Set working directory
 WORKDIR /app
 
-# Install Python dependencies with Poetry
-RUN poetry install --no-root
+# Copy virtualenv and app code from builder (owned by appuser)
+COPY --from=builder --chown=appuser:appuser /app/.venv /app/.venv
+COPY --from=builder --chown=appuser:appuser /app/src /app/src
+COPY --from=builder --chown=appuser:appuser /app/pyproject.toml /app/pyproject.toml
+
+# Ensure virtualenv binaries are on PATH
+ENV PATH="/app/.venv/bin:${PATH}"
+ENV VIRTUAL_ENV="/app/.venv"
+
+# Switch to non-root user
+USER appuser
 
-# Expose the port (default 8000)
 EXPOSE 8000
 
-# Run the app with Uvicorn (development mode with reload; switch to --no-reload for prod)
-CMD ["poetry", "run", "uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "8000", "--reload"]
+# Production CMD — no --reload
+CMD ["uvicorn", "src.main:app", "--host", "0.0.0.0", "--port", "8000"]

PR.md

@@ -0,0 +1,24 @@
+# Release v2.3.0: Concurrency improvements, SDK options wiring, and critical bug fixes
+
+This PR introduces version 2.3.0, focusing on significant reliability improvements, full support for concurrent SDK calls, wiring of new Claude API options, and resolutions for several critical proxy bugs.
+
+## Features & Enhancements
+* **SDK Options Wiring:** Full support for `reasoning_effort`, `response_format`, `thinking`, `max_budget_usd`, and `user` fields passed directly to the Claude SDK.
+* **Concurrency:** Removed `os.environ` mutex (`_env_lock`) by passing auth via `options.env`, allowing fully concurrent SDK calls. `SessionManager` has been refactored to use `asyncio.Lock` with all session methods converted to async.
+* **Token & Reason Mapping:** Extracts real token counts directly from the SDK's `ResultMessage` and properly maps `stop_reason` to `finish_reason` (e.g., `max_tokens` → `length`).
+* **Tool Handling:** Changed `AnthropicMessagesRequest.enable_tools` default to `False` so simple message requests do not trigger unintended 10-turn loops. 
+
+## Bug Fixes
+* **Session Continuity:** Fixed session continuation by correcting `continue_session` to `continue_conversation` and replaced list appending with replacement to prevent exponential duplication.
+* **Timeouts & Hangs:** Wrapped async `query()` iterations with `asyncio.timeout` to prevent indefinite hangs when the SDK subprocess stalls.
+* **Proxy Reliability:** 
+  * Removed `filter_content()` from user input which was silently stripping XML-like tags.
+  * Secured `/v1/auth/status` endpoint with the `verify_api_key()` auth guard.
+  * Marked the Bash tool as `is_safe=False`.
+  * Replaced bare `except:` clauses with `except Exception:`.
+
+## Maintenance & Chores
+* Updated `poetry.lock` and the test suite for compatibility with `pydantic 2.13` and `poetry 2.3`.
+* Replaced deprecated `datetime.utcnow()` with `datetime.now(timezone.utc)`.
+* Ignored `.worktrees` directories in `.gitignore`.
+* Added diagnostic print statements for `/v1/messages` and improved the `test_message.py` script.