No description
Find a file
Dickson Tsai fbda510ee4
Some checks are pending
Lint / lint (push) Waiting to run
Test / test (3.10) (push) Waiting to run
Test / test (3.11) (push) Waiting to run
Test / test (3.12) (push) Waiting to run
Test / test (3.13) (push) Waiting to run
Fix subprocess deadlock with MCP servers via stderr redirection (#103)
## Summary

Fixes a critical deadlock issue that occurs when MCP servers produce
verbose stderr output. The SDK would hang indefinitely when the stderr
pipe buffer filled up.

## The Problem

The deadlock occurred due to sequential reading of subprocess streams:
1. SDK reads stdout completely before reading stderr
2. When stderr pipe buffer fills (64KB on Linux, 16KB on macOS),
subprocess blocks on write
3. Subprocess can't continue to stdout, parent waits for stdout →
**DEADLOCK** 🔒

## The Solution  

Redirect stderr to a temporary file instead of a pipe:
- **No pipe buffer** = no possibility of deadlock
- Temp file can grow as needed (no 64KB limit)
- Still capture stderr for error reporting (last 100 lines)
- Works consistently across all async backends

## Implementation Details

- `stderr=tempfile.NamedTemporaryFile()` instead of `stderr=PIPE`
- Use `deque(maxlen=100)` to keep only recent stderr lines in memory
- Temp file is automatically cleaned up on disconnect
- Add `[stderr truncated, showing last 100 lines]` message when buffer
is full

## Testing

- Verified no deadlock with 150+ lines of stderr output
- Confirmed stderr is still captured for error reporting
- All existing tests pass
- Works with asyncio, trio, and other anyio backends

## Impact

- Fixes consistent hangs in production with MCP servers
- No functional regression - stderr handling is preserved
- Simpler than concurrent reading alternatives
- More robust than pipe-based solutions

Fixes the issue reported in Slack where SDK would hang indefinitely when
receiving messages from MCP servers with verbose logging.

🤖 Generated with [Claude Code](https://claude.ai/code)

---------

Co-authored-by: Claude <noreply@anthropic.com>
2025-07-31 11:42:20 -07:00
.github/workflows Fix "Publish to PyPI" workflow: Add commit signing and improve diff (#82) 2025-07-21 09:53:24 -07:00
examples Improve UserMessage types to include ToolResultBlock (#101) 2025-07-31 07:51:39 -07:00
scripts Fix "Publish to PyPI" workflow: Add commit signing and improve diff (#82) 2025-07-21 09:53:24 -07:00
src/claude_code_sdk Fix subprocess deadlock with MCP servers via stderr redirection (#103) 2025-07-31 11:42:20 -07:00
tests Improve UserMessage types to include ToolResultBlock (#101) 2025-07-31 07:51:39 -07:00
.gitignore Initial Python SDK import 2025-06-12 00:16:19 -07:00
CHANGELOG.md Add settings option to ClaudeCodeOptions (#100) 2025-07-30 23:59:21 -07:00
CLAUDE.md Fix lint and test 2025-07-19 20:04:58 -07:00
LICENSE Initial Python SDK import 2025-06-12 00:16:19 -07:00
pyproject.toml chore: bump version to 0.0.18 (#102) 2025-07-31 11:02:29 -07:00
README.md fix: update the tool list in README.md 2025-06-27 06:30:54 +10:00

Claude Code SDK for Python

Python SDK for Claude Code. See the Claude Code SDK documentation for more information.

Installation

pip install claude-code-sdk

Prerequisites:

  • Python 3.10+
  • Node.js
  • Claude Code: npm install -g @anthropic-ai/claude-code

Quick Start

import anyio
from claude_code_sdk import query

async def main():
    async for message in query(prompt="What is 2 + 2?"):
        print(message)

anyio.run(main)

Usage

Basic Query

from claude_code_sdk import query, ClaudeCodeOptions, AssistantMessage, TextBlock

# Simple query
async for message in query(prompt="Hello Claude"):
    if isinstance(message, AssistantMessage):
        for block in message.content:
            if isinstance(block, TextBlock):
                print(block.text)

# With options
options = ClaudeCodeOptions(
    system_prompt="You are a helpful assistant",
    max_turns=1
)

async for message in query(prompt="Tell me a joke", options=options):
    print(message)

Using Tools

options = ClaudeCodeOptions(
    allowed_tools=["Read", "Write", "Bash"],
    permission_mode='acceptEdits'  # auto-accept file edits
)

async for message in query(
    prompt="Create a hello.py file", 
    options=options
):
    # Process tool use and results
    pass

Working Directory

from pathlib import Path

options = ClaudeCodeOptions(
    cwd="/path/to/project"  # or Path("/path/to/project")
)

API Reference

query(prompt, options=None)

Main async function for querying Claude.

Parameters:

  • prompt (str): The prompt to send to Claude
  • options (ClaudeCodeOptions): Optional configuration

Returns: AsyncIterator[Message] - Stream of response messages

Types

See src/claude_code_sdk/types.py for complete type definitions:

  • ClaudeCodeOptions - Configuration options
  • AssistantMessage, UserMessage, SystemMessage, ResultMessage - Message types
  • TextBlock, ToolUseBlock, ToolResultBlock - Content blocks

Error Handling

from claude_code_sdk import (
    ClaudeSDKError,      # Base error
    CLINotFoundError,    # Claude Code not installed
    CLIConnectionError,  # Connection issues
    ProcessError,        # Process failed
    CLIJSONDecodeError,  # JSON parsing issues
)

try:
    async for message in query(prompt="Hello"):
        pass
except CLINotFoundError:
    print("Please install Claude Code")
except ProcessError as e:
    print(f"Process failed with exit code: {e.exit_code}")
except CLIJSONDecodeError as e:
    print(f"Failed to parse response: {e}")

See src/claude_code_sdk/_errors.py for all error types.

Available Tools

See the Claude Code documentation for a complete list of available tools.

Examples

See examples/quick_start.py for a complete working example.

License

MIT