This PR updates the version to 0.0.17 after publishing to PyPI.
## Changes
- Updated version in `pyproject.toml`
- Updated version in `src/claude_code_sdk/__init__.py`
## Release Information
- Published to PyPI: https://pypi.org/project/claude-code-sdk/0.0.17/
- Install with: `pip install claude-code-sdk==0.0.17`
🤖 Generated by GitHub Actions
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
## Summary
- Replace asyncio.create_task() with anyio task group for trio
compatibility
- Update client.py docstring example to use anyio.sleep
- Add trio example demonstrating multi-turn conversation
## Details
The SDK already uses anyio for most async operations, but one line was
using asyncio.create_task() which broke trio compatibility. This PR
fixes that by using anyio's task group API with proper lifecycle
management.
### Changes:
1. **subprocess_cli.py**: Replace asyncio.create_task() with anyio task
group, ensuring proper cleanup on disconnect
2. **client.py**: Update docstring example to use anyio.sleep instead of
asyncio.sleep
3. **streaming_mode_trio.py**: Add new example showing how to use the
SDK with trio
## Test plan
- [x] All existing tests pass
- [x] Manually tested with trio runtime (created test script that
successfully runs multi-turn conversation)
- [x] Linting and type checking pass
🤖 Generated with [Claude Code](https://claude.ai/code)
This PR updates the version to 0.0.16 after publishing to PyPI.
## Changes
- Updated version in `pyproject.toml`
- Updated version in `src/claude_code_sdk/__init__.py`
## Release Information
- Published to PyPI: https://pypi.org/project/claude-code-sdk/0.0.16/
- Install with: `pip install claude-code-sdk==0.0.16`
🤖 Generated by GitHub Actions
---------
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
* Adds commit signing
* Converts sed pattern matching to a script to ensure we don't update
version values unrelated to PyPI
* Remove the `Publish to Test PyPI first'` step since it no longer works
- Uses claude-code-base-action for automated issue triage
- Analyzes new issues and applies appropriate labels
- Uses GitHub MCP server for issue operations
- Requires ANTHROPIC_API_KEY secret to be configured
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
This PR updates the version to 0.0.14 after publishing to PyPI.
## Changes
- Updated version in `pyproject.toml`
- Updated version in `src/claude_code_sdk/__init__.py`
## Release Information
- Published to PyPI: https://pypi.org/project/claude-code-sdk/0.0.14/
- Install with: `pip install claude-code-sdk==0.0.14`
## Next Steps
After merging this PR, a release tag will be created automatically.
Signed-off-by: Lina <lina@anthropic.com>
Add critical safety mechanisms to the sequential stderr reading approach:
- 10MB memory limit on stderr collection with truncation message
- 30 second timeout protection to prevent hanging
- Proper exit code based error detection instead of string matching
- Debug logging for stderr on successful runs
- Better exception handling for edge cases
This addresses potential production issues while maintaining FastAPI compatibility.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
The test was checking source code for specific strings rather than
testing behavior. The existing subprocess tests already verify the
functionality works correctly.
Remove anyio.create_task_group() from receive_messages() to fix the
RuntimeError "Attempted to exit cancel scope in a different task than
it was entered in" when using the SDK with FastAPI's SSE streaming.
The issue occurred because FastAPI can move async generators between
different asyncio tasks during the streaming lifecycle, which conflicts
with anyio's cancel scope tracking.
Changes:
- Remove task group usage from receive_messages()
- Read stderr sequentially after stdout completes
- Add test to ensure no task groups are used
- Fix existing test expectation for buffer overflow
This is a minimal fix that maintains compatibility while solving the
core issue. The trade-off is that stderr is read after stdout instead
of concurrently, but this is unlikely to cause issues in practice.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Removed redundant comments that simply restate what the code is doing.
Kept only comments that provide valuable context or explain complex behavior.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
The CLIJSONDecodeError constructor expects an Exception as the second
argument, not None. Changed to pass a ValueError with details about
the buffer size limit being exceeded.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Adds buffering to accumulate incomplete JSON messages that are split
across multiple stream reads due to asyncio's 64KB default buffer limit.
- Implement 1MB buffer to accumulate partial JSON
- Clear buffer on successful parse or size limit exceeded
- Add comprehensive tests for split JSON scenarios
Fixes CLIJSONDecodeError when reading large minified JSON files.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
- Update publish.yml to create PR after publishing
- Add create-release-tag.yml to tag releases when PR merges
- Eliminates manual version syncing between repo and PyPI
