Currently wheels with packaged claude-code CLI are only published for
windows amd64, linux x86_64 and macos arm64. For version 0.1.10, we can
see the following download files are available on pypi contain the
following artifacts:
https://pypi.org/project/claude-agent-sdk/0.1.10/#files
- claude_agent_sdk-0.1.10.tar.gz
- claude_agent_sdk-0.1.10-py3-none-win_amd64.whl
- claude_agent_sdk-0.1.10-py3-none-manylinux_2_17_x86_64.whl
- claude_agent_sdk-0.1.10-py3-none-macosx_11_0_arm64.whl
The existing publishing code should support adding a new linux arm64
wheel builder, using the Github ARM runners:
https://github.blog/changelog/2025-08-07-arm64-hosted-runners-for-public-repositories-are-now-generally-available/
Unfortunately, there's no `ubuntu-latest-arm` label similar to the one
we use for the other builds, so I'm using the `ubuntu-24.04-arm` label.
Posts new issues to claude-agent-sdk-feedback. Can't use the default
github slack bot as it's too noisy (all comments and issue updates such
as comments, closing, etc...)
---------
Co-authored-by: Ashwin Bhat <ashwin@anthropic.com>
Remove the claude_code_version workflow input and instead read the CLI
version directly from src/claude_agent_sdk/_cli_version.py. This allows
the version to be managed separately and updated by automation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
The build_wheel.py script uses `python -m wheel tags` to retag wheels
with platform-specific tags, but `wheel` wasn't explicitly installed.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Wheels are already ZIP files - double compression via GitHub Actions
artifacts can cause "Mis-matched data size" errors on PyPI upload.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Bundle platform-specific Claude Code CLI binaries directly in the Python
package, eliminating the need for separate CLI installation.
## Changes
### Build System
- Created `scripts/download_cli.py` to fetch CLI during build
- Created `scripts/build_wheel.py` for building platform-specific wheels
- Created `scripts/update_cli_version.py` to track bundled CLI version
- Updated `pyproject.toml` to properly bundle CLI without duplicate file
warnings
- Made twine check non-blocking (License-File warnings are false
positives)
### Runtime
- Modified `subprocess_cli.py` to check for bundled CLI first
- Added `_cli_version.py` to track which CLI version is bundled
- SDK automatically uses bundled CLI, falling back to system
installation if not found
- Users can still override with `cli_path` option
### Release Workflow
- Updated GitHub workflow to build separate wheels per platform (macOS,
Linux, Windows)
- Workflow now accepts two inputs:
- `version`: Package version to publish (e.g., `0.1.5`)
- `claude_code_version`: CLI version to bundle (e.g., `2.0.0` or
`latest`)
- Workflow builds platform-specific wheels with bundled CLI
- Creates release PR that updates:
- `pyproject.toml` version
- `src/claude_agent_sdk/_version.py`
- `src/claude_agent_sdk/_cli_version.py` with bundled CLI version
- `CHANGELOG.md` with auto-generated release notes
### Documentation
- Updated README to reflect bundled CLI (removed Node.js requirement)
- Added release workflow documentation
- Added local wheel building instructions
## Benefits
- **Zero external dependencies**: No need for Node.js or npm
- **Easier installation**: Single `pip install` gets everything
- **Version control**: Track exactly which CLI version is bundled
- **Flexible releases**: Can release new package versions with updated
CLI without code changes
- **Better user experience**: Works out of the box with no setup
Platform-specific wheels are automatically selected by pip during
installation based on the user's OS and architecture.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Reduce CI job count by only running examples on Python 3.13 instead of
all Python versions (3.10-3.13). This reduces the combinatorial
explosion while still ensuring examples work on the latest Python
version.
Co-authored-by: Claude <noreply@anthropic.com>
Move changelog generation prompt from publish.yml into a reusable slash
command at .claude/commands/generate-changelog.md. Update workflow to
call the command with version parameters.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
The changelog generation step was failing to get the previous release
tag because the checkout action was doing a shallow clone. Adding
fetch-depth: 0 ensures all tags are available for git describe.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Closes the gap between Python and TypeScript SDK hook output types by
adding:
- `reason` field for explaining decisions
- `continue_` field for controlling execution flow
- `suppressOutput` field for hiding stdout
- `stopReason` field for stop explanations
- `decision` now supports both "approve" and "block" (not just "block")
- `AsyncHookJSONOutput` type for deferred hook execution
- Proper typing for `hookSpecificOutput` with discriminated unions
Also adds comprehensive examples and tests:
- New examples in hooks.py demonstrating all new fields
- Unit tests in test_tool_callbacks.py for new output types
- E2E tests in e2e-tests/test_hooks.py with real API calls
- CI integration in .github/workflows/test.yml
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Temporarily removes windows-latest from the test-e2e job matrix to
disable Windows end-to-end testing. Unit tests continue to run on
Windows.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Replace GitHub API-based commits with local git workflow and integrate
claude-code-action to automatically generate changelog entries. The
workflow now:
- Creates release branch locally with version commits
- Uses Claude to review changes and update CHANGELOG.md
- Pushes complete branch with all commits together
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Add cross-platform testing for Windows alongside Linux across all test
jobs (unit tests, e2e tests, and examples). Uses native Windows
installation via PowerShell script and platform-specific timeout
handling for example scripts.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Include the SDK version in the environment when spawning the Claude CLI
process.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Use `gh release create --generate-notes` to automatically include PR
titles, commits, and contributors in release notes instead of static
template text.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
This PR adds support for custom tool callbacks and comprehensive e2e
testing for MCP calculator functionality.
## Key Features Added
- **Custom tool permission callbacks** - Allow dynamic tool permission
control via `can_use_tool` callback
- **E2E test suite** - Real Claude API tests validating MCP tool
execution end-to-end
- **Fixed MCP calculator example** - Now properly uses `allowed_tools`
for permission management
## Changes
### Custom Callbacks
- Added `ToolPermissionContext` and `PermissionResult` types for tool
permission handling
- Implemented `can_use_tool` callback support in SDK client
- Added comprehensive tests in `tests/test_tool_callbacks.py`
### E2E Testing Infrastructure
- Created `e2e-tests/` directory with pytest-based test suite
- `test_mcp_calculator.py` - Tests all calculator operations with real
API calls
- `conftest.py` - Pytest config with mandatory API key validation
- GitHub Actions workflow for automated e2e testing on main branch
- Comprehensive documentation in `e2e-tests/README.md`
### Bug Fixes
- Fixed MCP calculator example to use `allowed_tools` instead of
incorrect `permission_mode`
- Resolved tool permission issues preventing MCP tools from executing
## Testing
E2E tests require `ANTHROPIC_API_KEY` environment variable and will fail
without it.
Run locally:
```bash
export ANTHROPIC_API_KEY=your-key
python -m pytest e2e-tests/ -v -m e2e
```
Run unit tests including callback tests:
```bash
python -m pytest tests/test_tool_callbacks.py -v
```
🤖 Generated with [Claude Code](https://claude.ai/code)
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Kashyap Murali <kashyap@anthropic.com>
## Summary
- Standardized the trigger configuration across test, lint, and e2e
workflows
- All workflows now use consistent format with pull_request listed
before push
- E2E workflow now also runs on pushes to main branch
## Test plan
- [ ] Verify workflows trigger correctly on pull requests
- [ ] Verify workflows trigger correctly on pushes to main branch
- [ ] Check that e2e tests run successfully on main branch
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
- Added GitHub Actions workflow to test SDK integration with Claude Code
CLI
- Tests run on PR open/synchronize events across Python 3.10-3.13
## Test plan
- [x] Workflow triggers on PR events
- [x] Installs Claude Code CLI via official script
- [x] Runs quickstart example
- [x] Runs streaming_mode example
🤖 Generated with [Claude Code](https://claude.ai/code)
---------
Co-authored-by: Claude <noreply@anthropic.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>
- 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
This PR adds a GitHub Actions workflow that enables Claude Code integration in our repository.
Claude Code is an AI coding agent that can help with:
- Bug fixes and improvements
- Documentation updates
- Implementing new features
- Code reviews and suggestions
- Writing tests
- And more\!
Once merged, we'll be able to interact with Claude by mentioning @claude in a pull request or issue comment.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
