When a workflow is cancelled, the comment now shows "Claude's task was cancelled"
instead of the generic "Claude encountered an error" message. This provides clearer
feedback to users about why the workflow stopped.
Changes:
- Add CLAUDE_CANCELLED environment variable using cancelled() function in action.yml
- Implement cancellation detection logic in update-comment-link.ts
- Update comment-logic.ts to show specific cancellation message
- Add comprehensive tests for cancellation handling
Fixes#123
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
- Changed CLAUDE_SUCCESS check from !== "false" to === "true" for more explicit handling
- This ensures undefined or empty values are treated as failures
- Moved status check before output file parsing to ensure consistent behavior
- Added comprehensive tests for various workflow status scenarios
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Update the MCP configuration structure to properly wrap the github
server configuration within an mcpServers object, matching the
expected format for MCP config files.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add claude_env input for custom environment variables
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
* docs: add claude_env input documentation with clear syntax examples
Added comprehensive documentation for the new claude_env input including:
- Entry in the Inputs table with description
- Example in the basic workflow configuration
- Detailed section in Advanced Configuration with practical use cases
This makes it clear how users can pass custom environment variables
to Claude Code execution in YAML format for CI/test setups.
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
---------
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
* feat: add unified update_claude_comment tool
- Add new update_claude_comment tool that automatically handles both issue and PR comments
- Remove individual update_issue_comment and update_pull_request_comment tools
- Pass CLAUDE_COMMENT_ID, GITHUB_EVENT_NAME, and IS_PR to MCP server environment
- Simplify Claude's comment update workflow by removing need for owner/repo/commentId params
- Update prompts and tests to use the new unified tool
* feat: add unified update_claude_comment tool
- Add new update_claude_comment tool that automatically handles both issue and PR comments
- Remove individual update_issue_comment and update_pull_request_comment tools
- Pass CLAUDE_COMMENT_ID, GITHUB_EVENT_NAME, and IS_PR to MCP server environment
- Use Octokit instead of raw fetch for better type safety and error handling
- Simplify Claude's comment update workflow by removing need for owner/repo/commentId params
- Update prompts and tests to use the new unified tool
* refactor: extract update_claude_comment logic to standalone testable function
- Create new updateClaudeComment function in operations/comments
- Add comprehensive unit tests following image-downloader pattern
- Update MCP server to use extracted function
- Refactor update-comment-link.ts and update-with-branch.ts to eliminate duplication
- All tests passing (10 new tests for update-claude-comment)
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
* prettier
* tsc
* clean up comments
---------
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
The last message in the Claude Code output does not have a role, but instead has a field "type" set to "result". With the current condition, the duration is never appended to the header of the comments.
- Add FAQ.md with sections on triggering, authentication, capabilities, and troubleshooting
- Document key limitations including workflow access, PR creation, and CI results visibility
- Include workarounds for common issues like automated workflows and test result access
- Cover security considerations and best practices for safe usage
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* Add enhanced text sanitization
* Format code with prettier
* Refactor tests to remove redundancy and improve structure
- Remove redundant 'mixed input patterns' test from sanitizer.test.ts
- Consolidate integration tests into 2 focused real-world scenarios
- Add HTML comment stripping to sanitizeContent function
- Update test expectations to match sanitization behavior
- Maintain full coverage with fewer, more focused tests
* Fix prettier formatting
* Remove rendered.html from repository
* Remove test-markdown.json and update .gitignore
* Revert .gitignore changes
The workflow was using 'mcp_config_file' which is not a valid parameter for
the claude-code-base-action. The correct parameter name is 'mcp_config' as
defined in the action.yml file.
This fix ensures that the MCP server configuration is properly passed to the
action, allowing the GitHub MCP server to be correctly initialized.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add base_branch input to specify source branch for new Claude branches
- Add base_branch input parameter to action.yml allowing users to specify which branch to use as source
- Update setupBranch function to accept and use the base branch parameter
- Defaults to repository default branch if no base branch is specified
- Addresses issue #62 for better branch control
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
* perf: optimize setupBranch to avoid unnecessary default branch fetch
Only fetch repository default branch when actually needed:
- Skip initial fetch when baseBranch is provided
- Fetch default branch at end only for return value and GitHub Actions output
- Eliminates unnecessary API call when users specify base branch
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
* fix: properly handle base branch throughout the action workflow
- Fix TypeScript error where defaultBranch was used before being assigned
- Replace DEFAULT_BRANCH with BASE_BRANCH in subsequent workflow steps
- Update PR creation and branch comparison to use the actual base branch
- Ensure custom base_branch input is respected in all operations
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: move BASE_BRANCH env reading into parseGitHubContext
- Move BASE_BRANCH environment variable reading into parseGitHubContext for consistency
- Update setupBranch to use context.inputs.baseBranch instead of process.env
- Fix test descriptions to correctly reference BASE_BRANCH instead of DEFAULT_BRANCH
- Update test environment setup to use BASE_BRANCH
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
* feat: display detailed error messages when prepare step fails
- Capture prepare step errors in action.yml (up to 2000 chars)
- Add error details to comment update with collapsible section
- Handle both prepare and Claude execution failures separately
- Add test coverage for error detail display
This helps users debug issues like git errors, permission problems,
and branch creation failures more easily.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: simplify error capture to show clean error messages only
- Remove complex shell script that captured full output logs
- Use core.setOutput in prepare.ts to pass clean error message directly
- Avoid exposing potentially sensitive information from logs
- Show only the actual error message (e.g. 'Failed to fetch issue data')
This provides cleaner, more readable error messages without the risk
of exposing sensitive information from debug logs.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: simplify error display to show clean error messages only
- Remove collapsible <details> section for error messages
- Display errors in simple code blocks since messages are now clean and short
- Makes error messages more direct and readable
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: allow user override of hardcoded disallowed tools
Allow users to override hardcoded disallowed tools (WebSearch, WebFetch) by including them in their allowed_tools configuration. This provides users with the ability to control tool access based on their security requirements.
Changes:
- Modified buildDisallowedToolsString() to accept allowedTools parameter
- Added logic to filter out hardcoded disallowed tools if present in allowed tools
- Updated function call site to pass allowedTools
- Added comprehensive test coverage for override behavior
- Maintains backward compatibility
Resolves#49
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
* prettier
---------
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
* Add shallow fetch to improve performance for large repositories
This change adds `--depth=1` to git fetch operations to perform shallow
fetches instead of full history downloads. This significantly reduces
checkout time for large repositories as reported in issue #52.
Changes:
- Line 55: Added --depth=1 to PR branch fetch
- Line 102: Added --depth=1 to new branch fetch
Fixes#52
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
* fetch 50 commits for PRs
---------
Co-authored-by: claude[bot] <209825114+claude[bot]@users.noreply.github.com>
Co-authored-by: ashwin-ant <ashwin-ant@users.noreply.github.com>
Pin oven-sh/setup-bun and anthropics/claude-code-base-action to specific commit SHAs instead of version tags to ensure reproducible builds and improve supply chain security.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
- Add helpful hint about workflow permissions when OIDC token is not found
- Include response body in app token exchange failure errors for better debugging
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
- Add error field to MCP error responses to fix 'undefined' errors
- Add REPO_DIR environment variable to fix file path resolution
- Use GITHUB_WORKSPACE for correct repository directory
- Simplify path processing logic in commit_files tool
This fixes the issue where mcp__github_file_ops__commit_files would fail
with 'Error calling tool commit_files: undefined' by ensuring error messages
are properly formatted and files are read from the correct directory.
The table row was broken across two lines which caused markdown rendering issues.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
This updates claude-code-action to pass the model parameter to claude-code-base-action using the new primary `model` parameter instead of the deprecated `anthropic_model`.
This change is made in conjunction with https://github.com/anthropics/claude-code-base-action/pull/4 which adds the `model` parameter to claude-code-base-action.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
