* feat: add inline comment MCP server for experimental review mode
- Create standalone inline PR comments without review workflow
- Support single-line and multi-line comments
- Auto-install server when in experimental review mode
- Uses octokit.rest.pulls.createReviewComment() directly
* docs: clarify GitHub code suggestion syntax in inline comment server
Add clear documentation that suggestion blocks replace the entire selected
line range and must be syntactically complete drop-in replacements.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Renamed scripts/pre-push to scripts/pre-commit
- Updated install-hooks.sh to install pre-commit hook
- Hook now runs formatting, type checking, and tests before commit
These git config commands are no longer needed as allowed tools since
Claude should not be modifying git configuration settings. Updated
the corresponding test to reflect this intentional change.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
- Restore prompt file creation logic that was accidentally removed in PR #374
- Agent mode now creates the prompt file directly in prepare() method
- Uses override_prompt or direct_prompt if available, falls back to minimal prompt
- Fixes 'Prompt file does not exist' error for workflow_dispatch and schedule events
- Add TODO comment to refactor this to use createPrompt in the future
Fixes#403
Allows modes to provide custom system prompts that are appended to Claude's base system prompt. This enables mode-specific instructions without modifying the core action logic.
- Add optional getSystemPrompt method to Mode interface
- Implement method in all existing modes (tag, agent, review)
- Update prepare.ts to call getSystemPrompt and export as env var
- Wire up APPEND_SYSTEM_PROMPT in action.yml to pass to base-action
All modes currently return undefined (no additional prompts), but the infrastructure is now in place for future modes to provide custom instructions.
* feat: add slash command shipping infrastructure
- Created /slash-commands/ directory to store bundled slash commands
- Added code-review.md slash command for automated PR reviews
- Modified setup-claude-code-settings.ts to copy slash commands to ~/.claude/
- Added test coverage for slash command installation
- Commands are automatically installed when the GitHub Action runs
* fix: simplify slash command implementation to match codebase patterns
- Reverted to using Bun's $ shell syntax consistently with the rest of the codebase
- Simplified slash command copying to basic shell commands
- Removed unnecessary fs/promises complexity
- Maintained all functionality and test coverage
- More appropriate for GitHub Action context where inputs are trusted
* remove test slash command
* fix: rename slash_commands_dir to experimental_slash_commands_dir
- Added 'experimental' prefix as suggested by Ashwin
- Updated all references in action.yml and base-action
- Restored accidentally removed code-review.md file
---------
Co-authored-by: km-anthropic <km-anthropic@users.noreply.github.com>
Updated all references from ACTIONS_TOKEN to DEFAULT_WORKFLOW_TOKEN to match
the naming convention used in action.yml where the GitHub token is passed as
DEFAULT_WORKFLOW_TOKEN environment variable.
* docs: clarify agent mode only works with workflow_dispatch and schedule events
Updates documentation to match the current implementation where agent mode
is restricted to workflow_dispatch and schedule events only. This addresses
the confusion reported in issues #364 and #376.
Changes:
- Updated README to clearly state agent mode limitations
- Added explicit note that agent mode does NOT work with PR/issue events
- Updated example workflows to only show supported event types
- Updated CLAUDE.md internal documentation
Fixes#364Fixes#376🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* minor formatting update
* update agent mode docs
---------
Co-authored-by: km-anthropic <km-anthropic@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add review mode for PR code reviews
- Add 'review' as a new execution mode in action.yml
- Use default GitHub Action token (ACTIONS_TOKEN) for review mode
- Create review mode implementation with GitHub MCP tools included by default
- Move review-specific prompt to review mode's generatePrompt method
- Add comprehensive review workflow instructions for inline comments
- Fix type safety with proper mode validation
- Keep agent mode's simple inline prompt handling
* docs: add review mode example workflow
* update sample workflow
* fix: update review mode example to use @beta tag
* fix: enable automatic triggering for review mode on PR events
* fix: export allowed tools environment variables in review mode
The GitHub MCP tools were not being properly allowed because review mode
wasn't exporting the ALLOWED_TOOLS environment variable like agent mode does.
This caused all GitHub MCP tool calls to be blocked with permission errors.
* feat: add review mode workflow for testing
* fix: use INPUT_ prefix for allowed/disallowed tools environment variables
The base action expects INPUT_ALLOWED_TOOLS and INPUT_DISALLOWED_TOOLS
(following GitHub Actions input naming convention) but we were exporting
them without the INPUT_ prefix. This was causing the tools to not be
properly allowed in the base action.
* fix: add explicit review tool names and additional workflow permissions
- Add explicit tool names in case wildcards aren't working properly
- Add statuses and checks write permissions to workflow
- Include both github and github_comment MCP server tools
* refactor: consolidate review workflows and use review mode
- Update claude-review.yml to use review mode instead of direct_prompt
- Use km-anthropic fork action
- Remove duplicate claude-review-mode.yml workflow
- Add synchronize event to review PR updates
- Update permissions for review mode (remove id-token, add pull-requests/issues write)
* feat: enhance review mode to provide detailed tracking comment summary
- Update review mode prompt to explicitly request detailed summaries
- Include issue counts, key findings, and recommendations in tracking comment
- Ensure users can see complete review overview without checking each inline comment
* Revert "refactor: consolidate review workflows and use review mode"
This reverts commit 54ca948599.
* fix: address PR review feedback for review mode
- Make generatePrompt required in Mode interface
- Implement generatePrompt in all modes (tag, agent, review)
- Remove unnecessary git/branch operations from review mode
- Restrict review mode triggers to specific PR actions
- Fix type safety issues by removing any types
- Update tests to support new Mode interface
* test: update mode registry tests to include review mode
* chore: run prettier formatting
* fix: make mode parameter required in generatePrompt function
Remove optional mode parameter since the function throws an error when mode is not provided. This makes the type signature consistent with the actual behavior.
* fix: remove last any type and update README with review mode
- Remove any type cast in review mode by using isPullRequestEvent type guard
- Add review mode documentation to README execution modes section
- Update mode parameter description in README configuration table
* mandatory bun format
* fix: improve review mode GitHub suggestion format instructions
- Add clear guidance on GitHub's suggestion block format
- Emphasize that suggestions must only replace the specific commented lines
- Add examples of correct vs incorrect suggestion formatting
- Clarify when to use multi-line comments with startLine and line parameters
- Guide on handling complex changes that require multiple modifications
This should resolve issues where suggestions aren't directly committable.
* Add missing MCP tools for experimental-review mode based on test requirements
* chore: format code
* docs: add experimental-review mode documentation with clear warnings
* docs: remove emojis from experimental-review mode documentation
* docs: clarify experimental-review mode triggers - depends on workflow configuration
* minor format update
* test: fix registry tests for experimental-review mode name change
* refactor: clean up review mode implementation based on feedback
- Remove unused parameters from generatePrompt in agent and review modes
- Keep Claude comment requirement for review mode (tracking comment)
- Add overridePrompt support to review mode
- Remove non-existent MCP tools from review mode allowed list
- Fix unused import in agent mode
These changes address all review feedback while maintaining clean code
and proper functionality.
* fix: remove redundant update_claude_comment from review mode allowed tools
The github_comment server is always included automatically, so we don't
need to explicitly list mcp__github_comment__update_claude_comment in
the allowed tools.
* feat: review mode now uses review body instead of tracking comment
- Remove tracking comment creation from review mode
- Update prompt to instruct Claude to write comprehensive review in body
- Remove comment ID requirement for review mode
- The review submission body now serves as the main review content
This makes review mode cleaner with one less comment on the PR. The
review body contains all the information that would have been in the
tracking comment.
* add back id-token: write for example
* Add PR number for context + make it mandatory to have a PR associated
* add `mcp__github__add_issue_comment` tool
* rename token
* bun format
---------
Co-authored-by: km-anthropic <km-anthropic@users.noreply.github.com>
Update add_pull_request_review_comment_to_pending_review to add_comment_to_pending_review
following upstream change in github/github-mcp-server#697
- Update .github/workflows/claude-review.yml
- Update examples/claude-auto-review.yml
In the previous commit (e07ea013bd), the GITHUB_HOST variable was placed after the image name in the Docker run command, which caused a runtime error. This commit moves the -e option before the image name so it is correctly passed into the container.
* feat: add agent mode for automation scenarios
- Add agent mode that always triggers without checking for mentions
- Implement Mode interface with support for mode-specific tool configuration
- Add getAllowedTools() and getDisallowedTools() methods to Mode interface
- Simplify tests by combining related test cases
- Update documentation and examples to include agent mode
- Fix TypeScript imports to prevent circular dependencies
Agent mode is designed for automation and workflow_dispatch scenarios
where Claude should always run without requiring trigger phrases.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Minor update to readme (from @main to @beta)
* Since workflow_dispatch isn't in the base action, update the examples accordingly
* minor formatting issue
* Update to say beta instead of main
* Fix missed tracking comment to be false
* add schedule & workflow dispatch paths. Also make prepare logic conditional
* tests
* Add test workflow for workflow_dispatch functionality
* Update workflow to use correct branch reference
* remove test workflow dispatch file
* minor lint update
* update workflow dispatch agent example
* minor lint update
* refactor: simplify prepare logic with mode-specific implementations
* ensure tag mode can't work with workflow dispatch and schedule tasks
* simplify: remove workflow_dispatch/schedule from create-prompt
- Remove workflow_dispatch and schedule event handling from create-prompt
since agent mode doesn't use the standard prompt generation flow
- Enforce mode compatibility at selection time in the registry instead
of runtime validation in tag mode
- Add explanatory comment in agent mode about why prompt file is needed
- Update tests to reflect simplified event handling
This reduces code duplication and makes the separation between tag mode
(entity-based events) and agent mode (automation events) clearer.
* simplify PR by making agent mode only work with workflow dispatch and schedule events
* remove unnecessary changes
* remove unnecessary changes from PR
- Revert update-comment-link.ts changes (agent mode doesn't use this)
- Revert create-initial.ts changes (agent mode doesn't create comments)
- Remove unused default-branch.ts file
- Revert install-mcp-server.ts changes (agent mode uses minimal MCP)
These files are only used by tag mode for entity-based events, not needed
for workflow_dispatch/schedule support via agent mode.
* fix: handle optional entityNumber for TypeScript
- Add runtime checks in files that require entityNumber
- These files are only used by tag mode which always has entityNumber
- Agent mode (workflow_dispatch/schedule) doesn't use these files
* linting update
* refactor: implement discriminated unions for GitHub contexts
Split ParsedGitHubContext into entity-specific and automation contexts:
- ParsedGitHubContext: For entity events (issues/PRs) with required entityNumber and isPR
- AutomationContext: For workflow_dispatch/schedule events without entity fields
- GitHubContext: Union type for all contexts
This eliminates ~20 null checks throughout the codebase and provides better type safety.
Entity-specific code paths are now guaranteed to have the required fields.
Co-Authored-By: Claude <noreply@anthropic.com>
* update comment
* More robust type checking
* refactor: improve discriminated union implementation based on review feedback
- Use eventName checks instead of 'in' operator for more robust type guards
- Remove unnecessary type assertions - TypeScript's control flow analysis works correctly
- Remove redundant runtime checks for entityNumber and isPR
- Simplify code by using context directly after type guard
Co-Authored-By: Claude <noreply@anthropic.com>
* some structural simplification
* refactor: further simplify discriminated union implementation
- Add event name constants to reduce duplication
- Derive EntityEventName and AutomationEventName types from constants
- Use isAutomationContext consistently in agent mode and registry
- Simplify parseGitHubContext by removing redundant type assertions
- Extract payload casts to variables for cleaner code
Co-Authored-By: Claude <noreply@anthropic.com>
* bun format
* specify the type
* minor linting update again
---------
Co-authored-by: km-anthropic <km-anthropic@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add agent mode for automation scenarios
- Add agent mode that always triggers without checking for mentions
- Implement Mode interface with support for mode-specific tool configuration
- Add getAllowedTools() and getDisallowedTools() methods to Mode interface
- Simplify tests by combining related test cases
- Update documentation and examples to include agent mode
- Fix TypeScript imports to prevent circular dependencies
Agent mode is designed for automation and workflow_dispatch scenarios
where Claude should always run without requiring trigger phrases.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Minor update to readme (from @main to @beta)
* Since workflow_dispatch isn't in the base action, update the examples accordingly
* minor formatting issue
* Update to say beta instead of main
* Fix missed tracking comment to be false
* add schedule & workflow dispatch paths. Also make prepare logic conditional
* tests
* Add test workflow for workflow_dispatch functionality
* Update workflow to use correct branch reference
* remove test workflow dispatch file
* minor lint update
* update workflow dispatch agent example
* minor lint update
* refactor: simplify prepare logic with mode-specific implementations
* ensure tag mode can't work with workflow dispatch and schedule tasks
* simplify: remove workflow_dispatch/schedule from create-prompt
- Remove workflow_dispatch and schedule event handling from create-prompt
since agent mode doesn't use the standard prompt generation flow
- Enforce mode compatibility at selection time in the registry instead
of runtime validation in tag mode
- Add explanatory comment in agent mode about why prompt file is needed
- Update tests to reflect simplified event handling
This reduces code duplication and makes the separation between tag mode
(entity-based events) and agent mode (automation events) clearer.
* simplify PR by making agent mode only work with workflow dispatch and schedule events
* remove unnecessary changes
* remove unnecessary changes from PR
- Revert update-comment-link.ts changes (agent mode doesn't use this)
- Revert create-initial.ts changes (agent mode doesn't create comments)
- Remove unused default-branch.ts file
- Revert install-mcp-server.ts changes (agent mode uses minimal MCP)
These files are only used by tag mode for entity-based events, not needed
for workflow_dispatch/schedule support via agent mode.
* fix: handle optional entityNumber for TypeScript
- Add runtime checks in files that require entityNumber
- These files are only used by tag mode which always has entityNumber
- Agent mode (workflow_dispatch/schedule) doesn't use these files
* linting update
---------
Co-authored-by: km-anthropic <km-anthropic@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
- Switch from npm to bun for Claude Code installation in base-action
- Update Claude Code version from 1.0.59 to 1.0.61 in main action
- Ensures consistent package manager usage across both action files
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add agent mode for automation scenarios
- Add agent mode that always triggers without checking for mentions
- Implement Mode interface with support for mode-specific tool configuration
- Add getAllowedTools() and getDisallowedTools() methods to Mode interface
- Simplify tests by combining related test cases
- Update documentation and examples to include agent mode
- Fix TypeScript imports to prevent circular dependencies
Agent mode is designed for automation and workflow_dispatch scenarios
where Claude should always run without requiring trigger phrases.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Minor update to readme (from @main to @beta)
* Since workflow_dispatch isn't in the base action, update the examples accordingly
* minor formatting issue
* Update to say beta instead of main
* Fix missed tracking comment to be false
---------
Co-authored-by: km-anthropic <km-anthropic@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
* feat: format PR and issue body text in prompt variables
Apply formatBody function to PR_BODY and ISSUE_BODY variables to properly handle images and markdown formatting in prompt context.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* style: format PR_BODY and ISSUE_BODY ternary expressions
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat: add claude_code_oauth_token to all GitHub workflow tests
Add claude_code_oauth_token parameter to all test workflow files to support new authentication method. This ensures proper authentication for Claude Code API access in GitHub Actions.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* Revert "feat: add claude_code_oauth_token to all GitHub workflow tests"
This reverts commit fccc1a0ebd.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* Add mode support
* update "as any" with proper "as unknwon as ModeName" casting
* Add documentation to README and registry.ts
* Add tests for differen event types, integration flows, and error conditions
* Clean up some tests
* Minor test fix
* Minor formatting test + switch from interface to type
* correct the order of mkdir call
* always configureGitAuth as there's already a fallback to handle null users by using the bot ID
* simplify registry setup
---------
Co-authored-by: km-anthropic <km-anthropic@users.noreply.github.com>
Enables detailed permission messages in Claude Code by setting the
DETAILED_PERMISSION_MESSAGES environment variable to '1' in the
Run Claude Code step.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: integrate Claude Code SDK to replace process spawning
- Add @anthropic-ai/claude-code dependency to base-action
- Replace mkfifo/cat process spawning with direct SDK usage
- Remove global Claude Code installation from action.yml files
- Maintain full compatibility with existing options
- Add comprehensive tests for SDK integration
This change makes the implementation cleaner and more reliable by
eliminating the complexity of managing child processes and named pipes.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: add debugging and bun executable for Claude Code SDK
- Add stderr handler to capture CLI errors
- Explicitly set bun as the executable for the SDK
- This should help diagnose why the CLI is exiting with code 1
* fix: extract mcpServers from parsed MCP config
The SDK expects just the servers object, not the wrapper object with mcpServers property.
* tsc
---------
Co-authored-by: Claude <noreply@anthropic.com>
- Added IMPORTANT note explaining direct prompts are user instructions that take precedence
- Updated the direct instruction notice to be marked as CRITICAL and HIGH PRIORITY
- These changes make it clearer that direct prompts override other context
- Update wording to remind users about available git commands instead of implying limitation
- Remove git user configuration instruction as it's not needed for action usage
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
Replace npm install with bun install for consistency with the rest of the project's package management.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-authored-by: Claude <noreply@anthropic.com>
