| trigger_phrase | The trigger phrase to look for in comments or issue body | no | @rehearsal |
| assignee_trigger | The assignee username that triggers the action (e.g. @claude) | no | — |
| label_trigger | The label that triggers the action (e.g. qa-test) | no | qa-test |
| base_branch | The branch to use as the base/source when creating new branches (defaults to repository default branch) | no | — |
| branch_prefix | The prefix to use for Rehearsal branches (defaults to 'rehearsal/', use 'rehearsal-' for dash format) | no | rehearsal/ |
| allowed_bots | Comma-separated list of allowed bot usernames, or '*' to allow all bots. Empty string (default) allows no bots. | no | "" |
| rehearsal_api_key | API key for Rehearsal platform to save test results | no | — |
| rehearsal_app_id | GitHub App ID for Rehearsal AI bot | no | 1757535 |
| rehearsal_app_private_key | GitHub App private key for Rehearsal AI bot | no | — |
| mode | Execution mode for the action. Valid modes: 'tag' (default - triggered by mentions/assignments), 'agent' (for automation with no trigger checking), 'experimental-review' (experimental mode for code reviews with inline comments and suggestions) | no | tag |
| model | Model to use (provider-specific format required for Bedrock/Vertex) | no | — |
| anthropic_model | DEPRECATED: Use 'model' instead. Model to use (provider-specific format required for Bedrock/Vertex) | no | — |
| fallback_model | Enable automatic fallback to specified model when primary model is unavailable | no | — |
| allowed_tools | Additional tools for Claude to use (the base GitHub tools will always be included) | no | "" |
| disallowed_tools | Tools that Claude should never use | no | "" |
| custom_instructions | Additional custom instructions to include in the prompt for Claude | no | "" |
| direct_prompt | Direct instruction for Claude (bypasses normal trigger detection) | no | "" |
| override_prompt | Complete replacement of Claude's prompt with custom template (supports variable substitution) | no | "" |
| mcp_config | Additional MCP configuration (JSON string) that merges with the built-in GitHub MCP servers | — | — |
| additional_permissions | Additional permissions to enable. Currently supports 'actions: read' for viewing workflow results | no | "" |
| claude_env | Custom environment variables to pass to Claude Code execution (YAML format) | no | "" |
| settings | Claude Code settings as JSON string or path to settings JSON file | no | "" |
| anthropic_api_key | Anthropic API key (required for direct API, not needed for Bedrock/Vertex) | no | — |
| claude_code_oauth_token | Claude Code OAuth token (alternative to anthropic_api_key) | no | — |
| github_token | GitHub token with repo and pull request permissions (optional if using GitHub App) | no | — |
| use_bedrock | Use Amazon Bedrock with OIDC authentication instead of direct Anthropic API | no | false |
| use_vertex | Use Google Vertex AI with OIDC authentication instead of direct Anthropic API | no | false |
| max_turns | Maximum number of conversation turns | no | "" |
| timeout_minutes | Timeout in minutes for execution | no | 30 |
| use_sticky_comment | Use just one comment to deliver issue/PR comments | no | false |
| use_commit_signing | Enable commit signing using GitHub's commit signature verification. When false, Claude uses standard git commands | no | false |
| experimental_allowed_domains | Restrict network access to these domains only (newline-separated). If not set, no restrictions are applied. Provider domains are auto-detected. | no | "" |