Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| RUN_ID | No | Workflow run ID to inspect. | |
| REPOSITORY | No | Target GitHub repository in 'owner/repo' format. | |
| BASE_BRANCH | No | The base branch for repair operations. | main |
| GITHUB_TOKEN | Yes | GitHub personal access token for repository inspection and PR creation. | |
| WORKFLOW_NAME | No | Filter latest failed run by workflow name (e.g., 'ci'). | |
| OPENAI_API_KEY | Yes | OpenAI API key used for the LLM diagnosis flow. | |
| PATCH_STRATEGY | No | Patch format expected from the model. | unified_diff |
| FORCE_AUTOFIX_ALL | No | If set to 'true', bypasses thresholds and forces the auto-fix path. | |
| LLM_PATCH_MAX_CHARS | No | Upper bound on patch payload size. | |
| MAX_REPAIR_ATTEMPTS | No | Number of patch generation/application retries. | 3 |
| RISK_AUTO_FIX_THRESHOLD | No | Score threshold below which fixes are applied autonomously. | |
| RISK_HUMAN_REVIEW_THRESHOLD | No | Score threshold below which human review is required. |
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |