arch-playground/AI Workflow Runner
Run AI workflows with Node.js, Python, and Java runtime support
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Stale
- License
- None
Inputs
| name | description | required | default |
|---|---|---|---|
| workflow_path | Path to the workflow.md file (relative to workspace root). Required unless list_models is true. | no | "" |
| prompt | Input prompt to pass to the workflow (max 100KB) | no | "" |
| env_vars | JSON object of environment variables (max 64KB, 100 entries) | no | {} |
| timeout_minutes | Maximum execution time in minutes (default: 30) | no | 30 |
| validation_script | Optional validation script (file path like check.py or inline with prefix like python:print("ok")). Receives AI_LAST_MESSAGE env. Return empty/true for success, other string to continue workflow. | no | "" |
| validation_script_type | Script type for inline scripts: python or javascript. Auto-detected for file paths by extension (.py or .js). Only required when validation_script is set and type cannot be auto-detected. | no | "" |
| validation_max_retry | Maximum validation retry attempts when script returns non-empty/non-true (default: 5, max: 20) | no | 5 |
| opencode_config | Path to OpenCode config.json file (relative to workspace, or absolute under runner.temp/tmp). Contains provider and model settings. | no | "" |
| auth_config | Path to OpenCode auth.json file (relative to workspace, or absolute under runner.temp/tmp). Contains API keys and authentication. Store in GitHub Secrets, not Variables. | no | "" |
| model | Model to use for AI execution (e.g., "anthropic/claude-3-opus"). Overrides config file default. | no | "" |
| list_models | If "true", print available models and exit without running workflow | no | false |
| debug_log | Enable verbose debug logging to file. Also activated by ACTIONS_STEP_DEBUG=true or RUNNER_DEBUG=1. | no | false |
| debug_log_path | Path for debug log file. Defaults to $RUNNER_TEMP/opencode-debug.log. Accepts workspace-relative or absolute paths under RUNNER_TEMP/tmp. | no | "" |
Outputs
| name | description |
|---|---|
| status | Execution status: success, failure, cancelled, or timeout |
| result | Workflow execution result as JSON string (max 900KB) |