workbench_open_run
Create a run folder and initial evidence artifacts to enable acceptance gates and validation for AI coding-agent runs.
Instructions
Create a Workbench run folder and initial evidence artifacts.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"project": "<project>",
"task": "<task>"
},
"name": "workbench_open_run"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| project | Yes | ||
| task | Yes | ||
| run_dir | No | ||
| prompt | No | implement_request_change_request | |
| risk | No | medium | |
| context_profile | No | ||
| recipe | No | ||
| changed_files | No | ||
| docs | No | ||
| include_diff | No | ||
| execution_host | No | goose | |
| auto_select_policy_pack | No | ||
| policy_pack | No | ||
| validation_profile | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||