workbench_record_execution
Records model response text as evidence artifacts for AI coding-agent runs, enabling validation and quality gates.
Instructions
Capture Goose/model response text into Workbench 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>",
"run_dir": "<run_dir>",
"response_text": "<response_text>"
},
"name": "workbench_record_execution"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| project | Yes | ||
| run_dir | Yes | ||
| response_text | Yes | ||
| files_touched | No | ||
| model_output_status | No | response_captured | |
| run_status | No | in_progress | |
| response_source | No | goose | |
| validation | No | ||
| follow_up | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||