regression_gate
Prevent prompt regressions by running evaluation against the stored baseline and blocking updates that score lower, returning allow or deny.
Instructions
CI for prompts. Runs run_eval against the current assistant and blocks the update if the score regressed vs the stored baseline. Returns allow/deny.
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": {
"assistantId": "<assistantId>",
"market": "<market>",
"vertical": "<vertical>",
"baselineScore": "<baselineScore>"
},
"name": "regression_gate"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| market | Yes | ||
| vertical | Yes | ||
| assistantId | Yes | ||
| baselineScore | Yes | Previous accepted grade /100 |