train_risk_model
Retrain the PR-risk classifier using historical file changes and test results, then returns accuracy, precision, recall, and F1. Reports a caveat when the training set is too small for metrics to be meaningful.
Instructions
Retrain the PR-risk classifier on everything currently in the database.
Trains a GradientBoostingClassifier using file_changes/test_results history as labelled examples (did a test tied to this file fail within N runs after the file changed?), then reports accuracy, precision, recall, and F1 on a held-out split. When the training set is small, the returned metrics come with an explicit caveat that they aren't yet statistically meaningful — this tool never reports metrics as trustworthy without that context.
Returns: Training set size and accuracy/precision/recall/F1, with an honest caveat attached when the training set is too small for the metrics to mean much.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "train_risk_model"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||