Run local workflow
run_ai_workflowRun deterministic local workflows over ProxyKit engine data to explain failures, generate issues or mocks, suggest tests, and summarize sessions; returns markdown for agent chaining.
Instructions
Run one of ProxyKit's built-in local workflows over engine data. These workflows are deterministic — they do not call an external LLM. Returns markdown the agent can chain into its own reasoning ("explain_failure → generate_issue → suggest_tests").
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": {
"workflow": "<workflow>"
},
"name": "run_ai_workflow"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| entry_id | No | Traffic entry id. Required for explain_failure, generate_issue, generate_mock. | |
| workflow | Yes | One of: explain_failure, generate_issue, suggest_tests, summarize_session, generate_mock. | |
| session_id | No | Session id. Required for summarize_session and suggest_tests (candidate). | |
| baseline_id | No | Baseline session id. Required for suggest_tests. |