Agent Improvement
Auto-improve runs that iterate on an agent flow toward a target score.
Start the auto-improve process for an agent
Runs the selected evals (or all of the agent when `testCaseIds` is omitted), analyzes results and iteratively improves the agent flow until `targetScore` is reached or `maxIterations` runs are done. When a process is already running, answers 200 with its id instead of starting another one.
List auto-improve runs of an agent
Returns the runs newest first, at most `limit` of them (default 20). When `applicationId` is given, read access to the application is checked first.
Get an auto-improve run of an agent
Returns the run together with the test runs of its iterations. Use it to poll the progress of a process started via `POST /api/v1/agents/{agentId}/auto-improve/`. Answers `400` when the run exists but belongs to a different agent.
Delete an auto-improve run of an agent
Permanently removes the run record. It does not stop a running process, use `DELETE /api/v1/agents/{agentId}/auto-improve/stop/` for that. Requires write access to the application.
Stop a running auto-improve process of an agent
Marks the run identified by `processId` as `STOPPED` so the background process terminates gracefully at its next checkpoint instead of starting another iteration. Answers `404` when the process has already finished or been stopped.