---
title: "Set per-agent eval configuration"
method: PUT
path: "/v1/agents/{agent_id}/eval-config"
tags: ["agents"]
---

# Set per-agent eval configuration

`PUT /v1/agents/{agent_id}/eval-config`

## Path parameters

- `agent_id` string, uuid, required

## Request body

- AgentEvalConfigUpdate — Body for ``PUT /v1/agents/{id}/eval-config``. Both fields are optional so the UI can flip one switch at a time without having to re-assert the other; a field left unset means "no change".
  - `evaluate_live` boolean, nullable
  - `evaluate_test` boolean, nullable

## Response `200`

Successful Response

- AgentEvalConfigResponse — Per-agent eval configuration exposed by ``/v1/agents/{id}/eval-config``. Two independent toggles: ``evaluate_live`` gates ``SessionType.LIVE`` (production) sessions and ``evaluate_test`` gates ``SessionType.TEST`` (dev-initiated) sessions. Simulation runs always evaluate.
  - `evaluate_live` boolean, required
  - `evaluate_test` boolean, required

## Other responses

- `400` — Bad request
- `401` — Authentication required
- `404` — Resource not found
- `422` — Validation Error

---

[API](https://skmtc.net/oneloop-hq/apis/feather-api.md) · [All operations](https://skmtc.net/oneloop-hq/apis/feather-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/oneloop-hq/feather-api/versions/888bdd5c076e/schema)