---
title: "Re-run all current evaluator bindings against a v2 conversation"
method: POST
path: "/v1/v2/conversations/{conversation_id}/reevaluate"
tags: ["runtime v2"]
---

# Re-run all current evaluator bindings against a v2 conversation

`POST /v1/v2/conversations/{conversation_id}/reevaluate`

v2 alias of ``POST /v1/sessions/{id}/reevaluate``.

The legacy eval endpoint already operates on the conv_* ``Conversation``
model and works unchanged — this thin alias keeps the admin UI's path
family consistent under ``/v2/conversations``. Wipes existing EvalRuns and
re-runs the currently bound evaluators with fresh snapshots; rejects (409)
while any run for the conversation is ``pending`` / ``running``.

## Path parameters

- `conversation_id` string, uuid, required

## Response `202`

Successful Response

- EvalTaskAcceptedResponse — 202 acknowledgement returned by reevaluate / retry endpoints.
  - `task_id` string, required
  - `status` 'queued'

## 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)