Rate one assistant reply (Nu Feedback).

Records a thumbs-up / thumbs-down on a single assistant reply, together with a **snapshot of the interaction that produced it**, for the Nurama team to review. **What gets stored.** The reply being rated, up to ten preceding turns of the conversation, and — when the client supplies them — the page context and pinned Context-column items that were in play at the time. Each captured message is truncated at 4,000 characters. Tell the user before submitting that context from the interaction will be shared with the Nurama team for review. The interaction is **snapshotted, not referenced**: the record captures what the assistant actually said at the time, and remains useful if the chat is later deleted or the topic rewritten. **Authorisation.** The caller must be able to read `chatId` — the same check the chat endpoints apply. A user can only rate a reply in a chat they can already read, so this endpoint cannot be used to capture someone else's conversation by guessing message ids. Failure is `403 forbidden`. This endpoint is **not** subject to the subscription, AI-feature or credit-balance checks that gate AI use: feedback can be submitted even when a workspace's AI add-on has been switched off. A snapshot that cannot be built does not fail the request — the rating is still recorded, with `context.snapshotError: true`. Losing a thumbs-down to a transcript read failure would be the wrong trade.

curl -X POST "https://example.com/ai/feedback" \  -H "Content-Type: application/json" \  -d '{    "rating": "positive",    "surface": "chat",    "chatId": "f255124e-3419-4f6e-b7ee-17a6577db94d"  }'

{  "id": "0192f3a4-5b6c-7d8e-9f01-23456789abcf"}