Feedback
Package ai is Hanzo AI — the model API on /v1 (/v1/chat/completions, /v1/messages, /v1/models and the rest of hanzoai/ai's surface) — mounted into a cloud binary with the money, ingest and telemetry…
Package ai is Hanzo AI — the model API on /v1 (/v1/chat/completions, /v1/messages, /v1/models and the rest of hanzoai/ai's surface) — mounted into a cloud binary with the money, ingest and telemetry callbacks cloud BUILDS but cannot INSTALL.
| Base URL | https://api.hanzo.ai |
| Operations | 1 |
| Auth | Authorization: Bearer $HANZO_API_KEY |
feedback
POST /v1/feedback
Attaches a per-request outcome reward to the routing decision that served request_id — the enso training loop's quality signal. Org-scoped via the same session-OR-Bearer principal the usage read uses (RequirePrincipal): the reward lands only on the caller's OWN org's event, so a request_id from another org (or unknown) is a 404 — cross-org writes are impossible and unknown ids are indistinguishable from foreign ones. Idempotent: a repeat overwrites. The body carries NO prompt text — only {request_id, reward|rating}.
How is this guide?