Can the writing pipeline actually run right now?
Reports, per critical sidecar, the resolved provider fallback chain and whether ANY link in it is currently reachable. A chain whose every link is cooling down is the shape that parks jobs indefinitely — the job defers for provider recovery to a retry that cannot succeed — and it is otherwise only visible as a misleading generation timeout. Check this before blaming a failed job on your request, and when triaging repeated failures. A link whose stored API key this server cannot decrypt is never healthy, and a request that reaches it fails there with no fallback tried, so its sidecar is unreachable even with a healthy fallback; its unreachableReason and the entry's reason name the fix (re-enter the key, or fix the server's AI_ENCRYPTION_KEY). Reports posture only; never provider credentials or base URLs.
Request
- Base URL: https://docs.sleeperhit.studio/api/v1
- URL: https://docs.sleeperhit.studio/api/v1/generation-health
- Auth: HTTP bearer
Query parameters
Also SMOKE TEST each critical binding with a small real model call. Reachability and usability are different questions: a provider can be perfectly reachable while rejecting the sampling parameters this pipeline sends, or while returning output the pipeline cannot use — neither shows up in provider health. Slower and costs a token or two per sidecar; use when triaging repeated failures or immediately after rebinding a provider.
Response
Generation health summary.
Changes
No recorded changes to this operation across all 2 revisions of this API.