Instrument privacy-safe model health, latency, abstention, and failure metrics #19

New Issue

timmy · 2026-08-19T01:58:59Z

timmy commented

2026-08-19 01:58:59 +00:00

Parent epic: #2

Outcome

Operate the worker without logging medical imagery.

Acceptance criteria

Metrics expose readiness, queue depth, cold/warm latency, failure class, and abstention rate.
No metric label contains note text, image hash, base64, or user identity.
Dashboard separates app, queue, and model boundaries.

Dependencies

#17 — Add bounded inference queue, cancellation, and overload fallback

Required evidence

Test or executable receipt attached to the issue/PR
Privacy/safety boundary checked where applicable
Clean checkout and relevant full suite pass

Delivery

Open a focused branch and PR with Closes #ISSUE. Do not include real medical images in issue comments or Git history.

Parent epic: #2 ## Outcome Operate the worker without logging medical imagery. ## Acceptance criteria - [ ] Metrics expose readiness, queue depth, cold/warm latency, failure class, and abstention rate. - [ ] No metric label contains note text, image hash, base64, or user identity. - [ ] Dashboard separates app, queue, and model boundaries. ## Dependencies - #17 — Add bounded inference queue, cancellation, and overload fallback ## Required evidence - Test or executable receipt attached to the issue/PR - Privacy/safety boundary checked where applicable - Clean checkout and relevant full suite pass ## Delivery Open a focused branch and PR with `Closes #ISSUE`. Do not include real medical images in issue comments or Git history.

timmy added this to the M1 — Sovereign Photo Intelligence milestone 2026-08-19 01:58:59 +00:00

timmy added the

labels 2026-08-19 01:58:59 +00:00

timmy referenced this issue

2026-08-19 01:59:02 +00:00

Create release observability and incident-response dashboard #41

timmy referenced this issue

2026-08-19 01:59:03 +00:00