Commit Graph

3 Commits

Author SHA1 Message Date
Khalid Abdi addddc8972 feat(ai): clinic-wide AI kill-switch (admin-controlled)
- new org_ai_policy table + GET/PUT /api/ai/policy (read for any member,
  write owner/admin only); migration 0018
- /api/chat hard-blocks (403) when AI is off for the caller
- Settings → AI "Availability" section: enable AI, or disable for
  employees only (owners/admins keep access); read-only for non-admins
- sidebar, command palette and route guard hide/redirect the AI chat
  when it's disabled for the current user

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-15 18:42:50 +03:00
Khalid Abdi ddf4b49d82 fix: chat works with any configured provider + surfaces errors
The chat defaulted to a Claude model, so a user who saved only a Gemini key got
a silent failure (backend derived Anthropic, found no key, errored — and the UI
showed nothing).

- Backend: resolveModel now falls back to whichever provider actually has a key
  (preferring the configured one), so a Gemini key just works regardless of the
  picked model. Clear 400 if no provider is configured at all.
- Frontend: the chat seeds its model/effort from the saved AI config, and now
  surfaces request failures as both a persistent alert banner and a toast —
  never silent.
- Settings: switching provider auto-selects that provider's default model.
- Refreshed the model catalog to current ids (Gemini 2.5 Pro/Flash + 2.0 Flash;
  dropped the retired gemini-1.5-pro); per-provider default model updated.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-13 19:27:37 +03:00
Khalid Abdi ff37b555b0 frontend: Settings → AI panel (modes, providers, Veil)
New per-user AI settings section (visible to every clinician, not just admins):
- Inference mode: cloud API key vs local Ollama.
- Provider + key (OpenAI / Anthropic / Gemini) via a select; the key field is
  write-only and shows a "key set" indicator from the backend's apiKeySet,
  never echoing the stored secret. Default model + effort per provider.
- Local Ollama: base URL + model name with a "Test connection" probe.
- Veil: de-identification level (full / names / off) with mode-aware copy.

Talks to the new /api/ai/config + /api/ai/test endpoints via lib/ai-settings.ts.
The old mock clinical selects (specialty/facility/time range/access/response)
are dropped entirely rather than relocated — they were placeholder knobs.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-13 18:38:38 +03:00