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>
Replace the five clinical context selects (access, response mode, specialty,
facility, time range) with one model picker styled like the reference design:
a primary model list with descriptions, an Effort submenu, and a "More models"
submenu. Move the Add-patient pill up into the toolbar and drop the now-empty
bottom context-selector card so the input is a single clean rounded surface.
Model/effort selection is lifted to ChatPanel so it can travel with each send
(wired to the backend agent in a later phase). Adds a shared model catalog
(lib/ai-models.ts) reused by the picker, Settings, and the chat wiring.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Khalid Abdi