Replace the mock chat with the live backend agent:
- chat-panel uses @ai-sdk/react useChat against /api/chat (credentials included),
passing the selected model + effort per send. The `/patient <file#>` fast-path
is kept as an instant client-side shortcut.
- Renders the agent's streamed data parts: patientCard → record cards
(PatientResult), labCard → new LabChartCard (visx area chart with a high/low
flag badge in the top-right corner + recent values), importPreview →
ImportPreviewCard (the human approval gate: review counts/issues, then commit
via POST /api/ai/import — nothing is written until approved).
- Veil consent: a one-time dialog before the first send to a cloud model,
explaining that identifiers are de-identified before leaving the clinic.
- Attached text files (csv/json/txt…) now include their content in the message
so the agent can parse an export for import.
Shared chat message/data-part types in lib/ai-chat.ts.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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>
Khalid Abdi