Make the chat feel alive and let the agent act on the clinic — safely.
UX (frontend):
- Stream `data-step` parts from each tool into an inline Chain-of-Thought
trace, plus a "Thinking…" shimmer while a request is in flight (works even
on the non-streamed external+Veil path).
- Replace the modal Veil consent Dialog with an inline, once-per-session
"Veil" confirmation above the input (with a "Use local model" option).
- Render new list + action-preview cards; chat-input now uses COSS tokens.
Agent (backend):
- Add display tools (listAppointments / listTasks / listPrescriptions) and
propose tools (proposeAppointment / proposeTask / proposePrescription) that
validate as a dry run and stream an approval card — nothing is written until
the clinician approves, via the existing RBAC-gated create endpoints.
- previewImport now also covers single-patient add + migration.
- System prompt: display + add only, never edit/delete or alter the schema;
stronger migration guidance. ToolContext carries the viewer for task scoping.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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>
Khalid Abdi