frontend: wire chat to the real agent + lab charts + import approval

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>

frontend/package.json

@@ -9,6 +9,7 @@
     "lint": "eslint"
   },
   "dependencies": {
+    "@ai-sdk/react": "^3.0.206",
     "@base-ui/react": "^1.5.0",
     "@number-flow/react": "^0.6.0",
     "@radix-ui/react-use-controllable-state": "^1.2.2",