frontend: Claude-style AI chat (tool cards, reasoning, queue, suggestions)

Wire the existing ai-elements into the chat:
- collapsible tool-call cards (name, params, result, status) for native tool
  parts on the streamed path
- a reasoning block (shimmer while thinking, "Thought for Ns") when the model
  emits reasoning; backend forwards it via toUIMessageStream({ sendReasoning })
- a message queue: typing + Enter while the assistant is responding queues the
  message (shown above the input, removable) and auto-sends when it goes idle
- starter suggestion chips on the empty state, each tied to a tool

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

frontend/lib/i18n/locales/en/translation.json

@@ -772,6 +772,16 @@
     "patientNotFound": "I couldn't find a patient with file number {{fileNumber}}.",
     "thinking": "Thinking…",
     "steps": "Steps",
+    "suggestions": {
+      "schedule": "Show today's schedule",
+      "tasks": "List open tasks",
+      "prescriptions": "Show recent prescriptions",
+      "import": "Import a patient database"
+    },
+    "queue": {
+      "label": "Queued · {{count}}",
+      "remove": "Remove from queue"
+    },
     "veil": {
       "title": "Veil",
       "body": "This message will be processed by {{provider}}, an external provider. Veil de-identifies patient information (names, MRNs, providers) before it leaves your infrastructure, and restores it in the answer.",