feat(web): cloud chat-model selector in Settings

Pick which OpenAI model answers on the Cloud backend (gpt-4o / -mini / 4.1 /
4.1-mini / o4-mini, or Default). Persisted in localStorage, sent as `model` in
the chat request; respond() applies it only on the cloud backend (local/mi50
keep their fixed models). Reachable from desktop + mobile via Settings.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

lyra/web/server.py

@@ -92,9 +92,10 @@ def create_app() -> FastAPI:
         backend = _backend_for(body.get("backend"))
         user_msg = _last_user_message(body.get("messages", []))
 
+        model_override = body.get("model") or None
         memory.ensure_session(session_id)
         try:
-            reply = await asyncio.to_thread(chat.respond, session_id, user_msg, backend)
+            reply = await asyncio.to_thread(chat.respond, session_id, user_msg, backend, model_override)
         except Exception as exc:
             logbus.log("error", "chat failed", session=session_id, error=str(exc))
             reply = f"[error] {exc}"

lyra/web/static/index.html

@@ -143,6 +143,19 @@
           </div>
         </div>
 
+        <div class="settings-section" style="margin-top: 24px;">
+          <h4>Chat Model (Cloud)</h4>
+          <p class="settings-desc">Which OpenAI model answers on the Cloud backend. Tools (poker, equity, journaling) require Cloud.</p>
+          <select id="cloudModel">
+            <option value="">Default (gpt-4o)</option>
+            <option value="gpt-4o">gpt-4o — best persona</option>
+            <option value="gpt-4o-mini">gpt-4o-mini — cheap/fast</option>
+            <option value="gpt-4.1">gpt-4.1</option>
+            <option value="gpt-4.1-mini">gpt-4.1-mini</option>
+            <option value="o4-mini">o4-mini — reasoning</option>
+          </select>
+        </div>
+
         <div class="settings-section" style="margin-top: 24px;">
           <h4>Session Management</h4>
           <p class="settings-desc">Manage your saved chat sessions:</p>
@@ -283,6 +296,12 @@
         body.backend = backend;
       }
 
+      // Cloud chat-model override (ignored server-side unless backend is cloud)
+      const cloudModel = localStorage.getItem("cloudModel");
+      if (cloudModel) {
+        body.model = cloudModel;
+      }
+
       try {
         const resp = await fetch(API_URL, {
           method: "POST",
@@ -571,6 +590,10 @@
       const initialRadio = document.querySelector(`input[name="backend"][value="${savedBackend}"]`);
       if (initialRadio) initialRadio.checked = true;
 
+      // Restore saved cloud-model choice
+      const savedModelSel = document.getElementById("cloudModel");
+      if (savedModelSel) savedModelSel.value = localStorage.getItem("cloudModel") || "";
+
       // Session management functions
       async function loadSessionList() {
         try {
@@ -679,7 +702,11 @@
         const backendValue = selectedRadio ? selectedRadio.value : "local";
 
         localStorage.setItem("standardModeBackend", backendValue);
-        addMessage("system", `Backend changed to: ${backendValue}`);
+        const modelSel = document.getElementById("cloudModel");
+        const modelValue = modelSel ? modelSel.value : "";
+        localStorage.setItem("cloudModel", modelValue);
+        const modelLabel = modelValue || "default (gpt-4o)";
+        addMessage("system", `Backend: ${backendValue} · cloud model: ${modelLabel}`);
         hideModal();
       });