Add model dropdowns to settings and set qwen2.5:1.5b as intent default

- Default OLLAMA_INTENT_MODEL to qwen2.5:1.5b in code instead of empty
- Add GET /api/settings/models endpoint returning installed models and defaults
- Validate intent_model against installed models on save (same as default_model)
- Replace intent model text input with a dropdown of installed models
- Add chat model dropdown to Assistant settings section

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

frontend/src/views/SettingsView.vue

@@ -9,7 +9,11 @@ const store = useSettingsStore();
 const authStore = useAuthStore();
 const toastStore = useToastStore();
 const assistantName = ref("");
+const defaultModel = ref("");
 const intentModel = ref("");
+const installedModels = ref<string[]>([]);
+const defaultChatModel = ref("");
+const defaultIntentModel = ref("");
 const newEmail = ref("");
 const emailPassword = ref("");
 const changingEmail = ref(false);
@@ -66,8 +70,19 @@ onMounted(async () => {
   assistantName.value = store.assistantName;
   newEmail.value = authStore.user?.email ?? "";
 
+  // Load installed models and configured defaults
+  try {
+    const modelsData = await apiGet<{ models: string[]; default_chat_model: string; default_intent_model: string }>("/api/settings/models");
+    installedModels.value = modelsData.models;
+    defaultChatModel.value = modelsData.default_chat_model;
+    defaultIntentModel.value = modelsData.default_intent_model;
+  } catch {
+    // Ollama unreachable — dropdowns will be empty
+  }
+
   // Load notification preferences from user settings
   const allSettings = await apiGet<Record<string, string>>("/api/settings");
+  defaultModel.value = allSettings.default_model ?? "";
   intentModel.value = allSettings.intent_model ?? "";
   if (allSettings.notify_task_reminders !== undefined) {
     notifyTaskReminders.value = allSettings.notify_task_reminders !== "false";
@@ -157,7 +172,8 @@ async function saveAssistant() {
   try {
     await store.updateSettings({
       assistant_name: assistantName.value.trim() || "Fable",
-      intent_model: intentModel.value.trim(),
+      default_model: defaultModel.value,
+      intent_model: intentModel.value,
     });
     saved.value = true;
     setTimeout(() => (saved.value = false), 2000);
@@ -342,20 +358,22 @@ async function handleRestoreFile(event: Event) {
         </p>
       </div>
 
+      <div class="field">
+        <label for="default-model">Chat Model</label>
+        <select id="default-model" v-model="defaultModel" class="input">
+          <option value="">Default ({{ defaultChatModel || "qwen3" }})</option>
+          <option v-for="m in installedModels" :key="m" :value="m">{{ m }}</option>
+        </select>
+        <p class="field-hint">Model used for new conversations.</p>
+      </div>
+
       <div class="field">
         <label for="intent-model">Intent Model</label>
-        <input
-          id="intent-model"
-          v-model="intentModel"
-          type="text"
-          placeholder="Same as chat model"
-          class="input"
-        />
-        <p class="field-hint">
-          Optional smaller/faster model for intent routing (e.g. <code>llama3.2:3b</code>,
-          <code>qwen2.5:3b</code>). Leave empty to use the same model as chat.
-          Can also be set via <code>OLLAMA_INTENT_MODEL</code> environment variable.
-        </p>
+        <select id="intent-model" v-model="intentModel" class="input">
+          <option value="">Default ({{ defaultIntentModel || "qwen2.5:1.5b" }})</option>
+          <option v-for="m in installedModels" :key="m" :value="m">{{ m }}</option>
+        </select>
+        <p class="field-hint">Smaller/faster model for intent routing. Runs before the main model to detect tool calls.</p>
       </div>
 
       <div class="actions">