Enable thinking mode in full chat view, keep disabled in widget/panel

stream_chat_with_tools now accepts a think parameter. run_generation
forwards it to Ollama. The message POST route reads think from the
request body. ChatView passes think=true so qwen3 uses chain-of-thought
reasoning for full conversations; the dashboard widget and ChatPanel
omit it, staying fast. Dashboard button updated to "Think it through
in Chat →" to signal the deeper capability.

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

frontend/src/stores/chat.ts

@@ -120,6 +120,7 @@ export const useChatStore = defineStore("chat", () => {
     content: string,
     contextNoteId?: number | null,
     excludeNoteIds?: number[],
+    think = false,
   ) {
     if (!currentConversation.value) return;
 
@@ -165,6 +166,7 @@ export const useChatStore = defineStore("chat", () => {
           content,
           context_note_id: contextNoteId,
           exclude_note_ids: excludeNoteIds?.length ? excludeNoteIds : undefined,
+          think,
         },
       );
       assistantMessageId = resp.assistant_message_id;