Add thinking indicator and fix input visibility

- LLM progress indicator: animated status bar ('✦ LLM is weaving the
  narrative ✦') with rotating dots, shown during processing, hidden on
  completion. Disabled input shows 'LLM is thinking...' placeholder.
- Fix input not visible: added 'height: 1fr' to TabbedContent so the PLAY
  tab and its input widget fill available vertical space.
- Replace @work(thread=True) with threading.Thread for reliable worker
  execution across all environments (headless, test, TUI).

session/config.json

@@ -1,8 +1,8 @@
 {
   "llm": {
-    "model": "ollama/llama3.1",
-    "api_key": null,
-    "api_base": null,
+    "model": "openai/gpt-4o-mini",
+    "api_key": "not-needed",
+    "api_base": "http://localhost:8080/v1",
     "temperature": 0.8
   }
 }