feat: add interactive mode for agent loop

Re-architects the agent loop to support interactive (chat-like) mode
where text-only responses pause execution and wait for user input,
while tool-call responses continue looping autonomously.

- Add `interactive` flag to LLMConfig (default False, no regression)
- Add configurable `waiting_timeout` to AgentState (0 = disabled)
- _process_iteration returns None for text-only → agent_loop pauses
- Conditional system prompt: interactive allows natural text responses
- Skip <meta>Continue the task.</meta> injection in interactive mode
- Sub-agents inherit interactive from parent (300s auto-resume timeout)
- Root interactive agents wait indefinitely for user input (timeout=0)
- TUI sets interactive=True; CLI unchanged (non_interactive=True)

strix/llm/llm.py

@@ -97,6 +97,7 @@ class LLM:
             result = env.get_template("system_prompt.jinja").render(
                 get_tools_prompt=get_tools_prompt,
                 loaded_skill_names=list(skill_content.keys()),
+                interactive=self.config.interactive,
                 **skill_content,
             )
             return str(result)
@@ -186,7 +187,7 @@ class LLM:
         conversation_history.extend(compressed)
         messages.extend(compressed)
 
-        if messages[-1].get("role") == "assistant":
+        if messages[-1].get("role") == "assistant" and not self.config.interactive:
             messages.append({"role": "user", "content": "<meta>Continue the task.</meta>"})
 
         if self._is_anthropic() and self.config.enable_prompt_caching: