fix: preserve streaming UI callbacks across agent loop iterations

StreamHandler.reset() was clearing on_content, on_thinking, and on_done
callbacks after every LLM response, but they were only set once per turn.
This caused the thinking indicator and streaming display to stop working
after the first tool call in a multi-step agent turn.

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

app/services/streaming.py

@@ -183,11 +183,8 @@ class StreamHandler:
         return bool(self._accumulated_reasoning) and not self._accumulated_content and not self._tool_calls
 
     def reset(self) -> None:
-        """Clear all accumulators for the next turn."""
+        """Clear accumulators for the next LLM call, preserving UI callbacks."""
         self._accumulated_content = ""
         self._accumulated_reasoning = ""
         self._tool_calls.clear()
         self._usage = None
-        self._on_content = None
-        self._on_thinking = None
-        self._on_done = None