Capture partial LLM output on interruption

traced_llm only attached the aggregated ``output`` attribute to the
span after the wrapped function returned successfully. When the LLM
call was cancelled mid-stream (e.g. interruption during generation),
the accumulated text was discarded — the span had no ``output``.

Moved the attribute assignment into the ``finally`` block alongside
the existing TTFB write so the partial text we already captured via
the patched ``push_frame`` lands on the span regardless of whether
``f`` returned normally, raised, or was cancelled.

src/pipecat/utils/tracing/service_decorators.py

@@ -889,10 +889,6 @@ def traced_llm(func: Callable | None = None, *, name: str | None = None) -> Call
                         fn_called = True
                         result = await f(self, context, *args, **kwargs)
 
-                        # Add aggregated output after function completes, if available
-                        if output_text:
-                            current_span.set_attribute("output", output_text)
-
                         return result
 
                     finally:
@@ -905,6 +901,15 @@ def traced_llm(func: Callable | None = None, *, name: str | None = None) -> Call
                         ):
                             self.start_llm_usage_metrics = original_start_llm_usage_metrics
 
+                        # Attach whatever output text we accumulated so
+                        # far. Doing this in finally captures partial
+                        # output when ``f`` is cancelled or raises mid-
+                        # stream (e.g. interruption during LLM
+                        # generation), rather than only on clean
+                        # completion.
+                        if output_text:
+                            current_span.set_attribute("output", output_text)
+
                         # Update TTFB metric
                         ttfb: float | None = getattr(getattr(self, "_metrics", None), "ttfb", None)
                         if ttfb is not None: