feat: Add trace generation for all LLM calls

src/dreamer/specialists.py

@@ -219,6 +219,7 @@ If you update it, send the full deduplicated list and remove stale entries.
             messages=messages,
             track_name=f"Dreamer/{self.name}",
             iteration_callback=iteration_callback,
+            trace_name=f"dreamer_{self.name}",
         )
 
         # Log metrics

src/utils/clients.py

@@ -1499,9 +1499,9 @@ async def honcho_llm_call(
         result: (
             HonchoLLMCallResponse[Any] | AsyncIterator[HonchoLLMCallStreamChunk]
         ) = await decorated()
-        if trace_name and isinstance(result, HonchoLLMCallResponse):
+        if isinstance(result, HonchoLLMCallResponse):
             log_reasoning_trace(
-                task_type=trace_name,
+                task_type=trace_name or "untagged",
                 llm_settings=llm_settings,
                 prompt=prompt,
                 response=result,
@@ -1549,9 +1549,9 @@ async def honcho_llm_call(
         stream_final=stream_final_only,
         iteration_callback=iteration_callback,
     )
-    if trace_name and isinstance(result, HonchoLLMCallResponse):
+    if isinstance(result, HonchoLLMCallResponse):
         log_reasoning_trace(
-            task_type=trace_name,
+            task_type=trace_name or "untagged",
             llm_settings=llm_settings,
             prompt=prompt,
             response=result,

src/utils/summarizer.py

@@ -215,6 +215,7 @@ async def create_short_summary(
         llm_settings=settings.SUMMARY,
         prompt=prompt,
         max_tokens=settings.SUMMARY.MAX_TOKENS_SHORT,
+        trace_name="short_summary",
     )
 
 
@@ -240,6 +241,7 @@ async def create_long_summary(
         llm_settings=settings.SUMMARY,
         prompt=prompt,
         max_tokens=settings.SUMMARY.MAX_TOKENS_LONG,
+        trace_name="long_summary",
     )