Timmy_Foundation/hermes-agent
15
0
Fork 0
Code Issues 248 Pull Requests 14 Actions 1 Packages Projects Releases Wiki Activity

fix: use reasoning content as response when model only produces think blocks

Browse Source 
Local models (especially Qwen 3.5) sometimes wrap their entire response
inside <think> tags, leaving actual content empty. Previously this caused
3 retries and then an error, wasting tokens and failing the request.

Now when retries are exhausted and reasoning_text contains the response,
it is used as final_response instead of returning an error. The user
sees the actual answer instead of "Model generated only think blocks."
This commit is contained in:
Peppi Littera
2026-03-20 00:26:36 +01:00
parent ec5fdb8b92
commit 746abf5e28
1 changed files with 17 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
run_agent.py
View File

@@ -6532,7 +6532,21 @@ class AIAgent:
self._response_was_previewed = True
break
# No fallback -- append the empty message as-is
# No fallback -- if reasoning_text exists, the model put its
# entire response inside <think> tags; use that as the content.
if reasoning_text:
self._vprint(f"{self.log_prefix}Using reasoning as response content (model wrapped entire response in think tags).", force=True)
final_response = reasoning_text
empty_msg = {
"role": "assistant",
"content": final_response,
"reasoning": reasoning_text,
"finish_reason": finish_reason,
}
messages.append(empty_msg)
break
# Truly empty -- no reasoning and no content
empty_msg = {
"role": "assistant",
"content": final_response,
@@ -6540,10 +6554,10 @@ class AIAgent:
"finish_reason": finish_reason,
}
messages.append(empty_msg)
self._cleanup_task_resources(effective_task_id)
self._persist_session(messages, conversation_history)
return {
"final_response": final_response or None,
"messages": messages,