Fix: KeyError 'message' in response.py when both keys missing#927
Closed
hurtdidit wants to merge 1 commit intoagent0ai:developmentfrom
Closed
Fix: KeyError 'message' in response.py when both keys missing#927hurtdidit wants to merge 1 commit intoagent0ai:developmentfrom
hurtdidit wants to merge 1 commit intoagent0ai:developmentfrom
Conversation
Bug: response.py execute() crashes with KeyError when neither 'text' nor
'message' keys exist in self.args dictionary.
Current buggy code:
self.args['text'] if 'text' in self.args else self.args['message']
This fails when both keys are missing, causing agent to completely stall.
Fix: Use .get() method with safe fallback:
message_text = self.args.get('text') or self.args.get('message', '')
return Response(message=message_text, break_loop=True)
Impact: Prevents agent stalls in edge cases where response tool is
called without proper arguments.
hurtdidit
pushed a commit
to hurtdidit/agent-zero
that referenced
this pull request
Feb 1, 2026
Empty or whitespace-only AI messages cause API validation errors with strict providers (OpenAI, Z.ai, GLM): "Assistant messages must have either content or tool_calls" This is a companion fix to PR agent0ai#927 (response.py KeyError fix). When that fix returns an empty string instead of crashing, the empty string can become an empty AIMessage that fails API validation. Changes: - Pre-compute content before creating message objects - Skip AI messages where content is None, empty, or whitespace-only - Human messages are not filtered (they can be empty per spec) Tested on 4 production A0 instances.
ky3mu4lp
pushed a commit
to ky3mu4lp/agent-zero
that referenced
this pull request
Feb 24, 2026
Empty or whitespace-only AI messages cause API validation errors with strict providers (OpenAI, Z.ai, GLM): "Assistant messages must have either content or tool_calls" This is a companion fix to PR agent0ai#927 (response.py KeyError fix). When that fix returns an empty string instead of crashing, the empty string can become an empty AIMessage that fails API validation. Changes: - Pre-compute content before creating message objects - Skip AI messages where content is None, empty, or whitespace-only - Human messages are not filtered (they can be empty per spec) Tested on 4 production A0 instances.
|
Closing due to inactivity of 90 days. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Bug Description
response.pyexecute()crashes withKeyError: 'message'when neithertextnormessagekeys exist inself.argsdictionary.Current Buggy Code (line 7)
When both keys are missing, this throws
KeyError: 'message'and causes the agent to completely stall.Proposed Fix
Using
.get()with a safe fallback prevents the crash.Impact
Testing
Note: This PR replaces #925 which incorrectly targeted
maininstead ofdevelopment.