Fix error handling in convert_to_model_response_object to handle empty error objects

[mcowger]

Relevant issues

Fixes #18407

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

[X] I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement
[X] My PR passes all unit tests on make test-unit
[X] My PR's scope is as isolated as possible, it only solves 1 specific problem

CI (LiteLLM team)
CI status guideline:

50-55 passing tests: main is stable with minor issues.
45-49 passing tests: acceptable but needs attention
<= 40 passing tests: unstable; be careful with your merges and assess the risk.
Branch creation CI run
Link:

CI run for the last commit
Link:

Merge / cherry-pick CI run
Links:

Type

🐛 Bug Fix

Changes

Modified convert_to_model_response_object in convert_dict_to_response.py to handle cases where providers (e.g., Minimax) return an empty error object (no message and no code) on successful responses. Previously, the mere presence of an error key would trigger an exception.
Added comprehensive unit tests in tests/llm_translation/test_llm_response_utils/test_empty_error_handling.py handling.py) to verify:

• Empty error objects do not trigger exceptions.
• Actual error messages still trigger exceptions.
• Error codes without messages still trigger exceptions.

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Review	Updated (UTC)
litellm	Ready	Preview, Comment	Dec 24, 2025 8:29pm