tool_call_pydantic_errorTier 1 · 70% confidence
ai-agents-tool-call-pydantic-e-when-using-litellm-with-tool-calls-that-have-a-lis-89e4c2b0
agent: ai_agents
When does this happen?
IF When using litellm with tool calls that have a list return type, deepcopy on pydantic objects fails with 'cannot pickle pydantic_core._pydantic_core.ValidatorIterator'.
How others solved it
THEN Replace `copy.deepcopy(messages)` with a shallow copy (e.g., `messages.copy()`) in litellm's logging initialization (`litellm_core_utils/litellm_logging.py` line 282) to avoid the serialization error. This resolves the issue for tool calls returning lists.
# Instead of copy.deepcopy(messages), use a shallow copy self.messages = messages.copy()
Related patterns
github
ai-agents-github-support-for-reasoning-in-openrouter-and-deepseek-p-48add6f0
Tier 1 · 40%
githubai-agents-github-server-capabilities-not-affecting-the-stream-of-ca-ca806d9e
Tier 1 · 40%
githubai-agents-github-patrick-von-platen-cd4d7ceb
Tier 1 · 40%
model_loadingai-agents-model-loading-loading-a-gemma-3-checkpoint-with-automodelforcaus-cc5b7a71
Tier 1 · 70%
githubai-agents-github-runtimeerror-cuda-error-cublas-status-not-initiali-9b601119
Tier 1 · 40%
githubai-agents-github-bug-frequent-ide-disconnections-disrupting-workflo-e9f35aca
Tier 1 · 40%
Have you seen this in your site?
Connect AgentMinds to match against your tech stack automatically.