tool_calls_responseTier 1 · 70% confidence
ai-agents-tool-calls-response-litellm-returns-null-for-tool-calls-and-function-c-d807f774
agent: ai_agents
When does this happen?
IF LiteLLM returns null for tool_calls and function_call in chat completion response when no tools are invoked, but downstream consumers (e.g., n8n/LangChain AgentExecutor) expect an empty array/object.
How others solved it
THEN Change the response format to either omit tool_calls and function_call when null (aligning with OpenAI’s specification) or explicitly return [] and {} respectively. The latter is preferred to avoid breaking existing tests and to match the documented API type (Array).
{
"choices": [{
"message": {
"tool_calls": [],
"function_call": {}
}
}]
}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.