mirror of
https://github.com/crewAIInc/crewAI.git
synced 2026-04-11 05:22:41 +00:00
f69171cd76
When api='responses' is set on an Azure LLM instance, calls are delegated to the OpenAI Responses API implementation with the Azure resource's /openai/v1/ base URL, reusing the fully-tested OpenAI Responses API code path. New fields on AzureCompletion: - api: Literal['completions', 'responses'] (default: 'completions') - instructions, store, previous_response_id, include, builtin_tools - parse_tool_outputs, auto_chain, auto_chain_reasoning - reasoning_effort, seed, max_completion_tokens Usage: llm = LLM(model='azure/gpt-4o', api='responses', api_key=KEY, endpoint=ENDPOINT) Closes #5202 Co-Authored-By: João <joao@crewai.com>