Deploy v9equilibre sur main: routing OFF (gpt-5.1 only) + k=3 + prompt adouci

Deploy v5 (BM25+routing gpt-mini) + prompt FR anti-hallucination renforce sur main

Fix error Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

Change endpoint to APIM endpoint

Add team yml and endpoint LLM models

Call LLM model from Azure OpenAI endpoint