fix(agent): URLs OpenAI-compatibles validees pour les fournisseurs LLM

Cohere -> /compatibility/v1, Google Gemini -> /v1beta/openai, Perplexity -> host racine, Chutes -> llm.chutes.ai/v1, SenseNova -> compatible-mode/v1. Mise a jour des modeles par defaut (xAI grok-4.6, Fireworks deepseek-v4-pro-0813, Cohere command-a-plus). Retrait de LTX Studio (aucune API chat-completions) et MemTensor/MemOS (API memoire non OpenAI-compatible, auth Token + /chat). Google utilise desormais l'auth Bearer pour lister les modeles. Test de non-regression ajoute.
2026-09-14 22:50:36 -04:00
parent fb14c7e709
commit a0db4d6e65
4 changed files with 42 additions and 28 deletions
@@ -83,8 +83,7 @@ class Settings(BaseSettings):
                                       #  nvidia, together, perplexity, xai,
                                       #  qwencloud, minimax, morph, fireworks,
                                       #  cerebras, sambanova, chutes, xiaomi,
-                                       #  ltx, sealion, sensenova, memtensor,
-                                       #  ollama, offline)
+                                       #  sealion, sensenova, ollama, offline)
    llm_model: str = "gpt-4o"
    llm_api_key: str = ""
    llm_api_base: str = ""             # custom base URL (Ollama, OpenRouter, ...)