feat(agent): 24 fournisseurs LLM + refonte du panneau Agent & IA

Enregistre OpenAI, Anthropic, Mistral, Cohere, Google Gemini, Groq, DeepSeek, OpenRouter, NVIDIA NIM, Together, Perplexity, xAI, DashScope, MiniMax, Morph, Fireworks, Cerebras, SambaNova, Chutes, Xiaomi, LTX, SEA-LION, SenseNova et MemTensor (URLs de base + presets de modeles + libelles).

Settings: panneau Agent & IA repense en maitre/detail (liste rechercheable + volet de configuration) pour tenir avec des dizaines de fournisseurs, en conservant tous les boutons/fonctions.

app/services/llm_config.py

@@ -14,7 +14,7 @@ import json
 import time
 
 from app.config import settings
-from app.services.llm_client import PROVIDER_MODELS, PROVIDERS
+from app.services.llm_client import PROVIDER_LABELS, PROVIDER_MODELS, PROVIDERS
 
 # Providers whose /v1/models lists far more entries than /v1/chat/completions
 # actually serves. The fetched list is validated (name filter + live probe)
@@ -165,7 +165,7 @@ def provider_info() -> list[dict]:
             models.insert(0, default_model)
         out.append({
             "id": name,
-            "name": name.capitalize(),
+            "name": PROVIDER_LABELS.get(name) or name.replace("_", " ").title(),
             "default_model": default_model,
             "models": models,
             "base_url": (base or ""),