feat(agent): 24 fournisseurs LLM + refonte du panneau Agent & IA
FlowDeck CI / lint (push) Successful in 53s
FlowDeck CI / test (push) Successful in 5m47s
FlowDeck CI / docker (push) Successful in 48s

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.
This commit is contained in:
2026-09-14 22:25:57 -04:00
parent 0d475c3d2d
commit fb14c7e709
4 changed files with 225 additions and 61 deletions
+8 -2
View File
@@ -77,8 +77,14 @@ class Settings(BaseSettings):
# FlowDeck Agent (v4.10.0) — multi-LLM. Empty keys → offline/mock mode
# (deterministic rule-based planner so the agent works without any API key).
agent_enabled: bool = True
llm_provider: str = "offline" # openai | anthropic | google | ollama |
# deepseek | qwencloud | nvidia | openrouter | offline
llm_provider: str = "offline" # any id from llm_client.PROVIDERS
# (openai, anthropic, mistral, cohere,
# google, groq, deepseek, openrouter,
# nvidia, together, perplexity, xai,
# qwencloud, minimax, morph, fireworks,
# cerebras, sambanova, chutes, xiaomi,
# ltx, sealion, sensenova, memtensor,
# ollama, offline)
llm_model: str = "gpt-4o"
llm_api_key: str = ""
llm_api_base: str = "" # custom base URL (Ollama, OpenRouter, ...)