# ═══════════════════════════════════════════════════════════
# LiteLLM Proxy — Routing pour Effi
# Endpoint OpenAI-compatible sur :4000 (host network)
# ‎
# Backend unique : JeanOrchestrator (port 8080 sur PC gaming .11)
# via jean-proxy :3012 + WOL auto si PC eteint.
# ‎
# L'orchestrateur gere automatiquement le switch entre :
#   - Qwen3.6-35B MoE I-Nano (defaut, 11.7 Go, 100k ctx, ~70 tok/s)
#   - Qwen3.6-27B IQ4_XS (code/analyse, 14.6 Go, 55k ctx, ~60 tok/s)
# ‎
# Tous les modeles passent par le meme proxy :3012.
# L'orchestrateur detecte le modele demande et charge le bon LLM.
# Retour automatique au MoE apres 15 min sans 27B.
# ═══════════════════════════════════════════════════════════

model_list:
  # ═════════════════════════════════════════════════════════
  # Profil 1 — Raisonnement ON (défaut, pour tâches complexes)
  # Le modele reflechit (jusqu'a 2048 tokens de reasoning_content)
  # avant de produire sa reponse. Bon pour code, analyse, RAG, rapports.
  # ═════════════════════════════════════════════════════════
  - model_name: qwen3.6-reason
    litellm_params:
      model: openai/qwen3.6-reason
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: true

  - model_name: qwen3.6-27b
    litellm_params:
      model: openai/qwen3.6-27b
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: true

  # ═════════════════════════════════════════════════════════
  # Profil 2 — Raisonnement OFF (chat rapide, ~5x moins de latence)
  # Reponse immediate (TTFT <1s) sans phase de reflexion.
  # Ideal pour : chat interactif, redaction de mail, extraction
  # structuree simple, Q/R directes.
  # ═════════════════════════════════════════════════════════
  - model_name: qwen3.6-fast
    litellm_params:
      model: openai/qwen3.6-fast
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: false

  # Alias court "qwen3.6" = fast par defaut (usage chat le plus courant)
  - model_name: qwen3.6
    litellm_params:
      model: openai/qwen3.6
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: false

  # ═════════════════════════════════════════════════════════
  # Profil 3 — Qwen3.6-35B MoE APEX I-Nano (chat Hermes, usage quotidien)
  # Modele MoE : 35B total / 3B actifs, 11.7 Go, cache KV 5x plus petit
  # que le 27B -> contexte 100k possible. Cohabite avec ComfyUI.
  # Route via le meme proxy :3012 que le 27B (orchestrateur fait le switch).
  # ═════════════════════════════════════════════════════════
  - model_name: qwen3.6-moe
    litellm_params:
      model: openai/qwen3.6-moe
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: false

  - model_name: qwen3.6-moe-reason
    litellm_params:
      model: openai/qwen3.6-moe-reason
      api_base: http://localhost:3012/v1
      api_key: "null"
      timeout: 600
      extra_body:
        chat_template_kwargs:
          enable_thinking: true

  # ═════════════════════════════════════════════════════════
  # Backend Ollama — COMMENTE (contention VRAM, voir entete)
  # Pour reactiver si dispo (autre machine / GPU dedie), decommenter
  # et s'assurer que le GPU peut charger les deux modeles.
  # ═════════════════════════════════════════════════════════
  # - model_name: llama3.1-8b
  #   litellm_params:
  #     model: ollama/llama3.1:8b
  #     api_base: http://localhost:3011
  #     timeout: 600

litellm_settings:
  drop_params: false   # ne pas dropper: on veut passer chat_template_kwargs a Jean
  telemetry: false

general_settings:
  master_key: sk-effi-litellm-master