# Known-working validation subset on the companion development account.
# This never substitutes for default_config.yaml's full BGE/OpenAI/Doubao sweep.
chat_models:
  kimi:
    model: kimi-k2.5
    base_url: https://api.moonshot.cn/v1
    api_key_env: KIMI_API_KEY
    disable_thinking: true
    temperature: 0.6
    pricing:
      currency: CNY
      as_of_date: "2026-07-29"
      source_url: https://platform.kimi.com/docs/pricing/chat-k25
      input_per_million: 4.00
      cached_input_per_million: 0.70
      output_per_million: 21.00
      source_note: Published Kimi K2.5 list price; input rate is cache-miss/uncached.
  doubao:
    model: doubao-seed-1-6-250615
    base_url: https://ark.cn-beijing.volces.com/api/v3
    api_key_env: ARK_API_KEY

embeddings:
  mistral:
    model: mistral-embed
    base_url: https://api.mistral.ai/v1
    api_key_env: MISTRAL_API_KEY
    pricing:
      currency: USD
      as_of_date: "2026-07-29"
      source_url: https://mistral.ai/pricing/api/
      input_per_million: 0.10
      source_note: Published Mistral Embed list price.
  codestral:
    model: codestral-embed
    base_url: https://api.mistral.ai/v1
    api_key_env: MISTRAL_API_KEY

rerankers:
  none:
    type: none
  kimi-semantic:
    type: llm
    chat_model: kimi

judge:
  evaluator: kimi
  model: kimi-k2.5

experiment_7_4:
  main_model: kimi
  embedding: mistral
  reranker: kimi-semantic
  rounds_per_chunk: 6
  overlap: 2

experiment_7_11:
  embeddings: [mistral, codestral]
  rerankers: [none, kimi-semantic]
  main_models: [kimi, doubao]
  retrieval_judge_model: kimi
  max_search_rounds: 3
  rounds_per_chunk: 6
  overlap: 2