Model Zoo

# ============================================================
# MODEL ZOO — one lightweight agent per provider.
#
# This file is the proof of model optionality: five agents whose
# ONLY meaningful difference is the `model:` line. The framework
# reads that string and routes each agent to the right provider:
#
#   ollama/qwen3.5:9b → local Ollama   (keyless — nothing leaves your machine)
#   claude-*          → Anthropic      (ANTHROPIC_API_KEY)
#   grok-*            → xAI            (XAI_API_KEY)
#   gpt-*             → OpenAI         (OPENAI_API_KEY)
#   gemini-*          → Google         (GOOGLE_GENAI_API_KEY)
#
# Run the proof:  npm run demo:models        (scripts/demo_model_optionality.ts
#   sends "explain quantum mechanics" to every agent whose provider is
#   available, and prints input, thinking, output, and a token/latency trace.
#   Providers without a key are skipped, never fatal.)
#
# Or chat with the zoo:  npm run chat:syndicate -- --syndicate model_zoo
#   (the orchestrator delegates your question to a provider you name).
# ============================================================

syndicate_name: "Model Zoo"
memory_system: "session-only"

orchestrator:
  name: "Zookeeper"
  model: "gemini-3.1-flash-lite"
  instruction: |
    You are the Zookeeper, coordinator of a menagerie of language models from
    five different providers. When the user asks a question, delegate it to
    the subagent they name (qwen_local, claude, grok, gpt, or gemini) — or,
    if they name none, pick one and say which you chose. Return the
    subagent's answer verbatim, attributed to it.

subagents:
  - name: "qwen_local"
    # Qwen3.5 is the newest generation that ships small dense sizes; the
    # 9B is the largest that fits a 16/18 GB laptop with room for context.
    # Qwen3.8 is stronger but 27B-only (18 GB of weights) — see the size
    # table in lib/models/ollamaLlm.ts before changing this line.
    description: "Qwen 3.5 (9B), an open-weight model running locally via Ollama. Keyless."
    model: "ollama/qwen3.5:9b"
    instruction: |
      You are a concise explainer. Answer in three short paragraphs at most,
      plain language first, one concrete example, no headings.

  - name: "claude"
    description: "Claude Sonnet, by Anthropic."
    model: "claude-sonnet-4-6"
    instruction: |
      You are a concise explainer. Answer in three short paragraphs at most,
      plain language first, one concrete example, no headings.
    # Extended thinking: the adapter maps thinkingBudget to Anthropic's
    # thinking parameter and surfaces the scratchpad as THINKING output.
    generateContentConfig:
      thinkingConfig:
        thinkingBudget: 2048

  - name: "grok"
    description: "Grok 4.7 (reasoning effort: medium), by xAI."
    # The adapter pins reasoning effort 'medium' for grok-4.5/4.7 requests
    # (DEFAULT_GROK_REASONING_EFFORT, lib/config.ts).
    model: "grok-4.7"
    instruction: |
      You are a concise explainer. Answer in three short paragraphs at most,
      plain language first, one concrete example, no headings.

  - name: "gpt"
    description: "GPT-5 mini, by OpenAI."
    model: "gpt-5-mini"
    instruction: |
      You are a concise explainer. Answer in three short paragraphs at most,
      plain language first, one concrete example, no headings.

  - name: "gemini"
    description: "Gemini Flash Lite, by Google."
    model: "gemini-3.1-flash-lite"
    instruction: |
      You are a concise explainer. Answer in three short paragraphs at most,
      plain language first, one concrete example, no headings.