deer-flow/config.example.yaml

# Configuration for the DeerFlow application
#
# Guidelines:
# - Copy this file to `config.yaml` and customize it for your environment
# - The default path of this configuration file is `config.yaml` in the current working directory.
#   However you can change it using the `DEER_FLOW_CONFIG_PATH` environment variable.
# - Environment variables are available for all field values. Example: `api_key: $OPENAI_API_KEY`
# - The `use` path is a string that looks like "package_name.sub_package_name.module_name:class_name/variable_name".

# ============================================================================
# Models Configuration
# ============================================================================
# Configure available LLM models for the agent to use

models:
  # Example: OpenAI model
  - name: gpt-4
    display_name: GPT-4
    use: langchain_openai:ChatOpenAI
    model: gpt-4
    api_key: $OPENAI_API_KEY # Use environment variable
    max_tokens: 4096
    temperature: 0.7
    supports_vision: true # Enable vision support for view_image tool

  # Example: Novita AI (OpenAI-compatible)
  # Novita provides an OpenAI-compatible API with competitive pricing
  # See: https://novita.ai
  - name: novita-deepseek-v3.2
    display_name: Novita DeepSeek V3.2
    use: langchain_openai:ChatOpenAI
    model: deepseek/deepseek-v3.2
    api_key: $NOVITA_API_KEY
    base_url: https://api.novita.ai/openai
    max_tokens: 4096
    temperature: 0.7
    supports_thinking: true
    supports_vision: true
    when_thinking_enabled:
      extra_body:
        thinking:
          type: enabled

  # Example: Anthropic Claude model
  # - name: claude-3-5-sonnet
  #   display_name: Claude 3.5 Sonnet
  #   use: langchain_anthropic:ChatAnthropic
  #   model: claude-3-5-sonnet-20241022
  #   api_key: $ANTHROPIC_API_KEY
  #   max_tokens: 8192
  #   supports_vision: true  # Enable vision support for view_image tool

  # Example: Google Gemini model
  # - name: gemini-2.5-pro
  #   display_name: Gemini 2.5 Pro
  #   use: langchain_google_genai:ChatGoogleGenerativeAI
  #   model: gemini-2.5-pro
  #   google_api_key: $GOOGLE_API_KEY
  #   max_tokens: 8192
  #   supports_vision: true

  # Example: DeepSeek model (with thinking support)
  # - name: deepseek-v3
  #   display_name: DeepSeek V3 (Thinking)
  #   use: src.models.patched_deepseek:PatchedChatDeepSeek
  #   model: deepseek-reasoner
  #   api_key: $DEEPSEEK_API_KEY
  #   max_tokens: 16384
  #   supports_thinking: true
  #   supports_vision: false  # DeepSeek V3 does not support vision
  #   when_thinking_enabled:
  #     extra_body:
  #       thinking:
  #         type: enabled

  # Example: Volcengine (Doubao) model
  - name: doubao-seed-1.8
    display_name: Doubao-Seed-1.8
    use: src.models.patched_deepseek:PatchedChatDeepSeek
    model: doubao-seed-1-8-251228
    api_base: https://ark.cn-beijing.volces.com/api/v3
    api_key: $VOLCENGINE_API_KEY
    supports_thinking: true
    supports_vision: true
    supports_reasoning_effort: true
    when_thinking_enabled:
      extra_body:
        thinking:
          type: enabled

  # Example: Kimi K2.5 model
  # - name: kimi-k2.5
  #   display_name: Kimi K2.5
  #   use: src.models.patched_deepseek:PatchedChatDeepSeek
  #   model: kimi-k2.5
  #   api_base: https://api.moonshot.cn/v1
  #   api_key: $MOONSHOT_API_KEY
  #   max_tokens: 32768
  #   supports_thinking: true
  #   supports_vision: true  # Check your specific model's capabilities
  #   when_thinking_enabled:
  #     extra_body:
  #       thinking:
  #         type: enabled

# ============================================================================
# Tool Groups Configuration
# ============================================================================
# Define groups of tools for organization and access control

tool_groups:
  - name: web
  - name: file:read
  - name: file:write
  - name: bash

# ============================================================================
# Tools Configuration
# ============================================================================
# Configure available tools for the agent to use

tools:
  # Web search tool (requires Tavily API key)
  - name: web_search
    group: web
    use: src.community.tavily.tools:web_search_tool
    max_results: 5
    # api_key: $TAVILY_API_KEY  # Set if needed

  # Web fetch tool (uses Jina AI reader)
  - name: web_fetch
    group: web
    use: src.community.jina_ai.tools:web_fetch_tool
    timeout: 10

  # Image search tool (uses DuckDuckGo)
  # Use this to find reference images before image generation
  - name: image_search
    group: web
    use: src.community.image_search.tools:image_search_tool
    max_results: 5

  # File operations tools
  - name: ls
    group: file:read
    use: src.sandbox.tools:ls_tool

  - name: read_file
    group: file:read
    use: src.sandbox.tools:read_file_tool

  - name: write_file
    group: file:write
    use: src.sandbox.tools:write_file_tool

  - name: str_replace
    group: file:write
    use: src.sandbox.tools:str_replace_tool

  # Bash execution tool
  - name: bash
    group: bash
    use: src.sandbox.tools:bash_tool

# ============================================================================
# Sandbox Configuration
# ============================================================================
# Choose between local sandbox (direct execution) or Docker-based AIO sandbox

# Option 1: Local Sandbox (Default)
# Executes commands directly on the host machine
sandbox:
  use: src.sandbox.local:LocalSandboxProvider

# Option 2: Container-based AIO Sandbox
# Executes commands in isolated containers (Docker or Apple Container)
# On macOS: Automatically prefers Apple Container if available, falls back to Docker
# On other platforms: Uses Docker
# Uncomment to use:
# sandbox:
#   use: src.community.aio_sandbox:AioSandboxProvider
#
#   # Optional: Use existing sandbox at this URL (no container will be started)
#   # base_url: http://localhost:8080
#
#   # Optional: Container image to use (works with both Docker and Apple Container)
#   # Default: enterprise-public-cn-beijing.cr.volces.com/vefaas-public/all-in-one-sandbox:latest
#   # Recommended: enterprise-public-cn-beijing.cr.volces.com/vefaas-public/all-in-one-sandbox:latest (works on both x86_64 and arm64)
#   # image: enterprise-public-cn-beijing.cr.volces.com/vefaas-public/all-in-one-sandbox:latest
#
#   # Optional: Base port for sandbox containers (default: 8080)
#   # port: 8080
#
#   # Optional: Whether to automatically start Docker container (default: true)
#   # auto_start: true
#
#   # Optional: Prefix for container names (default: deer-flow-sandbox)
#   # container_prefix: deer-flow-sandbox
#
#   # Optional: Additional mount directories from host to container
#   # NOTE: Skills directory is automatically mounted from skills.path to skills.container_path
#   # mounts:
#   #   # Other custom mounts
#   #   - host_path: /path/on/host
#   #     container_path: /home/user/shared
#   #     read_only: false
#
#   # Optional: Environment variables to inject into the sandbox container
#   # Values starting with $ will be resolved from host environment variables
#   # environment:
#   #   NODE_ENV: production
#   #   DEBUG: "false"
#   #   API_KEY: $MY_API_KEY        # Reads from host's MY_API_KEY env var
#   #   DATABASE_URL: $DATABASE_URL  # Reads from host's DATABASE_URL env var

# Option 3: Provisioner-managed AIO Sandbox (docker-compose-dev)
# Each sandbox_id gets a dedicated Pod in k3s, managed by the provisioner.
# Recommended for production or advanced users who want better isolation and scalability.:
# sandbox:
#   use: src.community.aio_sandbox:AioSandboxProvider
#   provisioner_url: http://provisioner:8002

# ============================================================================
# Subagents Configuration
# ============================================================================
# Configure timeouts for subagent execution
# Subagents are background workers delegated tasks by the lead agent

# subagents:
#   # Default timeout in seconds for all subagents (default: 900 = 15 minutes)
#   timeout_seconds: 900
#
#   # Optional per-agent timeout overrides
#   agents:
#     general-purpose:
#       timeout_seconds: 1800  # 30 minutes for complex multi-step tasks
#     bash:
#       timeout_seconds: 300   # 5 minutes for quick command execution

# ============================================================================
# Skills Configuration
# ============================================================================
# Configure skills directory for specialized agent workflows

skills:
  # Path to skills directory on the host (relative to project root or absolute)
  # Default: ../skills (relative to backend directory)
  # Uncomment to customize:
  # path: /absolute/path/to/custom/skills

  # Path where skills are mounted in the sandbox container
  # This is used by the agent to access skills in both local and Docker sandbox
  # Default: /mnt/skills
  container_path: /mnt/skills

# ============================================================================
# Title Generation Configuration
# ============================================================================
# Automatic conversation title generation settings

title:
  enabled: true
  max_words: 6
  max_chars: 60
  model_name: null # Use default model (first model in models list)

# ============================================================================
# Summarization Configuration
# ============================================================================
# Automatically summarize conversation history when token limits are approached
# This helps maintain context in long conversations without exceeding model limits

summarization:
  enabled: true

  # Model to use for summarization (null = use default model)
  # Recommended: Use a lightweight, cost-effective model like "gpt-4o-mini" or similar
  model_name: null

  # Trigger conditions - at least one required
  # Summarization runs when ANY threshold is met (OR logic)
  # You can specify a single trigger or a list of triggers
  trigger:
    # Trigger when token count reaches 15564
    - type: tokens
      value: 15564
    # Uncomment to also trigger when message count reaches 50
    # - type: messages
    #   value: 50
    # Uncomment to trigger when 80% of model's max input tokens is reached
    # - type: fraction
    #   value: 0.8

  # Context retention policy after summarization
  # Specifies how much recent history to preserve
  keep:
    # Keep the most recent 10 messages (recommended)
    type: messages
    value: 10
    # Alternative: Keep specific token count
    # type: tokens
    # value: 3000
    # Alternative: Keep percentage of model's max input tokens
    # type: fraction
    # value: 0.3

  # Maximum tokens to keep when preparing messages for summarization
  # Set to null to skip trimming (not recommended for very long conversations)
  trim_tokens_to_summarize: 15564

  # Custom summary prompt template (null = use default LangChain prompt)
  # The prompt should guide the model to extract important context
  summary_prompt: null

# ============================================================================
# Memory Configuration
# ============================================================================
# Global memory mechanism
# Stores user context and conversation history for personalized responses
memory:
  enabled: true
  storage_path: memory.json # Path relative to backend directory
  debounce_seconds: 30 # Wait time before processing queued updates
  model_name: null # Use default model
  max_facts: 100 # Maximum number of facts to store
  fact_confidence_threshold: 0.7 # Minimum confidence for storing facts
  injection_enabled: true # Whether to inject memory into system prompt
  max_injection_tokens: 2000 # Maximum tokens for memory injection