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".

# ============================================================================
# Config Version (used to detect outdated config files)
# ============================================================================
# Bump this number when the config schema changes.
# Run `make config-upgrade` to merge new fields into your local config.yaml.
config_version: 3

# ============================================================================
# Logging
# ============================================================================
# Log level for deerflow modules (debug/info/warning/error)
log_level: info

# ============================================================================
# Token Usage Tracking
# ============================================================================
# Track LLM token usage per model call (input/output/total tokens)
# Logs at info level via TokenUsageMiddleware
token_usage:
  enabled: false

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

models:
  # Example: Volcengine (Doubao) model
  # - name: doubao-seed-1.8
  #   display_name: Doubao-Seed-1.8
  #   use: deerflow.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: 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: OpenAI Responses API model
  # - name: gpt-5-responses
  #   display_name: GPT-5 (Responses API)
  #   use: langchain_openai:ChatOpenAI
  #   model: gpt-5
  #   api_key: $OPENAI_API_KEY
  #   use_responses_api: true
  #   output_version: responses/v1
  #   supports_vision: true

  # 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
  #   when_thinking_enabled:
  #     thinking:
  #       type: enabled

  # Example: Google Gemini model (native SDK, no thinking support)
  # - name: gemini-2.5-pro
  #   display_name: Gemini 2.5 Pro
  #   use: langchain_google_genai:ChatGoogleGenerativeAI
  #   model: gemini-2.5-pro
  #   gemini_api_key: $GEMINI_API_KEY
  #   max_tokens: 8192
  #   supports_vision: true

  # Example: Gemini model via OpenAI-compatible gateway (with thinking support)
  # Use PatchedChatOpenAI so that tool-call thought_signature values on tool_calls
  # are preserved across multi-turn tool-call conversations — required by the
  # Gemini API when thinking is enabled. See:
  # https://docs.cloud.google.com/vertex-ai/generative-ai/docs/thought-signatures
  # - name: gemini-2.5-pro-thinking
  #   display_name: Gemini 2.5 Pro (Thinking)
  #   use: deerflow.models.patched_openai:PatchedChatOpenAI
  #   model: google/gemini-2.5-pro-preview   # model name as expected by your gateway
  #   api_key: $GEMINI_API_KEY
  #   base_url: https://<your-openai-compat-gateway>/v1
  #   max_tokens: 16384
  #   supports_thinking: true
  #   supports_vision: true
  #   when_thinking_enabled:
  #     extra_body:
  #       thinking:
  #         type: enabled

  # Example: DeepSeek model (with thinking support)
  # - name: deepseek-v3
  #   display_name: DeepSeek V3 (Thinking)
  #   use: deerflow.models.patched_deepseek:PatchedChatDeepSeek
  #   model: deepseek-reasoner
  #   api_key: $DEEPSEEK_API_KEY
  #   max_tokens: 8192
  #   supports_thinking: true
  #   supports_vision: false  # DeepSeek V3 does not support vision
  #   when_thinking_enabled:
  #     extra_body:
  #       thinking:
  #         type: enabled

  # Example: Kimi K2.5 model
  # - name: kimi-k2.5
  #   display_name: Kimi K2.5
  #   use: deerflow.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

  # 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: MiniMax (OpenAI-compatible) - International Edition
  # MiniMax provides high-performance models with 204K context window
  # Docs: https://platform.minimax.io/docs/api-reference/text-openai-api
  # - name: minimax-m2.5
  #   display_name: MiniMax M2.5
  #   use: langchain_openai:ChatOpenAI
  #   model: MiniMax-M2.5
  #   api_key: $MINIMAX_API_KEY
  #   base_url: https://api.minimax.io/v1
  #   max_tokens: 4096
  #   temperature: 1.0  # MiniMax requires temperature in (0.0, 1.0]
  #   supports_vision: true

  # - name: minimax-m2.5-highspeed
  #   display_name: MiniMax M2.5 Highspeed
  #   use: langchain_openai:ChatOpenAI
  #   model: MiniMax-M2.5-highspeed
  #   api_key: $MINIMAX_API_KEY
  #   base_url: https://api.minimax.io/v1
  #   max_tokens: 4096
  #   temperature: 1.0  # MiniMax requires temperature in (0.0, 1.0]
  #   supports_vision: true

  # Example: MiniMax (OpenAI-compatible) - CN 中国区用户
  # MiniMax provides high-performance models with 204K context window
  # Docs: https://platform.minimaxi.com/docs/api-reference/text-openai-api
  # - name: minimax-m2.7
  #   display_name: MiniMax M2.7
  #   use: langchain_openai:ChatOpenAI
  #   model: MiniMax-M2.7
  #   api_key: $MINIMAX_API_KEY
  #   base_url: https://api.minimaxi.com/v1
  #   max_tokens: 4096
  #   temperature: 1.0  # MiniMax requires temperature in (0.0, 1.0]
  #   supports_vision: true

  # - name: minimax-m2.5-highspeed
  #   display_name: MiniMax M2.5 Highspeed
  #   use: langchain_openai:ChatOpenAI
  #   model: MiniMax-M2.5-highspeed
  #   api_key: $MINIMAX_API_KEY
  #   base_url: https://api.minimaxi.com/v1
  #   max_tokens: 4096
  #   temperature: 1.0  # MiniMax requires temperature in (0.0, 1.0]
  #   supports_vision: true

  
  # Example: OpenRouter (OpenAI-compatible)
  # OpenRouter models use the same ChatOpenAI + base_url pattern as other OpenAI-compatible gateways.
  # - name: openrouter-gemini-2.5-flash
  #   display_name: Gemini 2.5 Flash (OpenRouter)
  #   use: langchain_openai:ChatOpenAI
  #   model: google/gemini-2.5-flash-preview
  #   api_key: $OPENAI_API_KEY
  #   base_url: https://openrouter.ai/api/v1
  #   max_tokens: 8192
  #   temperature: 0.7

# ============================================================================
# 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: deerflow.community.tavily.tools:web_search_tool
    max_results: 5
    # api_key: $TAVILY_API_KEY  # Set if needed

  # Web search tool (uses InfoQuest, requires InfoQuest API key)
  # - name: web_search
  #   group: web
  #   use: deerflow.community.infoquest.tools:web_search_tool
  #   # Used to limit the scope of search results, only returns content within the specified time range. Set to -1 to disable time filtering
  #   search_time_range: 10

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

  # Web fetch tool (uses InfoQuest)
  # - name: web_fetch
  #   group: web
  #   use: deerflow.community.infoquest.tools:web_fetch_tool
  #   # Overall timeout for the entire crawling process (in seconds). Set to positive value to enable, -1 to disable
  #   timeout: 10
  #   # Waiting time after page loading (in seconds). Set to positive value to enable, -1 to disable
  #   fetch_time: 10
  #   # Timeout for navigating to the page (in seconds). Set to positive value to enable, -1 to disable
  #   navigation_timeout: 30

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

  # Image search tool (uses InfoQuest)
  # - name: image_search
  #   group: web
  #   use: deerflow.community.infoquest.tools:image_search_tool
  #   # Used to limit the scope of image search results, only returns content within the specified time range. Set to -1 to disable time filtering
  #   image_search_time_range: 10
  #   # Image size filter. Options: "l" (large), "m" (medium), "i" (icon).
  #   image_size: "i"

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

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

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

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

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

# ============================================================================
# Tool Search Configuration (Deferred Tool Loading)
# ============================================================================
# When enabled, MCP tools are not loaded into the agent's context directly.
# Instead, they are listed by name in the system prompt and discoverable
# via the tool_search tool at runtime.
# This reduces context usage and improves tool selection accuracy when
# multiple MCP servers expose a large number of tools.

tool_search:
  enabled: false

# ============================================================================
# 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: deerflow.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: deerflow.community.aio_sandbox:AioSandboxProvider
#
#   # 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: Maximum number of concurrent sandbox containers (default: 3)
#   # When the limit is reached the least-recently-used sandbox is evicted to
#   # make room for new ones. Use a positive integer here; omit this field to use the default.
#   # replicas: 3
#
#   # 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: deerflow.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

# ============================================================================
# ACP Agents Configuration
# ============================================================================
# Configure external ACP-compatible agents for the built-in `invoke_acp_agent` tool.

# acp_agents:
#   claude_code:
#     # DeerFlow expects an ACP adapter here. The standard `claude` CLI does not
#     # speak ACP directly. Install `claude-agent-acp` separately or use:
#     command: npx
#     args: ["-y", "@zed-industries/claude-agent-acp"]
#     description: Claude Code for implementation, refactoring, and debugging
#     model: null
#     # auto_approve_permissions: false  # Set to true to auto-approve ACP permission requests
#
#   codex:
#     # DeerFlow expects an ACP adapter here. The standard `codex` CLI does not
#     # speak ACP directly. Install `codex-acp` separately or use:
#     command: npx
#     args: ["-y", "@zed-industries/codex-acp"]
#     description: Codex CLI for repository tasks and code generation
#     model: null
#     # auto_approve_permissions: false  # Set to true to auto-approve ACP permission requests

# ============================================================================
# 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

# ============================================================================
# Checkpointer Configuration
# ============================================================================
# Configure state persistence for the embedded DeerFlowClient.
# The LangGraph Server manages its own state persistence separately
# via the server infrastructure (this setting does not affect it).
#
# When configured, DeerFlowClient will automatically use this checkpointer,
# enabling multi-turn conversations to persist across process restarts.
#
# Supported types:
#   memory   - In-process only. State is lost when the process exits. (default)
#   sqlite   - File-based SQLite persistence. Survives restarts.
#              Requires: uv add langgraph-checkpoint-sqlite
#   postgres - PostgreSQL persistence. Suitable for multi-process deployments.
#              Requires: uv add langgraph-checkpoint-postgres psycopg[binary] psycopg-pool
#
# Examples:
#
# In-memory (default when omitted — no persistence):
# checkpointer:
#   type: memory
#
# SQLite (file-based, single-process):
checkpointer:
  type: sqlite
  connection_string: checkpoints.db
#
# PostgreSQL (multi-process, production):
# checkpointer:
#   type: postgres
#   connection_string: postgresql://user:password@localhost:5432/deerflow

# ============================================================================
# IM Channels Configuration
# ============================================================================
# Connect DeerFlow to external messaging platforms.
# All channels use outbound connections (WebSocket or polling) — no public IP required.

# channels:
#   # LangGraph Server URL for thread/message management (default: http://localhost:2024)
#   langgraph_url: http://localhost:2024
#   # Gateway API URL for auxiliary queries like /models, /memory (default: http://localhost:8001)
#   gateway_url: http://localhost:8001
#
#   # Optional: default mobile/session settings for all IM channels
#   session:
#     assistant_id: lead_agent
#     config:
#       recursion_limit: 100
#     context:
#       thinking_enabled: true
#       is_plan_mode: false
#       subagent_enabled: false
#
#   feishu:
#     enabled: false
#     app_id: $FEISHU_APP_ID
#     app_secret: $FEISHU_APP_SECRET
#
#   slack:
#     enabled: false
#     bot_token: $SLACK_BOT_TOKEN     # xoxb-...
#     app_token: $SLACK_APP_TOKEN     # xapp-... (Socket Mode)
#     allowed_users: []               # empty = allow all
#
#   telegram:
#     enabled: false
#     bot_token: $TELEGRAM_BOT_TOKEN
#     allowed_users: []               # empty = allow all
#
#     # Optional: channel-level session overrides
#     session:
#       assistant_id: mobile_agent
#       context:
#         thinking_enabled: false
#
#       # Optional: per-user overrides by user_id
#       users:
#         "123456789":
#           assistant_id: vip_agent
#           config:
#             recursion_limit: 150
#           context:
#             thinking_enabled: true
#             subagent_enabled: true

# ============================================================================
# Guardrails Configuration
# ============================================================================
# Optional pre-execution authorization for tool calls.
# When enabled, every tool call passes through the configured provider
# before execution. Three options: built-in allowlist, OAP policy provider,
# or custom provider. See backend/docs/GUARDRAILS.md for full documentation.
#
# Providers are loaded by class path via resolve_variable (same as models/tools).

# --- Option 1: Built-in AllowlistProvider (zero external deps) ---
# guardrails:
#   enabled: true
#   provider:
#     use: deerflow.guardrails.builtin:AllowlistProvider
#     config:
#       denied_tools: ["bash", "write_file"]

# --- Option 2: OAP passport provider (open standard, any implementation) ---
#   The Open Agent Passport (OAP) spec defines passport format and decision codes.
#   Any OAP-compliant provider works. Example using APort (reference implementation):
#     pip install aport-agent-guardrails && aport setup --framework deerflow
# guardrails:
#   enabled: true
#   provider:
#     use: aport_guardrails.providers.generic:OAPGuardrailProvider

# --- Option 3: Custom provider (any class with evaluate/aevaluate methods) ---
# guardrails:
#   enabled: true
#   provider:
#     use: my_package:MyGuardrailProvider
#     config:
#       key: value