Files
deer-flow/backend/packages/harness/deerflow/config/app_config.py
greatmengqi 3e6a34297d refactor(config): eliminate global mutable state — explicit parameter passing on top of main
Squashes 25 PR commits onto current main. AppConfig becomes a pure value
object with no ambient lookup. Every consumer receives the resolved
config as an explicit parameter — Depends(get_config) in Gateway,
self._app_config in DeerFlowClient, runtime.context.app_config in agent
runs, AppConfig.from_file() at the LangGraph Server registration
boundary.

Phase 1 — frozen data + typed context

- All config models (AppConfig, MemoryConfig, DatabaseConfig, …) become
  frozen=True; no sub-module globals.
- AppConfig.from_file() is pure (no side-effect singleton loaders).
- Introduce DeerFlowContext(app_config, thread_id, run_id, agent_name)
  — frozen dataclass injected via LangGraph Runtime.
- Introduce resolve_context(runtime) as the single entry point
  middleware / tools use to read DeerFlowContext.

Phase 2 — pure explicit parameter passing

- Gateway: app.state.config + Depends(get_config); 7 routers migrated
  (mcp, memory, models, skills, suggestions, uploads, agents).
- DeerFlowClient: __init__(config=...) captures config locally.
- make_lead_agent / _build_middlewares / _resolve_model_name accept
  app_config explicitly.
- RunContext.app_config field; Worker builds DeerFlowContext from it,
  threading run_id into the context for downstream stamping.
- Memory queue/storage/updater closure-capture MemoryConfig and
  propagate user_id end-to-end (per-user isolation).
- Sandbox/skills/community/factories/tools thread app_config.
- resolve_context() rejects non-typed runtime.context.
- Test suite migrated off AppConfig.current() monkey-patches.
- AppConfig.current() classmethod deleted.

Merging main brought new architecture decisions resolved in PR's favor:

- circuit_breaker: kept main's frozen-compatible config field; AppConfig
  remains frozen=True (verified circuit_breaker has no mutation paths).
- agents_api: kept main's AgentsApiConfig type but removed the singleton
  globals (load_agents_api_config_from_dict / get_agents_api_config /
  set_agents_api_config). 8 routes in agents.py now read via
  Depends(get_config).
- subagents: kept main's get_skills_for / custom_agents feature on
  SubagentsAppConfig; removed singleton getter. registry.py now reads
  app_config.subagents directly.
- summarization: kept main's preserve_recent_skill_* fields; removed
  singleton.
- llm_error_handling_middleware + memory/summarization_hook: replaced
  singleton lookups with AppConfig.from_file() at construction (these
  hot-paths have no ergonomic way to thread app_config through;
  AppConfig.from_file is a pure load).
- worker.py + thread_data_middleware.py: DeerFlowContext.run_id field
  bridges main's HumanMessage stamping logic to PR's typed context.

Trade-offs (follow-up work):

- main's #2138 (async memory updater) reverted to PR's sync
  implementation. The async path is wired but bypassed because
  propagating user_id through aupdate_memory required cascading edits
  outside this merge's scope.
- tests/test_subagent_skills_config.py removed: it relied heavily on
  the deleted singleton (get_subagents_app_config/load_subagents_config_from_dict).
  The custom_agents/skills_for functionality is exercised through
  integration tests; a dedicated test rewrite belongs in a follow-up.

Verification: backend test suite — 2560 passed, 4 skipped, 84 failures.
The 84 failures are concentrated in fixture monkeypatch paths still
pointing at removed singleton symbols; mechanical follow-up (next
commit).
2026-04-26 21:45:02 +08:00

239 lines
11 KiB
Python

from __future__ import annotations
import logging
import os
from pathlib import Path
from typing import Any, Self
import yaml
from dotenv import load_dotenv
from pydantic import BaseModel, ConfigDict, Field
from deerflow.config.acp_config import ACPAgentConfig
from deerflow.config.agents_api_config import AgentsApiConfig
from deerflow.config.checkpointer_config import CheckpointerConfig
from deerflow.config.database_config import DatabaseConfig
from deerflow.config.extensions_config import ExtensionsConfig
from deerflow.config.guardrails_config import GuardrailsConfig
from deerflow.config.memory_config import MemoryConfig
from deerflow.config.model_config import ModelConfig
from deerflow.config.run_events_config import RunEventsConfig
from deerflow.config.sandbox_config import SandboxConfig
from deerflow.config.skill_evolution_config import SkillEvolutionConfig
from deerflow.config.skills_config import SkillsConfig
from deerflow.config.stream_bridge_config import StreamBridgeConfig
from deerflow.config.subagents_config import SubagentsAppConfig
from deerflow.config.summarization_config import SummarizationConfig
from deerflow.config.title_config import TitleConfig
from deerflow.config.token_usage_config import TokenUsageConfig
from deerflow.config.tool_config import ToolConfig, ToolGroupConfig
from deerflow.config.tool_search_config import ToolSearchConfig
load_dotenv()
logger = logging.getLogger(__name__)
class CircuitBreakerConfig(BaseModel):
"""Configuration for the LLM Circuit Breaker."""
failure_threshold: int = Field(default=5, description="Number of consecutive failures before tripping the circuit")
recovery_timeout_sec: int = Field(default=60, description="Time in seconds before attempting to recover the circuit")
def _default_config_candidates() -> tuple[Path, ...]:
"""Return deterministic config.yaml locations without relying on cwd."""
backend_dir = Path(__file__).resolve().parents[4]
repo_root = backend_dir.parent
return (backend_dir / "config.yaml", repo_root / "config.yaml")
class AppConfig(BaseModel):
"""Config for the DeerFlow application"""
log_level: str = Field(default="info", description="Logging level for deerflow modules (debug/info/warning/error)")
token_usage: TokenUsageConfig = Field(default_factory=TokenUsageConfig, description="Token usage tracking configuration")
models: list[ModelConfig] = Field(default_factory=list, description="Available models")
sandbox: SandboxConfig = Field(description="Sandbox configuration")
tools: list[ToolConfig] = Field(default_factory=list, description="Available tools")
tool_groups: list[ToolGroupConfig] = Field(default_factory=list, description="Available tool groups")
skills: SkillsConfig = Field(default_factory=SkillsConfig, description="Skills configuration")
skill_evolution: SkillEvolutionConfig = Field(default_factory=SkillEvolutionConfig, description="Agent-managed skill evolution configuration")
extensions: ExtensionsConfig = Field(default_factory=ExtensionsConfig, description="Extensions configuration (MCP servers and skills state)")
tool_search: ToolSearchConfig = Field(default_factory=ToolSearchConfig, description="Tool search / deferred loading configuration")
title: TitleConfig = Field(default_factory=TitleConfig, description="Automatic title generation configuration")
summarization: SummarizationConfig = Field(default_factory=SummarizationConfig, description="Conversation summarization configuration")
memory: MemoryConfig = Field(default_factory=MemoryConfig, description="Memory subsystem configuration")
agents_api: AgentsApiConfig = Field(default_factory=AgentsApiConfig, description="Custom-agent management API configuration")
subagents: SubagentsAppConfig = Field(default_factory=SubagentsAppConfig, description="Subagent runtime configuration")
guardrails: GuardrailsConfig = Field(default_factory=GuardrailsConfig, description="Guardrail middleware configuration")
circuit_breaker: CircuitBreakerConfig = Field(default_factory=CircuitBreakerConfig, description="LLM circuit breaker configuration")
database: DatabaseConfig = Field(default_factory=DatabaseConfig, description="Unified database backend configuration")
run_events: RunEventsConfig = Field(default_factory=RunEventsConfig, description="Run event storage configuration")
model_config = ConfigDict(extra="allow", frozen=True)
checkpointer: CheckpointerConfig | None = Field(default=None, description="Checkpointer configuration")
stream_bridge: StreamBridgeConfig | None = Field(default=None, description="Stream bridge configuration")
acp_agents: dict[str, ACPAgentConfig] = Field(default_factory=dict, description="ACP agent configurations keyed by agent name")
@classmethod
def resolve_config_path(cls, config_path: str | None = None) -> Path:
"""Resolve the config file path.
Priority:
1. If provided `config_path` argument, use it.
2. If provided `DEER_FLOW_CONFIG_PATH` environment variable, use it.
3. Otherwise, search deterministic backend/repository-root defaults from `_default_config_candidates()`.
"""
if config_path:
path = Path(config_path)
if not Path.exists(path):
raise FileNotFoundError(f"Config file specified by param `config_path` not found at {path}")
return path
elif os.getenv("DEER_FLOW_CONFIG_PATH"):
path = Path(os.getenv("DEER_FLOW_CONFIG_PATH"))
if not Path.exists(path):
raise FileNotFoundError(f"Config file specified by environment variable `DEER_FLOW_CONFIG_PATH` not found at {path}")
return path
else:
for path in _default_config_candidates():
if path.exists():
return path
raise FileNotFoundError("`config.yaml` file not found at the default backend or repository root locations")
@classmethod
def from_file(cls, config_path: str | None = None) -> Self:
"""Load config from YAML file.
See `resolve_config_path` for more details.
Args:
config_path: Path to the config file.
Returns:
AppConfig: The loaded config.
"""
resolved_path = cls.resolve_config_path(config_path)
with open(resolved_path, encoding="utf-8") as f:
config_data = yaml.safe_load(f) or {}
# Check config version before processing
cls._check_config_version(config_data, resolved_path)
config_data = cls.resolve_env_variables(config_data)
# Load extensions config separately (it's in a different file)
extensions_config = ExtensionsConfig.from_file()
config_data["extensions"] = extensions_config.model_dump()
result = cls.model_validate(config_data)
return result
@classmethod
def _check_config_version(cls, config_data: dict, config_path: Path) -> None:
"""Check if the user's config.yaml is outdated compared to config.example.yaml.
Emits a warning if the user's config_version is lower than the example's.
Missing config_version is treated as version 0 (pre-versioning).
"""
try:
user_version = int(config_data.get("config_version", 0))
except (TypeError, ValueError):
user_version = 0
# Find config.example.yaml by searching config.yaml's directory and its parents
example_path = None
search_dir = config_path.parent
for _ in range(5): # search up to 5 levels
candidate = search_dir / "config.example.yaml"
if candidate.exists():
example_path = candidate
break
parent = search_dir.parent
if parent == search_dir:
break
search_dir = parent
if example_path is None:
return
try:
with open(example_path, encoding="utf-8") as f:
example_data = yaml.safe_load(f)
raw = example_data.get("config_version", 0) if example_data else 0
try:
example_version = int(raw)
except (TypeError, ValueError):
example_version = 0
except Exception:
return
if user_version < example_version:
logger.warning(
"Your config.yaml (version %d) is outdated — the latest version is %d. Run `make config-upgrade` to merge new fields into your config.",
user_version,
example_version,
)
@classmethod
def resolve_env_variables(cls, config: Any) -> Any:
"""Recursively resolve environment variables in the config.
Environment variables are resolved using the `os.getenv` function. Example: $OPENAI_API_KEY
Args:
config: The config to resolve environment variables in.
Returns:
The config with environment variables resolved.
"""
if isinstance(config, str):
if config.startswith("$"):
env_value = os.getenv(config[1:])
if env_value is None:
raise ValueError(f"Environment variable {config[1:]} not found for config value {config}")
return env_value
return config
elif isinstance(config, dict):
return {k: cls.resolve_env_variables(v) for k, v in config.items()}
elif isinstance(config, list):
return [cls.resolve_env_variables(item) for item in config]
return config
def get_model_config(self, name: str) -> ModelConfig | None:
"""Get the model config by name.
Args:
name: The name of the model to get the config for.
Returns:
The model config if found, otherwise None.
"""
return next((model for model in self.models if model.name == name), None)
def get_tool_config(self, name: str) -> ToolConfig | None:
"""Get the tool config by name.
Args:
name: The name of the tool to get the config for.
Returns:
The tool config if found, otherwise None.
"""
return next((tool for tool in self.tools if tool.name == name), None)
def get_tool_group_config(self, name: str) -> ToolGroupConfig | None:
"""Get the tool group config by name.
Args:
name: The name of the tool group to get the config for.
Returns:
The tool group config if found, otherwise None.
"""
return next((group for group in self.tool_groups if group.name == name), None)
# AppConfig is a pure value object: construct with ``from_file()``, pass around.
# Composition roots that hold the resolved instance:
# - Gateway: ``app.state.config`` via ``Depends(get_config)``
# - Client: ``DeerFlowClient._app_config``
# - Agent run: ``Runtime[DeerFlowContext].context.app_config``