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).
This commit is contained in:
greatmengqi
2026-04-26 21:45:02 +08:00
parent 9dc25987e0
commit 3e6a34297d
365 changed files with 31220 additions and 5303 deletions
@@ -17,6 +17,7 @@ from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
from langchain_core.runnables import RunnableConfig
from deerflow.agents.thread_state import SandboxState, ThreadDataState, ThreadState
from deerflow.config.app_config import AppConfig
from deerflow.models import create_chat_model
from deerflow.subagents.config import SubagentConfig
@@ -132,24 +133,16 @@ class SubagentExecutor:
self,
config: SubagentConfig,
tools: list[BaseTool],
app_config: AppConfig,
parent_model: str | None = None,
sandbox_state: SandboxState | None = None,
thread_data: ThreadDataState | None = None,
thread_id: str | None = None,
trace_id: str | None = None,
):
"""Initialize the executor.
Args:
config: Subagent configuration.
tools: List of all available tools (will be filtered).
parent_model: The parent agent's model name for inheritance.
sandbox_state: Sandbox state from parent agent.
thread_data: Thread data from parent agent.
thread_id: Thread ID for sandbox operations.
trace_id: Trace ID from parent for distributed tracing.
"""
"""Initialize the executor."""
self.config = config
self.app_config = app_config
self.parent_model = parent_model
self.sandbox_state = sandbox_state
self.thread_data = thread_data
@@ -169,7 +162,7 @@ class SubagentExecutor:
def _create_agent(self):
"""Create the agent instance."""
model_name = _get_model_name(self.config, self.parent_model)
model = create_chat_model(name=model_name, thinking_enabled=False)
model = create_chat_model(name=model_name, thinking_enabled=False, app_config=self.app_config)
from deerflow.agents.middlewares.tool_error_handling_middleware import build_subagent_runtime_middlewares
@@ -3,6 +3,7 @@
import logging
from dataclasses import replace
from deerflow.config.app_config import AppConfig
from deerflow.sandbox.security import is_host_bash_allowed
from deerflow.subagents.builtins import BUILTIN_SUBAGENTS
from deerflow.subagents.config import SubagentConfig
@@ -10,19 +11,17 @@ from deerflow.subagents.config import SubagentConfig
logger = logging.getLogger(__name__)
def _build_custom_subagent_config(name: str) -> SubagentConfig | None:
def _build_custom_subagent_config(name: str, app_config: AppConfig) -> SubagentConfig | None:
"""Build a SubagentConfig from config.yaml custom_agents section.
Args:
name: The name of the custom subagent.
app_config: The resolved application config.
Returns:
SubagentConfig if found in custom_agents, None otherwise.
"""
from deerflow.config.subagents_config import get_subagents_app_config
app_config = get_subagents_app_config()
custom = app_config.custom_agents.get(name)
custom = app_config.subagents.custom_agents.get(name)
if custom is None:
return None
@@ -39,67 +38,44 @@ def _build_custom_subagent_config(name: str) -> SubagentConfig | None:
)
def get_subagent_config(name: str) -> SubagentConfig | None:
def get_subagent_config(name: str, app_config: AppConfig) -> SubagentConfig | None:
"""Get a subagent configuration by name, with config.yaml overrides applied.
Resolution order (mirrors Codex's config layering):
1. Built-in subagents (general-purpose, bash)
2. Custom subagents from config.yaml custom_agents section
3. Per-agent overrides from config.yaml agents section (timeout, max_turns, model, skills)
Args:
name: The name of the subagent.
Returns:
SubagentConfig if found (with any config.yaml overrides applied), None otherwise.
"""
# Step 1: Look up built-in, then fall back to custom_agents
config = BUILTIN_SUBAGENTS.get(name)
if config is None:
config = _build_custom_subagent_config(name)
config = _build_custom_subagent_config(name, app_config)
if config is None:
return None
# Step 2: Apply per-agent overrides from config.yaml agents section.
# Only explicit per-agent overrides are applied here. Global defaults
# (timeout_seconds, max_turns at the top level) apply to built-in agents
# but must NOT override custom agents' own values — custom agents define
# their own defaults in the custom_agents section.
# Lazy import to avoid circular deps.
from deerflow.config.subagents_config import get_subagents_app_config
sub_config = app_config.subagents
overrides: dict = {}
app_config = get_subagents_app_config()
is_builtin = name in BUILTIN_SUBAGENTS
agent_override = app_config.agents.get(name)
# Timeout: subagents config supplies effective per-agent override or global default.
effective_timeout = sub_config.get_timeout_for(name)
if effective_timeout != config.timeout_seconds:
logger.debug("Subagent '%s': timeout overridden (%ss -> %ss)", name, config.timeout_seconds, effective_timeout)
overrides["timeout_seconds"] = effective_timeout
overrides = {}
# Timeout: per-agent override > global default (builtins only) > config's own value
if agent_override is not None and agent_override.timeout_seconds is not None:
if agent_override.timeout_seconds != config.timeout_seconds:
logger.debug("Subagent '%s': timeout overridden (%ss -> %ss)", name, config.timeout_seconds, agent_override.timeout_seconds)
overrides["timeout_seconds"] = agent_override.timeout_seconds
elif is_builtin and app_config.timeout_seconds != config.timeout_seconds:
logger.debug("Subagent '%s': timeout from global default (%ss -> %ss)", name, config.timeout_seconds, app_config.timeout_seconds)
overrides["timeout_seconds"] = app_config.timeout_seconds
# Max turns: per-agent override > global default (builtins only) > config's own value
if agent_override is not None and agent_override.max_turns is not None:
if agent_override.max_turns != config.max_turns:
logger.debug("Subagent '%s': max_turns overridden (%s -> %s)", name, config.max_turns, agent_override.max_turns)
overrides["max_turns"] = agent_override.max_turns
elif is_builtin and app_config.max_turns is not None and app_config.max_turns != config.max_turns:
logger.debug("Subagent '%s': max_turns from global default (%s -> %s)", name, config.max_turns, app_config.max_turns)
overrides["max_turns"] = app_config.max_turns
# Max turns: subagents config supplies effective per-agent override or global default
# (falls back to ``config.max_turns`` when no override is configured).
effective_max_turns = sub_config.get_max_turns_for(name, config.max_turns)
if effective_max_turns != config.max_turns:
logger.debug("Subagent '%s': max_turns overridden (%s -> %s)", name, config.max_turns, effective_max_turns)
overrides["max_turns"] = effective_max_turns
# Model: per-agent override only (no global default for model)
effective_model = app_config.get_model_for(name)
effective_model = sub_config.get_model_for(name)
if effective_model is not None and effective_model != config.model:
logger.debug("Subagent '%s': model overridden (%s -> %s)", name, config.model, effective_model)
overrides["model"] = effective_model
# Skills: per-agent override only (no global default for skills)
effective_skills = app_config.get_skills_for(name)
effective_skills = sub_config.get_skills_for(name)
if effective_skills is not None and effective_skills != config.skills:
logger.debug("Subagent '%s': skills overridden (%s -> %s)", name, config.skills, effective_skills)
overrides["skills"] = effective_skills
@@ -110,21 +86,21 @@ def get_subagent_config(name: str) -> SubagentConfig | None:
return config
def list_subagents() -> list[SubagentConfig]:
def list_subagents(app_config: AppConfig) -> list[SubagentConfig]:
"""List all available subagent configurations (with config.yaml overrides applied).
Returns:
List of all registered SubagentConfig instances (built-in + custom).
"""
configs = []
for name in get_subagent_names():
config = get_subagent_config(name)
configs: list[SubagentConfig] = []
for name in get_subagent_names(app_config):
config = get_subagent_config(name, app_config)
if config is not None:
configs.append(config)
return configs
def get_subagent_names() -> list[str]:
def get_subagent_names(app_config: AppConfig) -> list[str]:
"""Get all available subagent names (built-in + custom).
Returns:
@@ -132,26 +108,22 @@ def get_subagent_names() -> list[str]:
"""
names = list(BUILTIN_SUBAGENTS.keys())
# Merge custom_agents from config.yaml
from deerflow.config.subagents_config import get_subagents_app_config
app_config = get_subagents_app_config()
for custom_name in app_config.custom_agents:
for custom_name in app_config.subagents.custom_agents:
if custom_name not in names:
names.append(custom_name)
return names
def get_available_subagent_names() -> list[str]:
def get_available_subagent_names(app_config: AppConfig) -> list[str]:
"""Get subagent names that should be exposed to the active runtime.
Returns:
List of subagent names visible to the current sandbox configuration.
"""
names = get_subagent_names()
names = get_subagent_names(app_config)
try:
host_bash_allowed = is_host_bash_allowed()
host_bash_allowed = is_host_bash_allowed(app_config)
except Exception:
logger.debug("Could not determine host bash availability; exposing all subagents")
return names