furyhawk/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-05-23 16:35:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(config): eliminate global mutable state, wire DeerFlowContext into runtime

Browse Source 
- Freeze all config models (AppConfig + 15 sub-configs) with frozen=True
- Purify from_file() — remove 9 load_*_from_dict() side-effect calls
- Replace mtime/reload/push/pop machinery with single ContextVar + init_app_config()
- Delete 10 sub-module globals and their getters/setters/loaders
- Migrate 50+ consumers from get_*_config() to get_app_config().xxx

- Expand DeerFlowContext: app_config + thread_id + agent_name (frozen dataclass)
- Wire into Gateway runtime (worker.py) and DeerFlowClient via context= parameter
- Remove sandbox_id from runtime.context — flows through ThreadState.sandbox only
- Middleware/tools access runtime.context directly via Runtime[DeerFlowContext] generic
- resolve_context() retained at server entry points for LangGraph Server fallback
This commit is contained in:
greatmengqi
2026-04-13 23:49:31 +08:00
parent c4d273a68a
commit edf345cd72
111 changed files with 4848 additions and 4079 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/packages/harness/deerflow/agents/checkpointer/async_provider.py
+2 -2
View File
@@ -29,7 +29,7 @@ from deerflow.agents.checkpointer.provider import (
POSTGRES_INSTALL,
SQLITE_INSTALL,
)
from deerflow.config.app_config import get_app_config
from deerflow.config.app_config import AppConfig
from deerflow.runtime.store._sqlite_utils import ensure_sqlite_parent_dir, resolve_sqlite_conn_str
logger = logging.getLogger(__name__)
@@ -94,7 +94,7 @@ async def make_checkpointer() -> AsyncIterator[Checkpointer]:
Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
"""
config = get_app_config()
config = AppConfig.current()
if config.checkpointer is None:
from langgraph.checkpoint.memory import InMemorySaver
backend/packages/harness/deerflow/agents/checkpointer/provider.py
+6 -21
View File
@@ -25,7 +25,7 @@ from collections.abc import Iterator
from langgraph.types import Checkpointer
from deerflow.config.app_config import get_app_config
from deerflow.config.app_config import AppConfig
from deerflow.config.checkpointer_config import CheckpointerConfig
from deerflow.runtime.store._sqlite_utils import resolve_sqlite_conn_str
@@ -113,25 +113,10 @@ def get_checkpointer() -> Checkpointer:
if _checkpointer is not None:
return _checkpointer
# Ensure app config is loaded before checking checkpointer config
# This prevents returning InMemorySaver when config.yaml actually has a checkpointer section
# but hasn't been loaded yet
from deerflow.config.app_config import _app_config
from deerflow.config.checkpointer_config import get_checkpointer_config
config = get_checkpointer_config()
if config is None and _app_config is None:
# Only load app config lazily when neither the app config nor an explicit
# checkpointer config has been initialized yet. This keeps tests that
# intentionally set the global checkpointer config isolated from any
# ambient config.yaml on disk.
try:
get_app_config()
except FileNotFoundError:
# In test environments without config.yaml, this is expected.
pass
config = get_checkpointer_config()
try:
config = AppConfig.current().checkpointer
except (LookupError, FileNotFoundError):
config = None
if config is None:
from langgraph.checkpoint.memory import InMemorySaver
@@ -180,7 +165,7 @@ def checkpointer_context() -> Iterator[Checkpointer]:
Yields an ``InMemorySaver`` when no checkpointer is configured in *config.yaml*.
"""
config = get_app_config()
config = AppConfig.current()
if config.checkpointer is None:
from langgraph.checkpoint.memory import InMemorySaver
backend/packages/harness/deerflow/agents/lead_agent/agent.py
+11 -8
View File
@@ -3,6 +3,7 @@ import logging
from langchain.agents import create_agent
from langchain.agents.middleware import AgentMiddleware, SummarizationMiddleware
from langchain_core.runnables import RunnableConfig
from langgraph.graph.state import CompiledStateGraph
from deerflow.agents.lead_agent.prompt import apply_prompt_template
from deerflow.agents.middlewares.clarification_middleware import ClarificationMiddleware
@@ -16,8 +17,8 @@ from deerflow.agents.middlewares.tool_error_handling_middleware import build_lea
from deerflow.agents.middlewares.view_image_middleware import ViewImageMiddleware
from deerflow.agents.thread_state import ThreadState
from deerflow.config.agents_config import load_agent_config
from deerflow.config.app_config import get_app_config
from deerflow.config.summarization_config import get_summarization_config
from deerflow.config.app_config import AppConfig
from deerflow.config.deer_flow_context import DeerFlowContext
from deerflow.models import create_chat_model
logger = logging.getLogger(__name__)
@@ -25,7 +26,7 @@ logger = logging.getLogger(__name__)
def _resolve_model_name(requested_model_name: str | None = None) -> str:
"""Resolve a runtime model name safely, falling back to default if invalid. Returns None if no models are configured."""
app_config = get_app_config()
app_config = AppConfig.current()
default_model_name = app_config.models[0].name if app_config.models else None
if default_model_name is None:
raise ValueError("No chat models are configured. Please configure at least one model in config.yaml.")
@@ -40,7 +41,7 @@ def _resolve_model_name(requested_model_name: str | None = None) -> str:
def _create_summarization_middleware() -> SummarizationMiddleware | None:
"""Create and configure the summarization middleware from config."""
config = get_summarization_config()
config = AppConfig.current().summarization
if not config.enabled:
return None
@@ -230,7 +231,7 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
middlewares.append(todo_list_middleware)
# Add TokenUsageMiddleware when token_usage tracking is enabled
if get_app_config().token_usage.enabled:
if AppConfig.current().token_usage.enabled:
middlewares.append(TokenUsageMiddleware())
# Add TitleMiddleware
@@ -241,7 +242,7 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
# Add ViewImageMiddleware only if the current model supports vision.
# Use the resolved runtime model_name from make_lead_agent to avoid stale config values.
app_config = get_app_config()
app_config = AppConfig.current()
model_config = app_config.get_model_config(model_name) if model_name else None
if model_config is not None and model_config.supports_vision:
middlewares.append(ViewImageMiddleware())
@@ -270,7 +271,7 @@ def _build_middlewares(config: RunnableConfig, model_name: str | None, agent_nam
return middlewares
def make_lead_agent(config: RunnableConfig):
def make_lead_agent(config: RunnableConfig) -> CompiledStateGraph:
# Lazy import to avoid circular dependency
from deerflow.tools import get_available_tools
from deerflow.tools.builtins import setup_agent
@@ -293,7 +294,7 @@ def make_lead_agent(config: RunnableConfig):
# Final model name resolution: request → agent config → global default, with fallback for unknown names
model_name = _resolve_model_name(requested_model_name or agent_model_name)
app_config = get_app_config()
app_config = AppConfig.current()
model_config = app_config.get_model_config(model_name)
if model_config is None:
@@ -336,6 +337,7 @@ def make_lead_agent(config: RunnableConfig):
middleware=_build_middlewares(config, model_name=model_name),
system_prompt=apply_prompt_template(subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, available_skills=set(["bootstrap"])),
state_schema=ThreadState,
context_schema=DeerFlowContext,
)
# Default lead agent (unchanged behavior)
@@ -347,4 +349,5 @@ def make_lead_agent(config: RunnableConfig):
subagent_enabled=subagent_enabled, max_concurrent_subagents=max_concurrent_subagents, agent_name=agent_name, available_skills=set(agent_config.skills) if agent_config and agent_config.skills is not None else None
),
state_schema=ThreadState,
context_schema=DeerFlowContext,
)
backend/packages/harness/deerflow/agents/lead_agent/prompt.py
+6 -14
View File
@@ -5,6 +5,7 @@ from datetime import datetime
from functools import lru_cache
from deerflow.config.agents_config import load_agent_soul
from deerflow.config.app_config import AppConfig
from deerflow.skills import load_skills
from deerflow.skills.types import Skill
from deerflow.subagents import get_available_subagent_names
@@ -518,9 +519,8 @@ def _get_memory_context(agent_name: str | None = None) -> str:
"""
try:
from deerflow.agents.memory import format_memory_for_injection, get_memory_data
from deerflow.config.memory_config import get_memory_config
config = get_memory_config()
config = AppConfig.current().memory
if not config.enabled or not config.injection_enabled:
return ""
@@ -576,9 +576,7 @@ def get_skills_prompt_section(available_skills: set[str] | None = None) -> str:
skills = _get_enabled_skills()
try:
from deerflow.config import get_app_config
config = get_app_config()
config = AppConfig.current()
container_base_path = config.skills.container_path
skill_evolution_enabled = config.skill_evolution.enabled
except Exception:
@@ -617,9 +615,7 @@ def get_deferred_tools_prompt_section() -> str:
from deerflow.tools.builtins.tool_search import get_deferred_registry
try:
from deerflow.config import get_app_config
if not get_app_config().tool_search.enabled:
if not AppConfig.current().tool_search.enabled:
return ""
except Exception:
return ""
@@ -635,9 +631,7 @@ def get_deferred_tools_prompt_section() -> str:
def _build_acp_section() -> str:
"""Build the ACP agent prompt section, only if ACP agents are configured."""
try:
from deerflow.config.acp_config import get_acp_agents
agents = get_acp_agents()
agents = AppConfig.current().acp_agents
if not agents:
return ""
except Exception:
@@ -655,9 +649,7 @@ def _build_acp_section() -> str:
def _build_custom_mounts_section() -> str:
"""Build a prompt section for explicitly configured sandbox mounts."""
try:
from deerflow.config import get_app_config
mounts = get_app_config().sandbox.mounts or []
mounts = AppConfig.current().sandbox.mounts or []
except Exception:
logger.exception("Failed to load configured sandbox mounts for the lead-agent prompt")
return ""
backend/packages/harness/deerflow/agents/memory/queue.py
+3 -3
View File
@@ -7,7 +7,7 @@ from dataclasses import dataclass, field
from datetime import UTC, datetime
from typing import Any
from deerflow.config.memory_config import get_memory_config
from deerflow.config.app_config import AppConfig
logger = logging.getLogger(__name__)
@@ -56,7 +56,7 @@ class MemoryUpdateQueue:
correction_detected: Whether recent turns include an explicit correction signal.
reinforcement_detected: Whether recent turns include a positive reinforcement signal.
"""
config = get_memory_config()
config = AppConfig.current().memory
if not config.enabled:
return
@@ -87,7 +87,7 @@ class MemoryUpdateQueue:
def _reset_timer(self) -> None:
"""Reset the debounce timer."""
config = get_memory_config()
config = AppConfig.current().memory
# Cancel existing timer if any
if self._timer is not None:
backend/packages/harness/deerflow/agents/memory/storage.py
+3 -3
View File
@@ -9,7 +9,7 @@ from pathlib import Path
from typing import Any
from deerflow.config.agents_config import AGENT_NAME_PATTERN
from deerflow.config.memory_config import get_memory_config
from deerflow.config.app_config import AppConfig
from deerflow.config.paths import get_paths
logger = logging.getLogger(__name__)
@@ -84,7 +84,7 @@ class FileMemoryStorage(MemoryStorage):
self._validate_agent_name(agent_name)
return get_paths().agent_memory_file(agent_name)
config = get_memory_config()
config = AppConfig.current().memory
if config.storage_path:
p = Path(config.storage_path)
return p if p.is_absolute() else get_paths().base_dir / p
@@ -177,7 +177,7 @@ def get_memory_storage() -> MemoryStorage:
if _storage_instance is not None:
return _storage_instance
config = get_memory_config()
config = AppConfig.current().memory
storage_class_path = config.storage_class
try:
backend/packages/harness/deerflow/agents/memory/updater.py
+4 -4
View File
@@ -16,7 +16,7 @@ from deerflow.agents.memory.storage import (
get_memory_storage,
utc_now_iso_z,
)
from deerflow.config.memory_config import get_memory_config
from deerflow.config.app_config import AppConfig
from deerflow.models import create_chat_model
logger = logging.getLogger(__name__)
@@ -265,7 +265,7 @@ class MemoryUpdater:
def _get_model(self):
"""Get the model for memory updates."""
config = get_memory_config()
config = AppConfig.current().memory
model_name = self._model_name or config.model_name
return create_chat_model(name=model_name, thinking_enabled=False)
@@ -289,7 +289,7 @@ class MemoryUpdater:
Returns:
True if update was successful, False otherwise.
"""
config = get_memory_config()
config = AppConfig.current().memory
if not config.enabled:
return False
@@ -378,7 +378,7 @@ class MemoryUpdater:
Returns:
Updated memory data.
"""
config = get_memory_config()
config = AppConfig.current().memory
now = utc_now_iso_z()
# Update user sections
backend/packages/harness/deerflow/agents/middlewares/loop_detection_middleware.py
+6 -7
View File
@@ -24,6 +24,8 @@ from langchain.agents.middleware import AgentMiddleware
from langchain_core.messages import HumanMessage
from langgraph.runtime import Runtime
from deerflow.config.deer_flow_context import DeerFlowContext
logger = logging.getLogger(__name__)
# Defaults — can be overridden via constructor
@@ -180,12 +182,9 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
self._tool_freq: dict[str, dict[str, int]] = defaultdict(lambda: defaultdict(int))
self._tool_freq_warned: dict[str, set[str]] = defaultdict(set)
def _get_thread_id(self, runtime: Runtime) -> str:
def _get_thread_id(self, runtime: Runtime[DeerFlowContext]) -> str:
"""Extract thread_id from runtime context for per-thread tracking."""
thread_id = runtime.context.get("thread_id") if runtime.context else None
if thread_id:
return thread_id
return "default"
return runtime.context.thread_id or "default"
def _evict_if_needed(self) -> None:
"""Evict least recently used threads if over the limit.
@@ -350,11 +349,11 @@ class LoopDetectionMiddleware(AgentMiddleware[AgentState]):
return None
@override
def after_model(self, state: AgentState, runtime: Runtime) -> dict | None:
def after_model(self, state: AgentState, runtime: Runtime[DeerFlowContext]) -> dict | None:
return self._apply(state, runtime)
@override
async def aafter_model(self, state: AgentState, runtime: Runtime) -> dict | None:
async def aafter_model(self, state: AgentState, runtime: Runtime[DeerFlowContext]) -> dict | None:
return self._apply(state, runtime)
def reset(self, thread_id: str | None = None) -> None:
backend/packages/harness/deerflow/agents/middlewares/memory_middleware.py
+5 -10
View File
@@ -6,11 +6,10 @@ from typing import Any, override
from langchain.agents import AgentState
from langchain.agents.middleware import AgentMiddleware
from langgraph.config import get_config
from langgraph.runtime import Runtime
from deerflow.agents.memory.queue import get_memory_queue
from deerflow.config.memory_config import get_memory_config
from deerflow.config.deer_flow_context import DeerFlowContext
logger = logging.getLogger(__name__)
@@ -193,7 +192,7 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
self._agent_name = agent_name
@override
def after_agent(self, state: MemoryMiddlewareState, runtime: Runtime) -> dict | None:
def after_agent(self, state: MemoryMiddlewareState, runtime: Runtime[DeerFlowContext]) -> dict | None:
"""Queue conversation for memory update after agent completes.
Args:
@@ -203,15 +202,11 @@ class MemoryMiddleware(AgentMiddleware[MemoryMiddlewareState]):
Returns:
None (no state changes needed from this middleware).
"""
config = get_memory_config()
if not config.enabled:
memory_config = runtime.context.app_config.memory
if not memory_config.enabled:
return None
# Get thread ID from runtime context first, then fall back to LangGraph's configurable metadata
thread_id = runtime.context.get("thread_id") if runtime.context else None
if thread_id is None:
config_data = get_config()
thread_id = config_data.get("configurable", {}).get("thread_id")
thread_id = runtime.context.thread_id
if not thread_id:
logger.debug("No thread_id in context, skipping memory update")
return None
backend/packages/harness/deerflow/agents/middlewares/thread_data_middleware.py
+4 -8
View File
@@ -3,10 +3,10 @@ from typing import NotRequired, override
from langchain.agents import AgentState
from langchain.agents.middleware import AgentMiddleware
from langgraph.config import get_config
from langgraph.runtime import Runtime
from deerflow.agents.thread_state import ThreadDataState
from deerflow.config.deer_flow_context import DeerFlowContext
from deerflow.config.paths import Paths, get_paths
logger = logging.getLogger(__name__)
@@ -74,14 +74,10 @@ class ThreadDataMiddleware(AgentMiddleware[ThreadDataMiddlewareState]):
return self._get_thread_paths(thread_id)
@override
def before_agent(self, state: ThreadDataMiddlewareState, runtime: Runtime) -> dict | None:
context = runtime.context or {}
thread_id = context.get("thread_id")
if thread_id is None:
config = get_config()
thread_id = config.get("configurable", {}).get("thread_id")
def before_agent(self, state: ThreadDataMiddlewareState, runtime: Runtime[DeerFlowContext]) -> dict | None:
thread_id = runtime.context.thread_id
if thread_id is None:
if not thread_id:
raise ValueError("Thread ID is required in runtime context or config.configurable")
if self._lazy_init:
backend/packages/harness/deerflow/agents/middlewares/title_middleware.py
+6 -6
View File
@@ -7,7 +7,7 @@ from langchain.agents import AgentState
from langchain.agents.middleware import AgentMiddleware
from langgraph.runtime import Runtime
from deerflow.config.title_config import get_title_config
from deerflow.config.app_config import AppConfig
from deerflow.models import create_chat_model
logger = logging.getLogger(__name__)
@@ -45,7 +45,7 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
def _should_generate_title(self, state: TitleMiddlewareState) -> bool:
"""Check if we should generate a title for this thread."""
config = get_title_config()
config = AppConfig.current().title
if not config.enabled:
return False
@@ -70,7 +70,7 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
Returns (prompt_string, user_msg) so callers can use user_msg as fallback.
"""
config = get_title_config()
config = AppConfig.current().title
messages = state.get("messages", [])
user_msg_content = next((m.content for m in messages if m.type == "human"), "")
@@ -88,13 +88,13 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
def _parse_title(self, content: object) -> str:
"""Normalize model output into a clean title string."""
config = get_title_config()
config = AppConfig.current().title
title_content = self._normalize_content(content)
title = title_content.strip().strip('"').strip("'")
return title[: config.max_chars] if len(title) > config.max_chars else title
def _fallback_title(self, user_msg: str) -> str:
config = get_title_config()
config = AppConfig.current().title
fallback_chars = min(config.max_chars, 50)
if len(user_msg) > fallback_chars:
return user_msg[:fallback_chars].rstrip() + "..."
@@ -113,7 +113,7 @@ class TitleMiddleware(AgentMiddleware[TitleMiddlewareState]):
if not self._should_generate_title(state):
return None
config = get_title_config()
config = AppConfig.current().title
prompt, user_msg = self._build_title_prompt(state)
try:
backend/packages/harness/deerflow/agents/middlewares/tool_error_handling_middleware.py
+2 -2
View File
@@ -94,9 +94,9 @@ def _build_runtime_middlewares(
middlewares.append(LLMErrorHandlingMiddleware())
# Guardrail middleware (if configured)
from deerflow.config.guardrails_config import get_guardrails_config
from deerflow.config.app_config import AppConfig
guardrails_config = get_guardrails_config()
guardrails_config = AppConfig.current().guardrails
if guardrails_config.enabled and guardrails_config.provider:
import inspect
backend/packages/harness/deerflow/agents/middlewares/uploads_middleware.py
+3 -9
View File
@@ -9,6 +9,7 @@ from langchain.agents.middleware import AgentMiddleware
from langchain_core.messages import HumanMessage
from langgraph.runtime import Runtime
from deerflow.config.deer_flow_context import DeerFlowContext
from deerflow.config.paths import Paths, get_paths
from deerflow.utils.file_conversion import extract_outline
@@ -184,7 +185,7 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
return files if files else None
@override
def before_agent(self, state: UploadsMiddlewareState, runtime: Runtime) -> dict | None:
def before_agent(self, state: UploadsMiddlewareState, runtime: Runtime[DeerFlowContext]) -> dict | None:
"""Inject uploaded files information before agent execution.
New files come from the current message's additional_kwargs.files.
@@ -213,14 +214,7 @@ class UploadsMiddleware(AgentMiddleware[UploadsMiddlewareState]):
return None
# Resolve uploads directory for existence checks
thread_id = (runtime.context or {}).get("thread_id")
if thread_id is None:
try:
from langgraph.config import get_config
thread_id = get_config().get("configurable", {}).get("thread_id")
except RuntimeError:
pass # get_config() raises outside a runnable context (e.g. unit tests)
thread_id = runtime.context.thread_id
uploads_dir = self._paths.sandbox_uploads_dir(thread_id) if thread_id else None
# Get newly uploaded files from the current message's additional_kwargs.files