mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-23 08:25:57 +00:00
greatmengqi
3e6a34297d
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).
97 lines
2.6 KiB
Python
97 lines
2.6 KiB
Python
"""Abstract interface for run metadata storage.
|
|
|
|
RunManager depends on this interface. Implementations:
|
|
- MemoryRunStore: in-memory dict (development, tests)
|
|
- Future: RunRepository backed by SQLAlchemy ORM
|
|
|
|
All methods accept an optional user_id for user isolation.
|
|
When user_id is None, no user filtering is applied (single-user mode).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import abc
|
|
from typing import Any
|
|
|
|
|
|
class RunStore(abc.ABC):
|
|
@abc.abstractmethod
|
|
async def put(
|
|
self,
|
|
run_id: str,
|
|
*,
|
|
thread_id: str,
|
|
assistant_id: str | None = None,
|
|
user_id: str | None = None,
|
|
status: str = "pending",
|
|
multitask_strategy: str = "reject",
|
|
metadata: dict[str, Any] | None = None,
|
|
kwargs: dict[str, Any] | None = None,
|
|
error: str | None = None,
|
|
created_at: str | None = None,
|
|
follow_up_to_run_id: str | None = None,
|
|
) -> None:
|
|
pass
|
|
|
|
@abc.abstractmethod
|
|
async def get(self, run_id: str) -> dict[str, Any] | None:
|
|
pass
|
|
|
|
@abc.abstractmethod
|
|
async def list_by_thread(
|
|
self,
|
|
thread_id: str,
|
|
*,
|
|
user_id: str | None = None,
|
|
limit: int = 100,
|
|
) -> list[dict[str, Any]]:
|
|
pass
|
|
|
|
@abc.abstractmethod
|
|
async def update_status(
|
|
self,
|
|
run_id: str,
|
|
status: str,
|
|
*,
|
|
error: str | None = None,
|
|
) -> None:
|
|
pass
|
|
|
|
@abc.abstractmethod
|
|
async def delete(self, run_id: str) -> None:
|
|
pass
|
|
|
|
@abc.abstractmethod
|
|
async def update_run_completion(
|
|
self,
|
|
run_id: str,
|
|
*,
|
|
status: str,
|
|
total_input_tokens: int = 0,
|
|
total_output_tokens: int = 0,
|
|
total_tokens: int = 0,
|
|
llm_call_count: int = 0,
|
|
lead_agent_tokens: int = 0,
|
|
subagent_tokens: int = 0,
|
|
middleware_tokens: int = 0,
|
|
message_count: int = 0,
|
|
last_ai_message: str | None = None,
|
|
first_human_message: str | None = None,
|
|
error: str | None = None,
|
|
) -> None:
|
|
pass
|
|
|
|
@abc.abstractmethod
|
|
async def list_pending(self, *, before: str | None = None) -> list[dict[str, Any]]:
|
|
pass
|
|
|
|
@abc.abstractmethod
|
|
async def aggregate_tokens_by_thread(self, thread_id: str) -> dict[str, Any]:
|
|
"""Aggregate token usage for completed runs in a thread.
|
|
|
|
Returns a dict with keys: total_tokens, total_input_tokens,
|
|
total_output_tokens, total_runs, by_model (model_name → {tokens, runs}),
|
|
by_caller ({lead_agent, subagent, middleware}).
|
|
"""
|
|
pass
|