mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-05-24 17:06:00 +00:00
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
@@ -0,0 +1,187 @@
|
||||
"""JSONL file-backed RunEventStore implementation.
|
||||
|
||||
Each run's events are stored in a single file:
|
||||
``.deer-flow/threads/{thread_id}/runs/{run_id}.jsonl``
|
||||
|
||||
All categories (message, trace, lifecycle) are in the same file.
|
||||
This backend is suitable for lightweight single-node deployments.
|
||||
|
||||
Known trade-off: ``list_messages()`` must scan all run files for a
|
||||
thread since messages from multiple runs need unified seq ordering.
|
||||
``list_events()`` reads only one file -- the fast path.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
from datetime import UTC, datetime
|
||||
from pathlib import Path
|
||||
|
||||
from deerflow.runtime.events.store.base import RunEventStore
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_SAFE_ID_PATTERN = re.compile(r"^[A-Za-z0-9_\-]+$")
|
||||
|
||||
|
||||
class JsonlRunEventStore(RunEventStore):
|
||||
def __init__(self, base_dir: str | Path | None = None):
|
||||
self._base_dir = Path(base_dir) if base_dir else Path(".deer-flow")
|
||||
self._seq_counters: dict[str, int] = {} # thread_id -> current max seq
|
||||
|
||||
@staticmethod
|
||||
def _validate_id(value: str, label: str) -> str:
|
||||
"""Validate that an ID is safe for use in filesystem paths."""
|
||||
if not value or not _SAFE_ID_PATTERN.match(value):
|
||||
raise ValueError(f"Invalid {label}: must be alphanumeric/dash/underscore, got {value!r}")
|
||||
return value
|
||||
|
||||
def _thread_dir(self, thread_id: str) -> Path:
|
||||
self._validate_id(thread_id, "thread_id")
|
||||
return self._base_dir / "threads" / thread_id / "runs"
|
||||
|
||||
def _run_file(self, thread_id: str, run_id: str) -> Path:
|
||||
self._validate_id(run_id, "run_id")
|
||||
return self._thread_dir(thread_id) / f"{run_id}.jsonl"
|
||||
|
||||
def _next_seq(self, thread_id: str) -> int:
|
||||
self._seq_counters[thread_id] = self._seq_counters.get(thread_id, 0) + 1
|
||||
return self._seq_counters[thread_id]
|
||||
|
||||
def _ensure_seq_loaded(self, thread_id: str) -> None:
|
||||
"""Load max seq from existing files if not yet cached."""
|
||||
if thread_id in self._seq_counters:
|
||||
return
|
||||
max_seq = 0
|
||||
thread_dir = self._thread_dir(thread_id)
|
||||
if thread_dir.exists():
|
||||
for f in thread_dir.glob("*.jsonl"):
|
||||
for line in f.read_text(encoding="utf-8").strip().splitlines():
|
||||
try:
|
||||
record = json.loads(line)
|
||||
max_seq = max(max_seq, record.get("seq", 0))
|
||||
except json.JSONDecodeError:
|
||||
logger.debug("Skipping malformed JSONL line in %s", f)
|
||||
continue
|
||||
self._seq_counters[thread_id] = max_seq
|
||||
|
||||
def _write_record(self, record: dict) -> None:
|
||||
path = self._run_file(record["thread_id"], record["run_id"])
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(path, "a", encoding="utf-8") as f:
|
||||
f.write(json.dumps(record, default=str, ensure_ascii=False) + "\n")
|
||||
|
||||
def _read_thread_events(self, thread_id: str) -> list[dict]:
|
||||
"""Read all events for a thread, sorted by seq."""
|
||||
events = []
|
||||
thread_dir = self._thread_dir(thread_id)
|
||||
if not thread_dir.exists():
|
||||
return events
|
||||
for f in sorted(thread_dir.glob("*.jsonl")):
|
||||
for line in f.read_text(encoding="utf-8").strip().splitlines():
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
events.append(json.loads(line))
|
||||
except json.JSONDecodeError:
|
||||
logger.debug("Skipping malformed JSONL line in %s", f)
|
||||
continue
|
||||
events.sort(key=lambda e: e.get("seq", 0))
|
||||
return events
|
||||
|
||||
def _read_run_events(self, thread_id: str, run_id: str) -> list[dict]:
|
||||
"""Read events for a specific run file."""
|
||||
path = self._run_file(thread_id, run_id)
|
||||
if not path.exists():
|
||||
return []
|
||||
events = []
|
||||
for line in path.read_text(encoding="utf-8").strip().splitlines():
|
||||
if not line:
|
||||
continue
|
||||
try:
|
||||
events.append(json.loads(line))
|
||||
except json.JSONDecodeError:
|
||||
logger.debug("Skipping malformed JSONL line in %s", path)
|
||||
continue
|
||||
events.sort(key=lambda e: e.get("seq", 0))
|
||||
return events
|
||||
|
||||
async def put(self, *, thread_id, run_id, event_type, category, content="", metadata=None, created_at=None):
|
||||
self._ensure_seq_loaded(thread_id)
|
||||
seq = self._next_seq(thread_id)
|
||||
record = {
|
||||
"thread_id": thread_id,
|
||||
"run_id": run_id,
|
||||
"event_type": event_type,
|
||||
"category": category,
|
||||
"content": content,
|
||||
"metadata": metadata or {},
|
||||
"seq": seq,
|
||||
"created_at": created_at or datetime.now(UTC).isoformat(),
|
||||
}
|
||||
self._write_record(record)
|
||||
return record
|
||||
|
||||
async def put_batch(self, events):
|
||||
if not events:
|
||||
return []
|
||||
results = []
|
||||
for ev in events:
|
||||
record = await self.put(**ev)
|
||||
results.append(record)
|
||||
return results
|
||||
|
||||
async def list_messages(self, thread_id, *, limit=50, before_seq=None, after_seq=None):
|
||||
all_events = self._read_thread_events(thread_id)
|
||||
messages = [e for e in all_events if e.get("category") == "message"]
|
||||
|
||||
if before_seq is not None:
|
||||
messages = [e for e in messages if e["seq"] < before_seq]
|
||||
return messages[-limit:]
|
||||
elif after_seq is not None:
|
||||
messages = [e for e in messages if e["seq"] > after_seq]
|
||||
return messages[:limit]
|
||||
else:
|
||||
return messages[-limit:]
|
||||
|
||||
async def list_events(self, thread_id, run_id, *, event_types=None, limit=500):
|
||||
events = self._read_run_events(thread_id, run_id)
|
||||
if event_types is not None:
|
||||
events = [e for e in events if e.get("event_type") in event_types]
|
||||
return events[:limit]
|
||||
|
||||
async def list_messages_by_run(self, thread_id, run_id, *, limit=50, before_seq=None, after_seq=None):
|
||||
events = self._read_run_events(thread_id, run_id)
|
||||
filtered = [e for e in events if e.get("category") == "message"]
|
||||
if before_seq is not None:
|
||||
filtered = [e for e in filtered if e.get("seq", 0) < before_seq]
|
||||
if after_seq is not None:
|
||||
filtered = [e for e in filtered if e.get("seq", 0) > after_seq]
|
||||
if after_seq is not None:
|
||||
return filtered[:limit]
|
||||
else:
|
||||
return filtered[-limit:] if len(filtered) > limit else filtered
|
||||
|
||||
async def count_messages(self, thread_id):
|
||||
all_events = self._read_thread_events(thread_id)
|
||||
return sum(1 for e in all_events if e.get("category") == "message")
|
||||
|
||||
async def delete_by_thread(self, thread_id):
|
||||
all_events = self._read_thread_events(thread_id)
|
||||
count = len(all_events)
|
||||
thread_dir = self._thread_dir(thread_id)
|
||||
if thread_dir.exists():
|
||||
for f in thread_dir.glob("*.jsonl"):
|
||||
f.unlink()
|
||||
self._seq_counters.pop(thread_id, None)
|
||||
return count
|
||||
|
||||
async def delete_by_run(self, thread_id, run_id):
|
||||
events = self._read_run_events(thread_id, run_id)
|
||||
count = len(events)
|
||||
path = self._run_file(thread_id, run_id)
|
||||
if path.exists():
|
||||
path.unlink()
|
||||
return count
|
||||
Reference in New Issue
Block a user