Files
deer-flow/backend/packages/harness/deerflow/skills/manager.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

161 lines
6.0 KiB
Python

"""Utilities for managing custom skills and their history."""
from __future__ import annotations
import json
import re
import tempfile
from datetime import UTC, datetime
from pathlib import Path
from typing import Any
from deerflow.config.app_config import AppConfig
from deerflow.skills.loader import load_skills
from deerflow.skills.validation import _validate_skill_frontmatter
SKILL_FILE_NAME = "SKILL.md"
HISTORY_FILE_NAME = "HISTORY.jsonl"
HISTORY_DIR_NAME = ".history"
ALLOWED_SUPPORT_SUBDIRS = {"references", "templates", "scripts", "assets"}
_SKILL_NAME_PATTERN = re.compile(r"^[a-z0-9]+(?:-[a-z0-9]+)*$")
def get_skills_root_dir(app_config: AppConfig) -> Path:
"""Return the configured skills root."""
return app_config.skills.get_skills_path()
def get_public_skills_dir(app_config: AppConfig) -> Path:
return get_skills_root_dir(app_config) / "public"
def get_custom_skills_dir(app_config: AppConfig) -> Path:
path = get_skills_root_dir(app_config) / "custom"
path.mkdir(parents=True, exist_ok=True)
return path
def validate_skill_name(name: str) -> str:
normalized = name.strip()
if not _SKILL_NAME_PATTERN.fullmatch(normalized):
raise ValueError("Skill name must be hyphen-case using lowercase letters, digits, and hyphens only.")
if len(normalized) > 64:
raise ValueError("Skill name must be 64 characters or fewer.")
return normalized
def get_custom_skill_dir(name: str, app_config: AppConfig) -> Path:
return get_custom_skills_dir(app_config) / validate_skill_name(name)
def get_custom_skill_file(name: str, app_config: AppConfig) -> Path:
return get_custom_skill_dir(name, app_config) / SKILL_FILE_NAME
def get_custom_skill_history_dir(app_config: AppConfig) -> Path:
path = get_custom_skills_dir(app_config) / HISTORY_DIR_NAME
path.mkdir(parents=True, exist_ok=True)
return path
def get_skill_history_file(name: str, app_config: AppConfig) -> Path:
return get_custom_skill_history_dir(app_config) / f"{validate_skill_name(name)}.jsonl"
def get_public_skill_dir(name: str, app_config: AppConfig) -> Path:
return get_public_skills_dir(app_config) / validate_skill_name(name)
def custom_skill_exists(name: str, app_config: AppConfig) -> bool:
return get_custom_skill_file(name, app_config).exists()
def public_skill_exists(name: str, app_config: AppConfig) -> bool:
return (get_public_skill_dir(name, app_config) / SKILL_FILE_NAME).exists()
def ensure_custom_skill_is_editable(name: str, app_config: AppConfig) -> None:
if custom_skill_exists(name, app_config):
return
if public_skill_exists(name, app_config):
raise ValueError(f"'{name}' is a built-in skill. To customise it, create a new skill with the same name under skills/custom/.")
raise FileNotFoundError(f"Custom skill '{name}' not found.")
def ensure_safe_support_path(name: str, relative_path: str, app_config: AppConfig) -> Path:
skill_dir = get_custom_skill_dir(name, app_config).resolve()
if not relative_path or relative_path.endswith("/"):
raise ValueError("Supporting file path must include a filename.")
relative = Path(relative_path)
if relative.is_absolute():
raise ValueError("Supporting file path must be relative.")
if any(part in {"..", ""} for part in relative.parts):
raise ValueError("Supporting file path must not contain parent-directory traversal.")
top_level = relative.parts[0] if relative.parts else ""
if top_level not in ALLOWED_SUPPORT_SUBDIRS:
raise ValueError(f"Supporting files must live under one of: {', '.join(sorted(ALLOWED_SUPPORT_SUBDIRS))}.")
target = (skill_dir / relative).resolve()
allowed_root = (skill_dir / top_level).resolve()
try:
target.relative_to(allowed_root)
except ValueError as exc:
raise ValueError("Supporting file path must stay within the selected support directory.") from exc
return target
def validate_skill_markdown_content(name: str, content: str) -> None:
with tempfile.TemporaryDirectory() as tmp_dir:
temp_skill_dir = Path(tmp_dir) / validate_skill_name(name)
temp_skill_dir.mkdir(parents=True, exist_ok=True)
(temp_skill_dir / SKILL_FILE_NAME).write_text(content, encoding="utf-8")
is_valid, message, parsed_name = _validate_skill_frontmatter(temp_skill_dir)
if not is_valid:
raise ValueError(message)
if parsed_name != name:
raise ValueError(f"Frontmatter name '{parsed_name}' must match requested skill name '{name}'.")
def atomic_write(path: Path, content: str) -> None:
path.parent.mkdir(parents=True, exist_ok=True)
with tempfile.NamedTemporaryFile("w", encoding="utf-8", delete=False, dir=str(path.parent)) as tmp_file:
tmp_file.write(content)
tmp_path = Path(tmp_file.name)
tmp_path.replace(path)
def append_history(name: str, record: dict[str, Any], app_config: AppConfig) -> None:
history_path = get_skill_history_file(name, app_config)
history_path.parent.mkdir(parents=True, exist_ok=True)
payload = {
"ts": datetime.now(UTC).isoformat(),
**record,
}
with history_path.open("a", encoding="utf-8") as f:
f.write(json.dumps(payload, ensure_ascii=False))
f.write("\n")
def read_history(name: str, app_config: AppConfig) -> list[dict[str, Any]]:
history_path = get_skill_history_file(name, app_config)
if not history_path.exists():
return []
records: list[dict[str, Any]] = []
for line in history_path.read_text(encoding="utf-8").splitlines():
if not line.strip():
continue
records.append(json.loads(line))
return records
def list_custom_skills(app_config: AppConfig) -> list:
return [skill for skill in load_skills(app_config, enabled_only=False) if skill.category == "custom"]
def read_custom_skill_content(name: str, app_config: AppConfig) -> str:
skill_file = get_custom_skill_file(name, app_config)
if not skill_file.exists():
raise FileNotFoundError(f"Custom skill '{name}' not found.")
return skill_file.read_text(encoding="utf-8")