mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-21 05:14:45 +08:00
* refactor: extract shared skill installer and upload manager to harness Move duplicated business logic from Gateway routers and Client into shared harness modules, eliminating code duplication. New shared modules: - deerflow.skills.installer: 6 functions (zip security, extraction, install) - deerflow.uploads.manager: 7 functions (normalize, deduplicate, validate, list, delete, get_uploads_dir, ensure_uploads_dir) Key improvements: - SkillAlreadyExistsError replaces stringly-typed 409 status routing - normalize_filename rejects backslash-containing filenames - Read paths (list/delete) no longer mkdir via get_uploads_dir - Write paths use ensure_uploads_dir for explicit directory creation - list_files_in_dir does stat inside scandir context (no re-stat) - install_skill_from_archive uses single is_file() check (one syscall) - Fix agent config key not reset on update_mcp_config/update_skill Tests: 42 new (22 installer + 20 upload manager) + client hardening * refactor: centralize upload URL construction and clean up installer - Extract upload_virtual_path(), upload_artifact_url(), enrich_file_listing() into shared manager.py, eliminating 6 duplicated URL constructions across Gateway router and Client - Derive all upload URLs from VIRTUAL_PATH_PREFIX constant instead of hardcoded "mnt/user-data/uploads" strings - Eliminate TOCTOU pre-checks and double file read in installer — single ZipFile() open with exception handling replaces is_file() + is_zipfile() + ZipFile() sequence - Add missing re-exports: ensure_uploads_dir in uploads/__init__.py, SkillAlreadyExistsError in skills/__init__.py - Remove redundant .lower() on already-lowercase CONVERTIBLE_EXTENSIONS - Hoist sandbox_uploads_dir(thread_id) before loop in uploads router * fix: add input validation for thread_id and filename length - Reject thread_id containing unsafe filesystem characters (only allow alphanumeric, hyphens, underscores, dots) — prevents 500 on inputs like <script> or shell metacharacters - Reject filenames longer than 255 bytes (OS limit) in normalize_filename - Gateway upload router maps ValueError to 400 for invalid thread_id * fix: address PR review — symlink safety, input validation coverage, error ordering - list_files_in_dir: use follow_symlinks=False to prevent symlink metadata leakage; check is_dir() instead of exists() for non-directory paths - install_skill_from_archive: restore is_file() pre-check before extension validation so error messages match the documented exception contract - validate_thread_id: move from ensure_uploads_dir to get_uploads_dir so all entry points (upload/list/delete) are protected - delete_uploaded_file: catch ValueError from thread_id validation (was 500) - requires_llm marker: also skip when OPENAI_API_KEY is unset - e2e fixture: update TitleMiddleware exclusion comment (kept filtering — middleware triggers extra LLM calls that add non-determinism to tests) * chore: revert uv.lock to main — no dependency changes in this PR * fix: use monkeypatch for global config in e2e fixture to prevent test pollution The e2e_env fixture was calling set_title_config() and set_summarization_config() directly, which mutated global singletons without automatic cleanup. When pytest ran test_client_e2e.py before test_title_middleware_core_logic.py, the leaked enabled=False caused 5 title tests to fail in CI. Switched to monkeypatch.setattr on the module-level private variables so pytest restores the originals after each test. * fix: address code review — URL encoding, API consistency, test isolation - upload_artifact_url: percent-encode filename to handle spaces/#/? - deduplicate_filename: mutate seen set in place (caller no longer needs manual .add() — less error-prone API) - list_files_in_dir: document that size is int, enrich stringifies - e2e fixture: monkeypatch _app_config instead of set_app_config() to prevent global singleton pollution (same pattern as title/summarization fix) - _make_e2e_config: read LLM connection details from env vars so external contributors can override defaults - Update tests to match new deduplicate_filename contract * docs: rewrite RFC in English and add alternatives/breaking changes sections * fix: address code review feedback on PR #1202 - Rename deduplicate_filename to claim_unique_filename to make the in-place set mutation explicit in the function name - Replace PermissionError with PathTraversalError(ValueError) for path traversal detection — malformed input is 400, not 403 * fix: set _app_config_is_custom in e2e test fixture to prevent config.yaml lookup in CI --------- Co-authored-by: greatmengqi <chenmengqi.0376@bytedance.com> Co-authored-by: Willem Jiang <willem.jiang@gmail.com> Co-authored-by: DanielWalnut <45447813+hetaoBackend@users.noreply.github.com>
174 lines
6.6 KiB
Python
174 lines
6.6 KiB
Python
import json
|
|
import logging
|
|
from pathlib import Path
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
from pydantic import BaseModel, Field
|
|
|
|
from app.gateway.path_utils import resolve_thread_virtual_path
|
|
from deerflow.config.extensions_config import ExtensionsConfig, SkillStateConfig, get_extensions_config, reload_extensions_config
|
|
from deerflow.skills import Skill, load_skills
|
|
from deerflow.skills.installer import SkillAlreadyExistsError, install_skill_from_archive
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
router = APIRouter(prefix="/api", tags=["skills"])
|
|
|
|
|
|
class SkillResponse(BaseModel):
|
|
"""Response model for skill information."""
|
|
|
|
name: str = Field(..., description="Name of the skill")
|
|
description: str = Field(..., description="Description of what the skill does")
|
|
license: str | None = Field(None, description="License information")
|
|
category: str = Field(..., description="Category of the skill (public or custom)")
|
|
enabled: bool = Field(default=True, description="Whether this skill is enabled")
|
|
|
|
|
|
class SkillsListResponse(BaseModel):
|
|
"""Response model for listing all skills."""
|
|
|
|
skills: list[SkillResponse]
|
|
|
|
|
|
class SkillUpdateRequest(BaseModel):
|
|
"""Request model for updating a skill."""
|
|
|
|
enabled: bool = Field(..., description="Whether to enable or disable the skill")
|
|
|
|
|
|
class SkillInstallRequest(BaseModel):
|
|
"""Request model for installing a skill from a .skill file."""
|
|
|
|
thread_id: str = Field(..., description="The thread ID where the .skill file is located")
|
|
path: str = Field(..., description="Virtual path to the .skill file (e.g., mnt/user-data/outputs/my-skill.skill)")
|
|
|
|
|
|
class SkillInstallResponse(BaseModel):
|
|
"""Response model for skill installation."""
|
|
|
|
success: bool = Field(..., description="Whether the installation was successful")
|
|
skill_name: str = Field(..., description="Name of the installed skill")
|
|
message: str = Field(..., description="Installation result message")
|
|
|
|
|
|
def _skill_to_response(skill: Skill) -> SkillResponse:
|
|
"""Convert a Skill object to a SkillResponse."""
|
|
return SkillResponse(
|
|
name=skill.name,
|
|
description=skill.description,
|
|
license=skill.license,
|
|
category=skill.category,
|
|
enabled=skill.enabled,
|
|
)
|
|
|
|
|
|
@router.get(
|
|
"/skills",
|
|
response_model=SkillsListResponse,
|
|
summary="List All Skills",
|
|
description="Retrieve a list of all available skills from both public and custom directories.",
|
|
)
|
|
async def list_skills() -> SkillsListResponse:
|
|
try:
|
|
skills = load_skills(enabled_only=False)
|
|
return SkillsListResponse(skills=[_skill_to_response(skill) for skill in skills])
|
|
except Exception as e:
|
|
logger.error(f"Failed to load skills: {e}", exc_info=True)
|
|
raise HTTPException(status_code=500, detail=f"Failed to load skills: {str(e)}")
|
|
|
|
|
|
@router.get(
|
|
"/skills/{skill_name}",
|
|
response_model=SkillResponse,
|
|
summary="Get Skill Details",
|
|
description="Retrieve detailed information about a specific skill by its name.",
|
|
)
|
|
async def get_skill(skill_name: str) -> SkillResponse:
|
|
try:
|
|
skills = load_skills(enabled_only=False)
|
|
skill = next((s for s in skills if s.name == skill_name), None)
|
|
|
|
if skill is None:
|
|
raise HTTPException(status_code=404, detail=f"Skill '{skill_name}' not found")
|
|
|
|
return _skill_to_response(skill)
|
|
except HTTPException:
|
|
raise
|
|
except Exception as e:
|
|
logger.error(f"Failed to get skill {skill_name}: {e}", exc_info=True)
|
|
raise HTTPException(status_code=500, detail=f"Failed to get skill: {str(e)}")
|
|
|
|
|
|
@router.put(
|
|
"/skills/{skill_name}",
|
|
response_model=SkillResponse,
|
|
summary="Update Skill",
|
|
description="Update a skill's enabled status by modifying the extensions_config.json file.",
|
|
)
|
|
async def update_skill(skill_name: str, request: SkillUpdateRequest) -> SkillResponse:
|
|
try:
|
|
skills = load_skills(enabled_only=False)
|
|
skill = next((s for s in skills if s.name == skill_name), None)
|
|
|
|
if skill is None:
|
|
raise HTTPException(status_code=404, detail=f"Skill '{skill_name}' not found")
|
|
|
|
config_path = ExtensionsConfig.resolve_config_path()
|
|
if config_path is None:
|
|
config_path = Path.cwd().parent / "extensions_config.json"
|
|
logger.info(f"No existing extensions config found. Creating new config at: {config_path}")
|
|
|
|
extensions_config = get_extensions_config()
|
|
extensions_config.skills[skill_name] = SkillStateConfig(enabled=request.enabled)
|
|
|
|
config_data = {
|
|
"mcpServers": {name: server.model_dump() for name, server in extensions_config.mcp_servers.items()},
|
|
"skills": {name: {"enabled": skill_config.enabled} for name, skill_config in extensions_config.skills.items()},
|
|
}
|
|
|
|
with open(config_path, "w", encoding="utf-8") as f:
|
|
json.dump(config_data, f, indent=2)
|
|
|
|
logger.info(f"Skills configuration updated and saved to: {config_path}")
|
|
reload_extensions_config()
|
|
|
|
skills = load_skills(enabled_only=False)
|
|
updated_skill = next((s for s in skills if s.name == skill_name), None)
|
|
|
|
if updated_skill is None:
|
|
raise HTTPException(status_code=500, detail=f"Failed to reload skill '{skill_name}' after update")
|
|
|
|
logger.info(f"Skill '{skill_name}' enabled status updated to {request.enabled}")
|
|
return _skill_to_response(updated_skill)
|
|
|
|
except HTTPException:
|
|
raise
|
|
except Exception as e:
|
|
logger.error(f"Failed to update skill {skill_name}: {e}", exc_info=True)
|
|
raise HTTPException(status_code=500, detail=f"Failed to update skill: {str(e)}")
|
|
|
|
|
|
@router.post(
|
|
"/skills/install",
|
|
response_model=SkillInstallResponse,
|
|
summary="Install Skill",
|
|
description="Install a skill from a .skill file (ZIP archive) located in the thread's user-data directory.",
|
|
)
|
|
async def install_skill(request: SkillInstallRequest) -> SkillInstallResponse:
|
|
try:
|
|
skill_file_path = resolve_thread_virtual_path(request.thread_id, request.path)
|
|
result = install_skill_from_archive(skill_file_path)
|
|
return SkillInstallResponse(**result)
|
|
except FileNotFoundError as e:
|
|
raise HTTPException(status_code=404, detail=str(e))
|
|
except SkillAlreadyExistsError as e:
|
|
raise HTTPException(status_code=409, detail=str(e))
|
|
except ValueError as e:
|
|
raise HTTPException(status_code=400, detail=str(e))
|
|
except HTTPException:
|
|
raise
|
|
except Exception as e:
|
|
logger.error(f"Failed to install skill: {e}", exc_info=True)
|
|
raise HTTPException(status_code=500, detail=f"Failed to install skill: {str(e)}")
|