furyhawk/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-06-10 09:25:57 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(agents): offload blocking filesystem IO in the custom-agent router off the event loop (#3457)

Browse Source 
* fix(agents): offload blocking filesystem IO in delete_agent off the event loop

delete_agent is an async route handler but resolved the agent directory (Paths.base_dir -> Path.resolve), probed it (Path.exists), and removed it (shutil.rmtree) directly on the event loop, blocking it for the duration of every delete. Surfaced by 'make detect-blocking-io'.

Move the resolve/exists/rmtree sequence into a sync helper run via asyncio.to_thread, mapping its outcome back to the existing 404/409/500 responses (behavior unchanged). Adds a tests/blocking_io/ regression anchor under the strict Blockbuster gate, mirroring test_skills_load.py (#1917).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* fix(agents): offload blocking filesystem IO in create_agent_endpoint too

Like delete_agent, the async create_agent_endpoint resolved and created the agent directory and wrote config.yaml + SOUL.md (with rmtree cleanup on failure) directly on the event loop. Move the whole create-or-409 sequence into a sync helper run via asyncio.to_thread; behavior is unchanged (201 / 409 / 500). Extends the blocking_io regression anchor to cover create as well as delete and renames it to test_agents_router.py.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* Apply suggestions from code review

Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: ly-wang19 <ly-wang19@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Willem Jiang <willem.jiang@gmail.com>
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
This commit is contained in:
ly-wang19
2026-06-09 22:24:53 +08:00
committed by GitHub
parent 5b81588b87
commit b62c5a7b5b
2 changed files with 134 additions and 45 deletions
Download Patch File Download Diff File Expand all files Collapse all files
backend/app/gateway/routers/agents.py
+70 -45
View File
@@ -1,5 +1,6 @@
"""CRUD API for custom agents."""
import asyncio
import logging
import re
import shutil
@@ -213,48 +214,61 @@ async def create_agent_endpoint(request: AgentCreateRequest) -> AgentResponse:
user_id = get_effective_user_id()
paths = get_paths()
agent_dir = paths.user_agent_dir(user_id, normalized_name)
legacy_dir = paths.agent_dir(normalized_name)
def _create_agent() -> AgentResponse | None:
# Worker thread: base-dir resolution, existence checks, directory/file
# creation, read-back, and failure cleanup are all blocking filesystem
# IO that must stay off the event loop.
agent_dir = paths.user_agent_dir(user_id, normalized_name)
legacy_dir = paths.agent_dir(normalized_name)
if agent_dir.exists() or legacy_dir.exists():
raise HTTPException(status_code=409, detail=f"Agent '{normalized_name}' already exists")
if legacy_dir.exists():
return None # signals 409 to the caller
try:
try:
agent_dir.mkdir(parents=True, exist_ok=False)
except FileExistsError:
return None # signals 409 to the caller
# Write config.yaml
config_data: dict = {"name": normalized_name}
if request.description:
config_data["description"] = request.description
if request.model is not None:
config_data["model"] = request.model
if request.tool_groups is not None:
config_data["tool_groups"] = request.tool_groups
if request.skills is not None:
config_data["skills"] = request.skills
config_file = agent_dir / "config.yaml"
with open(config_file, "w", encoding="utf-8") as f:
yaml.dump(config_data, f, default_flow_style=False, allow_unicode=True)
# Write SOUL.md
soul_file = agent_dir / "SOUL.md"
soul_file.write_text(request.soul, encoding="utf-8")
logger.info(f"Created agent '{normalized_name}' at {agent_dir}")
agent_cfg = load_agent_config(normalized_name, user_id=user_id)
return _agent_config_to_response(agent_cfg, include_soul=True, user_id=user_id)
except Exception:
# Clean up partial state on failure before surfacing the error.
if agent_dir.exists():
shutil.rmtree(agent_dir)
raise
try:
agent_dir.mkdir(parents=True, exist_ok=True)
# Write config.yaml
config_data: dict = {"name": normalized_name}
if request.description:
config_data["description"] = request.description
if request.model is not None:
config_data["model"] = request.model
if request.tool_groups is not None:
config_data["tool_groups"] = request.tool_groups
if request.skills is not None:
config_data["skills"] = request.skills
config_file = agent_dir / "config.yaml"
with open(config_file, "w", encoding="utf-8") as f:
yaml.dump(config_data, f, default_flow_style=False, allow_unicode=True)
# Write SOUL.md
soul_file = agent_dir / "SOUL.md"
soul_file.write_text(request.soul, encoding="utf-8")
logger.info(f"Created agent '{normalized_name}' at {agent_dir}")
agent_cfg = load_agent_config(normalized_name, user_id=user_id)
return _agent_config_to_response(agent_cfg, include_soul=True, user_id=user_id)
except HTTPException:
raise
response = await asyncio.to_thread(_create_agent)
except Exception as e:
# Clean up on failure
if agent_dir.exists():
shutil.rmtree(agent_dir)
logger.error(f"Failed to create agent '{request.name}': {e}", exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to create agent: {str(e)}")
if response is None:
raise HTTPException(status_code=409, detail=f"Agent '{normalized_name}' already exists")
return response
@router.put(
"/agents/{name}",
@@ -428,19 +442,30 @@ async def delete_agent(name: str) -> None:
name = _normalize_agent_name(name)
user_id = get_effective_user_id()
paths = get_paths()
agent_dir = paths.user_agent_dir(user_id, name)
if not agent_dir.exists():
if paths.agent_dir(name).exists():
raise HTTPException(
status_code=409,
detail=(f"Agent '{name}' only exists in the legacy shared layout and is not scoped to a user. Run scripts/migrate_user_isolation.py to move legacy agents into the per-user layout before deleting."),
)
raise HTTPException(status_code=404, detail=f"Agent '{name}' not found")
def _remove_agent_dir() -> tuple[str, str]:
# Runs in a worker thread: resolving the base dir, probing the directory
# (`exists`), and removing it (`rmtree`) are all blocking filesystem IO
# that must stay off the event loop.
agent_dir = paths.user_agent_dir(user_id, name)
if not agent_dir.exists():
outcome = "legacy" if paths.agent_dir(name).exists() else "missing"
return outcome, str(agent_dir)
shutil.rmtree(agent_dir)
return "deleted", str(agent_dir)
try:
shutil.rmtree(agent_dir)
logger.info(f"Deleted agent '{name}' from {agent_dir}")
outcome, agent_dir = await asyncio.to_thread(_remove_agent_dir)
except Exception as e:
logger.error(f"Failed to delete agent '{name}': {e}", exc_info=True)
raise HTTPException(status_code=500, detail=f"Failed to delete agent: {str(e)}")
if outcome == "legacy":
raise HTTPException(
status_code=409,
detail=(f"Agent '{name}' only exists in the legacy shared layout and is not scoped to a user. Run scripts/migrate_user_isolation.py to move legacy agents into the per-user layout before deleting."),
)
if outcome == "missing":
raise HTTPException(status_code=404, detail=f"Agent '{name}' not found")
logger.info(f"Deleted agent '{name}' from {agent_dir}")