mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-10-26 21:26:39 +00:00
f623e64e07
* fix(acp): resolve a bare agent command through PATH before spawning `invoke_acp_agent` handed `acp_agents.<name>.command` straight to the ACP SDK, which spawns it with `asyncio.create_subprocess_exec`. That API applies no `PATHEXT` lookup on Windows, so a bare npm launcher (`npx`, `mcode`) raised `FileNotFoundError` although its `.cmd` shim was on `PATH`. The documented `command: npx` and `command: mcode` shapes could not start, and the tool reported "was not found on PATH" for an installed launcher. Resolve the configured command with `shutil.which` before spawning — the way the MCP Python SDK normalizes stdio server commands — and keep the configured value when nothing matches, so the existing install guidance still fires. Fixes #6597 * fix(acp): resolve the ACP agent command off the event loop `_resolve_agent_command` calls `shutil.which`, which stats the filesystem. Calling it inline in the async `_invoke` tripped the strict BlockBuster gate (`BlockingError: Blocking call to os.access`) for every command that resolves, and would block the Gateway event loop in production. Offload the lookup with `asyncio.to_thread`, matching the neighbouring `_get_work_dir`, `_build_acp_mcp_servers`, and `_format_invocation_error` calls. The blocking-io anchor configured `command="test-agent"`, a name that resolves nowhere, so `shutil.which` short-circuited before `os.access` and the gate never covered the new call. Point it at `sys.executable` so the lookup is really exercised, and cover the unresolvable-guidance branch end-to-end with a new test. Refs #6597 * fix(acp): keep the configured command in ACP remediation text Review follow-ups on the PATH resolution: - Only bare names are resolved. A configured path is interpreted by the spawn against the per-thread ACP workspace, so resolving it against the Gateway's working directory could pick a different file or hand the spawn a path that then fails. - `_format_invocation_error` receives `agent_config.command` again. A command can resolve on PATH and still fail to launch (a broken shebang, for example), and reporting the resolved path made "was not found on PATH" false and dropped the `codex-acp` hint. - The blocking-io anchor uses a bare name backed by a shim on a controlled PATH instead of `sys.executable`, which the bare-name scoping no longer resolves. Tests: the pass-through assertion in `test_invoke_acp_agent_uses_fixed_acp_workspace` pins PATH, and new coverage covers the bare-name scoping and the spawn-failure message. Refs #6597 * docs(acp): correct the path-resolution rationale A configured path is resolved by the spawn in its own process, so the pass-through reason must not claim it is resolved against the ACP workspace: that only holds on POSIX, while Windows resolves a relative executable against the calling process's directory. State the platform-neutral reason instead. Refs #6597 * fix(acp): resolve the launcher against the agent's own PATH The ACP SDK merges acp_agents.<name>.env over its inherited environment at spawn time, so a configured PATH, not the Gateway's, decides which launcher the agent would find. Resolve a bare command against that effective PATH, and use the Gateway's only when the agent does not override it. Return a successful lookup as an absolute path: a relative PATH entry makes shutil.which yield a result relative to the Gateway's cwd, while the spawn runs with cwd set to the ACP workspace, where that path resolves elsewhere or not at all. Regressions: a real-subprocess test with same-named launchers in the Gateway and agent PATHs (asserting which one ran), and a real-subprocess test whose PATH holds a relative directory while the ACP workspace is elsewhere. Both are red on the pre-fix code.
83 lines
3.0 KiB
Python
83 lines
3.0 KiB
Python
"""Regression test for ACP invocation setup on the event loop.
|
|
|
|
The configured command is a bare name backed by a launcher shim on a controlled
|
|
``PATH``, so the gate really runs the ``shutil.which`` lookup (``os.access``)
|
|
instead of short-circuiting on a name that resolves nowhere.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import asyncio
|
|
import contextlib
|
|
import sys
|
|
from types import SimpleNamespace
|
|
from typing import Any
|
|
|
|
import acp
|
|
import pytest
|
|
|
|
from deerflow.config.acp_config import ACPAgentConfig
|
|
from deerflow.tools.builtins import invoke_acp_agent_tool as acp_tool
|
|
|
|
pytestmark = pytest.mark.asyncio
|
|
|
|
|
|
async def test_invoke_acp_agent_setup_does_not_block_event_loop(monkeypatch, tmp_path) -> None:
|
|
from deerflow.config import paths as paths_module
|
|
|
|
configured_paths = SimpleNamespace(
|
|
base_dir=tmp_path,
|
|
acp_workspace_dir=lambda thread_id, user_id=None: tmp_path / "threads" / thread_id / "acp-workspace",
|
|
)
|
|
monkeypatch.setattr(paths_module, "get_paths", lambda: configured_paths)
|
|
config_path = tmp_path / "extensions_config.json"
|
|
await asyncio.to_thread(
|
|
config_path.write_text,
|
|
'{"mcpServers": {"test-server": {"enabled": true, "type": "http", "url": "https://example.test/mcp"}}, "skills": {}}',
|
|
encoding="utf-8",
|
|
)
|
|
monkeypatch.setenv("DEER_FLOW_EXTENSIONS_CONFIG_PATH", str(config_path))
|
|
|
|
shim_dir = tmp_path / "bin"
|
|
shim_dir.mkdir()
|
|
shim = shim_dir / ("test-agent.cmd" if sys.platform == "win32" else "test-agent")
|
|
shim.write_text("@echo off\n" if sys.platform == "win32" else "#!/bin/sh\n", encoding="utf-8")
|
|
if sys.platform != "win32":
|
|
shim.chmod(0o755)
|
|
monkeypatch.setenv("PATH", str(shim_dir))
|
|
|
|
captured: dict[str, Any] = {}
|
|
|
|
class _Connection:
|
|
async def initialize(self, **kwargs: Any) -> None:
|
|
captured["initialize"] = kwargs
|
|
|
|
async def new_session(self, **kwargs: Any) -> SimpleNamespace:
|
|
captured["new_session"] = kwargs
|
|
return SimpleNamespace(session_id="session-1")
|
|
|
|
async def prompt(self, **kwargs: Any) -> None:
|
|
captured["prompt"] = kwargs
|
|
|
|
@contextlib.asynccontextmanager
|
|
async def fake_spawn_agent_process(client, command, *args, env=None, cwd=None):
|
|
captured["cwd"] = cwd
|
|
yield _Connection(), SimpleNamespace()
|
|
|
|
monkeypatch.setattr(acp, "spawn_agent_process", fake_spawn_agent_process)
|
|
|
|
tool = acp_tool.build_invoke_acp_agent_tool(
|
|
{"test-agent": ACPAgentConfig(command="test-agent", description="Test agent")},
|
|
)
|
|
result = await tool.coroutine(
|
|
agent="test-agent",
|
|
prompt="run",
|
|
config={"configurable": {"thread_id": "thread-1"}},
|
|
)
|
|
|
|
expected_cwd = tmp_path / "threads" / "thread-1" / "acp-workspace"
|
|
assert result == "(no response)"
|
|
assert captured["cwd"] == str(expected_cwd)
|
|
assert captured["new_session"]["mcp_servers"] == [{"name": "test-server", "type": "http", "url": "https://example.test/mcp", "headers": []}]
|
|
assert expected_cwd.is_dir()
|