mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-03 06:12:14 +08:00
* refactor: extract shared utils to break harness→app cross-layer imports Move _validate_skill_frontmatter to src/skills/validation.py and CONVERTIBLE_EXTENSIONS + convert_file_to_markdown to src/utils/file_conversion.py. This eliminates the two reverse dependencies from client.py (harness layer) into gateway/routers/ (app layer), preparing for the harness/app package split. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor: split backend/src into harness (deerflow.*) and app (app.*) Physically split the monolithic backend/src/ package into two layers: - **Harness** (`packages/harness/deerflow/`): publishable agent framework package with import prefix `deerflow.*`. Contains agents, sandbox, tools, models, MCP, skills, config, and all core infrastructure. - **App** (`app/`): unpublished application code with import prefix `app.*`. Contains gateway (FastAPI REST API) and channels (IM integrations). Key changes: - Move 13 harness modules to packages/harness/deerflow/ via git mv - Move gateway + channels to app/ via git mv - Rename all imports: src.* → deerflow.* (harness) / app.* (app layer) - Set up uv workspace with deerflow-harness as workspace member - Update langgraph.json, config.example.yaml, all scripts, Docker files - Add build-system (hatchling) to harness pyproject.toml - Add PYTHONPATH=. to gateway startup commands for app.* resolution - Update ruff.toml with known-first-party for import sorting - Update all documentation to reflect new directory structure Boundary rule enforced: harness code never imports from app. All 429 tests pass. Lint clean. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * chore: add harness→app boundary check test and update docs Add test_harness_boundary.py that scans all Python files in packages/harness/deerflow/ and fails if any `from app.*` or `import app.*` statement is found. This enforces the architectural rule that the harness layer never depends on the app layer. Update CLAUDE.md to document the harness/app split architecture, import conventions, and the boundary enforcement test. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * feat: add config versioning with auto-upgrade on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated. This adds a config_version field and auto-upgrade mechanism so breaking changes (like src.* → deerflow.* renames) are applied automatically before services start. - Add config_version: 1 to config.example.yaml - Add startup version check warning in AppConfig.from_file() - Add scripts/config-upgrade.sh with migration registry for value replacements - Add `make config-upgrade` target - Auto-run config-upgrade in serve.sh and start-daemon.sh before starting services - Add config error hints in service failure messages Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix comments * fix: update src.* import in test_sandbox_tools_security to deerflow.* Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: handle empty config and search parent dirs for config.example.yaml Address Copilot review comments on PR #1131: - Guard against yaml.safe_load() returning None for empty config files - Search parent directories for config.example.yaml instead of only looking next to config.yaml, fixing detection in common setups Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix: correct skills root path depth and config_version type coercion - loader.py: fix get_skills_root_path() to use 5 parent levels (was 3) after harness split, file lives at packages/harness/deerflow/skills/ so parent×3 resolved to backend/packages/harness/ instead of backend/ - app_config.py: coerce config_version to int() before comparison in _check_config_version() to prevent TypeError when YAML stores value as string (e.g. config_version: "1") - tests: add regression tests for both fixes Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix: update test imports from src.* to deerflow.*/app.* after harness refactor Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * feat(harness): add tool-first ACP agent invocation (#37) * feat(harness): add tool-first ACP agent invocation * build(harness): make ACP dependency required * fix(harness): address ACP review feedback * feat(harness): decouple ACP agent workspace from thread data ACP agents (codex, claude-code) previously used per-thread workspace directories, causing path resolution complexity and coupling task execution to DeerFlow's internal thread data layout. This change: - Replace _resolve_cwd() with a fixed _get_work_dir() that always uses {base_dir}/acp-workspace/, eliminating virtual path translation and thread_id lookups - Introduce /mnt/acp-workspace virtual path for lead agent read-only access to ACP agent output files (same pattern as /mnt/skills) - Add security guards: read-only validation, path traversal prevention, command path allowlisting, and output masking for acp-workspace - Update system prompt and tool description to guide LLM: send self-contained tasks to ACP agents, copy results via /mnt/acp-workspace - Add 11 new security tests for ACP workspace path handling Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * refactor(prompt): inject ACP section only when ACP agents are configured The ACP agent guidance in the system prompt is now conditionally built by _build_acp_section(), which checks get_acp_agents() and returns an empty string when no ACP agents are configured. This avoids polluting the prompt with irrelevant instructions for users who don't use ACP. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix lint * fix(harness): address Copilot review comments on sandbox path handling and ACP tool - local_sandbox: fix path-segment boundary bug in _resolve_path (== or startswith +"/") and add lookahead in _resolve_paths_in_command regex to prevent /mnt/skills matching inside /mnt/skills-extra - local_sandbox_provider: replace print() with logger.warning(..., exc_info=True) - invoke_acp_agent_tool: guard getattr(option, "optionId") with None default + continue; move full prompt from INFO to DEBUG level (truncated to 200 chars) - sandbox/tools: fix _get_acp_workspace_host_path docstring to match implementation; remove misleading "read-only" language from validate_local_bash_command_paths Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(acp): thread-isolated workspaces, permission guardrail, and ContextVar registry P1.1 – ACP workspace thread isolation - Add `Paths.acp_workspace_dir(thread_id)` for per-thread paths - `_get_work_dir(thread_id)` in invoke_acp_agent_tool now uses `{base_dir}/threads/{thread_id}/acp-workspace/`; falls back to global workspace when thread_id is absent or invalid - `_invoke` extracts thread_id from `RunnableConfig` via `Annotated[RunnableConfig, InjectedToolArg]` - `sandbox/tools.py`: `_get_acp_workspace_host_path(thread_id)`, `_resolve_acp_workspace_path(path, thread_id)`, and all callers (`replace_virtual_paths_in_command`, `mask_local_paths_in_output`, `ls_tool`, `read_file_tool`) now resolve ACP paths per-thread P1.2 – ACP permission guardrail - New `auto_approve_permissions: bool = False` field in `ACPAgentConfig` - `_build_permission_response(options, *, auto_approve: bool)` now defaults to deny; only approves when `auto_approve=True` - Document field in `config.example.yaml` P2 – Deferred tool registry race condition - Replace module-level `_registry` global with `contextvars.ContextVar` - Each asyncio request context gets its own registry; worker threads inherit the context automatically via `loop.run_in_executor` - Expose `get_deferred_registry` / `set_deferred_registry` / `reset_deferred_registry` helpers Tests: 831 pass (57 for affected modules, 3 new tests) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(sandbox): mount /mnt/acp-workspace in docker sandbox container The AioSandboxProvider was not mounting the ACP workspace into the sandbox container, so /mnt/acp-workspace was inaccessible when the lead agent tried to read ACP results in docker mode. Changes: - `ensure_thread_dirs`: also create `acp-workspace/` (chmod 0o777) so the directory exists before the sandbox container starts — required for Docker volume mounts - `_get_thread_mounts`: add read-only `/mnt/acp-workspace` mount using the per-thread host path (`host_paths.acp_workspace_dir(thread_id)`) - Update stale CLAUDE.md description (was "fixed global workspace") Tests: `test_aio_sandbox_provider.py` (4 new tests) Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * fix(lint): remove unused imports in test_aio_sandbox_provider Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> * fix config --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
387 lines
13 KiB
Python
387 lines
13 KiB
Python
"""Tests for the built-in ACP invocation tool."""
|
|
|
|
import sys
|
|
from types import SimpleNamespace
|
|
|
|
import pytest
|
|
|
|
from deerflow.config.acp_config import ACPAgentConfig
|
|
from deerflow.config.extensions_config import ExtensionsConfig, McpServerConfig, set_extensions_config
|
|
from deerflow.tools.builtins.invoke_acp_agent_tool import (
|
|
_build_mcp_servers,
|
|
_build_permission_response,
|
|
_get_work_dir,
|
|
build_invoke_acp_agent_tool,
|
|
)
|
|
from deerflow.tools.tools import get_available_tools
|
|
|
|
|
|
def test_build_mcp_servers_filters_disabled_and_maps_transports():
|
|
set_extensions_config(ExtensionsConfig(mcp_servers={"stale": McpServerConfig(enabled=True, type="stdio", command="echo")}, skills={}))
|
|
fresh_config = ExtensionsConfig(
|
|
mcp_servers={
|
|
"stdio": McpServerConfig(enabled=True, type="stdio", command="npx", args=["srv"]),
|
|
"http": McpServerConfig(enabled=True, type="http", url="https://example.com/mcp"),
|
|
"disabled": McpServerConfig(enabled=False, type="stdio", command="echo"),
|
|
},
|
|
skills={},
|
|
)
|
|
monkeypatch = pytest.MonkeyPatch()
|
|
monkeypatch.setattr(
|
|
"deerflow.config.extensions_config.ExtensionsConfig.from_file",
|
|
classmethod(lambda cls: fresh_config),
|
|
)
|
|
|
|
try:
|
|
assert _build_mcp_servers() == {
|
|
"stdio": {"transport": "stdio", "command": "npx", "args": ["srv"]},
|
|
"http": {"transport": "http", "url": "https://example.com/mcp"},
|
|
}
|
|
finally:
|
|
monkeypatch.undo()
|
|
set_extensions_config(ExtensionsConfig(mcp_servers={}, skills={}))
|
|
|
|
|
|
def test_build_permission_response_prefers_allow_once():
|
|
response = _build_permission_response(
|
|
[
|
|
SimpleNamespace(kind="reject_once", optionId="deny"),
|
|
SimpleNamespace(kind="allow_always", optionId="always"),
|
|
SimpleNamespace(kind="allow_once", optionId="once"),
|
|
],
|
|
auto_approve=True,
|
|
)
|
|
|
|
assert response.outcome.outcome == "selected"
|
|
assert response.outcome.option_id == "once"
|
|
|
|
|
|
def test_build_permission_response_denies_when_no_allow_option():
|
|
response = _build_permission_response(
|
|
[
|
|
SimpleNamespace(kind="reject_once", optionId="deny"),
|
|
SimpleNamespace(kind="reject_always", optionId="deny-forever"),
|
|
],
|
|
auto_approve=True,
|
|
)
|
|
|
|
assert response.outcome.outcome == "cancelled"
|
|
|
|
|
|
def test_build_permission_response_denies_when_auto_approve_false():
|
|
"""P1.2: When auto_approve=False, permission is always denied regardless of options."""
|
|
response = _build_permission_response(
|
|
[
|
|
SimpleNamespace(kind="allow_once", optionId="once"),
|
|
SimpleNamespace(kind="allow_always", optionId="always"),
|
|
],
|
|
auto_approve=False,
|
|
)
|
|
|
|
assert response.outcome.outcome == "cancelled"
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_build_invoke_tool_description_and_unknown_agent_error():
|
|
tool = build_invoke_acp_agent_tool(
|
|
{
|
|
"codex": ACPAgentConfig(command="codex-acp", description="Codex CLI"),
|
|
"claude_code": ACPAgentConfig(command="claude-code-acp", description="Claude Code"),
|
|
}
|
|
)
|
|
|
|
assert "Available agents:" in tool.description
|
|
assert "- codex: Codex CLI" in tool.description
|
|
assert "- claude_code: Claude Code" in tool.description
|
|
assert "Do NOT include /mnt/user-data paths" in tool.description
|
|
assert "/mnt/acp-workspace/" in tool.description
|
|
|
|
result = await tool.coroutine(agent="missing", prompt="do work")
|
|
assert result == "Error: Unknown agent 'missing'. Available: codex, claude_code"
|
|
|
|
|
|
def test_get_work_dir_uses_base_dir_when_no_thread_id(monkeypatch, tmp_path):
|
|
"""_get_work_dir(None) uses {base_dir}/acp-workspace/ (global fallback)."""
|
|
from deerflow.config import paths as paths_module
|
|
|
|
monkeypatch.setattr(paths_module, "get_paths", lambda: paths_module.Paths(base_dir=tmp_path))
|
|
result = _get_work_dir(None)
|
|
expected = tmp_path / "acp-workspace"
|
|
assert result == str(expected)
|
|
assert expected.exists()
|
|
|
|
|
|
def test_get_work_dir_uses_per_thread_path_when_thread_id_given(monkeypatch, tmp_path):
|
|
"""P1.1: _get_work_dir(thread_id) uses {base_dir}/threads/{thread_id}/acp-workspace/."""
|
|
from deerflow.config import paths as paths_module
|
|
|
|
monkeypatch.setattr(paths_module, "get_paths", lambda: paths_module.Paths(base_dir=tmp_path))
|
|
result = _get_work_dir("thread-abc-123")
|
|
expected = tmp_path / "threads" / "thread-abc-123" / "acp-workspace"
|
|
assert result == str(expected)
|
|
assert expected.exists()
|
|
|
|
|
|
def test_get_work_dir_falls_back_to_global_for_invalid_thread_id(monkeypatch, tmp_path):
|
|
"""P1.1: Invalid thread_id (e.g. path traversal chars) falls back to global workspace."""
|
|
from deerflow.config import paths as paths_module
|
|
|
|
monkeypatch.setattr(paths_module, "get_paths", lambda: paths_module.Paths(base_dir=tmp_path))
|
|
result = _get_work_dir("../../evil")
|
|
expected = tmp_path / "acp-workspace"
|
|
assert result == str(expected)
|
|
assert expected.exists()
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_invoke_acp_agent_uses_fixed_acp_workspace(monkeypatch, tmp_path):
|
|
"""ACP agent uses {base_dir}/acp-workspace/ when no thread_id is available (no config)."""
|
|
from deerflow.config import paths as paths_module
|
|
|
|
monkeypatch.setattr(paths_module, "get_paths", lambda: paths_module.Paths(base_dir=tmp_path))
|
|
|
|
monkeypatch.setattr(
|
|
"deerflow.config.extensions_config.ExtensionsConfig.from_file",
|
|
classmethod(
|
|
lambda cls: ExtensionsConfig(
|
|
mcp_servers={"github": McpServerConfig(enabled=True, type="stdio", command="npx", args=["github-mcp"])},
|
|
skills={},
|
|
)
|
|
),
|
|
)
|
|
|
|
captured: dict[str, object] = {}
|
|
|
|
class DummyClient:
|
|
def __init__(self) -> None:
|
|
self._chunks: list[str] = []
|
|
|
|
@property
|
|
def collected_text(self) -> str:
|
|
return "".join(self._chunks)
|
|
|
|
async def session_update(self, session_id: str, update, **kwargs) -> None:
|
|
if hasattr(update, "content") and hasattr(update.content, "text"):
|
|
self._chunks.append(update.content.text)
|
|
|
|
async def request_permission(self, options, session_id: str, tool_call, **kwargs):
|
|
raise AssertionError("request_permission should not be called in this test")
|
|
|
|
class DummyConn:
|
|
async def initialize(self, **kwargs):
|
|
captured["initialize"] = kwargs
|
|
|
|
async def new_session(self, **kwargs):
|
|
captured["new_session"] = kwargs
|
|
return SimpleNamespace(session_id="session-1")
|
|
|
|
async def prompt(self, **kwargs):
|
|
captured["prompt"] = kwargs
|
|
client = captured["client"]
|
|
await client.session_update(
|
|
"session-1",
|
|
SimpleNamespace(content=text_content_block("ACP result")),
|
|
)
|
|
|
|
class DummyProcessContext:
|
|
def __init__(self, client, cmd, *args, cwd):
|
|
captured["client"] = client
|
|
captured["spawn"] = {"cmd": cmd, "args": list(args), "cwd": cwd}
|
|
|
|
async def __aenter__(self):
|
|
return DummyConn(), object()
|
|
|
|
async def __aexit__(self, exc_type, exc, tb):
|
|
return False
|
|
|
|
class DummyRequestError(Exception):
|
|
@staticmethod
|
|
def method_not_found(method: str):
|
|
return DummyRequestError(method)
|
|
|
|
monkeypatch.setitem(
|
|
sys.modules,
|
|
"acp",
|
|
SimpleNamespace(
|
|
PROTOCOL_VERSION="2026-03-24",
|
|
Client=DummyClient,
|
|
RequestError=DummyRequestError,
|
|
spawn_agent_process=lambda client, cmd, *args, cwd: DummyProcessContext(client, cmd, *args, cwd=cwd),
|
|
text_block=lambda text: {"type": "text", "text": text},
|
|
),
|
|
)
|
|
monkeypatch.setitem(
|
|
sys.modules,
|
|
"acp.schema",
|
|
SimpleNamespace(
|
|
ClientCapabilities=lambda: {"supports": []},
|
|
Implementation=lambda **kwargs: kwargs,
|
|
TextContentBlock=type(
|
|
"TextContentBlock",
|
|
(),
|
|
{"__init__": lambda self, text: setattr(self, "text", text)},
|
|
),
|
|
),
|
|
)
|
|
text_content_block = sys.modules["acp.schema"].TextContentBlock
|
|
|
|
expected_cwd = str(tmp_path / "acp-workspace")
|
|
|
|
tool = build_invoke_acp_agent_tool(
|
|
{
|
|
"codex": ACPAgentConfig(
|
|
command="codex-acp",
|
|
args=["--json"],
|
|
description="Codex CLI",
|
|
model="gpt-5-codex",
|
|
)
|
|
}
|
|
)
|
|
|
|
try:
|
|
result = await tool.coroutine(
|
|
agent="codex",
|
|
prompt="Implement the fix",
|
|
)
|
|
finally:
|
|
sys.modules.pop("acp", None)
|
|
sys.modules.pop("acp.schema", None)
|
|
|
|
assert result == "ACP result"
|
|
assert captured["spawn"] == {"cmd": "codex-acp", "args": ["--json"], "cwd": expected_cwd}
|
|
assert captured["new_session"] == {
|
|
"cwd": expected_cwd,
|
|
"mcp_servers": {
|
|
"github": {"transport": "stdio", "command": "npx", "args": ["github-mcp"]},
|
|
},
|
|
"model": "gpt-5-codex",
|
|
}
|
|
assert captured["prompt"] == {
|
|
"session_id": "session-1",
|
|
"prompt": [{"type": "text", "text": "Implement the fix"}],
|
|
}
|
|
|
|
|
|
@pytest.mark.anyio
|
|
async def test_invoke_acp_agent_uses_per_thread_workspace_when_thread_id_in_config(monkeypatch, tmp_path):
|
|
"""P1.1: When thread_id is in the RunnableConfig, ACP agent uses per-thread workspace."""
|
|
from deerflow.config import paths as paths_module
|
|
|
|
monkeypatch.setattr(paths_module, "get_paths", lambda: paths_module.Paths(base_dir=tmp_path))
|
|
|
|
monkeypatch.setattr(
|
|
"deerflow.config.extensions_config.ExtensionsConfig.from_file",
|
|
classmethod(lambda cls: ExtensionsConfig(mcp_servers={}, skills={})),
|
|
)
|
|
|
|
captured: dict[str, object] = {}
|
|
|
|
class DummyClient:
|
|
def __init__(self) -> None:
|
|
self._chunks: list[str] = []
|
|
|
|
@property
|
|
def collected_text(self) -> str:
|
|
return "".join(self._chunks)
|
|
|
|
async def session_update(self, session_id, update, **kwargs):
|
|
pass
|
|
|
|
async def request_permission(self, options, session_id, tool_call, **kwargs):
|
|
raise AssertionError("should not be called")
|
|
|
|
class DummyConn:
|
|
async def initialize(self, **kwargs):
|
|
pass
|
|
|
|
async def new_session(self, **kwargs):
|
|
captured["new_session"] = kwargs
|
|
return SimpleNamespace(session_id="s1")
|
|
|
|
async def prompt(self, **kwargs):
|
|
pass
|
|
|
|
class DummyProcessContext:
|
|
def __init__(self, client, cmd, *args, cwd):
|
|
captured["cwd"] = cwd
|
|
|
|
async def __aenter__(self):
|
|
return DummyConn(), object()
|
|
|
|
async def __aexit__(self, exc_type, exc, tb):
|
|
return False
|
|
|
|
class DummyRequestError(Exception):
|
|
@staticmethod
|
|
def method_not_found(method):
|
|
return DummyRequestError(method)
|
|
|
|
monkeypatch.setitem(
|
|
sys.modules,
|
|
"acp",
|
|
SimpleNamespace(
|
|
PROTOCOL_VERSION="2026-03-24",
|
|
Client=DummyClient,
|
|
RequestError=DummyRequestError,
|
|
spawn_agent_process=lambda client, cmd, *args, cwd: DummyProcessContext(client, cmd, *args, cwd=cwd),
|
|
text_block=lambda text: {"type": "text", "text": text},
|
|
),
|
|
)
|
|
monkeypatch.setitem(
|
|
sys.modules,
|
|
"acp.schema",
|
|
SimpleNamespace(
|
|
ClientCapabilities=lambda: {},
|
|
Implementation=lambda **kwargs: kwargs,
|
|
TextContentBlock=type("TextContentBlock", (), {"__init__": lambda self, text: setattr(self, "text", text)}),
|
|
),
|
|
)
|
|
|
|
thread_id = "thread-xyz-789"
|
|
expected_cwd = str(tmp_path / "threads" / thread_id / "acp-workspace")
|
|
|
|
tool = build_invoke_acp_agent_tool({"codex": ACPAgentConfig(command="codex-acp", description="Codex CLI")})
|
|
|
|
try:
|
|
await tool.coroutine(
|
|
agent="codex",
|
|
prompt="Do something",
|
|
config={"configurable": {"thread_id": thread_id}},
|
|
)
|
|
finally:
|
|
sys.modules.pop("acp", None)
|
|
sys.modules.pop("acp.schema", None)
|
|
|
|
assert captured["cwd"] == expected_cwd
|
|
|
|
|
|
def test_get_available_tools_includes_invoke_acp_agent_when_agents_configured(monkeypatch):
|
|
from deerflow.config.acp_config import load_acp_config_from_dict
|
|
|
|
load_acp_config_from_dict(
|
|
{
|
|
"codex": {
|
|
"command": "codex-acp",
|
|
"args": [],
|
|
"description": "Codex CLI",
|
|
}
|
|
}
|
|
)
|
|
|
|
fake_config = SimpleNamespace(
|
|
tools=[],
|
|
models=[],
|
|
tool_search=SimpleNamespace(enabled=False),
|
|
get_model_config=lambda name: None,
|
|
)
|
|
monkeypatch.setattr("deerflow.tools.tools.get_app_config", lambda: fake_config)
|
|
monkeypatch.setattr(
|
|
"deerflow.config.extensions_config.ExtensionsConfig.from_file",
|
|
classmethod(lambda cls: ExtensionsConfig(mcp_servers={}, skills={})),
|
|
)
|
|
|
|
tools = get_available_tools(include_mcp=True, subagent_enabled=False)
|
|
assert "invoke_acp_agent" in [tool.name for tool in tools]
|
|
|
|
load_acp_config_from_dict({})
|