mirror of
https://gitee.com/wanwujie/deer-flow
synced 2026-04-02 22:02:13 +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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated.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>
243 lines
9.0 KiB
Python
243 lines
9.0 KiB
Python
import os
|
|
import re
|
|
import shutil
|
|
from pathlib import Path
|
|
|
|
# Virtual path prefix seen by agents inside the sandbox
|
|
VIRTUAL_PATH_PREFIX = "/mnt/user-data"
|
|
|
|
_SAFE_THREAD_ID_RE = re.compile(r"^[A-Za-z0-9_\-]+$")
|
|
|
|
|
|
class Paths:
|
|
"""
|
|
Centralized path configuration for DeerFlow application data.
|
|
|
|
Directory layout (host side):
|
|
{base_dir}/
|
|
├── memory.json
|
|
├── USER.md <-- global user profile (injected into all agents)
|
|
├── agents/
|
|
│ └── {agent_name}/
|
|
│ ├── config.yaml
|
|
│ ├── SOUL.md <-- agent personality/identity (injected alongside lead prompt)
|
|
│ └── memory.json
|
|
└── threads/
|
|
└── {thread_id}/
|
|
└── user-data/ <-- mounted as /mnt/user-data/ inside sandbox
|
|
├── workspace/ <-- /mnt/user-data/workspace/
|
|
├── uploads/ <-- /mnt/user-data/uploads/
|
|
└── outputs/ <-- /mnt/user-data/outputs/
|
|
|
|
BaseDir resolution (in priority order):
|
|
1. Constructor argument `base_dir`
|
|
2. DEER_FLOW_HOME environment variable
|
|
3. Local dev fallback: cwd/.deer-flow (when cwd is the backend/ dir)
|
|
4. Default: $HOME/.deer-flow
|
|
"""
|
|
|
|
def __init__(self, base_dir: str | Path | None = None) -> None:
|
|
self._base_dir = Path(base_dir).resolve() if base_dir is not None else None
|
|
|
|
@property
|
|
def host_base_dir(self) -> Path:
|
|
"""Host-visible base dir for Docker volume mount sources.
|
|
|
|
When running inside Docker with a mounted Docker socket (DooD), the Docker
|
|
daemon runs on the host and resolves mount paths against the host filesystem.
|
|
Set DEER_FLOW_HOST_BASE_DIR to the host-side path that corresponds to this
|
|
container's base_dir so that sandbox container volume mounts work correctly.
|
|
|
|
Falls back to base_dir when the env var is not set (native/local execution).
|
|
"""
|
|
if env := os.getenv("DEER_FLOW_HOST_BASE_DIR"):
|
|
return Path(env)
|
|
return self.base_dir
|
|
|
|
@property
|
|
def base_dir(self) -> Path:
|
|
"""Root directory for all application data."""
|
|
if self._base_dir is not None:
|
|
return self._base_dir
|
|
|
|
if env_home := os.getenv("DEER_FLOW_HOME"):
|
|
return Path(env_home).resolve()
|
|
|
|
cwd = Path.cwd()
|
|
if cwd.name == "backend" or (cwd / "pyproject.toml").exists():
|
|
return cwd / ".deer-flow"
|
|
|
|
return Path.home() / ".deer-flow"
|
|
|
|
@property
|
|
def memory_file(self) -> Path:
|
|
"""Path to the persisted memory file: `{base_dir}/memory.json`."""
|
|
return self.base_dir / "memory.json"
|
|
|
|
@property
|
|
def user_md_file(self) -> Path:
|
|
"""Path to the global user profile file: `{base_dir}/USER.md`."""
|
|
return self.base_dir / "USER.md"
|
|
|
|
@property
|
|
def agents_dir(self) -> Path:
|
|
"""Root directory for all custom agents: `{base_dir}/agents/`."""
|
|
return self.base_dir / "agents"
|
|
|
|
def agent_dir(self, name: str) -> Path:
|
|
"""Directory for a specific agent: `{base_dir}/agents/{name}/`."""
|
|
return self.agents_dir / name.lower()
|
|
|
|
def agent_memory_file(self, name: str) -> Path:
|
|
"""Per-agent memory file: `{base_dir}/agents/{name}/memory.json`."""
|
|
return self.agent_dir(name) / "memory.json"
|
|
|
|
def thread_dir(self, thread_id: str) -> Path:
|
|
"""
|
|
Host path for a thread's data: `{base_dir}/threads/{thread_id}/`
|
|
|
|
This directory contains a `user-data/` subdirectory that is mounted
|
|
as `/mnt/user-data/` inside the sandbox.
|
|
|
|
Raises:
|
|
ValueError: If `thread_id` contains unsafe characters (path separators
|
|
or `..`) that could cause directory traversal.
|
|
"""
|
|
if not _SAFE_THREAD_ID_RE.match(thread_id):
|
|
raise ValueError(f"Invalid thread_id {thread_id!r}: only alphanumeric characters, hyphens, and underscores are allowed.")
|
|
return self.base_dir / "threads" / thread_id
|
|
|
|
def sandbox_work_dir(self, thread_id: str) -> Path:
|
|
"""
|
|
Host path for the agent's workspace directory.
|
|
Host: `{base_dir}/threads/{thread_id}/user-data/workspace/`
|
|
Sandbox: `/mnt/user-data/workspace/`
|
|
"""
|
|
return self.thread_dir(thread_id) / "user-data" / "workspace"
|
|
|
|
def sandbox_uploads_dir(self, thread_id: str) -> Path:
|
|
"""
|
|
Host path for user-uploaded files.
|
|
Host: `{base_dir}/threads/{thread_id}/user-data/uploads/`
|
|
Sandbox: `/mnt/user-data/uploads/`
|
|
"""
|
|
return self.thread_dir(thread_id) / "user-data" / "uploads"
|
|
|
|
def sandbox_outputs_dir(self, thread_id: str) -> Path:
|
|
"""
|
|
Host path for agent-generated artifacts.
|
|
Host: `{base_dir}/threads/{thread_id}/user-data/outputs/`
|
|
Sandbox: `/mnt/user-data/outputs/`
|
|
"""
|
|
return self.thread_dir(thread_id) / "user-data" / "outputs"
|
|
|
|
def acp_workspace_dir(self, thread_id: str) -> Path:
|
|
"""
|
|
Host path for the ACP workspace of a specific thread.
|
|
Host: `{base_dir}/threads/{thread_id}/acp-workspace/`
|
|
Sandbox: `/mnt/acp-workspace/`
|
|
|
|
Each thread gets its own isolated ACP workspace so that concurrent
|
|
sessions cannot read each other's ACP agent outputs.
|
|
"""
|
|
return self.thread_dir(thread_id) / "acp-workspace"
|
|
|
|
def sandbox_user_data_dir(self, thread_id: str) -> Path:
|
|
"""
|
|
Host path for the user-data root.
|
|
Host: `{base_dir}/threads/{thread_id}/user-data/`
|
|
Sandbox: `/mnt/user-data/`
|
|
"""
|
|
return self.thread_dir(thread_id) / "user-data"
|
|
|
|
def ensure_thread_dirs(self, thread_id: str) -> None:
|
|
"""Create all standard sandbox directories for a thread.
|
|
|
|
Directories are created with mode 0o777 so that sandbox containers
|
|
(which may run as a different UID than the host backend process) can
|
|
write to the volume-mounted paths without "Permission denied" errors.
|
|
The explicit chmod() call is necessary because Path.mkdir(mode=...) is
|
|
subject to the process umask and may not yield the intended permissions.
|
|
|
|
Includes the ACP workspace directory so it can be volume-mounted into
|
|
the sandbox container at ``/mnt/acp-workspace`` even before the first
|
|
ACP agent invocation.
|
|
"""
|
|
for d in [
|
|
self.sandbox_work_dir(thread_id),
|
|
self.sandbox_uploads_dir(thread_id),
|
|
self.sandbox_outputs_dir(thread_id),
|
|
self.acp_workspace_dir(thread_id),
|
|
]:
|
|
d.mkdir(parents=True, exist_ok=True)
|
|
d.chmod(0o777)
|
|
|
|
def delete_thread_dir(self, thread_id: str) -> None:
|
|
"""Delete all persisted data for a thread.
|
|
|
|
The operation is idempotent: missing thread directories are ignored.
|
|
"""
|
|
thread_dir = self.thread_dir(thread_id)
|
|
if thread_dir.exists():
|
|
shutil.rmtree(thread_dir)
|
|
|
|
def resolve_virtual_path(self, thread_id: str, virtual_path: str) -> Path:
|
|
"""Resolve a sandbox virtual path to the actual host filesystem path.
|
|
|
|
Args:
|
|
thread_id: The thread ID.
|
|
virtual_path: Virtual path as seen inside the sandbox, e.g.
|
|
``/mnt/user-data/outputs/report.pdf``.
|
|
Leading slashes are stripped before matching.
|
|
|
|
Returns:
|
|
The resolved absolute host filesystem path.
|
|
|
|
Raises:
|
|
ValueError: If the path does not start with the expected virtual
|
|
prefix or a path-traversal attempt is detected.
|
|
"""
|
|
stripped = virtual_path.lstrip("/")
|
|
prefix = VIRTUAL_PATH_PREFIX.lstrip("/")
|
|
|
|
# Require an exact segment-boundary match to avoid prefix confusion
|
|
# (e.g. reject paths like "mnt/user-dataX/...").
|
|
if stripped != prefix and not stripped.startswith(prefix + "/"):
|
|
raise ValueError(f"Path must start with /{prefix}")
|
|
|
|
relative = stripped[len(prefix) :].lstrip("/")
|
|
base = self.sandbox_user_data_dir(thread_id).resolve()
|
|
actual = (base / relative).resolve()
|
|
|
|
try:
|
|
actual.relative_to(base)
|
|
except ValueError:
|
|
raise ValueError("Access denied: path traversal detected")
|
|
|
|
return actual
|
|
|
|
|
|
# ── Singleton ────────────────────────────────────────────────────────────
|
|
|
|
_paths: Paths | None = None
|
|
|
|
|
|
def get_paths() -> Paths:
|
|
"""Return the global Paths singleton (lazy-initialized)."""
|
|
global _paths
|
|
if _paths is None:
|
|
_paths = Paths()
|
|
return _paths
|
|
|
|
|
|
def resolve_path(path: str) -> Path:
|
|
"""Resolve *path* to an absolute ``Path``.
|
|
|
|
Relative paths are resolved relative to the application base directory.
|
|
Absolute paths are returned as-is (after normalisation).
|
|
"""
|
|
p = Path(path)
|
|
if not p.is_absolute():
|
|
p = get_paths().base_dir / path
|
|
return p.resolve()
|