2026-01-19 18:57:16 +08:00
|
|
|
"""Load MCP tools using langchain-mcp-adapters."""
|
|
|
|
|
|
2026-03-24 22:38:01 +08:00
|
|
|
import asyncio
|
|
|
|
|
import atexit
|
|
|
|
|
import concurrent.futures
|
2026-01-19 18:57:16 +08:00
|
|
|
import logging
|
2026-03-24 22:38:01 +08:00
|
|
|
from collections.abc import Callable
|
|
|
|
|
from typing import Any
|
2026-01-19 18:57:16 +08:00
|
|
|
|
|
|
|
|
from langchain_core.tools import BaseTool
|
|
|
|
|
|
refactor: split backend into harness (deerflow.*) and app (app.*) (#1131)
* 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- **App** (`app/`): unpublished application code with import prefix `app.*`.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>
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-14 22:55:52 +08:00
|
|
|
from deerflow.config.extensions_config import ExtensionsConfig
|
|
|
|
|
from deerflow.mcp.client import build_servers_config
|
|
|
|
|
from deerflow.mcp.oauth import build_oauth_tool_interceptor, get_initial_oauth_headers
|
2026-01-19 18:57:16 +08:00
|
|
|
|
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
2026-03-24 22:38:01 +08:00
|
|
|
# Global thread pool for sync tool invocation in async environments
|
|
|
|
|
_SYNC_TOOL_EXECUTOR = concurrent.futures.ThreadPoolExecutor(max_workers=10, thread_name_prefix="mcp-sync-tool")
|
|
|
|
|
|
|
|
|
|
# Register shutdown hook for the global executor
|
|
|
|
|
atexit.register(lambda: _SYNC_TOOL_EXECUTOR.shutdown(wait=False))
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
def _make_sync_tool_wrapper(coro: Callable[..., Any], tool_name: str) -> Callable[..., Any]:
|
|
|
|
|
"""Build a synchronous wrapper for an asynchronous tool coroutine.
|
|
|
|
|
|
|
|
|
|
Args:
|
|
|
|
|
coro: The tool's asynchronous coroutine.
|
|
|
|
|
tool_name: Name of the tool (for logging).
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
A synchronous function that correctly handles nested event loops.
|
|
|
|
|
"""
|
|
|
|
|
|
|
|
|
|
def sync_wrapper(*args: Any, **kwargs: Any) -> Any:
|
|
|
|
|
try:
|
|
|
|
|
loop = asyncio.get_running_loop()
|
|
|
|
|
except RuntimeError:
|
|
|
|
|
loop = None
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
if loop is not None and loop.is_running():
|
|
|
|
|
# Use global executor to avoid nested loop issues and improve performance
|
|
|
|
|
future = _SYNC_TOOL_EXECUTOR.submit(asyncio.run, coro(*args, **kwargs))
|
|
|
|
|
return future.result()
|
|
|
|
|
else:
|
|
|
|
|
return asyncio.run(coro(*args, **kwargs))
|
|
|
|
|
except Exception as e:
|
|
|
|
|
logger.error(f"Error invoking MCP tool '{tool_name}' via sync wrapper: {e}", exc_info=True)
|
|
|
|
|
raise
|
|
|
|
|
|
|
|
|
|
return sync_wrapper
|
|
|
|
|
|
2026-01-19 18:57:16 +08:00
|
|
|
|
|
|
|
|
async def get_mcp_tools() -> list[BaseTool]:
|
|
|
|
|
"""Get all tools from enabled MCP servers.
|
|
|
|
|
|
|
|
|
|
Returns:
|
|
|
|
|
List of LangChain tools from all enabled MCP servers.
|
|
|
|
|
"""
|
|
|
|
|
try:
|
|
|
|
|
from langchain_mcp_adapters.client import MultiServerMCPClient
|
|
|
|
|
except ImportError:
|
|
|
|
|
logger.warning("langchain-mcp-adapters not installed. Install it to enable MCP tools: pip install langchain-mcp-adapters")
|
|
|
|
|
return []
|
|
|
|
|
|
2026-01-25 22:37:53 +08:00
|
|
|
# NOTE: We use ExtensionsConfig.from_file() instead of get_extensions_config()
|
|
|
|
|
# to always read the latest configuration from disk. This ensures that changes
|
|
|
|
|
# made through the Gateway API (which runs in a separate process) are immediately
|
|
|
|
|
# reflected when initializing MCP tools.
|
|
|
|
|
extensions_config = ExtensionsConfig.from_file()
|
2026-01-20 13:57:36 +08:00
|
|
|
servers_config = build_servers_config(extensions_config)
|
2026-01-19 18:57:16 +08:00
|
|
|
|
|
|
|
|
if not servers_config:
|
|
|
|
|
logger.info("No enabled MCP servers configured")
|
|
|
|
|
return []
|
|
|
|
|
|
|
|
|
|
try:
|
|
|
|
|
# Create the multi-server MCP client
|
|
|
|
|
logger.info(f"Initializing MCP client with {len(servers_config)} server(s)")
|
2026-03-01 22:38:58 +08:00
|
|
|
|
|
|
|
|
# Inject initial OAuth headers for server connections (tool discovery/session init)
|
|
|
|
|
initial_oauth_headers = await get_initial_oauth_headers(extensions_config)
|
|
|
|
|
for server_name, auth_header in initial_oauth_headers.items():
|
|
|
|
|
if server_name not in servers_config:
|
|
|
|
|
continue
|
|
|
|
|
if servers_config[server_name].get("transport") in ("sse", "http"):
|
|
|
|
|
existing_headers = dict(servers_config[server_name].get("headers", {}))
|
|
|
|
|
existing_headers["Authorization"] = auth_header
|
|
|
|
|
servers_config[server_name]["headers"] = existing_headers
|
|
|
|
|
|
|
|
|
|
tool_interceptors = []
|
|
|
|
|
oauth_interceptor = build_oauth_tool_interceptor(extensions_config)
|
|
|
|
|
if oauth_interceptor is not None:
|
|
|
|
|
tool_interceptors.append(oauth_interceptor)
|
|
|
|
|
|
2026-03-17 20:43:55 +08:00
|
|
|
client = MultiServerMCPClient(servers_config, tool_interceptors=tool_interceptors, tool_name_prefix=True)
|
2026-01-19 18:57:16 +08:00
|
|
|
|
|
|
|
|
# Get all tools from all servers
|
|
|
|
|
tools = await client.get_tools()
|
|
|
|
|
logger.info(f"Successfully loaded {len(tools)} tool(s) from MCP servers")
|
feat(harness): integration ACP agent tool (#1344)
* 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>
2026-03-26 14:20:18 +08:00
|
|
|
|
2026-03-24 22:38:01 +08:00
|
|
|
# Patch tools to support sync invocation, as deerflow client streams synchronously
|
|
|
|
|
for tool in tools:
|
|
|
|
|
if getattr(tool, "func", None) is None and getattr(tool, "coroutine", None) is not None:
|
|
|
|
|
tool.func = _make_sync_tool_wrapper(tool.coroutine, tool.name)
|
2026-01-19 18:57:16 +08:00
|
|
|
|
|
|
|
|
return tools
|
|
|
|
|
|
|
|
|
|
except Exception as e:
|
|
|
|
|
logger.error(f"Failed to load MCP tools: {e}", exc_info=True)
|
|
|
|
|
return []
|