Files
deer-flow/backend/packages/harness/deerflow/config/app_config.py
DanielWalnut d119214fee 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- **App** (`app/`): unpublished application code with import prefix `app.*`.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files can silently become outdated.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

334 lines
13 KiB
Python

import logging
import os
from pathlib import Path
from typing import Any, Self
import yaml
from dotenv import load_dotenv
from pydantic import BaseModel, ConfigDict, Field
from deerflow.config.acp_config import load_acp_config_from_dict
from deerflow.config.checkpointer_config import CheckpointerConfig, load_checkpointer_config_from_dict
from deerflow.config.extensions_config import ExtensionsConfig
from deerflow.config.guardrails_config import load_guardrails_config_from_dict
from deerflow.config.memory_config import load_memory_config_from_dict
from deerflow.config.model_config import ModelConfig
from deerflow.config.sandbox_config import SandboxConfig
from deerflow.config.skills_config import SkillsConfig
from deerflow.config.subagents_config import load_subagents_config_from_dict
from deerflow.config.summarization_config import load_summarization_config_from_dict
from deerflow.config.title_config import load_title_config_from_dict
from deerflow.config.token_usage_config import TokenUsageConfig
from deerflow.config.tool_config import ToolConfig, ToolGroupConfig
from deerflow.config.tool_search_config import ToolSearchConfig, load_tool_search_config_from_dict
load_dotenv()
logger = logging.getLogger(__name__)
class AppConfig(BaseModel):
"""Config for the DeerFlow application"""
log_level: str = Field(default="info", description="Logging level for deerflow modules (debug/info/warning/error)")
token_usage: TokenUsageConfig = Field(default_factory=TokenUsageConfig, description="Token usage tracking configuration")
models: list[ModelConfig] = Field(default_factory=list, description="Available models")
sandbox: SandboxConfig = Field(description="Sandbox configuration")
tools: list[ToolConfig] = Field(default_factory=list, description="Available tools")
tool_groups: list[ToolGroupConfig] = Field(default_factory=list, description="Available tool groups")
skills: SkillsConfig = Field(default_factory=SkillsConfig, description="Skills configuration")
extensions: ExtensionsConfig = Field(default_factory=ExtensionsConfig, description="Extensions configuration (MCP servers and skills state)")
tool_search: ToolSearchConfig = Field(default_factory=ToolSearchConfig, description="Tool search / deferred loading configuration")
model_config = ConfigDict(extra="allow", frozen=False)
checkpointer: CheckpointerConfig | None = Field(default=None, description="Checkpointer configuration")
@classmethod
def resolve_config_path(cls, config_path: str | None = None) -> Path:
"""Resolve the config file path.
Priority:
1. If provided `config_path` argument, use it.
2. If provided `DEER_FLOW_CONFIG_PATH` environment variable, use it.
3. Otherwise, first check the `config.yaml` in the current directory, then fallback to `config.yaml` in the parent directory.
"""
if config_path:
path = Path(config_path)
if not Path.exists(path):
raise FileNotFoundError(f"Config file specified by param `config_path` not found at {path}")
return path
elif os.getenv("DEER_FLOW_CONFIG_PATH"):
path = Path(os.getenv("DEER_FLOW_CONFIG_PATH"))
if not Path.exists(path):
raise FileNotFoundError(f"Config file specified by environment variable `DEER_FLOW_CONFIG_PATH` not found at {path}")
return path
else:
# Check if the config.yaml is in the current directory
path = Path(os.getcwd()) / "config.yaml"
if not path.exists():
# Check if the config.yaml is in the parent directory of CWD
path = Path(os.getcwd()).parent / "config.yaml"
if not path.exists():
raise FileNotFoundError("`config.yaml` file not found at the current directory nor its parent directory")
return path
@classmethod
def from_file(cls, config_path: str | None = None) -> Self:
"""Load config from YAML file.
See `resolve_config_path` for more details.
Args:
config_path: Path to the config file.
Returns:
AppConfig: The loaded config.
"""
resolved_path = cls.resolve_config_path(config_path)
with open(resolved_path, encoding="utf-8") as f:
config_data = yaml.safe_load(f) or {}
# Check config version before processing
cls._check_config_version(config_data, resolved_path)
config_data = cls.resolve_env_variables(config_data)
# Load title config if present
if "title" in config_data:
load_title_config_from_dict(config_data["title"])
# Load summarization config if present
if "summarization" in config_data:
load_summarization_config_from_dict(config_data["summarization"])
# Load memory config if present
if "memory" in config_data:
load_memory_config_from_dict(config_data["memory"])
# Load subagents config if present
if "subagents" in config_data:
load_subagents_config_from_dict(config_data["subagents"])
# Load tool_search config if present
if "tool_search" in config_data:
load_tool_search_config_from_dict(config_data["tool_search"])
# Load guardrails config if present
if "guardrails" in config_data:
load_guardrails_config_from_dict(config_data["guardrails"])
# Load checkpointer config if present
if "checkpointer" in config_data:
load_checkpointer_config_from_dict(config_data["checkpointer"])
# Always refresh ACP agent config so removed entries do not linger across reloads.
load_acp_config_from_dict(config_data.get("acp_agents", {}))
# Load extensions config separately (it's in a different file)
extensions_config = ExtensionsConfig.from_file()
config_data["extensions"] = extensions_config.model_dump()
result = cls.model_validate(config_data)
return result
@classmethod
def _check_config_version(cls, config_data: dict, config_path: Path) -> None:
"""Check if the user's config.yaml is outdated compared to config.example.yaml.
Emits a warning if the user's config_version is lower than the example's.
Missing config_version is treated as version 0 (pre-versioning).
"""
try:
user_version = int(config_data.get("config_version", 0))
except (TypeError, ValueError):
user_version = 0
# Find config.example.yaml by searching config.yaml's directory and its parents
example_path = None
search_dir = config_path.parent
for _ in range(5): # search up to 5 levels
candidate = search_dir / "config.example.yaml"
if candidate.exists():
example_path = candidate
break
parent = search_dir.parent
if parent == search_dir:
break
search_dir = parent
if example_path is None:
return
try:
with open(example_path, encoding="utf-8") as f:
example_data = yaml.safe_load(f)
raw = example_data.get("config_version", 0) if example_data else 0
try:
example_version = int(raw)
except (TypeError, ValueError):
example_version = 0
except Exception:
return
if user_version < example_version:
logger.warning(
"Your config.yaml (version %d) is outdated — the latest version is %d. Run `make config-upgrade` to merge new fields into your config.",
user_version,
example_version,
)
@classmethod
def resolve_env_variables(cls, config: Any) -> Any:
"""Recursively resolve environment variables in the config.
Environment variables are resolved using the `os.getenv` function. Example: $OPENAI_API_KEY
Args:
config: The config to resolve environment variables in.
Returns:
The config with environment variables resolved.
"""
if isinstance(config, str):
if config.startswith("$"):
env_value = os.getenv(config[1:])
if env_value is None:
raise ValueError(f"Environment variable {config[1:]} not found for config value {config}")
return env_value
return config
elif isinstance(config, dict):
return {k: cls.resolve_env_variables(v) for k, v in config.items()}
elif isinstance(config, list):
return [cls.resolve_env_variables(item) for item in config]
return config
def get_model_config(self, name: str) -> ModelConfig | None:
"""Get the model config by name.
Args:
name: The name of the model to get the config for.
Returns:
The model config if found, otherwise None.
"""
return next((model for model in self.models if model.name == name), None)
def get_tool_config(self, name: str) -> ToolConfig | None:
"""Get the tool config by name.
Args:
name: The name of the tool to get the config for.
Returns:
The tool config if found, otherwise None.
"""
return next((tool for tool in self.tools if tool.name == name), None)
def get_tool_group_config(self, name: str) -> ToolGroupConfig | None:
"""Get the tool group config by name.
Args:
name: The name of the tool group to get the config for.
Returns:
The tool group config if found, otherwise None.
"""
return next((group for group in self.tool_groups if group.name == name), None)
_app_config: AppConfig | None = None
_app_config_path: Path | None = None
_app_config_mtime: float | None = None
_app_config_is_custom = False
def _get_config_mtime(config_path: Path) -> float | None:
"""Get the modification time of a config file if it exists."""
try:
return config_path.stat().st_mtime
except OSError:
return None
def _load_and_cache_app_config(config_path: str | None = None) -> AppConfig:
"""Load config from disk and refresh cache metadata."""
global _app_config, _app_config_path, _app_config_mtime, _app_config_is_custom
resolved_path = AppConfig.resolve_config_path(config_path)
_app_config = AppConfig.from_file(str(resolved_path))
_app_config_path = resolved_path
_app_config_mtime = _get_config_mtime(resolved_path)
_app_config_is_custom = False
return _app_config
def get_app_config() -> AppConfig:
"""Get the DeerFlow config instance.
Returns a cached singleton instance and automatically reloads it when the
underlying config file path or modification time changes. Use
`reload_app_config()` to force a reload, or `reset_app_config()` to clear
the cache.
"""
global _app_config, _app_config_path, _app_config_mtime
if _app_config is not None and _app_config_is_custom:
return _app_config
resolved_path = AppConfig.resolve_config_path()
current_mtime = _get_config_mtime(resolved_path)
should_reload = _app_config is None or _app_config_path != resolved_path or _app_config_mtime != current_mtime
if should_reload:
if _app_config_path == resolved_path and _app_config_mtime is not None and current_mtime is not None and _app_config_mtime != current_mtime:
logger.info(
"Config file has been modified (mtime: %s -> %s), reloading AppConfig",
_app_config_mtime,
current_mtime,
)
_load_and_cache_app_config(str(resolved_path))
return _app_config
def reload_app_config(config_path: str | None = None) -> AppConfig:
"""Reload the config from file and update the cached instance.
This is useful when the config file has been modified and you want
to pick up the changes without restarting the application.
Args:
config_path: Optional path to config file. If not provided,
uses the default resolution strategy.
Returns:
The newly loaded AppConfig instance.
"""
return _load_and_cache_app_config(config_path)
def reset_app_config() -> None:
"""Reset the cached config instance.
This clears the singleton cache, causing the next call to
`get_app_config()` to reload from file. Useful for testing
or when switching between different configurations.
"""
global _app_config, _app_config_path, _app_config_mtime, _app_config_is_custom
_app_config = None
_app_config_path = None
_app_config_mtime = None
_app_config_is_custom = False
def set_app_config(config: AppConfig) -> None:
"""Set a custom config instance.
This allows injecting a custom or mock config for testing purposes.
Args:
config: The AppConfig instance to use.
"""
global _app_config, _app_config_path, _app_config_mtime, _app_config_is_custom
_app_config = config
_app_config_path = None
_app_config_mtime = None
_app_config_is_custom = True