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 - **App** (`app/`): unpublished application code with import prefix `app.*`.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on startup When config.example.yaml schema changes, developers' local config.yaml files can silently become outdated.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> --------- Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
121 lines
3.4 KiB
Python
121 lines
3.4 KiB
Python
"""Configuration and loaders for custom agents."""
|
|
|
|
import logging
|
|
import re
|
|
from typing import Any
|
|
|
|
import yaml
|
|
from pydantic import BaseModel
|
|
|
|
from deerflow.config.paths import get_paths
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
SOUL_FILENAME = "SOUL.md"
|
|
AGENT_NAME_PATTERN = re.compile(r"^[A-Za-z0-9-]+$")
|
|
|
|
|
|
class AgentConfig(BaseModel):
|
|
"""Configuration for a custom agent."""
|
|
|
|
name: str
|
|
description: str = ""
|
|
model: str | None = None
|
|
tool_groups: list[str] | None = None
|
|
|
|
|
|
def load_agent_config(name: str | None) -> AgentConfig | None:
|
|
"""Load the custom or default agent's config from its directory.
|
|
|
|
Args:
|
|
name: The agent name.
|
|
|
|
Returns:
|
|
AgentConfig instance.
|
|
|
|
Raises:
|
|
FileNotFoundError: If the agent directory or config.yaml does not exist.
|
|
ValueError: If config.yaml cannot be parsed.
|
|
"""
|
|
|
|
if name is None:
|
|
return None
|
|
|
|
if not AGENT_NAME_PATTERN.match(name):
|
|
raise ValueError(f"Invalid agent name '{name}'. Must match pattern: {AGENT_NAME_PATTERN.pattern}")
|
|
agent_dir = get_paths().agent_dir(name)
|
|
config_file = agent_dir / "config.yaml"
|
|
|
|
if not agent_dir.exists():
|
|
raise FileNotFoundError(f"Agent directory not found: {agent_dir}")
|
|
|
|
if not config_file.exists():
|
|
raise FileNotFoundError(f"Agent config not found: {config_file}")
|
|
|
|
try:
|
|
with open(config_file, encoding="utf-8") as f:
|
|
data: dict[str, Any] = yaml.safe_load(f) or {}
|
|
except yaml.YAMLError as e:
|
|
raise ValueError(f"Failed to parse agent config {config_file}: {e}") from e
|
|
|
|
# Ensure name is set from directory name if not in file
|
|
if "name" not in data:
|
|
data["name"] = name
|
|
|
|
# Strip unknown fields before passing to Pydantic (e.g. legacy prompt_file)
|
|
known_fields = set(AgentConfig.model_fields.keys())
|
|
data = {k: v for k, v in data.items() if k in known_fields}
|
|
|
|
return AgentConfig(**data)
|
|
|
|
|
|
def load_agent_soul(agent_name: str | None) -> str | None:
|
|
"""Read the SOUL.md file for a custom agent, if it exists.
|
|
|
|
SOUL.md defines the agent's personality, values, and behavioral guardrails.
|
|
It is injected into the lead agent's system prompt as additional context.
|
|
|
|
Args:
|
|
agent_name: The name of the agent or None for the default agent.
|
|
|
|
Returns:
|
|
The SOUL.md content as a string, or None if the file does not exist.
|
|
"""
|
|
agent_dir = get_paths().agent_dir(agent_name) if agent_name else get_paths().base_dir
|
|
soul_path = agent_dir / SOUL_FILENAME
|
|
if not soul_path.exists():
|
|
return None
|
|
content = soul_path.read_text(encoding="utf-8").strip()
|
|
return content or None
|
|
|
|
|
|
def list_custom_agents() -> list[AgentConfig]:
|
|
"""Scan the agents directory and return all valid custom agents.
|
|
|
|
Returns:
|
|
List of AgentConfig for each valid agent directory found.
|
|
"""
|
|
agents_dir = get_paths().agents_dir
|
|
|
|
if not agents_dir.exists():
|
|
return []
|
|
|
|
agents: list[AgentConfig] = []
|
|
|
|
for entry in sorted(agents_dir.iterdir()):
|
|
if not entry.is_dir():
|
|
continue
|
|
|
|
config_file = entry / "config.yaml"
|
|
if not config_file.exists():
|
|
logger.debug(f"Skipping {entry.name}: no config.yaml")
|
|
continue
|
|
|
|
try:
|
|
agent_cfg = load_agent_config(entry.name)
|
|
agents.append(agent_cfg)
|
|
except Exception as e:
|
|
logger.warning(f"Skipping agent '{entry.name}': {e}")
|
|
|
|
return agents
|