Files
deer-flow/backend/packages/harness/deerflow/skills/parser.py
T
AochenShen99 cef4224381 fix(skills): enforce allowed-tools metadata (#2626)
* fix(skills): parse allowed-tools frontmatter

* fix(skills): validate allowed-tools metadata

* fix(skills): add shared allowed-tools policy

* fix(subagents): enforce skill allowed-tools

* fix(agent): enforce skill allowed-tools

* refactor(skills): dedupe TypeVar and reuse cached enabled skills

- Drop redundant module-level TypeVar in tool_policy; rely on PEP 695 syntax.
- Expose get_cached_enabled_skills() and have the lead agent reuse it
  instead of synchronously rescanning skills on every request.

* fix(agent): expose config-scoped skill cache

* fix(subagents): pass filtered tools explicitly

* fix(skills): clean allowed-tools policy feedback
2026-05-07 08:34:43 +08:00

111 lines
3.7 KiB
Python

import logging
import re
from pathlib import Path
import yaml
from .types import SKILL_MD_FILE, Skill, SkillCategory
logger = logging.getLogger(__name__)
def parse_allowed_tools(raw: object, skill_file: Path) -> list[str] | None:
"""Parse the optional allowed-tools frontmatter field.
Returns None when the field is omitted. Returns a list when the field is a
YAML sequence of strings, including an empty list for explicit no-tool
skills. Raises ValueError for malformed values.
"""
if raw is None:
return None
if not isinstance(raw, list):
raise ValueError(f"allowed-tools in {skill_file} must be a list of strings")
allowed_tools: list[str] = []
for item in raw:
if not isinstance(item, str):
raise ValueError(f"allowed-tools in {skill_file} must contain only strings")
tool_name = item.strip()
if not tool_name:
raise ValueError(f"allowed-tools in {skill_file} cannot contain empty tool names")
allowed_tools.append(tool_name)
return allowed_tools
def parse_skill_file(skill_file: Path, category: SkillCategory, relative_path: Path | None = None) -> Skill | None:
"""Parse a SKILL.md file and extract metadata.
Args:
skill_file: Path to the SKILL.md file.
category: Category of the skill.
relative_path: Relative path from the category root to the skill
directory. Defaults to the skill directory name when omitted.
Returns:
Skill object if parsing succeeds, None otherwise.
"""
if not skill_file.exists() or skill_file.name != SKILL_MD_FILE:
return None
try:
content = skill_file.read_text(encoding="utf-8")
# Extract YAML front-matter block between leading ``---`` fences.
front_matter_match = re.match(r"^---\s*\n(.*?)\n---\s*\n", content, re.DOTALL)
if not front_matter_match:
return None
front_matter_text = front_matter_match.group(1)
try:
metadata = yaml.safe_load(front_matter_text)
except yaml.YAMLError as exc:
logger.error("Invalid YAML front-matter in %s: %s", skill_file, exc)
return None
if not isinstance(metadata, dict):
logger.error("Front-matter in %s is not a YAML mapping", skill_file)
return None
# Extract required fields. Both must be non-empty strings.
name = metadata.get("name")
description = metadata.get("description")
if not name or not isinstance(name, str):
return None
if not description or not isinstance(description, str):
return None
# Normalise: strip surrounding whitespace that YAML may preserve.
name = name.strip()
description = description.strip()
if not name or not description:
return None
license_text = metadata.get("license")
if license_text is not None:
license_text = str(license_text).strip() or None
try:
allowed_tools = parse_allowed_tools(metadata.get("allowed-tools"), skill_file)
except ValueError as exc:
logger.error("Invalid allowed-tools in %s: %s", skill_file, exc)
return None
return Skill(
name=name,
description=description,
license=license_text,
skill_dir=skill_file.parent,
skill_file=skill_file,
relative_path=relative_path or Path(skill_file.parent.name),
category=category,
allowed_tools=allowed_tools,
enabled=True, # Actual state comes from the extensions config file.
)
except Exception:
logger.exception("Unexpected error parsing skill file %s", skill_file)
return None