yangzheli 59c4a3f0a4
feat(agent): add custom-agent self-updates with user isolation (#2713)
* feat(agent): add update_agent tool for in-chat custom-agent self-updates (#2616)

Custom agents had no built-in way to persist updates to their own SOUL.md /
config.yaml from a normal chat — `setup_agent` was only bound during the
bootstrap flow, so when the user asked the agent to refine its description
or personality, the agent would shell out via bash/write_file and the edits
landed in a temporary sandbox/tool workspace instead of
`{base_dir}/agents/{agent_name}/`.

Changes:
- New `update_agent` builtin tool with partial-update semantics (only the
  fields you pass are written) and atomic temp-file + os.replace writes so
  a failed update never corrupts existing SOUL.md / config.yaml.
- Lead agent now binds `update_agent` in the non-bootstrap path whenever
  `agent_name` is set in the runtime context. Default agent (no
  agent_name) and bootstrap flow are unchanged.
- New `<self_update>` system-prompt section is injected for custom agents,
  instructing them to use `update_agent` — and explicitly NOT bash /
  write_file — to persist self-updates.
- Tests: 11 new cases in `tests/test_update_agent_tool.py` covering
  validation (missing/invalid agent_name, unknown agent, no fields),
  partial updates (soul-only, description-only, skills=[] vs omitted),
  no-op detection, atomic-write safety, and AgentConfig round-tripping;
  plus 2 new cases in `tests/test_lead_agent_prompt.py` covering the
  self-update prompt section.
- Docs: updated backend/CLAUDE.md builtin tools list and tools.mdx
  (en/zh) with the new tool description.

* feat(agent): isolate custom agents per user

Store custom agent definitions under the effective user, keep legacy agents readable until migration, and cover API/tool/migration behavior with tests.

Co-authored-by: Cursor <cursoragent@cursor.com>

* feat: consistent write/delete targets & add --user-id to migration

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-05-05 23:17:42 +08:00

201 lines
6.8 KiB
Python

"""Configuration and loaders for custom agents.
Custom agents are stored per-user under ``{base_dir}/users/{user_id}/agents/{name}/``.
A legacy shared layout at ``{base_dir}/agents/{name}/`` is still readable so that
installations that pre-date user isolation continue to work until they run the
``scripts/migrate_user_isolation.py`` migration. New writes always target the
per-user layout.
"""
import logging
import re
from pathlib import Path
from typing import Any
import yaml
from pydantic import BaseModel
from deerflow.config.paths import get_paths
from deerflow.runtime.user_context import get_effective_user_id
logger = logging.getLogger(__name__)
SOUL_FILENAME = "SOUL.md"
AGENT_NAME_PATTERN = re.compile(r"^[A-Za-z0-9-]+$")
def validate_agent_name(name: str | None) -> str | None:
"""Validate a custom agent name before using it in filesystem paths."""
if name is None:
return None
if not isinstance(name, str):
raise ValueError("Invalid agent name. Expected a string or None.")
if not AGENT_NAME_PATTERN.fullmatch(name):
raise ValueError(f"Invalid agent name '{name}'. Must match pattern: {AGENT_NAME_PATTERN.pattern}")
return name
class AgentConfig(BaseModel):
"""Configuration for a custom agent."""
name: str
description: str = ""
model: str | None = None
tool_groups: list[str] | None = None
# skills controls which skills are loaded into the agent's prompt:
# - None (or omitted): load all enabled skills (default fallback behavior)
# - [] (explicit empty list): disable all skills
# - ["skill1", "skill2"]: load only the specified skills
skills: list[str] | None = None
def resolve_agent_dir(name: str, *, user_id: str | None = None) -> Path:
"""Return the on-disk directory for an agent, preferring the per-user layout.
Resolution order:
1. ``{base_dir}/users/{user_id}/agents/{name}/`` (per-user, current layout).
2. ``{base_dir}/agents/{name}/`` (legacy shared layout — read-only fallback).
If neither exists, the per-user path is returned so callers that intend to
create the agent write into the new layout.
Args:
name: Validated agent name.
user_id: Owner of the agent. Defaults to the effective user from the
request context (or ``"default"`` in no-auth mode).
"""
paths = get_paths()
effective_user = user_id or get_effective_user_id()
user_path = paths.user_agent_dir(effective_user, name)
if user_path.exists():
return user_path
legacy_path = paths.agent_dir(name)
if legacy_path.exists():
return legacy_path
return user_path
def load_agent_config(name: str | None, *, user_id: str | None = None) -> AgentConfig | None:
"""Load the custom or default agent's config from its directory.
Reads from the per-user layout first; falls back to the legacy shared layout
for installations that have not yet been migrated.
Args:
name: The agent name.
user_id: Owner of the agent. Defaults to the effective user from the
current request context.
Returns:
AgentConfig instance, or ``None`` if ``name`` is ``None``.
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
name = validate_agent_name(name)
agent_dir = resolve_agent_dir(name, user_id=user_id)
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, *, user_id: str | None = 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.
user_id: Owner of the agent. Defaults to the effective user from the
current request context.
Returns:
The SOUL.md content as a string, or None if the file does not exist.
"""
if agent_name:
agent_dir = resolve_agent_dir(agent_name, user_id=user_id)
else:
agent_dir = 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(*, user_id: str | None = None) -> list[AgentConfig]:
"""Scan the agents directory and return all valid custom agents.
Returns the union of agents in the per-user layout and the legacy shared
layout, so that pre-migration installations remain visible until they are
migrated. Per-user entries shadow legacy entries with the same name.
Args:
user_id: Owner whose agents to list. Defaults to the effective user
from the current request context.
Returns:
List of AgentConfig for each valid agent directory found.
"""
paths = get_paths()
effective_user = user_id or get_effective_user_id()
seen: set[str] = set()
agents: list[AgentConfig] = []
user_root = paths.user_agents_dir(effective_user)
legacy_root = paths.agents_dir
for root in (user_root, legacy_root):
if not root.exists():
continue
for entry in sorted(root.iterdir()):
if not entry.is_dir():
continue
if entry.name in seen:
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, user_id=effective_user)
if agent_cfg is None:
continue
agents.append(agent_cfg)
seen.add(entry.name)
except Exception as e:
logger.warning(f"Skipping agent '{entry.name}': {e}")
agents.sort(key=lambda a: a.name)
return agents