feat(skills): 自我进化 - 软归档/恢复 + Agent 归属 + 状态分层 UI

后端:
- 新增 PUT /api/skills/custom/{name}/state 与 /pinned 软归档/恢复 + 钉选 API
- skill_manage 工具: agent 创建写 DB 归属; 删除清理 .usage.json + DB row + cascade 引用; 加 ownership 预校验
- curator 全部软归档(文件保留在 custom/), 加 reason 必填(中文), 修 user_context 跨线程传播 / 协程泄漏 / archive 文件不再移动
- LLM 评审接 ToolErrorHandlingMiddleware, 工具异常自动重试不中止本轮; 替换 create_react_agent 为 create_agent
- skill_list 按当前 agent config.yaml 的 skills 字段过滤(custom agent), lead agent 仍可见全部
- 自我进化提示词对齐 Hermes 风格: 主动询问保存, reason 强制中文且面向用户
- 控制台日志增强: 自动归档/标过时/LLM 合并/删减建议 都按条目输出原因

前端:
- 技能管理页 Tab 改「全部 / 我的」, 正确包含他人发布的 custom 技能(修复 isCustom 互斥 bug)
- 新增「过时 N / 归档 N」右侧抽屉(恢复/查看/立即归档 ⋯ 菜单)
- 新增徽章: 钉选 / 来源(Agent 创建 / 用户上传) / 使用次数展示
- 内置技能徽章修复(原 isBuiltin && isCustom 永远 false)
- 自我进化日志 run_started sentinel 在前端展示为中文分隔条
- 移除冗余 enabled 开关(归档已覆盖此能力, 减少术语)

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
xuhdandClaude Opus 4.7 committed 2026-05-15 00:00:52 +08:00
1 parent f8bc74b27f
commit 62d525dae7
16 files changed
+1270 -97

No files matched your search

@@ -5,11 +5,60 @@ from __future__ import annotations
import json
import logging
from langchain.tools import tool
from langchain.tools import ToolRuntime, tool
logger = logging.getLogger(__name__)
def _resolve_active_agent_id(runtime: ToolRuntime | None) -> str | None:
"""Extract the agent_id under which the current tool call is running.
Custom agents pass their id via either the ``context`` dict or the
``configurable`` section of the LangGraph runtime config. The default
lead agent runs without an explicit agent_id — callers should treat
a None return as "no per-agent skills filter applies".
"""
if runtime is None:
return None
try:
if getattr(runtime, "context", None):
ctx_id = runtime.context.get("agent_id")
if ctx_id:
return str(ctx_id)
cfg = getattr(runtime, "config", None)
if isinstance(cfg, dict):
cid = cfg.get("configurable", {}).get("agent_id")
if cid:
return str(cid)
except Exception:
return None
return None
def _load_agent_skill_whitelist(agent_id: str | None) -> set[str] | None:
"""Return the explicit skill name set declared in an agent's config.yaml.
Semantics:
- ``None`` returned → no agent_id, or config missing — caller should
fall back to "all skills visible".
- ``set()`` (empty) → agent has ``skills: []`` declared — visibility
is intentionally empty.
- Non-empty set → only these names are visible to this agent.
"""
if not agent_id:
return None
try:
from deerflow.config.agents_config import load_agent_config
cfg = load_agent_config(agent_id)
if cfg is None or cfg.skills is None:
return None
return set(cfg.skills)
except Exception:
logger.debug("Failed to load agent config for skill_list filter", exc_info=True)
return None
@tool("skill_view")
def skill_view_tool(name: str) -> str:
"""Read the full SKILL.md content of a skill by name.
@@ -48,21 +97,36 @@ def skill_view_tool(name: str) -> str:
@tool("skill_list")
def skill_list_tool() -> str:
"""List all available skills with metadata and usage stats. Does NOT read SKILL.md content.
def skill_list_tool(runtime: ToolRuntime) -> str:
"""List skills available to this agent, with metadata and usage stats.
Does NOT read SKILL.md content.
Returns a JSON array with fields: name, description, category, enabled, state,
use_count, view_count, patch_count, last_activity_at, pinned, source.
For a **custom agent**, the result is filtered to skills explicitly
declared in the agent's ``.deer-flow/agents/{agent_id}/config.yaml``
under the ``skills:`` field — the agent only sees what it was wired to
use.
For the **default lead agent** (no agent_id in runtime), there is no
per-agent whitelist and every visible skill is returned.
Returns a JSON array with fields: name, description, category, enabled,
state, use_count, view_count, patch_count, last_activity_at, pinned,
source.
"""
from deerflow.skills.storage import get_or_new_skill_storage
from deerflow.skills.usage import all_entries, latest_activity_at
agent_id = _resolve_active_agent_id(runtime)
allowed = _load_agent_skill_whitelist(agent_id)
try:
storage = get_or_new_skill_storage()
skills = storage.load_skills(enabled_only=False)
usage = all_entries()
result = []
for skill in skills:
if allowed is not None and skill.name not in allowed:
continue
entry = usage.get(skill.name, {})
result.append({
"name": skill.name,