Merge remote-tracking branch 'origin/master' into ji

# Conflicts:
#	frontend-web/src/core/page-layout/sidebar-menu.ts
#	frontend-web/src/core/system-settings/api.ts
#	frontend-web/src/core/system-settings/hooks.ts
#	frontend-web/src/strategy-components/Header.tsx
#	offline-backend-20260512/backend/CLAUDE.md
#	offline-backend-20260512/backend/app/gateway/routers/system_settings.py
#	offline-backend-20260512/backend/packages/harness/deerflow/config/system_settings.py
#	offline-backend-20260512/backend/scripts/sql/column_additions_mysql.sql
This commit is contained in:
Administrator committed 2026-06-16 20:01:42 +08:00
commit b380575f16
103 files changed
+5915 -859

No files matched your search

@@ -141,6 +141,30 @@ def _load_configured_skills() -> list:
return resolved or [_fallback_knowledge_skill()]
def _fallback_candidate_skills(tried: set[str]) -> list:
"""容错兜底:从技能目录里挑出**尚未尝试过**的可用技能,内置「知识库检索」优先。
当配置技能调用全部失败、且没收集到任何新素材时,researcher 用这些技能再试一轮,
而不是直接报错。内置知识库检索(原生多关键词并发,最稳)排在最前,其后是技能目录里
其它已启用的技能。技能目录加载失败时只回退内置知识库检索,保证兜底链永不断。
"""
candidates: list = []
seen: set[str] = set(tried)
if KNOWLEDGE_SEARCH_SKILL_NAME not in seen:
candidates.append(_fallback_knowledge_skill())
seen.add(KNOWLEDGE_SEARCH_SKILL_NAME)
try:
from deerflow.skills.storage import get_or_new_skill_storage
for s in get_or_new_skill_storage().load_skills(enabled_only=True):
if getattr(s, "name", None) and s.name not in seen:
candidates.append(s)
seen.add(s.name)
except Exception:
logger.warning("researcher: 兜底加载技能目录失败", exc_info=True)
return candidates
def _resolve_keyword_count(raw: object) -> int:
"""把用户传入的检索关键词数量规整到 [1, _MAX_KEYWORD_COUNT],非法值回退默认 6。"""
try:
@@ -511,24 +535,35 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
added += 1
return added
async def _timed_search(skill_name: str, query: str, limit: int) -> list[SearchResult]:
async def _timed_search(skill_name: str, query: str, limit: int) -> tuple[list[SearchResult], str]:
# 加超时兜底:单个技能检索最多等 _SKILL_SEARCH_TIMEOUT_SECONDS 秒,
# 超时不再阻塞后续技能,避免整段过程看起来"冻结"。
# 返回 (结果, 错误详情):错误详情非空 = 该技能调用失败(触发兜底)。
try:
return await asyncio.wait_for(
results = await asyncio.wait_for(
provider.search(query, max_results=limit),
timeout=_SKILL_SEARCH_TIMEOUT_SECONDS,
) or []
)
return (results or []), ""
except asyncio.TimeoutError:
msg = f"检索超时(>{_SKILL_SEARCH_TIMEOUT_SECONDS}s)"
logger.warning("skill[%s] search timed out after %ss", skill_name, _SKILL_SEARCH_TIMEOUT_SECONDS)
search_errors.append(f"skill[{skill_name}]: 检索超时(>{_SKILL_SEARCH_TIMEOUT_SECONDS}s)")
return []
search_errors.append(f"skill[{skill_name}]: {msg}")
return [], msg
except Exception as e:
logger.warning("skill[%s] search failed: %s", skill_name, e)
search_errors.append(f"skill[{skill_name}]: {e}")
return []
return [], str(e)
for sk in ordered:
def _skill_display(sk) -> str:
return _KNOWLEDGE_SKILL_DISPLAY if sk.name == KNOWLEDGE_SEARCH_SKILL_NAME else sk.name
async def _execute_skill(sk) -> tuple[int, str]:
"""运行单个技能检索,返回 (新增素材数, 错误详情)。
错误详情非空 = 该技能整体调用失败(超时 / 抛异常 / 全部检索词失败),
调用方据此 emit ``skill_error`` 步骤并触发"改用其它技能"的兜底逻辑。
"""
is_knowledge = sk.name == KNOWLEDGE_SEARCH_SKILL_NAME
if is_knowledge and not is_user_query_search:
# 原生知识库检索:对全部检索词并发检索(旧版默认路径)。
@@ -557,13 +592,20 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
gathered = await asyncio.gather(*[_search_one(kw) for kw in search_keywords], return_exceptions=True)
added = 0
errs: list[str] = []
for results in gathered:
if isinstance(results, Exception):
logger.warning("search failed: %s", results)
search_errors.append(f"{type(results).__name__}: {results}")
errs.append(f"{type(results).__name__}: {results}")
continue
added += _collect(results)
search_errors.extend(getattr(provider, "errors", []))
search_errors.extend(errs)
# 全部检索词都抛异常且 0 新增 → 视为该技能整体调用失败,触发兜底
error_detail = ""
if added == 0 and errs and len(errs) == total:
error_detail = ";".join(dict.fromkeys(errs))[:200]
return added, error_detail
else:
# 定向技能检索:user_query 模式优先用用户原话;非知识库技能再
# 附上 description 让 query 贴合该技能的领域。
@@ -576,14 +618,35 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
"message": f"使用技能「{sk.name}」检索:{skill_query[:60]}",
"skill_name": sk.name,
})
added = _collect(await _timed_search(sk.name, skill_query, per_skill))
results, error_detail = await _timed_search(sk.name, skill_query, per_skill)
return _collect(results), error_detail
_emit_skill_step({
"type": "skill_result",
"message": f"技能「{_KNOWLEDGE_SKILL_DISPLAY if is_knowledge else sk.name}」检索到 {added} 条新素材",
"skill_name": sk.name,
"matched_count": added,
})
# 失败技能名(去重后用于兜底提示):记录配置技能里调用失败的那些
failed_skill_names: list[str] = []
tried_names: set[str] = set()
def _emit_skill_outcome(sk, added: int, error_detail: str) -> None:
"""单个技能跑完后,按成功 / 失败 emit 对应步骤事件。"""
if error_detail:
failed_skill_names.append(_skill_display(sk))
_emit_skill_step({
"type": "skill_error",
"message": f"技能「{_skill_display(sk)}」调用失败,尝试使用其他技能检索",
"skill_name": sk.name,
"reason": error_detail,
})
else:
_emit_skill_step({
"type": "skill_result",
"message": f"技能「{_skill_display(sk)}」检索到 {added} 条新素材",
"skill_name": sk.name,
"matched_count": added,
})
for sk in ordered:
added, error_detail = await _execute_skill(sk)
tried_names.add(sk.name)
_emit_skill_outcome(sk, added, error_detail)
# 早停:累积素材已达上限
if len(new_results) >= max_materials:
@@ -594,6 +657,27 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
})
break
# ── 容错兜底:配置技能调用失败且没收集到任何新素材 → 改用其它可用技能继续检索 ──
# (不直接报错;前端时间线靠 skill_error / fallback 步骤展示"技能报错,改用其它技能搜集")
if not new_results and failed_skill_names:
fallback_skills = _fallback_candidate_skills(tried_names)
if fallback_skills:
_emit_skill_step({
"type": "fallback",
"message": (
f"已配置技能({'、'.join(dict.fromkeys(failed_skill_names))})检索失败,"
"改用其他技能继续搜集素材"
),
"skill_names": [_skill_display(s) for s in fallback_skills],
})
for sk in fallback_skills:
added, error_detail = await _execute_skill(sk)
tried_names.add(sk.name)
_emit_skill_outcome(sk, added, error_detail)
if new_results:
# 兜底已拿到素材即止,不再无谓尝试后续技能
break
# 合并去重
# - 首次检索 / 普通 re_search(无输入,用户只想重出):旧素材丢弃,覆盖式替换
# - 素材不足求助 supplement_search:保留旧素材 + 追加新检索结果
@@ -190,6 +190,37 @@ class SkillCompressionSettings(BaseModel):
model_config = ConfigDict(extra="ignore")
class AgentModuleSettings(BaseModel):
"""Admin-configured「按类型聚合」module → selected agent-tag ids.
Keyed by module key (e.g. ``"zzjc"`` / ``"zzxd"``). Each value is the list
of agent **tag ids** whose agents that module's left sidebar shows. A missing
key / empty list means "not configured" — the frontend falls back to showing
all visible agents grouped by tag.
"""
modules: dict[str, list[str]] = Field(
default_factory=dict,
description="module key → selected agent tag ids",
)
model_config = ConfigDict(extra="ignore")
def get_module_tag_ids(settings: AgentModuleSettings, key: str) -> list[str]:
"""Return the configured agent-tag ids for ``key`` (empty when unset)."""
return list(settings.modules.get(key, []))
def set_module_tag_ids(
settings: AgentModuleSettings, key: str, tag_ids: list[str]
) -> AgentModuleSettings:
"""Return a copy with ``key`` set to a de-duplicated, stripped tag-id list."""
cleaned = list(dict.fromkeys([str(t).strip() for t in tag_ids if str(t).strip()]))
modules = dict(settings.modules)
modules[key] = cleaned
return settings.model_copy(update={"modules": modules})
class SystemSettings(BaseModel):
"""Top-level system settings document."""
@@ -200,6 +231,7 @@ class SystemSettings(BaseModel):
citation_display: CitationDisplaySettings = Field(default_factory=CitationDisplaySettings)
leaderboard: LeaderboardSettings = Field(default_factory=LeaderboardSettings)
skill_compression: SkillCompressionSettings = Field(default_factory=SkillCompressionSettings)
agent_modules: AgentModuleSettings = Field(default_factory=AgentModuleSettings)
model_config = ConfigDict(extra="ignore")
@@ -0,0 +1,50 @@
"""Add seat_mode column to roundtable_chains.
Per-chain「默认席位执行模式」: an optional short string (flash/thinking/pro/ultra, see
frontend ``lib/seat-mode.ts``) the user picks in the chain editor. When the chain is
selected into a roundtable discussion the picker defaults to it (still overridable per
run). NULL = unset → callers fall back to the default (pro). VARCHAR(16) on MySQL, plain
String elsewhere — matching ``String(16)`` on ``RoundtableChainRow.seat_mode``.
``create_all`` adds the column for brand-new DBs; the startup ``_ensure_orm_columns_sync``
sweep adds it to already-existing tables (sqlite/mysql/postgres). This revision keeps the
alembic graph consistent with the rest of the chain columns and documents the change.
Revision ID: 20260615_01
Revises: 20260612_01
Create Date: 2026-06-15
"""
from __future__ import annotations
import sqlalchemy as sa
from alembic import op
from sqlalchemy import inspect
revision = "20260615_01"
down_revision = "20260612_01"
branch_labels = None
depends_on = None
def _has_table(table_name: str) -> bool:
inspector = inspect(op.get_bind())
return table_name in inspector.get_table_names()
def _has_column(table_name: str, column_name: str) -> bool:
if not _has_table(table_name):
return False
inspector = inspect(op.get_bind())
return any(col["name"] == column_name for col in inspector.get_columns(table_name))
def upgrade() -> None:
if _has_table("roundtable_chains") and not _has_column("roundtable_chains", "seat_mode"):
op.add_column("roundtable_chains", sa.Column("seat_mode", sa.String(length=16), nullable=True))
def downgrade() -> None:
if _has_column("roundtable_chains", "seat_mode"):
op.drop_column("roundtable_chains", "seat_mode")
@@ -45,6 +45,7 @@ from deerflow.persistence.notifications.model import NotificationRow
from deerflow.persistence.parallel_agent_tasks.model import ParallelAgentTaskRow
from deerflow.persistence.positions.model import PositionRow, PositionTagBindingRow
from deerflow.persistence.recommended_questions.model import RecommendedQuestionRow
from deerflow.persistence.research_templates.model import ResearchTemplateRow
from deerflow.persistence.roundtable_chains.model import RoundtableChainRow
from deerflow.persistence.roundtable_draft_shares.model import RoundtableDraftShareRow
from deerflow.persistence.roundtable_drafts.model import (
@@ -96,6 +97,7 @@ __all__ = [
"PositionRow",
"PositionTagBindingRow",
"RecommendedQuestionRow",
"ResearchTemplateRow",
"RoundtableChainRow",
"RoundtableDraftRow",
"RoundtableDraftShareRow",
@@ -0,0 +1,15 @@
from deerflow.persistence.research_templates.model import ResearchTemplateRow
from deerflow.persistence.research_templates.sql import ResearchTemplateRepository
def make_research_template_store(session_factory) -> ResearchTemplateRepository | None:
if session_factory is None:
return None
return ResearchTemplateRepository(session_factory)
__all__ = [
"ResearchTemplateRow",
"ResearchTemplateRepository",
"make_research_template_store",
]
@@ -0,0 +1,35 @@
"""ORM model for AI writing research templates (课题研究模板).
A research template bundles a set of writing-form presets — article type,
outline, material source, word count, audience, strict mode and a topic/intent —
so a user can one-click pre-fill the whole 课题研究 form. Maintained from the
research-template config page (需求 0616 #5).
"""
from __future__ import annotations
from datetime import UTC, datetime
from sqlalchemy import Boolean, DateTime, Integer, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
class ResearchTemplateRow(Base):
__tablename__ = "ai_writing_research_templates"
id: Mapped[str] = mapped_column(String(64), primary_key=True)
name: Mapped[str] = mapped_column(String(128), nullable=False)
description: Mapped[str | None] = mapped_column(Text, nullable=True)
# 预设字段(点击模板时回填表单)。
article_type_key: Mapped[str | None] = mapped_column(String(64), nullable=True)
outline: Mapped[str | None] = mapped_column(Text, nullable=True)
material_source: Mapped[str] = mapped_column(String(32), nullable=False, default="general")
word_count: Mapped[int] = mapped_column(Integer, nullable=False, default=800)
audience: Mapped[str | None] = mapped_column(String(128), nullable=True)
strict_mode: Mapped[bool] = mapped_column(Boolean, nullable=False, default=False)
topic: Mapped[str | None] = mapped_column(Text, nullable=True)
sort_order: Mapped[int] = mapped_column(Integer, nullable=False, default=0)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=lambda: datetime.now(UTC))
@@ -0,0 +1,221 @@
"""SQLAlchemy-backed research template storage."""
from __future__ import annotations
import uuid
from datetime import UTC, datetime
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession, async_sessionmaker
from deerflow.persistence.research_templates.model import ResearchTemplateRow
_UNSET = object()
# 新机器内置范例模板(表为空时由 seed_defaults() 写入;作为给用户的范例,内容务求规范好用)。
# article_type_key 取自默认文章类型(news/analysis/feature/report,见 20260517_02 迁移)。
DEFAULT_RESEARCH_TEMPLATES: list[dict] = [
{
"name": "网摘",
"description": "汇编近期网络热点信息,分条摘录核心要点并标注来源,快速掌握全貌",
"article_type_key": "news",
"material_source": "general",
"word_count": 1000,
"audience": "关注热点动态的一般读者",
"strict_mode": False,
"topic": (
"围绕【主题】检索并汇编近一周网络上的重要信息与热点动态,"
"逐条摘录核心事实、关键数据与原文出处,帮助读者快速掌握全貌。"
),
"outline": (
"一、热点速览(用一句话清单列出本期要点)\n"
"二、重点摘录\n"
" 1.【事件/话题标题】——核心事实、关键数据、信息来源\n"
" 2.【事件/话题标题】——……\n"
" 3.(按重要性依次罗列)\n"
"三、关联动态与背景补充(串联相关信息、补足来龙去脉)\n"
"四、小结与观察(提炼趋势或值得关注的看点)"
),
"sort_order": 0,
},
{
"name": "周报",
"description": "按周梳理工作进展、数据指标与问题风险,输出结构化周度汇报",
"article_type_key": "report",
"material_source": "general",
"word_count": 1200,
"audience": "团队成员与上级主管",
"strict_mode": True,
"topic": (
"汇总本周【项目/团队】的工作进展,撰写周报:"
"覆盖关键成果、数据指标、问题风险与下周计划,简明、客观、可量化。"
),
"outline": (
"一、本周概览(一句话总结 + 关键指标对比上周)\n"
"二、重点进展\n"
" 1. 已完成事项与成果(结论先行,附支撑数据)\n"
" 2. 关键数据 / 里程碑达成情况\n"
"三、问题与风险(逐条列出问题、影响面及应对措施)\n"
"四、下周计划与资源需求(目标、负责人、所需支持)"
),
"sort_order": 1,
},
{
"name": "要讯",
"description": "提炼最重要的资讯,精炼成简报式要点,突出核心事实与潜在影响",
"article_type_key": "analysis",
"material_source": "general",
"word_count": 600,
"audience": "需快速掌握要点的决策者",
"strict_mode": True,
"topic": (
"围绕【主题/领域】提炼近期最重要的资讯,编写要讯:"
"每条聚焦核心事实、关键背景与潜在影响,文字精炼、判断审慎。"
),
"outline": (
"一、头条要讯(1–3 条,每条用一句话点明核心)\n"
"二、要点详述(逐条展开)\n"
" · 事实:发生了什么、何时何地、涉及谁\n"
" · 背景:为何重要、与既有态势的关系\n"
" · 影响:可能带来的后果与连锁反应\n"
"三、研判与建议(给出倾向性判断与可行动建议)"
),
"sort_order": 2,
},
]
class ResearchTemplateRepository:
def __init__(self, session_factory: async_sessionmaker[AsyncSession]) -> None:
self._sf = session_factory
@staticmethod
def _row_to_dict(row: ResearchTemplateRow) -> dict:
d = row.to_dict()
for k in ("created_at", "updated_at"):
if isinstance(d.get(k), datetime):
d[k] = d[k].isoformat()
return d
async def create(
self,
*,
name: str,
description: str | None = None,
article_type_key: str | None = None,
outline: str | None = None,
material_source: str = "general",
word_count: int = 800,
audience: str | None = None,
strict_mode: bool = False,
topic: str | None = None,
sort_order: int = 0,
) -> dict:
now = datetime.now(UTC)
row = ResearchTemplateRow(
id=str(uuid.uuid4()),
name=name,
description=description,
article_type_key=article_type_key,
outline=outline,
material_source=material_source,
word_count=word_count,
audience=audience,
strict_mode=strict_mode,
topic=topic,
sort_order=sort_order,
created_at=now,
updated_at=now,
)
async with self._sf() as session:
session.add(row)
await session.commit()
await session.refresh(row)
return self._row_to_dict(row)
async def update(
self,
template_id: str,
*,
name=_UNSET,
description=_UNSET,
article_type_key=_UNSET,
outline=_UNSET,
material_source=_UNSET,
word_count=_UNSET,
audience=_UNSET,
strict_mode=_UNSET,
topic=_UNSET,
sort_order=_UNSET,
) -> dict | None:
async with self._sf() as session:
row = await session.get(ResearchTemplateRow, template_id)
if row is None:
return None
if name is not _UNSET:
row.name = name
if description is not _UNSET:
row.description = description
if article_type_key is not _UNSET:
row.article_type_key = article_type_key
if outline is not _UNSET:
row.outline = outline
if material_source is not _UNSET:
row.material_source = material_source
if word_count is not _UNSET:
row.word_count = word_count
if audience is not _UNSET:
row.audience = audience
if strict_mode is not _UNSET:
row.strict_mode = strict_mode
if topic is not _UNSET:
row.topic = topic
if sort_order is not _UNSET:
row.sort_order = sort_order
row.updated_at = datetime.now(UTC)
await session.commit()
await session.refresh(row)
return self._row_to_dict(row)
async def get(self, template_id: str) -> dict | None:
async with self._sf() as session:
row = await session.get(ResearchTemplateRow, template_id)
if row is None:
return None
return self._row_to_dict(row)
async def list(self) -> list[dict]:
stmt = select(ResearchTemplateRow).order_by(
ResearchTemplateRow.sort_order.asc(), ResearchTemplateRow.created_at.asc()
)
async with self._sf() as session:
result = await session.execute(stmt)
return [self._row_to_dict(r) for r in result.scalars()]
async def delete(self, template_id: str) -> bool:
async with self._sf() as session:
row = await session.get(ResearchTemplateRow, template_id)
if row is None:
return False
await session.delete(row)
await session.commit()
return True
async def seed_defaults(self) -> int:
"""新机器/空表时写入内置范例模板(网摘/周报/要讯)。
幂等:仅当表为空时插入;已有任何模板则跳过(避免覆盖用户配置或重复播种)。
返回插入条数。
"""
async with self._sf() as session:
existing = await session.execute(select(ResearchTemplateRow.id).limit(1))
if existing.first() is not None:
return 0
now = datetime.now(UTC)
for t in DEFAULT_RESEARCH_TEMPLATES:
session.add(
ResearchTemplateRow(id=str(uuid.uuid4()), created_at=now, updated_at=now, **t)
)
await session.commit()
return len(DEFAULT_RESEARCH_TEMPLATES)
@@ -49,6 +49,9 @@ class RoundtableChainRow(Base):
# 怎么派活、做什么(整体编排策略 / 风格 / 约束)。**仅分层 DAG 模式生效**:注入到总控
# 每阶段派活提示(``buildDagStageLeaderTask``)。NULL = 不注入。纯文本,存为 LONGTEXT。
coordinator_prompt: Mapped[str | None] = mapped_column(PortableLongText, nullable=True)
# 可选「默认席位执行模式」:flash/thinking/pro/ultra(见前端 lib/seat-mode.ts)。选入研讨时
# 弹窗默认用它(仍可临时改)。NULL = 未设,调用方回退默认(pro)。短串,VARCHAR(16)。
seat_mode: Mapped[str | None] = mapped_column(String(16), nullable=True)
# 发布开关:True = 公共(所有账号可在「公共」筛选里查看 / 选用);False = 仅本人可见。
# 编辑 / 删除始终只限 owner;发布只是放开「查看 + 选入研讨」。索引以支持「公共」列表筛选。
is_public: Mapped[bool] = mapped_column(
@@ -56,6 +56,8 @@ class RoundtableChainRepository:
"stage_goals": _loads(getattr(row, "stage_goals", None)),
# 总控编排提示(写给总控的派活指引,dag-only);None/空 = 不注入。纯文本,不 json。
"coordinator_prompt": getattr(row, "coordinator_prompt", None),
# 默认席位执行模式(flash/thinking/pro/ultra);None = 未设。
"seat_mode": getattr(row, "seat_mode", None),
# 发布状态 + 是否本人所有(前端据此显示「公共」徽标、决定能否编辑 / 发布)。
"is_public": bool(getattr(row, "is_public", False)),
"is_mine": (current_user_id is None) or (row.user_id == current_user_id),
@@ -110,6 +112,7 @@ class RoundtableChainRepository:
stages=_dumps(data.get("stages")),
stage_goals=_dumps(data.get("stage_goals")),
coordinator_prompt=(data.get("coordinator_prompt") or None),
seat_mode=(data.get("seat_mode") or None),
is_public=bool(data.get("is_public") or False),
created_at=now,
updated_at=now,
@@ -131,6 +134,7 @@ class RoundtableChainRepository:
stages=_UNSET,
stage_goals=_UNSET,
coordinator_prompt=_UNSET,
seat_mode=_UNSET,
is_public=_UNSET,
) -> dict[str, Any] | None:
async with self._sf() as session:
@@ -149,6 +153,8 @@ class RoundtableChainRepository:
row.stage_goals = _dumps(stage_goals)
if coordinator_prompt is not _UNSET:
row.coordinator_prompt = coordinator_prompt or None
if seat_mode is not _UNSET:
row.seat_mode = seat_mode or None
if is_public is not _UNSET and is_public is not None:
row.is_public = bool(is_public)
row.updated_at = datetime.now(UTC)