fix(会商第三步): 流程图入库限 rwfx-A + 修复跳过报告生成流程图出现双调度中卡片

- 入库功能仅 rwfx-A(businessCode 6BF)深链会商模式提供,其它业务深链生成流程图不再出现入库按钮/询问
- 流程图抽取串行化:auto 自动出图与用户「跳过报告直接生成流程图」手动出图竞态时,先中止上一轮、复用/移除被取代气泡,保证任意时刻只有一张流程图卡片

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
fengxiangdebaoziandClaude Opus 4.8 committed 2026-06-25 12:29:45 +08:00
1 parent 04e6d0aa00
commit 893f1e6933
19 files changed
+559 -51

No files matched your search

@@ -53,19 +53,135 @@ def use_skill_search_agent() -> bool:
_REAL_AGENT_MAX_TURNS = 16
# 真实智能体跑技能:整段运行(读 SKILL.md + 多轮工具调用)的超时上限,**硬编码 5 分钟**。
# 内网检索很慢、技能常做多次检索,单次直连检索的 120s 不够整段用;这里写死,不依赖 env
# (部署方不一定会配环境变量),保证内网慢检索至少有 5 分钟才被切断。
# 内网检索很慢、技能常做多次检索,单次直连检索的 120s 不够整段用;5 分钟足够整段跑完
# (含模型对超时检索词自行换简单词重试),不依赖 env(部署方不一定会配环境变量)。
_REAL_AGENT_TIMEOUT_SECONDS = 300
_MATERIAL_OUTPUT_CONTRACT = (
"你的任务:严格按上面挂载的检索技能(SKILL.md)的说明,用相应工具检索与「写作意图」相关的**真实素材**。\n"
"- 必须按技能说明实际调用工具完成检索(读取知识库文件 / 调用内网检索接口 / MCP 等),**不得凭记忆编造**。\n"
"- **某个检索词返回 0 条或报「请求超时」时,不要就此放弃**:请把它换成更核心、更简短的检索词再试一次"
"(去掉「竞选/诉讼/政策/动向」等话题后缀,只保留核心实体,例如「特朗普竞选」→「特朗普」、"
"「特朗普法律诉讼」→「特朗普」;多词时只留最关键的那个词)。\n"
"- **只要有任何检索词成功拿到了数据,就必须把这些数据全部收下并输出**,绝不能因为别的检索词没出结果/超时就丢弃已经检索到的素材。\n"
"- 检索完成后,**只输出一个 JSON 对象**(不要解释、不要 markdown 代码块、用英文双引号),把检索到的真实素材列出:\n"
'{"materials": [{"title": "标题", "content": "素材正文摘录(尽量保留原文, <=500字)", "source": "来源", "url": "原文链接(可空)", "published_at": "日期(可空)"}]}\n'
"- content 必须来自检索到的真实内容;若确实没检索到任何素材,输出 {\"materials\": []}。"
"- content 必须来自检索到的真实内容;只有当**所有**检索词(含简化后重试)都没拿到任何素材时,才输出 {\"materials\": []}。"
)
# 技能 stdout 里「结果列表」常见的字段名(不同技能各异,做并集兼容)
_RESULT_LIST_KEYS = ("results", "data", "items", "materials", "documents", "list", "hits")
_TITLE_KEYS = ("title", "m_title", "name", "doc_title")
_CONTENT_KEYS = ("content", "content_preview", "page_content", "text", "summary", "abstract")
_SOURCE_KEYS = ("source", "source_category", "source1", "source_name", "kb_name")
_DATE_KEYS = ("publish_time", "published_at", "m_publish", "date", "create_time")
def _try_load_json(text: str):
"""尽量从技能 stdout 解析出 JSON:先整体 loads,失败再截取首个平衡的 {…}/[…]。
技能脚本的输出常带尾巴(如 ``...}\n\nExit Code: 1``),整体 loads 会失败,故再用
「首个左括号 → 最后一个对应右括号」截取主体重试。
"""
import json as _json
text = (text or "").strip()
if not text:
return None
try:
return _json.loads(text)
except Exception: # noqa: BLE001
pass
for open_c, close_c in (("{", "}"), ("[", "]")):
start = text.find(open_c)
end = text.rfind(close_c)
if 0 <= start < end:
try:
return _json.loads(text[start : end + 1])
except Exception: # noqa: BLE001
continue
return None
def _extract_result_items(obj) -> list:
"""从解析出的 JSON 里取「结果数组」:顶层就是数组则直接用,否则按常见字段名找。"""
if isinstance(obj, list):
return obj
if isinstance(obj, dict):
for key in _RESULT_LIST_KEYS:
v = obj.get(key)
if isinstance(v, list):
return v
return []
def _pick(d: dict, keys: tuple) -> str:
for k in keys:
v = d.get(k)
if isinstance(v, str) and v.strip():
return v.strip()
if v not in (None, "") and not isinstance(v, (dict, list)):
return str(v).strip()
return ""
def _harvest_tool_results(tool_outputs: list, skill_name: str, limit: int) -> list:
"""**直接从技能 stdout 收割真实检索结果**(不依赖模型最后的 JSON 汇总)。
关键容错:一次写作会对同一技能跑多个检索词,部分检索词可能超时(``success:false``),
但成功的那些(``success:true``)拿回的真实数据**必须照单全收**,不能因为别的检索词没出
数据就整段丢弃。本函数逐条解析技能输出、跳过 ``success:false`` 的、把结果数组映射成
SearchResult,按 url/recUuid/title 去重,截断到 limit。字段名做并集兼容(适配 knowledge-
search-v2 的 ``{success,query,count,results:[{recUuid,title,url,content_preview,...}]}``
及内网 ES 的 ``{m_title,content,recUuid,...}`` 等多种技能输出)。
"""
from ..search.base import SearchResult
harvested: list = []
seen: set[str] = set()
for raw in tool_outputs:
obj = _try_load_json(raw)
if obj is None:
continue
# 明确标记失败的(超时 / 报错)跳过,但不影响其它成功的输出
if isinstance(obj, dict) and obj.get("success") is False:
continue
for it in _extract_result_items(obj):
if not isinstance(it, dict):
continue
# 内网 ES 风格:真实字段藏在 metadata 里
md = it.get("metadata") if isinstance(it.get("metadata"), dict) else {}
merged = {**md, **it} if md else it
content = _pick(merged, _CONTENT_KEYS)
title = _pick(merged, _TITLE_KEYS)
if not content and not title:
continue
url = _pick(merged, ("url",))
rec = _pick(merged, ("recUuid", "rec_uuid", "id"))
key = url or rec or title
if key in seen:
continue
seen.add(key)
try:
score = float(merged.get("relevance_score") or 0.0)
except (TypeError, ValueError):
score = 0.0
harvested.append(SearchResult(
title=title or "(无标题)",
content=content[:500],
source=_pick(merged, _SOURCE_KEYS) or skill_name,
published_at=_pick(merged, _DATE_KEYS),
url=url,
relevance_score=score or 0.75,
source_type="skill",
recUuid=rec,
))
if len(harvested) >= limit:
return harvested
return harvested
def _summarize_tool_args(args: dict) -> str:
"""把工具调用参数压成一句简短摘要,放进步骤条文案(取最能代表本次调用的字段)。"""
if isinstance(args, dict):
@@ -102,7 +218,7 @@ async def run_skill_via_real_agent(
SearchResult。返回 ``(results, error_detail)``:results 为空且 error 非空 = 该技能失败
(researcher 据此回退直连检索)。
"""
from langchain_core.messages import AIMessage
from langchain_core.messages import AIMessage, ToolMessage
from deerflow.config import get_app_config
from deerflow.subagents.config import SubagentConfig
@@ -206,6 +322,9 @@ async def run_skill_via_real_agent(
# 这样 custom 事件能被 LangGraph **实时**刷给前端 SSE;若在嵌套 astream 里直接 emit,
# 事件会被攒到整段跑完才一次性吐出(后端在跑、前端却一直 loading)。
final_text = ""
# 技能每次工具调用的 stdout(如 search.py 打印的 {success,results} JSON),用于**直接收割**
# 真实检索结果,不依赖模型最后是否把它们汇总进 {materials}。
tool_outputs: list[str] = []
seen_msg_ids: set[str] = set()
step_queue: asyncio.Queue = asyncio.Queue()
@@ -229,6 +348,10 @@ async def run_skill_via_real_agent(
text = _content_to_text(m.content)
if text.strip():
final_text = text
elif isinstance(m, ToolMessage):
out = _content_to_text(m.content)
if out.strip():
tool_outputs.append(out)
finally:
step_queue.put_nowait(None) # sentinel:跑完/出错都让 pump 收尾
@@ -255,29 +378,45 @@ async def run_skill_via_real_agent(
logger.warning("skill real-agent[%s]: astream failed: %s", skill_name, e, exc_info=True)
return [], f"技能检索失败: {e}"
# 1) 模型最终汇总的 materials(它可能已按相关度筛选/去重)
model_results: list = []
parsed = parse_json(final_text or "", {"materials": []})
raw_materials = parsed.get("materials")
if not isinstance(raw_materials, list):
return [], ""
if isinstance(raw_materials, list):
for m in raw_materials:
if not isinstance(m, dict):
continue
content = str(m.get("content") or "").strip()
title = str(m.get("title") or "").strip()
if not content and not title:
continue
model_results.append(SearchResult(
title=title or "(无标题)",
content=content[:500],
source=str(m.get("source") or skill_name).strip() or skill_name,
published_at=str(m.get("published_at") or "").strip(),
url=str(m.get("url") or "").strip(),
relevance_score=0.8,
source_type="skill",
))
results: list = []
for m in raw_materials[:max_results]:
if not isinstance(m, dict):
# 2) **直接从技能 stdout 收割真实检索结果**——哪怕模型最后没汇总、或别的检索词超时,
# 成功检索词拿回的数据也照单全收(用户诉求:拿到的数据必须接收,不能整段丢)。
harvested = _harvest_tool_results(tool_outputs, skill_name, max_results)
# 3) 合并去重(模型汇总优先、技能原始结果补齐),按 url/recUuid/title 去重,截断到上限。
merged: list = []
seen_keys: set[str] = set()
for r in model_results + harvested:
key = (r.url or "").strip() or (r.recUuid or "").strip() or (r.title or "").strip()
if key and key in seen_keys:
continue
content = str(m.get("content") or "").strip()
title = str(m.get("title") or "").strip()
if not content and not title:
continue
results.append(SearchResult(
title=title or "(无标题)",
content=content[:500],
source=str(m.get("source") or skill_name).strip() or skill_name,
published_at=str(m.get("published_at") or "").strip(),
url=str(m.get("url") or "").strip(),
relevance_score=0.8,
source_type="skill",
))
return results, ""
if key:
seen_keys.add(key)
merged.append(r)
if len(merged) >= max_results:
break
return merged, ""
def _read_skill_body(skill) -> str:
@@ -818,6 +818,9 @@ async def researcher_node(state: AIWritingState, config: RunnableConfig) -> dict
intranet = IntranetSearchProvider(
base_url=intranet_url,
knowledge_base_name=ai_writing_config.get("intranet_knowledge_base", "samples"),
# 兜底接口超时可在 config.yaml 的 ai_writing.intranet_search_timeout 调大,
# 默认 600s(10 分钟),给内网慢检索留足时间。
timeout=ai_writing_config.get("intranet_search_timeout", 600),
)
fb_keywords = keywords[:keyword_count] or [intent]
fb_gathered = await asyncio.gather(
@@ -1,7 +1,51 @@
import re
from abc import ABC, abstractmethod
from dataclasses import dataclass, field
from typing import List
# 复合检索词里常见的「话题/类别后缀」——核心实体后面跟的修饰词。内网 ES 对
# 「实体+话题」这类长词常检不出(如「特朗普竞选」0 条),但「实体」本身能检出
# (「特朗普」30 条)。剥掉这些后缀回退到核心实体重试,能救回大量检索词。
_TOPIC_SUFFIXES = (
"竞选", "诉讼", "法律", "政策", "主张", "纲领", "动向", "动态", "影响", "分析",
"进展", "现状", "情况", "问题", "事件", "活动", "关系", "布局", "态势", "格局",
"趋势", "背景", "历史", "观点", "评价", "报道", "新闻", "研究", "报告", "概况",
"走势", "前景", "措施", "方案", "计划", "战略", "改革", "发展",
)
def simplify_query(query: str) -> str:
"""把一个「检不出」的复合检索词简化成更核心、更短的检索词,供 0 结果时重试。
规则(无需大模型,纯启发式):
1. 多词(含空格)→ 取第一个词(通常是核心实体),如「美国政局 特朗普」→「美国政局」;
2. 单词复合 → 反复剥掉结尾的话题后缀,保留核心实体,如「特朗普法律诉讼」→「特朗普」、
「特朗普竞选」→「特朗普」。
返回空串 = 无法进一步简化(调用方据此不再重试,避免空转)。
"""
s = (query or "").strip()
if not s:
return ""
# 1) 多词:取第一个词
if re.search(r"\s", s):
first = re.split(r"\s+", s)[0].strip()
if first and first != s and len(first) >= 2:
return first
# 2) 单词复合:循环剥离结尾话题后缀
changed = s
while True:
stripped = changed
for suf in sorted(_TOPIC_SUFFIXES, key=len, reverse=True):
if stripped.endswith(suf) and len(stripped) - len(suf) >= 2:
stripped = stripped[: -len(suf)]
break
if stripped == changed:
break
changed = stripped
if changed != s and len(changed) >= 2:
return changed
return ""
@dataclass
class SearchResult:
@@ -4,7 +4,7 @@ from __future__ import annotations
import logging
from typing import List
from .base import BaseSearchProvider, SearchResult
from .base import BaseSearchProvider, SearchResult, simplify_query
logger = logging.getLogger(__name__)
@@ -27,13 +27,17 @@ class IntranetSearchProvider(BaseSearchProvider):
self,
base_url: str = "",
knowledge_base_name: str = _DEFAULT_KB,
timeout: int = 300,
timeout: int = 600,
**_ignored,
):
self.endpoint = base_url or _DEFAULT_ENDPOINT
self.knowledge_base_name = knowledge_base_name or _DEFAULT_KB
# 内网 ES 接口很慢,超时硬编码放宽到 5 分钟(不依赖 env 配置)
self.timeout = timeout
# 内网 ES 接口很慢,兜底检索超时放宽到 10 分钟(不依赖 env 配置);构造方可传更大值覆盖。
# 「咱们先把自己的做好」:我方兜底超时给足,避免因我方过早超时被甩锅成「检不出」。
try:
self.timeout = max(int(timeout), 1)
except (TypeError, ValueError):
self.timeout = 600
# 收集本次运行的检索异常,供 researcher 节点取出并提示用户(ES 波动等)
self.errors: list[str] = []
# 解析失败时收集的原始响应体,供前端「错误返回结果」折叠展示
@@ -49,6 +53,17 @@ class IntranetSearchProvider(BaseSearchProvider):
self.raw_responses.append(body)
async def search(self, query: str, max_results: int = 5, **kwargs) -> List[SearchResult]:
results = await self._search_once(query, max_results)
# 0 结果兜底:复合检索词常检不出(如「特朗普竞选」),换成更核心的检索词重试一次
# (「特朗普竞选」→「特朗普」)。仅在首检为空、且能简化出不同的词时才重试。
if not results:
simpler = simplify_query(query)
if simpler and simpler != query:
logger.info("intranet search empty for %r, retry with simplified %r", query, simpler)
results = await self._search_once(simpler, max_results)
return results
async def _search_once(self, query: str, max_results: int = 5) -> List[SearchResult]:
import httpx
payload = {
@@ -0,0 +1,52 @@
"""Add login_params_json column to task_buttons.
按钮管理「外部链接」按钮新增「追加登录参数」能力(与应用管理一致):``url`` 外链在
拼好地址后,可再依次追加 ``?{key}={value}``,``value`` 由前端运行时从 ``userInfo``
按 ``source`` 解析(``other`` 时取字面 ``custom_value``)。整列以 JSON 存一个
``[{key, source, custom_value}, ...]`` 列表,默认空 → 旧按钮行为不变。
ORM: ``TaskButtonRow.login_params_json = PortableJSON()``(SQLite/PG 原生 JSON,
MySQL 落 TEXT)。``create_all`` 给全新库建列;已有库由启动期
``_ensure_orm_columns_sync`` 补列。本 revision 保持 alembic 图一致并留档。
Revision ID: 20260625_01
Revises: 20260620_02
Create Date: 2026-06-25
"""
from __future__ import annotations
import sqlalchemy as sa
from alembic import op
from sqlalchemy import inspect
revision = "20260625_01"
down_revision = "20260620_02"
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("task_buttons") and not _has_column("task_buttons", "login_params_json"):
op.add_column(
"task_buttons",
sa.Column("login_params_json", sa.Text(), nullable=True),
)
def downgrade() -> None:
if _has_column("task_buttons", "login_params_json"):
op.drop_column("task_buttons", "login_params_json")
@@ -19,6 +19,7 @@ def _normalize(data: dict[str, Any], updated_by: str | None) -> dict[str, Any]:
"id_param": str(data.get("id_param") or "id"),
"id_kind": str(data.get("id_kind") or "task"),
"open_mode": str(data.get("open_mode") or "blank"),
"login_params": list(data.get("login_params") or []),
"enabled": bool(data.get("enabled", True)),
"sort_order": int(data.get("sort_order", 0)),
"updated_by": updated_by,
@@ -29,7 +29,7 @@ from sqlalchemy import Boolean, Integer, String
from sqlalchemy.orm import Mapped, mapped_column
from deerflow.persistence.base import Base
from deerflow.persistence.types import BeijingDateTime
from deerflow.persistence.types import BeijingDateTime, PortableJSON
class TaskButtonRow(Base):
@@ -48,6 +48,11 @@ class TaskButtonRow(Base):
id_kind: Mapped[str | None] = mapped_column(String(16), default="task")
# ``url`` 外链打开方式:``blank``=新窗口(默认)/ ``self``=当前窗口。可空,读时归一化为 ``blank``。
open_mode: Mapped[str | None] = mapped_column(String(16), default="blank")
# ``url`` 外链追加的登录参数(与应用管理一致):在拼好的地址后再依次追加
# ``?{key}={value}``,``value`` 由前端运行时从 ``userInfo`` 按 ``source`` 解析
# (``other`` 时取 ``custom_value`` 字面值)。每项 ``{key, source, custom_value}``。
# 旧行 / NULL 读时归一化为 ``[]``。
login_params_json: Mapped[list] = mapped_column(PortableJSON(), default=list)
enabled: Mapped[bool] = mapped_column(Boolean, default=True)
sort_order: Mapped[int] = mapped_column(Integer, default=0)
updated_by: Mapped[str | None] = mapped_column(String(64))
@@ -21,6 +21,8 @@ def _to_dict(row: TaskButtonRow) -> dict[str, Any]:
data["id_param"] = data.get("id_param") or "id"
data["id_kind"] = data.get("id_kind") or "task"
data["open_mode"] = data.get("open_mode") or "blank"
# JSON 列改名 login_params_json → login_params;旧行 / NULL 归一化为 []。
data["login_params"] = data.pop("login_params_json", None) or []
return data
@@ -35,6 +37,7 @@ def _row_from(data: dict[str, Any], updated_by: str | None) -> TaskButtonRow:
id_param=str(data.get("id_param") or "id"),
id_kind=str(data.get("id_kind") or "task"),
open_mode=str(data.get("open_mode") or "blank"),
login_params_json=list(data.get("login_params") or []),
enabled=bool(data.get("enabled", True)),
sort_order=int(data.get("sort_order", 0)),
updated_by=updated_by,