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

@@ -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 = {