fix(ai写作): 技能检索稳定接收数据(复用参考文献提取+截断抢救+上限早停)

- 复用主智能体「参考文献」模式的提取逻辑(deerflow.runtime.references)解析技能JSON,字段并集兼容
- bash输出中间截断时逐条抢救完整记录对象,不再因大JSON解析失败而全丢
- 所有退出路径(超时/递归上限/异常)都从tool输出收割,不依赖模型最终汇总
- 达到max_materials上限即停止驱动模型,修复步骤条爆100+条/素材超额
- 步骤条实时显示每次检索获得多少条数据
- 内网兜底:与技能并行预跑、响应解析兼容两套接口字段、0结果换简单检索词重试、超时放宽到10分钟

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 17:05:09 +08:00
1 parent 893f1e6933
commit 854de9b43c
7 files changed
+340 -162

No files matched your search

@@ -15,6 +15,17 @@ _DEFAULT_KB = "samples"
_RAW_SNIPPET_LIMIT = 2000
def _pick(d: dict, keys: tuple) -> str:
"""从结果项里按候选字段名取第一个非空值(两套接口字段名不同,做并集兼容)。"""
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 ""
class IntranetSearchProvider(BaseSearchProvider):
"""内网知识库搜索接口适配器。
@@ -92,11 +103,17 @@ class IntranetSearchProvider(BaseSearchProvider):
self._record_raw(raw_text)
return []
# 正常情况下接口直接返回数组;兼容个别情况下包了一层 data/results 的结构
# 正常情况下接口直接返回数组;兼容包了一层 data/results 的结构(含工作正常的
# knowledge-search-v2:{"success":true,"results":[...]})。
if isinstance(data, list):
items = data
elif isinstance(data, dict):
items = data.get("data") or data.get("results") or []
# 接口显式标失败时把整体回传前端便于定位
if data.get("success") is False:
self.errors.append(f"接口返回 success=false:{str(data.get('error') or '')[:200]}")
self._record_raw(raw_text)
return []
items = data.get("data") or data.get("results") or data.get("documents") or []
else:
# 返回结构既不是数组也不是已知 dict 包装:视为异常,把原始响应回传前端
logger.warning("intranet search unexpected response type for query=%r: %s", query, type(data).__name__)
@@ -106,18 +123,32 @@ class IntranetSearchProvider(BaseSearchProvider):
results: List[SearchResult] = []
for i, item in enumerate(items[:max_results]):
md = (item or {}).get("metadata") or {}
content = md.get("content") or (item or {}).get("page_content") or ""
if not isinstance(item, dict):
continue
# 字段名做并集兼容两套接口:
# 老 ES: {page_content, metadata:{m_title, content, recUuid, m_publish, source1}}
# knowledge-search-v2:{title, content_preview, url, recUuid, source_category, publish_time, relevance_score}
md = item.get("metadata") if isinstance(item.get("metadata"), dict) else {}
merged = {**md, **item} if md else item
content = _pick(merged, ("content", "content_preview", "page_content", "text", "summary"))
title = _pick(merged, ("title", "m_title", "name", "doc_title"))
if not content and not title:
continue
try:
score = float(merged.get("relevance_score"))
except (TypeError, ValueError):
# 接口未返回相关度分值:按返回顺序赋递减分以保留排序
score = max(0.5, 0.95 - i * 0.03)
results.append(SearchResult(
title=str(md.get("m_title") or "").strip() or "(无标题)",
title=title or "(无标题)",
content=str(content)[:500],
source=str(md.get("source1") or "").strip() or "内网知识库",
published_at=str(md.get("m_publish") or "").strip(),
url="", # 内网素材的原文地址由前端依据 recUuid 拼接
# 接口未返回相关度分值,按 ES 返回顺序赋递减分以保留排序
relevance_score=max(0.5, 0.95 - i * 0.03),
source=_pick(merged, ("source_category", "source1", "source", "source_name", "kb_name")) or "内网知识库",
published_at=_pick(merged, ("publish_time", "m_publish", "published_at", "date")),
# 工作接口直接给了 url;老 ES 没有 url(由前端依据 recUuid 拼接),保持空串
url=_pick(merged, ("url",)),
relevance_score=score,
source_type="intranet",
recUuid=str(md.get("recUuid") or "").strip(),
recUuid=_pick(merged, ("recUuid", "rec_uuid", "id")),
))
return results