github Tencent/WeKnora v0.7.1

6 hours ago

What's Changed

  • feat(chat): add session header actions and Markdown export by @lyingbug in #2109
  • feat(tracing): migrate langfuse client to OTLP/OTel wire protocol by @lordk911 in #2099
  • fix(tracing): merge Langfuse finish metadata and export auto root spans by @lyingbug in #2111
  • style(chat): widen conversation content area from 800px to 960px by @lyingbug in #2114
  • fix(wiki): prevent stale pending tasks after ingest timeout by @014-code in #2106
  • fix: stabilize top-k retrieval ordering by @KKtwo in #2091
  • refactor: remove Neo4j-based conversation memory feature by @lyingbug in #2130
  • feat(web-search): add Zhipu AI web search provider support by @lyingbug in #2115
  • feat(session): add admin API session bucket and stabilize sidebar filter by @lyingbug in #2151
  • fix(frontend): pin nginx base image by digest for old-host compatibility by @lyingbug in #2153
  • fix(api-keys): allow scoped file serve and ingest batch routes by @lyingbug in #2154
  • fix(frontend): load complete TDesign styles by @jacentsao in #2148
  • feat: support Volcengine rerank by @KKtwo in #2147
  • fix(rerank): batch Volcengine rerank requests over API document limit by @lyingbug in #2155
  • feat(session): gate IM/embed/API channel sessions behind admin by @lyingbug in #2156
  • fix(embed): 兼容不支持 crypto.randomUUID 的浏览器以及http请求模式 by @hbh112233abc in #2159
  • fix(types): use correct GORM tag separator in Message.KnowledgeReferences by @steptian in #2157
  • fix(rerank): stop sending vLLM truncate_prompt_tokens by default by @draix in #2160
  • feat(im): add Yunzhijia integration by @jacentsao in #2149
  • feat(compose): align env vars with code + fix helm GraphRAG bug by @Greenplumwine in #2164
  • fix(compose): let PDF render parallelism follow CPU-aware code default by @lyingbug in #2168
  • fix(feishu): resilient large-wiki sync — retry, streaming resume, failure visibility by @voidkey in #2166
  • feat(api-keys): add platform-scoped API keys for control-plane automation by @lyingbug in #2165
  • fix(knowledge): multiset AminusB for KB clone sync by @lyingbug in #2169
  • fix(frontend): keep custom theme tokens in production builds by @lyingbug in #2172
  • feat(im): render Yunzhijia replies as Markdown by @jacentsao in #2180
  • fix(knowledge): rewrite chunk content image URLs on clone by @lyingbug in #2183
  • fix(knowledge): rewrite parent text chunk image URLs via global pass by @lyingbug in #2188
  • fix: 修复IM问答无法读取session的问题 by @wangkeee2002 in #2182
  • fix(cli): repair acceptance e2e for current CLI contracts by @yuefanxiao in #2178
  • fix(knowledge): copy embedded chunk images into exports namespace by @lyingbug in #2191
  • fix(chat): show model reasoning inline in agent timeline by @lyingbug in #2193
  • fix: normalize API key expiry timestamps to UTC (#2137) by @lyingbug in #2171
  • fix(knowledge): stop async delete from leaving visible/zombie rows (#2192) by @lyingbug in #2195
  • fix: correct graph and multimodal processing traces by @ttommybot in #2190
  • feat(wiki): prune empty folders after document retract by @lyingbug in #2196
  • fix(dev): nc 兼容BSD netcat by @hbh112233abc in #2205
  • 修复跨工作空间共享知识库原始文档预览失败 by @chang30519-art in #2200
  • fix(wiki): support orphan count on sqlite by @wolfkill in #2209
  • feat(knowledge): add scoped activity audit trail by @lyingbug in #2198
  • fix(embedding): reuse SSRF-safe HTTP transport by @March-77 in #2201
  • refactor(http): share SSRF-safe transport across model clients by @lyingbug in #2213
  • fix: refresh pending join request counts after review by @ttommybot in #2212
  • fix(search): validate hybrid search query text by @March-77 in #2203
  • fix(tasks): dequeue work for deleted knowledge bases by @March-77 in #2202
  • fix(tasks): detach KB deletion queue cleanup from request ctx by @lyingbug in #2215
  • feat(im): support Yunzhijia WebSocket image messages by @jacentsao in #2214
  • fix(im): harden Yunzhijia image download after #2214 by @lyingbug in #2216
  • fix(task-inspector): handle lazy queue not found errors by @LHYintheCode in #2218
  • fix(mcp): coordinate OAuth token refresh and authorization polling by @lyingbug in #2227
  • fix: prevent API keys from assigning owner role by @ttommybot in #2225
  • docs: clarify workspace owner cardinality by @ttommybot in #2224
  • feat(runtime): bulk purge archived queue tasks and chat_attachment i18n by @lyingbug in #2233
  • feat(llm): add prompt-cache observability and wiki cache-friendly prompts by @lyingbug in #2236
  • feat(chat): show wiki tool results in the references drawer by @lyingbug in #2239
  • fix(models): align model debug upload limit with global MAX_FILE_SIZE by @lyingbug in #2240
  • feat(frontend): polish shared space settings and join preview UI by @lyingbug in #2245
  • feat(frontend): polish organization space UI and share-to-space panels by @lyingbug in #2249
  • fix(knowledge): restrict source file download to Editor and above by @lyingbug in #2250
  • fix: synchronize organization state after writes by @ttommybot in #2268
  • fix(frontend): correct optimistic organization state after review and detail loads by @lyingbug in #2269
  • fix(agent): honor suggested-questions limit parameter by @jack-wang-176 in #2253
  • fix: prevent TDesign textarea autosize crash in org settings popup by @lyingbug in #2271
  • fix(org): disambiguate shared-space terms and tighten invite search by @lyingbug in #2273
  • fix(doris): harden Stream Load HTTP with SSRF-safe client by @lyingbug in #2276
  • fix(wiki): harden slug integrity across ingest and agent write paths by @lyingbug in #2280
  • chore(release): prepare v0.7.1 by @lyingbug in #2286

New Contributors

Full Changelog: v0.7.0...v0.7.1

Don't miss a new WeKnora release

NewReleases is sending notifications on new releases.