Starstruk Logo MarkStarstruk

v0.5.1

luminal-ai/luminalv0.5.1Apr 30, 2026by lyingbug

AI Summary

This release focuses on enhancing agent capabilities, improving the knowledge base interface, and fixing various bugs including LaTeX rendering and IM session handling.

Key Highlights

  • Added LLM call timeout for agents to prevent hanging.
  • Introduced a WeChat mini program plugin for mobile accessibility.
  • Added document batch delete and list view for the knowledge base.
  • Refactored IM session isolation and adapter factories.
  • Enhanced documentation for Agent Mode and Observability using Langfuse.

New Features

  • LLM call timeout for agents
  • WeChat mini program plugin
  • Knowledge base document batch delete and list view
  • Tenant API Key reset from API Info page
  • Keyword search and user-scoped pinning for sessions

Full Release Notes

## What's Changed
* docs(readme): enhance layout for Agent Mode and Observability sections across multiple languages by @lyingbug in https://github.com/Tencent/WeKnora/pull/1047
* docs(readme): update tracing references from Jaeger to Langfuse across multiple languages by @lyingbug in https://github.com/Tencent/WeKnora/pull/1048
* feat(frontend): add LLM call timeout for agents by @lyingbug in https://github.com/Tencent/WeKnora/pull/1059
* fix(wiki): queue JSON handling and failed ingest operations by @lyingbug in https://github.com/Tencent/WeKnora/pull/1061
* feat(types): support legacy and current formats in tenant Scan by @lyingbug in https://github.com/Tencent/WeKnora/pull/1060
* chore(i18n): align en-US/ko-KR/ru-RU locales with zh-CN by @lyingbug in https://github.com/Tencent/WeKnora/pull/1062
* chore(i18n): align en-US/ko-KR/ru-RU locales with zh-CN by @lyingbug in https://github.com/Tencent/WeKnora/pull/1063
* fix(wiki): Lite ingest lock, failed-op requeue, sync task retry parity by @lyingbug in https://github.com/Tencent/WeKnora/pull/1064
* fix: LaTeX formulas flash and disappear during streaming (#1056) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1065
* fix(container): aggregate registration errors in connector registry initialization by @Goodnight77 in https://github.com/Tencent/WeKnora/pull/1054
* fix(search): align rerank priority between Execute and rerankResults by @lyingbug in https://github.com/Tencent/WeKnora/pull/1067
* fix(im): isolate IM sessions per agent, recover from deleted sessions by @lyingbug in https://github.com/Tencent/WeKnora/pull/1069
* fix(im): remove pipeline-level timeout that kills multi-round agent reasoning by @lyingbug in https://github.com/Tencent/WeKnora/pull/1070
* fix(docreader): remove default 100-page limit for DOCX parsing by @lyingbug in https://github.com/Tencent/WeKnora/pull/1071
* fix: inject KB document listing on fallback for broad queries by @lyingbug in https://github.com/Tencent/WeKnora/pull/1072
* feat: data_analysis sql validation & type processing by @1141520944 in https://github.com/Tencent/WeKnora/pull/1053
* fix(docparser): preserve standalone image uploads from icon filter by @lyingbug in https://github.com/Tencent/WeKnora/pull/1076
* feat(miniprogram): add WeChat mini program plugin by @wolfkill in https://github.com/Tencent/WeKnora/pull/1055
* feat(knowledge-base): add document batch delete and list view by @voidkey in https://github.com/Tencent/WeKnora/pull/1075
* fix(knowledge-base): restore hover feedback on selected list rows by @voidkey in https://github.com/Tencent/WeKnora/pull/1078
* fix(frontend): 知识库文档区布局、批量条与列表/卡片体验 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1080
* fix(chat): stop button behavior and input layout fixes by @lyingbug in https://github.com/Tencent/WeKnora/pull/1083
* fix: prevent API key ciphertext (enc:v1:...) from leaking to the UI by @lyingbug in https://github.com/Tencent/WeKnora/pull/1087
* 客户端添加切换租户 by @cn-kali-team in https://github.com/Tencent/WeKnora/pull/1085
* feat: add STORAGE_ALLOW_LIST env var by @Windfarer in https://github.com/Tencent/WeKnora/pull/1086
* feat(tenant): expose API Key reset from the API Info page by @lyingbug in https://github.com/Tencent/WeKnora/pull/1089
* fix(frontend): polish knowledge list sticky header and floating batch bar by @lyingbug in https://github.com/Tencent/WeKnora/pull/1088
* refactor(im): move adapter factories into per-platform subpackages by @lyingbug in https://github.com/Tencent/WeKnora/pull/1084
* fix:attachment_document_failed by @MaoMengww in https://github.com/Tencent/WeKnora/pull/1094
* refactor(frontend): unify Model/WebSearch/MCP settings pages with shared card + drawer by @lyingbug in https://github.com/Tencent/WeKnora/pull/1093
* fix(frontend): polish KB list sticky header, batch bar, and card checkbox by @lyingbug in https://github.com/Tencent/WeKnora/pull/1090
* fix(frontend): route chat drag-and-drop uploads correctly by @Aphroq in https://github.com/Tencent/WeKnora/pull/1095
* fix(im): rewrite private storage URLs to HTTP in IM channel replies by @lyingbug in https://github.com/Tencent/WeKnora/pull/1068
* fix(crypto): fail loudly when encrypted DB fields cannot be decrypted by @lyingbug in https://github.com/Tencent/WeKnora/pull/1100
* fix(web-search): normalize default tenant web search config at runtime by @sqkstwj in https://github.com/Tencent/WeKnora/pull/1097
* feat(im): tenant-wide IM channels overview under the user menu by @lyingbug in https://github.com/Tencent/WeKnora/pull/1102
* feat(sessions): add keyword search, user-scoped pinning, and IM source visibility by @lyingbug in https://github.com/Tencent/WeKnora/pull/1101

## New Contributors
* @cn-kali-team made their first contribution in https://github.com/Tencent/WeKnora/pull/1085
* @Aphroq made their first contribution in https://github.com/Tencent/WeKnora/pull/1095
* @sqkstwj made their first contribution in https://github.com/Tencent/WeKnora/pull/1097

**Full Changelog**: https://github.com/Tencent/WeKnora/compare/v0.5.0...v0.5.1