WeKnora - Browse /v0.9.0 at SourceForge.net

The interactive file manager requires Javascript. Please enable it or use sftp or scp.
You may still browse the files here.

Name	Modified	Size	InfoDownloads / Week
Parent folder
README.md	2026-10-29	44.2 kB	0
v0.9.0 source code.tar.gz	2026-10-29	117.7 MB	0
v0.9.0 source code.zip	2026-10-29	121.1 MB	0
Totals: 3 Items		238.9 MB	0

What's Changed

fix(docs): stabilize anchor navigation and link release topics by @lyingbug in https://github.com/Tencent/WeKnora/pull/4287
feat(agent): persist human-in-the-loop prompts with a shared broker by @lyingbug in https://github.com/Tencent/WeKnora/pull/4250
feat(search): add RRF controls in a tabbed settings popover by @lyingbug in https://github.com/Tencent/WeKnora/pull/4300
docs(swagger): document the real request and response types by @lyingbug in https://github.com/Tencent/WeKnora/pull/4304
feat(agent): add the built-in WeKnora assistant with an operation catalog by @lyingbug in https://github.com/Tencent/WeKnora/pull/4302
feat(agent): let the WeKnora assistant read the bundled documentation by @lyingbug in https://github.com/Tencent/WeKnora/pull/4303
fix(ui): compact resource list headers in Lite mode by @lyingbug in https://github.com/Tencent/WeKnora/pull/4316
fix(agent): admit catalog operations only from knowledge API areas by @lyingbug in https://github.com/Tencent/WeKnora/pull/4317
fix(agent): let the WeKnora assistant search without its own rerank model by @lyingbug in https://github.com/Tencent/WeKnora/pull/4315
feat(frontend): open the WeKnora assistant from anywhere with page context by @lyingbug in https://github.com/Tencent/WeKnora/pull/4314
feat(agent): open more workspace operations to the WeKnora assistant by @lyingbug in https://github.com/Tencent/WeKnora/pull/4318
feat(agent): let the assistant delete and move documents in batches by @lyingbug in https://github.com/Tencent/WeKnora/pull/4319
docs(site): add the model leaderboard page by @begoniezhao in https://github.com/Tencent/WeKnora/pull/4333
feat(agent): let the assistant manage FAQ entries by @lyingbug in https://github.com/Tencent/WeKnora/pull/4327
feat(assistant): side panel, access levels and role-aware operations by @lyingbug in https://github.com/Tencent/WeKnora/pull/4342
feat(assistant): manage agents and skills, separate history, refresh pages by @lyingbug in https://github.com/Tencent/WeKnora/pull/4344
fix(assistant): reject restored ordinary sessions by @hahahahahayesyeseys in https://github.com/Tencent/WeKnora/pull/4356
feat(assistant): let the assistant manage knowledge bases by @lyingbug in https://github.com/Tencent/WeKnora/pull/4353
refactor(image): turn the hard-coded image flow into configurable pipelines by @tayadwx in https://github.com/Tencent/WeKnora/pull/3746
feat(datasource): deep-adapt Feishu/Lark sync with folder mirror, block parsing and embedded objects by @Greenplumwine in https://github.com/Tencent/WeKnora/pull/3497
fix(im): cap IM callback bodies before any adapter reads them by @Tong-bit-art in https://github.com/Tencent/WeKnora/pull/4369
fix(web-search): bound provider response bodies instead of buffering them whole by @Tong-bit-art in https://github.com/Tencent/WeKnora/pull/4370
fix(mcp): avoid replaying tools after ambiguous call failures by @Guo-Yixin in https://github.com/Tencent/WeKnora/pull/4124
fix(embedding): read the pool's first-error guard under its own mutex by @Tong-bit-art in https://github.com/Tencent/WeKnora/pull/4014
fix(chat): persist failed quick-answer turns so errors survive refresh by @AstonKrss in https://github.com/Tencent/WeKnora/pull/4306
fix(data-analysis): resolve workspace storage backends in quick answers by @kerthans in https://github.com/Tencent/WeKnora/pull/4214
fix(mcp): separate SSE connection lifetime from request timeouts by @yeliheng-010 in https://github.com/Tencent/WeKnora/pull/4140
fix(docparser): bound MinerU result packages and their expansion by @Tong-bit-art in https://github.com/Tencent/WeKnora/pull/4396
fix(embed): hide host context in user messages by @LuckVd in https://github.com/Tencent/WeKnora/pull/4388
fix(embed): send images when an OpenAI-compatible row declares them by @JSJ189 in https://github.com/Tencent/WeKnora/pull/4389
fix(models/api): cap non-streaming provider response bodies by @Tong-bit-art in https://github.com/Tencent/WeKnora/pull/4397
fix(tools): reject legacy binary .xls with an actionable error by @Jay0130-a in https://github.com/Tencent/WeKnora/pull/4374
build(docker): mount the Go build cache when building the app image by @tayadwx in https://github.com/Tencent/WeKnora/pull/4320
feat(assistant): trial runs, session grants, page links, and MCP/model/skill management by @lyingbug in https://github.com/Tencent/WeKnora/pull/4375
fix(frontend): cap concurrent status requests in upload polling by @ignity21 in https://github.com/Tencent/WeKnora/pull/4348
fix(frontend): label the parser engine the backend will actually pick by @NIU-123370 in https://github.com/Tencent/WeKnora/pull/4354
fix(knowledge): leave the root span open while a retry is left by @NIU-123370 in https://github.com/Tencent/WeKnora/pull/4357
feat(assistant): expand management operations and polish interaction UI by @lyingbug in https://github.com/Tencent/WeKnora/pull/4427
feat(assistant): let the assistant find skills and MCP services on the web by @lyingbug in https://github.com/Tencent/WeKnora/pull/4429
fix(anydoc): upgrade patched zip dependency to 9 by @lyingbug in https://github.com/Tencent/WeKnora/pull/4437
fix(docreader): keep a pipe inside an HTML table cell in that cell by @L4XB in https://github.com/Tencent/WeKnora/pull/4433
fix(agent): share one configurable budget for web_fetch by @Frank-zhu2000 in https://github.com/Tencent/WeKnora/pull/4432
fix(docparser): keep JSON numbers and <, >, & as written in JSON uploads by @L4XB in https://github.com/Tencent/WeKnora/pull/4436
fix(knowledge): 文件夹树显示递归文档数，不再把有子目录的文件夹显示成 0 by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4428
fix(chat): 消息历史与搜索的 limit 补上下界，limit=-1 不再取消 SQL LIMIT by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4409
fix(wiki): 列 wiki 页面的 page_size 补上界，与兄弟路径一致 by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4407
fix(models): 图片解析复用仓储层的 provider scheme 表，对象存储上的图片不再原样交给厂商 by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4405
fix(mcp): clarify read_document query and pagination semantics by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4403
fix(search): preserve chunk types in tool results by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4402
fix(feishu): keep nested text in native table cells by @davien in https://github.com/Tencent/WeKnora/pull/4400
feat(graph): add standalone JSON graph search API by @ZXLyyds100 in https://github.com/Tencent/WeKnora/pull/4395
fix(docparser): keep every row and cell of a CSV upload in its table by @L4XB in https://github.com/Tencent/WeKnora/pull/4435
fix(wiki): read scanned-page OCR when the text chunks are only images by @wangrui19971019 in https://github.com/Tencent/WeKnora/pull/4430
feat(resource): 相同图片字节复用一个 handle，不再重复写字节与重复注册 by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4419
fix(docreader): Excel 百分比被读小 100 倍 —— 加开关（默认关） by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4423
fix(helm): make the data-files claim access modes configurable by @Jay0130-a in https://github.com/Tencent/WeKnora/pull/4425
feat(datasource/dingtalk): 保留来源目录结构（开关控制，默认关） by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4422
fix(datasource/dingtalk): Validate 只校验所选范围，不再扫全租户 by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4421
fix(datasource): 数据源类型图标的 alt 用本地化显示名，不再用裸 type by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4420
fix(yuque): 两处 offset 分页补跳数上限、重复页检测与 meta.total 提前结束 by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4415
fix(notion): 附件下载失败中止本轮不再推进游标，附件不再永久缺失 by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4413
fix(notion): 递归子块分页补重复游标与跳数上限，兜底不再被空页绕过 by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4411
test(mcp): cover read_document query and pagination contract by @Activer007 in https://github.com/Tencent/WeKnora/pull/4426
fix(frontend): bundle PDF.js wasm decoders by @LuckVd in https://github.com/Tencent/WeKnora/pull/4382
feat(docreader): 上传 HTML 只索引正文，与 URL 导入路径对齐（开关，默认关） by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4424
fix(feishu): stop logging tenant access token fragments by @davien in https://github.com/Tencent/WeKnora/pull/4399
feat(assistant): add durable multi-agent collaboration and live task views by @lyingbug in https://github.com/Tencent/WeKnora/pull/4438
fix(agent): let open_page finish the turn with the answer above it by @lyingbug in https://github.com/Tencent/WeKnora/pull/4472
style(assistant): tone down the running child agent highlight by @lyingbug in https://github.com/Tencent/WeKnora/pull/4476
fix: reject invalid image inputs before multimodal extraction by @lyingbug in https://github.com/Tencent/WeKnora/pull/4489
feat(agent): unified agent permission model with grants and run modes by @lyingbug in https://github.com/Tencent/WeKnora/pull/4490
fix: preserve business session identity in model requests by @lyingbug in https://github.com/Tencent/WeKnora/pull/4491
feat(chat): fold long streaming timelines and steady their height by @lyingbug in https://github.com/Tencent/WeKnora/pull/4496
feat(automation): scheduled agent runs with in-app notifications by @lyingbug in https://github.com/Tencent/WeKnora/pull/4492
feat(sandbox): 双模式沙箱分配的基础（门控关闭，线上行为不变） by @nullptr-error in https://github.com/Tencent/WeKnora/pull/4507
fix(automation): enforce execution identity, cancellation, and scheduling limits by @lyingbug in https://github.com/Tencent/WeKnora/pull/4506
feat(sandbox): 按分配记录定位共享沙箱（门控仍关闭） by @nullptr-error in https://github.com/Tencent/WeKnora/pull/4509
feat(sandbox): 共享机器的用户模式闭环（删除、回收、管理与桌面） by @nullptr-error in https://github.com/Tencent/WeKnora/pull/4510
feat(automation): improve model settings, task controls, and notification inbox by @lyingbug in https://github.com/Tencent/WeKnora/pull/4514
fix(agent): route new knowledge through document ingestion by @lyingbug in https://github.com/Tencent/WeKnora/pull/4525
refactor(automation): run scheduled tasks through the assistant by @lyingbug in https://github.com/Tencent/WeKnora/pull/4522
fix: preserve source references and refine chat automation UI by @lyingbug in https://github.com/Tencent/WeKnora/pull/4534
feat(chat): animate active timeline icons by @lyingbug in https://github.com/Tencent/WeKnora/pull/4535
fix(settings): keep direct settings closes inside the app by @jiangjiang248 in https://github.com/Tencent/WeKnora/pull/4524
feat(sandbox): 共享沙箱短会话目录 + 移除工具层目录限制 by @nullptr-error in https://github.com/Tencent/WeKnora/pull/4533
fix(mcp): invalidate stale OAuth dialog requests by @dakjdakd in https://github.com/Tencent/WeKnora/pull/4531
perf(sourceloc): index align matches in one document scan by @sun-sh in https://github.com/Tencent/WeKnora/pull/4544
fix(auth): let retrieve-scoped API keys discover shared knowledge bases by @u7-u7 in https://github.com/Tencent/WeKnora/pull/4523
fix(datasource): enforce sync log retention policies by @dakjdakd in https://github.com/Tencent/WeKnora/pull/4532
fix(qa): resolve shared KB chat models in their owner tenant by @lyingbug in https://github.com/Tencent/WeKnora/pull/4557
fix(web_fetch): decode non-UTF-8 HTML pages by declared charset by @kerthans in https://github.com/Tencent/WeKnora/pull/4556
fix(db): stop logging bound parameters in GORM slow-query logs by @Frank-zhu2000 in https://github.com/Tencent/WeKnora/pull/4561
fix(export): sort conversation messages by timestamp instants by @fengyue-xve in https://github.com/Tencent/WeKnora/pull/4559
fix(citations): match canonically equivalent Unicode text by @fengyue-xve in https://github.com/Tencent/WeKnora/pull/4560
fix(datasource): truncate failed sync detail at rune boundary by @kerthans in https://github.com/Tencent/WeKnora/pull/4555
fix(router): truncate dead-letter knowledge errors at rune boundary by @kerthans in https://github.com/Tencent/WeKnora/pull/4554
fix(agent): show legacy empty MCP config as all in editor by @wzxsdf in https://github.com/Tencent/WeKnora/pull/4558
fix(automation): reject nonexistent one-shot local times by @fengyue-xve in https://github.com/Tencent/WeKnora/pull/4551
feat(confluence): support personal access token authentication by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4549
fix(rerank): preserve literal fenced code in model passages by @mmhh256 in https://github.com/Tencent/WeKnora/pull/4521
fix(rerank): accept bare array responses from self-hosted runtimes by @u7-u7 in https://github.com/Tencent/WeKnora/pull/4518
fix(download): honor language tags in extended filenames by @fengyue-xve in https://github.com/Tencent/WeKnora/pull/4517
fix(preview): distinguish image and audio ISO media brands by @fengyue-xve in https://github.com/Tencent/WeKnora/pull/4515
fix(postgres): 兼容 pgsearch 关键词评分函数 by @panjiedev in https://github.com/Tencent/WeKnora/pull/4502
fix(im): resolve resource URLs through bound storage backends by @lyingbug in https://github.com/Tencent/WeKnora/pull/4578
feat(image): add opt-in, bounded preprocessing before OCR by @tayadwx in https://github.com/Tencent/WeKnora/pull/4381
fix(web-search): keep error previews valid UTF-8 by @sun-sh in https://github.com/Tencent/WeKnora/pull/4583
fix(faq): preserve disabled state when importing entries by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4581
feat(background): shared background-work runtime by @nullptr-error in https://github.com/Tencent/WeKnora/pull/4579
feat(shell): async shell jobs for web and Lite by @nullptr-error in https://github.com/Tencent/WeKnora/pull/4580
fix(frontend): ignore stale document detail responses by @dakjdakd in https://github.com/Tencent/WeKnora/pull/4627
fix(rss): preserve full text during article refresh failures by @dakjdakd in https://github.com/Tencent/WeKnora/pull/4625
fix(knowledge): preserve shared resources during clone rollback by @dakjdakd in https://github.com/Tencent/WeKnora/pull/4623
fix(gallery): cancel stale image fetches before Blob allocation by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4588
fix(ui): avoid full list reloads while awaiting batch reparse by @jiangjiang248 in https://github.com/Tencent/WeKnora/pull/4618
fix(datasource): truncate connector error previews at rune boundaries by @yetuge in https://github.com/Tencent/WeKnora/pull/4614
fix(errors): truncate error messages at rune boundaries by @sun-sh in https://github.com/Tencent/WeKnora/pull/4609
fix(import): accept formats advertised by parser engines by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4602
fix(feishu): 支持知识库快捷方式子文档同步 by @Lyang77 in https://github.com/Tencent/WeKnora/pull/4565
fix(wiki): restore rewritten wkimg placeholders instead of persisting broken links by @u7-u7 in https://github.com/Tencent/WeKnora/pull/4552
fix(agent): reject oversized sandbox appends before reading by @icearia0219 in https://github.com/Tencent/WeKnora/pull/4577
fix(agent): honor read_file match limits when searching by @icearia0219 in https://github.com/Tencent/WeKnora/pull/4575
fix(data-analysis): allow safe scalar casts in SQL validation by @kerthans in https://github.com/Tencent/WeKnora/pull/4215
fix(openaicompletions): keep streamed tool calls without an index apart by @pcbeingused333 in https://github.com/Tencent/WeKnora/pull/4593
fix(googlegenai): map the remaining safety finish reasons to content_filter by @pcbeingused333 in https://github.com/Tencent/WeKnora/pull/4592
fix(agent): treat model_context_window_exceeded as a length finish reason by @pcbeingused333 in https://github.com/Tencent/WeKnora/pull/4589
fix(logger): namespace log format configuration and isolate log tests by @lyingbug in https://github.com/Tencent/WeKnora/pull/4639
fix(agent): preserve multimodal content during message sanitization by @icearia0219 in https://github.com/Tencent/WeKnora/pull/3949
fix(docparser): treat anydoc resource limits as permanent parse failures by @Frank-zhu2000 in https://github.com/Tencent/WeKnora/pull/4573
fix(retriever): bound vector indexing memory with saved windows by @mmhh256 in https://github.com/Tencent/WeKnora/pull/4584
fix(docreader): crop the original image after detecting on a probe by @tayadwx in https://github.com/Tencent/WeKnora/pull/4586
fix: store inline images and apply AI budget in document order by @jacentsao in https://github.com/Tencent/WeKnora/pull/4121
fix(frontend): preserve numeric literals in JSON preview by @Zicheng-Xie in https://github.com/Tencent/WeKnora/pull/4620
fix(preview): reject invalid UTF-8 before decoding CSV by @XY-code1 in https://github.com/Tencent/WeKnora/pull/4479
fix(wiki): support similar page lookup on SQLite by @huong8373tt-beep in https://github.com/Tencent/WeKnora/pull/4605
fix(docreader): release raw PDF images after encoding by @uhhgxg in https://github.com/Tencent/WeKnora/pull/4562
fix(sandbox): rebind when attachment staging loses its container by @wangrui19971019 in https://github.com/Tencent/WeKnora/pull/4220
feat(faq): add list view toggle by @Arc10p in https://github.com/Tencent/WeKnora/pull/4566
fix(lite): reclaim superseded reparse chunks by @huong8373tt-beep in https://github.com/Tencent/WeKnora/pull/4595
fix(im): only reply to Feishu group messages mentioning this bot by @johnnyjy in https://github.com/Tencent/WeKnora/pull/3505
fix(vectorstore): clarify PostgreSQL requirements by @huong8373tt-beep in https://github.com/Tencent/WeKnora/pull/4655
fix(knowledge): keep document toolbar actions inside the pane by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4653
fix(datasource): escape filenames in generated multipart uploads by @sun-sh in https://github.com/Tencent/WeKnora/pull/4647
perf(wiki): coalesce graph label updates and skip hidden SVG layout by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4646
fix(login): keep the sign-in form visible on phones by @huong8373tt-beep in https://github.com/Tencent/WeKnora/pull/4645
fix(datasource): honor skip conflict strategy by @LuckVd in https://github.com/Tencent/WeKnora/pull/4643
perf(chunker): avoid quadratic protected span sorting by @po-et in https://github.com/Tencent/WeKnora/pull/4633
fix(docreader): keep Markdown block structure in EPUB chapters by @MaxFreedomPollard in https://github.com/Tencent/WeKnora/pull/4632
fix(docreader): reclaim memory after large read requests by @helloxjade in https://github.com/Tencent/WeKnora/pull/4628
fix(knowledge): hide parser hint for read-only users by @LuckVd in https://github.com/Tencent/WeKnora/pull/4487
fix(search): isolate multi-KB embedding dimensions by @sun-sh in https://github.com/Tencent/WeKnora/pull/4659
fix(mcp): offload chat metadata lookups from event loop by @Linxiushen in https://github.com/Tencent/WeKnora/pull/4499
fix(docreader): preserve transparency in PPTX fallback images by @LingYi-Liang in https://github.com/Tencent/WeKnora/pull/4678
fix(docreader): preserve external EPUB image references by @po-et in https://github.com/Tencent/WeKnora/pull/4676
fix(wiki): respect word boundaries in SQLite trigram candidates by @wcy12378 in https://github.com/Tencent/WeKnora/pull/4679
fix(agent): clear the exhausted-compaction mark when a compaction succeeds by @ydflow in https://github.com/Tencent/WeKnora/pull/4677
fix(system): keep sandbox deep-check probe previews valid UTF-8 by @ydflow in https://github.com/Tencent/WeKnora/pull/4675
fix(sandbox): keep stderr previews in user-facing errors valid UTF-8 by @ydflow in https://github.com/Tencent/WeKnora/pull/4674
fix(agent): truncate tool-call hints by runes, not bytes by @ydflow in https://github.com/Tencent/WeKnora/pull/4673
fix(agent): compact the unsanitized history on overflow recovery by @ydflow in https://github.com/Tencent/WeKnora/pull/4672
fix(client): cap SDK error response bodies at 1 MiB by @Tong-bit-art in https://github.com/Tencent/WeKnora/pull/4721
fix(chat): keep distinct facts in partial-overlap dedup by @Frank-zhu2000 in https://github.com/Tencent/WeKnora/pull/4719
fix(docparser): recover malformed PDFs with the builtin reader by @acse-bq23 in https://github.com/Tencent/WeKnora/pull/4716
fix(docreader): bound embedded PDF image selection memory by @acse-bq23 in https://github.com/Tencent/WeKnora/pull/4715
fix: preserve shared sandboxes across skill updates by @lyingbug in https://github.com/Tencent/WeKnora/pull/4729
fix(settings): preserve retrieval changes during autosave by @wuning159 in https://github.com/Tencent/WeKnora/pull/4722
fix: show async postprocess duration in trace by @FOWEPJF255 in https://github.com/Tencent/WeKnora/pull/4711
fix(rerank): describe score scales by endpoint output by @mmhh256 in https://github.com/Tencent/WeKnora/pull/4701
fix(sqlite): support organization and wiki searches by @wzxsdf in https://github.com/Tencent/WeKnora/pull/4698
fix(knowledge): cap the knowledge-base definition body at 1 MiB by @yetuge in https://github.com/Tencent/WeKnora/pull/4730
docs(api): document VLM setup when creating a knowledge base by @Linxiushen in https://github.com/Tencent/WeKnora/pull/4695
fix(knowledge): configurable question-generation token budget by @LuckVd in https://github.com/Tencent/WeKnora/pull/4690
fix(knowledge): feed OCR chunks to auto-tag classification by @LuckVd in https://github.com/Tencent/WeKnora/pull/4689
fix(organization): ignore stale member search responses by @wuning159 in https://github.com/Tencent/WeKnora/pull/4726
fix(cli): trim env credentials in auth token output by @ydflow in https://github.com/Tencent/WeKnora/pull/4696
fix(docreader): prevent XLSX chunking timeouts by @wzxsdf in https://github.com/Tencent/WeKnora/pull/4683
fix(agent): stop repeated failed tool calls by @LuckVd in https://github.com/Tencent/WeKnora/pull/4334
fix(docreader): report the file size limit in MB by @LingYi-Liang in https://github.com/Tencent/WeKnora/pull/4670
fix(cli): carry --modified-args/--reason in the exit-10 retry argv by @ydflow in https://github.com/Tencent/WeKnora/pull/4686
fix(docparser): budget the CSV table render before padding it out by @ydflow in https://github.com/Tencent/WeKnora/pull/4702
fix(knowledge): cap the hybrid-search body at 1 MiB by @yetuge in https://github.com/Tencent/WeKnora/pull/4731
fix(docreader): preserve regex semantics when splitting text by @LingYi-Liang in https://github.com/Tencent/WeKnora/pull/4669
fix(docreader): preserve declared XLSX shared string parts by @LingYi-Liang in https://github.com/Tencent/WeKnora/pull/4666
fix(skills): truncate a downloaded skill error body at a rune boundary by @yetuge in https://github.com/Tencent/WeKnora/pull/4665
fix(docreader): bound streamed PDF image memory by @LuckVd in https://github.com/Tencent/WeKnora/pull/4664
fix(memory): resolve shared-agent memory in the caller's workspace by @cainbit in https://github.com/Tencent/WeKnora/pull/4663
fix(agent): treat model_context_window_exceeded as a length stop in compaction by @ydflow in https://github.com/Tencent/WeKnora/pull/4681
fix(modelcontext): preserve citations in JSON strings by @errpunk in https://github.com/Tencent/WeKnora/pull/4733
fix(models): ask Claude for summarized thinking in adaptive mode by @pcbeingused333 in https://github.com/Tencent/WeKnora/pull/4184
fix(agent): preserve native integer literals during parameter casting by @icearia0219 in https://github.com/Tencent/WeKnora/pull/4483
fix(agent): normalize Python physical newlines before quote checks by @icearia0219 in https://github.com/Tencent/WeKnora/pull/4482
fix(docparser): escape standalone image filenames in Markdown by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4475
fix(settings): ignore stale member list search responses by @wuning159 in https://github.com/Tencent/WeKnora/pull/4735
fix(docparser): attach api key in MinerU protocol detection by @JSJ189 in https://github.com/Tencent/WeKnora/pull/4470
fix(search): keep vector hits when keyword retrieval fails by @LuckVd in https://github.com/Tencent/WeKnora/pull/4459
feat(assistant): add contextual entry points and guided actions by @lyingbug in https://github.com/Tencent/WeKnora/pull/4757
feat(assistant): tailor welcome questions to the current page by @lyingbug in https://github.com/Tencent/WeKnora/pull/4758
fix(mcp): add VS Code setup and pin the stdio fallback by @playb0t in https://github.com/Tencent/WeKnora/pull/4363
fix(multimodal): fall back to knowledge base VLM when document model is unavailable by @LuckVd in https://github.com/Tencent/WeKnora/pull/4743
fix(feishu-drive): skip OS metadata files instead of failing the sync by @u7-u7 in https://github.com/Tencent/WeKnora/pull/4738
fix(web-fetch): report a Chromium deadline as a retryable timeout by @wangrui19971019 in https://github.com/Tencent/WeKnora/pull/4468
fix(feishu): checkpoint sync rounds that skip every node by @u7-u7 in https://github.com/Tencent/WeKnora/pull/4736
fix(helm): derive safe app rollout strategy for RWO storage by @wzxsdf in https://github.com/Tencent/WeKnora/pull/4756
fix(models): prevent heartbeats from restoring released concurrency leases by @ydflow in https://github.com/Tencent/WeKnora/pull/4755
fix(cli): classify keychain read failures as keychain_denied, not token_expired by @ydflow in https://github.com/Tencent/WeKnora/pull/4684
fix(im): preserve attachment filenames by @sun-sh in https://github.com/Tencent/WeKnora/pull/4752
fix(client): expose knowledge-base parser engine rules by @jiangjiang248 in https://github.com/Tencent/WeKnora/pull/4753
fix(sandbox): rebind a file op when the container has already stopped by @wangrui19971019 in https://github.com/Tencent/WeKnora/pull/4749
fix(modelcontext): keep literal ref text out of citation expansion by @wangrui19971019 in https://github.com/Tencent/WeKnora/pull/4748
fix(metric): keep every sentence in BLEU and ROUGE scores by @xiashao in https://github.com/Tencent/WeKnora/pull/4746
refactor(wiki): remove unused string truncation helper by @xiashao in https://github.com/Tencent/WeKnora/pull/4744
fix(docparser): 限制 CSV 转换膨胀并支持取消 by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4485
fix(parser): route PPTX vector media through docreader by @mmhh256 in https://github.com/Tencent/WeKnora/pull/4705
fix(googlegenai): count tool-use prompt tokens as input tokens by @pcbeingused333 in https://github.com/Tencent/WeKnora/pull/4594
fix(web-search): truncate the DuckDuckGo result title at a rune boundary by @yetuge in https://github.com/Tencent/WeKnora/pull/4615
fix(knowledge): bound batch polling and ignore stale responses by @wuning159 in https://github.com/Tencent/WeKnora/pull/4648
feat(server): allow explicit frontend directory in standard edition by @alikatgh in https://github.com/Tencent/WeKnora/pull/4637
fix(docreader): honor explicit MHTML root parts by @po-et in https://github.com/Tencent/WeKnora/pull/4636
fix(docreader): preserve code fences during table normalization by @fengyue-xve in https://github.com/Tencent/WeKnora/pull/4494
feat(vlm): make max_tokens configurable via VLM_MAX_TOKENS by @OUAO-FRANK in https://github.com/Tencent/WeKnora/pull/4478
feat(mcp): support document-scoped knowledge search by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4463
fix(chat): generate concise sidebar session titles by @Annabelle0726 in https://github.com/Tencent/WeKnora/pull/4465
fix(web-search): make default provider changes atomic by @hahahahahayesyeseys in https://github.com/Tencent/WeKnora/pull/4454
fix(docreader): keep spreadsheet cells that say N/A, None or NULL by @L4XB in https://github.com/Tencent/WeKnora/pull/4452
fix(docreader): keep the text of DOCX content controls and tracked insertions by @L4XB in https://github.com/Tencent/WeKnora/pull/4448
fix(docreader): keep the footer rows of an HTML table in that table by @L4XB in https://github.com/Tencent/WeKnora/pull/4441
fix(preview): 知识库文档预览的 Markdown 排版（标题层级/间距/代码块/去重标题） by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4439
fix(agent): describe uploads when the chat model cannot see images by @wangrui19971019 in https://github.com/Tencent/WeKnora/pull/4219
fix(data-analysis): read legacy xls workbooks by @wangrui19971019 in https://github.com/Tencent/WeKnora/pull/4218
fix(client): close the response body on the duplicate-URL path by @Tong-bit-art in https://github.com/Tencent/WeKnora/pull/4202
fix(cli): emit bool retry_argv flags in the form pflag can parse back by @Tong-bit-art in https://github.com/Tencent/WeKnora/pull/4197
fix(frontend): distinguish graph availability errors from disabled state by @yeungmingyik in https://github.com/Tencent/WeKnora/pull/4172
fix(docreader): keep Excel header labels unique by @ranjianghong526-hash in https://github.com/Tencent/WeKnora/pull/4160
feat(helm): support app.extraVolumes and app.extraVolumeMounts by @kalandramo in https://github.com/Tencent/WeKnora/pull/4332
fix(housekeeping): scan the queues once per sweep, not once per row by @ignity21 in https://github.com/Tencent/WeKnora/pull/4360
fix(docreader): preserve numeric rows in PDF text extraction by @dvd233 in https://github.com/Tencent/WeKnora/pull/3228
fix(frontend): tolerate malformed EPUB paths and clean up failed previews by @Jarvis636431 in https://github.com/Tencent/WeKnora/pull/4324
perf(search): reuse fixed query-expansion regexps by @xiashao in https://github.com/Tencent/WeKnora/pull/4309
fix(audit_log): stop the retention loop in the ticker cadence test by @AnonymousLesserPanda in https://github.com/Tencent/WeKnora/pull/4308
fix(repository): SearchUsers 兼容 SQLite 方言并转义 LIKE 通配符 by @Winoren in https://github.com/Tencent/WeKnora/pull/3996
fix(agent): preserve user requests during context overflow recovery by @yeliheng-010 in https://github.com/Tencent/WeKnora/pull/4280
fix(ui): preserve explicit zero chunk_overlap when loading KB settings by @Li-john1021 in https://github.com/Tencent/WeKnora/pull/4274
fix(frontend): keep distinct reasoning visible beside final answers by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4267
fix(docreader): preserve all modern XMind topic groups by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4266
fix(frontend): release queued refreshes when browser storage fails by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4265
fix(client): preserve agent reasoning effort during updates by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4264
test: cover qdrant copy pagination by @Goodnight77 in https://github.com/Tencent/WeKnora/pull/4162
test(security): cover NAT64 encodings in TestIsRestrictedIP_IPv6 (fixes [#4092]) by @RerankerGuo in https://github.com/Tencent/WeKnora/pull/4263
fix(mcp): honor a leading UTF-8 BOM in chat streams by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4262
fix(cli): report chunk truncation only when rows are omitted by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4260
fix(cli): reject invalid jq syntax before polling by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4258
fix(cli): preserve raw MCP document download bytes by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4256
fix(client): encode file type filters as a comma-separated value by @xili-ytl in https://github.com/Tencent/WeKnora/pull/4240
fix(ui): allow Owner to demote themselves on the members page by @Li-john1021 in https://github.com/Tencent/WeKnora/pull/4213
fix(knowledge): drop generated questions when the switch is off by @wangrui19971019 in https://github.com/Tencent/WeKnora/pull/4096
fix(embed): keep allowed_origins when a channel update omits it by @VictorMaznyuk in https://github.com/Tencent/WeKnora/pull/4205
fix(skills): explain unfederated skills.sh imports by @tsumon in https://github.com/Tencent/WeKnora/pull/4196
fix(agent): invalidate context checkpoints when rewinding steered turns by @yeliheng-010 in https://github.com/Tencent/WeKnora/pull/4143
fix(session): cap text attachments at 32 KiB instead of failing on long lines by @Jinzhengxu in https://github.com/Tencent/WeKnora/pull/4148
fix(frontend): 通用选择器创建临时数据源前先校验可创建 by @linus-liu-web in https://github.com/Tencent/WeKnora/pull/4050
fix: reject missing qdrant embeddings by @Goodnight77 in https://github.com/Tencent/WeKnora/pull/4165
fix qdrant collection matching by @Goodnight77 in https://github.com/Tencent/WeKnora/pull/3089
fix(chat): lazy-load noVNC only when opening sandbox desktop by @JYao-Chen in https://github.com/Tencent/WeKnora/pull/4034
fix(build): inject version metadata into compose-built app images by @DerrickLinus in https://github.com/Tencent/WeKnora/pull/4123
fix(embed): preserve draft when attachment read fails by @hahahahahayesyeseys in https://github.com/Tencent/WeKnora/pull/4118
fix(sandbox): support Docker Desktop socket permissions by @helloxjade in https://github.com/Tencent/WeKnora/pull/3088
fix(lite): load dotenv files before server startup by @tsumon in https://github.com/Tencent/WeKnora/pull/3618
fix(chat): preselect the answer's knowledge base when saving to a KB by @Yi-111-a in https://github.com/Tencent/WeKnora/pull/3853
fix(agent): validate graph relation evidence in every query scope by @knqiufan in https://github.com/Tencent/WeKnora/pull/3955
fix(mineru): split large Cloud PDFs without checkpoint storage by @JYao-Chen in https://github.com/Tencent/WeKnora/pull/4030
fix(download): preserve existing files when transfers fail by @LeonSGP43 in https://github.com/Tencent/WeKnora/pull/3988
fix(agent): retain new file paths when compaction tracking is full by @icearia0219 in https://github.com/Tencent/WeKnora/pull/4003
fix(agent): reject overlapping matches in unique sandbox edits by @icearia0219 in https://github.com/Tencent/WeKnora/pull/4002
feat(assistant): give each settings page its own starter questions by @lyingbug in https://github.com/Tencent/WeKnora/pull/4762
fix(datasource): make knowledge replacement transactional by @younggglcy in https://github.com/Tencent/WeKnora/pull/4473
fix(datasource): retain retry cursors on ingestion failure by @yeliheng-010 in https://github.com/Tencent/WeKnora/pull/3852
fix(automation): prevent premature SQLite automation claims by @LuckVd in https://github.com/Tencent/WeKnora/pull/4501
fix(agent): recover final-answer context overflow and propagate synthesis errors by @rtmalikian in https://github.com/Tencent/WeKnora/pull/4629
fix(models): preserve string fields in streamed tool arguments by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4253
fix(models): assemble multiline provider SSE packets by @rudycelekli in https://github.com/Tencent/WeKnora/pull/4255
fix(chat-pipeline): honor normalized graph search targets by @dakjdakd in https://github.com/Tencent/WeKnora/pull/4530
fix(kb-delete): give wiki cleanup its own longer timeout budget by @tsumon in https://github.com/Tencent/WeKnora/pull/4292
fix(sandbox): 被超时杀掉的文件系统操作不再误报为请求错误 by @Goodeve0 in https://github.com/Tencent/WeKnora/pull/3921
fix(knowledge): add missing POST /knowledge-bases/:id/rebuild-index route by @tsumon in https://github.com/Tencent/WeKnora/pull/4621
fix(docparser): decode GBK and UTF-16 text files in the simple reader by @L4XB in https://github.com/Tencent/WeKnora/pull/4446
fix(docreader): recognize Unicode BOMs before legacy decoding by @fengyue-xve in https://github.com/Tencent/WeKnora/pull/4498
fix(chunker): preserve explicit zero chunk_overlap on ingest by @Li-john1021 in https://github.com/Tencent/WeKnora/pull/4276
fix(knowledge): strip think blocks from generated questions and summaries by @stanleys12 in https://github.com/Tencent/WeKnora/pull/4691
fix(chat): retry history loading after transient failures by @hahahahahayesyeseys in https://github.com/Tencent/WeKnora/pull/4186
fix(tenant): honor default storage quota across creation paths by @tianhaotian in https://github.com/Tencent/WeKnora/pull/3213
fix(datasource): 保留钉钉超限文件失败后的定时同步 by @panjiedev in https://github.com/Tencent/WeKnora/pull/4505
fix(ui): keep knowledge folders readable and shrink tag editing by @lyingbug in https://github.com/Tencent/WeKnora/pull/4765
fix(agent): discard failed stream drafts before retry by @sun-sh in https://github.com/Tencent/WeKnora/pull/4780
fix(mcp): reject malformed knowledge base selectors by @ydflow in https://github.com/Tencent/WeKnora/pull/4773
fix(config): reject malformed environment-expanded YAML by @xiashao in https://github.com/Tencent/WeKnora/pull/4770
fix(models): preserve Responses API refusal text by @ydflow in https://github.com/Tencent/WeKnora/pull/4766
fix(agent): show matches in long file search lines by @ydflow in https://github.com/Tencent/WeKnora/pull/4774
fix(metric): normalize MAP by all relevant documents by @xiashao in https://github.com/Tencent/WeKnora/pull/4771
feat(lite): ask before host deletes and widen the sandbox on approval by @nullptr-error in https://github.com/Tencent/WeKnora/pull/4076
fix(frontend): 持久化审批卡片直接显示后台等待 by @lyingbug in https://github.com/Tencent/WeKnora/pull/4824
feat: add workspace default settings for models and web search by @lyingbug in https://github.com/Tencent/WeKnora/pull/4822
fix(openaicompletions): recover leaked DSML tool calls safely by @lyingbug in https://github.com/Tencent/WeKnora/pull/4851
fix(agent): preserve manual markdown whitespace by @ydflow in https://github.com/Tencent/WeKnora/pull/4844
fix(mcp): reject chat streams without completion by @ydflow in https://github.com/Tencent/WeKnora/pull/4843
fix(vlm): bound WeKnoraCloud vision response bodies by @Tong-bit-art in https://github.com/Tencent/WeKnora/pull/4806
fix(agent): disable thinking during final answer synthesis by @errpunk in https://github.com/Tencent/WeKnora/pull/4783
fix(chat): carry Ollama's done_reason on the final stream chunk by @pcbeingused333 in https://github.com/Tencent/WeKnora/pull/4845
fix(metric): preserve zero precision in unsmoothed BLEU by @xiashao in https://github.com/Tencent/WeKnora/pull/4833
fix(metric): normalize NDCG against the full ideal ranking by @xiashao in https://github.com/Tencent/WeKnora/pull/4832
fix(lite): skip empty tokenized FTS queries by @u7-u7 in https://github.com/Tencent/WeKnora/pull/4819
feat: prepare v0.9.0 release with assistant onboarding by @lyingbug in https://github.com/Tencent/WeKnora/pull/4836
docs: finalize v0.9.0 release notes and upgrade guidance by @lyingbug in https://github.com/Tencent/WeKnora/pull/4864