Skip to content

WeKnora

v0.6.0 Feature

This release adds 3 notable features for engineering teams evaluating rollout.

Published 13d RAG & Retrieval
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent agentic ai llm embeddings evaluation
+12 more
generative-ai go knowledge-base multi-tenant multimodel ollama openai question-answering reranking semantic-search vector-db wiki

Affected surfaces

auth rbac

ReleasePort's take

Light signal
editorial:auto 13d

v0.6.0 patches a security vulnerability where searchable join bypassed invite code expiry checks, implements multi-tenant RBAC with encrypted credentials, and raises the grpcio floor to 1.78.0.

Why it matters: Upgrade immediately if using invite flows; validate grpcio ≥1.78.0 before deploying. Multi-tenant RBAC adds organization-wide access control—review member ownership and audit logs on rollout.

Summary

AI summary

Updates span frontend UI, session scoping, CLI management, auth integration, knowledge-base validation, embedding support, RBAC multi-tenant features, and OBS storage.

Changes in this release

Security Medium

Searchable join bypasses invite code expiry check.

Searchable join bypasses invite code expiry check.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Security Medium

Scope session access by user.

Scope session access by user.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Security Medium

Harden gRPC TLS/Token rollout for docreader auth.

Harden gRPC TLS/Token rollout for docreader auth.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Security Medium

Redact sensitive fields and prevent credential loss on edit.

Redact sensitive fields and prevent credential loss on edit.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

Surface DB migration errors with troubleshooting links.

Surface DB migration errors with troubleshooting links.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Add docreader auth support.

Add docreader auth support.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Validate vector store bindings on create, copy, and delete.

Validate vector store bindings on create, copy, and delete.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Show UI build version on system info page.

Show UI build version on system info page.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

CLI v0.3: extended management surface and session subtree.

CLI v0.3: extended management surface and session subtree.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

CLI v0.4: output contract hardening and mainstream alignment.

CLI v0.4: output contract hardening and mainstream alignment.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

Modify the skills registration directory.

Modify the skills registration directory.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

CLI v0.5: agent CRUD, chunk subtree, audit-driven cleanup.

CLI v0.5: agent CRUD, chunk subtree, audit-driven cleanup.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

Add Zhipu AI embedder implementation.

Add Zhipu AI embedder implementation.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

CLI v0.6: output contract, doc wait, status, multi-id delete.

CLI v0.6: output contract, doc wait, status, multi-id delete.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

Multi-tenant RBAC: schema, enforcement, member management, ownership, audit log.

Multi-tenant RBAC: schema, enforcement, member management, ownership, audit log.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Dependency Medium

Bump grpcio floor to 1.78.0 to match generated proto.

Bump grpcio floor to 1.78.0 to match generated proto.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Dependency Low

Bump grpcio minimum version to 1.78.0 to match generated protobuf.

Bump grpcio minimum version to 1.78.0 to match generated protobuf.

Source: granite4.1:30b@2026-05-21-audit

Confidence: high

 —
Bugfix Medium

Stop publishing docreader gRPC port to host.

Stop publishing docreader gRPC port to host.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Make rerank model optional in agent editor save.

Make rerank model optional in agent editor save.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Map ErrSessionNotFound to 404 across all handlers.

Map ErrSessionNotFound to 404 across all handlers.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Map ErrKnowledgeBaseNotFound to 404 across handler helpers.

Map ErrKnowledgeBaseNotFound to 404 across handler helpers.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Extend document processing timeout for large files.

Extend document processing timeout for large files.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Prevent infinite scroll race condition causing missing documents.

Prevent infinite scroll race condition causing missing documents.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Guard against empty choices and message=None in LLM response.

Guard against empty choices and message=None in LLM response.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Update AgentQA to conditionally disable title based on request.

Update AgentQA to conditionally disable title based on request.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Bugfix Medium

Ensure pg_trgm created before trigram index in migration 000041.

Ensure pg_trgm created before trigram index in migration 000041.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Bugfix Medium

Hide Ollama tip for remote models.

Hide Ollama tip for remote models.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Bugfix Medium

Repair broken comment in Zhipu embedder.

Repair broken comment in Zhipu embedder.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Bugfix Medium

Exclude processing docs from prompt.

Exclude processing docs from prompt.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Refactor Medium

Add /credentials subresource, at-rest encryption, test-connection UX.

Add /credentials subresource, at-rest encryption, test-connection UX.

Source: llm_adapter@2026-05-21

Confidence: high

 —
Refactor Medium

Introduce factory for KB-scoped retrieve engine resolution.

Introduce factory for KB-scoped retrieve engine resolution.

Source: llm_adapter@2026-05-21

Confidence: low

 —
Full changelog

What's Changed

  • fix(compose): stop publishing docreader gRPC port to the host by @lyingbug in https://github.com/Tencent/WeKnora/pull/1308
  • feat(frontend): show UI build version on system info page by @lyingbug in https://github.com/Tencent/WeKnora/pull/1313
  • fix(org): searchable join bypasses invite code expiry by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/1324
  • fix(frontend): make rerank model optional in agent editor save by @guangyang1206 in https://github.com/Tencent/WeKnora/pull/1317
  • feat(cli): v0.3 — extended management surface and session subtree by @voidkey in https://github.com/Tencent/WeKnora/pull/1315
  • refactor(retriever): introduce factory for KB-scoped retrieve engine resolution by @ochanism in https://github.com/Tencent/WeKnora/pull/1310
  • fix(session): scope session access by user by @wolfkill in https://github.com/Tencent/WeKnora/pull/1309
  • feat(system-info): surface DB migration errors with troubleshooting links by @lyingbug in https://github.com/Tencent/WeKnora/pull/1335
  • fix(session): map ErrSessionNotFound to 404 across all handlers (#1309 follow-up) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1336
  • fix(migration): ensure pg_trgm is created before trigram index in 000041 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1334
  • fix(kb): map ErrKnowledgeBaseNotFound to 404 across handler helpers by @lyingbug in https://github.com/Tencent/WeKnora/pull/1339
  • feat(cli): v0.4 - output contract hardening and mainstream alignment by @voidkey in https://github.com/Tencent/WeKnora/pull/1342
  • feat: modify the skills registration directory by @1141520944 in https://github.com/Tencent/WeKnora/pull/1344
  • fix: extend document processing timeout for large files by @HelloWeit in https://github.com/Tencent/WeKnora/pull/1346
  • fix(model): hide Ollama tip for remote models by @wolfkill in https://github.com/Tencent/WeKnora/pull/1330
  • fix(knowledge): prevent infinite scroll race condition causing missing documents by @caiyuze-cpu in https://github.com/Tencent/WeKnora/pull/1356
  • feat(cli): v0.5 — agent CRUD + chunk subtree + audit-driven cleanup by @voidkey in https://github.com/Tencent/WeKnora/pull/1354
  • feat(auth): 连接docreader支持auth by @CodeMarker0 in https://github.com/Tencent/WeKnora/pull/1359
  • fix(docreader/auth): harden gRPC TLS/Token rollout from #1359 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1361
  • fix: redact sensitive fields and prevent credential loss on edit by @ochanism in https://github.com/Tencent/WeKnora/pull/990
  • fix(docreader): bump grpcio floor to 1.78.0 to match generated proto by @toy0116 in https://github.com/Tencent/WeKnora/pull/1363
  • refactor(credentials): /credentials subresource, at-rest encryption, and test-connection UX by @lyingbug in https://github.com/Tencent/WeKnora/pull/1364
  • feat(embedding): add Zhipu AI embedder implementation by @Wellbek in https://github.com/Tencent/WeKnora/pull/1365
  • fix(embedding): repair broken comment in Zhipu embedder by @lyingbug in https://github.com/Tencent/WeKnora/pull/1366
  • test(repo): add wiki_config + indexing_strategy to sqlite test DDL by @toy0116 in https://github.com/Tencent/WeKnora/pull/1362
  • fix: guard against empty choices and message=None in LLM response by @qizwiz in https://github.com/Tencent/WeKnora/pull/1369
  • feat(cli): v0.6 — output contract, doc wait, status, multi-id delete by @voidkey in https://github.com/Tencent/WeKnora/pull/1368
  • feat(knowledge-base): validate vector store bindings on create, copy, and delete by @ochanism in https://github.com/Tencent/WeKnora/pull/1372
  • fix(agent): exclude processing docs from prompt by @wolfkill in https://github.com/Tencent/WeKnora/pull/1370
  • feat(rbac): multi-tenant RBAC — schema, enforcement, member management, ownership, audit log (#1303) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1367
  • fix(session): update AgentQA to conditionally disable title based on request by @lyingbug in https://github.com/Tencent/WeKnora/pull/1375
  • feat(frontend): redesign knowledge document tag selector by @lyingbug in https://github.com/Tencent/WeKnora/pull/1376
  • feat(obs): 支持华为云obs存储 by @CodeMarker0 in https://github.com/Tencent/WeKnora/pull/1377
  • feat(url): 支持docreader不上传替换白名单url的图片 by @CodeMarker0 in https://github.com/Tencent/WeKnora/pull/1378
  • feat(tenant): richer workspace-switch toast that survives the post-switch reload by @lyingbug in https://github.com/Tencent/WeKnora/pull/1379
  • feat(tenant): remember user's last-active workspace across logins by @lyingbug in https://github.com/Tencent/WeKnora/pull/1381
  • fix(auth): unify DISABLE_REGISTRATION and auth.registration_mode by @lyingbug in https://github.com/Tencent/WeKnora/pull/1384
  • chore(env): expose tenant RBAC + per-user tenant cap as env knobs by @lyingbug in https://github.com/Tencent/WeKnora/pull/1385
  • fix(docparser): unescape MinerU markdown image syntax by @nixidexiangjiao in https://github.com/Tencent/WeKnora/pull/1382
  • fix(moonshot): pin temperature=1 for models that reject other values by @nixidexiangjiao in https://github.com/Tencent/WeKnora/pull/1383
  • style(menu): tighten session list density in sidebar by @lyingbug in https://github.com/Tencent/WeKnora/pull/1387
  • fix(menu): avoid refreshing session list when opening an existing chat by @lyingbug in https://github.com/Tencent/WeKnora/pull/1388
  • fix(menu): stop truncating session titles when extra space is available by @lyingbug in https://github.com/Tencent/WeKnora/pull/1389
  • feat(session): persist last request state for UI restoration by @lyingbug in https://github.com/Tencent/WeKnora/pull/1390
  • revert: drop colored role chip styling on tenant members page by @lyingbug in https://github.com/Tencent/WeKnora/pull/1391
  • fix(i18n): escape '@' in invite email placeholder by @lyingbug in https://github.com/Tencent/WeKnora/pull/1392
  • fix(chunker): keep top-level heading chunks separate by @wolfkill in https://github.com/Tencent/WeKnora/pull/1396
  • doris: add configurable compatibility modes and guard mode switches by @SilentMil in https://github.com/Tencent/WeKnora/pull/1395
  • feat: add vLLM server URL configuration for MinerU by @xdgu0275 in https://github.com/Tencent/WeKnora/pull/1405
  • chore: update Go version to 1.26.0 in go.mod by @lyingbug in https://github.com/Tencent/WeKnora/pull/1407
  • fix(frontend): mirror cross-tenant superuser Admin role in UI gates by @lyingbug in https://github.com/Tencent/WeKnora/pull/1406
  • refactor(agent): simplify grep_chunks tool to a single regex query by @lyingbug in https://github.com/Tencent/WeKnora/pull/1410
  • feat(frontend): make Vite dev proxy target configurable by @lyingbug in https://github.com/Tencent/WeKnora/pull/1412
  • fix(chat): stabilize history pagination and keep message order by @lyingbug in https://github.com/Tencent/WeKnora/pull/1409
  • feat(search): fan-out KB retrieval across bound vector stores by @ochanism in https://github.com/Tencent/WeKnora/pull/1386
  • fix(knowledge): complete indexed documents immediately by @wolfkill in https://github.com/Tencent/WeKnora/pull/1408
  • fix(client): align UpdateAgent request types with internal API by @HQF2017 in https://github.com/Tencent/WeKnora/pull/1398
  • fix(session): scope wiki fixer to shared KB tenant by @wolfkill in https://github.com/Tencent/WeKnora/pull/1413
  • fix(chat): improve history rendering stability by @lyingbug in https://github.com/Tencent/WeKnora/pull/1419
  • fix(docparser): preserve MinerU markdown and persist relative images by @M1dnightSUN in https://github.com/Tencent/WeKnora/pull/1404
  • fix(docparser): address review feedback on #1404 (MinerU markdown & image persistence) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1420
  • docs: add Chinese RBAC guide and link with shared space docs by @lyingbug in https://github.com/Tencent/WeKnora/pull/1421
  • fix(frontend): guard knowledge list against stale updates by @iceloon in https://github.com/Tencent/WeKnora/pull/1424
  • fix(chat): adjust user message container to support pre-wrapped text by @ThinhTT84 in https://github.com/Tencent/WeKnora/pull/1425
  • fix(repository): correct query syntax to get correctly built-in models #1373 by @ThinhTT84 in https://github.com/Tencent/WeKnora/pull/1428
  • chore(release): v0.6.0 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1422
  • docs(readme): flatten Latest Updates into single-line per-version list by @lyingbug in https://github.com/Tencent/WeKnora/pull/1430

New Contributors

  • @HelloWeit made their first contribution in https://github.com/Tencent/WeKnora/pull/1346
  • @caiyuze-cpu made their first contribution in https://github.com/Tencent/WeKnora/pull/1356
  • @Wellbek made their first contribution in https://github.com/Tencent/WeKnora/pull/1365
  • @qizwiz made their first contribution in https://github.com/Tencent/WeKnora/pull/1369
  • @nixidexiangjiao made their first contribution in https://github.com/Tencent/WeKnora/pull/1382
  • @SilentMil made their first contribution in https://github.com/Tencent/WeKnora/pull/1395
  • @xdgu0275 made their first contribution in https://github.com/Tencent/WeKnora/pull/1405
  • @M1dnightSUN made their first contribution in https://github.com/Tencent/WeKnora/pull/1404
  • @iceloon made their first contribution in https://github.com/Tencent/WeKnora/pull/1424
  • @ThinhTT84 made their first contribution in https://github.com/Tencent/WeKnora/pull/1425

Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.5.2...v0.6.0

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track WeKnora

Get notified when new releases ship.

Sign up free

About WeKnora

LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.

All releases →

Related context

Beta — feedback welcome: [email protected]