Skip to content

WeKnora

v0.6.2 Breaking

This release includes 1 breaking change for platform teams planning a safe upgrade.

Published 1mo 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

ReleasePort's take

Moderate signal
editorial:auto 1mo

The v0.9 agent‑first CLI introduces major contract changes and consolidates authentication and profile handling.

Why it matters: Breaking change in the CLI requires developers and SREs to update integration scripts before upgrade; severity rated high (70).

Summary

AI summary

Updates affect auth, chat, frontend, migrations, duckdb, tracing, client, release tooling.

Changes in this release

Breaking High

feat(cli)!: v0.9 agent-first CLI — contract harmonization, auth/profile consolidation, bundled Agent Skills

feat(cli)!: v0.9 agent-first CLI — contract harmonization, auth/profile consolidation, bundled Agent Skills

Source: llm_adapter@2026-06-10

Confidence: low

Feature Low

feat(migrations): add HNSW index support for 1024‑dim embeddings (bge-m3)

feat(migrations): add HNSW index support for 1024‑dim embeddings (bge-m3)

Source: llm_adapter@2026-06-10

Confidence: high

Feature Low

feat(client): enhance knowledge file upload with process configuration support

feat(client): enhance knowledge file upload with process configuration support

Source: llm_adapter@2026-06-10

Confidence: high

Feature Low

feat(frontend): inject commit ID into frontend build for version tracking

feat(frontend): inject commit ID into frontend build for version tracking

Source: granite4.1:30b@2026-06-10-audit

Confidence: low

Feature Low

feat(frontend): enhance dark mode syntax highlighting for code previews

feat(frontend): enhance dark mode syntax highlighting for code previews

Source: granite4.1:30b@2026-06-10-audit

Confidence: low

Feature Low

feat(frontend): implement marquee selection for knowledge base

feat(frontend): implement marquee selection for knowledge base

Source: granite4.1:30b@2026-06-10-audit

Confidence: low

Feature Low

feat(release): bump version to 0.6.2 with new features and improvements

feat(release): bump version to 0.6.2 with new features and improvements

Source: granite4.1:30b@2026-06-10-audit

Confidence: low

Bugfix Medium

fix(frontend): KB list now renders correctly with ≥2 knowledge bases

fix(frontend): KB list now renders correctly with ≥2 knowledge bases

Source: llm_adapter@2026-06-10

Confidence: high

Bugfix Medium

fix(duckdb): avoid extension install during startup

fix(duckdb): avoid extension install during startup

Source: llm_adapter@2026-06-10

Confidence: high

Bugfix Medium

fix(auth): allow anonymous access to share-link endpoints

fix(auth): allow anonymous access to share-link endpoints

Source: llm_adapter@2026-06-10

Confidence: low

Bugfix Low

fix(knowledge): update doc-scroll-container class binding for loading state

fix(knowledge): update doc-scroll-container class binding for loading state

Source: granite4.1:30b@2026-06-10-audit

Confidence: low

Bugfix Low

fix: refresh wiki status after document polling completes

fix: refresh wiki status after document polling completes

Source: granite4.1:30b@2026-06-10-audit

Confidence: low

Bugfix Low

fix: support custom jieba dictionary directory

fix: support custom jieba dictionary directory

Source: granite4.1:30b@2026-06-10-audit

Confidence: low

Bugfix Low

fix(chat): preserve provider tool-call metadata

fix(chat): preserve provider tool-call metadata

Source: granite4.1:30b@2026-06-10-audit

Confidence: low

Refactor Low

refactor(tracing): remove Jaeger integration and related components

refactor(tracing): remove Jaeger integration and related components

Source: llm_adapter@2026-06-10

Confidence: high

Refactor Low

refactor(get_document_info): update schema definition and input parameters

refactor(get_document_info): update schema definition and input parameters

Source: granite4.1:30b@2026-06-10-audit

Confidence: low

Full changelog

What's Changed

  • fix(auth): allow anonymous access to share-link endpoints (#1617) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1618
  • refactor(chat): improve model name sanitization and path validation by @lyingbug in https://github.com/Tencent/WeKnora/pull/1619
  • fix(knowledge): update doc-scroll-container class binding to account for loading state by @lyingbug in https://github.com/Tencent/WeKnora/pull/1623
  • fix(frontend): KB list renders empty with ≥2 knowledge bases (#795) by @draix in https://github.com/Tencent/WeKnora/pull/1620
  • feat(migrations): HNSW index for 1024-dim embeddings (bge-m3) by @toy0116 in https://github.com/Tencent/WeKnora/pull/1609
  • fix(migrations): update migration comments for HNSW index by @lyingbug in https://github.com/Tencent/WeKnora/pull/1624
  • fix(duckdb): avoid extension install during startup by @langcaiye in https://github.com/Tencent/WeKnora/pull/1615
  • fix: support custom jieba dictionary directory by @langcaiye in https://github.com/Tencent/WeKnora/pull/1627
  • fix: refresh wiki status after document polling completes by @shifang0511 in https://github.com/Tencent/WeKnora/pull/1622
  • feat(cli)!: v0.9 agent-first CLI — contract harmonization, auth/profile consolidation, bundled Agent Skills by @voidkey in https://github.com/Tencent/WeKnora/pull/1551
  • refactor(tracing): remove Jaeger integration and related components by @lyingbug in https://github.com/Tencent/WeKnora/pull/1629
  • fix:langfuse init failed by @MaoMengww in https://github.com/Tencent/WeKnora/pull/1634
  • refactor(frontend): streamline knowledge base and agent handling with chat resources store by @lyingbug in https://github.com/Tencent/WeKnora/pull/1630
  • feat(frontend): inject commit ID into frontend build for version tracking by @lyingbug in https://github.com/Tencent/WeKnora/pull/1635
  • feat(client): enhance knowledge file upload with process configuration support by @lyingbug in https://github.com/Tencent/WeKnora/pull/1636
  • fix(chat): preserve provider tool-call metadata by @ziwon in https://github.com/Tencent/WeKnora/pull/1625
  • feat(frontend): enhance dark mode syntax highlighting for code previews by @lyingbug in https://github.com/Tencent/WeKnora/pull/1637
  • feat(frontend): implement marquee selection for knowledge base by @lyingbug in https://github.com/Tencent/WeKnora/pull/1639
  • refactor(get_document_info): update schema definition and input parameters by @lyingbug in https://github.com/Tencent/WeKnora/pull/1640
  • feat(release): update to version 0.6.2 with new features and improvements by @lyingbug in https://github.com/Tencent/WeKnora/pull/1641

New Contributors

  • @shifang0511 made their first contribution in https://github.com/Tencent/WeKnora/pull/1622

Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.6.1...v0.6.2

Breaking Changes

  • feat(cli)!: v0.9 agent-first CLI — contract harmonization, auth/profile consolidation, bundled Agent Skills

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

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

Earlier breaking changes

  • v0.7.0 Rename user‑facing tenant labels to workspace.

Beta — feedback welcome: [email protected]