Skip to content

WeKnora

v0.5.2 Feature

This release adds 1 notable feature for engineering teams evaluating rollout.

Published 21d 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

Moderate signal
editorial:auto 13d

ReleasePort Layer 1 v0.5.2 adds Apache Doris as a vector‑database retriever and introduces several feature, bugfix, refactor, dependency, performance, and security updates across frontend, backend, agent, storage, wiki, client, i18n, IM, chunker, knowledge, middleware, CLI, and chat components.

Why it matters: Patch to v0.5.2 immediately to obtain the LLM timeout‑protection fix (security) that prevents worker hangs; test other new features in development before production rollout.

Summary

AI summary

Added Apache Doris as a vector database retriever.

Changes in this release

Security Medium

Fix LLM timeout protection to prevent worker hangs

Fix LLM timeout protection to prevent worker hangs

Source: llm_adapter@2026-05-21

Confidence: low

 —
Feature Medium

Add SearXNG provider to web search

Add SearXNG provider to web search

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Support Anthropic chat provider

Support Anthropic chat provider

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Introduce human-in-the-loop approval for MCP tool calls

Introduce human-in-the-loop approval for MCP tool calls

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Add Tencent VectorDB keyword retrieval support

Add Tencent VectorDB keyword retrieval support

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Enforce strict citation tracing and ontology reuse in wiki

Enforce strict citation tracing and ontology reuse in wiki

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Add KS3 object storage support

Add KS3 object storage support

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Replace standalone search page with global ⌘K palette

Replace standalone search page with global ⌘K palette

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Support apt-based Docker install for restricted-egress hosts

Support apt-based Docker install for restricted-egress hosts

Source: llm_adapter@2026-05-21

Confidence: high

 —
Feature Medium

Add Chrome Extension and ClawHub Skill badges to README

Add Chrome Extension and ClawHub Skill badges to README

Source: llm_adapter@2026-05-21

Confidence: low

 —
Dependency Medium

Bump github.com/mattn/go-isatty from 0.0.20 to 0.0.22 in /cli

Bump github.com/mattn/go-isatty from 0.0.20 to 0.0.22 in /cli

Source: llm_adapter@2026-05-21

Confidence: low

 —
Performance Medium

Subgraph API and interactive exploration for large graphs in wiki

Subgraph API and interactive exploration for large graphs in wiki

Source: llm_adapter@2026-05-21

Confidence: high

 —
Performance Medium

Lazy-load sidebar page list with virtual-scroll tabs in wiki

Lazy-load sidebar page list with virtual-scroll tabs in wiki

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Include history in model fallback during chat

Include history in model fallback during chat

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Propagate user attachments to agent query in AgentQA

Propagate user attachments to agent query in AgentQA

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Clamp reconnect backoff to avoid int64 overflow busy loop

Clamp reconnect backoff to avoid int64 overflow busy loop

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Recognise CN chapter titles and multi-level numeric headings in chunker

Recognise CN chapter titles and multi-level numeric headings in chunker

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Mask camelCase secret fields in request logs

Mask camelCase secret fields in request logs

Source: llm_adapter@2026-05-21

Confidence: high

 —
Bugfix Medium

Correct GetChunkByIDOnly endpoint in client

Correct GetChunkByIDOnly endpoint in client

Source: llm_adapter@2026-05-21

Confidence: low

 —
Bugfix Medium

Remove duplicate liveIndicator key in ko-KR locale

Remove duplicate liveIndicator key in ko-KR locale

Source: llm_adapter@2026-05-21

Confidence: low

 —
Bugfix Medium

Include shared knowledge in knowledge search

Include shared knowledge in knowledge search

Source: llm_adapter@2026-05-21

Confidence: low

 —
Refactor Medium

Split 9.8k-line service file by responsibility

Split 9.8k-line service file by responsibility

Source: llm_adapter@2026-05-21

Confidence: high

 —
Full changelog

What's Changed

  • chore: release v0.5.1 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1104
  • docs(readme): add Chrome Extension and ClawHub Skill badges by @lyingbug in https://github.com/Tencent/WeKnora/pull/1105
  • fix(embedding): OpenAIEmbedder.doRequestWithRetry shadows err · retur… by @toy0116 in https://github.com/Tencent/WeKnora/pull/1116
  • fix(chat): include history in model fallback by @Aphroq in https://github.com/Tencent/WeKnora/pull/1112
  • fix(memory): dedupe episode write on duplicate streaming Done by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/1125
  • feat(wiki): enforce strict citation tracing and ontology reuse in Wik… by @lFeynman in https://github.com/Tencent/WeKnora/pull/1120
  • feat(openmaic-classroom): 增加基于wiki知识图谱概念的微课堂生成支持，更新需求构建模板 by @peterchan2020 in https://github.com/Tencent/WeKnora/pull/1119
  • fix: oidc auth login by @Windfarer in https://github.com/Tencent/WeKnora/pull/1127
  • feat(ks3): add KS3 object storage support by @ChenRussell in https://github.com/Tencent/WeKnora/pull/1109
  • fix(im): clamp reconnect backoff to avoid int64 overflow busy loop by @lyingbug in https://github.com/Tencent/WeKnora/pull/1128
  • feat(frontend): unify fonts across the app and add per-user font/size/theme preferences by @Puma7 in https://github.com/Tencent/WeKnora/pull/1121
  • fix(i18n): remove duplicate liveIndicator key in ko-KR locale by @lyingbug in https://github.com/Tencent/WeKnora/pull/1129
  • feat(frontend): respect BASE_URL so the SPA works behind a path-prefi… by @toy0116 in https://github.com/Tencent/WeKnora/pull/1115
  • fix: include shared knowledge in knowledge search by @Aphroq in https://github.com/Tencent/WeKnora/pull/1111
  • fix(agent): correct graph config reporting by @Aphroq in https://github.com/Tencent/WeKnora/pull/1114
  • fix(data-analysis): capture LOCAL_STORAGE_BASE_DIR at init time (#1040) by @guangyang1206 in https://github.com/Tencent/WeKnora/pull/1130
  • fix(ingest): prevent filename-driven LLM hallucinations on scanned PDFs by @Puma7 in https://github.com/Tencent/WeKnora/pull/1122
  • feat(kb-list): group pinned knowledge bases into a labeled section by @lyingbug in https://github.com/Tencent/WeKnora/pull/1132
  • feat(frontend): replace standalone search page with global ⌘K palette by @lyingbug in https://github.com/Tencent/WeKnora/pull/1135
  • feat(kb-list): source column + description subtitle, fix XSS by @lyingbug in https://github.com/Tencent/WeKnora/pull/1136
  • fix(files): fall back to global file service when tenant storage config is unavailable by @sqkstwj in https://github.com/Tencent/WeKnora/pull/1096
  • refactor(knowledge): split 9.8k-line service file by responsibility by @lyingbug in https://github.com/Tencent/WeKnora/pull/1134
  • Revert "refactor(knowledge): split 9.8k-line service file by responsibility" by @lyingbug in https://github.com/Tencent/WeKnora/pull/1138
  • fix(storage): merge tos/s3/oss/ks3 tenant configs in buildStorageConfig (#1117) by @voidborne-d in https://github.com/Tencent/WeKnora/pull/1137
  • feat(chunking): adaptive 3-tier strategy with editor UI and live debug panel by @Puma7 in https://github.com/Tencent/WeKnora/pull/1124
  • refactor(knowledge): split 9.8k-line service file by responsibility by @lyingbug in https://github.com/Tencent/WeKnora/pull/1139
  • feat(chunker): coalesce tiny adjacent heading chunks; drop redundant TierRecursive by @lyingbug in https://github.com/Tencent/WeKnora/pull/1140
  • fix(frontend): rework chunking debug UX in the KB editor by @lyingbug in https://github.com/Tencent/WeKnora/pull/1141
  • refactor(chunker): phase 1 cleanup — overlap bug, profile threading, protected spans, embedding trim, parent-child strategy by @lyingbug in https://github.com/Tencent/WeKnora/pull/1142
  • fix(chunker): recognise CN chapter titles and multi-level numeric headings by @lyingbug in https://github.com/Tencent/WeKnora/pull/1143
  • fix(knowledge): polish chunking-settings debug trigger and strategy hint by @lyingbug in https://github.com/Tencent/WeKnora/pull/1148
  • fix: 为前端静态资源设置 Cache-Control，修复升级后需重新登录才能看到新页面 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1149
  • fix(frontend): make general-settings font picker actually work by @lyingbug in https://github.com/Tencent/WeKnora/pull/1150
  • fix(graph): recover JSON from malformed/truncated fences in extract_entity (#1113) by @draix in https://github.com/Tencent/WeKnora/pull/1131
  • fix: 修复流式回答think/answer混淆及对话结束标记问题 by @peterchan2020 in https://github.com/Tencent/WeKnora/pull/1126
  • fix(agent): 统一最终答案渲染并去除重复/空思考块 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1153
  • fix(docreader): throttle heavy parser concurrency by @wolfkill in https://github.com/Tencent/WeKnora/pull/1151
  • chore(agent): add fire-once stream diagnostic logs (agent + OpenAI layer) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1157
  • fix(frontend): render markdown tables in chat wiki drawer by @lyingbug in https://github.com/Tencent/WeKnora/pull/1158
  • fix(frontend): polish model settings UI and fix disabled brand color by @lyingbug in https://github.com/Tencent/WeKnora/pull/1162
  • feat: cli foundation by @voidkey in https://github.com/Tencent/WeKnora/pull/1144
  • perf(wiki): subgraph API and interactive exploration for large graphs by @lyingbug in https://github.com/Tencent/WeKnora/pull/1167
  • perf(wiki): lazy-load sidebar page list with virtual-scroll tabs by @lyingbug in https://github.com/Tencent/WeKnora/pull/1169
  • fix(frontend): allow build scripts for pnpm to unblock Docker build by @lyingbug in https://github.com/Tencent/WeKnora/pull/1170
  • fix(frontend): pass allow-build flags to pnpm install in Docker build by @lyingbug in https://github.com/Tencent/WeKnora/pull/1171
  • fix(frontend): configure pnpm v11 build approvals in workspace file by @lyingbug in https://github.com/Tencent/WeKnora/pull/1172
  • Fix authentication API documentation links by @aqilaziz in https://github.com/Tencent/WeKnora/pull/1163
  • fix: propagate user attachments to agent query in AgentQA by @lyingbug in https://github.com/Tencent/WeKnora/pull/1175
  • fix(frontend): use npm to match committed lockfile by @YunfanDu in https://github.com/Tencent/WeKnora/pull/1174
  • Pr/wiki requeue fix by @toy0116 in https://github.com/Tencent/WeKnora/pull/1155
  • perf(wiki): move ingest log to event table and index to on-demand API by @lyingbug in https://github.com/Tencent/WeKnora/pull/1176
  • fix(wiki-ingest): harden lock-conflict handling and reduce retry churn by @lyingbug in https://github.com/Tencent/WeKnora/pull/1177
  • feat(retriever): 接入 Apache Doris 4.1 作为向量数据库 by @tianlinzx in https://github.com/Tencent/WeKnora/pull/1154
  • fix(retriever/doris): code review cleanup by @lyingbug in https://github.com/Tencent/WeKnora/pull/1180
  • feat(wiki/graph): 优化操作帮助入口与图例视觉 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1181
  • fix(wiki-ingest): reconcile summary links and log feed when reduce LLM fails by @lyingbug in https://github.com/Tencent/WeKnora/pull/1182
  • feat:cli v0.1 by @voidkey in https://github.com/Tencent/WeKnora/pull/1179
  • chore(deps): bump github.com/mattn/go-isatty from 0.0.20 to 0.0.22 in /cli by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1193
  • chore(deps): bump github.com/spf13/cobra from 1.8.1 to 1.10.2 in /cli by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1192
  • chore(deps): bump actions/setup-node from 4 to 6 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1191
  • chore(deps): bump docker/metadata-action from 5 to 6 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1187
  • chore(deps): bump actions/download-artifact from 4 to 8 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1186
  • chore(deps): bump docker/build-push-action from 3 to 7 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1188
  • chore(deps): bump actions/setup-go from 5 to 6 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1189
  • chore(deps): bump github.com/mattn/go-runewidth from 0.0.16 to 0.0.23 in /cli by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1190
  • chore(dependabot): expand coverage beyond /cli by @lyingbug in https://github.com/Tencent/WeKnora/pull/1194
  • chore(deps): bump github.com/google/jsonschema-go from 0.4.2 to 0.4.3 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1212
  • chore(deps): bump github.com/volcengine/ve-tos-golang-sdk/v2 from 2.7.23 to 2.9.4 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1211
  • chore(deps): bump github.com/aws/aws-sdk-go-v2/service/s3 from 1.83.0 to 1.101.0 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1213
  • chore(deps): bump github.com/minio/minio-go/v7 from 7.0.91 to 7.1.0 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1216
  • chore(deps): bump github.com/sashabaranov/go-openai from 1.40.5 to 1.41.2 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1214
  • chore(deps): bump github.com/aliyun/alibabacloud-oss-go-sdk-v2 from 1.4.1 to 1.5.1 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1210
  • chore(deps-dev): bump less from 4.3.0 to 4.6.4 in /frontend by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1208
  • chore(deps): bump github.com/duckdb/duckdb-go/v2 from 2.5.4 to 2.10502.0 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1215
  • chore(deps): bump github.com/go-openapi/strfmt from 0.25.0 to 0.26.2 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1218
  • chore(deps): bump github.com/aws/aws-sdk-go-v2/credentials from 1.19.11 to 1.19.16 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1217
  • chore(deps): bump gorm.io/gorm from 1.30.0 to 1.31.1 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1209
  • chore(deps): update minio requirement from >=7.2.18 to >=7.2.20 in /docreader by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1206
  • chore(deps-dev): bump less-loader from 12.3.0 to 12.3.2 in /frontend by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1207
  • chore(deps): update lxml requirement from >=6.0.2 to >=6.1.0 in /docreader by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1205
  • chore(deps): update oss2 requirement from >=2.18.0 to >=2.19.1 in /docreader by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1203
  • chore(deps): update cos-python-sdk-v5 requirement from >=1.9.38 to >=1.9.42 in /docreader by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1200
  • chore(deps): bump docker/setup-buildx-action from 3 to 4 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1199
  • chore(deps): bump docker/login-action from 3 to 4 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1195
  • chore(deps): bump actions/upload-artifact from 4 to 7 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1196
  • chore(deps): bump actions/checkout from 3 to 6 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1197
  • chore(deps): bump @types/papaparse from 5.5.0 to 5.5.2 in /frontend by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1198
  • chore(deps): update paddlepaddle requirement from <4.0.0,>=3.0.0 to >=3.3.1,<4.0.0 in /docreader by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1201
  • chore(deps): bump vue from 3.5.17 to 3.5.34 in /frontend by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1204
  • chore(deps): bump github.com/weaviate/weaviate from 1.33.0-rc.1 to 1.37.2 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1219
  • chore(deps): bump dompurify and @types/dompurify in /frontend by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1202
  • chore(deps): bump github.com/aws/aws-sdk-go-v2/config from 1.32.14 to 1.32.17 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1221
  • chore(deps): bump github.com/chromedp/chromedp from 0.14.2 to 0.15.1 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1223
  • chore(deps): bump nltk from 3.9.2 to 3.9.4 in /docreader by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1229
  • feat: add Tencent VectorDB retriever backend by @langcaiye in https://github.com/Tencent/WeKnora/pull/1184
  • chore: bump Go to 1.26 and slim docreader dependencies by @lyingbug in https://github.com/Tencent/WeKnora/pull/1231
  • chore(deps): bump google.golang.org/grpc from 1.80.0 to 1.81.0 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1228
  • chore(deps): bump gorm.io/driver/postgres from 1.5.11 to 1.6.0 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1227
  • chore(deps): bump github.com/ollama/ollama from 0.11.4 to 0.23.2 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1226
  • chore(deps): bump github.com/milvus-io/milvus/client/v2 from 2.6.2 to 2.6.4 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1224
  • chore(deps): bump github.com/jackc/pgx/v5 from 5.7.2 to 5.9.2 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1239
  • chore(deps): update github.com/go-openapi/swag to v0.26.0 and remove unused dependencies by @lyingbug in https://github.com/Tencent/WeKnora/pull/1240
  • chore(deps): bump golang.org/x/crypto from 0.50.0 to 0.51.0 by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1225
  • perf(wiki-ingest): scale to 4w-doc KBs + generic task queue / dead-letter by @lyingbug in https://github.com/Tencent/WeKnora/pull/1241
  • feat: support Tencent VectorDB keyword retrieval by @langcaiye in https://github.com/Tencent/WeKnora/pull/1234
  • fix(chat): 为 LLM 非流式/流式调用添加超时保护，防止 worker 被 hung 请求永久阻塞 by @ymkzs in https://github.com/Tencent/WeKnora/pull/1238
  • fix(chat): LLM 兜底超时仅在上层无 deadline 时生效，并修复 ChatStream raw HTTP 路径的 cancel 泄漏 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1242
  • fix(frontend): 修正 LLM 调用超时文案与实际行为一致，上限放宽至 3600s by @lyingbug in https://github.com/Tencent/WeKnora/pull/1243
  • feat(agent): human-in-the-loop approval for MCP tool calls (#1173) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1245
  • docs(cloud-image): add cloud-agnostic image packaging scripts by @lyingbug in https://github.com/Tencent/WeKnora/pull/1249
  • fix(client): correct GetChunkByIDOnly endpoint by @HQF2017 in https://github.com/Tencent/WeKnora/pull/1254
  • fix(cloud-image): enhance firstboot and cleanup scripts for improved security and functionality by @lyingbug in https://github.com/Tencent/WeKnora/pull/1255
  • feat(web-search): add SearXNG provider (#1166) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1246
  • feat(cloud-image): support apt-based docker install for restricted-egress hosts by @lyingbug in https://github.com/Tencent/WeKnora/pull/1260
  • chore(env): remove WEKNORA_SANDBOX_DOCKER_IMAGE from .env.example by @lyingbug in https://github.com/Tencent/WeKnora/pull/1261
  • refactor(agent): rebuild multi-turn history from DB, drop llmcontext layer by @lyingbug in https://github.com/Tencent/WeKnora/pull/1263
  • docs(api): full audit and update of API documentation by @voidkey in https://github.com/Tencent/WeKnora/pull/1251
  • feat: cli v0.2 by @voidkey in https://github.com/Tencent/WeKnora/pull/1247
  • chore(deps): bump the frontend-deps group in /frontend with 15 updates by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1269
  • chore(deps): bump the server-deps group with 25 updates by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1272
  • chore(deps): bump github.com/spf13/pflag from 1.0.9 to 1.0.10 in /cli in the cli-deps group by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1265
  • chore(deps): update pydantic requirement from >=2.12.3 to >=2.13.4 in /docreader by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1266
  • chore(deps): update pypdfium2 requirement from >=5.0.0 to >=5.8.0 in /docreader by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1267
  • chore(deps-dev): bump typescript from 5.8.3 to 6.0.3 in /frontend by @dependabot[bot] in https://github.com/Tencent/WeKnora/pull/1270
  • fix(agent): replay attachments in multi-turn history by @lyingbug in https://github.com/Tencent/WeKnora/pull/1275
  • chore(deps): update dependencies in /docreader and adjust dependabot configuration by @lyingbug in https://github.com/Tencent/WeKnora/pull/1276
  • fix(agent): exclude wiki-only KBs from quick-answer (RAG) mode by @lyingbug in https://github.com/Tencent/WeKnora/pull/1278
  • fix(faq): correct PostgreSQL cast precedence in FAQ search by @voidkey in https://github.com/Tencent/WeKnora/pull/1274
  • fix(agent): relax rerank model requirement for custom agents by @lyingbug in https://github.com/Tencent/WeKnora/pull/1281
  • feat: support Anthropic chat provider by @langcaiye in https://github.com/Tencent/WeKnora/pull/1280
  • fix(multimodal): unblock processing when provider:// image read fails by @lyingbug in https://github.com/Tencent/WeKnora/pull/1284
  • fix(feishu): tolerate partial wiki node listing failures by @wolfkill in https://github.com/Tencent/WeKnora/pull/1286
  • chore(github): translate issue/PR templates to English and improve content by @lyingbug in https://github.com/Tencent/WeKnora/pull/1289
  • feat(knowledge-base): document list filters and explicit batch-management UX by @lyingbug in https://github.com/Tencent/WeKnora/pull/1288
  • fix(middleware): mask camelCase secret fields in request logs by @lyingbug in https://github.com/Tencent/WeKnora/pull/1291
  • fix(pipeline): make data-analysis stage opt-in per agent (#1244) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1293
  • fix(agent-editor): move data-analysis toggle to retrieval section by @lyingbug in https://github.com/Tencent/WeKnora/pull/1294
  • feat(agent): support dedicated model for query understanding step by @lyingbug in https://github.com/Tencent/WeKnora/pull/1295
  • feat(observability): fill Langfuse trace gaps and add end-to-end TTFB logs by @lyingbug in https://github.com/Tencent/WeKnora/pull/1298
  • fix: support Anthropic gateway streaming by @langcaiye in https://github.com/Tencent/WeKnora/pull/1292
  • fix(chat): map MaxTokens to MaxCompletionTokens for GPT-5/o-series by @lyingbug in https://github.com/Tencent/WeKnora/pull/1299
  • fix(frontend): persist graph extract toggle state on KB save (#1297) by @lyingbug in https://github.com/Tencent/WeKnora/pull/1300
  • docs(frontend): clarify Wiki page-link graph vs entity-relation knowledge graph by @lyingbug in https://github.com/Tencent/WeKnora/pull/1301
  • fix(agent): pass reasoning_content back to providers that require it by @lyingbug in https://github.com/Tencent/WeKnora/pull/1305
  • Fix/issue 1302 mimo reasoning content passthrough by @lyingbug in https://github.com/Tencent/WeKnora/pull/1306
  • chore: release v0.5.2 by @lyingbug in https://github.com/Tencent/WeKnora/pull/1307

New Contributors

  • @toy0116 made their first contribution in https://github.com/Tencent/WeKnora/pull/1116
  • @lFeynman made their first contribution in https://github.com/Tencent/WeKnora/pull/1120
  • @Puma7 made their first contribution in https://github.com/Tencent/WeKnora/pull/1121
  • @guangyang1206 made their first contribution in https://github.com/Tencent/WeKnora/pull/1130
  • @voidborne-d made their first contribution in https://github.com/Tencent/WeKnora/pull/1137
  • @aqilaziz made their first contribution in https://github.com/Tencent/WeKnora/pull/1163
  • @YunfanDu made their first contribution in https://github.com/Tencent/WeKnora/pull/1174
  • @tianlinzx made their first contribution in https://github.com/Tencent/WeKnora/pull/1154
  • @dependabot[bot] made their first contribution in https://github.com/Tencent/WeKnora/pull/1193
  • @langcaiye made their first contribution in https://github.com/Tencent/WeKnora/pull/1184
  • @ymkzs made their first contribution in https://github.com/Tencent/WeKnora/pull/1238
  • @HQF2017 made their first contribution in https://github.com/Tencent/WeKnora/pull/1254

Full Changelog: https://github.com/Tencent/WeKnora/compare/v0.5.1...v0.5.2

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]