What's Changed
- perf(repository): exclude embedding field from Elasticsearch search r… by @majinding in #1433
- fix(swagger): Fix some Swagger API endpoints returning 404 errors and regenerate the Swagger documentation by @ChenRussell in #1436
- fix(repository): qualify tenant_id with table name to resolve ambiguous column reference by @ChenRussell in #1435
- fix(frontend): improve tenant settings and member list UX by @lyingbug in #1438
- fix(summary): preserve image caption/OCR text in document summaries by @lyingbug in #1447
- fix (chat history): #1431 Preserve multiline formatting in chat messages by @tranphuongyd in #1446
- feat(frontend): expose KB ↔ vector store binding in editor, list, and detail by @ochanism in #1427
- fix(frontend): keep X-Tenant-ID override when switching back to home by @lyingbug in #1451
- refactor(logger): support LOG_FORMAT template and harden level coloring by @nixidexiangjiao in #1426
- feat(retriever): add OpenSearch type prep ahead of Phase 3 driver by @ochanism in #1445
- feat(wiki): add "View in Graph" entry on wiki page by @lyingbug in #1452
- fix: correct agent selector position under zoom by @shenDv6 in #1459
- fix(frontend): correct floating UI positioning under root
zoom(follow-up to #1459) by @lyingbug in #1460 - fix(chat): stabilize tool ordering and report cached prompt tokens by @young1lin in #1463
- 修复客户端模型类型枚举 by @cn-kali-team in #1464
- fix: skip empty milvus enabled status groups by @wolfkill in #1462
- 增加sandbox对windows编译支持，现在默认是linux的实现，windows直接编译报错 by @Hitvz in #1434
- refactor(knowledge): route single delete through async pipeline by @lyingbug in #1467
- feat(chunk): support filtering chunks by multiple chunk_type params by @lyingbug in #1470
- feat(docreader): improve web parser for WeChat Official Account articles by @lyingbug in #1473
- refactor(chunk): remove unused VideoInfo field from Chunk struct by @lyingbug in #1472
- refactor(knowledge): make checkStorageEngineConfigured a service method with global file-service fallback by @lyingbug in #1471
- feat(frontend): consolidate KB metadata into an info popover by @lyingbug in #1478
- fix: respect multi-turn-disabled flag in KnowledgeQA pipeline by @lyingbug in #1480
- feat(builtin-models): add YAML-based declarative config with ${ENV} interpolation by @jackson-jia-914 in #1453
- feat(builtin-models): add YAML lifecycle (delete, resurrect, default invariant) on top of #1453 by @lyingbug in #1483
- fix(frontend): apply default context template when switching to quick-answer mode by @HelloAndyZhang in #1492
- fix(input-field): wrong toast when selecting built-in agents other than quick-answer / smart-reasoning by @jackson-jia-914 in #1489
- fix(doris): inline LIMIT/OFFSET as literals and enable parameter inte… by @SilentMil in #1488
- feat(agent): add intent prompt customization in agent editor by @HelloAndyZhang in #1491
- fix(pipeline): fallback to raw retrieval results when rerank API fails by @ChenRussell in #1484
- fix(datasource): support Yuque team token in connector by @Once-the-sea-was-difficult-for-water in #1477
- feat(retriever): add OpenSearch driver skeleton with gated interface stubs by @ochanism in #1481
- fix(agent): preserve agent intent prompt whitespace and add tests by @lyingbug in #1494
- feat(system): unified system administration console + platform audit log by @lyingbug in #1493
- feat(cli)!: v0.7 agent-first wire contract + command-surface cleanup by @voidkey in #1475
- feat(settings): regroup sidebar nav and redesign model card by @lyingbug in #1495
- fix(im): recover from deleted session when GetSession returns app sentinel (#1499) by @lyingbug in #1500
- feat(rbac): add multi-use share-link invitations for invite_only mode by @lyingbug in #1504
- refactor(qdrant): optimize batch save, map iteration, and error wrapping by @sheep44044 in #1508
- fix(agent): harden tool parameter parsing against LLM type mismatches by @caiyuze-cpu in #1505
- feat(retriever): implement OpenSearch driver read/write paths by @ochanism in #1482
- fix(im): make presigned URL flow diagnosable end-to-end by @lyingbug in #1507
- fix(knowledge): prevent stuck parsing with span-tree progress tracking by @lyingbug in #1503
- feat(knowledge-base): integrate trace availability checks and enhance UI interactions by @lyingbug in #1514
- fix: add model display name by @wolfkill in #1523
- fix: show agent id in editor by @wolfkill in #1521
- feat(cli): v0.8 — --dry-run, MCP annotations, session continue-stream by @voidkey in #1510
- feat: add knowledge parse cancellation with finalizing post-process state by @lyingbug in #1522
- fix: apply document process timeout to asynq tasks by @HelloWeit in #1525
- test: add document process task options tests by @lyingbug in #1529
- feat(frontend): improve agent/KB editor ID display and intent prompts UX by @lyingbug in #1532
- fix(im,kb): storage URL rewriting and tenant default KB storage by @lyingbug in #1540
- feat(frontend): enhance IMChannelsOverviewPanel layout and functionality by @lyingbug in #1543
- fix(knowledgeBase): improve tag loading logic and ensure consistent behavior by @lyingbug in #1544
- fix(container): correct resetPendingTasks SQL on startup by @lyingbug in #1538
- fix(knowledgeBase): improve tag loading logic and ensure consistent behavior by @lyingbug in #1545
- feat(retriever): activate OpenSearch k-NN driver (PR 3 of 3) by @ochanism in #1542
- feat(mcp): expose read-only wiki tools via Python MCP server by @zhuzhaoyun in #1502
- feat(mcp-server): add multi-transport support and restore session configuration by @SilentMil in #1490
- fix: avoid stale knowledge records on upload failure by @wolfkill in #1537
- fix: scrub inline image payloads before embedding by @wolfkill in #1536
- refactor(keywords_vector_hybrid_indexer): enhance image payload sanitization logic by @lyingbug in #1546
- feat(migrations): add display_name column to models table by @lyingbug in #1547
- fix(knowledge): unstick summary and isolate manual re-index trace attempts by @lyingbug in #1548
- feat(knowledge): add stop-parse button to the trace timeline panel by @lyingbug in #1549
- feat(knowledge): count wiki ingest in the finalizing subtask counter by @lyingbug in #1550
- fix(chat): keep in-progress message reactive so continue-stream renders by @lyingbug in #1553
- fix(knowledge): make finalizing subtask counter reliable + async question fan-out by @lyingbug in #1552
- fix(knowledge): wrap locale code with LanguageLocaleName in wiki ingest prompts by @jackson-jia-914 in #1554
- fix(knowledge): stitch chunks by text overlap, not by position by @lyingbug in #1555
- refactor(settings): unify drawer style across model/parser/storage/vector/websearch/mcp by @lyingbug in #1558
- refactor(settings): enhance card interactions and accessibility across components by @lyingbug in #1561
- fix(doc_parser): enhance DOC to DOCX conversion reliability by @lyingbug in #1566
- feat(chat): implement local image resolver for multimodal chat by @lyingbug in #1567
- fix(embedding): support native Gemini embeddings by @ziwon in #1571
- feat: add MiniMax-M3 to provider model list by @octo-patch in #1569
- chore(deps): bump github.com/mattn/go-runewidth from 0.0.23 to 0.0.24 in /cli in the cli-deps group by @dependabot[bot] in #1572
- feat(tour): implement new user guide component and integrate into user menu by @lyingbug in #1578
- feat(docreader): scanned PDF streaming, task queues, and parser engines by @lyingbug in #1583
- feat(contextualGuides): add multiple contextual guide components for agent and knowledge base creation by @lyingbug in #1585
- fix: deep-copy stored files and images when cloning a knowledge base by @ochanism in #1574
- fix: validate vector store connection addresses against SSRF policy by @ochanism in #1596
- fix(dev): use writable local storage path by @langcaiye in #1593
- fix: skip credential validation when editing data source by @langcaiye in #1588
- feat: support Feishu wiki node resources by @langcaiye in #1587
- fix(datasource): align Feishu connector capabilities by @langcaiye in #1586
- fix(event): add panic recovery to async goroutines by @gordonlu in #1581
- refactor(agent): remove final_answer tool references and update related logic by @lyingbug in #1597
- fix(im): inject synthetic identity so IM channels can use shared KBs by @lyingbug in #1601
- feat(lkeap): integrate Tencent Cloud LKEAP Rerank support by @lyingbug in #1602
- fix(frontend): pass {size} param to fileSizeExceeded i18n on Nginx 413 by @jackson-jia-914 in #1598
- fix: preserve agent system prompt for greetings by @wolfkill in #1527
- Revert "fix: preserve agent system prompt for greetings" by @lyingbug in #1603
- fix(datasource): fail sync when all fetched items fail by @langcaiye in #1599
- feat(faq): enhance FAQ handling and localization support by @lyingbug in #1607
- feat(thinkingControl): implement thinking mode configuration in model editor by @lyingbug in #1613
- fix(handler): /knowledge/search — accept ?query= alias, reject empty keyword by @toy0116 in #1612
- fix: reject cross-store reuse_vectors knowledge move by @ochanism in #1611
- feat: support Milvus database selection for vector stores by @LiRuihaoA in #1608
- fix(schema): expand knowledge source length by @langcaiye in #1605
- feat: release v0.6.1 by @lyingbug in #1614
New Contributors
- @majinding made their first contribution in #1433
- @tranphuongyd made their first contribution in #1446
- @shenDv6 made their first contribution in #1459
- @young1lin made their first contribution in #1463
- @Hitvz made their first contribution in #1434
- @jackson-jia-914 made their first contribution in #1453
- @HelloAndyZhang made their first contribution in #1492
- @Once-the-sea-was-difficult-for-water made their first contribution in #1477
- @sheep44044 made their first contribution in #1508
- @zhuzhaoyun made their first contribution in #1502
- @ziwon made their first contribution in #1571
- @gordonlu made their first contribution in #1581
- @LiRuihaoA made their first contribution in #1608
Full Changelog: v0.6.0...v0.6.1