v0.3.5

## What's Changed
* fix: guard pg_search update with skip_embedding by @Dounx in https://github.com/Tencent/WeKnora/pull/778
* feat/im optimization by @voidkey in https://github.com/Tencent/WeKnora/pull/774
* feat(dev): fix initial dev environment setup issues by @Dounx in https://github.com/Tencent/WeKnora/pull/779
* fix: add OpenRouter embedding provider support by @Dounx in https://github.com/Tencent/WeKnora/pull/780
* feat: expose builtin parser engine in settings by @Dounx in https://github.com/Tencent/WeKnora/pull/781
* fix: allow temperature 0, default if negative by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/777
* fix: use milvus result set length for empty search results by @Dounx in https://github.com/Tencent/WeKnora/pull/782
* fix: respect global default storage engine when creating knowledge base (#772) by @lyingbug in https://github.com/Tencent/WeKnora/pull/784
* fix: use service name instead of UUID for MCP tool naming (#715) by @lyingbug in https://github.com/Tencent/WeKnora/pull/783
* fix(chat): preserve image markdown during sanitize by @qiangfeidog in https://github.com/Tencent/WeKnora/pull/789
* chore(client): remove redeclared `UserInfo` in client package by @chengjoey in https://github.com/Tencent/WeKnora/pull/792
* fix(frontend): reset page counter when reloading knowledge files by @ChenRussell in https://github.com/Tencent/WeKnora/pull/790
* fix(chat): support native reasoning for vllm by bypassing go-openai limitations by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/791
* feat: add Novita AI as LLM provider by @Alex-wuhu in https://github.com/Tencent/WeKnora/pull/794
* Feat/im new platform by @voidkey in https://github.com/Tencent/WeKnora/pull/796
* fix(rerank): filter empty passages to prevent Aliyun API error by @ChenRussell in https://github.com/Tencent/WeKnora/pull/806
* feat(i18n): add missing locale keys for new features added after #724 by @ochanism in https://github.com/Tencent/WeKnora/pull/804
* fix: use COSINE metric instead of IP for Milvus vector search by @Dounx in https://github.com/Tencent/WeKnora/pull/802
* fix: add missing common.saveSuccess and common.saveFailed i18n keys by @tsukiga-kirei in https://github.com/Tencent/WeKnora/pull/801
* fix(tenant): prevent api_key encryption loss on tenant settings update by @ochanism in https://github.com/Tencent/WeKnora/pull/800
* fix(frontend): fix markdown code block rendering error by @manx98 in https://github.com/Tencent/WeKnora/pull/797
* feat(agent): auto-describe MCP tool result images via VLM by @ochanism in https://github.com/Tencent/WeKnora/pull/808
* feat(agent): add GetSuggestedQuestions API for retrieving agent-specific question suggestions by @lyingbug in https://github.com/Tencent/WeKnora/pull/809
* chore(go.mod): update dependencies to include tiktoken-go and golang.… by @lyingbug in https://github.com/Tencent/WeKnora/pull/810
* feat(security): enhance SSRF protection in RemoteAPIChat by @lyingbug in https://github.com/Tencent/WeKnora/pull/811
* feat: upgrade MiniMax models from M2.1 to M2.7 by @octo-patch in https://github.com/Tencent/WeKnora/pull/812
* fix(app): prevent UTF-8 truncation in summary fallback by @ChenRussell in https://github.com/Tencent/WeKnora/pull/813
* feat(prompt): enhance context and intent classification in templates by @lyingbug in https://github.com/Tencent/WeKnora/pull/814
* Add IM channel Mattermost by @rakaustin in https://github.com/Tencent/WeKnora/pull/820
* fix(agent): prevent empty response when no Knowledge Base is configured by @ochanism in https://github.com/Tencent/WeKnora/pull/819
* fix: marked usage errors by @manx98 in https://github.com/Tencent/WeKnora/pull/816
* chore(release): update version to 0.3.5 by @lyingbug in https://github.com/Tencent/WeKnora/pull/822

## New Contributors
* @Alex-wuhu made their first contribution in https://github.com/Tencent/WeKnora/pull/794
* @octo-patch made their first contribution in https://github.com/Tencent/WeKnora/pull/812
* @rakaustin made their first contribution in https://github.com/Tencent/WeKnora/pull/820

**Full Changelog**: https://github.com/Tencent/WeKnora/compare/v0.3.4...v0.3.5