What's Changed

• fix(search): prevent empty activeTools when web search is the only tool by @TakotsuboChen in https://github.com/CherryHQ/cherry-studio/pull/14752
• hotfix(vertex): vertex model list fetch and improve service account setup by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/14611
• fix(messages): prevent outer scrolling in horizontal multi-model layout by @Fu-Jumping in https://github.com/CherryHQ/cherry-studio/pull/14768
• fix(reasoning): use enable_thinking param for SiliconFlow DeepSeek/Zhipu models when reasoning_effort is none by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/14782
• feat(claw): add timeout_minutes parameter to cron tool by @xvweirong in https://github.com/CherryHQ/cherry-studio/pull/14707
• hotfix(gateway): bypass @ai-sdk/gateway schema for Vercel model listing by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14772
• fix(api-server): strip trailing /v1 from Anthropic SDK baseURL by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/14818
• hotfix(feishu): use emoji reaction as typing indicator by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14799
• hotfix(i18n): update default assistant and topic names on language switch by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/14607
• fix(anthropic): support Claude Opus 4.7 by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14349
• hotfix(models): update DeepSeek default models to V4 by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/14877
• fix(NewApiPage): restore generated image re-editing by @404-Page-Found in https://github.com/CherryHQ/cherry-studio/pull/14500
• Feat(AIhubmix): painting module add gpt-image-2 to AiHubMix provider by @DDU1222 in https://github.com/CherryHQ/cherry-studio/pull/14903
• hotfix(models):detect routed DeepSeek V4 model slugs for reasoning effort by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/14887
• hotfix(models): support hosted Gemma 4 thinking mode by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/14793
• fix(code-tools): disable opencode built-in auto-update check by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/14925
• hotfix(models): correct Tongyi model icon matching by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/14922
• fix(agent): allow CherryIN OpenAI-protocol models in Agent model picker by @Azure12355 in https://github.com/CherryHQ/cherry-studio/pull/14811
• hotfix(backup): stage restored data into .restore dirs to fix silent data loss on macOS by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14781
• fix: sanitize subprocess call in run_eval.py by @orbisai0security in https://github.com/CherryHQ/cherry-studio/pull/14842
• hotfix(agents): remove stale mcp__browser__* references from agent prompt by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14815
• fix(backup): clean up selection hook before restore relaunch by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/14961
• hotfix(agents): show all sessions and agents in sidebar (#14854) by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14954
• hotfix(agents): report 1M context for DeepSeek V4+ pro on official host by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14965
• chore: release v1.9.5 by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/14963
• hotfix(naming): sanitize non-ASCII characters in provider name for env vars by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/14915

New Contributors

• @TakotsuboChen made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/14752
• @xvweirong made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/14707
• @Azure12355 made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/14811
• @orbisai0security made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/14842

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.4...v1.9.5