What's Changed

• hotfix(models): add DeepSeek V4+ model support with reasoning effort by @SiinXu in https://github.com/CherryHQ/cherry-studio/pull/14551
• hotfix(copilot): github copilot model fetch by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/14566
• hotfix(models): add MiMo V2.5 model support by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/14557
• hotfix(deepseek): forward reasoning effort for DeepSeek V4+ via Claude endpoint by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14572
• fix(models): add vision and reasoning_effort support for mistral-small-2603 by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/14541
• hotfix(models): disable temperature and top_p for Kimi K2.6 by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14580
• hotfix(agents): drop @cherry/browser MCP auto-injection by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14571
• hotfix(image-generation): fix gpt-image-2 / gpt-image-1.5 failures and stuck pending placeholder by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14578
• fix(gateway): pass user apiKey to createGateway when fetching models by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/14605
• fix(code-tools): support new-api providers and endpoint type routing for OpenCode by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/14511
• fix(images/edits): default to image/png when file has no extension by @LWWZH in https://github.com/CherryHQ/cherry-studio/pull/14616
• chore: release v1.9.4 by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/14681
• fix(CodeBlock): do not recognize Unix-style paths as clickable links on Windows by @LWWZH in https://github.com/CherryHQ/cherry-studio/pull/14709
• fix(deps): bump @ai-sdk/deepseek to 2.0.30 by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14718
• fix: suppress DeepSeek DSML tags in web search results by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/14721
• fix: parse DeepSeek DSML tool-call markup into AI SDK tool calls by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14747
• fix(deps): omit max_tokens for non-Anthropic models in @ai-sdk/anthropic by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/14749
• fix: refresh openrouter provider patch by @zhibisora in https://github.com/CherryHQ/cherry-studio/pull/14750

New Contributors

• @LWWZH made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/14616

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.3...v1.9.4