Aquesta és una versió anterior. La versió actual és la 2.1.8. Cherry Studio 2.1.8 · Data de publicació:
Fitxers d’instal·lació 1.7.16
| Arquitectura | Tipus | Àmbit | Mida del fitxer | Baixa | SHA256 |
|---|---|---|---|---|---|
| 64 bits | EXE (NSIS) | Usuari actual | — | github.com | VirusTotal |
| 64 bits | EXE (NSIS) | Tots els usuaris | — | github.com | VirusTotal |
| ARM64 | EXE (NSIS) | Usuari actual | — | github.com | VirusTotal |
| ARM64 | EXE (NSIS) | Tots els usuaris | — | github.com | VirusTotal |
L’enllaç i l’SHA256 provenen del manifest comunitari del Gestor de paquets del Windows. Convé comparar el hash del fitxer baixat abans d’executar-lo.
Notes de la versió
What's Changed
- feat: Add PaddleOCR as a new Preprocess provider by @XingweiDeng in https://github.com/CherryHQ/cherry-studio/pull/12067
- fix: Improve provider config type safety and ensure required fields by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/12589
- refactor(agent): improve tool call render ui/ux by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12540
- Update together models URL in providers configuration by @Here-is-Daiyu in https://github.com/CherryHQ/cherry-studio/pull/12597
- fix: Correct reasoning parameters for Aliyun Bailian GLM models and support qwen3-max snapshots by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/12614
- feat: add Kimi K2.5 model support by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/12620
- fix: remove trailing newline when copy from code blocks by @FyLost in https://github.com/CherryHQ/cherry-studio/pull/12624
- fix: Handle :cloud suffix in getLowerBaseModelName for Ollama models by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/12633
- feat: allow Kimi K2.5 to be specified via Model Name by @longyuxi in https://github.com/CherryHQ/cherry-studio/pull/12639
- fix(mcp): prevent infinite loop when refresh token expires by @tdh62 in https://github.com/CherryHQ/cherry-studio/pull/12598
- fix: prevent System Prompt duplication on recursive MCP tool calls by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12643
- docs: fix enterprise url by @TonyRL in https://github.com/CherryHQ/cherry-studio/pull/12666
- fix(agent): prevent claude agent sdk from using bedrock api by @defi-failure in https://github.com/CherryHQ/cherry-studio/pull/12685
- fix: remove quota check by @eeee0717 in https://github.com/CherryHQ/cherry-studio/pull/12634
- fix: handle developer-to-system role conversion for Chat Completions API by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12709
- fix: add toast notification for topic rename failures by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12711
- fix: add placeholder text for image-only assistant messages by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12712
- feat: add plugin package installation from ZIP，directory， remote by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12426
- fix: tool header bug by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12703
- fix: update Kimi/Moonshot provider logos by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12704
- fix(bedrock): reorder content blocks for Claude extended thinking by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12713
- fix: make disk space warning notification closable by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12710
- ci(deps): bump actions/upload-artifact from 5 to 6 by @dependabot[bot] in https://github.com/CherryHQ/cherry-studio/pull/12669
- ci(deps): bump actions/cache from 4 to 5 by @dependabot[bot] in https://github.com/CherryHQ/cherry-studio/pull/12668
- fix(nsis): auto-elevate silent updates for per-machine installations by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/12717
- feat: integrate OpenClaw personal AI assistant by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12705
- feat: Show token usage in bubble mode message headers (#12693) by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/12723
- fix: align hub MCP tools with mcphub (remove search) by @vaayne in https://github.com/CherryHQ/cherry-studio/pull/12571
- fix: format apiHost and and response_format by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12721
- feat: pin TodoWriteTool above inputbar in Agent Session by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12468
- fix(thinking): unify click behavior for multi-level reasoning models by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/12665
- feat: implement CherryIn OAuth by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/12607
New Contributors
- @XingweiDeng made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/12067
- @FyLost made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/12624
- @longyuxi made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/12639
- @tdh62 made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/12598
- @TonyRL made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/12666
Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.7.15...v1.7.16https://github.com/CherryHQ/cherry-studio/releases/tag/v1.7.16
