# cherry-studio changelog

> cherry-studio release notes.

- Vendor: cherry-studio
- Category: AI
- Official site: https://cherryai.com/
- Tracked by: What's New (https://whatsnew.fyi/product/cherry-studio)
- Harvested from: GitHub (CherryHQ/cherry-studio)
- Entries below: 10 (newest first)

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

## Releases

### v2.0.0-rc.1

- Date: 2026-07-28
- Version: v2.0.0-rc.1
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v2.0.0-rc.1
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v2.0.0-rc.1
- Labels: Pre-release

- **fixed** — Allow selecting Markdown files from import hint in notes
- **fixed** — Filter non-chat model choices in onboarding
- **fixed** — Include sqlite-vec in portable Windows builds
- **fixed** — Stabilize topic and session image export in message capture
- **fixed** — Install both CPU architectures so x64 macOS builds ship sharp
- **fixed** — Preserve migrated custom apps and icon sizing in mini-app
- **fixed** — Preserve provider display names in provider models
- **fixed** — Skip macOS process transform for workspace-visible windows in window registry
- **fixed** — Improve trigram BM25 queries in knowledge search
- **fixed** — Keep Bedrock auth modes switchable in provider settings
- **fixed** — Show interrupted empty replies in message rendering
- **fixed** — Preserve streams across tab switches in AI transport
- **fixed** — Deduplicate custom size option in paintings
- **fixed** — Correct user message presentation in quick assistant
- **fixed** — Keep prompt fixed during image transforms in paintings
- **fixed** — Stabilize regeneration and image export in message list
- **added** — Select knowledge bases from the input in agent composer
- **added** — Sync skill catalog from disk so authored skills appear in agent skills
- **added** — Warn before contextual model switches in agent chat
- **added** — Add cost analytics and durable usage records in AI usage

##### What's Changed
* fix(notes): allow selecting Markdown files from import hint by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17527
* fix(onboarding): filter non-chat model choices by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17526
* fix(windows-packaging): include sqlite-vec in portable builds by @eeee0717 in https://github.com/CherryHQ/cherry-studio/pull/17521
* fix(message-capture): stabilize topic and session image export by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17523
* fix(build): install both cpu arches so x64 macOS builds ship sharp by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17419
* fix(mini-app): preserve migrated custom apps and icon sizing by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17522
* fix(provider-models): preserve provider display names by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17462
* fix(window-registry): skip macOS process transform for workspace-visible windows by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/17528
* fix(knowledge-search): improve trigram BM25 queries by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/17511
* fix(provider-settings): keep Bedrock auth modes switchable by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17534
* fix(message-rendering): show interrupted empty replies by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17533
* fix(ai-transport): preserve streams across tab switches by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17514
* refactor(path-registry): remove media directory keys by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17541
* fix(paintings): deduplicate custom size option by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/17540
* fix(quick-assistant): correct user message presentation by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17532
* fix(paintings): keep prompt fixed during image transforms by @Pleasurecruise in https://github.com/CherryHQ/cherry-studio/pull/17518
* feat(agent-composer): select knowledge bases from the input by @eeee0717 in https://github.com/CherryHQ/cherry-studio/pull/17493
* fix(message-list): stabilize regeneration and image export by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17544
* feat(agent-skills): sync skill catalog from disk so authored skills appear by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17134
* feat(agent-chat): warn before contextual model switches by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17529
* fix(file-preview): avoid false binary detection for Unicode text by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17551
* fix(new-conversation-icon): use thinner scalable strokes by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17552
* fix(agent-migration): handle Windows workspace links by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17542
* feat(ai-usage): add cost analytics and durable usage records by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/15992
* fix(composer): preserve follow-up queue pause across conversations by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/17487
* fix(global-search): keep input focused after clearing by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/17468
* fix(agent-seeding): leave default agent model unconfigured by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17554
* refactor(data-migration): consolidate v2 storage layout by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17553
* feat(paintings): reveal generated images through sampled grid by @SiinXu in https://github.com/CherryHQ/cherry-studio/pull/17548
* fix(data-migration): skip existing Claude config directory by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17556
* feat

_[Truncated at 4000 characters — full notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v2.0.0-rc.1]_

### v2.0.0-beta.3

- Date: 2026-07-28
- Version: v2.0.0-beta.3
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v2.0.0-beta.3
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v2.0.0-beta.3
- Labels: Pre-release

- **fixed** — Validate renderer URL origins in window navigation
- **added** — Add managed CLI discovery and installation for agent-cli
- **changed** — Disable model thinking for translation when supported
- **fixed** — Keep AskUserQuestion interactive in claude-code
- **fixed** — Create channels inactive so credential-gated types can be added
- **fixed** — Keep empty skills identity stable while the query loads
- **fixed** — Refine global-search reveal and composer toolbar behavior
- **fixed** — Stabilize streamed process history in message-renderer
- **fixed** — Prompt when model is missing in agent-composer
- **changed** — Pass model contextWindow as num_ctx in Ollama API requests
- **fixed** — Preserve state across approval overrides in composer
- **fixed** — Preserve and render composer knowledge tools in chat
- **fixed** — Mask generated API key in api-gateway
- **added** — Show client ID in developer mode in system-settings
- **changed** — Rename Code Switch across locales
- **fixed** — Support interactive QR authentication in agent-channels
- **fixed** — Freeze chat topic titles after AI or manual naming
- **added** — Mask API key and Authorization Header with a reveal toggle in api-gateway
- **added** — Offer a v1 download when a retried migration fails again
- **fixed** — Apply registry updates to existing provider model configurations

> [!WARNING]
> This Beta is not stable and is intended for testing only. Do not use it as a replacement for Cherry Studio v1. Data created by v2 may be cleared in later Beta releases or the final v2 release.
>
> 此 Beta 版本尚不稳定，仅供测试使用，请勿将其作为 Cherry Studio v1 的替代版本。v2 产生的数据可能会在后续 Beta 版本或 v2 正式版发布时被清除。

##### What's Changed
* fix(window-navigation): validate renderer URL origins by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/17456
* feat(agent-cli): add managed CLI discovery and installation by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17449
* feat(translate): disable model thinking for translation when supported by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17333
* fix(claude-code): keep AskUserQuestion interactive by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17451
* fix(channels-settings): create channels inactive so credential-gated types can be added by @vaayne in https://github.com/CherryHQ/cherry-studio/pull/17481
* fix(skills): keep empty skills identity stable while the query loads by @vaayne in https://github.com/CherryHQ/cherry-studio/pull/17488
* fix(ui): refine global-search reveal and composer toolbar behavior by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17478
* fix(message-renderer): stabilize streamed process history by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17475
* fix(agent-composer): prompt when model is missing by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17491
* feat(ollama): pass model contextWindow as num_ctx in API requests by @ccl125 in https://github.com/CherryHQ/cherry-studio/pull/17413
* fix(composer): preserve state across approval overrides by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17479
* fix(chat): preserve and render composer knowledge tools by @eeee0717 in https://github.com/CherryHQ/cherry-studio/pull/17466
* fix(api-gateway): mask generated API key by @Pleasurecruise in https://github.com/CherryHQ/cherry-studio/pull/17483
* chore(package-scripts): replace npm run with pnpm run in package.json scripts by @beyondkmp in https://github.com/CherryHQ/cherry-studio/pull/17464
* feat(system-settings): show client ID in developer mode by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17489
* feat(code-mate): rename Code Switch across locales by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17498
* fix(agent-channels): support interactive QR authentication by @Pleasurecruise in https://github.com/CherryHQ/cherry-studio/pull/17473
* fix(topic-naming): freeze chat topic titles after AI or manual naming by @kennyzheng-builds in https://github.com/CherryHQ/cherry-studio/pull/17404
* feat(api-gateway): mask API key + Authorization Header with a reveal toggle by @kennyzheng-builds in https://github.com/CherryHQ/cherry-studio/pull/17492
* feat(migration-v2): offer a v1 download when a retried migration fails again by @eeee0717 in https://github.com/CherryHQ/cherry-studio/pull/17484
* fix(provider-model): apply registry updates to existing configurations by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17442
* refactor(agent-storage): decouple agent data from workspaces by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17450
* 🤖 Daily Auto I18N Sync: Jul 28, 2026 by @github-actions[bot] in https://github.com/CherryHQ/cherry-studio/pull/17510
* Add MiniMax image generation support by @octo-patch in https://github.com/CherryHQ/cherry-studio/pull/17417
* fix(code-cli): normalize Claude Code Anthropic endpoints by @Pleasurecruise in https://github.com/CherryHQ/cherry-studio/pull/17480
* fix(privacy): allow use without policy consent by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17497
* fix(ui): highlight the current selection when a Combobox opens by @kennyzheng-builds in https://github.com/CherryHQ/cherry-studio/pull/17502
* refactor(conversation): co

_[Truncated at 4000 characters — full notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v2.0.0-beta.3]_

### v2.0.0-beta.2

- Date: 2026-07-27
- Version: v2.0.0-beta.2
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v2.0.0-beta.2
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v2.0.0-beta.2
- Labels: Pre-release

- **added** — Unify collection empty states with v1-style illustrations
- **added** — Clearer stream-status indicators and awaiting-approval badge in session list
- **fixed** — Accept nullable Bocha response fields in web search
- **fixed** — Make read_file offset/limit schema Gemini-compatible in builtin tools
- **fixed** — Delay conversation link preview cards in chat
- **changed** — Adopt Chrome-style tab context menu and close behavior
- **fixed** — Identify models in multi-model replies
- **added** — Enable transparent windows by default on macOS
- **fixed** — Localize initial agent name for Chinese systems in cherry assistant
- **added** — Add copy action to span details in trace
- **added** — Warmer runtime copy and rolling reasoning preview in agent message
- **fixed** — Constrain opacity slider height in selection assistant
- **fixed** — Make local embeddings opt-in on creation in knowledge
- **fixed** — Preserve models for recalled prompts in composer
- **fixed** — Preserve artifact pane visuals across themes and tabs in right pane
- **added** — Reference topics and sessions as @ mention context tokens in composer
- **added** — Doubao and Bailian catalog enrichment with built-in web search
- **added** — Bind knowledge bases with assistant-parity scoping in agent
- **added** — Surface Claude SDK api_retry as ephemeral status in agent session
- **fixed** — Prevent command injection and path traversal in addModel

> [!WARNING]
> This Beta is not stable and is intended for testing only. Do not use it as a replacement for Cherry Studio v1. Data created by v2 may be cleared in later Beta releases or the final v2 release.
>
> 此 Beta 版本尚不稳定，仅供测试使用，请勿将其作为 Cherry Studio v1 的替代版本。v2 产生的数据可能会在后续 Beta 版本或 v2 正式版发布时被清除。

##### What's Changed
* feat(empty-states): unify collection empty states with v1-style illustrations by @kennyzheng-builds in https://github.com/CherryHQ/cherry-studio/pull/17105
* 🤖 Daily Auto I18N Sync: Jul 25, 2026 by @github-actions[bot] in https://github.com/CherryHQ/cherry-studio/pull/17373
* feat(session-list): clearer stream-status indicators and awaiting-approval badge by @kennyzheng-builds in https://github.com/CherryHQ/cherry-studio/pull/17040
* fix(web-search): accept nullable Bocha response fields by @AtomsH4 in https://github.com/CherryHQ/cherry-studio/pull/17378
* fix(builtin-tools): make read_file offset/limit schema Gemini-compatible by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17384
* fix(chat): delay conversation link preview cards by @AtomsH4 in https://github.com/CherryHQ/cherry-studio/pull/17385
* refactor(tabs): adopt Chrome-style tab context menu and close behavior by @kennyzheng-builds in https://github.com/CherryHQ/cherry-studio/pull/17021
* fix(chat): identify models in multi-model replies by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/17381
* feat(window-style): enable transparent windows by default on macOS by @AtomsH4 in https://github.com/CherryHQ/cherry-studio/pull/17350
* fix(cherry-assistant): localize initial agent name for Chinese systems by @AtomsH4 in https://github.com/CherryHQ/cherry-studio/pull/17376
* chore(deps): bump claude-agent-sdk to 0.3.218 and fix agent session reporting by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17380
* ci(preview-build): remove v2 daily preview workflow by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/17390
* feat(trace): add copy action to span details by @AtomsH4 in https://github.com/CherryHQ/cherry-studio/pull/17386
* feat(agent-message): warmer runtime copy and rolling reasoning preview by @SiinXu in https://github.com/CherryHQ/cherry-studio/pull/17312
* fix(selection-assistant): constrain opacity slider height by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/17395
* fix(knowledge): make local embeddings opt-in on creation by @eeee0717 in https://github.com/CherryHQ/cherry-studio/pull/17396
* fix(composer): preserve models for recalled prompts by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/17369
* fix(right-pane): preserve artifact pane visuals across themes and tabs by @AtomsH4 in https://github.com/CherryHQ/cherry-studio/pull/17401
* feat(composer): reference topics and sessions as @ mention context tokens by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17368
* feat(provider): Doubao & Bailian catalog enrichment + built-in web search by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17360
* fix(main-window): register web-contents-created context menu listener once by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/17337
* feat(agent): bind knowledge bases with assistant-parity scoping by @eeee0717 in https://github.com/CherryHQ/cherry-studio/pull/17147
* feat(agent-session): surface Claude SDK api_retry as ephemeral status by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/17099
* perf(conversation): stage initial rendering and share resource data by @zhangjiadi225 in https://github.com/CherryHQ/cherry-studio/pull/17382
* feat(data-settings): make Data Reset a real v2 userData wipe by @vaayne in https://github.com/CherryHQ/cherry-studio/pull/17138
* refactor(file-types): unify filesystem path types as Zod brands by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/16740
* fix(ovms): prevent command injection and path traversal in addModel by @kovsu in https://github.com/CherryHQ/

_[Truncated at 4000 characters — full notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v2.0.0-beta.2]_

### v2.0.0-beta.1

- Date: 2026-07-24
- Version: v2.0.0-beta.1
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v2.0.0-beta.1
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v2.0.0-beta.1
- Labels: Pre-release

- **added** — Upgraded interface with new interactions and visual design for chats, roles, projects, and tasks
- **added** — Multi-window and split-view layouts for multitasking and switching between work and reviewing progress
- **added** — Support for both OpenAI and Anthropic endpoints
- **added** — Built-in Agent runtime core, reducing dependency installation and environment setup
- **added** — Agents can read and maintain knowledge bases
- **added** — Code tools upgraded to Code Mate with one-click model service configuration
- **added** — Image generation dynamically shows parameters available for each model
- **changed** — Data foundation upgraded for improved responsiveness with extensive history
- **fixed** — Smoother scrolling in very long conversations
- **fixed** — Large-folder imports no longer block the interface

> [!WARNING]
> This Beta is not stable and is intended for testing only. Do not use it as a replacement for Cherry Studio v1. Data created by v2 may be cleared in later Beta releases or the final v2 release.
>
> 此 Beta 版本尚不稳定，仅供测试使用，请勿将其作为 Cherry Studio v1 的替代版本。v2 产生的数据可能会在后续 Beta 版本或 v2 正式版发布时被清除。

Cherry Studio 2.0.0-beta.1 - A New AI Workspace, from Chat to Getting Work Done

✨ New Interface, New Experience
- Upgraded interactions and visual design make chats, roles, projects, and tasks clearer and easier to organize
- Built for multitasking, with multi-window and split-view layouts for switching between work and reviewing progress and deliverables

🤖 More Powerful Agents
- Supports both OpenAI and Anthropic endpoints, reuses Claude and Codex subscriptions, and works with more models
- The core Agent runtime is built in, greatly reducing dependency installation and environment setup
- Complete research, documents, presentations, data analysis, and coding faster, with one-click previews of results

🛠️ More Tool Upgrades
- Agents can read and maintain knowledge bases, helping your knowledge grow continuously like a Wiki
- Code tools are upgraded to Code Mate, with one-click model service configuration for Claude Code, Codex, and more
- Image generation dynamically shows the parameters available for each model, making results easier to control

⚡ Performance
- A fully upgraded data foundation stays responsive even with extensive history
- Smoother scrolling in very long conversations, while large-folder imports no longer block the interface

### v1.9.12

- Date: 2026-07-05
- Version: v1.9.12
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v1.9.12
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v1.9.12

- **fixed** — Forward DeepSeek V4+ reasoning_effort for openai-compatible providers
- **fixed** — Support Claude Fable series and Opus 5 in capability detection
- **fixed** — Add Anthropic native /v1/models fetcher
- **fixed** — Prevent AccordionTrigger toggle when clicking approval buttons in collapsed group header
- **fixed** — Use anthropicApiHost for NewAPI provider's anthropic endpoint
- **fixed** — Inject Cherry Studio identity headers into agent mode requests
- **fixed** — Support downloading SVG data URL images blocked by CSP
- **fixed** — Restore leading dot in ext for saveBase64Image and savePastedImage
- **fixed** — Correct MiniMax-M3 thinking control
- **added** — Add Kimi K2.7 Code support
- **fixed** — Surface abnormal stream finish reasons as error chunks
- **fixed** — Preserve full URLs and parse Highlights in ExaMCP results
- **fixed** — Recover claude-code install when native binary is missing
- **fixed** — Derive Gemini baseURL from configured baseURL in aihubmix
- **fixed** — Use first configured key for claude code agents
- **fixed** — Use fs.statfs for disk info to stop powershell process leak
- **changed** — Redirect provider links to inferera and follow configured base URL in aihubmix
- **fixed** — Hide CherryIN manual model add button

##### What's Changed
* fix: forward DeepSeek V4+ reasoning_effort for openai-compatible providers by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/15834
* fix(model): support Claude Fable series and Opus 5 in capability detection by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/15872
* fix(models): add Anthropic native /v1/models fetcher(target V1 branch) by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/15779
* fix(tools): prevent AccordionTrigger toggle when clicking approval buttons in collapsed group header by @LWWZH in https://github.com/CherryHQ/cherry-studio/pull/15839
* fix: use anthropicApiHost for NewAPI provider's anthropic endpoint by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/15934
* fix(agents): inject Cherry Studio identity headers into agent mode requests by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/15978
* fix: support downloading SVG data URL images blocked by CSP by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/15301
* fix(file): restore leading dot in ext for saveBase64Image and savePastedImage by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/14668
* fix(reasoning): correct MiniMax-M3 thinking control by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15991
* feat(models): add Kimi K2.7 Code support by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/16017
* fix(ai-core): surface abnormal stream finish reasons as error chunks by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/16079
* fix(websearch): preserve full URLs and parse Highlights in ExaMCP results by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/15329
* fix: recover claude-code install when native binary is missing by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/15369
* fix(aihubmix): derive Gemini baseURL from configured baseURL by @DDU1222 in https://github.com/CherryHQ/cherry-studio/pull/16371
* fix: use first configured key for claude code agents by @zhibisora in https://github.com/CherryHQ/cherry-studio/pull/16437
* fix: use fs.statfs for disk info to stop powershell process leak by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/16556
* feat(aihubmix): redirect provider links to inferera and follow configured base URL by @DDU1222 in https://github.com/CherryHQ/cherry-studio/pull/16606
* fix: hide CherryIN manual model add button by @zhibisora in https://github.com/CherryHQ/cherry-studio/pull/16703


**Full Changelog**: https://github.com/CherryHQ/cherry-studio/compare/v1.9.11...v1.9.12

### v1.9.11

- Date: 2026-06-07
- Version: v1.9.11
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v1.9.11
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v1.9.11

- **removed** — Prune legacy MiniMax models, keeping only M2.7 and M3
- **fixed** — Encode gemini model list API key
- **fixed** — Infer custom provider model groups
- **fixed** — Clean up agent session messages on delete
- **fixed** — Fix oversized text in Gemini mini-program due to Electron UA detection
- **added** — Add MiniMax M3 thinking process support
- **added** — Support Anthropic Opus 4.8 adaptive thinking
- **changed** — Use openPath instead of openExternal for HTML artifacts external browser
- **fixed** — Avoid embedding dimensions request parameter
- **fixed** — Bind CherryIN OAuth flow to sender
- **fixed** — Upgrade mermaid to 11.15.0 to fix CJK parsing error in flowcharts
- **fixed** — Fix agent task completed but task list still shows unchecked items

##### What's Changed
* chore(models): prune legacy MiniMax models, keep M2.7 and M3 by @kapelame in https://github.com/CherryHQ/cherry-studio/pull/15580
* fix: encode gemini model list api key by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15575
* fix: infer custom provider model groups by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15577
* fix: clean up agent session messages on delete by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15531
* fix: oversized text in Gemini mini-program due to Electron UA detection by @LWWZH in https://github.com/CherryHQ/cherry-studio/pull/15389
* fix(reasoning): add MiniMax M3 thinking process support (v1.9.8) by @HUQIANTAO in https://github.com/CherryHQ/cherry-studio/pull/15513
* fix(anthropic): support Opus 4.8 adaptive thinking by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15532
* fix: use openPath instead of openExternal for HTML artifacts external browser by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/15644
* fix: avoid embedding dimensions request parameter by @eeee0717 in https://github.com/CherryHQ/cherry-studio/pull/15727
* fix: bind CherryIN OAuth flow to sender by @3em0 in https://github.com/CherryHQ/cherry-studio/pull/15410
* fix: upgrade mermaid to 11.15.0 to fix CJK parsing error in flowcharts by @LWWZH in https://github.com/CherryHQ/cherry-studio/pull/15391
* fix: agent task completed but task list still shows unchecked items by @LWWZH in https://github.com/CherryHQ/cherry-studio/pull/15358

##### New Contributors
* @3em0 made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/15410

**Full Changelog**: https://github.com/CherryHQ/cherry-studio/compare/v1.9.9...v1.9.11

### v1.9.9

- Date: 2026-06-02
- Version: v1.9.9
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v1.9.9
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v1.9.9

- **fixed** — Guard OV OCR availability CPU detection
- **fixed** — Respect topic naming setting for agent sessions
- **added** — Add MiniMax M3 to the system model registry

##### What's Changed
* fix: guard OV OCR availability CPU detection by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15538
* fix: respect topic naming setting for agent sessions by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15533
* feat(models): add MiniMax M3 to the system model registry by @kapelame in https://github.com/CherryHQ/cherry-studio/pull/15543

##### New Contributors
* @kapelame made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/15543

**Full Changelog**: https://github.com/CherryHQ/cherry-studio/compare/v1.9.8...v1.9.9

### v1.9.8

- Date: 2026-05-31
- Version: v1.9.8
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v1.9.8
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v1.9.8

- **fixed** — Add v1 branch to workflow triggers
- **changed** — Update tool components for improved styling and functionality

##### What's Changed
* fix(ci): add v1 branch to workflow triggers by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/15446
* refactor: update tool components for improved styling and functionality


**Full Changelog**: https://github.com/CherryHQ/cherry-studio/compare/v1.9.7...v1.9.8

### v1.9.7

- Date: 2026-05-28
- Version: v1.9.7
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v1.9.7
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v1.9.7

- **fixed** — Clarify OpenClaw external install prompt
- **fixed** — Support Grok 4.3 reasoning effort in xAI responses
- **fixed** — Keep light theme tokens readable in code view
- **fixed** — Apply [1m] context suffix for DeepSeek V4 Flash and MiMo V2.5+ in claudecode
- **fixed** — Pass custom headers to claude code in agents
- **fixed** — Launch opencode from package-local executable
- **fixed** — Align Gemini 3.x UI and sampling handling
- **fixed** — Add missing key prop to SendMessageButton in InputbarCore
- **fixed** — Correct provider ID for AIHubMix reasoning effort
- **added** — Support StepFun as Anthropic-compatible provider
- **fixed** — Support capabilities for grok-build-0.1
- **fixed** — Exclude Qwen max series from vision model detection
- **fixed** — Respect enableDataCollection setting in renderer for analytics
- **fixed** — Do not treat Gemini model via non-Gemini provider as native PDF
- **fixed** — Align ExaMCP response parser with server field names in websearch
- **fixed** — Add CherryIN DeepSeek 1m suffix
- **fixed** — Keep note toolbar static at top during scroll
- **changed** — Change Gemini Safety Settings to BLOCK_NONE
- **fixed** — Refresh cached miniapp URLs

##### What's Changed
* fix: clarify OpenClaw external install prompt by @mturac in https://github.com/CherryHQ/cherry-studio/pull/15147
* fix: support Grok 4.3 reasoning effort in xAI responses by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/15137
* fix(code): keep light theme tokens readable by @mturac in https://github.com/CherryHQ/cherry-studio/pull/15143
* fix(claudecode): apply [1m] context suffix for DeepSeek V4 Flash and MiMo V2.5+ by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/15162
* fix(agents): pass custom headers to claude code by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/15185
* fix: launch opencode from package-local executable by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/15188
* hotfix(model): align Gemini 3.x UI and sampling handling by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/15204
* chore(gitignore): Ignore Antigravity CLI local files by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/15201
* fix: add missing key prop to SendMessageButton in InputbarCore by @LGiki in https://github.com/CherryHQ/cherry-studio/pull/15233
* fix: correct provider ID for AIHubMix reasoning effort by @xxiaoxiong in https://github.com/CherryHQ/cherry-studio/pull/15283
* fix(provider): support StepFun as Anthropic-compatible provider by @lianshuang-photo in https://github.com/CherryHQ/cherry-studio/pull/15277
* hotfix(models): support capabilities for grok-build-0.1 by @ousugo in https://github.com/CherryHQ/cherry-studio/pull/15256
* fix(models): exclude Qwen max series from vision model detection by @xxiaoxiong in https://github.com/CherryHQ/cherry-studio/pull/15288
* fix(analytics): respect enableDataCollection setting in renderer by @EurFelux in https://github.com/CherryHQ/cherry-studio/pull/15318
* fix(aiCore): do not treat Gemini model via non-Gemini provider as native PDF by @octo-patch in https://github.com/CherryHQ/cherry-studio/pull/14329
* fix(websearch): align ExaMCP response parser with server field names by @zhibisora in https://github.com/CherryHQ/cherry-studio/pull/15331
* fix: add CherryIN DeepSeek 1m suffix by @zhibisora in https://github.com/CherryHQ/cherry-studio/pull/15352
* hotfix(ci): run GitCode sync on signing runner by @zhibisora in https://github.com/CherryHQ/cherry-studio/pull/15324
* chore: release v1.9.7 by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15362
* fix: keep note toolbar static at top during scroll by @LWWZH in https://github.com/CherryHQ/cherry-studio/pull/15349
* Fix: change Gemini Safety Settings to BLOCK_NONE - For main by @ous50 in https://github.com/CherryHQ/cherry-studio/pull/15303
* fix: refresh cached miniapp urls by @mturac in https://github.com/CherryHQ/cherry-studio/pull/15146

##### New Contributors
* @mturac made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/15147
* @LGiki made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/15233
* @xxiaoxiong made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/15283

**Full Changelog**: https://github.com/CherryHQ/cherry-studio/compare/v1.9.6...v1.9.7

### v1.9.6

- Date: 2026-05-15
- Version: v1.9.6
- Original notes: https://github.com/CherryHQ/cherry-studio/releases/tag/v1.9.6
- Permalink: https://whatsnew.fyi/product/cherry-studio/releases/v1.9.6

- **fixed** — Preserve HTTP URLs in knowledge base documents
- **fixed** — Thread idle timeout handle to stream chunk adapter
- **fixed** — Improve GitCode sync reliability
- **fixed** — Convert assistant image blocks to base64 for multi-turn editing
- **fixed** — Invalidate provider cache on settings changes
- **fixed** — Recognize ctrl by uniKey value
- **fixed** — Prevent crash when model.provider not found
- **fixed** — Align provider model list actions
- **fixed** — Use task name as session name for cron task sessions
- **fixed** — Resolve ENOENT in OpenMinerU preprocessing caused by MinerU ZIP structure change
- **fixed** — Clean up OAuth tokens when deleting MCP server
- **fixed** — Exclude deepseek-r1 models from function_calling capability
- **fixed** — Auto-expand MCP tool approval card so action buttons are immediately visible
- **fixed** — Add environment variable for claude code provider management
- **fixed** — Preserve updatedAt timestamps when creating new agents
- **fixed** — Qiniu PDF fallback for GPT-5.4
- **fixed** — Handle Codex CLI reserved provider IDs

##### What's Changed
* fix(knowledge): preserve HTTP URLs in knowledge base documents by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/14983
* fix(ai): thread idle timeout handle to stream chunk adapter by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/15056
* fix(ci): improve GitCode sync reliability by @zhibisora in https://github.com/CherryHQ/cherry-studio/pull/15063
* fix(image): convert assistant image blocks to base64 for multi-turn editing by @Raymond8196 in https://github.com/CherryHQ/cherry-studio/pull/15011
* fix(agent): invalidate provider cache on settings changes by @404-Page-Found in https://github.com/CherryHQ/cherry-studio/pull/14596
* fix: recognize ctrl by uniKey value by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/15002
* hotfix(aiCore): prevent crash when model.provider not found (#14999) by @DeJeune in https://github.com/CherryHQ/cherry-studio/pull/15001
* fix: align provider model list actions by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15078
* fix(agents): use task name as session name for cron task sessions by @Kingzi49 in https://github.com/CherryHQ/cherry-studio/pull/15053
* fix: resolve ENOENT in OpenMinerU preprocessing caused by MinerU ZIP structure change by @suujonH in https://github.com/CherryHQ/cherry-studio/pull/15061
* fix: clean up OAuth tokens when deleting MCP server by @xr843 in https://github.com/CherryHQ/cherry-studio/pull/14083
* fix: exclude deepseek-r1 models from function_calling capability by @404-Page-Found in https://github.com/CherryHQ/cherry-studio/pull/15102
* fix: auto-expand MCP tool approval card so action buttons are immediately visible by @LWWZH in https://github.com/CherryHQ/cherry-studio/pull/15080
* hotfix: add environment variable for claude code provider management by @kovsu in https://github.com/CherryHQ/cherry-studio/pull/15089
* fix(agents): preserve updatedAt timestamps when creating new agents by @LWWZH in https://github.com/CherryHQ/cherry-studio/pull/14675
* fix(aiCore): Qiniu PDF fallback for GPT-5.4 by @404-Page-Found in https://github.com/CherryHQ/cherry-studio/pull/15090
* fix(code-tools): handle Codex CLI reserved provider IDs by @GeorgeDong32 in https://github.com/CherryHQ/cherry-studio/pull/15068
* chore: release v1.9.6 by @kangfenmao in https://github.com/CherryHQ/cherry-studio/pull/15116

##### New Contributors
* @Kingzi49 made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/15053
* @suujonH made their first contribution in https://github.com/CherryHQ/cherry-studio/pull/15061

**Full Changelog**: https://github.com/CherryHQ/cherry-studio/compare/v1.9.5...v1.9.6