0.28.5

Full Changelog: 0.28.4...0.28.5

0.28.4

Full Changelog: 0.28.3...0.28.4

0.28.3

Highlights

• support claude sonnet 4.6
• sdk: support specify outputStyle

What's Changed

• feat: add minimax-m2.5 model support by @jhao0413 in #752

Full Changelog: 0.28.2...0.28.3

0.28.2

Highlights

• add support for minimax m2.5 and gpt-5.3-codex-spark
• clear project context after /login successful
• improve providers

What's Changed

• fix(provider): iflow provider should use merged provider config by @jhao0413 in #751

New Contributors

• @jhao0413 made their first contribution in #751

Full Changelog: 0.28.1...0.28.2

0.28.1

Highlights

• gml-5 model support

What's Changed

• feat: add GLM-5 model support by @sorrycc in #748
• feat: add noContextCache option to disable context caching by @sorrycc in #747

Full Changelog: 0.28.0...0.28.1

0.28.0

Highlights

• add rewind code checkpoints with snapshot and recovery system
• improve model and providers for opus 4.6, iflow, antigravity and others

What's Changed

• feat: add rewind code checkpoints with snapshot and recovery system by @xierenyuan in #744

Full Changelog: 0.27.1...0.28.0

0.27.1

Highlights

• Providers: add opus 4.6 to providers, add gpt-5.3-codex to codex, add kimi coding plan, add kimi-k2.5 to iflow
• Add three-level validation for large file optimization
• Run command respect quiet/yes flags and handle prompt arguments

What's Changed

• feat: add providerMetadata support for tool calls in history by @xierenyuan in #737
• fix(run): respect quiet/yes flags and handle prompt arguments by @kamusis in #739
• feat: filter unmatched tool_use messages in message history by @xierenyuan in #740
• feat: add three-level validation for large file optimization by @xierenyuan in #741
• fix(textinput): correct tab key handling in useTextInput hook by @sorrycc in #743

New Contributors

• @kamusis made their first contribution in #739

Full Changelog: 0.27.0...0.27.1

0.27.0

Highlights

• add thinkingLevel config option for model reasoning effort
• notification will only trigger when not focus and also for tool approval state
• fix codex thinking problem
• fix acp problems
• simplify approval options for plan mode

What's Changed

• refactor: simplify approval options for auto-edit modes by @xierenyuan in #734
• fix: Repeated request for permission by @suxin2017 in #735

Full Changelog: 0.26.1...0.27.0

0.26.1

Highlights

• only show logined provider for /model
• improve acp support
• fix openrouter provider integrate

What's Changed

• feat: add ACP file system support with plugin architecture by @suxin2017 in #732
• feat: add persistent permission caching for tool approvals by @suxin2017 in #733

Full Changelog: 0.26.0...0.26.1

0.26.0

Highlights

• show Recent Models in /model
• improve plan mode like claude-code
• add providers codex and qwen with oauth, and remove antigravity provider
• support acp
• upgrade ai to 6 and fix kimi k2.5 and deepseek r1 problems
• improve prompt caching
• improve thinking config
• improve the way to custom provider and models
• improve auto compact strategy
• log llm request and response to request jsonl file
• truncate large tool output and use file as ref
• support kimi k2.5 model
• fix llm cancel don't stop immediately
• refact run command
• refact commit command for simplify

What's Changed

• fix: add fallback beep for notification sound errors by @sorrycc in #689
• fix: allow model command to bypass initialization error by @sorrycc in #690
• deps: update ink from 6.5.1 to 6.6.0 by @xierenyuan in #691
• refactor: remove unused tool approval logic by @xierenyuan in #696
• feat: optimize slash command UI with fixed width and truncation by @xierenyuan in #695
• fix: record tool results for remaining tools on denial by @sorrycc in #698
• feat: add skills option to sdk session options by @sorrycc in #694
• chore: remove biome code actions on save by @xierenyuan in #702
• feat: add repair to safeParseJson by @xierenyuan in #700
• fix: win32 spawn npx enoent error by @sorrycc in #705
• fix: ensure executable permissions for bundled ripgrep binary by @sorrycc in #706
• feat(at): ignore directory @mentions by @xierenyuan in #701
• refactor: reorganize tool resolution order in resolveTools by @xierenyuan in #708
• refactor(run): rewrite run command with readline interface by @sorrycc in #710
• feat: add responses model type support by @sorrycc in #711
• refactor: rename createModelType to apiFormat by @sorrycc in #712
• feat: add content output limits to grep tool by @xierenyuan in #707
• fix: handle terminal focus events globally by @sorrycc in #713
• feat: add external signal synchronization for loop cancellation by @xierenyuan in #714
• fix: improve tool argument display truncation and formatting by @xierenyuan in #715
• feat: add truncation plugin for automatic tool output management by @xierenyuan in #718
• refactor: support language-specific compact system prompts by @xierenyuan in #720
• refactor: move ProviderConfig export to fix duplicate export by @xierenyuan in #721
• feat: upgrade ai-sdk to v3 and update language model types by @sorrycc in #722
• feat: implement auto compression strategy optimization by @xierenyuan in #719
• fix: handle AI SDK v6 usage format with nested token objects by @xierenyuan in #724
• refactor: move providers to modular structure with pipeline by @sorrycc in #725
• fix: add fallback for undefined model in provider normalization by @xierenyuan in #726
• refactor: move thinking config to model variants by @sorrycc in #727
• feat: enhance prompt caching and api format support by @sorrycc in #728
• feat: add onRequest/onResponse HTTP logging hooks by @sorrycc in #729
• refactor: move CLAUDE.md rule loading into conditional block by @xierenyuan in #730
• feat: acp support by @suxin2017 in #717
• feat: implement complete plan mode with 5-phase workflow by @xierenyuan in #709

Full Changelog: 0.25.0...0.26.0