* refactor(settings): move spell check languages to constants and add type
Add Slovak language option and define SpellCheckOption type for better type safety
* fix(settings): disable spell check selector on Mac platforms
The spell check selector should not be shown on Mac platforms as it's not supported. This change adds a platform check to hide the selector when running on macOS.
* fix(prompts): clarify language detection rules for edge cases
Update LANG_DETECT_PROMPT to explicitly handle cases where the input text describes a language but is written in a different language. Add examples to illustrate the expected behavior.
* fix(prompts): correct language code mapping for Chinese input
Update the language detection prompt to properly map '英语' to 'zh-cn' instead of 'en-us' since it's a Chinese word
* Initial plan
* Fix custom parameters placement for Vercel AI Gateway
For AI Gateway provider, custom parameters are now placed at the body level
instead of being nested inside providerOptions.gateway. This fixes the issue
where parameters like 'tools' were being incorrectly added to
providerOptions.gateway when they should be at the same level as providerOptions.
Fixes#4197
Co-authored-by: DeJeune <67425183+DeJeune@users.noreply.github.com>
* Revert "Fix custom parameters placement for Vercel AI Gateway"
This reverts commit b14e48dd78.
* fix: rename 'ai-gateway' to 'gateway' across the codebase and update related configurations
* fix: resolve PR review issues for custom parameters field
- Fix Migration 174: use string literal 'ai-gateway' instead of non-existent constant for historical compatibility
- Fix Migration 180: update model.provider references to prevent orphaned models when renaming provider ID
- Add logging in mapVertexAIGatewayModelToProviderId when unknown model type is encountered
- Replace `any` with `Record<string, unknown>` in buildAIGatewayOptions return type for better type safety
- Add gateway mapping to getAiSdkProviderId mock in options.test.ts to match production behavior
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: version
* fix(options): enhance custom parameters handling for proxy providers
* fix(options): add support for cherryin provider with custom parameters handling
* chore
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: DeJeune <67425183+DeJeune@users.noreply.github.com>
Co-authored-by: suyao <sy20010504@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
* fix: update deepseek dependency to version 1.0.31 and improve provider creation logging
* chore
* feat: deepseek official hybrid infer
* fix: deepseek-v3.2-speciale tooluse and reasoning
* fix: 添加固定推理模型支持并更新相关逻辑
* refactor: simplify logic
* feat: aihubmix
* all system_providers
* feat: cherryin
* temp fix
* fix: address PR review feedback for DeepSeek v3.2 implementation
- Add default case in buildCherryInProviderOptions to fallback to genericProviderOptions
- Add clarifying comment for switch fall-through in reasoning.ts
- Add comprehensive test coverage for isFixedReasoningModel (negative cases)
- Add test coverage for new provider whitelist (deepseek, cherryin, new-api, aihubmix, sophnet, dmxapi)
- Add test coverage for isDeepSeekHybridInferenceModel prefix patterns
- Verify function calling logic works correctly via regex matching after removing provider-based checks
- Use includes() for deepseek-chat matching to support potential variants
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: remove unnecessary fall-through case for unknown providers in getReasoningEffort
---------
Co-authored-by: Claude <noreply@anthropic.com>
* fix(a11y): improve screen reader support with aria-label attributes
Add aria-label attributes to all interactive buttons and toolbar elements
to improve accessibility for screen reader users (NVDA, etc.).
Changes:
- Add aria-label with i18n translations to all ActionIconButton components
- Add role="button", tabIndex, and keyboard handlers for non-semantic elements
- Fix hardcoded English aria-labels in WindowControls to use i18n
- Add aria-pressed for toggle buttons to indicate state
- Add aria-expanded for expandable menus
- Add aria-disabled for disabled buttons
Components updated:
- SendMessageButton, CopyButton, SelectionToolbar
- CodeToolbar, RichEditor toolbar, MinimalToolbar
- WindowControls
- 12 Inputbar tool buttons (WebSearch, Attachment, KnowledgeBase, etc.)
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(a11y): enhance accessibility in CodeToolbar snapshot
Added aria-label, role, and tabindex attributes to improve screen reader support for interactive elements in the CodeToolbar component. This change aligns with ongoing efforts to enhance accessibility across the application.
---------
Co-authored-by: Claude <noreply@anthropic.com>
* fix(inputbar): block enter send while generating
- reuse unified send disable state for keyboard and button
- prevent enter sending when loading or searching
* refactor: optimize InputbarCore component's useHotkeys hook
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* refactor(InputbarCore): rename cannotSend to noContent for clarity
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix(apiServer): use 127.0.0.1 instead of localhost for better compatibility
- Change default host from localhost to 127.0.0.1 in config and settings
- Add buildApiServerUrl helper to properly construct API server URLs
- Update OpenAPI documentation server URL
- Update test files to use 127.0.0.1
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(migration): migrate existing localhost config to 127.0.0.1
- Add migration 180 to automatically update localhost to 127.0.0.1
- Handle both plain host and hosts with http/https protocol
- Increment store version to 180
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor(apiServer): simplify buildApiServerUrl implementation
- Remove complex URL parsing and protocol handling
- Use simple string concatenation for URL building
- Assume http protocol since API server is local
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor: remove buildApiServerUrl helper and simplify migration
- Remove buildApiServerUrl helper function
- Use 127.0.0.1 directly in URL construction
- Simplify migration 180 to unconditionally set host to 127.0.0.1
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor(apiServer): fix critical bugs and improve code structure
🔴 Critical Fixes:
- Fix config.ts to use stored host value instead of ignoring it
- Fix hardcoded 127.0.0.1 URLs to use apiServerConfig.host
🟡 Improvements:
- Extract API_SERVER_DEFAULTS to shared constants in packages/shared/config/constant.ts
- Apply consistent fallback pattern using API_SERVER_DEFAULTS.HOST and API_SERVER_DEFAULTS.PORT
- Update all imports to use shared constants across main and renderer processes
Files changed:
- packages/shared/config/constant.ts: Add API_SERVER_DEFAULTS constants
- src/main/apiServer/config.ts: Use stored host with fallback
- src/main/apiServer/middleware/openapi.ts: Use constants
- src/renderer/src/pages/settings/ToolSettings/ApiServerSettings/ApiServerSettings.tsx: Use config host and constants
- src/renderer/src/store/settings.ts: Use constants in initial state
- src/renderer/src/store/migrate.ts: Use constants in migration
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* update
* fix(apiServer): use relative URL in OpenAPI spec for better compatibility
- Change server URL from hardcoded defaults to relative path '/'
- This ensures Swagger UI "Try it out" works correctly regardless of configured host/port
- Remove unused API_SERVER_DEFAULTS import
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* fix: update Inputbar components to support dynamic textarea height adjustment
* fix: align drag handler maxHeight with hook configuration (500px)
- Update hardcoded maxHeight from 400 to 500 in InputbarCore drag handler
- This ensures consistency with useTextareaResize hook maxHeight parameter
- Resolves PR comment about maxHeight inconsistency between hook and drag handler
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* fix(settings): fix wrong type caused by as assertion and migration
Add migration step 180 to properly handle 'undefined' string values in OpenAI settings
Update selector components to use value conversion helpers for summaryText and verbosity
* feat(models): add null as supported verbosity level for OpenAI models
Update model utils and types to include null as a valid verbosity level option alongside undefined. This provides more flexibility in controlling verbosity behavior, with null representing an explicit "off" state. Tests and UI components are updated to reflect this change.
* fix(verbosity): fix wrong verbosity type definition and handling in #11281
* style: format
* fix(store): correct verbosity check in migration config
The condition was incorrectly checking for 'undefined' string instead of undefined value, and was assigning to summaryText instead of verbosity. This fixes the migration logic to properly handle the verbosity setting.
* docs(aiCore): improve comments for verbosity and summary types
Update type comments to better explain the behavior of verbosity and summary parameters in OpenAI API requests
* fix: topic name remains after deleting last topic
- Fix logic error when deleting the last topic
- Only clear messages in the last topic before the commit
- Now creates new topic before deleting the original one to ensure proper topic name update
Signed-off-by: Do1e <i@do1e.cn>
* fix(topic): integrate the same code in `handleConfirmDelete`
Signed-off-by: Do1e <i@do1e.cn>
---------
Signed-off-by: Do1e <i@do1e.cn>
* fix: improve code block copy in collapsed state with virtual scroll
- Add saveSelection mechanism to track selection across virtual scroll updates
- Implement custom copy handler to extract complete content from raw data
- Auto-expand code block when multi-line selection is detected in collapsed state
- Only enable auto-expand when codeCollapsible setting is enabled
- Add comprehensive logging for debugging selection and copy issues
Fixes issue where copying code in collapsed state would lose content from
virtualized rows that are not rendered in DOM. The solution captures
selection position (line + offset) during scroll and uses it to extract
complete content from the original source when copying.
* fix(CodeViewer): scope selection and copy to viewer container to prevent multiple blocks appearing selected\n\n- Add selectionBelongsToViewer() to ensure selection anchors are within this viewer\n- Guard saveSelection, copy handler, and selectionchange auto-expand logic\n- Avoids cross-viewer selection bleed when multiple CodeViewer instances exist on a page\n\nFollow-up to 37c2b5ecb (virtual scroll selection/copy).
* fix(CodeViewer): clear saved selection when active selection belongs to another viewer\n\n- Early-return in selectionchange handler when selection is outside this viewer\n- Complements scoping guards to avoid misleading multi-selection states
* fix(CodeViewer): change logger info to debug for selection and copy events
- Adjust logging level from info to debug for various selection and copy operations to reduce log verbosity.
- Ensure selection belongs to the current viewer before processing.
* fix(CodeViewer): remove invisible character from import statement
* fix(CodeViewer): complete useCallback deps to avoid stale closure
- saveSelection deps -> [selectionBelongsToViewer]
- handleCopy deps -> [selectionBelongsToViewer, expanded, saveSelection, rawLines]
- no behavior change; satisfy exhaustive-deps; reduce risk of stale refs
* fix(CodeViewer): improve selection handling for virtual scrolling and enhance comments
* fix(CodeViewer): handle clipboardData unavailability and remove unused ref
- Add null check for event.clipboardData to prevent silent copy failure
- When clipboardData is unavailable, fall back to browser default copy behavior
- Remove unused isRestoringSelectionRef and its dead code check
- Improve copy reliability in edge cases where clipboard API may be unavailable
* fix: update @modelcontextprotocol/sdk to v1.23.0 and enhance MCP tool schemas
* fix: add dotenv type definitions and implement parseKeyValueString utility with tests
- Renamed `MultiPreferencesResultType` to `PreferenceMultipleResultType` for clarity and consistency.
- Updated `getMultipleRaw` method in `PreferenceService` to reflect the new type name.
- Adjusted related components and services to utilize the updated type, ensuring consistent usage across the application.
- Renamed `Preference_GetMultiple` to `Preference_GetMultipleRaw` in IpcChannel for clarity.
- Introduced `MultiPreferencesResultType` to better map requested keys to their values or undefined in preferenceTypes.
- Updated `PreferenceService` to implement `getMultipleRaw` for synchronous access to multiple preferences.
- Adjusted related components and services to utilize the new method for fetching multiple preferences.
- Cleaned up imports and ensured consistent usage across the application.
- Removed the config module and replaced its usage with preferenceService across the API server implementation.
- Updated the auth middleware to retrieve the API key from preferenceService instead of the config.
- Adjusted the ApiServerService to ensure a valid API key is generated and stored in preferences.
- Refactored the useApiServer hook to utilize the new preference system for API server configuration.
- Updated related tests to mock preferenceService instead of config.
- Cleaned up unused imports and adjusted related components to align with the new configuration approach.
- Replace local imports of Input and Switch components with imports from the @cherrystudio/ui package for consistency.
- Minor adjustment to the Switch story to include a button type for the toggle state functionality.
* refactor(ui): migrate switch component from heroui to radix-ui
replace heroui switch implementation with radix-ui for better maintainability
update package.json and yarn.lock to include new dependency
* fix(eslint): enable heroui import restriction for deprecated Switch component
* refactor(ui): update Switch component props from isSelected/onValueChange to checked/onCheckedChange
Standardize Switch component props across the codebase to use checked/onCheckedChange instead of isSelected/onValueChange for better consistency with common React patterns. Also updates loading state prop from isLoading to loading and removes size prop where unnecessary.
The changes include:
- Replacing isSelected with checked
- Replacing onValueChange with onCheckedChange
- Updating isLoading to loading
- Removing redundant size props
- Adjusting styling to accommodate new loading state
* refactor(switch): improve switch component styling and structure
- Add default values for loading and disabled props
- Update styling classes and add group cursor pointer
- Restructure loading indicator and thumb positioning
- Wrap DescriptionSwitch children in flex container
* refactor(ui): improve switch component structure and usage
- Restructure DescriptionSwitch to use explicit props instead of children
- Add label, description, and position props for better customization
- Update all switch usages in SettingsTab to use new props format
* refactor(primitives): simplify switch props by omitting children
Remove redundant children prop from CustomSwitchProps since it's already omitted from the parent type
* fix(switch): add useId for label accessibility in DescriptionSwitch
Ensure proper label association with switch input by generating unique ID using React's useId hook
* refactor(settings): remove commented out SettingRowTitleSmall components
* refactor(SettingsTab): add todo comment for memoization optimization
* feat(switch): add size prop to customize switch dimensions
Add sm, md, and lg size options to the Switch component with corresponding styles. This allows for better visual consistency across different UI contexts.
* style(ui): adjust switch component styling and theme colors
update switch component layout and spacing to improve consistency
modify secondary-foreground color variable to use correct semantic token
* feat(switch): add new switch component styles and animations
- Add new switch.css file with gradient and transition styles
- Update switch.tsx component with new styling classes and animations
- Remove loader icon in favor of animated gradient effect
* fix(i18n): Auto update translations for PR #11061
* style(primitives): remove redundant border style from switch component
* refactor(switch): remove switch.css and update switch component styles
Remove deprecated switch.css file and migrate styles to inline tailwind classes. Update disabled state styling to use opacity instead of linear gradient for better consistency.
* refactor(switch): simplify switch thumb implementation
Replace complex div structure with svg for loading state
Adjust disabled opacity and loading state styling
* style(switch): adjust thumb size and positioning for better consistency
* feat(switch): add storybook documentation for switch component
Add comprehensive Storybook documentation for the Switch component, including:
- Basic usage examples
- Different states (checked, disabled, loading)
- Size variations
- DescriptionSwitch variant
- Real-world usage scenarios
- Accessibility examples
- Form integration examples
Also remove redundant box-content class from switch styles
* fix(switch): adjust thumb positioning for md and lg sizes
* style(primitives): improve switch component styling and spacing
- Add padding to the container
- Simplify label height logic
- Update typography classes for better consistency
- Adjust switch container alignment
* feat(switch): add size prop to DescriptionSwitch component
Add support for sm, md, and lg sizes to DescriptionSwitch component with responsive text sizing. Also includes comprehensive Storybook documentation with examples of all sizes and states.
* style(switch): align label text to right when isLeftSide is true
* refactor(stories): clean up DescriptionSwitch stories by removing unused imports and simplifying JSX
* refactor(ui): rename CustomizedSwitch to Switch for consistency
Simplify component naming by removing redundant 'Customized' prefix and aligning with common naming conventions
* refactor(switch): extract switch root styles into cva variants
Improve maintainability by using class-variance-authority to manage switch root styles and variants
* refactor(switch): extract thumb variants into separate cva function
Improve maintainability by moving switch thumb styling logic into a dedicated variants configuration. This makes the component more readable and easier to modify.
* feat(switch): add classNames prop for custom styling
Allow custom class names to be applied to switch root, thumb, and thumbSvg elements for more flexible styling options.
* feat(switch): add loading animation variants for switch thumb
Extract loading animation logic into separate cva variants for better maintainability and reusability
---------
Co-authored-by: GitHub Action <action@github.com>
* docs(providerConfig): improve jsdoc for formatProviderApiHost function
* refactor(aiCore): improve provider handling with adaptProvider function
Introduce adaptProvider to centralize provider transformations and replace direct usage of handleSpecialProviders and formatProviderApiHost. This improves maintainability and provides consistent behavior across all provider usage scenarios.
* refactor(ProviderSettings): simplify api host formatting logic by using adaptProvider
Replace multiple format functions with a single adaptProvider utility to centralize host formatting logic and improve maintainability
* feat(api): add withoutTrailingSharp utility and update formatApiHost
add utility function to remove trailing # from URLs and update formatApiHost to use it
add comprehensive tests for new functionality
* feat(ProviderSetting): add help tooltip for api url selector
Add HelpTooltip component next to host selector to provide additional guidance about API URL configuration
Updated the Inputbar and AgentSessionInputbar components to use the new cacheService for managing draft persistence and mentioned models, ensuring consistency across the application.
* fix(ApiService): handle stream errors properly in checkApi
Ensure stream errors are properly caught and thrown when checking API availability
* docs(types): add type safety comment for ResponseError
Add FIXME comment highlighting weak type safety in ResponseError type
* feat(dom): extend scrollIntoView with Chromium-specific options
Add ChromiumScrollIntoViewOptions interface to support additional scroll container options
* refactor(hooks): optimize timer and scroll position hooks
- Use useMemo for scrollKey in useScrollPosition to avoid unnecessary recalculations
- Refactor useTimer to use useCallback for all functions to prevent unnecessary recreations
- Reorganize function order and improve cleanup logic in useTimer
* fix: stabilize home scroll behavior
* Update src/renderer/src/pages/home/Messages/ChatNavigation.tsx
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix(utils/dom): add null check for element in scrollIntoView
Prevent potential runtime errors by gracefully handling falsy elements with a warning log
* fix(hooks): use ref for scroll key to avoid stale closure
* fix(useScrollPosition): add cleanup for scroll handler to prevent memory leaks
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix(i18n): remove image-generation translations and clarify endpoint type
Update English locale to specify OpenAI for image generation
Add comments to clarify image-generation endpoint type relationship
* fix(i18n): correct portuguese translations in pt-pt.json
fix(reasoning): handle reasoning effort none case properly
separate undefined and none reasoning effort cases
clean up redundant model checks and add fallback logging
Fix the issue where doubao provider could not infer models using the name field.
Refactored `isDeepSeekHybridInferenceModel` to use `withModelIdAndNameAsId`
utility function to check both model.id and model.name, avoiding duplicate
calls in `isReasoningModel`.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
- Convert all image formats to PNG before writing to clipboard to ensure compatibility
- Refactor handleCopyImage to unify image source handling (Base64, File, URL)
- Add convertImageToPng utility function using canvas API for robust conversion
- Remove fallback logic that attempted to write unsupported JPEG format
* refactor(api): extract version regex into constant for reuse
Move the version matching regex pattern into a module-level constant to improve code reuse and maintainability. The functionality remains unchanged.
* refactor(api): rename regex constant and use dynamic regex construction
Use a string pattern for version regex to allow dynamic construction and improve maintainability. Rename constant to better reflect its purpose.
* feat(api): add getLastApiVersion utility function
Implement a utility function to extract the last API version segment from URLs. This is useful for handling cases where multiple version segments exist in the path and we need to determine the most specific version being used.
Add comprehensive test cases covering various URL patterns and edge cases.
* feat(api): add utility to remove trailing API version from URLs
Add withoutTrailingApiVersion function to clean up URLs by removing version segments
at the end of paths. This helps standardize API endpoint URLs when version is not needed.
* refactor(api): rename isSupportedAPIVerion to supportApiVersion for clarity
* fix(gemini): handle api version dynamically for non-vertex providers
Use getLastApiVersion utility to determine the latest API version for non-vertex providers instead of hardcoding to v1beta
* feat(api): add function to extract trailing API version from URL
Add getTrailingApiVersion utility function to specifically extract API version segments
that appear at the end of URLs. This complements existing version-related utilities
and helps handle cases where we only care about the final version in the path.
* refactor(gemini): use getTrailingApiVersion instead of getLastApiVersion
The function name was changed to better reflect its purpose of extracting the trailing API version from the URL. The logic was also simplified and made more explicit.
* refactor(api): remove unused getLastApiVersion function
The function was removed as it was no longer needed, simplifying the API version handling to only use trailing version detection. The trailing version regex was extracted to a constant for reuse.
- Replace direct Redux state access for memory preferences with preferenceService calls in multiple components.
- Introduce new preference mappings for memory settings, including 'feature.memory.auto_dimensions'.
- Remove deprecated preference mappings and update default preferences accordingly.
- Regenerate preference schemas to reflect the latest changes in memory configuration.
* feat: enhance support for AWS Bedrock and Azure OpenAI providers
* fix: resolve PR review issues for AWS Bedrock support
- Fix header.ts logic bug: change && to || for Vertex/Bedrock provider check
- Fix regex in reasoning.ts to match AWS Bedrock model format (anthropic.claude-*)
- Add test coverage for AWS Bedrock format in isClaude4SeriesModel
- Add Bedrock provider tests including anthropicBeta parameter
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* fix(provider): update service tier support logic for OpenAI and Azure providers
* fix(settings): enhance OpenAI settings visibility logic with verbosity support
Previously, JSON-type custom parameters were incorrectly parsed and stored
as objects in the UI layer, causing API requests to fail when getCustomParameters()
attempted to JSON.parse() an already-parsed object.
Changes:
- AssistantModelSettings.tsx: Remove JSON.parse() in onChange handler, store as string
- reasoning.ts: Add comments explaining JSON parsing flow
- BaseApiClient.ts: Add comments for legacy API clients
* refactor(models): improve verbosity level handling for GPT-5 models
Replace hardcoded verbosity configuration with validator functions
Add support for GPT-5.1 series models
* test(models): restructure model utility tests into logical groups
Improve test organization by grouping related test cases under descriptive describe blocks for better maintainability and readability. Each model utility function now has its own dedicated test section with clear subcategories for different behaviors.
* fix: add null check for model in getModelSupportedVerbosity
Handle null model case defensively by returning default verbosity
* refactor(config): remove redundant as const from MODEL_SUPPORTED_VERBOSITY array
* refactor(models): simplify validator function in MODEL_SUPPORTED_VERBOSITY
* test(model utils): add tests for undefined/null input handling
* fix(models): handle undefined/null input in getModelSupportedVerbosity
Remove ts-expect-error comments and update type signature to explicitly handle undefined/null inputs. Also add support for GPT-5.1 series models.
* test(models): add test case for gpt-5-pro variant model
When updating assistant preset settings, if agent.settings was undefined,
it was assigned the DEFAULT_ASSISTANT_SETTINGS object directly. Since this
object is defined with `as const`, it is readonly and subsequent property
assignments would fail with "Cannot assign to read only property".
Fixed by creating a shallow copy of DEFAULT_ASSISTANT_SETTINGS instead of
referencing it directly.
Closes#11490🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Move color and font-size styles from p selector to container level
in UpdateNotesWrapper. This ensures all content (including li elements
not wrapped in p tags) uses consistent color.
The issue occurred because .replace(/\n/g, '\n\n') creates a "loose list"
in Markdown where most list items get wrapped in <p> tags, but the last
item (without trailing newline) may not, causing it to inherit a different
color from the parent .markdown class.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* Initial plan
* feat: Add proper Poe API reasoning parameters support for GPT-5 and other models
Co-authored-by: DeJeune <67425183+DeJeune@users.noreply.github.com>
* test: Add comprehensive tests for Poe API reasoning support
Co-authored-by: DeJeune <67425183+DeJeune@users.noreply.github.com>
* fix: Add missing isGPT5SeriesModel import in reasoning.ts
Co-authored-by: DeJeune <67425183+DeJeune@users.noreply.github.com>
* fix: Use correct extra_body format for Poe API reasoning parameters
Per Poe API documentation, custom bot parameters like reasoning_effort
and thinking_budget should be passed directly in extra_body, not as
nested structures.
Changed from:
- reasoning_effort: 'low' -> extra_body: { reasoning_effort: 'low' }
- thinking: { type: 'enabled', budget_tokens: X } -> extra_body: { thinking_budget: X }
- extra_body: { google: { thinking_config: {...} } } -> extra_body: { thinking_budget: X }
Updated tests to match the corrected implementation.
Co-authored-by: DeJeune <67425183+DeJeune@users.noreply.github.com>
* fix: Update reasoning parameters and improve type definitions for GPT-5 support
* fix lint
* docs
* fix(reasoning): handle edge cases for models without token limit configuration
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: DeJeune <67425183+DeJeune@users.noreply.github.com>
Co-authored-by: suyao <sy20010504@gmail.com>
* fix(anthropic): prevent duplicate /v1 in API endpoints
Anthropic SDK automatically appends /v1 to endpoints, so we should not add it in our formatting. This change ensures URLs are correctly formatted without duplicate path segments.
* fix(anthropic): strip /v1 suffix in getSdkClient to prevent duplicate in models endpoint
The issue was:
- AI SDK (for chat) needs baseURL with /v1 suffix
- Anthropic SDK (for listModels) automatically appends /v1 to all endpoints
Solution:
- Keep /v1 in formatProviderApiHost for AI SDK compatibility
- Strip /v1 in getSdkClient before passing to Anthropic SDK
- This ensures chat works correctly while preventing /v1/v1/models duplication
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(anthropic): correct preview URL to match actual request behavior
The preview now correctly shows:
- Input: https://api.siliconflow.cn/v2
- Preview: https://api.siliconflow.cn/v2/messages (was incorrectly showing /v2/v1/messages)
- Actual: https://api.siliconflow.cn/v2/messages
This matches the actual behavior where getSdkClient strips /v1 suffix before
passing to Anthropic SDK, which then appends /v1/messages.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(anthropic): strip all API version suffixes, not just /v1
The Anthropic SDK always appends /v1 to endpoints, regardless of the baseURL.
Previously we only stripped /v1 suffix, causing issues with custom versions like /v2.
Now we strip all version suffixes (/v1, /v2, /v1beta, etc.) before passing to Anthropic SDK.
Examples:
- Input: https://api.siliconflow.cn/v2/
- After strip: https://api.siliconflow.cn
- Actual request: https://api.siliconflow.cn/v1/messages✅🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(anthropic): correct preview to show AI SDK behavior, not Anthropic SDK
The preview was showing the wrong URL because it was reflecting Anthropic SDK behavior
(which strips versions and uses /v1), but checkApi and chat use AI SDK which preserves
the user's version path.
Now preview correctly shows:
- Input: https://api.siliconflow.cn/v2/
- AI SDK (checkApi/chat): https://api.siliconflow.cn/v2/messages✅
- Preview: https://api.siliconflow.cn/v2/messages✅
Note: Anthropic SDK (for listModels) still strips versions to use /v1/models,
but this is not shown in preview since it's a different code path.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor(checkApi): remove unnecessary legacy fallback
The legacy fallback logic in checkApi was:
1. Complex and hard to maintain
2. Never actually triggered in practice for Modern SDK supported providers
3. Could cause duplicate API requests
Since Modern AI SDK now handles all major providers correctly,
we can simplify by directly throwing errors instead of falling back.
This also removes unused imports: AiProvider and CompletionsParams.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(anthropic): restore version stripping in getSdkClient for Anthropic SDK
The Anthropic SDK (used for listModels) always appends /v1 to endpoints,
so we need to strip version suffixes from baseURL to avoid duplication.
This only affects Anthropic SDK operations (like listModels).
AI SDK operations (chat/checkApi) use provider.apiHost directly via
providerToAiSdkConfig, which preserves the user's version path.
Examples:
- AI SDK (chat): https://api.siliconflow.cn/v1 -> /v1/messages ✅
- Anthropic SDK (models): https://api.siliconflow.cn/v1 -> strip v1 -> /v1/models ✅🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(anthropic): ensure AI SDK gets /v1 in baseURL, strip for Anthropic SDK
The correct behavior is:
1. formatProviderApiHost: Add /v1 to apiHost (for AI SDK compatibility)
2. AI SDK (chat/checkApi): Use apiHost with /v1 -> /v1/messages ✅
3. Anthropic SDK (listModels): Strip /v1 from baseURL -> SDK adds /v1/models ✅
4. Preview: Show AI SDK behavior (main use case) -> /v1/messages ✅
Examples:
- Input: https://api.siliconflow.cn
- Formatted: https://api.siliconflow.cn/v1 (added by formatApiHost)
- AI SDK: https://api.siliconflow.cn/v1/messages✅
- Anthropic SDK: https://api.siliconflow.cn (stripped) + /v1/models ✅
- Preview: https://api.siliconflow.cn/v1/messages✅🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* refactor(ai): simplify AiProviderNew initialization and improve docs
Update AiProviderNew constructor to automatically format URLs by default
Add comprehensive documentation explaining constructor behavior and usage
* chore: remove unused play.ts file
* fix(anthropic): strip api version from baseURL to avoid endpoint duplication
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add silicon provider support for Anthropic API compatibility
* fix: update handling of ANTHROPIC_BASE_URL for silicon provider compatibility
* fix: update anthropicApiHost for silicon provider to use the correct endpoint
* fix: remove silicon from CLAUDE_OFFICIAL_SUPPORTED_PROVIDERS
* chore: add comment to clarify silicon model fallback logic in CLAUDE_OFFICIAL_SUPPORTED_PROVIDERS
* fix: add claude-opus-4-5 pattern to THINKING_TOKEN_MAP
Adds missing regex pattern for claude-opus-4-5 models (e.g., claude-opus-4-5-20251101)
to the THINKING_TOKEN_MAP configuration. Without this pattern, the model was not
recognized, causing findTokenLimit() to return undefined and leading to an
AI_InvalidArgumentError when using Google Vertex AI Anthropic provider.
The fix adds the pattern 'claude-opus-4-5.*$': { min: 1024, max: 64_000 } to
match the existing claude-4 thinking token configuration.
Fixes AI_InvalidArgumentError: invalid anthropic provider options caused by
budgetTokens receiving NaN instead of a number.
Signed-off-by: Shuchen Luo (personal linux) <nemo0806@gmail.com>
* refactor: make THINKING_TOKEN_MAP constant private
* fix(reasoning): update claude model token limit regex patterns
- Consolidate claude model regex patterns to be more consistent
- Add comprehensive test cases for various claude model variants
- Ensure case insensitivity and proper handling of edge cases
* fix: format
* feat(models): extend claude model regex patterns to support AWS and GCP formats
Update regex patterns in THINKING_TOKEN_MAP to support additional Claude model ID formats used in AWS Bedrock and GCP Vertex AI
Add comprehensive test cases for new model ID formats and reorganize test suite
* fix: format
---------
Signed-off-by: Shuchen Luo (personal linux) <nemo0806@gmail.com>
Co-authored-by: icarus <eurfelux@gmail.com>
* Initial plan
* fix(aiCore): extract AI SDK standard params from custom params for Gemini
Custom parameters like topK, frequencyPenalty, presencePenalty,
stopSequences, and seed should be passed as top-level streamText()
parameters, not in providerOptions. This fixes the issue where these
parameters were being ignored by the AI SDK's @ai-sdk/google module.
Changes:
- Add extractAiSdkStandardParams function to separate standard params
- Update buildProviderOptions to return both providerOptions and standardParams
- Update buildStreamTextParams to spread standardParams into params object
- Update tests to reflect new return structure
Co-authored-by: DeJeune <67425183+DeJeune@users.noreply.github.com>
* refactor(aiCore): remove extractAiSdkStandardParams function and its tests, streamline parameter extraction logic
* chore: type
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: DeJeune <67425183+DeJeune@users.noreply.github.com>
Co-authored-by: suyao <sy20010504@gmail.com>
* feat(settings): show OpenAI settings for supported service tier providers
Add support for displaying OpenAI settings when provider supports service tiers.
This includes refactoring the condition check and fixing variable naming consistency.
* fix(settings): set openAI verbosity to undefined by default
* fix(store): bump version to 178 and disable verbosity for groq provider
Add migration to remove verbosity from groq provider and implement provider utility to check verbosity support
Update provider types to include verbosity support flag
* feat(provider): add verbosity option support for providers
Add verbosity parameter support in provider API options settings
* fix(aiCore): check provider support for verbosity before applying
Add provider validation and check for verbosity support to prevent errors when unsupported providers are used with verbosity settings
* feat(settings): add Groq settings group component and translations
add new GroqSettingsGroup component for managing Groq provider settings
update translations for Groq settings in both zh-cn and en-us locales
refactor OpenAISettingsGroup to separate Groq-specific logic
* feat(i18n): add groq settings and verbosity support translations
add translations for groq settings title and verbosity parameter support in multiple languages
* refactor(settings): simplify service tier mode fallback logic
Remove conditional service tier mode fallback and use provider-specific defaults directly
* fix(provider): remove redundant system provider check in verbosity support
* test(provider): add tests for verbosity support detection
* fix(OpenAISettingsGroup): add endpoint_type check for showSummarySetting condition
Add model.endpoint_type check to properly determine when to show summary setting for OpenAI models
* refactor(selector): simplify selector option types and add utility functions
remove undefined and null from selector option types
add utility functions to convert between option values and real values
update groq and openai settings groups to use new utilities
add new translation for "ignore" option
* fix(ApiOptionsSettings): correct checked state for verbosity toggle
* feat(i18n): add "ignore" translation for multiple languages
* refactor(groq): remove unused model prop and related checks
Clean up GroqSettingsGroup component by removing unused model prop and unnecessary service tier checks
refactor(models): improve text delta support check for qwen-mt models
Replace direct qwen-mt model check with regex pattern matching
Add comprehensive test cases for isNotSupportTextDeltaModel
Update all references to use new function name
The previous implementation used `a = preset` inside forEach, which only
reassigns the local variable and doesn't actually update the array element.
Changed to use findIndex + direct array assignment to properly update
the preset in the state.
Fixes#11451🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* fix: respect enableMaxTokens setting when maxTokens is not configured
When enableMaxTokens is disabled, getMaxTokens() should return undefined
to let the API use its own default value, instead of forcing 4096 tokens.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix(modelParameters): handle max tokens when feature is disabled
Check if max tokens feature is enabled before returning undefined to ensure proper API behavior
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: icarus <eurfelux@gmail.com>
* feat: update Google and OpenAI SDKs with new features and fixes
- Updated Google SDK to ensure model paths are correctly formatted.
- Enhanced OpenAI SDK to include support for image URLs in chat responses.
- Added reasoning content handling in OpenAI chat responses and chunks.
- Introduced Azure Anthropic provider configuration for Claude integration.
* fix: azure error
* fix: lint
* fix: test
* fix: test
* fix type
* fix comment
* fix: redundant
* chore resolution
* fix: test
* fix: comment
* fix: comment
* fix
* feat: 添加 OpenRouter 推理中间件以支持内容过滤
* refactor: improve model filtering with todo for robust conversion
* refactor(aiCore): add AiSdkConfig type and update provider config handling
- Introduce new AiSdkConfig type in aiCoreTypes for better type safety
- Update provider factory and config to use AiSdkConfig consistently
- Simplify getAiSdkProviderId return type to string
- Add config validation in ModernAiProvider
* refactor(aiCore): move ai core types to dedicated module
Consolidate AI core type definitions into a dedicated module under aiCore/types. This improves code organization by keeping related types together and removes circular dependencies between modules. The change includes:
- Moving AiSdkConfig to aiCore/types
- Updating all imports to reference the new location
- Removing duplicate type definitions
* refactor(provider): add return type to createAiSdkProvider function
* feat(messages): add filter for error-only messages and their related pairs
Add new filter function to remove assistant messages containing only error blocks along with their associated user messages, identified by askId. This improves conversation quality by cleaning up error-only responses.
* refactor(ConversationService): improve message filtering pipeline readability
Break down complex message filtering chain into clearly labeled steps
Add comments explaining each filtering step's purpose
Maintain same functionality while improving code maintainability
* test(messageUtils): add test cases for message filter utilities
* docs(messageUtils): correct jsdoc for filterUsefulMessages
* refactor(ConversationService): extract message filtering logic into pipeline method
Move message filtering steps into a dedicated static method to improve testability and maintainability. Add comprehensive tests to verify pipeline behavior.
* refactor(ConversationService): add logging and improve message filtering readability
Add logger service to track message pipeline output
Split filterUserRoleStartMessages into separate variable for better debugging
* refactor(types): consolidate OpenAI types and improve type safety
- Move OpenAI-related types to aiCoreTypes.ts
- Rename FetchChatCompletionOptions to FetchChatCompletionRequestOptions
- Add proper type definitions for service tiers and verbosity
- Improve type guards for service tier checks
* refactor(api): rename options parameter to requestOptions for consistency
Update parameter name across multiple files to use requestOptions instead of options for better clarity and consistency in API calls
* refactor(aiCore): simplify OpenAI summary text handling and improve type safety
- Remove 'off' option from OpenAISummaryText type and use null instead
- Add migration to convert 'off' values to null
- Add utility function to convert undefined to null
- Update Selector component to handle null/undefined values
- Improve type safety in provider options and reasoning params
* fix(i18n): Auto update translations for PR #10964
* feat(utils): add notNull function to convert null to undefined
* refactor(utils): move defined and notNull functions to shared package
Consolidate utility functions into shared package to improve code organization and reuse
* Revert "fix(i18n): Auto update translations for PR #10964"
This reverts commit 68bd7eaac5.
* feat(i18n): add "off" translation and remove "performance" tier
Add "off" translation for multiple languages and remove "performance" service tier option from translations
* Apply suggestion from @EurFelux
* docs(types): clarify handling of undefined and null values
Add comments to explain that undefined is treated as default and null as explicitly off in OpenAIVerbosity and OpenAIServiceTier types. Also update type safety for OpenAIServiceTiers record.
* fix(migration): update migration version from 167 to 171 for removed type
* chore: update store version to 172
* fix(migrate): update migration version number from 171 to 172
* fix(i18n): Auto update translations for PR #10964
* refactor(types): improve type safety for verbosity handling
add NotUndefined and NotNull utility types to better handle null/undefined cases
clarify verbosity types in aiCoreTypes and update related utility functions
* refactor(types): replace null with undefined for verbosity values
Standardize on undefined instead of null for verbosity values to align with OpenAI API docs and improve type consistency
* refactor(aiCore): update OpenAI provider options type import and usage
* fix(openai): change summaryText default from null to 'auto'
Update OpenAI settings to use 'auto' as default summaryText value instead of null for consistency with API behavior. Remove 'off' option and add 'concise' option while maintaining type safety.
* refactor(OpenAISettingsGroup): extract service tier options type for better maintainability
* refactor(types): make SystemProviderIdTypeMap internal type
* docs(provider): clarify OpenAIServiceTier behavior for undefined vs null
Explain that undefined and null values for serviceTier should be treated differently since they affect whether the field appears in the response
* refactor(utils): rename utility functions for clarity
Rename `defined` to `toNullIfUndefined` and `notNull` to `toUndefinedIfNull` to better reflect their functionality
* refactor(aiCore): extract service tier logic and improve type safety
Extract service tier validation logic into separate functions for better reusability
Add proper type annotations for provider options
Pass service tier parameter through provider option builders
* refactor(utils): comment out unused utility functions
Keep commented utility functions for potential future use while cleaning up current codebase
* fix(migration): update migration version number from 172 to 177
* docs(aiCoreTypes): clarify parameter passing behavior in OpenAI API
Update comments to consistently use 'undefined' instead of 'null' when describing parameter passing behavior in OpenAI API requests, as they share the same meaning in this context
---------
Co-authored-by: GitHub Action <action@github.com>
* 100m
* feat: add web search header for Claude 4 series models
* fix: typo
* fix: identify model
---------
Co-authored-by: defi-failure <159208748+defi-failure@users.noreply.github.com>
Implement single instance IPC subscription pattern to resolve MaxListenersExceededWarning. Previously, each component using useApiServer would register a separate 'api-server:ready' listener, and React strict mode double rendering would quickly exceed the 10 listener limit.
Changes:
- Add module-level subscription manager with onReadyCallbacks Set
- Ensure only one IPC listener is registered regardless of component count
- Use useRef to maintain stable callback references
- Properly cleanup subscriptions when all components unmount
This maintains existing behavior while keeping listener count constant at 1.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add endpoint type support for cherryin provider
* chore: bump @cherrystudio/ai-sdk-provider version to 0.1.1
* chore: bump ai-sdk-provider version to 0.1.3
* test(knowledge): fix tests for knowledge base form modal refactoring
Update all test files to match the new vertical layout structure with button-based advanced settings toggle. Remove obsolete tests for deleted features.
Changes:
- Rewrite KnowledgeBaseFormModal.test.tsx for new button-toggle structure
- Remove tests for preprocess and rerank features from GeneralSettingsPanel
- Update AdvancedSettingsPanel tests with required props
- Update all snapshots to reflect new component structure
- Format test files according to biome rules
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* test(knowledge): simplify KnowledgeBaseFormModal button tests
Simplify button interaction tests to avoid text matching issues. Focus on testing behavior rather than implementation details.
Changes:
- Simplify advanced settings toggle test
- Simplify footer buttons test to check button count instead of text content
- Remove fragile text-based button selection
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add Git Bash detection and requirement check for Windows agents
- Add System_CheckGitBash IPC channel for detecting Git Bash installation
- Implement detection logic checking common installation paths and PATH environment
- Display non-closable error alert in AgentModal when Git Bash is not found
- Disable agent creation/edit button until Git Bash is installed
- Add recheck functionality to verify installation without restarting app
Git Bash is required for agents to function properly on Windows systems.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* i18n: add Git Bash requirement translations for agent modal
- Add English translations for Git Bash detection warnings
- Add Simplified Chinese (zh-cn) translations
- Add Traditional Chinese (zh-tw) translations
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* format code
---------
Co-authored-by: Claude <noreply@anthropic.com>
* feat: add ChatGPT conversation import feature
Introduces a new import workflow for ChatGPT conversations, including UI components, service logic, and i18n support for English, Simplified Chinese, and Traditional Chinese. Adds an import menu to data settings, a popup for file selection and progress, and a service to parse and store imported conversations as topics and messages.
* fix: ci failure
* refactor: import service and add modular importers
Refactored the import service to support a modular importer architecture. Moved ChatGPT import logic to a dedicated importer class and directory. Updated UI components and i18n descriptions for clarity. Removed unused Redux selector in ImportMenuSettings. This change enables easier addition of new importers in the future.
* Apply suggestion from @Copilot
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* fix: improve ChatGPT import UX and set model for assistant
Added a loading state and spinner for file selection in the ChatGPT import popup, with new translations for the 'selecting' state in en-us, zh-cn, and zh-tw locales. Also, set the model property for imported assistant messages to display the GPT-5 logo.
---------
Co-authored-by: SuYao <sy20010504@gmail.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
- Deleted the DataRefactorMigrateService and associated HTML files, as they are no longer needed.
- Removed test components and files related to data refactor migration, streamlining the codebase.
- Updated configuration files to reflect the removal of the data refactor migration functionality.
- Replaced core types with shared types in migration files to ensure consistency across the application.
- Deleted obsolete core types file and updated imports in migrator and window components to reference the new shared types.
- Enhanced the migration process by streamlining type definitions and improving code maintainability.
- Added internationalization support to the MigrationApp component, enabling dynamic language changes.
- Updated button labels and informational texts to use translation keys for better localization.
- Introduced a language selector to allow users to switch between languages during the migration process.
- Ensured that the migration process waits for i18n initialization before rendering the main application.
- Added 'migration_completed' stage to the migration process for better tracking of completion.
- Updated relevant components and hooks to handle the new stage, including UI changes to confirm migration completion.
- Adjusted messages and progress indicators to reflect the new stage in the migration workflow.
- Integrated migration v2 functionality by importing necessary modules and registering IPC handlers.
- Updated the migration process to check for data migration needs and handle the migration window.
- Added new dependencies for stream-json and its types in package.json.
- Updated electron.vite.config.ts to include the new migration window HTML file.
