* feat: add Linux system title bar setting option
Add a setting in Display Settings that allows Linux users to switch
between custom title bar (frameless window with WindowControls) and
native system title bar. The setting requires app restart to take effect
since Electron's frame option cannot be changed at runtime.
- Add useSystemTitleBar config key and getter/setter in ConfigManager
- Add IPC channel and handler for setting persistence
- Add Redux state and action for useSystemTitleBar
- Add UI toggle in DisplaySettings (Linux only)
- Hide WindowControls when system title bar is enabled on Linux
- Modify WindowService to check setting when creating window on Linux
- Add translations for all supported locales
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: improve window controls positioning in left navbar layout
Move WindowControls inside NavbarContainer as a flex item instead of
using fixed positioning. This ensures the window controls are properly
positioned adjacent to the navbar content when using the left navbar
layout.
- Remove position: fixed from WindowControlsContainer styling
- Include WindowControls as last child of NavbarContainer
- Remove extra padding-right from NavbarRight since controls are now
in the flex layout
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: remove padding-right from TabsBar to align window controls to edge
Remove the 8px padding-right for Windows/Linux in TabsBar that was
causing window controls to not be flush against the window edge.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* fix: add right padding for settings button when Linux uses system title bar
* fix: restore NavbarRight paddingRight to 15px for consistent spacing
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
When clicking the tray icon on Linux with another window on top,
the main window would not properly come to the front. This was due
to Linux window managers' focus stealing prevention.
The fix uses a hide/show sequence to simulate the "close to tray
and reopen" behavior which works correctly. This approach resets
the window state and makes the window manager treat it as a new
window activation request.
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
The normalizeProvider() calls inside useAppSelector callbacks were
creating new object references on every render, causing infinite
re-render loops in components that depend on provider objects.
This fix uses createSelector from Redux Toolkit to properly memoize
the normalized providers, preventing unnecessary re-renders in:
- GithubCopilotSettings (useEffect depends on provider)
- Painting pages (useAllProviders returns new array each render)
Fixes the "Maximum update depth exceeded" error introduced in 8186d4fa.
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat(notes): add export to Word functionality
Add a menu item in the Notes page to export the current note to a Word document.
The feature leverages the existing ExportService which converts markdown to docx format.
Changes:
- Add "Export to Word" menu item in MenuConfig.tsx
- Add handleExportToWord handler in HeaderNavbar.tsx
- Add i18n translations for all supported languages
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* feat(i18n): Update translations for multiple languages to improve export functionality
Updated the translation files for German, Greek, Spanish, French, Japanese, Portuguese, Romanian, and Russian to provide accurate translations for export-related messages. This includes phrases for exporting to Word and handling content export scenarios, ensuring a consistent user experience across different languages.
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: kangfenmao <kangfenmao@qq.com>
refactor(ThinkingEffect): replace useState+useEffect with useMemo for derived state
The messages array is purely derived from content and isThinking props,
not fetched from an API. Using useState+useEffect for derived state is
a React anti-pattern that causes unnecessary re-renders.
This change:
- Removes lodash isEqual dependency
- Reduces code complexity
- Avoids double render cycle
Signed-off-by: SherlockShemol <shemol@163.com>
* fix(i18n): update and refine Romanian translation
I have corrected several typos and refined the terminology in the ro-ro.json file for better linguistic accuracy. This update ensures translation consistency throughout the user interface.
* i18n: Update and fix Romanian localization (ro-RO)
The Romanian localization file has been updated.
Necessary corrections have been applied to address issues identified during an interface review, ensuring consistent terminology and improved message clarity.
* i18n: Capitalize "Users" label for UI consistency
Updated the "users" key in ro-ro.json to use an uppercase initial. This ensures visual consistency with other menu items in the settings section (User Management).
* Update Romanian localization (ro-RO)
* fix(i18n): update topic time translation for clarity
Updated settings.topic.show.time to "Afișează ora subiectului" to maintain context as requested by reviewer.
* feat(i18n): Update and refine Romanian localization (ro-RO)
Hi! I have updated the Romanian localization file (`ro-ro.json`) to improve the overall user experience.
Key changes:
- Refined terminology for better UI consistency (e.g., changed "folder" to "dosar").
- Fixed grammar and phrasing to ensure a more natural flow.
- Synced the branch with the latest upstream changes.
All checks have passed, and the translation is now ready for review. Thank you!
* feat: integrate Kimi CLI into Code Tools
- Add Kimi CLI as a new code tool option in Code Tools page
- Support OpenAI-compatible models for Kimi CLI
- Use uvx to automatically download and run kimi-cli (Python package)
- Configure environment variables (OPENAI_API_KEY, OPENAI_BASE_URL, OPENAI_MODEL)
- Skip installation check as uvx handles package management automatically
Changes:
- Add kimiCli to codeTools enum
- Add Kimi CLI to CLI_TOOLS list with label
- Add provider filter for OpenAI-compatible providers
- Add environment variable generation logic
- Add model filtering logic in UI
- Special handling in CodeToolsService to use uvx instead of bun
- Skip installation process for kimi-cli as uvx auto-downloads
This integration allows users to launch Kimi CLI directly from Cherry Studio
without manual installation, leveraging uvx for seamless Python package management.
* Update src/renderer/src/pages/code/index.ts
Co-authored-by: George·Dong <98630204+GeorgeDong32@users.noreply.github.com>
* Update src/main/services/CodeToolsService.ts
Co-authored-by: George·Dong <98630204+GeorgeDong32@users.noreply.github.com>
* Update src/renderer/src/pages/code/CodeToolsPage.tsx
Co-authored-by: George·Dong <98630204+GeorgeDong32@users.noreply.github.com>
* fix: remove extra blank line in CodeToolsPage.tsx for biome format compliance
---------
Co-authored-by: xiaoju111a <xiaoju111a@users.noreply.github.com>
Co-authored-by: George·Dong <98630204+GeorgeDong32@users.noreply.github.com>
Updated the needsUpdate condition to handle cases where the tool is installed but has no version, ensuring updates are correctly flagged when necessary.
fix: normalize provider apiHost at source to handle trailing slashes
Normalize provider apiHost by removing trailing slashes in useProvider.ts
selectors. This ensures consistent URL concatenation across the entire
application, including image generation pages, without modifying each
usage point individually.
Fixes#12485
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix(i18n): update and refine Romanian translation
I have corrected several typos and refined the terminology in the ro-ro.json file for better linguistic accuracy. This update ensures translation consistency throughout the user interface.
* i18n: Update and fix Romanian localization (ro-RO)
The Romanian localization file has been updated.
Necessary corrections have been applied to address issues identified during an interface review, ensuring consistent terminology and improved message clarity.
* i18n: Capitalize "Users" label for UI consistency
Updated the "users" key in ro-ro.json to use an uppercase initial. This ensures visual consistency with other menu items in the settings section (User Management).
* Update Romanian localization (ro-RO)
* fix(i18n): update topic time translation for clarity
Updated settings.topic.show.time to "Afișează ora subiectului" to maintain context as requested by reviewer.
* fix(aiCore): preserve conversation history for image enhancement models
- Changed image enhancement model handling to preserve full conversation context
- Only merge images from previous assistant message into last user message
- Return messages as-is when no images need to be merged
- Added test case for LLM-to-image-model switching scenario
This allows users to switch from LLM conversations to image generation models
while keeping the conversation context for guiding image generation.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: format
---------
Co-authored-by: Claude <noreply@anthropic.com>
The Qwen Code tool was failing with 'Model stream ended without a finish reason'
because the OPENAI_BASE_URL environment variable was not properly formatted.
This fix adds /v1 suffix to the baseUrl when it's missing for OpenAI-compatible
tools (qwenCode, openaiCodex, iFlowCli).
Changes:
- Import formatApiHost from @renderer/utils/api
- Use formatApiHost to format baseUrl before passing to environment variables
- Add unit tests for the URL formatting behavior
* fix(i18n): update and refine Romanian translation
I have corrected several typos and refined the terminology in the ro-ro.json file for better linguistic accuracy. This update ensures translation consistency throughout the user interface.
* i18n: Update and fix Romanian localization (ro-RO)
The Romanian localization file has been updated.
Necessary corrections have been applied to address issues identified during an interface review, ensuring consistent terminology and improved message clarity.
* i18n: Capitalize "Users" label for UI consistency
Updated the "users" key in ro-ro.json to use an uppercase initial. This ensures visual consistency with other menu items in the settings section (User Management).
* fix: update dependencies and patch files for strict JSON schema compliance
- Updated `@ai-sdk/openai-compatible` to include version 1.0.30 and adjusted related patch files.
- Removed obsolete patch for `@ai-sdk/openai-compatible@1.0.28`.
- Added new patch for `@openrouter/ai-sdk-provider` to support strict JSON schema options.
- Modified `options.ts` to set `strictJsonSchema` to false for OpenAI models.
- Enhanced OpenAI compatible provider options to include `sendReasoning` and `strictJsonSchema`.
- Updated lockfile to reflect changes in patched dependencies and their hashes.
* fix: filter strictJsonSchema from request body in OpenRouter patch
- Destructure and remove strictJsonSchema from openrouterOptions before spreading into request body
- This prevents sending the internal option to the OpenRouter API
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* Initial plan
* feat: Add year to topic time display format
Co-authored-by: GeorgeDong32 <98630204+GeorgeDong32@users.noreply.github.com>
* fix: improve topic unpin UX by moving to top of unpinned list
- Unpinned topics now move to the top of the unpinned section
- List automatically scrolls to the unpinned topic position
- Keeps the requirement to unpin before deleting pinned topics
Closes#12398
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: GeorgeDong32 <98630204+GeorgeDong32@users.noreply.github.com>
Co-authored-by: George·Dong <GeorgeDong32@qq.com>
* fix(logger): allow logging with unknown window source
Previously, LoggerService would block all logging when window source
was not initialized, which could swallow important business errors.
Now it uses 'UNKNOWN' as the window source and continues logging.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* chore(logger): update documentation links for LoggerService eslint
Updated the ESLint configuration to point to the correct documentation for the unified LoggerService, ensuring users have access to the latest guides in both English and Chinese.
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* feat(models): add Qwen text-embedding models to defaults
Add four Qwen text-embedding models (v4, v3, v2, v1) to the
default model list in the renderer config. Group them under
"Qwen-text-embedding" and set the provider to "dashscope".
This ensures embedding models are available by default for
features that require text embeddings.
* fix(models): normalize qwen embedding group name
Change group value for Dashscope Qwen embedding models from
'Qwen-text-embedding' to 'qwen-text-embedding' in the default models
configuration. This makes the group naming consistent with other Qwen
model groups (lowercase) and avoids potential mismatches or lookup
errors caused by case differences.
* feat(dashscope): add qwen3-rerank model
Add qwen3-rerank model for Alibaba Cloud Bailian rerank API.
- Updated package.json to remove redundant i18n:check command.
- Added a "careers" section in the AboutSettings component with a button linking to the careers page.
- Introduced translations for the "careers" section in multiple languages including English, Chinese, German, Spanish, French, Japanese, Portuguese, Romanian, and Russian.
- Updated cache-related translations across various languages to provide localized support.
* fix(security): prevent path traversal vulnerability in DXT plugin system
Add input validation to prevent path traversal attacks in DXT plugin handling:
- Add sanitizeName() to filter dangerous characters from manifest.name
- Add validateCommand() to reject commands with path traversal sequences
- Add validateArgs() to validate command arguments
- Remove unsafe fallback logic in cleanupDxtServer()
The vulnerability allowed attackers to write files to arbitrary locations
on Windows by crafting malicious DXT packages with path traversal sequences
(e.g., "..\\..\\Windows\\System32\\") in manifest.name or command fields.
* refactor: use path validation instead of input sanitization
---------
Co-authored-by: defi-failure <159208748+defi-failure@users.noreply.github.com>
sendReasoning is a patch specific to @ai-sdk/openai-compatible package.
Previously it was incorrectly applied to all providers in buildGenericProviderOptions,
including those with dedicated SDK packages (e.g., cerebras, deepseek, openrouter).
Now it only applies when the provider will actually use openai-compatible SDK:
- No dedicated SDK registered (!hasProviderConfig(providerId))
- OR explicitly openai-compatible (providerId === 'openai-compatible')
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* fix: add dispose method to prevent abort listener leak
Add dispose() method to StreamAbortController that explicitly removes
the abort event listener when stream ends normally. Previously, the
listener would only be removed when abort was triggered ({ once: true }),
but if the stream completed normally without abort, the listener would
remain attached until garbage collection.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
* chore: format code
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
fix: set X11 window class and name to cherry-studio
Set window class and name for Linux X11 to ensure system tray and
window manager identify the app correctly instead of using default
'electron' identifier.
This commit fixes a bug where search results could not be retrieved from Bing, Baidu, and Google.
The root cause of this issue was a discrepancy in page content when the Electron window was hidden versus when it was visible. Additionally, the previous use of `did-finish-load` caused page jitter within the window, leading to sporadic failures in fetching search content.
To resolve this, I've enabled offscreen rendering, ensuring consistent page content regardless of window visibility. Furthermore, I've switched to using the `ready-to-show` event to ensure the complete page DOM is available before attempting to retrieve content, thereby eliminating the search bug.
* feat(fetch): add request throttling (already present in the original, keeping it)
Co-authored-by: suyao <sy20010504@gmail.com>
* refactor: separate message extraction from rendering
Extract `lastAssistantMessage` memoization separately from rendering
`MessageContent` component, improving code clarity and separation of
concerns.
* feat: Replace manual loading state with AssistantMessageStatus tracking
* refactor: Replace loading state with status enum in translation action
- Add LoadingOutlined icon for preparing state
- Remove AssistantMessageStatus dependency
- Simplify streaming detection using local status state
* feat: Add logging and status sync for translation action
* feat: Refactor action component state management to be consistent with
translate action
Replace separate `isContented` and `isLoading` states with a single
`status` state that tracks 'preparing', 'streaming', and 'finished'
phases. Sync status with assistant message status and update footer
loading prop accordingly.
* fix: Add missing pauseTrace import to ActionTranslate component
* fix: Add missing break statements in assistant message status handling
* fix: Move pauseTrace call inside abort completion condition
* feat(mcp): add hub server type definitions
- Add 'hub' to BuiltinMCPServerNames enum as '@cherry/hub'
- Create GeneratedTool, SearchQuery, ExecInput, ExecOutput types
- Add ExecutionContext and ConsoleMethods interfaces
Amp-Thread-ID: https://ampcode.com/threads/T-019b4e7d-86a3-770d-82f8-9e646e7e597e
Co-authored-by: Amp <amp@ampcode.com>
* feat(mcp): implement hub server core components
- generator.ts: Convert MCP tools to JS functions with JSDoc
- tool-registry.ts: In-memory cache with 10-min TTL
- search.ts: Comma-separated keyword search with ranking
- runtime.ts: Code execution with parallel/settle/console helpers
Amp-Thread-ID: https://ampcode.com/threads/T-019b4e7d-86a3-770d-82f8-9e646e7e597e
Co-authored-by: Amp <amp@ampcode.com>
* feat(mcp): integrate hub server with MCP infrastructure
- Create HubServer class with search/exec tools
- Implement mcp-bridge for calling tools via MCPService
- Register hub server in factory with dependency injection
- Initialize hub dependencies in MCPService constructor
- Add hub server description label for i18n
Amp-Thread-ID: https://ampcode.com/threads/T-019b4e7d-86a3-770d-82f8-9e646e7e597e
Co-authored-by: Amp <amp@ampcode.com>
* test(mcp): add unit tests for hub server
- generator.test.ts: Test schema conversion and JSDoc generation
- search.test.ts: Test keyword matching, ranking, and limits
- runtime.test.ts: Test code execution, helpers, and error handling
Amp-Thread-ID: https://ampcode.com/threads/T-019b4e7d-86a3-770d-82f8-9e646e7e597e
Co-authored-by: Amp <amp@ampcode.com>
* docs(mcp): add hub server documentation
- Document search/exec tool usage and parameters
- Explain configuration and caching behavior
- Include architecture diagram and file structure
Amp-Thread-ID: https://ampcode.com/threads/T-019b4e7d-86a3-770d-82f8-9e646e7e597e
Co-authored-by: Amp <amp@ampcode.com>
* ♻️ refactor(hub): simplify dependency injection for HubServer
- Remove HubServerDependencies interface and setHubServerDependencies from factory
- Add initHubBridge() to mcp-bridge for direct initialization
- Make HubServer constructor parameterless (uses pre-initialized bridge)
- MCPService now calls initHubBridge() directly instead of factory setter
- Add integration tests for full search → exec flow
* 📝 docs(hub): add comments explaining why hub is not in builtin list
- Add JSDoc to HubServer class explaining its purpose and design
- Add comment to builtinMCPServers explaining hub exclusion
- Hub is a meta-server for LLM code mode, auto-enabled internally
* ✨ feat: add available tools section to HUB_MODE_SYSTEM_PROMPT
- Add shared utility for generating MCP tool function names (serverName_toolName format)
- Update hub server to use consistent function naming across search, exec and prompt
- Add fetchAllActiveServerTools to ApiService for renderer process
- Update parameterBuilder to include available tools in auto/hub mode prompt
- Use CacheService for 1-minute tools caching in hub server
- Remove ToolRegistry in favor of direct fetching with caching
- Update search ranking to include server name matching
- Fix tests to use new naming format
Amp-Thread-ID: https://ampcode.com/threads/T-019b6971-d5c9-7719-9245-a89390078647
Co-authored-by: Amp <amp@ampcode.com>
* ♻️ refactor: consolidate MCP tool name utilities into shared module
- Merge buildFunctionCallToolName from src/main/utils/mcp.ts into packages/shared/mcp.ts
- Create unified buildMcpToolName base function with options for prefix, delimiter, maxLength, existingNames
- Fix toCamelCase to normalize uppercase snake case (MY_SERVER → myServer)
- Fix maxLength + existingNames interaction to respect length limit when adding collision suffix
- Add comprehensive JSDoc documentation
- Update tests and hub.test.ts for new lowercase normalization behavior
* ✨ feat: isolate hub exec worker and filter disabled tools
* 🐛 fix: inline hub worker source
* 🐛 fix: sync hub tool cache and map
* Update import path for buildFunctionCallToolName in BaseService
* ✨ feat: refine hub mode system prompt
* 🐛 fix: propagate hub tool errors
* 📝 docs: clarify hub exec return
* ✨ feat(hub): improve prompts and tool descriptions for better LLM success rate
- Rewrite HUB_MODE_SYSTEM_PROMPT_BASE with Critical Rules section
- Add Common Mistakes to Avoid section with examples
- Update exec tool description with IMPORTANT return requirement
- Improve search tool description clarity
- Simplify generator output with return reminder in header
- Add per-field @param JSDoc with required/optional markers
Fixes issue where LLMs forgot to return values from exec code
* ♻️ refactor(hub): return empty string when no tools available
* ✨ feat(hub): add dedicated AUTO_MODE_SYSTEM_PROMPT for auto mode
- Create self-contained prompt teaching XML tool_use format
- Only shows search/exec tools (no generic examples)
- Add complete workflow example with common mistakes
- Update parameterBuilder to use getAutoModeSystemPrompt()
- User prompt comes first, then auto mode instructions
- Skip hub prompt when no tools available
* ♻️ refactor: move hub prompts to dedicated prompts-code-mode.ts
- Create src/renderer/src/config/prompts-code-mode.ts
- Move HUB_MODE_SYSTEM_PROMPT_BASE and AUTO_MODE_SYSTEM_PROMPT_BASE
- Move getHubModeSystemPrompt() and getAutoModeSystemPrompt()
- Extract shared buildToolsSection() helper
- Update parameterBuilder.ts import
* ♻️ refactor: add mcpMode support to promptToolUsePlugin
- Add mcpMode parameter to PromptToolUseConfig and defaultBuildSystemPrompt
- Pass mcpMode through middleware config to plugin builder
- Consolidate getAutoModeSystemPrompt into getHubModeSystemPrompt
- Update parameterBuilder to use getHubModeSystemPrompt
* ♻️ refactor: move getHubModeSystemPrompt to shared package
- Create @cherrystudio/shared workspace package with exports
- Move getHubModeSystemPrompt and ToolInfo to packages/shared/prompts
- Add @cherrystudio/shared dependency to @cherrystudio/ai-core
- Update promptToolUsePlugin to import from shared package
- Update renderer prompts-code-mode.ts to re-export from shared
- Add toolSetToToolInfoArray converter for type compatibility
* Revert "♻️ refactor: move getHubModeSystemPrompt to shared package"
This reverts commit 894b2fd487.
* Remove duplicate Tool Use Examples header from system prompt
* fix: add handleModeChange call in MCPToolsButton for manual mode activation
* style: update AssistantMCPSettings to use min-height instead of overflow for better layout control
* feat(i18n): add MCP server modes and truncate messages in multiple languages
- Introduced new "mode" options for MCP servers: auto, disabled, and manual with corresponding descriptions and labels.
- Added translations for "base64DataTruncated" and "truncated" messages across various language files.
- Enhanced user experience by providing clearer feedback on data truncation.
* Normalize tool names for search and exec in parser
* Clarify tool usage rules in code mode prompts and examples
* Clarify code execution instructions and update example usage
* refactor: simplify JSDoc description handling by removing unnecessary truncation
* refactor: optimize listAllActiveServerTools method to use Promise.allSettled for improved error handling and performance
---------
Co-authored-by: Amp <amp@ampcode.com>
Co-authored-by: kangfenmao <kangfenmao@qq.com>
* fix: resolve ActionTranslate stalling after initialization
Issue: When invoking translate from the selection assistant, the fetchResult function does not react to the completion of initialize, causing the ActionTranslate component to enter an infinite loading state.
Cause: In commit 680bda3993, the initialize effect hook was refactored into a callback function. This refactor omitted the notification that fetchResult should run after initialization, so fetchResult never executes post‑initialization.
Fix: Change the initialized flag from a ref to a state variable and have fetchResult listen to this state. This modification ensures the effect hook triggers fetchResult exactly once after initialization is complete.
* fix(ActionTranslate): fix missing dependency in useEffect hook
---------
Co-authored-by: icarus <eurfelux@gmail.com>
AI SDK v5 uses 'developer' role for reasoning models, but some providers
like Azure DeepSeek R1 only support 'system', 'user', 'assistant', 'tool'
roles, causing HTTP 422 errors.
This fix adds a custom fetch wrapper that converts 'developer' role back
to 'system' for providers that don't support it.
Fixes#12321🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Use fixed base URL for TokenFlux image API instead of provider.apiHost.
After migration 191, apiHost was changed to include /openai/v1 suffix
for chat API compatibility, but image API needs the base URL without
this suffix, causing /openai/v1/v1/images/models (wrong path).
Fixes#12284
Signed-off-by: SherlockShemol <shemol@163.com>
- Changed all 'Assistant:' labels to 'A:' in tool use examples for consistency
- Added missing blank line before final response in both files
- Affects promptToolUsePlugin.ts and prompt.ts
- Resolves#12310
* fix: use ipinfo lite API with token for IP country detection
Switch from ipinfo.io/json to api.ipinfo.io/lite/me endpoint with
authentication token to improve reliability and avoid rate limiting.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
* fix: use country_code field from ipinfo lite API response
The lite API returns country_code instead of country field.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
---------
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
