Anthropic's Node client uses node-fetch, which expects a Node http(s).Agent.
Stop providing undici's Dispatcher as httpAgent; only set httpAgent when a proxy
is configured (via https-proxy-agent), otherwise let the SDK use its default.
- Footer.test.tsx: provide contextWindowSize in mock config to match
Footer component's new requirement for displaying context usage
- tokenLimits.test.ts: consolidate Kimi K2 tests and update expectations
to 256K for all variants to match the implementation
- Fix contextWindowSize not updating when switching models via setModel()
- Fix ACP agent to respect provider-configured contextWindowSize before auto-detection
- Simplify getTruncateToolOutputThreshold to use static threshold
- Add support for GLM-4.7, Kimi-2.5, and MiniMax-M2.1 models
- Update context usage display to require explicit contextWindowSize
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Redesign ModelSelector positioning to use fixed positioning with max-width
for better responsive layout
- Add model caching in WebViewProvider to resend available models when
webview becomes ready
- Add native VSCode notifications for model switching success/failure
- Display error messages to users in the chat when errors occur
- Simplify InputForm by removing redundant model selector wrapper styles
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
This commit includes several updates:
- Updated eslint configuration with improved formatting and organization
- Added SaveMemoryToolCall support in vscode-ide-companion
- Translated Chinese comments and UI text to English in various components
- Made minor code formatting improvements across multiple files
Add extra_body configuration option to model.generationConfig for passing
custom parameters to OpenAI-compatible API request bodies.
- Add extra_body to ContentGeneratorConfig type
- Add extra_body to MODEL_GENERATION_CONFIG_FIELDS and ModelGenerationConfig
- Implement extra_body merging in DefaultOpenAICompatibleProvider
- Implement extra_body merging in DashScopeOpenAICompatibleProvider
- Update documentation with examples and provider compatibility notes
- Note: This feature is only for OpenAI-compatible providers (openai, qwen-oauth)
Resolves#1647Resolves#1644
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Delete orphaned fallback/handler.ts and its tests (no longer imported
after removing onPersistent429 callback)
- Add JSDoc to getErrorStatus() documenting property check priority
- Add WebFetchToolCall import to toolcalls index
- Add fetch/web_fetch/webfetch/web_search/websearch kind support
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add expand/collapse functionality to ThinkingMessage
- Support defaultExpanded prop to control initial state
- Add status prop (loading/default) with pulse animation
- Introduce ChevronIcon for expand/collapse toggle
- Update ThinkingMessage styles with timeline support
- Add stories for all states (default, expanded, loading)
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
- Add WebFetchToolCall component to display web fetch and search operations
- Support URL/query display with output card
- Add expand/collapse for long output content
- Export WebFetchToolCall from toolcalls index
- Integrate WebFetchToolCall in ChatViewer component
Co-authored-by: Qwen-Coder <qwen-coder@alibabacloud.com>
