- Add skills and agents sections to extensionToOutputString() output
- Implement full i18n support for all extension info labels
- Add translations for en, zh, de, ru languages
- Display skill names and agent names in extension list command
- Increase max retry attempts from 5 to 7 for better resilience
- Reduce initial delay from 5000ms to 1500ms for faster recovery
- Simplify getErrorStatus() to handle more status field variations
(status, statusCode, response.status, error.code)
- Remove model fallback mechanism (onPersistent429 callback)
- Remove isQwenThrottlingError() in favor of generic retry logic
- Clean up retry logging and error handling code
This improves the experience for users on services with throttling
like Idealab by providing more robust and faster retry behavior.
Related to #973
- Skip thought parts when accumulating roundText so reasoning content
does not leak into the subagent's final answer.
- Remove unnecessary `as SubAgentStreamTextEvent` type assertion.
- Add core tests for STREAM_TEXT thought flag and finalText exclusion.
When the model tries to invoke a skill name directly as a tool
(e.g., Tool: "pdf" instead of Tool: "Skill" with skill: "pdf"),
provide a clear error message explaining how to properly invoke skills.
🤖 Generated with [Qoder][https://qoder.com]
ACP prompt resolution called read_many_files with an outdated param name,
triggering a schema validation error. Pass paths and add a regression test.
Fixes#1354
- Move contextWindowSize auto-detection from resolveContentGeneratorConfigWithSources to ModelsConfig.applyResolvedModelDefaults
- Improves separation of concerns: validation vs. default value application
- resolveContentGeneratorConfigWithSources now focuses on validation and parsing
- applyResolvedModelDefaults handles all model-specific default configurations
- Add tokenLimit import to modelsConfig.ts
- All 105 tests passing
Addresses PR review comment about appropriate placement of fallback calculation logic.
- Remove maxOutputTokens field from ContentGeneratorConfig
- Remove maxOutputTokens auto-calculation logic in contentGenerator.ts
- Remove maxOutputTokens sync logic in config.ts hot-update
- Update dashscope.ts to use tokenLimit() function for dynamic calculation
- Remove maxOutputTokens from documentation (settings.md)
- Update all test cases to use correct model output limits
- All 143 tests passing (config.test.ts: 105, dashscope.test.ts: 38)
Changes:
- Users can no longer configure maxOutputTokens via settings
- Output token limits are now always dynamically calculated based on model
- contextWindowSize (input) remains user-configurable
- Prevents long text output truncation caused by default value settings
The schema incorrectly defined the field as 'loadMemoryFromIncludeDirectories'
while the migration map and documentation specified 'loadFromIncludeDirectories'.
This caused user configurations to be ignored.
Changes:
- Rename schema field from loadMemoryFromIncludeDirectories to loadFromIncludeDirectories
- Update all references in config loading and UI components
- Update test cases to reflect the correct field name
Fixes#1603
Clarify that when modelLimit is undefined, it could be either:
- No limit configured
- Config not initialized yet
In both cases, we don't modify max_tokens and let the API handle it.
- Fix handleModelChange to update contextWindowSize and maxOutputTokens during hot-update
- Fix dashscope.ts to use contentGeneratorConfig.maxOutputTokens instead of tokenLimit()
- Fix acpAgent.ts to use model-specific contextLimit for each model
- Add comprehensive tests for model switching scenarios
- Fix all TypeScript type errors (index signature and ConfigSource types)
- Fix all ESLint errors (remove 'any' types)
- Remove legacy childKey field from settingsSchema
- Add contextWindowSize and maxOutputTokens to documentation
- Refactor ContextUsageDisplay to accept contextWindowSize directly instead of Config object
- Add useMemo optimization for contextWindowSize in Footer component
- Fix logic gaps in contentGenerator for contextWindowSize and maxOutputTokens initialization
- Increase DEFAULT_OUTPUT_TOKEN_LIMIT from 4K to 8K for better usability
- Add fallback to default values when model is not available
- Add comprehensive LSP tool guidance in the Tool Usage section
- Document all LSP operations with their required parameters
- Clarify that workspaceSymbol only requires query, not filePath/line/character
- Emphasize using LSP directly instead of grep for code intelligence queries
- Extract NativeLspClient from NativeLspService for better separation of concerns
- Simplify LspConfigLoader by removing built-in configuration options
- Remove LSP_DEBUGGING_GUIDE.md as it's no longer needed
- Clean up unused LSP constants
- Remove deprecated LSP configuration from config.ts
- remove configuration options such as lsp.enabled, lsp.allowed, lsp.excluded, etc. from settings.json schema
- Delete lspSettingsSchema.ts files and associated JSON schema definitions
- Removed VS Code settings loading function, no longer merge. vscode/settings.json configuration
- Updated LSP documentation to reflect new configurations and experimental flags
-remove allow/exclude parameters in NativeLspService constructor
- Create new LspConfigLoader classes to handle LSP configuration loading and merging
- Updated debug guide to match the new configuration mechanism
- Simplify loadCliConfig functions, remove startLsp options
- Reconstruct the configuration loading process to remove duplicate configuration merge logic
- Add LspConfigLoader classes to implement configuration parsing and merging functions
