Add IO Intelligence Provider

[ertan2002]

Description

This PR adds comprehensive support for IO Intelligence as a new provider in Roo Code, enabling users to access a wide range of cutting-edge AI models through IO Intelligence's unified API platform.

Key Implementation Details:

• OpenAI-Compatible Integration: Extends BaseOpenAiCompatibleProvider for seamless integration with existing infrastructure
• Dynamic Model Discovery: Implements intelligent model fetching with caching and error handling through getIOIntelligenceModels
• Comprehensive Model Support: Includes support for various model families including Llama, DeepSeek, Qwen, Mistral and OpenAI models with proper pricing, context windows, and technical specifications
• Robust Error Handling: Implements proper fallback mechanisms and error recovery for API failures
• Type-Safe Configuration: Uses TypeScript discriminated unions for provider settings integration

Design Choices:

• Used caching strategy for model fetching to improve performance and reduce API calls
• Implemented fallback model information when API is unavailable
• Followed existing provider patterns for consistency with the codebase
• Added comprehensive test coverage for both success and error scenarios

Test Procedure

Manual Testing Steps:

1. Install the generated VSIX package: code --install-extension bin/roo-cline-3.25.10.vsix
2. Open Roo Code extension settings
3. Select "IO Intelligence" from the API Provider dropdown
4. Enter a valid IO Intelligence API key and test model functionality
5. Verify model selection shows available IO Intelligence models
6. Test streaming responses and message handling
7. Verify proper error handling for invalid API keys
8. Test model fallback behavior when API is unavailable

Automated Testing:

• All TypeScript type checks pass (npm run check-types)
• ESLint validation passes with zero warnings (npm run lint)
• Build process completes successfully (npm run build)
• Unit tests pass for IO Intelligence provider (npm test)
• Integration tests verify API compatibility and streaming functionality

Pre-Submission Checklist

• Issue Linked: This PR is linked to an approved GitHub Issue (see "Related GitHub Issue" above).
• Scope: My changes are focused on the linked issue (one major feature/fix per PR).
• Self-Review: I have performed a thorough self-review of my code.
• Testing: New and/or updated tests have been added to cover my changes (if applicable).
• Documentation Impact: I have considered if my changes require documentation updates (see "Documentation Updates" section below).
• Contribution Guidelines: I have read and agree to the Contributor Guidelines.

Screenshots / Videos

Documentation Updates

• No documentation updates are required.
• Yes, documentation updates are required.

Documentation is needed for the IO Intelligence provider at:
https://docs.roocode.com/providers/io-intelligence

Please contact the IONET team to obtain:

• API authentication details
• Available models and capabilities
• Usage examples and configuration
• Pricing information

Additional Notes

Files Changed:

• Core Types: packages/types/src/providers/io-intelligence.ts - Complete IO Intelligence model definitions and types
• Provider Implementation: src/api/providers/io-intelligence.ts - Main IO Intelligence provider handler
• Model Fetching: src/api/providers/fetchers/io-intelligence.ts - Dynamic model discovery with caching
• Provider Settings: Updated provider configuration schema with IO Intelligence support
• API Integration: src/api/index.ts - IO Intelligence provider registration
• UI Components: webview-ui/src/components/settings/providers/IOIntelligence.tsx - Settings interface
• Localization: Added IO Intelligence strings across all supported languages
• Tests: src/api/providers/__tests__/io-intelligence.spec.ts - Comprehensive test suite

The implementation maintains consistency with existing provider patterns while adding robust model discovery and caching capabilities specific to IO Intelligence's API structure.

Get in Touch

Please join our Discord server. After verification, you can participate in the #io-intelligence channel.

We also have a Telegram group for IO Intelligence where we organize competitions, hackathons, and grant programs. Feel free to join us

---

Important

Adds IO Intelligence as a new provider with model fetching, caching, error handling, and comprehensive testing.

• Behavior:
  • Adds IO Intelligence as a new provider in src/api/providers/io-intelligence.ts, extending BaseOpenAiCompatibleProvider.
  • Implements model fetching with caching in src/api/providers/fetchers/io-intelligence.ts.
  • Supports models like Llama, DeepSeek, Qwen, and OpenAI with pricing and context specifications.
• Error Handling:
  • Adds error handling for API failures and fallback mechanisms in io-intelligence.ts.
• Configuration:
  • Updates provider-settings.ts to include IO Intelligence configuration.
  • Adds TypeScript discriminated unions for provider settings.
• Testing:
  • Adds tests for IO Intelligence in src/api/providers/__tests__/io-intelligence.spec.ts.
  • Updates validate.test.ts to include IO Intelligence model validation.
• Localization:
  • Adds IO Intelligence strings to multiple language files for localization support.

^{This description was created by for b27fde7. You can customize this summary. It will automatically update as commits are pushed.}

[roomote]

Thank you for your contribution! I've reviewed the IO Intelligence provider implementation and found it to be well-structured overall, following existing provider patterns nicely. The OpenAI-compatible integration approach is solid, and the test coverage is comprehensive. I've left some suggestions inline to help improve the implementation.

[daniel-lxs]

Thank you @ertan2002!