feat: add LiteLLM as AI gateway provider

[RheagalFire]

Summary

Add LiteLLM as an AI gateway provider. Users point the base URL at a LiteLLM proxy to access 100+ LLM providers through one OpenAI-compatible endpoint. No new dependencies - reuses existing chatWithOpenAICompatible handler.

Related Issue

N/A

Changes Made

• src/shared/providers/constants.ts - Added LiteLLM to ProviderName, OpenClawProviderId, and PROVIDER_DEFINITIONS
• src/main/libs/openclawConfigSync.ts - Added LiteLLM descriptor to PROVIDER_REGISTRY
• src/renderer/components/icons/providers/LiteLLMIcon.tsx - New icon component
• src/renderer/components/icons/providers/index.ts - Export new icon
• src/renderer/providers/uiRegistry.tsx - Register icon in provider icon map
• src/shared/providers/constants.test.ts - Added dedicated LiteLLM test + updated count assertions

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• Code refactoring
• Documentation update
• Performance improvement
• Other (please describe):

Testing

• Tested locally
• Added new tests
• Updated existing tests
• Manual testing performed

Screenshots (if applicable)

N/A

Checklist

• My code follows the project's style guidelines
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

Electron-Specific Changes

• Changes to main process (src/main/)
• Changes to preload script (src/main/preload.ts)
• Changes to IPC communication
• Changes to window management
• None

Additional Notes

• Additive only, no existing providers modified
• No new dependencies
• Default model list is empty, users add models matching their proxy config
• Live E2E verified: LiteLLM proxy (localhost:4000) -> Claude via Azure Foundry -> response parsed correctly

[github-actions]

👋 感谢你提交第一个 Pull Request！欢迎参与 LobsterAI 社区。

请确认 PR 已满足以下要求：

• 遵循 Conventional Commits 规范
• 包含清晰的变更说明
• UI 变更附上截图
• 通过所有 CI 检查

维护者会尽快 Review，感谢你的贡献！

---

👋 Thanks for your first pull request to LobsterAI! We appreciate your contribution.

Please make sure your PR:

• Follows the Conventional Commits spec
• Includes a clear description of the changes
• Has screenshots for UI changes
• Passes all CI checks

A maintainer will review your PR soon. Thank you! 🚀