Add RodiumAi as OpenAI-compatible model provider

[Docteur-Parfait]

Summary

• Add RodiumAi as a native Continue provider (rodiumai) with OpenAI-compatible API at https://api.rodiumai.io/v1/
• Dynamic model listing via GET /v1/models with RodiumAi catalogue metadata (display names, capabilities, provider icons)
• GUI Add New Model integration with auto-fetch of the public catalogue and RodiumAi-specific model packages
• Provider parity with OpenRouter for multi-upstream routing: Anthropic prompt caching, Gemini tool-call handling, reasoning fields, and dedicated openai-adapters adapter
• Vitest coverage for RodiumAi caching/Gemini behavior plus Jest tests for fetchRodiumAiModels
• Local CI scripts (scripts/ci-local.ps1 / Docker) to validate PR checks before opening upstream

Test plan

• Local Docker CI (mode PR RodiumAi): Prettier, core tsc/lint, fetchRodiumAiModels Jest, RodiumAi.vitest.ts, GUI tsc, openai-adapters unit tests
• Manual: Add New Model → RodiumAi → catalogue loads → chat on anthropic/claude-fable-5 and openai/gpt-5.4
• config.yaml with provider: rodiumai and model: provider/model-id

CLA

I have read the CLA Document and I hereby sign the CLA

[github-actions]

All contributors have signed the CLA ✍️ ✅
_{Posted by the CLA Assistant Lite bot.}

[cubic-dev-ai]

No issues found across 13 files

_{Re-trigger cubic}

[rodiumai]

I have read the CLA Document and I hereby sign the CLA

[Docteur-Parfait]

I have read the CLA Document and I hereby sign the CLA

[Docteur-Parfait]

recheck