feat: extract models from command-code dist, load via models.json

[ninehills]

• Add scripts/extract-models.ts to parse command-code npm dist file
• Generate models.json (21 models, 15 pricing entries) with contextWindow and maxOutputTokens pre-filled; no nulls or hardcoded fallbacks in index.ts
• Rewrite index.ts to load model list and costs from models.json
• Cap gateway model maxOutputTokens at 65536 (API limit for Baseten/Vercel)
• Add 'Update models' section to README documenting the generation flow
• Add npm run extract-models script

[patlux]

Thanks @ninehills for opening this and adding the updated model list. I pushed two follow-up commits on top of your PR:

• switched model discovery from a committed/generated models.json to live fetching from https://api.commandcode.ai/provider/v1/models at startup
• removed the command-code package/dist extractor and models.json from the package
• added COMMANDCODE_MODELS_URL for tests/local mocks
• updated the README model-discovery docs
• added parser coverage and updated the local pi integration test to mock the model-list endpoint and assert Qwen/Qwen3.7-Max

Verified locally: npm run format:check, npm run typecheck, and npm test all pass. Merging this now.

[patlux]

Shipped in pi-commandcode-provider@0.1.1 / tag v0.1.1.

Install/update via:

pi update npm:pi-commandcode-provider
# or pin explicitly
pi install npm:pi-commandcode-provider@0.1.1