Implement Chutes AI adapter

[ZHOUEU-star]

Summary

• replace the Chutes stub with an OpenAI-compatible chat completions integration
• use CHUTES_API_KEY and the llm.chutes.ai model API
• support model overrides, system prompts, max tokens, temperature, extra request fields, dry-run behavior, and usage token mapping

Verification

• pnpm --filter @profullstack/sh1pt-ai-chutes typecheck
• tsx dry-run smoke check for missing-key and dry-run paths
• curl https://llm.chutes.ai/v1/models returns OpenAI-style model metadata

Note: local vitest startup is blocked by a macOS Rollup native package signature loading error before tests execute.