Simpler model stylesheets with provider auto-inference

Simpler model stylesheets

Model stylesheets no longer require you to specify the provider alongside the model. The llm_model and llm_provider properties have been renamed to model and provider, and the provider is now auto-inferred from the model catalog — so you can drop provider entirely in most cases.

Before:

* { llm_model: claude-opus-4-6; llm_provider: anthropic; }
.gpt { llm_model: gpt-5.2; llm_provider: openai; }

After:

* { model: claude-opus-4-6; }
.gpt { model: gpt-5.2; }

Breaking change. llm_model and llm_provider stylesheet properties have been renamed to model and provider. Update your workflow stylesheets.

More

Improvements

• SSH sandbox now supports preview_url_base for correct port preview URLs on remote hosts
• Renamed logs-directory to run-directory in docs reference

Fixes

• Fixed demo workflow serialization