felixxia-oai 37eef7bacc Scale skill metadata budgets with model context windows (#34626) ...

## Why

A fixed character limit does not account for the different context-window sizes supported by models.

## What changed

- Budget extension-rendered skill metadata at 2% of the resolved model context window, capped at 4,000 tokens.
- Keep the existing 8,000-character fallback when model context metadata is unavailable.
- Include the omission marker in the budget and still emit it when no skill entry fits.
- Apply the same resolved budget to executor and host skill catalogs assembled for a turn.

## Testing

- Cover proportional and capped budgets, multibyte fallback accounting, and omission-marker behavior.
- Verify through the production turn path that larger model context windows include more catalog entries without exceeding the computed budget.

GitOrigin-RevId: 4667293f1594de4dd605b32b9fa4255d26772c0f

2026-07-21 22:16:27 +00:00

..

executor_file_system_authority.rs

Add batched executor capability discovery (#33852)

2026-07-17 15:45:48 +00:00

skills_extension.rs

Scale skill metadata budgets with model context windows (#34626)

2026-07-21 22:16:27 +00:00