mirror of
https://github.com/openai/codex.git
synced 2026-04-30 01:16:54 +00:00
Cap the model-visible skills section to a small share of the context window, with a fallback character budget, and keep only as many implicit skills as fit within that budget. Emit a non-fatal warning when enabled skills are omitted, and add a new app-server warning notification Record thread-start skill metrics for total enabled skills, kept skills, and whether truncation happened --------- Co-authored-by: Matthew Zeng <mzeng@openai.com> Co-authored-by: Codex <noreply@openai.com>
122 KiB
122 KiB