From 5d70140d62bc5ae58693168e594b7d6440199f27 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E9=9B=B7=E7=94=B5=E8=8A=BD=E8=A1=A3?= Date: Tue, 22 Sep 2026 18:42:49 -0400 Subject: [PATCH] docs(agents): the codex table is seven models --- AGENTS.md | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 9f72fb4..9a85b17 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -403,9 +403,9 @@ client-side, no backend surface. carries the thinking level. NO websocket, NO base_instructions. CATALOG is HARDCODED (`PlatformId::hardcoded_catalog` → `openai_codex_wire_models`, mapped through the SAME - `platform_wire_model_to_entry` output): the 5 `visibility=list` && - `supported_in_api=true` models the backend served on 2026-09-21 - (`gpt-6-astra`, `gpt-5.6-sol/terra/luna`, `gpt-5.5`, ctx 272000, + `platform_wire_model_to_entry` output): the 7 `visibility=list` && + `supported_in_api=true` models the backend served on 2026-09-22 + (`gpt-6-astra/sol/luna`, `gpt-5.6-sol/terra/luna`, `gpt-5.5`, ctx 272000, per-model efforts) — NO live `/models` fetch, NO codex-CLI / `~/.codex` dependency; the hidden `gpt-reserve` and `codex-auto-review` are EXCLUDED. Refresh the table by reading