fix(codex): avoid partial model effort pinning (#842)
Co-authored-by: Andrew Kriz <akriz@vt.edu> Co-authored-by: Tom Boucher <trekkie@nomorestars.com>
This commit is contained in:
5
.changeset/838-codex-agent-model-effort-consistency.md
Normal file
5
.changeset/838-codex-agent-model-effort-consistency.md
Normal file
@@ -0,0 +1,5 @@
|
||||
---
|
||||
type: Fixed
|
||||
pr: 842
|
||||
---
|
||||
Codex agent TOML generation no longer pins `model_reasoning_effort` when the agent is intentionally inheriting the active Codex chat model. GSD still emits both `model` and `model_reasoning_effort` when a per-agent model override or `runtime: "codex"` resolver pins the model, avoiding the confusing partial state where the model followed Codex UI selection while effort followed GSD catalog defaults. (#838)
|
||||
Reference in New Issue
Block a user