You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Option A — CLI flag/env (e.g. --reasoning-effort or REASONING_EFFORT)
• Chosen once at launch → fixed for that run.
• Zero interactive code changes; works in CI/headless.
Option B — Interactive prompt in /model command (my preference)
• When any “o*” model is selected, prompt: low / medium / high.
• Users can change effort any time by re‑running /model (even with same model).
• Keeps startup simple; dynamic and intuitive for interactive use.
@tibo-openai Which approach do you prefer ?
Let me know and I’ll implement accordingly.
Activity
tibo-openai commentedon Apr 16, 2025
These cannot be set right now, but will accept a PR. This should be conditional on the model as not all models accept a reasoning effort.
zakkor commentedon Apr 16, 2025
What's the default?
lakshminarayanannn commentedon Apr 17, 2025
Option A — CLI flag/env (e.g. --reasoning-effort or REASONING_EFFORT)
• Chosen once at launch → fixed for that run.
• Zero interactive code changes; works in CI/headless.
Option B — Interactive prompt in /model command (my preference)
• When any “o*” model is selected, prompt: low / medium / high.
• Users can change effort any time by re‑running /model (even with same model).
• Keeps startup simple; dynamic and intuitive for interactive use.
@tibo-openai Which approach do you prefer ?
Let me know and I’ll implement accordingly.
rashim27us commentedon Apr 18, 2025
Hii @tibo-openai
I've implemented the
--reasoningCLI flag to allow users to customize the reasoning effort level used by the OpenAI 'o' models.Please review PR #314
feat: add `--reasoning` CLI flag (openai#314)
feat: add `--reasoning` CLI flag (openai#314)
aniketmaurya commentedon Aug 30, 2025
doesn't work for me
kcosr commentedon Sep 1, 2025
codex --config model_reasoning_effort="high"feat: add `--reasoning` CLI flag (openai#314)
Merge pull request #107 from just-every/upstream-merge
mymirai-nikki commentedon Aug 24, 2026
is the term extra high and max are just marketing terms in chatgpt web interface? or it also applies to codex cli?