›_ Codex Issues
Codex Issues / #10723

Feature Request: Add option to display reasoning summaries (thinking blocks) in Codex macOS app

Open 💬 9 comments Opened Feb 5, 2026 by JKay15
💡 Likely answer: A maintainer (swordfish444, contributor) responded on this thread — see the highlighted reply below.

Problem

The Codex macOS app does not display reasoning summaries or thinking blocks during model execution. When the model is thinking, the UI shows nothing until the final answer appears, which makes the app feel unresponsive. Other Codex tools such as the CLI and IDE render reasoning summaries, and there are configuration flags (model_reasoning_summary, hide_agent_reasoning, show_raw_agent_reasoning) documented to control reasoning visibility.

Steps to reproduce

  1. Install the latest Codex macOS app (observed on the build current as of 2026‑02‑05).
  2. Launch a new conversation and ask a non‑trivial question.
  3. Observe that during long thinking, the app does not stream reasoning summaries or display thinking blocks.
  4. Edit ~/.codex/config.toml and add:

``toml
model_reasoning_summary = "detailed"
hide_agent_reasoning = false
show_raw_agent_reasoning = true
``
then restart the app.

  1. Observe that the app still does not display reasoning summaries.

Expected behavior

The Codex macOS app should either:

  • Display reasoning summaries in the main chat view like the CLI/IDE does. The CLI issue #8204 proposes flushing reasoning summaries incrementally and showing them by default【902190394343352†L242-L254】.
  • Or provide a user-visible setting to toggle reasoning summaries and respect model_reasoning_summary, hide_agent_reasoning, and show_raw_agent_reasoning configuration flags.

Related issues

The CLI/TUI has existing tickets about reasoning summary visibility and configuration flags not being respected【405976122463457†L240-L269】. Those issues confirm that users want control over reasoning visibility. This request is specifically for the macOS app, which currently lacks any UI to display these summaries or to configure them.

Environment

  • Codex macOS app version: latest as of 2026‑02‑05 (Codex CLI 0.97.0)
  • Model: gpt‑5.2‑codex
  • Platform: macOS (Apple Silicon)

Thanks for considering adding this capability to improve perceived responsiveness and feature parity with other Codex tools.

View original on GitHub ↗

9 Comments

swordfish444 contributor · 5 months ago

@etraut-openai This seems like the same underlying request as #8204 (stream reasoning summaries incrementally so the UI doesn’t feel frozen during long thinking). Suggest consolidating into one canonical issue (e.g. add an app label to #8204 and close this as a dup) to keep discussion + prioritization in one place.

etraut-openai contributor · 5 months ago

@swordfish444, I think these are unrelated. This is specifically about the Codex app and the presence of reasoning summaries. The other is about streaming reasoning summaries in the CLI.

swordfish444 contributor · 5 months ago

@etraut-openai Good call — I was mapping this to the broader “UI feels frozen during long thinking” request, but agreed this is app-specific (displaying summaries at all) vs CLI streaming behavior. Thanks for the quick correction.

oliviervroom · 5 months ago

please implement this!!

wuyak · 5 months ago

Thanks — I dug into this on macOS and it looks like the app is currently dropping reasoning items at render time.

  • The session JSONL still contains reasoning summaries (payload.type="reasoning" with non-empty payload.summary).
  • In the desktop app bundle, the webview renderer explicitly filters them out: d.type==="reasoning"&&(l=null) (found in Codex.app/Contents/Resources/app.asar → webview/assets/index-*.js).
  • I also see code that constructs {type:"reasoning", ...} items from payload.summary, so they’re being created and then nulled during rendering.

Tested on 26.212.1823 and 26.217.1959 — same behavior.

Request: please gate this behind a user-visible toggle / respect the existing config flags, and when enabled render collapsed-by-default with i18n’d labels + optional “Translate” action for the summary.

notOrrytrout · 3 months ago

Adding a toggle to the macOS app to toggle show thinking output like the picture. Would be nice. The image is of the ollama app. I think the regular ChatGPT website even does this.

<img width="770" height="431" alt="Image" src="https://github.com/user-attachments/assets/fcec5d2e-c3dd-4412-add5-67432b259521" />

eric-gitta-moore · 2 months ago

I also need this feature, and it includes the codex cli and the codex app. I often observe Codex in the process of thinking, but I have no idea what he is thinking about. Only when the "phase" stage appears can I see the brief response.

Yosuke-Maeda · 2 months ago

Agreed. It's often useful to read reasoning summary to evaluate model's performance and logic behind its behaviour.

jiangying000 · 15 days ago

Agree, reasoning summaries will be very helpful and useful.