›_ Codex Issues
Codex Issues / #37660

[macOS Desktop 26.803.41515] Nearly every prompt/goal enters Reconnecting 5/5 and ends with "request timed out"

Open 💬 5 comments Opened Aug 9, 2026 by GGBondBlueWhale
💡 Likely answer: A maintainer (github-actions[bot], contributor) responded on this thread — see the highlighted reply below.

What version of the Codex App are you using (From “About Codex” dialog)?

ChatGPT/Codex Desktop 26.803.41515 (released Aug 7, 2026)

What subscription do you have?

ChatGPT Pro

What platform is your computer?

  • macOS Tahoe 26.5.2
  • Apple Silicon / arm64
  • MacBook Pro 16-inch
  • Apple M5 Max
  • 128 GB unified memory

What issue are you seeing?

On the current macOS desktop build, almost every time I send a prompt or start/resume a goal, the request spends several minutes in Working, then enters:

Reconnecting 5/5

and eventually ends with:

request timed out

Representative observed sequence:

Working for 5m 22s
Reconnecting 5/5

and in another occurrence:

Working for 7m 32s
Reconnecting 5/5
request timed out

This is recurrent rather than a one-off failure. In some cases, the task only begins or resumes after the timeout sequence, which makes the error state misleading: the UI appears to report a terminal failure even though work may subsequently continue.

The problem is visible in the ChatGPT macOS desktop application’s Codex surface and affects both ordinary prompts and goal/task starts.

What steps can reproduce the bug?

  1. Open ChatGPT/Codex Desktop on macOS.
  2. Open an existing project conversation or goal.
  3. Send a prompt, or start/resume a goal.
  4. Wait while the UI remains on Working for several minutes.
  5. Observe Reconnecting 5/5.
  6. Observe request timed out after the reconnect attempts are exhausted.
  7. Retry with another prompt/task; the same sequence occurs frequently.

What is the expected behavior?

  • Prompts and goals should begin normally without a multi-minute reconnect loop.
  • A transient transport interruption should recover without exhausting all five retries.
  • If the underlying task is still alive and later continues, the desktop UI should not present a terminal-looking timeout; it should reconcile and display the authoritative task state.
  • If the request truly failed, the app should provide a clear retry/resume action without requiring the user to guess whether work is still running.

Additional information

In-app feedback was submitted with the current ChatGPT session logs and browser tabs/browser logs included.

Feedback ID:

019fda84-a41b-7980-8108-bbb8616dfade

View original on GitHub ↗

5 Comments

github-actions[bot] contributor · 19 days ago

Potential duplicates detected. Please review them and close your issue if it is a duplicate.

  • #37647
  • #37649

Powered by Codex Action

qw72tc7fxw-prog · 8 days ago

Adding an independent reproduction from another macOS Codex Desktop user after the recent update.

Observed behavior:

  • Codex repeatedly hits timeout / reconnect behavior after prompts are submitted.
  • The problem persists across multiple full app restarts.
  • Restarting Codex several times has not resolved it.
  • This is frequent enough to disrupt normal project work rather than being an isolated transient timeout.

There is also a separate composer regression after the same update: after sending a prompt or using Steer, the submitted text can remain visible in the text box instead of clearing. I am reporting that separately so it can be tracked independently.

qw72tc7fxw-prog · 8 days ago

Additional affected environment from another user reproduction:

  • Codex Desktop: 26.814.41407
  • About dialog: Powered by Codex & OWL
  • Release date shown: Aug 18, 2026
  • Platform: macOS
  • Subscription: ChatGPT Pro
  • Symptom: frequent Reconnecting / timeout behavior after the update
  • Multiple full Codex app restarts did not resolve the issue

This suggests the timeout/reconnect regression is still reproducible on the Aug 18 desktop build, not only the earlier Aug 7 build originally reported here.

qw72tc7fxw-prog · 8 days ago

User impact/severity feedback for build 26.814.41407 (released Aug 18, 2026):

The user describes this as the worst Codex update they have experienced so far because the regression is not isolated to a cosmetic issue. Frequent timeout/reconnecting behavior is disrupting normal work, persists after multiple restarts, and is occurring alongside a separate composer-state regression after Send/Steer. Combined, these issues make the current desktop build materially less usable than the previous version.

qw72tc7fxw-prog · 8 days ago

Additional user impact report for Codex Desktop 26.814.41407 (released Aug 18, 2026):

This is not an occasional timeout. In normal project work, the user is seeing the reconnect/timeout failure roughly every 3–4 commands. When it happens, work stops and the UI does not provide a clear Retry button/action, so the user cannot simply resume the failed turn. Combined with the separate composer-state regression (submitted Send/Steer text sometimes remains in the input box), this makes it unclear what was accepted and materially disrupts ongoing work.

The user has already restarted the app multiple times with no improvement. Their feedback is that this release should have had stronger regression/reliability testing before rollout because the current frequency of failures is directly impacting work progress.

Requested UX/reliability improvements:

  • fix the recurrent reconnect/timeout regression;
  • provide an explicit Retry/Resume action when a request really fails;
  • reconcile UI state clearly when the backend task may still be alive;
  • avoid requiring users to restart or manually reconstruct the previous command.