›_ Codex Issues
Codex Issues / #32297

Built-in image generation repeatedly fails with network error after July 9 desktop update

Open 💬 14 comments Opened Jul 11, 2026 by woodenxyz

What version of the Codex App are you using?

Current Codex Desktop build installed after the July 9, 2026 update. The exact About-dialog version was not available in this session.

What subscription do you have?

ChatGPT subscription using the normal Codex Desktop sign-in.

What platform is your computer?

macOS, Apple Silicon.

What issue are you seeing?

The built-in image_gen tool repeatedly fails while sending the generation request to the Codex image endpoint.

The returned error is:

image generation failed: network error: error sending request for url
(https://chatgpt.com/backend-api/codex/images/generations)

Ordinary text conversations and other Codex operations continue to work in the same session. This appears specific to the built-in image-generation route rather than a general loss of connectivity.

Two separate image-generation attempts failed in the same way. Each request remained in a generating state for several minutes before returning the network error.

What steps can reproduce the bug?

  1. Open Codex Desktop.
  2. Start a normal local task.
  3. Ask Codex to use its built-in image generation tool to create a new image.
  4. The request stays in the generating state for several minutes.
  5. It eventually fails with the network error shown above.
  6. Retry with a different, shorter prompt; the same failure occurs.

What is the expected behavior?

The built-in image generation request should complete and display or save the generated image. If the image service is unavailable, the app should fail promptly with a useful status instead of waiting several minutes.

Additional information

  • Reproduced twice on July 11, 2026.
  • The prompts contained no reference images or unusual input.
  • Related recent reports after the same update window may include #32153, #32208, and #32038, although their visible failure modes are not identical.
  • No full diagnostic bundle is attached because it may contain unrelated local environment information. Additional narrowly scoped diagnostics can be provided if maintainers specify exactly which fields are needed.

View original on GitHub ↗

14 Comments

LastFlowerSociety · 9 days ago

Same issue.

weijie-he · 9 days ago

Same issue.

leo678910 · 8 days ago

same issue

zq123123667 · 8 days ago

same issue

zmq2163 · 7 days ago

same issue, anybody solve it?

jfbergado · 7 days ago

I got same issue, my alternative is Product Design plugin to generate image.

ivanchiu12 · 6 days ago

same here

acsghsc · 6 days ago

Same issue here (Windows 11 Pro, CLI 0.142.4 / desktop 26.707.8168.0, started ~July 13 after auto-update). I did some local log digging and found what appears to be the root cause — it may not actually be a network problem. Full analysis in #32937 (also related: #32440).

Summary:

  1. .codex/.sandbox/sandbox.<date>.log shows the sandbox setup failing repeatedly with SetNamedSecurityInfoW failed: 5 (ERROR_ACCESS_DENIED) when granting write ACEs on project folders and even read ACEs on Codex's own install dir under C:\Program Files\WindowsApps\. Zero occurrences in logs before the update, dozens per day after.
  1. Windows Application event log (Event ID 1509) shows the trigger: the sandbox now provisions dedicated local accounts (CodexSandboxOnline / CodexSandboxOffline), and profile initialization for them fails while copying TrustedInstaller-protected WindowsApps app-execution-alias reparse points from C:\Users\Default ("Access is denied").
  1. The broken sandbox then can't run any tool — image generation surfaces this as a generic "network error" (the request likely never leaves the machine), and file-reading tools fail with "tool execution environment failed to start".

Ruled out on my machine: antivirus/Controlled Folder Access (none active), proxy (none), TCP 443 connectivity to chatgpt.com/api.openai.com (fine). Reinstalling / running elevated does not help, consistent with reports here.

Evolan-wu · 5 days ago

same issue

InfiniteRandomVariable · 5 days ago

Temporarily solution is to use Gpt-5.5 for image generating tasks by reverting back to pre GPT-5.6 versions such as 0.138 or equivalent. The 0.144 is highly unstable, sometimes work, mostly not working for imagegen.

tuantuanmeow · 5 days ago

I used Qoder to fix the Codex, and it seems to be working.

C:\Users\admin\.codex\config.toml
find:
[windows]
sandbox = "elevated"

change to:
[windows]
sandbox = "unelevated"

This can bypass the problematic sandbox permission initialization. Note: This will reduce the security of sandbox isolation, but can restore image generation functionality, suitable as a temporary solution before waiting for an official fix.

xm2by · 5 days ago

same issue

waitingformywind · 5 days ago

Additional Windows reproduction on 2026-07-15.

Environment

  • Codex Desktop: 26.707.9981.0
  • Windows NT build: 26200.8655, x64
  • Built-in image_gen using the normal ChatGPT sign-in (no API/CLI fallback)
  • Windows sandbox config: [windows] sandbox = "elevated"

Observed behavior

A new-image request with no reference images and an ordinary prompt remained in the generating state for roughly 3–4 minutes, then failed with the exact error reported here:

image generation failed: network error: error sending request for url
https://chatgpt.com/backend-api/codex/images/generations

Normal Codex conversation and other tools continued to work in the same task.

Read-only checks

  • An unauthenticated HEAD request reached the same endpoint and returned HTTP 403, so basic DNS/TCP/TLS connectivity to chatgpt.com was available.
  • The three most recent Windows sandbox logs contained zero occurrences of:
  • SetNamedSecurityInfoW failed: 5
  • setup refresh had errors
  • helper_unknown_error
  • ERROR_ACCESS_DENIED
  • Those logs contained three successful WFP setup entries for the sandbox.
  • No Windows Application Event ID 1509 matching CodexSandboxOnline or CodexSandboxOffline was found in the previous seven days.

This confirms that the failure is still reproducible on a newer Desktop build. On this machine it does not match the sandbox-account provisioning failure described in #32937, so there may be more than one failure mode behind the same generic image-generation network error. The original report here is also on macOS.

It would help if the app exposed the underlying HTTP/auth/service error or a request correlation ID instead of collapsing these failures into a generic network error.

okokelly · 1 day ago

same issue today with my Mac version codex