Issue Station
Sign In
Tools hereToolbox

codex - 💡(How to fix) Fix 1m context window gone after Gpt 5.5 Release. [5 comments, 6 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openai/codex#19208•Fetched 2026-04-24 05:58:44
View on GitHub
Comments
5
Participants
6
Timeline
14
Reactions
6
Author
ZakisbZakisb
Participants
BillDuke13BillDuke13cccat6cccat6Cinea4678Cinea4678etraut-openaietraut-openaigithub-actions[bot]github-actions[bot]ZakisbZakisb
Timeline (top)
commented ×5labeled ×4subscribed ×3closed ×1

Code Example

model = "gpt-5.5"
model_reasoning_effort = "xhigh"
model_context_window = 1000000
model_auto_compact_token_limit = 900000
personality = "pragmatic"
RAW_BUFFERClick to expand / collapse

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

26.422.20832

What subscription do you have?

Pro plan

What platform is your computer?

Mac os

What issue are you seeing?

I've enable 1m context window via codex config since the release of GPT 5.4 and it was working exceptionally well. today Codex announces GPT 5.5 stating it supports 1m Context window but weirdly thought it's gone in the codex app.

<img width="884" height="227" alt="Image" src="https://github.com/user-attachments/assets/8e8048b6-e1b4-494f-982f-063f5f1cffba" />

What steps can reproduce the bug?

Just launch the codex app and enable 1m context window in config.toml file

What is the expected behavior?

Having 1m context window automatically enabled

Additional information

here's my current config.toml file

model = "gpt-5.5"
model_reasoning_effort = "xhigh"
model_context_window = 1000000
model_auto_compact_token_limit = 900000
personality = "pragmatic"

extent analysis

TL;DR

The issue might be resolved by adjusting the config.toml file to ensure compatibility with the updated GPT 5.5 model in the Codex App.

Guidance

  • Verify that the config.toml file is correctly formatted and that the model_context_window value is indeed set to 1000000, as this should enable the 1m context window.
  • Check the Codex App's documentation or release notes for GPT 5.5 to see if there are any specific requirements or changes needed for the config.toml file to work with the new model.
  • Try resetting the Codex App to its default settings and then re-enabling the 1m context window to see if the issue persists.
  • If the problem continues, consider reaching out to the Codex App support team for further assistance, as they may be able to provide more specific guidance or troubleshooting steps.

Notes

The provided information suggests that the issue is related to the compatibility of the config.toml file with the updated GPT 5.5 model, but without more details from the Codex App's documentation or support team, it's difficult to provide a more specific solution.

Recommendation

Apply workaround: Adjust the config.toml file according to the Codex App's documentation or release notes for GPT 5.5, as this may resolve the issue with the 1m context window not being enabled.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#model loading#dependency error#configuration error#environment variable#network issue

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

codex - 💡(How to fix) Fix 1m context window gone after Gpt 5.5 Release. [5 comments, 6 participants]