Issue Station
Sign In
Tools hereToolbox

codex - 💡(How to fix) Fix GPT-5.5 reports 258400 context window in Codex despite published 400K window [1 comments, 2 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#19319•Fetched 2026-04-25 06:11:50
View on GitHub
Comments
1
Participants
2
Timeline
9
Reactions
0
Author
alanxchen85alanxchen85
Participants
alanxchen85alanxchen85github-actions[bot]github-actions[bot]
Timeline (top)
cross-referenced ×4labeled ×3closed ×1commented ×1

Codex reports GPT-5.5 as having a 258400 token context window in live session events, while OpenAI's GPT-5.5 launch page says GPT-5.5 in Codex has a 400K context window.

Official source: https://openai.com/index/introducing-gpt-5-5/

Root Cause

Codex reports GPT-5.5 as having a 258400 token context window in live session events, while OpenAI's GPT-5.5 launch page says GPT-5.5 in Codex has a 400K context window.

Official source: https://openai.com/index/introducing-gpt-5-5/

Fix Action

Fix / Workaround

codex debug models reported this before a local hotfix:

Code Example

{"type":"task_started","model_context_window":258400}

---

{"type":"token_count","info":{"model_context_window":258400}}

---

{
  "slug": "gpt-5.5",
  "context_window": 272000,
  "max_context_window": 272000,
  "effective_context_window_percent": 95
}

---

272000 * 0.95 = 258400

---

model = "gpt-5.5"
model_context_window = 400000
model_auto_compact_token_limit = 370000
RAW_BUFFERClick to expand / collapse

Summary

Codex reports GPT-5.5 as having a 258400 token context window in live session events, while OpenAI's GPT-5.5 launch page says GPT-5.5 in Codex has a 400K context window.

Official source: https://openai.com/index/introducing-gpt-5-5/

Environment

  • Codex CLI: 0.124.0
  • Model: gpt-5.5
  • Plan: Pro
  • Platform: macOS

Observed

Live session JSONL events contain:

{"type":"task_started","model_context_window":258400}

and token count events also report:

{"type":"token_count","info":{"model_context_window":258400}}

The context-window-size status line showed about 258k for GPT-5.5 after a turn, even though it had previously shown 400k and there is a separate available-context metric.

Local evidence

codex debug models reported this before a local hotfix:

{
  "slug": "gpt-5.5",
  "context_window": 272000,
  "max_context_window": 272000,
  "effective_context_window_percent": 95
}

That exactly explains the emitted window:

272000 * 0.95 = 258400

Local config already specified:

model = "gpt-5.5"
model_context_window = 400000
model_auto_compact_token_limit = 370000

Expected

For GPT-5.5 in Codex, the total model context window displayed and emitted as model_context_window should be 400000, matching the published Codex window. Available/remaining context should be shown separately and may change with usage.

Suspected cause

The Codex model catalog appears to encode 272000 as the total GPT-5.5 Codex context window and then applies the 95% effective-window multiplier, producing 258400. The 272000 value looks like the input portion of a 400K split (272k input + 128k output) rather than the full Codex model window.

extent analysis

TL;DR

Update the Codex model catalog to reflect the correct total context window for GPT-5.5 as 400000.

Guidance

  • Verify the current model catalog configuration for GPT-5.5 to confirm the encoded context window value is indeed 272000.
  • Check if the effective-window multiplier is correctly applied and if it's necessary to adjust this value to achieve the desired context window of 400000.
  • Review the local config file to ensure the model_context_window is set to 400000 and that this value is being correctly propagated to the model catalog.
  • Investigate if the available-context metric is being displayed separately and if it's correctly updated based on usage.

Example

No code snippet is provided as the issue is related to configuration and model catalog settings.

Notes

The issue seems to be related to a discrepancy between the published context window for GPT-5.5 and the actual value encoded in the Codex model catalog. The provided local evidence suggests that the model catalog is using a split context window (272k input + 128k output) instead of the full 400k window.

Recommendation

Apply workaround: Update the local config file to override the model catalog settings and ensure the correct context window is used. Reason: The issue is likely caused by an incorrect configuration in the model catalog, and updating the local config file can provide a temporary workaround until the catalog is corrected.

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…
#API rate limit#retriever error#indexing error#inference speed#output truncation

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 GPT-5.5 reports 258400 context window in Codex despite published 400K window [1 comments, 2 participants]