Repository navigation
Regression: GPT-5.4 / GPT-5.5 1M context setting is ignored in Codex IDE extension, stuck at 258k #20132
Description
This appears to be a regression of the same context-window handling issue that happened when GPT-5.4 was first released. The model supports 1M context, but Codex IDE still behaves as if the usable context is capped at ~258k.
Impact:
This makes long coding sessions with GPT-5.4 / GPT-5.5 much less useful, because Codex starts auto-summarizing far earlier than expected. The main benefit of using the 1M context models is effectively unavailable inside the IDE extension.
What version of the IDE extension are you using?
latest
What subscription do you have?
Pro
Which IDE are you using?
VS Code
What platform is your computer?
Windows
What issue are you seeing?
The 5.4 and 5.5 models should support a 1M context window, but Codex appears to remain capped at around 258k context even after adding or changing the relevant 1M context configuration.
Because of this, Codex starts auto-summarizing very early, even when the actual conversation/workspace context is nowhere near 1M tokens. This makes long coding sessions difficult because useful context gets compressed or lost much earlier than expected.
This looks very similar to the issue that happened when 5.4 was first released: the model supported a larger context window, but Codex did not actually use it until the extension/config handling was fixed later. Now the same problem seems to be happening again with 5.5.
What steps can reproduce the bug?
Uploaded thread: 019dd732-5c39-77e3-9c28-d245c0bea2b4
What is the expected behavior?
Codex should respect the configured 1M context setting for models that support it, such as 5.4 and 5.5.
Configure Codex to use a 5.4 or 5.5 model that supports 1M context.
Add or change the relevant configuration for 1M context.
Start a long coding session in Codex.
Observe that Codex still reports or behaves as if the usable context is around 258k.
Auto-summarization begins much earlier than expected.
Additional information
The larger context window is one of the main reasons to use these models for coding tasks. If Codex is still capped at 258k internally, then the advertised 1M context support is effectively unusable inside Codex.
Please check whether the IDE extension / Codex runtime is correctly reading and applying the 1M context configuration for 5.4 and 5.5 models.
Activity
github-actions commentedon Apr 29, 2026
Potential duplicates detected. Please review them and close your issue if it is a duplicate.
Powered by Codex Action
[-]5.4 / 5.5 models are stuck at 258k context in Codex despite 1M context configuration[/-][+]Regression: GPT-5.4 / GPT-5.5 1M context setting is ignored in Codex IDE extension, stuck at 258k[/+]1812095643 commentedon Apr 29, 2026
Thanks for the duplicate detection. I reviewed the related issues and this does appear to be part of the same context-window regression / config-not-applied problem.
The important point I want to clarify for this report is that this is not just a UI display mismatch:
The bot-listed issues (#19185, #19409, #19208, #19142) seem to show the same pattern from different angles: config values, model catalog/session metadata, and actual runtime behavior do not agree.
Could the team clarify where the effective context limit is being enforced right now?
Specifically, is the ~258k runtime limit coming from:
If this is an intentional current product limit rather than a bug, it would be helpful for Codex to make that explicit instead of accepting 1M-related config values while still compacting around ~258k.