anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

GPT models consistently run out of context earlier than indicated #8790

New Issue
Open
opened 2026-02-16 18:10:51 -05:00 by yindo · 5 comments
yindo commented 2026-02-16 18:10:51 -05:00
Owner
Copy Link
Copy Source

Originally created by @iloveicedgreentea on GitHub (Feb 7, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

With 5.1, 5.2, and 5.2, I get context length errors at 67% every time and have to do manual compaction to fix it

Plugins

No response

OpenCode version

No response

Steps to reproduce

No response

Screenshot and/or share link

No response

Operating System

No response

Terminal

No response

Originally created by @iloveicedgreentea on GitHub (Feb 7, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description With 5.1, 5.2, and 5.2, I get context length errors at 67% every time and have to do manual compaction to fix it ### Plugins _No response_ ### OpenCode version _No response_ ### Steps to reproduce _No response_ ### Screenshot and/or share link _No response_ ### Operating System _No response_ ### Terminal _No response_
yindo added the bug label 2026-02-16 18:10:51 -05:00
yindo commented 2026-02-16 18:10:51 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Feb 7, 2026):

This issue might be a duplicate of existing issues. Please check:

  • #11086: GPT 5.2 Codex - Compaction happens way too early and context limit is wrong
  • #6071: [BUG]: GPT 5.2 context_length_exceeded / Your input exceeds the context window of this model.
  • #10220: Request size exceeds model context window
  • #8089: Auto-compaction enabled by default, but context_length_exceeded errors still occur in agent workflows
  • #10634: Compaction overflow check doesn't account for large tool outputs until the next step, causing context overflow

Feel free to ignore if none of these address your specific case.

@github-actions[bot] commented on GitHub (Feb 7, 2026): This issue might be a duplicate of existing issues. Please check: - #11086: GPT 5.2 Codex - Compaction happens way too early and context limit is wrong - #6071: [BUG]: GPT 5.2 context_length_exceeded / Your input exceeds the context window of this model. - #10220: Request size exceeds model context window - #8089: Auto-compaction enabled by default, but context_length_exceeded errors still occur in agent workflows - #10634: Compaction overflow check doesn't account for large tool outputs until the next step, causing context overflow Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 18:10:51 -05:00
Author
Owner
Copy Link
Copy Source

@jesussmile commented on GitHub (Feb 7, 2026):

same issue here

@jesussmile commented on GitHub (Feb 7, 2026): same issue here
yindo commented 2026-02-16 18:10:51 -05:00
Author
Owner
Copy Link
Copy Source

@jasgeo75 commented on GitHub (Feb 7, 2026):

Same, broken support for both the gpt-5.x-codex and opus 4.6 models is seriously impeding workflow.

@jasgeo75 commented on GitHub (Feb 7, 2026): Same, broken support for both the `gpt-5.x-codex` and `opus 4.6` models is seriously impeding workflow.
yindo commented 2026-02-16 18:10:52 -05:00
Author
Owner
Copy Link
Copy Source

@heswithme commented on GitHub (Feb 7, 2026):

yup, gotta compact manually around 200k tokens, otherwise session gets borked

@heswithme commented on GitHub (Feb 7, 2026): yup, gotta compact manually around 200k tokens, otherwise session gets borked
yindo commented 2026-02-16 18:10:52 -05:00
Author
Owner
Copy Link
Copy Source

@entrptaher commented on GitHub (Feb 8, 2026):

Facing same situation on gpt codex 5.3, with where it says,

271,647  68% ($0.00) v1.1.5

It was already suspecious that it allows 270k tokens with 68% usage mark. This confirms the same finding with the OP as well.

Plus, the /compact didn't actually compact it and allow me to continue, rather it asked me to copy a super stripped down version of the discussion and paste it in a new session.

@entrptaher commented on GitHub (Feb 8, 2026): Facing same situation on gpt codex 5.3, with where it says, ``` 271,647 68% ($0.00) v1.1.5 ``` It was already suspecious that it allows 270k tokens with 68% usage mark. This confirms the same finding with the OP as well. Plus, the /compact didn't actually compact it and allow me to continue, rather it asked me to copy a super stripped down version of the discussion and paste it in a new session.
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#8790
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?