anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-23 02:36:57 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

Default Codex context length not matching Pro plan #4672

New Issue
Open
opened 2026-02-16 17:44:59 -05:00 by yindo · 23 comments
yindo commented 2026-02-16 17:44:59 -05:00
Owner
Copy Link
Copy Source

Originally created by @sam-ulrich1 on GitHub (Jan 10, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

In the code, the context length for GPT 5.2 codex shows 400,000 tokens, which is technically correct for the API, but on the pro plan for ChatGPT, I believe you only get like 250 to 260, something like that. So, if the average user signs up with ChatGPT and uses it, they are likely to hit a context error, which forces compaction. So, it would make sense to maybe detect if it's a ChatGPT versus an API integration, and then automatically configure the defaults, maybe?

Plugins

No response

OpenCode version

1.1.111

Steps to reproduce

No response

Screenshot and/or share link

No response

Operating System

No response

Terminal

No response

Originally created by @sam-ulrich1 on GitHub (Jan 10, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description In the code, the context length for GPT 5.2 codex shows 400,000 tokens, which is technically correct for the API, but on the pro plan for ChatGPT, I believe you only get like 250 to 260, something like that. So, if the average user signs up with ChatGPT and uses it, they are likely to hit a context error, which forces compaction. So, it would make sense to maybe detect if it's a ChatGPT versus an API integration, and then automatically configure the defaults, maybe? ### Plugins _No response_ ### OpenCode version 1.1.111 ### 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 17:44:59 -05:00
yindo commented 2026-02-16 17:44:59 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Jan 10, 2026):

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

  • #6071: [BUG]: GPT 5.2 context_length_exceeded / Your input exceeds the context window of this model - reports the same context limit mismatch issue with GPT 5.2 (showing 270k tokens when API limit is 400k)

Feel free to ignore if this doesn't address your specific case.

@github-actions[bot] commented on GitHub (Jan 10, 2026): This issue might be a duplicate of existing issues. Please check: - #6071: [BUG]: GPT 5.2 context_length_exceeded / Your input exceeds the context window of this model - reports the same context limit mismatch issue with GPT 5.2 (showing 270k tokens when API limit is 400k) Feel free to ignore if this doesn't address your specific case.
yindo commented 2026-02-16 17:44:59 -05:00
Author
Owner
Copy Link
Copy Source

@sam-ulrich1 commented on GitHub (Jan 10, 2026):

To be clear, you have to compact whether you run out of context space abruptly or not. It's just that if you have plugins like OhMyOpencode, then compaction could happen earlier at a more optimal point than the last second when you fully run out of tokens. So having a correct representation of the context by default would be nice for a lot of users.

PS love the hook system, custom hooks on compaction are a god send

@sam-ulrich1 commented on GitHub (Jan 10, 2026): To be clear, you have to compact whether you run out of context space abruptly or not. It's just that if you have plugins like OhMyOpencode, then compaction could happen earlier at a more optimal point than the last second when you fully run out of tokens. So having a correct representation of the context by default would be nice for a lot of users. PS love the hook system, custom hooks on compaction are a god send
yindo commented 2026-02-16 17:44:59 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 10, 2026):

ah okay ill look into it

@rekram1-node commented on GitHub (Jan 10, 2026): ah okay ill look into it
yindo commented 2026-02-16 17:44:59 -05:00
Author
Owner
Copy Link
Copy Source

@sam-ulrich1 commented on GitHub (Jan 10, 2026):

@rekram1-node Is there some way that I can modify my open code JSON to fix this without having to redefine all of the models and variants that come default with the new official codex integration? Just as a temporary workaround.

@sam-ulrich1 commented on GitHub (Jan 10, 2026): @rekram1-node Is there some way that I can modify my open code JSON to fix this without having to redefine all of the models and variants that come default with the new official codex integration? Just as a temporary workaround.
yindo commented 2026-02-16 17:44:59 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 10, 2026):

ig show me ur config but u can do partial model overrides u dont need complete redefinitions

@rekram1-node commented on GitHub (Jan 10, 2026): ig show me ur config but u can do partial model overrides u dont need complete redefinitions
yindo commented 2026-02-16 17:44:59 -05:00
Author
Owner
Copy Link
Copy Source

@PSU3D0 commented on GitHub (Jan 11, 2026):

Are there docs on partial model overrides?

@PSU3D0 commented on GitHub (Jan 11, 2026): Are there docs on partial model overrides?
yindo commented 2026-02-16 17:44:59 -05:00
Author
Owner
Copy Link
Copy Source

@sam-ulrich1 commented on GitHub (Jan 11, 2026):

Updated config with and it worked. did not know that it was config merging

  "provider": {
    "openai": {
      "models": {
        "gpt-5.2": {
          "limit": { "context": 272000, "output": 128000 }
        },
        "gpt-5.2-codex": {
          "limit": { "context": 272000, "output": 128000 }
        },
        "gpt-5.1-codex-max": {
          "limit": { "context": 272000, "output": 128000 }
        },
        "gpt-5.1-codex-mini": {
          "limit": { "context": 272000, "output": 128000 }
        }
      }
    }
  }
@sam-ulrich1 commented on GitHub (Jan 11, 2026): Updated config with and it worked. did not know that it was config merging ``` "provider": { "openai": { "models": { "gpt-5.2": { "limit": { "context": 272000, "output": 128000 } }, "gpt-5.2-codex": { "limit": { "context": 272000, "output": 128000 } }, "gpt-5.1-codex-max": { "limit": { "context": 272000, "output": 128000 } }, "gpt-5.1-codex-mini": { "limit": { "context": 272000, "output": 128000 } } } } } ```
yindo commented 2026-02-16 17:44:59 -05:00
Author
Owner
Copy Link
Copy Source

@sam-ulrich1 commented on GitHub (Jan 11, 2026):

nvm it did not merge. it overwrote the defaults

@sam-ulrich1 commented on GitHub (Jan 11, 2026): nvm it did not merge. it overwrote the defaults
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@FBakkensen commented on GitHub (Jan 12, 2026):

I have the excact same issue, always when used just short of 270K tokens, which match the available token count when using the pro / plus sub in codex.

@FBakkensen commented on GitHub (Jan 12, 2026): I have the excact same issue, always when used just short of 270K tokens, which match the available token count when using the pro / plus sub in codex.
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@kostrse commented on GitHub (Jan 12, 2026):

openai and codex should probably become separate providers.

@kostrse commented on GitHub (Jan 12, 2026): `openai` and codex should probably become separate providers.
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 12, 2026):

Guys ill try to fix this real soon, does anyone have a link to where the limits are defined? If not ill try to find it

@rekram1-node commented on GitHub (Jan 12, 2026): Guys ill try to fix this real soon, does anyone have a link to where the limits are defined? If not ill try to find it
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@NERO2k commented on GitHub (Jan 12, 2026):

Guys ill try to fix this real soon, does anyone have a link to where the limits are defined? If not ill try to find it

This should help:
https://github.com/openai/codex/blob/main/codex-rs/core/src/models_manager/model_info.rs

@NERO2k commented on GitHub (Jan 12, 2026): > Guys ill try to fix this real soon, does anyone have a link to where the limits are defined? If not ill try to find it This should help: https://github.com/openai/codex/blob/main/codex-rs/core/src/models_manager/model_info.rs
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@mykola-dev commented on GitHub (Jan 13, 2026):

i use github copilot subscription and my context window is always 100k doesnt matter which model i use (even opus/gemini pro)

@mykola-dev commented on GitHub (Jan 13, 2026): i use github copilot subscription and my context window is always 100k doesnt matter which model i use (even opus/gemini pro)
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@kostrse commented on GitHub (Jan 14, 2026):

GPT 5.2 via OpenAI API should have 400K, right?

@kostrse commented on GitHub (Jan 14, 2026): GPT 5.2 via OpenAI API should have 400K, right?
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@FBakkensen commented on GitHub (Jan 14, 2026):

i use github copilot subscription and my context window is always 100k doesnt matter which model i use (even opus/gemini pro)

Yes, all models has an artificial low context window using github copilot, this is the same whether you use github copilot, or use their subscription in opencode or any other tool

@FBakkensen commented on GitHub (Jan 14, 2026): > i use github copilot subscription and my context window is always 100k doesnt matter which model i use (even opus/gemini pro) Yes, all models has an artificial low context window using github copilot, this is the same whether you use github copilot, or use their subscription in opencode or any other tool
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@rchybicki commented on GitHub (Jan 16, 2026):

I just hit the context length window error on gpt-5.2 using an API key at 275k tokens, so I believe it's not API vs Sub. AFAIK OpenAI's 400k is input 270k + output 130k, which is a bit misleading.

@rchybicki commented on GitHub (Jan 16, 2026): I just hit the context length window error on gpt-5.2 using an API key at 275k tokens, so I believe it's not API vs Sub. AFAIK OpenAI's 400k is input 270k + output 130k, which is a bit misleading.
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 16, 2026):

Yeah having people report this still exists, looking into it

@rekram1-node commented on GitHub (Jan 16, 2026): Yeah having people report this still exists, looking into it
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@brandon93s commented on GitHub (Jan 16, 2026):

@rchybicki 5.2 or 5.2 codex? I believe the input limit was only set for codex models.

@rekram1-node I did hit it again today when a tool-call boiled over the limit when it tried to add a large git diff. But, believe that's the second opportunity described in the PR where you'd need a retry post compaction since you don't know tokens in advance.

@brandon93s commented on GitHub (Jan 16, 2026): @rchybicki 5.2 or 5.2 codex? I believe the input limit was only set for codex models. @rekram1-node I did hit it again today when a tool-call boiled over the limit when it tried to add a large git diff. But, believe that's the second opportunity described in the PR where you'd need a retry post compaction since you don't know tokens in advance.
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@rchybicki commented on GitHub (Jan 16, 2026):

@brandon93s this was 5.2 non-codex

@rchybicki commented on GitHub (Jan 16, 2026): @brandon93s this was 5.2 non-codex
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 16, 2026):

@brandon93s I think the input thing applies to all gpt-5 models

@rekram1-node commented on GitHub (Jan 16, 2026): @brandon93s I think the input thing applies to all gpt-5 models
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Jan 16, 2026):

Ill double check w/ their docs and update

@rekram1-node commented on GitHub (Jan 16, 2026): Ill double check w/ their docs and update
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@brandon93s commented on GitHub (Jan 16, 2026):

@rekram1-node confirmed here: https://github.com/openai/codex/blob/main/codex-rs/core/src/models_manager/model_info.rs#L250

@brandon93s commented on GitHub (Jan 16, 2026): @rekram1-node confirmed here: https://github.com/openai/codex/blob/main/codex-rs/core/src/models_manager/model_info.rs#L250
yindo commented 2026-02-16 17:45:00 -05:00
Author
Owner
Copy Link
Copy Source

@HyunggyuJang commented on GitHub (Feb 5, 2026):

Update from my side: I think my earlier interpretation was wrong.

I traced this to model metadata in pi-mono:
https://github.com/badlogic/pi-mono/blob/f9161c4d4e0d001ebfbd3ba98f0b89adb253260a/packages/ai/src/models.generated.ts#L5099

From that data, ChatGPT subscription-backed Codex models appear constrained (roughly 272k input / 128k output) regardless of selected variant. So the default-vs-variant limit difference I reported was likely a mistaken read.

Sorry about the confusion.

@HyunggyuJang commented on GitHub (Feb 5, 2026): Update from my side: I think my earlier interpretation was wrong. I traced this to model metadata in pi-mono: https://github.com/badlogic/pi-mono/blob/f9161c4d4e0d001ebfbd3ba98f0b89adb253260a/packages/ai/src/models.generated.ts#L5099 From that data, ChatGPT subscription-backed Codex models appear constrained (roughly 272k input / 128k output) regardless of selected variant. So the default-vs-variant limit difference I reported was likely a mistaken read. Sorry about the confusion.
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#4672
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?