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

github copilot: 2x token (counts total=total+cached) compacts at 64k, instead of 128k #2198

New Issue
Open
opened 2026-02-16 17:34:38 -05:00 by yindo · 11 comments
yindo commented 2026-02-16 17:34:38 -05:00
Owner
Copy Link
Copy Source

Originally created by @hchaudhary1 on GitHub (Oct 20, 2025).

Originally assigned to: @rekram1-node on GitHub.

Description

  • The TUI shows 2X the actual tokens being used.
  • This ends up forcing opencode to compact much, much earlier than needed.
  • Taking a look at the console from the share link I can see that the JSON itself looks valid (1/2 TUI) and the correct number of tokens seems to be presented in the console.

OpenCode version

0.15.8

Steps to reproduce

  • To reproduce this you can use Grok 4 fast from OpenRouter or you can also use any model that's connected via GitHub Copilot (GPT-5-mini).
  • enter "hi" into prompt
  • e.g. https://opencode.ai/s/IVO2CNuh

Screenshot and/or share link

Image

Operating System

mac

Terminal

zsh

Originally created by @hchaudhary1 on GitHub (Oct 20, 2025). Originally assigned to: @rekram1-node on GitHub. ### Description - The TUI shows 2X the actual tokens being used. - This ends up forcing opencode to compact much, much earlier than needed. - Taking a look at the console from the share link I can see that the JSON itself looks valid (1/2 TUI) and the correct number of tokens seems to be presented in the console. ### OpenCode version 0.15.8 ### Steps to reproduce - To reproduce this you can use Grok 4 fast from OpenRouter or you can also use any model that's connected via GitHub Copilot (GPT-5-mini). - enter "hi" into prompt - e.g. https://opencode.ai/s/IVO2CNuh ### Screenshot and/or share link <img width="473" height="466" alt="Image" src="https://github.com/user-attachments/assets/b94e7c97-7199-41ec-9cba-7fadc864267d" /> ### Operating System mac ### Terminal zsh
yindo added the bug label 2026-02-16 17:34:38 -05:00
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@github-actions[bot] commented on GitHub (Oct 20, 2025):

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

  • #1937: Reports identical behavior where TUI shows 2X the actual tokens, causing premature auto /compact, while share link shows correct counts. Multiple users have reported this at ~50% rate across various providers and models.

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

@github-actions[bot] commented on GitHub (Oct 20, 2025): This issue might be a duplicate of existing issues. Please check: - #1937: Reports identical behavior where TUI shows 2X the actual tokens, causing premature auto /compact, while share link shows correct counts. Multiple users have reported this at ~50% rate across various providers and models. Feel free to ignore if none of these address your specific case.
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@hchaudhary1 commented on GitHub (Oct 20, 2025):

very annoying...any hack for this...? especially with copilot, effective context is 64k

  • wondering if I can somehow override and "fool" opencode to think max model input-context is 2x -- i.e. 256k

EDIT:
I guess, I can do something like this, to artificially double max context?

{
  "provider": {
    "openai": {
      "models": {
        "gpt-4o": {
          "limit": {
            "context": 131072,
            "output": 8192
          }
        }
      }
    }
  }
}
@hchaudhary1 commented on GitHub (Oct 20, 2025): very annoying...any hack for this...? especially with copilot, effective context is 64k - wondering if I can somehow override and "fool" opencode to think max model input-context is 2x -- i.e. 256k EDIT: I guess, I can do something like this, to artificially double max context? ```json { "provider": { "openai": { "models": { "gpt-4o": { "limit": { "context": 131072, "output": 8192 } } } } } } ```
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@hchaudhary1 commented on GitHub (Oct 20, 2025):

same issue on bunx opencode-ai@opentui
0.0.0-opentui-202510210139

@hchaudhary1 commented on GitHub (Oct 20, 2025): same issue on `bunx opencode-ai@opentui` 0.0.0-opentui-202510210139
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 21, 2025):

Hm will look into that

@rekram1-node commented on GitHub (Oct 21, 2025): Hm will look into that
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@simonxabris commented on GitHub (Oct 21, 2025):

I'm currently working on an opencode client and I had to look into how opencode reports token usage and for a while I thought I found the same issue, but then I realized that I forgot to add the cached tokens to calculate the actual number of tokens used. If you add cache tokens for this chat, it adds up to the same value in both the TUI and the JSON in the share link:

Input: 35844
Output: 404
Cache read: 35712

This is how the TUI calculates token usage

https://github.com/sst/opencode/blob/a99bd3aa2c0f7100d0bcbfa4a11d818b7c753661/packages/tui/internal/components/chat/messages.go#L897-L901

@simonxabris commented on GitHub (Oct 21, 2025): I'm currently working on an opencode client and I had to look into how opencode reports token usage and for a while I thought I found the same issue, but then I realized that I forgot to add the cached tokens to calculate the actual number of tokens used. If you add cache tokens for this chat, it adds up to the same value in both the TUI and the JSON in the share link: Input: 35844 Output: 404 Cache read: 35712 This is how the TUI calculates token usage https://github.com/sst/opencode/blob/a99bd3aa2c0f7100d0bcbfa4a11d818b7c753661/packages/tui/internal/components/chat/messages.go#L897-L901
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 21, 2025):

edit: maybe this is just a bug in the web view

@rekram1-node commented on GitHub (Oct 21, 2025): edit: maybe this is just a bug in the web view
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@hchaudhary1 commented on GitHub (Oct 21, 2025):

Webview token count (at the bottom of webview) is a completely different issue folks.

This issue is causing frequent compacts. The issue is with the TUI or backend

This is like a P0 issue... a basic feature is not working correctly.

@hchaudhary1 commented on GitHub (Oct 21, 2025): Webview token count (at the bottom of webview) is a completely different issue folks. This issue is causing frequent compacts. The issue is with the TUI or backend This is like a P0 issue... a basic feature is not working correctly.
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 21, 2025):

@hchaudhary1 the max context size is 128k for gpt-5-mini on github copilot, are you sure that isn't the cause?

I will look more into your session to verify

@rekram1-node commented on GitHub (Oct 21, 2025): @hchaudhary1 the max context size is 128k for gpt-5-mini on github copilot, are you sure that isn't the cause? I will look more into your session to verify
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@hchaudhary1 commented on GitHub (Oct 21, 2025):

Yes, but why do you compact at 64k?
When we hit 64k, OC thinks it's hitting 128k, and then compacts. I hope I'm explaining correctly 😀

@hchaudhary1 commented on GitHub (Oct 21, 2025): Yes, but why do you compact at 64k? When we hit 64k, OC thinks it's hitting 128k, and then compacts. I hope I'm explaining correctly 😀
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Oct 21, 2025):

It shouldn't compact at 64k, i guess I just wanted to verify that you understood the decreased context limit since most people that have said this with copilot normally are unaware of the substantially smaller context window than the real model has

But if it is actually compacting at 64k that's a big issue and we need to fix, ill look into it mroe

@rekram1-node commented on GitHub (Oct 21, 2025): It shouldn't compact at 64k, i guess I just wanted to verify that you understood the decreased context limit since most people that have said this with copilot normally are unaware of the substantially smaller context window than the real model has But if it is actually compacting at 64k that's a big issue and we need to fix, ill look into it mroe
yindo commented 2026-02-16 17:34:38 -05:00
Author
Owner
Copy Link
Copy Source

@hchaudhary1 commented on GitHub (Oct 21, 2025):

Bingo.

@hchaudhary1 commented on GitHub (Oct 21, 2025): Bingo.
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#2198
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?