Ollama Cloud doesn't display context size #6657

Closed
opened 2026-02-16 18:04:52 -05:00 by yindo · 12 comments
Owner

Originally created by @spiffytech on GitHub (Jan 17, 2026).

Originally assigned to: @rekram1-node on GitHub.

Description

When I use models from Ollama Cloud, the sidebar always says 0 tokens, 0% used, no matter how much I've chatted.

Plugins

No response

OpenCode version

1.1.25

Steps to reproduce

No response

Screenshot and/or share link

No response

Operating System

Fedora Linux, Windows 11

Terminal

No response

Originally created by @spiffytech on GitHub (Jan 17, 2026). Originally assigned to: @rekram1-node on GitHub. ### Description When I use models from Ollama Cloud, the sidebar always says `0 tokens`, `0% used`, no matter how much I've chatted. ### Plugins _No response_ ### OpenCode version 1.1.25 ### Steps to reproduce _No response_ ### Screenshot and/or share link _No response_ ### Operating System Fedora Linux, Windows 11 ### Terminal _No response_
yindo added the bug label 2026-02-16 18:04:52 -05:00
yindo closed this issue 2026-02-16 18:04:52 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Jan 17, 2026):

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

  • #6582: Ollama Cloud Models - Reports that new Ollama Cloud models aren't showing up in OpenCode model selection
  • #5760: Context size in sidebar not updated after /compact - Reports sidebar context display being stale/not updated immediately
  • #5871: [BUG] Switching models does not update context infos immediately - Reports context info in top right not updating when switching models

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

@github-actions[bot] commented on GitHub (Jan 17, 2026): This issue might be a duplicate of existing issues. Please check: - #6582: Ollama Cloud Models - Reports that new Ollama Cloud models aren't showing up in OpenCode model selection - #5760: Context size in sidebar not updated after /compact - Reports sidebar context display being stale/not updated immediately - #5871: [BUG] Switching models does not update context infos immediately - Reports context info in top right not updating when switching models Feel free to ignore if none of these address your specific case.
Author
Owner

@henryclw commented on GitHub (Jan 18, 2026):

Same with local model. I remember seeing the context usage of my local model couple days ago. So this might be a newly introduced bug.

@henryclw commented on GitHub (Jan 18, 2026): Same with local model. I remember seeing the context usage of my local model couple days ago. So this might be a newly introduced bug.
Author
Owner

@iamhenry commented on GitHub (Feb 12, 2026):

im getting this as well as a paid ollama cloud user with my api key

As you can see in the screenshot, both of the session headers don't include the context usage.

Image
@iamhenry commented on GitHub (Feb 12, 2026): im getting this as well as a paid ollama cloud user with my api key As you can see in the screenshot, both of the session headers don't include the context usage. <img width="1953" height="563" alt="Image" src="https://github.com/user-attachments/assets/6428aacb-37fd-4dee-9893-fb3ff7c84c59" />
Author
Owner

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

Hm if there is no usage coming back I tend to think ollama cloud isnt sending usage back in a standard format

@rekram1-node commented on GitHub (Feb 12, 2026): Hm if there is no usage coming back I tend to think ollama cloud isnt sending usage back in a standard format
Author
Owner

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

lemme sign up for an account and see

@rekram1-node commented on GitHub (Feb 12, 2026): lemme sign up for an account and see
Author
Owner

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

data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null}]}
data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"! How"},"finish_reason":null}]}
data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" can I"},"finish_reason":null}]}
data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" help you"},"finish_reason":null}]}
data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" with your"},"finish_reason":null}]}
data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" software engineering"},"finish_reason":null}]}
data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" tasks today"},"finish_reason":null}]}
data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"?"},"finish_reason":null}]}
data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop"}]}
data: [DONE]

See, no usage info is returned from them.

@rekram1-node commented on GitHub (Feb 12, 2026): ``` data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"},"finish_reason":null}]} data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"! How"},"finish_reason":null}]} data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" can I"},"finish_reason":null}]} data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" help you"},"finish_reason":null}]} data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" with your"},"finish_reason":null}]} data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" software engineering"},"finish_reason":null}]} data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":" tasks today"},"finish_reason":null}]} data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":"?"},"finish_reason":null}]} data: {"id":"chatcmpl-648","object":"chat.completion.chunk","created":1770941407,"model":"glm-4.6","system_fingerprint":"fp_ollama","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":"stop"}]} data: [DONE] ``` See, no usage info is returned from them.
Author
Owner

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

Prolly need to send them a param to fix this, lookin

@rekram1-node commented on GitHub (Feb 12, 2026): Prolly need to send them a param to fix this, lookin
Author
Owner

@iamhenry commented on GitHub (Feb 12, 2026):

I'm not sure if it's a bug or what, but I used a sub agent to commit and then the usage appeared.
this is kimi from zen but i started with glm 5 from ollama cloud

Image Image
@iamhenry commented on GitHub (Feb 12, 2026): I'm not sure if it's a bug or what, but I used a sub agent to commit and then the usage appeared. this is kimi from zen but i started with glm 5 from ollama cloud <img width="1512" height="367" alt="Image" src="https://github.com/user-attachments/assets/26d11164-88b3-4ece-b64d-33823259282d" /> <img width="1509" height="274" alt="Image" src="https://github.com/user-attachments/assets/deef234a-ace4-4836-8b15-300fd2b5776b" />
Author
Owner

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

"stream_options": {
"include_usage": true
}

Hmm we already send this actually

@rekram1-node commented on GitHub (Feb 12, 2026): "stream_options": { "include_usage": true } Hmm we already send this actually
Author
Owner

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

Confirmed w ollama team, this was a bug on their end, should be fixed now

@rekram1-node commented on GitHub (Feb 12, 2026): Confirmed w ollama team, this was a bug on their end, should be fixed now
Author
Owner

@iamhenry commented on GitHub (Feb 12, 2026):

dude, that was quick. thx!

@iamhenry commented on GitHub (Feb 12, 2026): dude, that was quick. thx!
Author
Owner

@iamhenry commented on GitHub (Feb 12, 2026):

confirmed it works

Image
@iamhenry commented on GitHub (Feb 12, 2026): confirmed it works <img width="1004" height="674" alt="Image" src="https://github.com/user-attachments/assets/8275735f-8347-4667-ae3d-701461710814" />
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#6657