github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-08 17:49:24 -05:00
Code Issues 14.6k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #15290] I'm having an issue when using the Ollama cloud model, especially when generating large outputs. #71843

New Issue
Open
opened 2026-05-05 02:41:20 -05:00 by GiteaMirror · 4 comments
GiteaMirror commented 2026-05-05 02:41:20 -05:00
Owner
Copy Link

Originally created by @Hevoon on GitHub (Apr 3, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/15290

What is the issue?

I’d like to subscribe to Ollama Pro, but when I use the free Ollama cloud models, I encounter an error when the function call outputs a large amount of content:

{"error":"Post v1/chat/completions?ts=1775218167": unexpected EOF"}

When using streaming, I get an error where chunk.finishReason = other.

If I directly use /llama.com/v1 with the ckimi-k2.5:cloud model (or any cloud model), normal conversations work fine. However, when using function calls to generate a slightly larger HTML page (such as a homepage), the process gets interrupted and throws an error:

SocketError: other side closed, code UND_ERR_SOCKET.

Will upgrading to Pro resolve this issue? Or is my usage approach incorrect? Could someone experienced help clarify this?

Relevant log output

OS

No response

GPU

No response

CPU

No response

Ollama version

No response

Originally created by @Hevoon on GitHub (Apr 3, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/15290 ### What is the issue? I’d like to subscribe to Ollama Pro, but when I use the free Ollama cloud models, I encounter an error when the function call outputs a large amount of content: {"error":"Post v1/chat/completions?ts=1775218167": unexpected EOF"} When using streaming, I get an error where chunk.finishReason = other. If I directly use /llama.com/v1 with the ckimi-k2.5:cloud model (or any cloud model), normal conversations work fine. However, when using function calls to generate a slightly larger HTML page (such as a homepage), the process gets interrupted and throws an error: SocketError: other side closed, code UND_ERR_SOCKET. Will upgrading to Pro resolve this issue? Or is my usage approach incorrect? Could someone experienced help clarify this? ### Relevant log output ```shell ``` ### OS _No response_ ### GPU _No response_ ### CPU _No response_ ### Ollama version _No response_
GiteaMirror added the bug label 2026-05-05 02:41:20 -05:00
GiteaMirror commented 2026-05-05 02:41:22 -05:00
Author
Owner
Copy Link

@imaboku commented on GitHub (Apr 8, 2026):

I recently started using Pro to blend cloud models with my local models and it has been working great with kimi-k2.5:cloud except the last couple of days I have started to see this same issue. I tried glm-5.1:cloud this evening and had the same issues. Im running claude code with some fairly complex coding tasks. Earlier this week it was working fine and just started give more of these errors today:
level=WARN source=cloud_proxy.go:257 msg="cloud proxy response copy failed" path=/v1/messages upstream_path=/v1/messages status=200 request_context_canceled=false request_context_err=<nil> error="unexpected EOF"

<!-- gh-comment-id:4203911722 --> @imaboku commented on GitHub (Apr 8, 2026): I recently started using Pro to blend cloud models with my local models and it has been working great with kimi-k2.5:cloud except the last couple of days I have started to see this same issue. I tried glm-5.1:cloud this evening and had the same issues. Im running claude code with some fairly complex coding tasks. Earlier this week it was working fine and just started give more of these errors today: `level=WARN source=cloud_proxy.go:257 msg="cloud proxy response copy failed" path=/v1/messages upstream_path=/v1/messages status=200 request_context_canceled=false request_context_err=<nil> error="unexpected EOF"`
GiteaMirror commented 2026-05-05 02:41:23 -05:00
Author
Owner
Copy Link

@Hevoon commented on GitHub (Apr 8, 2026):

did you activate Ollama Pro? I'm wondering if it's because I'm using the free version.

<!-- gh-comment-id:4205765972 --> @Hevoon commented on GitHub (Apr 8, 2026): did you activate Ollama Pro? I'm wondering if it's because I'm using the free version.
GiteaMirror commented 2026-05-05 02:41:23 -05:00
Author
Owner
Copy Link

@imaboku commented on GitHub (Apr 9, 2026):

Yes, using Pro access, same issue.

<!-- gh-comment-id:4210600254 --> @imaboku commented on GitHub (Apr 9, 2026): Yes, using Pro access, same issue.
GiteaMirror commented 2026-05-05 02:41:24 -05:00
Author
Owner
Copy Link

@PureBlissAK commented on GitHub (Apr 18, 2026):

🤖 Automated Triage & Analysis Report

Issue: #15290
Analyzed: 2026-04-18T18:22:41.417788

Analysis

  • Type: unknown
  • Severity: medium
  • Components: unknown

Implementation Plan

  • Effort: medium
  • Steps:

This issue has been triaged and marked for implementation.

<!-- gh-comment-id:4274310446 --> @PureBlissAK commented on GitHub (Apr 18, 2026): <!-- ollama-issue-orchestrator:v1 issue:15290 --> ## 🤖 Automated Triage & Analysis Report **Issue**: #15290 **Analyzed**: 2026-04-18T18:22:41.417788 ### Analysis - **Type**: unknown - **Severity**: medium - **Components**: unknown ### Implementation Plan - **Effort**: medium - **Steps**: *This issue has been triaged and marked for implementation.*
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#71843
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?