github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-22 05:31:43 -05:00
Code Issues 16.9k Packages Projects Releases 122 Wiki Activity

[GH-ISSUE #14745] qwen3.5:9b sometimes prints out tool call instead of executing it #87222

New Issue
Closed
opened 2026-05-10 05:08:08 -05:00 by GiteaMirror · 13 comments
GiteaMirror commented 2026-05-10 05:08:08 -05:00
Owner
Copy Link

Originally created by @Kangaroux on GitHub (Mar 9, 2026).
Original GitHub issue: https://github.com/ollama/ollama/issues/14745

Originally assigned to: @jmorganca on GitHub.

workaround: use ollama 0.17.5

What is the issue?

Using the model from ollama.com and Opencode 1.2.24. This happens fairly often and halts the work the agent was doing.

Thinking: I need to mock Valkey for tests. Let me check how the app initializes Valkey and update TESTING.md with this information.
<tool_call>
<function=bash>
<parameter=command>
grep "redacted" | head -20
</parameter>
<parameter=description>
Find Valkey initialization
</parameter>
</function>
</tool_call>

$ ollama ls
NAME          ID              SIZE      MODIFIED     
qwen3.5:9b    6488c96fa5fa    6.6 GB    25 hours ago

$ ollama show qwen3.5:9b
  Model
    architecture        qwen35    
    parameters          9.7B      
    context length      262144    
    embedding length    4096      
    quantization        Q4_K_M    
    requires            0.17.1    

  Capabilities
    completion    
    vision        
    tools         
    thinking      

  Parameters
    presence_penalty    1.5     
    temperature         1       
    top_k               20      
    top_p               0.95    

  License
    Apache License               
    Version 2.0, January 2004    
    ...

$ ollama show --modelfile qwen3.5:9b
# Modelfile generated by "ollama show"
# To build a new Modelfile based on this, replace FROM with:
# FROM qwen3.5:9b

FROM /usr/share/ollama/.ollama/models/blobs/sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c
TEMPLATE {{ .Prompt }}
RENDERER qwen3.5
PARSER qwen3.5
PARAMETER temperature 1
PARAMETER top_k 20
PARAMETER top_p 0.95
PARAMETER presence_penalty 1.5

Relevant log output

OS

Linux

GPU

AMD

CPU

AMD

Ollama version

0.17.7

Originally created by @Kangaroux on GitHub (Mar 9, 2026). Original GitHub issue: https://github.com/ollama/ollama/issues/14745 Originally assigned to: @jmorganca on GitHub. ## workaround: use ollama 0.17.5 ### What is the issue? Using the model from ollama.com and Opencode 1.2.24. This happens fairly often and halts the work the agent was doing. ``` Thinking: I need to mock Valkey for tests. Let me check how the app initializes Valkey and update TESTING.md with this information. <tool_call> <function=bash> <parameter=command> grep "redacted" | head -20 </parameter> <parameter=description> Find Valkey initialization </parameter> </function> </tool_call> ``` ``` $ ollama ls NAME ID SIZE MODIFIED qwen3.5:9b 6488c96fa5fa 6.6 GB 25 hours ago ``` ``` $ ollama show qwen3.5:9b Model architecture qwen35 parameters 9.7B context length 262144 embedding length 4096 quantization Q4_K_M requires 0.17.1 Capabilities completion vision tools thinking Parameters presence_penalty 1.5 temperature 1 top_k 20 top_p 0.95 License Apache License Version 2.0, January 2004 ... ``` ``` $ ollama show --modelfile qwen3.5:9b # Modelfile generated by "ollama show" # To build a new Modelfile based on this, replace FROM with: # FROM qwen3.5:9b FROM /usr/share/ollama/.ollama/models/blobs/sha256-dec52a44569a2a25341c4e4d3fee25846eed4f6f0b936278e3a3c900bb99d37c TEMPLATE {{ .Prompt }} RENDERER qwen3.5 PARSER qwen3.5 PARAMETER temperature 1 PARAMETER top_k 20 PARAMETER top_p 0.95 PARAMETER presence_penalty 1.5 ``` ### Relevant log output ```shell ``` ### OS Linux ### GPU AMD ### CPU AMD ### Ollama version 0.17.7
GiteaMirror added the bug label 2026-05-10 05:08:08 -05:00
GiteaMirror commented 2026-05-10 05:08:12 -05:00
Author
Owner
Copy Link

@Kangaroux commented on GitHub (Mar 9, 2026):

Possibly related?

<!-- gh-comment-id:4026249854 --> @Kangaroux commented on GitHub (Mar 9, 2026): Possibly related? - https://github.com/ollama/ollama/issues/14493 - https://github.com/ollama/ollama/issues/14601 - https://github.com/ollama/ollama/pull/14603
GiteaMirror commented 2026-05-10 05:08:12 -05:00
Author
Owner
Copy Link

@nandakho commented on GitHub (Mar 10, 2026):

yeah, i experienced this issue too, while running opencode with ollama 0.17.6 and 0.17.7.
seems related with how thinking tag open/close.
however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update

<!-- gh-comment-id:4027863732 --> @nandakho commented on GitHub (Mar 10, 2026): yeah, i experienced this issue too, while running opencode with ollama 0.17.6 and 0.17.7. seems related with how thinking tag open/close. however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update
GiteaMirror commented 2026-05-10 05:08:13 -05:00
Author
Owner
Copy Link

@TheSpaceGod commented on GitHub (Mar 10, 2026):

Having same issue as well. Can confirm switching to 17.5 also fixed the issue for me

<!-- gh-comment-id:4031213150 --> @TheSpaceGod commented on GitHub (Mar 10, 2026): Having same issue as well. Can confirm switching to 17.5 also fixed the issue for me
GiteaMirror commented 2026-05-10 05:08:14 -05:00
Author
Owner
Copy Link

@Kangaroux commented on GitHub (Mar 10, 2026):

yeah, i experienced this issue too with opencode on 0.17.6 and 0.17.7. seems related with how thinking tag open/close. however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update

You meant ollama yeah?

<!-- gh-comment-id:4032009091 --> @Kangaroux commented on GitHub (Mar 10, 2026): > yeah, i experienced this issue too with opencode on 0.17.6 and 0.17.7. seems related with how thinking tag open/close. however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update You meant ollama yeah?
GiteaMirror commented 2026-05-10 05:08:14 -05:00
Author
Owner
Copy Link

@TheSpaceGod commented on GitHub (Mar 10, 2026):

yeah, i experienced this issue too with opencode on 0.17.6 and 0.17.7. seems related with how thinking tag open/close. however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update

You meant ollama yeah?

Yes, ollama

<!-- gh-comment-id:4032051248 --> @TheSpaceGod commented on GitHub (Mar 10, 2026): > > yeah, i experienced this issue too with opencode on 0.17.6 and 0.17.7. seems related with how thinking tag open/close. however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update > > You meant ollama yeah? Yes, ollama
GiteaMirror commented 2026-05-10 05:08:15 -05:00
Author
Owner
Copy Link

@nandakho commented on GitHub (Mar 11, 2026):

yeah, i experienced this issue too with opencode on 0.17.6 and 0.17.7. seems related with how thinking tag open/close. however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update

You meant ollama yeah?

Yes, ollama. Edited to avoid confusion.

<!-- gh-comment-id:4036037367 --> @nandakho commented on GitHub (Mar 11, 2026): > > yeah, i experienced this issue too with opencode on 0.17.6 and 0.17.7. seems related with how thinking tag open/close. however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update > > You meant ollama yeah? Yes, ollama. Edited to avoid confusion.
GiteaMirror commented 2026-05-10 05:08:16 -05:00
Author
Owner
Copy Link

@aldi7th commented on GitHub (Mar 13, 2026):

Downgrade to 0.17.5 works for me, and I tried 0.17.8-rc3, still encountered this issue.

<!-- gh-comment-id:4052553576 --> @aldi7th commented on GitHub (Mar 13, 2026): Downgrade to 0.17.5 works for me, and I tried 0.17.8-rc3, still encountered this issue.
GiteaMirror commented 2026-05-10 05:08:16 -05:00
Author
Owner
Copy Link

@metal3d commented on GitHub (Mar 13, 2026):

I don't know what changed in 0.17.6 but I have the problem too and I needed to downgrade to 0.17.5 to have the model using tools correctly.

<!-- gh-comment-id:4053517643 --> @metal3d commented on GitHub (Mar 13, 2026): I don't know what changed in 0.17.6 but I have the problem too and I needed to downgrade to 0.17.5 to have the model using tools correctly.
GiteaMirror commented 2026-05-10 05:08:17 -05:00
Author
Owner
Copy Link

@mnlipp commented on GitHub (Mar 16, 2026):

The problem still exists with 0.18.

<!-- gh-comment-id:4069057854 --> @mnlipp commented on GitHub (Mar 16, 2026): The problem still exists with 0.18.
GiteaMirror commented 2026-05-10 05:08:17 -05:00
Author
Owner
Copy Link

@TheSpaceGod commented on GitHub (Mar 17, 2026):

Related PR that likely introduced the bug which other tickets are linking to: https://github.com/ollama/ollama/pull/14605

<!-- gh-comment-id:4076778583 --> @TheSpaceGod commented on GitHub (Mar 17, 2026): Related PR that likely introduced the bug which other tickets are linking to: https://github.com/ollama/ollama/pull/14605
GiteaMirror commented 2026-05-10 05:08:18 -05:00
Author
Owner
Copy Link

@LR1093141031 commented on GitHub (Mar 19, 2026):

0.18.2 still

<!-- gh-comment-id:4088383360 --> @LR1093141031 commented on GitHub (Mar 19, 2026): 0.18.2 still
GiteaMirror commented 2026-05-10 05:08:18 -05:00
Author
Owner
Copy Link

@krvkir commented on GitHub (Mar 19, 2026):

I get an error which looks similar but is probably of different origin. I try to use ollama in jupyter via jupyter-ai. Tools work fine with gemini3.1 hosted by Google, but when I use gemini3 over ollama (running in the cloud), I get this:

{"name": "get_active_notebook", "arguments": {"username": "<my user id>"}}

and the model halts after this message.

The same happens with ollama with other large models in the cloud and with small models running locally.

Ollama version is 0.18. I tried downgrading it to 0.17.5, but the problem was still there.

Interesting is that the same models happily use tools in emacs+gptel, so that's possibly a jupyter-ai bug.

<!-- gh-comment-id:4091896682 --> @krvkir commented on GitHub (Mar 19, 2026): I get an error which looks similar but is probably of different origin. I try to use ollama in jupyter via jupyter-ai. Tools work fine with gemini3.1 hosted by Google, but when I use gemini3 over ollama (running in the cloud), I get this: ``` {"name": "get_active_notebook", "arguments": {"username": "<my user id>"}} ``` and the model halts after this message. The same happens with ollama with other large models in the cloud and with small models running locally. Ollama version is 0.18. I tried downgrading it to 0.17.5, but the problem was still there. Interesting is that the same models happily use tools in emacs+gptel, so that's possibly a jupyter-ai bug.
GiteaMirror commented 2026-05-10 05:08:19 -05:00
Author
Owner
Copy Link

@fmacpro commented on GitHub (Apr 20, 2026):

yeah, i experienced this issue too, while running opencode with ollama 0.17.6 and 0.17.7. seems related with how thinking tag open/close. however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update

Thankyou! this helped me get qwen2.5-coder:latest tool calls working in vscode copilot chat with Ollama running in the WSL environment

<!-- gh-comment-id:4284150344 --> @fmacpro commented on GitHub (Apr 20, 2026): > yeah, i experienced this issue too, while running opencode with ollama 0.17.6 and 0.17.7. seems related with how thinking tag open/close. however, using 0.17.5 i haven't encountered this issue, so i'm sticking with it until further update Thankyou! this helped me get `qwen2.5-coder:latest` tool calls working in vscode copilot chat with Ollama running in the WSL environment
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#87222
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?