Qwen 3.5 and Gemma 4 can't call tools

[MidKnightXI]

Before submitting your bug report

• I've tried using the "Ask AI" feature on the Continue docs site to see if the docs have an answer
• I'm not able to find a related conversation on GitHub discussions that reports the same bug
• I'm not able to find an open issue that reports the same bug
• I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

- OS: macOS
- Continue version: 1.2.22
- IDE version: 1.115.0
- Model: Qwen 3.5 9B, Gemma 4 26B-A4B
- config:
  
name: Local Config
version: 1.0.0
schema: v1
models:
  - name: Autodetect (1)
    provider: lmstudio
    model: AUTODETECT
    apiBase: http://SERVER_IP:1234/v1

Description

When using the model I loaded on my server from LM Studio on my macbook and VS Code, they are trying to run a tool like that:

Now I need to find the user.js file. Let me search for it.

<tool_call> <function=file_glob_search> <parameter=pattern> **/user.js </tool_call>

But the tool_call is not being registered by Continue and ends up in the thinking part instead which acts up like a message ending.

same for:

read_file failed with the message: File "src/test.vue" does not exist or is not accessible. You might want to check the path and try again.

Please try something else or request further instructions.

that end up in the thinking part with:

<tool_call> <function=edit_existing_file> <parameter=filepath> src/components/Navbar.vue <parameter=changes>
... changes

To reproduce

Load any of these models with reasoning and try using them to modify files with it.

Log output

I can only share the following:

Type: Chat
Result: Success
Prompt Tokens: 5095
Generated Tokens: 0
ThinkingTokens: 4528
Total Time: 61.03s
To First Token: 0.53s
Tokens/s: 74.8

[MidKnightXI]

I saw an issue a bit similar to this one with ollama and GPT OSS 20B that was left unanswered but I'm not sure if that's the same issue or not.

Also when trying with Qwen 3.5 35B A3B, it seems to be able to use the tools but always fail to provide the parameters for it.

edit_existing_file failed with the message: `filepath` and `changes` arguments are required to edit an existing file.

Please try something else or request further instructions.

[mna-alf]

I have a similar issue. From what I can see, Continue only reads/outputs the thinking part of the response and not the actual response itself.

[weikis336]

The same with gemma models too

[alexdlhh]

Actually, I think the problem is that there isn't a “skill” for those models, unlike the ones available for GPT, Claude, Gemini, Grok, etc. It's as if they don't know what tools are out there.

[scottsweb]

I have been able to get tools to work with Qwen 3.5, using the following config:

  - name: Qwen3.5 4B
    provider: ollama
    model: qwen3.5:4b
    apiBase: https://ollama.local.lan
    roles:
      - chat
      - edit
      - apply
      - autocomplete
    capabilities:
      - tool_use

And enabling this experimental setting:

Less successful with Gemma4.