Keeps emitting <tool_call> json into the context
#23
by theliphant - opened
Ever since updating to merged 3.5/6 version randomly stops and emits json for tool_call
Using unsloth/Qwen3.6-27B-MTP-GGUF:Q5_K_XL in llama-server with q8 k/v cache.
<tool_call>
<function=bash>
<parameter=command>
find Library/PackageCache -name "UniversalResourceData.cs" 2>/dev/null
</parameter>
</function>
</tool_call>
Although this is in pi so I wonder if something broke there 🙃
Looks like it believed it was a thinking block
{
"type": "message",
"id": "ccbda428",
"parentId": "3318fa1e",
"timestamp": "2026-05-18T16:32:49.150Z",
"message": {
"role": "assistant",
"content": [
{
"type": "thinking",
"thinking": "<tool_call>\n<function=bash>\n<parameter=command>\nfind Library/PackageCache -name \"UniversalResourceData.cs\" 2>/dev/null\n</parameter>\n</function>\n</tool_call>",
"thinkingSignature": "reasoning_content"
}
],
"api": "openai-completions",
"provider": "llama-cpp-mac",
"model": "Qwen3.6-27B",
"usage": {
"input": 671,
"output": 43,
"cacheRead": 58402,
"cacheWrite": 0,
"totalTokens": 59116,
"cost": {
"input": 0,
"output": 0,
"cacheRead": 0,
"cacheWrite": 0,
"total": 0
}
},
"stopReason": "stop",
"timestamp": 1779121949860,
"responseId": "chatcmpl-xVLlDQ1nqLjtHoIgiuaBwOcwrNYRto06"
}
}
Hi @theliphant , if you want you give my just released template rebuild project a try.
https://huggingface.co/StableQuant/Qwen-Templates-Rebuild-Project/
If v1.0 doesnt fixes it for you please tell me. If it works tell me too :-)
It will then be added into the research pipeline
Regards