Name and Version

version: 4369 (21ae3b9)
built with Apple clang version 15.0.0 (clang-1500.3.9.4) for arm64-apple-darwin23.6.0

Operating systems

Mac

Which llama.cpp modules do you know to be affected?

llama-server

Problem description & steps to reproduce

llama-server throws:

{"code":500,"message":"Unsupported param: tools","type":"server_error"}

if the request has "tools" parameter.

To reproduce:

1. Start llama-server e.g.

./llama-server \
-m andyywl_Qwen2.5-1.5B-Instruct.Q6_K.gguf_Qwen2.5-1.5B-Instruct.Q6_K.gguf
--port 8080

2. Make a request to the server e.g.

curl http://localhost:8080/v1/chat/completions
-H "Content-Type: application/json"
-H "Authorization: Bearer NOT_APPLICABLE_FOR_LOCAL_MODELS"
-X POST
-d '{
"messages": [
{
"content": "You are a helpful AI assistant. Solve tasks using your tools. Reply with TERMINATE when the task has been completed.",
"role": "system"
},
{
"content": "What is the weather in New York?",
"role": "user",
"name": "user"
}
],
"model": null,
"stream": false,
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "",
"parameters": {
"type": "object",
"properties": {
"city": {
"description": "city",
"title": "City",
"type": "string"
}
},
"required": [
"city"
]
}
}
}
]
}'

First Bad Commit

No response

Relevant log output

srv          init: initializing slots, n_slots = 1
slot         init: id  0 | task -1 | new slot n_ctx_slot = 4096
main: model loaded
main: chat template, built_in: 1, chat_example: '<|im_start|>system
You are a helpful assistant<|im_end|>
<|im_start|>user
Hello<|im_end|>
<|im_start|>assistant
Hi there<|im_end|>
<|im_start|>user
How are you?<|im_end|>
<|im_start|>assistant
'
main: server is listening on http://127.0.0.1:8080 - starting the main loop
srv  update_slots: all slots are idle
got exception: {"code":500,"message":"Unsupported param: tools","type":"server_error"}
request: POST /v1/chat/completions 127.0.0.1 500