"tool_calls" not returning on native http request on a llama cpp server

# Prerequisites

Please answer the following questions for yourself before submitting an issue.

- [x] I am running the latest code. Development is very rapid so there are no tagged versions as of now.
- [x] I carefully followed the [README.md](https://github.com/abetlen/llama-cpp-python/blob/main/README.md).
- [x] I [searched using keywords relevant to my issue](https://docs.github.com/en/issues/tracking-your-work-with-issues/filtering-and-searching-issues-and-pull-requests) to make sure that I am creating a new issue that is not already open (or closed).
- [x] I reviewed the [Discussions](https://github.com/abetlen/llama-cpp-python/discussions), and have a new bug or useful enhancement to share.

# Expected Behavior

Behavior similar to https://github.com/abetlen/llama-cpp-python/blob/main/examples/notebooks/Functions.ipynb

# Current Behavior

is returning without "tool_calls":

{'id': 'chatcmpl-a8d9c08c-6260-4537-aa3a-b80ca7716de9', 'object': 'chat.completion', 'created': 1733614667, 'model': 'gpt-3.5-turbo-1106', 'choices': [{'index': 0, 'message': {'content': '{"name": "get_current_weather", "parameters": {"location": "San Francisco, CA", "unit": "fahrenheit"}}; {"name": "get_current_weather", "parameters": {"location": "Tokyo, JP", "unit": "celsius"}}; {"name": "get_current_weather", "parameters": {"location": "Paris, FR", "unit": "fahrenheit"}}', 'role': 'assistant'}, 'logprobs': None, 'finish_reason': 'stop'}], 'usage': {'prompt_tokens': 239, 'completion_tokens': 83, 'total_tokens': 322}}
None

# Environment and Context

llama cpp server: python -m llama_cpp.server --n_gpu_layers -1 --n_ctx 8000 --model .\Meta-Llama-3.1-8B-Instruct-Q4_K_M.gguf

windows 11

```python
# Client code

import requests
import json

# Função exemplo
def get_current_weather(location, unit="fahrenheit"):
"""Get the current weather in a given location"""
if "tokyo" in location.lower():
return json.dumps({"location": "Tokyo", "temperature": "10", "unit": "celsius"})
elif "san francisco" in location.lower():
return json.dumps(
{"location": "San Francisco", "temperature": "72", "unit": "fahrenheit"}
)
elif "paris" in location.lower():
return json.dumps({"location": "Paris", "temperature": "22", "unit": "celsius"})
else:
return json.dumps({"location": location, "temperature": "unknown"})

def run_conversation():
# Mensagem inicial do usuário
messages = [
{
"role": "user",
"content": "What's the weather like in San Francisco, Tokyo, and Paris?",
}
]

# Definição das ferramentas (funções) disponíveis
tools = [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA",
},
"unit": {"type": "string", "enum": ["celsius", "fahrenheit"]},
},
"required": ["location"],
},
},
}
]

# Primeiro request para obter a resposta inicial do modelo
payload = {
"model": "gpt-3.5-turbo-1106",
"messages": messages,
"tools": tools,
"tool_choice": "auto"
}

response = requests.post("http://localhost:8000/v1/chat/completions", json=payload)
response_data = response.json()

print(response_data)

# Extrai a primeira resposta do modelo
response_message = response_data["choices"][0]["message"]
tool_calls = response_message.get("tool_calls", [])

if tool_calls:
# Funções disponíveis
available_functions = {
"get_current_weather": get_current_weather,
}

# Adiciona a mensagem de resposta do modelo ao histórico
messages.append(response_message)

# Executa cada chamada de ferramenta solicitada
for tool_call in tool_calls:
function_name = tool_call["function"]["name"]
function_args = json.loads(tool_call["function"]["arguments"])
function_to_call = available_functions[function_name]
function_response = function_to_call(
location=function_args.get("location"),
unit=function_args.get("unit"),
)

# Adiciona a resposta da função ao histórico
messages.append(
{
"tool_call_id": tool_call["id"],
"role": "tool",
"name": function_name,
"content": function_response,
}
)

# Faz uma nova requisição ao modelo, agora incluindo a resposta da ferramenta
second_payload = {
"model": "gpt-3.5-turbo-1106",
"messages": messages,
}

second_response = requests.post("http://localhost:8000/v1/chat/completions", json=second_payload)
return second_response.json()

print(run_conversation())
```