Tool Call Parsing (Dynamo)

You can connect Dynamo to external tools and services using tool calling. By providing a list of available functions, Dynamo can choose to output function arguments for the relevant function(s) which you can execute to augment the prompt with relevant external information.

Tool calling is controlled using the tool_choice and tools request parameters.

This page covers parser names for the default Dynamo-native path. If Dynamo does not list a parser for your model, see Tool Call Parsing (Engine Fallback).

Prerequisites

To enable this feature, you should set the following flag while launching the backend worker

• --dyn-tool-call-parser: select the tool call parser from the supported list below

$
# <backend> can be sglang, trtllm, vllm, etc. based on your installation
$
python -m dynamo.<backend> --help

Supported Tool Call Parsers

The table below lists the currently supported tool call parsers in Dynamo’s registry. The Upstream name column shows where the vLLM or SGLang parser name differs from Dynamo’s — relevant when using --dyn-chat-processor vllm or sglang (see Tool Call Parsing (Engine Fallback)). A blank upstream column means the same name works everywhere. Dynamo-only means no upstream parser exists for this format.

Examples

Launch Dynamo Frontend and Backend

$
# launch backend worker (or dynamo.vllm)
$
python -m dynamo.sglang --model Qwen/Qwen3.5-4B --dyn-tool-call-parser qwen3_coder --dyn-reasoning-parser qwen3
$
$
# launch frontend worker
$
python -m dynamo.frontend

Tool Calling Request Example

$
curl -s http://localhost:8000/v1/chat/completions \
>
  -H 'Content-Type: application/json' \
>
  -d '{
>
    "model": "Qwen/Qwen3.5-4B",
>
    "messages": [
>
      {"role": "user", "content": "What is the weather in San Francisco and New York?"}
>
    ],
>
    "tools": [{
>
      "type": "function",
>
      "function": {
>
        "name": "get_weather",
>
        "description": "Get the current weather for a location.",
>
        "parameters": {
>
          "type": "object",
>
          "properties": {"location": {"type": "string"}},
>
          "required": ["location"]
>
        }
>
      }
>
    }],
>
    "tool_choice": "auto"
>
  }'

Dynamo parses the tool calls out of the model output and surfaces them as OpenAI-compatible tool_calls entries on the response:

1
{
2
  "id": "chatcmpl-b415caad-9be0-4d9e-ac6d-9d23bfe57703",
3
  "choices": [
4
    {
5
      "index": 0,
6
      "message": {
7
        "role": "assistant",
8
        "content": null,
9
        "reasoning_content": "The user is asking about the weather in two cities: San Francisco and New York. I need to call the get_weather function for each city. I'll make two separate function calls to get the weather information for both locations.\n",
10
        "tool_calls": [
11
          {
12
            "id": "call-56223a95-3d14-4433-a94e-011f106c0e40",
13
            "type": "function",
14
            "function": {
15
              "name": "get_weather",
16
              "arguments": "{\"location\":\"San Francisco\"}"
17
            }
18
          },
19
          {
20
            "id": "call-d5b5772b-6b0c-4120-ad01-623278a937fe",
21
            "type": "function",
22
            "function": {
23
              "name": "get_weather",
24
              "arguments": "{\"location\":\"New York\"}"
25
            }
26
          }
27
        ]
28
      },
29
      "finish_reason": "tool_calls",
30
      "logprobs": null
31
    }
32
  ],
33
  "created": 1778653281,
34
  "model": "Qwen/Qwen3.5-4B",
35
  ...
36
}