phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

fix: multiple tool calls in remote-vllm chat_completion (#2161)

Browse source 
# What does this PR do?

This fixes an issue in how we used the tool_call_buf from streaming tool
calls in the remote-vllm provider where it would end up concatenating
parameters from multiple different tool call results instead of
aggregating the results from each tool call separately.

It also fixes an issue found while digging into that where we were
accidentally mixing the json string form of tool call parameters with
the string representation of the python form, which mean we'd end up
with single quotes in what should be double-quoted json strings.

Closes #1120

## Test Plan

The following tests are now passing 100% for the remote-vllm provider,
where some of the test_text_inference were failing before this change:

```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" LLAMA_STACK_CONFIG=remote-vllm python -m pytest -v tests/integration/inference/test_text_inference.py --text-model "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic"

VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" LLAMA_STACK_CONFIG=remote-vllm python -m pytest -v tests/integration/inference/test_vision_inference.py --vision-model "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic"

```

All but one of the agent tests are passing (including the multi-tool
one). See the PR at https://github.com/vllm-project/vllm/pull/17917 and
a gist at
https://gist.github.com/bbrowning/4734240ce96b4264340caa9584e47c9e for
changes needed there, which will have to get made upstream in vLLM.

Agent tests:

```
VLLM_URL="http://localhost:8000/v1" INFERENCE_MODEL="RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic" LLAMA_STACK_CONFIG=remote-vllm python -m pytest -v tests/integration/agents/test_agents.py --text-model "RedHatAI/Llama-4-Scout-17B-16E-Instruct-FP8-dynamic"
````

---------

Signed-off-by: Ben Browning <bbrownin@redhat.com>
This commit is contained in:
Ben Browning 2025-05-15 14:23:29 -04:00 • committed by GitHub
parent bb5fca9521
commit 10b1056dea
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 225 additions and 34 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -531,13 +531,19 @@ async def convert_message_to_openai_dict(message: Message, download: bool = Fals
tool_name = tc.tool_name
if isinstance(tool_name, BuiltinTool):
tool_name = tool_name.value
# arguments_json can be None, so attempt it first and fall back to arguments
if hasattr(tc, "arguments_json") and tc.arguments_json:
arguments = tc.arguments_json
else:
arguments = json.dumps(tc.arguments)
result["tool_calls"].append(
{
"id": tc.call_id,
"type": "function",
"function": {
"name": tool_name,
"arguments": tc.arguments_json if hasattr(tc, "arguments_json") else json.dumps(tc.arguments),
"arguments": arguments,
},
}
)