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

fix: Updating ToolCall.arguments to allow for json strings that can be decoded on client side (#1685)

Browse source 
### What does this PR do?

Currently, `ToolCall.arguments` is a `Dict[str, RecursiveType]`.
However, on the client SDK side -- the `RecursiveType` gets deserialized
into a number ( both int and float get collapsed ) and hence when params
are `int` they get converted to float which might break client side
tools that might be doing type checking.

Closes: https://github.com/meta-llama/llama-stack/issues/1683

### Test Plan
Stainless changes --
https://github.com/meta-llama/llama-stack-client-python/pull/204
```
pytest -s -v --stack-config=fireworks tests/integration/agents/test_agents.py  --text-model meta-llama/Llama-3.1-8B-Instruct
```
This commit is contained in:
Hardik Shah 2025-03-19 10:36:19 -07:00 • committed by GitHub
parent 113f3a259c
commit 65ca85ba6b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 137 additions and 110 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -90,15 +90,12 @@ def _convert_to_vllm_tool_calls_in_response(
if not tool_calls:
return []
call_function_arguments = None
for call in tool_calls:
call_function_arguments = json.loads(call.function.arguments)
return [
ToolCall(
call_id=call.id,
tool_name=call.function.name,
arguments=call_function_arguments,
arguments=json.loads(call.function.arguments),
arguments_json=call.function.arguments,
)
for call in tool_calls
]
@ -183,6 +180,7 @@ async def _process_vllm_chat_completion_stream_response(
call_id=tool_call_buf.call_id,
tool_name=tool_call_buf.tool_name,
arguments=args,
arguments_json=args_str,
),
parse_status=ToolCallParseStatus.succeeded,
),