mirror/LocalAI
1
0
Fork 0
mirror of https://github.com/mudler/LocalAI.git synced 2026-06-12 02:38:19 -04:00
Code Issues Packages Projects Releases Wiki Activity

fix(vllm): parse tool_call function arguments before applying the chat template (#10256)

Browse Source 
Signed-off-by: pos-ei-don <1822533+pos-ei-don@users.noreply.github.com>
This commit is contained in:
pos-ei-don
2026-06-11 23:55:38 +02:00
committed by GitHub
parent b6fcb3e1db
commit b962f4a192
1 changed files with 16 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

17
backend/python/vllm/backend.py
View File

@@ -150,9 +150,24 @@ class BackendServicer(backend_pb2_grpc.BackendServicer):
d["reasoning_content"] = msg.reasoning_content
if msg.tool_calls:
try:
d["tool_calls"] = json.loads(msg.tool_calls)
tool_calls = json.loads(msg.tool_calls)
except json.JSONDecodeError:
pass
else:
# OpenAI wire format carries function.arguments as a
# JSON-encoded string, but chat templates (e.g. Qwen3)
# iterate over it as a mapping. vLLM's own OpenAI server
# parses arguments before applying the template, so do
# the same here.
if isinstance(tool_calls, list):
for tc in tool_calls:
func = tc.get("function") if isinstance(tc, dict) else None
if isinstance(func, dict) and isinstance(func.get("arguments"), str):
try:
func["arguments"] = json.loads(func["arguments"])
except json.JSONDecodeError:
pass
d["tool_calls"] = tool_calls
result.append(d)
return result