[Frontend] Support strict mode for tool calling (#45003)

Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: cjackal <44624812+cjackal@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
Chauncey
2026-06-12 07:51:48 +00:00
committed by GitHub
co-authored by cjackal mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent bd59c913bc
commit 2043258dec
29 changed files with 692 additions and 1956 deletions
+36
View File
@@ -25,6 +25,7 @@ from vllm.entrypoints.openai.responses.protocol import ResponsesRequest
from vllm.logger import init_logger
from vllm.parser.metrics import record_tool_parser_invocation
from vllm.reasoning.abs_reasoning_parsers import ReasoningParser
from vllm.sampling_params import StructuredOutputsParams
from vllm.tokenizers import TokenizerLike
from vllm.tool_parsers.abstract_tool_parser import Tool, ToolParser
from vllm.tool_parsers.streaming import (
@@ -427,10 +428,45 @@ class DelegatingParser(Parser):
) -> ChatCompletionRequest | ResponsesRequest:
if self._reasoning_parser is not None:
request = self._reasoning_parser.adjust_request(request)
if self._tool_parser is not None:
request = self._apply_structural_tag(request)
if self._tool_parser is not None:
request = self._tool_parser.adjust_request(request)
return request
def _apply_structural_tag(
self, request: ChatCompletionRequest | ResponsesRequest
) -> ChatCompletionRequest | ResponsesRequest:
if (
not isinstance(request, ChatCompletionRequest)
or self._tool_parser is None
or self._tool_parser.structural_tag_model is None
or not request.tools
):
return request
need_tool_calling = (
request.tool_choice == "auto"
or request.tool_choice == "required"
or isinstance(request.tool_choice, ChatCompletionNamedToolChoiceParam)
)
if not need_tool_calling:
return request
structure_tag = self._tool_parser.get_structural_tag(
request,
reasoning=False,
)
if structure_tag is None:
return request
structural_tag = json.dumps(structure_tag.model_dump())
request.structured_outputs = StructuredOutputsParams(
structural_tag=structural_tag,
)
request.response_format = None
return request
def extract_reasoning_streaming(
self,
previous_text: str,