[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
-14
View File
@@ -308,20 +308,6 @@ async def init_app_state(
) -> None:
vllm_config = engine_client.vllm_config
# Propagate enable_in_reasoning to the API-server process. The engine core
# runs in a separate process, so the contextvar that backs
# `get_current_vllm_config_or_none()` is None on this stack. Tool parsers
# call `get_enable_structured_outputs_in_reasoning()` during request
# handling and need to see the real flag, otherwise they silently fall
# back to False and mismatch the engine-side bitmask gating.
from vllm.tool_parsers.structural_tag_registry import (
set_enable_structured_outputs_in_reasoning,
)
set_enable_structured_outputs_in_reasoning(
vllm_config.structured_outputs_config.enable_in_reasoning
)
if args.tool_call_parser is not None:
from vllm.parser.metrics import init_parser_metrics