style(router): drop redundant discovery-skip comment (#42657)

The comment only restated the guard immediately below it and violated
the repository comment policy (AGENTS.md); the helper docstring already
explains why discovery is skipped when both token limits are configured.

No behavior change.
This commit is contained in:
RichardoMrMu 2026-09-29 17:11:53 +08:00
parent ce9d1cc8bf
commit 92f6df45db

View file

@ -10252,11 +10252,6 @@ class Router:
return
if api_base is None or "*" in model or params.get("use_clientside_credentials"):
return
# Skip the /v1/models discovery call when the deployment already
# declares its token limits: discovery can only confirm values that
# are already configured, so the request is pure cost. On scale-to-zero
# backends (e.g. RunPod Serverless vLLM) each such call cold-starts a
# GPU worker and bills real money with no chat traffic (issue #42657).
if self._deployment_token_limits_configured(raw_deployment.get("model_info")):
return
api_key: Final = params.api_key or dynamic_api_key