When I deployed the qwen model using VLLM, I encountered an error that the model was not found

What version of Codex CLI is running?

codex-cli 0.105.0

What subscription do you have?

No subscription

Which model were you using?

qwen3-vl-235

What platform is your computer?

Darwin 24.6.0 arm64 arm

What terminal emulator and version are you using (if applicable)?

iTerm2

What issue are you seeing?

When I deployed the qwen model using VLLM, I encountered an error that the model was not found

# 供应商设置
[model_providers.qwen]
name = "qwen"
base_url = "http://mycompany.com/v1"
env_key = "CodeX_API_KEY"
wire_api = "responses"
query_params = {}

[profiles.qwen]
model_provider = "qwen"
model = "qwen3-vl-235"

⚠ Model metadata for qwen3-vl-235 not found. Defaulting to fallback metadata;
this can degrade performance and cause issues.

■ {"error":{"cause":"","code":400,"message":"{\"code\":404,\"type\":
\"NOT_FOUND\",\"message\":\"model qwen3-vl-235 not found\",\"cause\":null,
\"details\":null}","status":"FAILED_RESPONSE"},"requestId":"2450010b0f1c7826899d
bd123021efd8-UjloR","result":null}

What steps can reproduce the bug?

codex --profile qwen

What is the expected behavior?

Answer questions normally

Additional information

_No response_