Docs: Observability Uses Incorrect `stream_options` Value

[danehans]

This doc states:

If you want to include usage metrics for vLLM model server streaming request, send the request with include_usage:

curl -i ${IP}:${PORT}/v1/completions -H 'Content-Type: application/json' -d '{
"model": "food-review",
"prompt": "whats your fav movie?",
"max_tokens": 10,
"temperature": 0,
"stream": true,
"stream_options": {"include_usage": "true"}
}'

According to OpenAI docs, the value of include_usage should be a boolean instead of a string. Here is an example error case:

curl -i http://localhost:8885/v1/completions -H 'Content-Type: application/json' -d '{
"model": "food-review-0",
"prompt": "whats your fav movie?",
"max_tokens": 10,
"temperature": 0,
"stream": true,
"stream_options": {"include_usage": "true"}
}'
HTTP/1.1 400 Bad Request
server: fasthttp
date: Mon, 20 Oct 2025 15:26:44 GMT
content-type: text/plain; charset=utf-8
x-went-into-resp-headers: true
transfer-encoding: chunked

Failed to read and parse request body, json: cannot unmarshal string into Go struct field StreamOptions.baseCompletionRequest.stream_options.include_usage of type bool%

[aman4433]

/assign