use std::collections::HashMap; use std::sync::Arc; use api::{ ContentBlockDelta, ContentBlockDeltaEvent, ContentBlockStartEvent, ContentBlockStopEvent, InputContentBlock, InputMessage, MessageDeltaEvent, MessageRequest, OpenAiCompatClient, OpenAiCompatConfig, OutputContentBlock, StreamEvent, ToolChoice, ToolDefinition, }; use serde_json::json; use tokio::io::{AsyncReadExt, AsyncWriteExt}; use tokio::net::TcpListener; use tokio::sync::Mutex; #[allow(clippy::await_holding_lock)] #[tokio::test] async fn openai_streaming_requests_opt_into_usage_chunks() { let state = Arc::new(Mutex::new(Vec::::new())); let sse = concat!( "data: {\"id\":\"chatcmpl_openai_stream\",\"model\":\"gpt-5\",\"choices\":[{\"delta\":{\"content\":\"Hi\"}}]}\n\n", "data: {\"id\":\"chatcmpl_openai_stream\",\"choices\":[{\"delta\":{},\"finish_reason\":\"stop\"}]}\n\n", "data: {\"id\":\"chatcmpl_openai_stream\",\"choices\":[],\"usage\":{\"prompt_tokens\":9,\"completion_tokens\":4}}\n\n", "data: [DONE]\n\n" ); let server = spawn_server( state.clone(), vec![http_response_with_headers( "200 OK", "text/event-stream", sse, &[("x-request-id", "req_openai_stream")], )], ) .await; let client = OpenAiCompatClient::new("openai-test-key", OpenAiCompatConfig::openai()) .with_base_url(server.base_url()); let mut stream = client .stream_message(&sample_request(false)) .await .expect("stream should start"); assert_eq!(stream.request_id(), Some("req_openai_stream")); let mut events = Vec::new(); while let Some(event) = stream.next_event().await.expect("event should parse") { events.push(event); } assert!(matches!(events[0], StreamEvent::MessageStart(_))); assert!(matches!( events[1], StreamEvent::ContentBlockStart(ContentBlockStartEvent { content_block: OutputContentBlock::Text { .. }, .. }) )); assert!(matches!( events[2], StreamEvent::ContentBlockDelta(ContentBlockDeltaEvent { delta: ContentBlockDelta::TextDelta { .. }, .. }) )); assert!(matches!( events[3], StreamEvent::ContentBlockStop(ContentBlockStopEvent { index: 0 }) )); assert!(matches!( events[4], StreamEvent::MessageDelta(MessageDeltaEvent { .. }) )); assert!(matches!(events[5], StreamEvent::MessageStop(_))); match &events[4] { StreamEvent::MessageDelta(MessageDeltaEvent { usage, .. }) => { assert_eq!(usage.input_tokens, 9); assert_eq!(usage.output_tokens, 4); } other => panic!("expected message delta, got {other:?}"), } let captured = state.lock().await; let request = captured.first().expect("captured request"); assert_eq!(request.path, "/chat/completions"); let body: serde_json::Value = serde_json::from_str(&request.body).expect("json body"); assert_eq!(body["stream"], json!(true)); assert_eq!(body["stream_options"], json!({"include_usage": true})); } #[derive(Debug, Clone, PartialEq, Eq)] struct CapturedRequest { path: String, headers: HashMap, body: String, } struct TestServer { base_url: String, join_handle: tokio::task::JoinHandle<()>, } impl TestServer { fn base_url(&self) -> String { self.base_url.clone() } } impl Drop for TestServer { fn drop(&mut self) { self.join_handle.abort(); } } async fn spawn_server( state: Arc>>, responses: Vec, ) -> TestServer { let listener = TcpListener::bind("127.0.0.1:0") .await .expect("listener should bind"); let address = listener.local_addr().expect("listener addr"); let join_handle = tokio::spawn(async move { for response in responses { let (mut socket, _) = listener.accept().await.expect("accept"); let mut buffer = Vec::new(); let mut header_end = None; loop { let mut chunk = [0_u8; 1024]; let read = socket.read(&mut chunk).await.expect("read request"); if read == 0 { break; } buffer.extend_from_slice(&chunk[..read]); if let Some(position) = find_header_end(&buffer) { header_end = Some(position); break; } } let header_end = header_end.expect("headers should exist"); let (header_bytes, remaining) = buffer.split_at(header_end); let header_text = String::from_utf8(header_bytes.to_vec()).expect("utf8 headers"); let mut lines = header_text.split("\r\n"); let request_line = lines.next().expect("request line"); let path = request_line .split_whitespace() .nth(1) .expect("path") .to_string(); let mut headers = HashMap::new(); let mut content_length = 0_usize; for line in lines { if line.is_empty() { continue; } let (name, value) = line.split_once(':').expect("header"); let value = value.trim().to_string(); if name.eq_ignore_ascii_case("content-length") { content_length = value.parse().expect("content length"); } headers.insert(name.to_ascii_lowercase(), value); } let mut body = remaining[4..].to_vec(); while body.len() < content_length { let mut chunk = vec![0_u8; content_length - body.len()]; let read = socket.read(&mut chunk).await.expect("read body"); if read == 0 { break; } body.extend_from_slice(&chunk[..read]); } state.lock().await.push(CapturedRequest { path, headers, body: String::from_utf8(body).expect("utf8 body"), }); socket .write_all(response.as_bytes()) .await .expect("write response"); } }); TestServer { base_url: format!("http://{address}"), join_handle, } } fn find_header_end(bytes: &[u8]) -> Option { bytes.windows(4).position(|window| window == b"\r\n\r\n") } fn http_response_with_headers( status: &str, content_type: &str, body: &str, headers: &[(&str, &str)], ) -> String { let mut extra_headers = String::new(); for (name, value) in headers { use std::fmt::Write as _; write!(&mut extra_headers, "{name}: {value}\r\n").expect("header write"); } format!( "HTTP/1.1 {status}\r\ncontent-type: {content_type}\r\n{extra_headers}content-length: {}\r\nconnection: close\r\n\r\n{body}", body.len() ) } fn sample_request(stream: bool) -> MessageRequest { MessageRequest { model: "grok-3".to_string(), max_tokens: 64, messages: Arc::new(vec![InputMessage { role: "user".to_string(), content: vec![InputContentBlock::Text { text: "Say hello".to_string(), }], }]), system: Some(Arc::from("Use tools when needed")), tools: Some(vec![ToolDefinition { name: "weather".to_string(), description: Some("Fetches weather".to_string()), input_schema: json!({ "type": "object", "properties": {"city": {"type": "string"}}, "required": ["city"] }), }]), tool_choice: Some(ToolChoice::Auto), stream, ..Default::default() } }