mirror of
https://github.com/fawney19/Aether.git
synced 2026-09-02 09:20:22 +08:00
feat: 提前记录 pending 用量、优化流遥测时序与前端活跃请求发现机制
- 将 record_pending 调用移至执行开始前（sync/stream 两路），确保请求在执行前即有 pending 记录 - stream_pump 在收到第一个数据块前优先 yield 遥测帧，保证 ttfb 早于 data 帧到达 - stream execution 增加 should_refresh_stream_usage_telemetry，在遥测帧携带新 ttfb/elapsed 时及时更新 record_stream_started - access_log 对高频轮询路径（usage/active、usage/records 等）降级为 TRACE 日志，减少日志噪音 - 前端新增 reconcileActiveRequestDiscovery 工具函数及 discoverActiveRequests 逻辑，活跃请求发现与全局自动刷新解耦，空闲时降频为 5 秒扫描 - RequestDetailDrawer 调整：进行中请求不再自动开启轮询，由用户手动触发；刷新按钮 title 动态适配状态
This commit is contained in:
fawney19
@@ -118,6 +118,159 @@ async fn gateway_records_usage_for_execution_runtime_sync_when_runtime_enabled()
|
||||
upstream_handle.abort();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn gateway_records_pending_usage_before_execution_runtime_sync_result_arrives() {
|
||||
let usage_repository = Arc::new(InMemoryUsageReadRepository::default());
|
||||
let request_candidate_repository = Arc::new(InMemoryRequestCandidateRepository::default());
|
||||
let execution_request_started = Arc::new(tokio::sync::Notify::new());
|
||||
let allow_execution_response = Arc::new(tokio::sync::Notify::new());
|
||||
|
||||
let upstream = Router::new().route(
|
||||
"/api/internal/gateway/report-sync",
|
||||
any(|_request: Request| async move { Json(json!({"ok": true})) }),
|
||||
);
|
||||
|
||||
let execution_runtime = Router::new().route(
|
||||
"/v1/execute/sync",
|
||||
any({
|
||||
let execution_request_started = Arc::clone(&execution_request_started);
|
||||
let allow_execution_response = Arc::clone(&allow_execution_response);
|
||||
move |_request: Request| {
|
||||
let execution_request_started = Arc::clone(&execution_request_started);
|
||||
let allow_execution_response = Arc::clone(&allow_execution_response);
|
||||
async move {
|
||||
execution_request_started.notify_one();
|
||||
allow_execution_response.notified().await;
|
||||
Json(json!({
|
||||
"request_id": "req-usage-sync-pending-123",
|
||||
"status_code": 200,
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": {
|
||||
"json_body": {
|
||||
"id": "chatcmpl-usage-sync-pending-123",
|
||||
"usage": {
|
||||
"input_tokens": 3,
|
||||
"output_tokens": 5,
|
||||
"total_tokens": 8
|
||||
}
|
||||
}
|
||||
},
|
||||
"telemetry": {
|
||||
"elapsed_ms": 45
|
||||
}
|
||||
}))
|
||||
}
|
||||
}
|
||||
}),
|
||||
);
|
||||
|
||||
let auth_repository = Arc::new(InMemoryAuthApiKeySnapshotRepository::seed(vec![(
|
||||
Some(hash_api_key("sk-client-openai-usage-sync-pending")),
|
||||
sample_local_openai_auth_snapshot(
|
||||
"api-key-usage-sync-pending-123",
|
||||
"user-usage-sync-pending-123",
|
||||
),
|
||||
)]));
|
||||
let candidate_selection_repository =
|
||||
Arc::new(InMemoryMinimalCandidateSelectionReadRepository::seed(vec![
|
||||
sample_local_openai_candidate_row(),
|
||||
]));
|
||||
let provider_catalog_repository = Arc::new(InMemoryProviderCatalogReadRepository::seed(
|
||||
vec![sample_local_openai_provider()],
|
||||
vec![sample_local_openai_endpoint()],
|
||||
vec![sample_local_openai_key()],
|
||||
));
|
||||
|
||||
let (upstream_url, upstream_handle) = start_server(upstream).await;
|
||||
let (execution_runtime_url, execution_runtime_handle) = start_server(execution_runtime).await;
|
||||
let gateway_state =
|
||||
build_state_with_execution_runtime_override(execution_runtime_url)
|
||||
.with_data_state_for_tests(
|
||||
GatewayDataState::with_auth_candidate_selection_provider_catalog_request_candidates_and_usage_for_tests(
|
||||
auth_repository,
|
||||
candidate_selection_repository,
|
||||
provider_catalog_repository,
|
||||
Arc::clone(&request_candidate_repository),
|
||||
Arc::clone(&usage_repository),
|
||||
DEVELOPMENT_ENCRYPTION_KEY,
|
||||
),
|
||||
)
|
||||
.with_usage_runtime_for_tests(UsageRuntimeConfig {
|
||||
enabled: true,
|
||||
..UsageRuntimeConfig::default()
|
||||
});
|
||||
let gateway = build_router_with_state(gateway_state);
|
||||
let (gateway_url, gateway_handle) = start_server(gateway).await;
|
||||
|
||||
let request_task = tokio::spawn({
|
||||
let gateway_url = gateway_url.clone();
|
||||
async move {
|
||||
let response = reqwest::Client::new()
|
||||
.post(format!("{gateway_url}/v1/chat/completions"))
|
||||
.header(http::header::CONTENT_TYPE, "application/json")
|
||||
.header(
|
||||
http::header::AUTHORIZATION,
|
||||
"Bearer sk-client-openai-usage-sync-pending",
|
||||
)
|
||||
.header(TRACE_ID_HEADER, "req-usage-sync-pending-123")
|
||||
.body("{\"model\":\"gpt-5\",\"messages\":[]}")
|
||||
.send()
|
||||
.await
|
||||
.expect("request should succeed");
|
||||
let status = response.status();
|
||||
let body = response.text().await.expect("body should read");
|
||||
(status, body)
|
||||
}
|
||||
});
|
||||
|
||||
execution_request_started.notified().await;
|
||||
|
||||
let mut pending = None;
|
||||
for _ in 0..50 {
|
||||
pending = usage_repository
|
||||
.find_by_request_id("req-usage-sync-pending-123")
|
||||
.await
|
||||
.expect("usage lookup should succeed");
|
||||
if pending
|
||||
.as_ref()
|
||||
.is_some_and(|stored| stored.status == "pending")
|
||||
{
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
}
|
||||
let pending = pending.expect("pending usage should be recorded before sync result resolves");
|
||||
assert_eq!(pending.status, "pending");
|
||||
assert_eq!(pending.billing_status, "pending");
|
||||
assert_eq!(pending.response_time_ms, None);
|
||||
|
||||
allow_execution_response.notify_one();
|
||||
|
||||
let (status, _body) = request_task.await.expect("request task should join");
|
||||
assert_eq!(status, StatusCode::OK);
|
||||
|
||||
let mut stored = None;
|
||||
for _ in 0..50 {
|
||||
stored = usage_repository
|
||||
.find_by_request_id("req-usage-sync-pending-123")
|
||||
.await
|
||||
.expect("usage lookup should succeed");
|
||||
if stored.as_ref().is_some_and(|row| row.status == "completed") {
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
}
|
||||
let stored = stored.expect("usage should be finalized");
|
||||
assert_eq!(stored.status, "completed");
|
||||
assert_eq!(stored.response_time_ms, Some(45));
|
||||
|
||||
gateway_handle.abort();
|
||||
execution_runtime_handle.abort();
|
||||
upstream_handle.abort();
|
||||
}
|
||||
|
||||
async fn gateway_records_usage_for_execution_runtime_stream_when_runtime_enabled() {
|
||||
let usage_repository = Arc::new(InMemoryUsageReadRepository::default());
|
||||
|
||||
@@ -239,3 +392,151 @@ async fn gateway_records_usage_for_execution_runtime_stream_when_runtime_enabled
|
||||
execution_runtime_handle.abort();
|
||||
upstream_handle.abort();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn gateway_records_pending_usage_before_execution_runtime_stream_headers_arrive() {
|
||||
let usage_repository = Arc::new(InMemoryUsageReadRepository::default());
|
||||
let request_candidate_repository = Arc::new(InMemoryRequestCandidateRepository::default());
|
||||
let execution_request_started = Arc::new(tokio::sync::Notify::new());
|
||||
let allow_execution_response = Arc::new(tokio::sync::Notify::new());
|
||||
|
||||
let upstream = Router::new().route(
|
||||
"/api/internal/gateway/report-stream",
|
||||
any(|_request: Request| async move { Json(json!({"ok": true})) }),
|
||||
);
|
||||
|
||||
let execution_runtime = Router::new().route(
|
||||
"/v1/execute/stream",
|
||||
any({
|
||||
let execution_request_started = Arc::clone(&execution_request_started);
|
||||
let allow_execution_response = Arc::clone(&allow_execution_response);
|
||||
move |_request: Request| {
|
||||
let execution_request_started = Arc::clone(&execution_request_started);
|
||||
let allow_execution_response = Arc::clone(&allow_execution_response);
|
||||
async move {
|
||||
execution_request_started.notify_one();
|
||||
allow_execution_response.notified().await;
|
||||
let frames = concat!(
|
||||
"{\"type\":\"headers\",\"payload\":{\"kind\":\"headers\",\"status_code\":200,\"headers\":{\"content-type\":\"text/event-stream\"}}}\n",
|
||||
"{\"type\":\"data\",\"payload\":{\"kind\":\"data\",\"text\":\"data: {\\\"id\\\":\\\"chatcmpl-usage-stream-pending-123\\\",\\\"usage\\\":{\\\"input_tokens\\\":2,\\\"output_tokens\\\":4,\\\"total_tokens\\\":6}}\\n\\n\"}}\n",
|
||||
"{\"type\":\"data\",\"payload\":{\"kind\":\"data\",\"text\":\"data: [DONE]\\n\\n\"}}\n",
|
||||
"{\"type\":\"telemetry\",\"payload\":{\"kind\":\"telemetry\",\"telemetry\":{\"elapsed_ms\":51,\"ttfb_ms\":19}}}\n",
|
||||
"{\"type\":\"eof\",\"payload\":{\"kind\":\"eof\"}}\n"
|
||||
);
|
||||
let mut response = Response::builder()
|
||||
.status(StatusCode::OK)
|
||||
.body(Body::from(frames))
|
||||
.expect("response should build");
|
||||
response.headers_mut().insert(
|
||||
http::header::CONTENT_TYPE,
|
||||
HeaderValue::from_static("application/x-ndjson"),
|
||||
);
|
||||
response
|
||||
}
|
||||
}
|
||||
}),
|
||||
);
|
||||
|
||||
let (upstream_url, upstream_handle) = start_server(upstream).await;
|
||||
let (execution_runtime_url, execution_runtime_handle) = start_server(execution_runtime).await;
|
||||
let auth_repository = Arc::new(InMemoryAuthApiKeySnapshotRepository::seed(vec![(
|
||||
Some(hash_api_key("sk-client-openai-stream-pending")),
|
||||
sample_local_openai_auth_snapshot(
|
||||
"api-key-usage-stream-pending-123",
|
||||
"user-usage-stream-pending-123",
|
||||
),
|
||||
)]));
|
||||
let candidate_selection_repository =
|
||||
Arc::new(InMemoryMinimalCandidateSelectionReadRepository::seed(vec![
|
||||
sample_local_openai_candidate_row(),
|
||||
]));
|
||||
let provider_catalog_repository = Arc::new(InMemoryProviderCatalogReadRepository::seed(
|
||||
vec![sample_local_openai_provider()],
|
||||
vec![sample_local_openai_endpoint()],
|
||||
vec![sample_local_openai_key()],
|
||||
));
|
||||
let gateway_state = build_state_with_execution_runtime_override(execution_runtime_url)
|
||||
.with_data_state_for_tests(
|
||||
GatewayDataState::with_auth_candidate_selection_provider_catalog_request_candidates_and_usage_for_tests(
|
||||
auth_repository,
|
||||
candidate_selection_repository,
|
||||
provider_catalog_repository,
|
||||
Arc::clone(&request_candidate_repository),
|
||||
usage_repository.clone(),
|
||||
DEVELOPMENT_ENCRYPTION_KEY,
|
||||
),
|
||||
)
|
||||
.with_usage_runtime_for_tests(UsageRuntimeConfig {
|
||||
enabled: true,
|
||||
..UsageRuntimeConfig::default()
|
||||
});
|
||||
let gateway = build_router_with_state(gateway_state);
|
||||
let (gateway_url, gateway_handle) = start_server(gateway).await;
|
||||
|
||||
let request_task = tokio::spawn({
|
||||
let gateway_url = gateway_url.clone();
|
||||
async move {
|
||||
let response = reqwest::Client::new()
|
||||
.post(format!("{gateway_url}/v1/chat/completions"))
|
||||
.header(http::header::CONTENT_TYPE, "application/json")
|
||||
.header(
|
||||
http::header::AUTHORIZATION,
|
||||
"Bearer sk-client-openai-stream-pending",
|
||||
)
|
||||
.header(TRACE_ID_HEADER, "req-usage-stream-pending-123")
|
||||
.body("{\"model\":\"gpt-5\",\"messages\":[],\"stream\":true}")
|
||||
.send()
|
||||
.await
|
||||
.expect("request should succeed");
|
||||
let status = response.status();
|
||||
let body = response.text().await.expect("stream body should read");
|
||||
(status, body)
|
||||
}
|
||||
});
|
||||
|
||||
execution_request_started.notified().await;
|
||||
|
||||
let mut pending = None;
|
||||
for _ in 0..50 {
|
||||
pending = usage_repository
|
||||
.find_by_request_id("req-usage-stream-pending-123")
|
||||
.await
|
||||
.expect("usage lookup should succeed");
|
||||
if pending
|
||||
.as_ref()
|
||||
.is_some_and(|stored| stored.status == "pending")
|
||||
{
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
}
|
||||
let pending = pending.expect("pending usage should be recorded before stream headers arrive");
|
||||
assert_eq!(pending.status, "pending");
|
||||
assert_eq!(pending.billing_status, "pending");
|
||||
assert_eq!(pending.first_byte_time_ms, None);
|
||||
assert_eq!(pending.response_time_ms, None);
|
||||
|
||||
allow_execution_response.notify_one();
|
||||
|
||||
let (status, _body) = request_task.await.expect("request task should join");
|
||||
assert_eq!(status, StatusCode::OK);
|
||||
|
||||
let mut stored = None;
|
||||
for _ in 0..50 {
|
||||
stored = usage_repository
|
||||
.find_by_request_id("req-usage-stream-pending-123")
|
||||
.await
|
||||
.expect("usage lookup should succeed");
|
||||
if stored.as_ref().is_some_and(|row| row.status == "completed") {
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
}
|
||||
let stored = stored.expect("usage should be finalized");
|
||||
assert_eq!(stored.status, "completed");
|
||||
assert_eq!(stored.first_byte_time_ms, Some(19));
|
||||
|
||||
gateway_handle.abort();
|
||||
execution_runtime_handle.abort();
|
||||
upstream_handle.abort();
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user