fix(admin): 修复 usage 观测全表扫描并下推聚合查询

- 收紧 admin usage/stats 默认时间范围和 active 轮询查询
- 将 summary/records/aggregation/time-series/leaderboard 下推到 SQL 侧
- 统一前端时间参数并补齐 admin usage/stats 回归测试
This commit is contained in:
fawney19
2026-04-16 17:41:32 +08:00
parent 10605d9fb0
commit 65cd9dc3e5
28 changed files with 3085 additions and 381 deletions

View File

@@ -156,6 +156,11 @@ fn sample_api_key_snapshot(
snapshot
}
fn recent_unix_secs(minutes_ago: u64) -> i64 {
let now = chrono::Utc::now().timestamp();
now.saturating_sub((minutes_ago * 60) as i64)
}
#[derive(Debug)]
struct PartialListAuthApiKeyRepository {
lookup: InMemoryAuthApiKeySnapshotRepository,
@@ -673,6 +678,83 @@ async fn gateway_handles_admin_stats_error_distribution_locally_without_usage_re
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_defaults_admin_stats_error_distribution_to_bounded_recent_window_when_query_missing(
) {
let (_upstream_url, upstream_hits, upstream_handle) =
start_stats_upstream("/api/admin/stats/errors/distribution").await;
let mut recent_error = sample_usage_row(
"usage-error-recent",
"req-error-recent",
Some("user-1"),
Some("key-1"),
Some("primary"),
"OpenAI",
"gpt-5",
20,
10,
0.02,
0.02,
recent_unix_secs(5),
);
recent_error.status_code = Some(429);
recent_error.error_category = Some("rate_limit".to_string());
recent_error.error_message = Some("rate limited".to_string());
let mut stale_error = sample_usage_row(
"usage-error-stale",
"req-error-stale",
Some("user-1"),
Some("key-1"),
Some("primary"),
"OpenAI",
"gpt-5",
20,
10,
0.02,
0.02,
recent_unix_secs(60 * 48),
);
stale_error.status_code = Some(401);
stale_error.error_category = Some("auth".to_string());
stale_error.error_message = Some("bad key".to_string());
let usage_repository = Arc::new(InMemoryUsageReadRepository::seed(vec![
recent_error,
stale_error,
]));
let gateway = build_router_with_state(
AppState::new()
.expect("gateway should build")
.with_data_state_for_tests(GatewayDataState::with_usage_reader_for_tests(
usage_repository,
)),
);
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response = admin_request(
reqwest::Client::new().get(format!("{gateway_url}/api/admin/stats/errors/distribution")),
)
.send()
.await
.expect("request should succeed");
assert_eq!(response.status(), StatusCode::OK);
let payload: serde_json::Value = response.json().await.expect("json body should parse");
assert_eq!(
payload["distribution"].as_array().map(|items| items.len()),
Some(1)
);
assert_eq!(payload["distribution"][0]["category"], "rate_limit");
assert_eq!(payload["distribution"][0]["count"], 1);
assert_eq!(payload["trend"][0]["total"], 1);
assert_eq!(*upstream_hits.lock().expect("mutex should lock"), 0);
gateway_handle.abort();
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_handles_admin_stats_performance_percentiles_locally_with_trusted_admin_principal()
{
@@ -839,6 +921,80 @@ async fn gateway_handles_admin_stats_time_series_locally_with_trusted_admin_prin
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_handles_admin_stats_time_series_hourly_locally_with_model_filter() {
let (_upstream_url, upstream_hits, upstream_handle) =
start_stats_upstream("/api/admin/stats/time-series").await;
let mut matching_row = sample_usage_row(
"usage-ts-hour-match",
"req-ts-hour-match",
Some("user-1"),
Some("key-1"),
Some("primary"),
"OpenAI",
"gpt-5",
80,
20,
0.12,
0.12,
1_710_997_800,
);
matching_row.cache_creation_input_tokens = 4;
matching_row.cache_read_input_tokens = 6;
let other_model_row = sample_usage_row(
"usage-ts-hour-other",
"req-ts-hour-other",
Some("user-1"),
Some("key-1"),
Some("primary"),
"OpenAI",
"gpt-4o-mini",
200,
40,
0.22,
0.22,
1_710_998_400,
);
let usage_repository = Arc::new(InMemoryUsageReadRepository::seed(vec![
matching_row,
other_model_row,
]));
let gateway = build_router_with_state(
AppState::new()
.expect("gateway should build")
.with_data_state_for_tests(GatewayDataState::with_usage_reader_for_tests(
usage_repository,
)),
);
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response = admin_request(
reqwest::Client::new().get(format!(
"{gateway_url}/api/admin/stats/time-series?start_date=2024-03-21&end_date=2024-03-21&granularity=hour&model=gpt-5&tz_offset_minutes=0"
)),
)
.send()
.await
.expect("request should succeed");
assert_eq!(response.status(), StatusCode::OK);
let payload: serde_json::Value = response.json().await.expect("json body should parse");
assert_eq!(payload.as_array().map(|items| items.len()), Some(24));
assert_eq!(payload[5]["date"], "2024-03-21T05:00:00+00:00");
assert_eq!(payload[5]["total_requests"], 1);
assert_eq!(payload[5]["input_tokens"], 80);
assert_eq!(payload[5]["cache_creation_tokens"], 4);
assert_eq!(payload[5]["cache_read_tokens"], 6);
assert_eq!(payload[6]["total_requests"], 0);
assert_eq!(*upstream_hits.lock().expect("mutex should lock"), 0);
gateway_handle.abort();
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_handles_admin_stats_time_series_locally_without_usage_reader() {
let (upstream_url, upstream_hits, upstream_handle) =
@@ -1055,6 +1211,71 @@ async fn gateway_handles_admin_stats_leaderboard_models_locally_without_usage_re
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_defaults_admin_stats_leaderboard_models_to_bounded_recent_window_when_query_missing(
) {
let (_upstream_url, upstream_hits, upstream_handle) =
start_stats_upstream("/api/admin/stats/leaderboard/models").await;
let recent_row = sample_usage_row(
"usage-model-recent",
"req-model-recent",
Some("user-1"),
Some("key-1"),
Some("primary"),
"OpenAI",
"gpt-5",
100,
50,
0.4,
0.4,
recent_unix_secs(10),
);
let stale_row = sample_usage_row(
"usage-model-stale",
"req-model-stale",
Some("user-1"),
Some("key-1"),
Some("primary"),
"Anthropic",
"claude-3-5-sonnet",
60,
20,
0.2,
0.2,
recent_unix_secs(60 * 48),
);
let usage_repository = Arc::new(InMemoryUsageReadRepository::seed(vec![
recent_row, stale_row,
]));
let gateway = build_router_with_state(
AppState::new()
.expect("gateway should build")
.with_data_state_for_tests(GatewayDataState::with_usage_reader_for_tests(
usage_repository,
)),
);
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response = admin_request(reqwest::Client::new().get(format!(
"{gateway_url}/api/admin/stats/leaderboard/models?metric=tokens&order=desc"
)))
.send()
.await
.expect("request should succeed");
assert_eq!(response.status(), StatusCode::OK);
let payload: serde_json::Value = response.json().await.expect("json body should parse");
assert_eq!(payload["total"], 1);
assert_eq!(payload["items"][0]["id"], "gpt-5");
assert_eq!(payload["items"][0]["value"], 150);
assert_eq!(*upstream_hits.lock().expect("mutex should lock"), 0);
gateway_handle.abort();
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_handles_admin_stats_leaderboard_api_keys_locally_with_trusted_admin_principal() {
let (upstream_url, upstream_hits, upstream_handle) =

View File

@@ -346,6 +346,72 @@ async fn gateway_handles_admin_usage_stats_locally_with_trusted_admin_principal(
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_defaults_admin_usage_stats_to_bounded_recent_window_when_query_missing() {
let (upstream_url, upstream_hits, upstream_handle) =
start_usage_upstream("/api/admin/usage/stats").await;
let recent_created_at = recent_unix_secs(5);
let stale_created_at = recent_unix_secs(60 * 48);
let usage_repository = Arc::new(InMemoryUsageReadRepository::seed(vec![
sample_usage_row(
"usage-recent",
"req-recent",
Some("user-1"),
Some("key-1"),
Some("primary"),
"OpenAI",
"gpt-5",
"completed",
120,
30,
0.3,
0.36,
recent_created_at,
),
sample_usage_row(
"usage-stale",
"req-stale",
Some("user-2"),
Some("key-2"),
Some("secondary"),
"Anthropic",
"claude-3-7",
"failed",
40,
10,
0.1,
0.12,
stale_created_at,
),
]));
let gateway = build_router_with_state(
AppState::new()
.expect("gateway should build")
.with_data_state_for_tests(GatewayDataState::with_usage_reader_for_tests(
usage_repository,
)),
);
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response =
admin_request(reqwest::Client::new().get(format!("{gateway_url}/api/admin/usage/stats")))
.send()
.await
.expect("request should succeed");
assert_eq!(response.status(), StatusCode::OK);
let payload: serde_json::Value = response.json().await.expect("json body should parse");
assert_eq!(payload["total_requests"], 1);
assert_eq!(payload["total_tokens"], 170);
assert_eq!(payload["error_count"], 0);
assert_eq!(*upstream_hits.lock().expect("mutex should lock"), 0);
gateway_handle.abort();
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_returns_service_unavailable_for_admin_usage_stats_without_usage_reader() {
assert_admin_usage_route_returns_local_503(
@@ -435,7 +501,7 @@ async fn gateway_handles_admin_usage_aggregation_stats_locally_with_trusted_admi
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response = admin_request(reqwest::Client::new().get(format!(
"{gateway_url}/api/admin/usage/aggregation/stats?group_by=model&limit=10"
"{gateway_url}/api/admin/usage/aggregation/stats?group_by=model&limit=10&start_date=2024-03-21&end_date=2024-03-22&tz_offset_minutes=0"
)))
.send()
.await
@@ -458,7 +524,7 @@ async fn gateway_handles_admin_usage_aggregation_stats_locally_with_trusted_admi
assert_eq!(items[1]["output_tokens"], 20);
let provider_response = admin_request(reqwest::Client::new().get(format!(
"{gateway_url}/api/admin/usage/aggregation/stats?group_by=provider&limit=10"
"{gateway_url}/api/admin/usage/aggregation/stats?group_by=provider&limit=10&start_date=2024-03-21&end_date=2024-03-22&tz_offset_minutes=0"
)))
.send()
.await
@@ -477,7 +543,7 @@ async fn gateway_handles_admin_usage_aggregation_stats_locally_with_trusted_admi
assert_eq!(provider_items[1]["output_tokens"], 20);
let api_format_response = admin_request(reqwest::Client::new().get(format!(
"{gateway_url}/api/admin/usage/aggregation/stats?group_by=api_format&limit=10"
"{gateway_url}/api/admin/usage/aggregation/stats?group_by=api_format&limit=10&start_date=2024-03-21&end_date=2024-03-22&tz_offset_minutes=0"
)))
.send()
.await
@@ -578,7 +644,7 @@ async fn gateway_handles_admin_usage_aggregation_stats_locally_with_bearer_admin
let response = reqwest::Client::new()
.get(format!(
"{gateway_url}/api/admin/usage/aggregation/stats?group_by=user"
"{gateway_url}/api/admin/usage/aggregation/stats?group_by=user&start_date=2024-03-21&end_date=2024-03-22&tz_offset_minutes=0"
))
.header("authorization", format!("Bearer {access_token}"))
.header("x-client-device-id", "device-admin-usage")
@@ -739,10 +805,12 @@ async fn gateway_handles_admin_usage_active_locally_with_trusted_admin_principal
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response =
admin_request(reqwest::Client::new().get(format!("{gateway_url}/api/admin/usage/active")))
.send()
.await
.expect("request should succeed");
admin_request(reqwest::Client::new().get(format!(
"{gateway_url}/api/admin/usage/active?start_date=2024-03-21&end_date=2024-03-22&tz_offset_minutes=0"
)))
.send()
.await
.expect("request should succeed");
assert_eq!(response.status(), StatusCode::OK);
let payload: serde_json::Value = response.json().await.expect("json body should parse");
@@ -761,6 +829,136 @@ async fn gateway_handles_admin_usage_active_locally_with_trusted_admin_principal
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_defaults_admin_usage_active_to_recent_window_when_query_missing() {
let (upstream_url, upstream_hits, upstream_handle) =
start_usage_upstream("/api/admin/usage/active").await;
let recent_created_at = recent_unix_secs(3);
let stale_created_at = recent_unix_secs(60 * 48);
let usage_repository = Arc::new(InMemoryUsageReadRepository::seed(vec![
sample_usage_row(
"usage-recent-pending",
"req-recent-pending",
Some("user-1"),
Some("key-1"),
Some("primary"),
"OpenAI",
"gpt-5",
"pending",
10,
0,
0.0,
0.0,
recent_created_at,
),
sample_usage_row(
"usage-stale-pending",
"req-stale-pending",
Some("user-2"),
Some("key-2"),
Some("secondary"),
"Anthropic",
"claude-3-7",
"pending",
40,
10,
0.1,
0.12,
stale_created_at,
),
sample_usage_row(
"usage-recent-completed",
"req-recent-completed",
Some("user-3"),
Some("key-3"),
Some("tertiary"),
"Google",
"gemini-2.5-pro",
"completed",
20,
5,
0.2,
0.22,
recent_created_at + 1,
),
]));
let gateway = build_router_with_state(
AppState::new()
.expect("gateway should build")
.with_data_state_for_tests(GatewayDataState::with_usage_reader_for_tests(
usage_repository,
)),
);
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response =
admin_request(reqwest::Client::new().get(format!("{gateway_url}/api/admin/usage/active")))
.send()
.await
.expect("request should succeed");
assert_eq!(response.status(), StatusCode::OK);
let payload: serde_json::Value = response.json().await.expect("json body should parse");
let requests = payload["requests"].as_array().expect("array");
assert_eq!(requests.len(), 1);
assert_eq!(requests[0]["id"], "usage-recent-pending");
assert_eq!(*upstream_hits.lock().expect("mutex should lock"), 0);
gateway_handle.abort();
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_handles_admin_usage_active_ids_for_terminal_updates() {
let (upstream_url, upstream_hits, upstream_handle) =
start_usage_upstream("/api/admin/usage/active").await;
let usage_repository = Arc::new(InMemoryUsageReadRepository::seed(vec![sample_usage_row(
"usage-completed",
"req-completed",
Some("user-1"),
Some("key-1"),
Some("primary"),
"OpenAI",
"gpt-5",
"completed",
20,
5,
0.2,
0.24,
recent_unix_secs(2),
)]));
let gateway = build_router_with_state(
AppState::new()
.expect("gateway should build")
.with_data_state_for_tests(GatewayDataState::with_usage_reader_for_tests(
usage_repository,
)),
);
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response = admin_request(reqwest::Client::new().get(format!(
"{gateway_url}/api/admin/usage/active?ids=usage-completed"
)))
.send()
.await
.expect("request should succeed");
assert_eq!(response.status(), StatusCode::OK);
let payload: serde_json::Value = response.json().await.expect("json body should parse");
let requests = payload["requests"].as_array().expect("array");
assert_eq!(requests.len(), 1);
assert_eq!(requests[0]["id"], "usage-completed");
assert_eq!(requests[0]["status"], "completed");
assert_eq!(*upstream_hits.lock().expect("mutex should lock"), 0);
gateway_handle.abort();
upstream_handle.abort();
}
#[tokio::test]
async fn gateway_handles_admin_usage_records_locally_with_trusted_admin_principal() {
let (upstream_url, upstream_hits, upstream_handle) =
@@ -825,7 +1023,7 @@ async fn gateway_handles_admin_usage_records_locally_with_trusted_admin_principa
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response = admin_request(reqwest::Client::new().get(format!(
"{gateway_url}/api/admin/usage/records?status=failed&provider=Anthropic&limit=10&offset=0"
"{gateway_url}/api/admin/usage/records?start_date=2024-03-21&end_date=2024-03-22&tz_offset_minutes=0&status=failed&provider=Anthropic&limit=10&offset=0"
)))
.send()
.await
@@ -949,7 +1147,7 @@ async fn gateway_handles_admin_usage_records_with_snapshot_first_user_and_api_ke
let (gateway_url, gateway_handle) = start_server(gateway).await;
let response = admin_request(reqwest::Client::new().get(format!(
"{gateway_url}/api/admin/usage/records?search=fresh-secondary&username=fresh-bob&limit=10&offset=0"
"{gateway_url}/api/admin/usage/records?start_date=2024-03-21&end_date=2024-03-22&tz_offset_minutes=0&search=fresh-secondary&username=fresh-bob&limit=10&offset=0"
)))
.send()
.await