mirror of
https://github.com/fawney19/Aether.git
synced 2026-09-02 09:20:22 +08:00
feat: 扩展 cache creation token 细分统计与 effective_input_tokens 计费逻辑
- 新增 cache_creation_ephemeral_5m/1h_input_tokens 字段，区分不同 TTL 的缓存写入 token - 引入 effective_input_tokens（扣除 cache read 后的有效输入 token），暴露给 usage 接口 - billing 规则生成器支持 5m/1h ephemeral cache 独立定价与分级计费 - usage_mapper 增加 Claude/Anthropic 格式映射，修复 OpenAI responses 格式字段兼容性 - 迁移逻辑增强：支持 checksum 容错、applied/pending 数量日志、逐步执行信息输出 - executor 抽离 LocalExecutionRequestOutcome 类型，统一 sync/stream 路径返回语义 - provider-transport auth 层新增 complete passthrough headers 构建逻辑 - 前端 usage 类型全面补充 effective_input_tokens、cache_creation_tokens、total_input_context 字段
This commit is contained in:
fawney19
@@ -183,6 +183,212 @@ async fn gateway_handles_local_openai_chat_sync_report_with_local_reporting_when
|
||||
upstream_handle.abort();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn gateway_records_failed_usage_when_all_local_openai_chat_candidates_exhaust_after_retryable_sync_failure(
|
||||
) {
|
||||
let usage_repository = Arc::new(InMemoryUsageReadRepository::default());
|
||||
let request_candidate_repository = Arc::new(InMemoryRequestCandidateRepository::default());
|
||||
let report_hits = Arc::new(Mutex::new(0usize));
|
||||
let report_hits_clone = Arc::clone(&report_hits);
|
||||
let decision_hits = Arc::new(Mutex::new(0usize));
|
||||
let decision_hits_clone = Arc::clone(&decision_hits);
|
||||
let plan_hits = Arc::new(Mutex::new(0usize));
|
||||
let plan_hits_clone = Arc::clone(&plan_hits);
|
||||
let public_hits = Arc::new(Mutex::new(0usize));
|
||||
let public_hits_clone = Arc::clone(&public_hits);
|
||||
|
||||
let upstream = Router::new()
|
||||
.route(
|
||||
"/api/internal/gateway/decision-sync",
|
||||
any(move |_request: Request| {
|
||||
let decision_hits_inner = Arc::clone(&decision_hits_clone);
|
||||
async move {
|
||||
*decision_hits_inner.lock().expect("mutex should lock") += 1;
|
||||
Json(json!({"action": "proxy_public"}))
|
||||
}
|
||||
}),
|
||||
)
|
||||
.route(
|
||||
"/api/internal/gateway/plan-sync",
|
||||
any(move |_request: Request| {
|
||||
let plan_hits_inner = Arc::clone(&plan_hits_clone);
|
||||
async move {
|
||||
*plan_hits_inner.lock().expect("mutex should lock") += 1;
|
||||
Json(json!({"action": "proxy_public"}))
|
||||
}
|
||||
}),
|
||||
)
|
||||
.route(
|
||||
"/api/internal/gateway/report-sync",
|
||||
any(move |_request: Request| {
|
||||
let report_hits_inner = Arc::clone(&report_hits_clone);
|
||||
async move {
|
||||
*report_hits_inner.lock().expect("mutex should lock") += 1;
|
||||
Json(json!({"ok": true}))
|
||||
}
|
||||
}),
|
||||
)
|
||||
.route(
|
||||
"/v1/chat/completions",
|
||||
any(move |_request: Request| {
|
||||
let public_hits_inner = Arc::clone(&public_hits_clone);
|
||||
async move {
|
||||
*public_hits_inner.lock().expect("mutex should lock") += 1;
|
||||
(StatusCode::IM_A_TEAPOT, Body::from("public-route-hit"))
|
||||
}
|
||||
}),
|
||||
);
|
||||
|
||||
let execution_runtime = Router::new().route(
|
||||
"/v1/execute/sync",
|
||||
any(|_request: Request| async move {
|
||||
Json(json!({
|
||||
"request_id": "trace-openai-chat-local-report-sync-failure-123",
|
||||
"status_code": 503,
|
||||
"headers": {
|
||||
"content-type": "application/json"
|
||||
},
|
||||
"body": {
|
||||
"json_body": {
|
||||
"error": {
|
||||
"message": "primary unavailable"
|
||||
}
|
||||
}
|
||||
},
|
||||
"telemetry": {
|
||||
"elapsed_ms": 25
|
||||
}
|
||||
}))
|
||||
}),
|
||||
);
|
||||
|
||||
let auth_repository = Arc::new(InMemoryAuthApiKeySnapshotRepository::seed(vec![(
|
||||
Some(hash_api_key("sk-client-openai-local-report-sync-failure")),
|
||||
sample_local_openai_auth_snapshot(
|
||||
"api-key-openai-usage-local-failure-1",
|
||||
"user-openai-usage-local-failure-1",
|
||||
),
|
||||
)]));
|
||||
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 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-local-report-sync-failure",
|
||||
)
|
||||
.header(
|
||||
TRACE_ID_HEADER,
|
||||
"trace-openai-chat-local-report-sync-failure-123",
|
||||
)
|
||||
.body("{\"model\":\"gpt-5\",\"messages\":[]}")
|
||||
.send()
|
||||
.await
|
||||
.expect("request should complete");
|
||||
|
||||
assert_eq!(response.status(), StatusCode::SERVICE_UNAVAILABLE);
|
||||
let body_json: serde_json::Value = response.json().await.expect("body should parse");
|
||||
assert_eq!(body_json["error"]["type"], "http_error");
|
||||
|
||||
let mut stored_usage = None;
|
||||
for _ in 0..50 {
|
||||
stored_usage = usage_repository
|
||||
.find_by_request_id("trace-openai-chat-local-report-sync-failure-123")
|
||||
.await
|
||||
.expect("usage lookup should succeed");
|
||||
if stored_usage.is_some() {
|
||||
break;
|
||||
}
|
||||
tokio::time::sleep(std::time::Duration::from_millis(10)).await;
|
||||
}
|
||||
let stored_usage = stored_usage.expect("failed usage should be recorded");
|
||||
assert_eq!(stored_usage.status, "failed");
|
||||
assert_eq!(stored_usage.billing_status, "void");
|
||||
assert_eq!(stored_usage.status_code, Some(503));
|
||||
assert_eq!(stored_usage.error_category.as_deref(), Some("server_error"));
|
||||
assert_eq!(
|
||||
stored_usage.user_id.as_deref(),
|
||||
Some("user-openai-usage-local-failure-1")
|
||||
);
|
||||
assert_eq!(stored_usage.provider_name, "openai");
|
||||
assert_eq!(stored_usage.model, "gpt-5");
|
||||
assert_eq!(stored_usage.api_format.as_deref(), Some("openai:chat"));
|
||||
assert_eq!(
|
||||
stored_usage
|
||||
.request_metadata
|
||||
.as_ref()
|
||||
.and_then(|value| value.get("trace_id"))
|
||||
.and_then(|value| value.as_str()),
|
||||
Some("trace-openai-chat-local-report-sync-failure-123")
|
||||
);
|
||||
assert_eq!(
|
||||
stored_usage
|
||||
.response_body
|
||||
.as_ref()
|
||||
.and_then(|value| value.get("error"))
|
||||
.and_then(|value| value.get("type"))
|
||||
.and_then(|value| value.as_str()),
|
||||
Some("upstream_error")
|
||||
);
|
||||
assert_eq!(
|
||||
stored_usage
|
||||
.client_response_body
|
||||
.as_ref()
|
||||
.and_then(|value| value.get("error"))
|
||||
.and_then(|value| value.get("type"))
|
||||
.and_then(|value| value.as_str()),
|
||||
Some("http_error")
|
||||
);
|
||||
|
||||
let stored_candidates = request_candidate_repository
|
||||
.list_by_request_id("trace-openai-chat-local-report-sync-failure-123")
|
||||
.await
|
||||
.expect("request candidate trace should read");
|
||||
assert_eq!(stored_candidates.len(), 1);
|
||||
assert_eq!(stored_candidates[0].status, RequestCandidateStatus::Failed);
|
||||
assert_eq!(stored_candidates[0].status_code, Some(503));
|
||||
|
||||
tokio::time::sleep(std::time::Duration::from_millis(100)).await;
|
||||
assert_eq!(*report_hits.lock().expect("mutex should lock"), 0);
|
||||
assert_eq!(*decision_hits.lock().expect("mutex should lock"), 0);
|
||||
assert_eq!(*plan_hits.lock().expect("mutex should lock"), 0);
|
||||
assert_eq!(*public_hits.lock().expect("mutex should lock"), 0);
|
||||
|
||||
gateway_handle.abort();
|
||||
execution_runtime_handle.abort();
|
||||
upstream_handle.abort();
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn gateway_handles_local_openai_chat_stream_report_with_local_reporting_when_usage_runtime_enabled(
|
||||
) {
|
||||
|
||||
Reference in New Issue
Block a user