Files
codex-proxy-rs/frontend/src/api/modules/usage.ts
T

511 lines
14 KiB
TypeScript

import type { RequestOptions } from '../request'
import type { AnalyticsMetadata } from './analytics'
import { API_BASE_URL } from '../constants'
import request from '../request'
export interface UsageTokenDetails {
inputTokens: number | null
outputTokens: number | null
cachedInputTokens: number | null
cacheWriteInputTokens: number | null
reasoningOutputTokens: number | null
imageInputTokens: number | null
imageOutputTokens: number | null
totalTokens: number | null
inputTokensDisplay: string
outputTokensDisplay: string
cachedInputTokensDisplay: string
cacheWriteInputTokensDisplay: string
reasoningOutputTokensDisplay: string
imageInputTokensDisplay: string
imageOutputTokensDisplay: string
totalTokensDisplay: string
}
export interface UsageCost {
currency: string
estimatedAmount: string
}
export interface UsageCostCoverage {
known: number
partial: number
unknown: number
notBillable: number
}
export interface UsageBilling {
longContextBillingApplied: boolean
image?: {
inputAmountDisplay: string
cacheReadAmountDisplay: string
inputPriceDisplay: string
cacheReadPriceDisplay: string
}
inputAmountDisplay: string
outputAmountDisplay: string
cacheReadAmountDisplay: string
cacheWriteAmountDisplay: string
standardAmountDisplay: string
totalAmountDisplay: string
inputPriceDisplay: string
outputPriceDisplay: string
cacheReadPriceDisplay: string
cacheWritePriceDisplay: string
serviceTierDisplay: string
multiplierDisplay: string
}
export interface UsageLatencyDetails {
upstreamResponseMs?: number
upstreamApiOverheadMs?: number
upstreamEngineMs?: number
admissionDecisionMs?: number
accountSelectionWaitMs?: number
capacityUsedSlots?: number
capacityTotalSlots?: number
transportDecisionWaitMs?: number
wsConnectMs?: number
upstreamHeadersMs?: number
firstEventMs?: number
firstReasoningMs?: number
firstTextMs?: number
openaiProcessingMs?: number
}
// Provider 私有观测字段;Core 字段由顶层 UsageRecord 提供,不再复制进 metadata。
export interface UsageRecordMetadata {
[key: string]: unknown
}
export type UsageRecordStatus = 'success' | 'error' | 'all'
export interface UsageErrorFacts {
errorCode: string | null
errorKind: string | null
websocketCloseCode: number | null
continuationUnavailableReason: string | null
upstreamConnectionExitReason: string | null
recovered: boolean
}
export interface UsageListRecord extends UsageErrorFacts {
logicalOutcome: string
errorMessage: string | null
clientApiKeyName: string | null
id: string
provider: string | null
authenticationKind: string | null
accountId: string | null
accountEmail: string | null
accountName: string | null
accountNotes: string | null
accountPlanType: string | null
accountPlanTypeDisplay: string | null
accountUpstreamPeer: boolean | null
route: string
model: string | null
requestedModel: string | null
upstreamModel: string | null
serviceTier: string | null
clientTransport: string
upstreamTransport: string | null
reasoningEffort: string | null
reasoningPreset: string | null
subagentKind: string | null
compact: boolean
tokenDetails: UsageTokenDetails
billing: UsageBilling | null
latencyDetails: UsageLatencyDetails
firstTokenLatencyMs: number | null
latencyMs: number | null
createdAt: string
createdAtDisplay: string
clientIp: string | null
userAgent: string | null
}
export interface UsageRecord extends UsageErrorFacts {
upstreamError: {
code: string | null
errorType: string | null
message: string | null
param: string | null
closeReason: string | null
lastEventType: string | null
} | null
retryAfterMs: number | null
id: string
requestId: string
clientApiKeyId: string | null
kind: string
provider: string | null
authenticationKind: string | null
accountId: string | null
accountEmail: string | null
accountName: string | null
route: string
model: string | null
requestedModel: string | null
upstreamModel: string | null
serviceTier: string | null
statusCode: number | null
clientTransport: string
upstreamTransport: string | null
protocol: string
httpVersion: string | null
clientStatusCode: number | null
upstreamStatusCode: number | null
websocketPool: { kind: string } | null
imageGenerationRequested: boolean
imageGenerationSucceeded: boolean | null
latencyDetails: UsageLatencyDetails | null
attemptIndex: number | null
attemptCount: number
responseId: string | null
upstreamRequestId: string | null
latencyMs: number | null
inputTokens: number | null
outputTokens: number | null
cachedInputTokens: number | null
cacheWriteInputTokens: number | null
reasoningOutputTokens: number | null
imageInputTokens: number | null
imageOutputTokens: number | null
message: string
metadata: UsageRecordMetadata
createdAt: string
createdAtDisplay: string
clientIp: string | null
userAgent: string | null
reasoningEffort: string | null
reasoningPreset: string | null
compact: boolean | null
requestKind: string | null
subagentKind: string | null
tokenDetails: UsageTokenDetails
billing: UsageBilling | null
costs: UsageCost[]
costCoverage: UsageCostCoverage
firstTokenLatencyMs: number | null
latencyMsDisplay: string
logicalOutcome: string
}
export interface UsageAttempt {
id: string
attemptIndex: number
trigger: string
provider: string
model: string | null
transport: string
sendState: string
outcome: string
downstreamCommitted: boolean
statusCode: number | null
providerErrorCode: string | null
failureClass: string | null
costEstimateStatus: string
estimatedCostAmount: string | null
estimatedCostCurrency: string | null
inputTokens: number | null
outputTokens: number | null
cachedInputTokens: number | null
totalTokens: number | null
firstTokenMs: number | null
latencyMs: number | null
credentialName: string | null
accountId: string | null
accountName: string | null
accountEmail: string | null
authenticationKind: string | null
startedAt: string
completedAt: string | null
}
export type UsageRecordDetail = UsageRecord & {
attempts: UsageAttempt[]
/** 尝试列表是否完整;best-effort 下恒为 false。 */
attemptsComplete: boolean
}
export interface UsageRecordsResponse {
items: UsageListRecord[]
currentPage: number
pageSize: number
total: number
}
export interface UsageSummaryResponse {
analytics: AnalyticsMetadata
totalRequests: string
inputTokens: string
outputTokens: string
cachedInputTokens: string
cacheWriteInputTokens: string
totalTokens: string
averageLatencyMs: string
averageLatencyMsValue: number | null
}
export interface UsageOverviewHealthPoint {
bucket: string
label: string
totalRequests: number
successRequests: number
failedRequests: number
cancelledRequests: number
incompleteRequests: number
callerErrorRequests: number
errorRate: number
}
export interface UsageOverviewHealth {
totalRequests: number
successRequests: number
failedRequests: number
cancelledRequests: number
incompleteRequests: number
callerErrorRequests: number
successRate: number
completionRate: number
requestChangeRate: number | null
successRateChange: number | null
points: UsageOverviewHealthPoint[]
}
export interface UsageOverviewLoad {
averageConcurrency: number
peakConcurrency: number
admissionDecisionP95Ms: number | null
accountSelectionWaitP95Ms: number | null
}
export interface UsageOverviewPerformanceMetrics {
latencyP50Ms: number | null
latencyP95Ms: number | null
latencyP99Ms: number | null
firstTokenP50Ms: number | null
firstTokenP95Ms: number | null
firstTokenP99Ms: number | null
outputThroughputP10: number | null
outputThroughputP50: number | null
outputThroughputP90: number | null
load: UsageOverviewLoad
}
export interface UsageOverviewPerformancePoint extends UsageOverviewPerformanceMetrics {
bucket: string
label: string
}
export interface UsageOverviewPerformance extends UsageOverviewPerformanceMetrics {
points: UsageOverviewPerformancePoint[]
}
export interface UsageOverviewCostPoint {
bucket: string
label: string
inputTokens: number
outputTokens: number
cachedInputTokens: number
totalTokens: number
estimatedCost: string | null
standardCost: string | null
noCacheCost: string | null
cacheSavings: string | null
cachedTokenRate: number
cacheHitRequestRate: number | null
}
export interface UsageOverviewCost {
estimatedCost: string | null
standardCost: string | null
noCacheCost: string | null
cacheSavings: string | null
tierPremium: string | null
costPerRequest: string | null
costPerSuccessfulRequest: string | null
tokensPerRequest: number
cachedTokenRate: number
cacheHitRequestRate: number | null
inputTokens: number
outputTokens: number
cachedInputTokens: number
totalTokens: number
points: UsageOverviewCostPoint[]
coverage: UsageCostCoverage
}
export interface UsageInsightsOverviewResponse {
analytics: AnalyticsMetadata
granularity: string
health: UsageOverviewHealth
performance: UsageOverviewPerformance
cost: UsageOverviewCost
}
export type UsagePerformanceMetric = 'latency' | 'firstToken' | 'throughput' | 'load'
export type UsageCostMetric = 'cost' | 'savings' | 'cache'
export interface UsageMetricSeries<S, P = S> {
summary: S
points: { bucket: string, label: string, requestCount: number, value: P }[]
}
interface UsageLatencyPercentiles {
p50Ms: number | null
p95Ms: number | null
p99Ms: number | null
}
type UsageCostSummary = Pick<UsageOverviewCost, 'estimatedCost' | 'cacheSavings' | 'tierPremium' | 'costPerSuccessfulRequest' | 'coverage'>
interface UsageMetricData {
health: UsageOverviewHealth
latency: UsageMetricSeries<UsageLatencyPercentiles>
firstToken: UsageMetricSeries<UsageLatencyPercentiles>
throughput: UsageMetricSeries<{ p10: number | null, p50: number | null, p90: number | null }>
load: UsageMetricSeries<UsageOverviewLoad>
cost: UsageMetricSeries<UsageCostSummary, { estimatedCost: string | null, noCacheCost: string | null }>
savings: UsageMetricSeries<UsageCostSummary, string | null>
cache: UsageMetricSeries<UsageCostSummary, { inputTokens: number, cachedTokenRate: number, cacheHitRequestRate: number | null }>
}
export type UsageMetricResponse<M extends keyof UsageMetricData> = {
[K in M]: { analytics: AnalyticsMetadata, granularity: string, metric: K, data: UsageMetricData[K] }
}[M]
export interface UsageDiagnosticItem {
key: string
name: string
authenticationKind: string | null
accountPlanType: string | null
accountPlanTypeDisplay: string | null
accountUpstreamPeer: boolean | null
requestCount: number
successCount: number
errorCount: number
errorRate: number
requestShare: number
averageLatencyMs: number | null
latencyP95Ms: number | null
firstTokenP95Ms: number | null
nonCompletionCount: number
nonCompletionRate: number
retryCount: number
retryRate: number
estimatedCost: string | null
attemptCount: number
totalTokens: number
}
export interface UsageDiagnosticsResponse {
analytics: AnalyticsMetadata
dimension: string
items: UsageDiagnosticItem[]
}
// 请求参数类型:仅定义 API 边界的形状,调用方不依赖显式声明。
interface UsageRangeQuery {
startTime: string
endTime: string
provider?: string
}
interface PageQuery {
currentPage: number
pageSize: number
}
type UsagePageQuery = UsageRangeQuery & PageQuery & {
clientApiKeyName?: string
accountName?: string
model?: string
status?: UsageRecordStatus
}
interface UsageDetailQuery {
id: string
}
type UsageDiagnosticsQuery = UsageRangeQuery & { dimension: string, model?: string, statusCode?: number }
type DiagnosticsDownloadParams = { requestId: string } | { errorId: string }
export function getUsageRecords(data: UsagePageQuery, options: RequestOptions = {}) {
return request<UsageRecordsResponse>({
url: '/api/admin/usage/records',
method: 'GET',
params: data,
...options,
})
}
export function getUsageRecordDetail(data: UsageDetailQuery, options: RequestOptions = {}) {
return request<UsageRecordDetail>({
url: '/api/admin/usage/records/detail',
method: 'GET',
params: data,
...options,
})
}
export function getUsageRecordSummary(data: UsageRangeQuery, options: RequestOptions = {}) {
return request<UsageSummaryResponse>({
url: '/api/admin/usage/records/summary',
method: 'GET',
params: data,
...options,
})
}
export function getUsageRecordInsightsOverview(data: UsageRangeQuery, options: RequestOptions = {}) {
return request<UsageInsightsOverviewResponse>({
url: '/api/admin/usage/insights/overview',
method: 'GET',
params: data,
...options,
})
}
export function getUsageRecordInsightsDiagnostics(data: UsageDiagnosticsQuery, options: RequestOptions = {}) {
return request<UsageDiagnosticsResponse>({
url: '/api/admin/usage/insights/diagnostics',
method: 'GET',
params: data,
...options,
})
}
export function getUsageHealth(data: UsageRangeQuery, options: RequestOptions = {}) {
return request<UsageMetricResponse<'health'>>({
url: '/api/admin/usage/insights/health',
method: 'GET',
params: data,
...options,
})
}
export function getUsagePerformance<M extends UsagePerformanceMetric>(data: UsageRangeQuery & { metric: M }, options: RequestOptions = {}) {
return request<UsageMetricResponse<M>>({
url: '/api/admin/usage/insights/performance',
method: 'GET',
params: data,
...options,
})
}
export function getUsageCost<M extends UsageCostMetric>(data: UsageRangeQuery & { metric: M }, options: RequestOptions = {}) {
return request<UsageMetricResponse<M>>({
url: '/api/admin/usage/insights/cost',
method: 'GET',
params: data,
...options,
})
}
export function getDiagnosticsDownloadUrl(data: DiagnosticsDownloadParams) {
return `${API_BASE_URL}/api/admin/diagnostics/export?${new URLSearchParams(data)}`
}