mirror of
https://github.com/OpenSquawk/OpenSquawk
synced 2026-07-31 13:55:34 +08:00
7367f7cdb7
Usage tracking: - new UsageEvent collection records every STT/TTS/LLM call per user with provider, model, volume (audio seconds, characters, tokens) and an estimated USD cost; self-hosted providers (Speaches/Piper) and cache hits record at $0 - pricing table for whisper-1, tts-1, gpt-5-nano & co. in server/utils/usage.ts - weekly KPI mail gains an "AI-Nutzung & Kosten" section: weekly and rolling 30-day cost, per-kind breakdown, top 5 users by cost - quota alert mail when rolling 30-day cost exceeds USAGE_ALERT_USD (default $5), at most once per calendar month (UsageAlertDelivery) Hardening: - /api/atc/say now requires an authenticated session (middleware exemption removed); useFlightLabAudio sends the bearer token - /api/service/tools/latency requires auth (was a public LLM endpoint) - per-user rate limits: PTT 20/min, say 60/min, latency 5/min - cron endpoints (waitlist-drip, weekly-kpi-report) require a shared secret via ?secret= or x-cron-secret (CRON_SECRET, falls back to KPI_CRON_SECRET); allowed with a warning while unset so existing deployments keep working - PTT records the actual transcribed audio duration for billing accuracy Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
66 lines
2.3 KiB
TypeScript
66 lines
2.3 KiB
TypeScript
// server/api/llm/latency.get.ts
|
|
import { createError } from 'h3'
|
|
import { getOpenAIClient } from '../../../utils/openai'
|
|
import { getServerRuntimeConfig } from '../../../utils/runtimeConfig'
|
|
import { requireUserSession } from '../../../utils/auth'
|
|
import { enforceRateLimit } from '../../../utils/rateLimit'
|
|
import { recordUsage } from '../../../utils/usage'
|
|
|
|
const SYSTEM_PROMPT =
|
|
'Check if the pilot readback contains ALL of: Frankfurt or EDDF, FL320, and 120.8 MHz. ' +
|
|
'Reply with single digit only: 1 = all present, 0 = one or more missing, 2 = invalid/unrelated.';
|
|
|
|
const READBACK =
|
|
'Lufthanser four seven eight cleared fra via NORDA1A, climb 5000 feet, expect flight level tree too zero, dep 120 decimal 8, squawk 4213.';
|
|
|
|
export default defineEventHandler(async (event) => {
|
|
const user = await requireUserSession(event)
|
|
enforceRateLimit(event, 'tools-latency', String(user._id), 5)
|
|
|
|
const client = getOpenAIClient()
|
|
const { llmModel } = getServerRuntimeConfig()
|
|
const model = llmModel || 'chatgpt-5-nano'
|
|
|
|
const started = Date.now()
|
|
|
|
try {
|
|
const response = await client.chat.completions.create({
|
|
model,
|
|
n: 1,
|
|
messages: [
|
|
{ role: 'system', content: SYSTEM_PROMPT },
|
|
{ role: 'user', content: `${READBACK}` }
|
|
],
|
|
})
|
|
|
|
const raw = response.choices?.[0]?.message?.content?.trim() || ''
|
|
const parsed = Number.parseInt(raw, 10)
|
|
const validResult = Number.isInteger(parsed) && parsed >= 0 && parsed <= 2 ? parsed : null
|
|
const latencyMs = Date.now() - started
|
|
|
|
await recordUsage({
|
|
user: String(user._id),
|
|
kind: 'llm',
|
|
provider: 'openai',
|
|
model,
|
|
endpoint: '/api/service/tools/latency',
|
|
inputTokens: response.usage?.prompt_tokens,
|
|
outputTokens: response.usage?.completion_tokens,
|
|
})
|
|
|
|
return {
|
|
result: validResult,
|
|
raw,
|
|
latency_ms: latencyMs
|
|
}
|
|
} catch (error: any) {
|
|
const latencyMs = Date.now() - started
|
|
console.error('[LLM] Latency check failed:', error)
|
|
throw createError({
|
|
statusCode: error?.status ?? 500,
|
|
statusMessage: error?.message ?? 'Latency check failed',
|
|
data: { latency_ms: latencyMs }
|
|
})
|
|
}
|
|
})
|