Backend counterpart to the Python engine's semantic router.
- POST /api/decision/route: service-secret-guarded endpoint the Python
backend calls on regex-miss. Calls gpt-5-mini (ROUTER_LLM_MODEL),
validates the chosen id against the candidate set, and writes both a
UsageEvent (central cost ledger) and a routing-review record — including
timeouts, with timeoutMs + actual latencyMs — so the budget can be tuned
- LlmRoutingDecision model + GET /api/admin/llm-routing (paginated,
status-filtered, per-status counts)
- admin "LLM Routing" tab: transcript vs expected phrase, candidate chips
with the chosen one highlighted, latency/budget chip, model reason
- serviceAuth util (mirrors CRON_SECRET pattern)
- .env.example: ROUTER_LLM_MODEL, SERVICE_SECRET
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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>
- Add collapsible sidebar with phase stepper (jump between phases)
- Add SimBridge conditions panel in sidebar (live values, progress bars, targets)
- Add global progress bar (top edge, glowing) + phase-local TTS progress bar
- Add skip button to skip TTS speech while ATC is speaking
- Add skipSpeech() to audio composable (stops current Pizzicato sound)
- Wire up bridge data.post.ts with user auth (JWT) + example payload
- Add server-side telemetry store with pub/sub for Bridge→WS relay
- Extend WS handler with subscribe-telemetry message + userId tracking
- Extend sync composable with subscribeTelemetry() + onTelemetry() callback
- Add require-auth middleware to all flightlab pages
- Fix instructor station ECONNREFUSED via import.meta.client guard
- Add animations: phase transitions, button lists, fade-scale, check-pop, pulse
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
chore: Optimize the input data sent to the OpenAI API to reduce token usage and improve decision quality. Add quick responses for common pilot utterances like radio checks and emergencies to avoid unnecessary LLM calls.
The key changes are:
- Use a smaller LLM model (`gpt-5-nano`) to reduce token usage
- Optimize the input data by only sending relevant candidate and context information
- Implement quick responses for common pilot utterances like radio checks and emergencies
- Ensure ATC responses are only included when necessary to reduce token usage
