Admin Bot e5a1f052a4 feat: add TTFT/ITL metrics for LLM inference ...

- RecordTTFT: Time-to-First-Token in milliseconds
- RecordITL: Inter-Token Latency in milliseconds
- RecordTokenCount: Track total tokens generated
- Prometheus exporter for /metrics endpoint
- Grafana dashboard ConfigMap (llm-metrics.json)
- ResponseWriterWrapper to capture metrics during LLM calls
- Metrics exported: llm_ttft_seconds, llm_itl_seconds, llm_tokens_total

2026-09-15 15:14:13 +09:00

..

exporter.go

feat: phase 8 serviceadapter crd rollout (32/33 tasks)

2026-08-26 13:47:36 -07:00

handler.go

feat: add TTFT/ITL metrics for LLM inference

2026-09-15 15:14:13 +09:00

metrics_test.go

feat: phase 8 serviceadapter crd rollout (32/33 tasks)

2026-08-26 13:47:36 -07:00

metrics.go

feat: add TTFT/ITL metrics for LLM inference

2026-09-15 15:14:13 +09:00

prometheus.go

feat: add TTFT/ITL metrics for LLM inference

2026-09-15 15:14:13 +09:00