Add TTFT & ITL Metrics for LLM Inference (#28)

Time-to-First-Token (TTFT) and Inter-Token Latency (ITL) metrics for LLM inference observability Metrics: llm_ttft_seconds, llm_itl_seconds, llm_tokens_total Closes #31 #32 #33 --------- Co-authored-by: poimen <[email protected]> Reviewed-on: #28
2026-09-15 08:53:58 +00:00
parent 30e0a83a50
commit d439536ca9
22 changed files with 2224 additions and 199 deletions
@@ -1,36 +1,20 @@
 #!/bin/bash
-# Example: Send email via notification/sendMsg endpoint
+# Example: Send email via notification service (X-Service routing)

 BASE_URL="${1:-https://api.riotpiao.com}"
-AUTH_TOKEN="${2:-}"  # Optional JWT token if auth required
+AUTH_TOKEN="${2:-}"

-PAYLOAD=$(cat <<'EOF'
-{
-  "format": "smtp",
-  "title": "System Alert",
-  "message": "CPU usage exceeded 90% threshold",
-  "priority": 7,
-  "extras": {
-    "to_email": "[email protected]",
-    "cc": "[email protected]"
-  }
-}
-EOF
-)
-
-if [ -n "$AUTH_TOKEN" ]; then
-  curl -X POST "$BASE_URL" \
-    -H "X-Service: notification" \
-    -H "X-Resource: sendMsg" \
-    -H "Content-Type: application/json" \
-    -H "Authorization: Bearer $AUTH_TOKEN" \
-    -d "$PAYLOAD"
-else
-  curl -X POST "$BASE_URL" \
-    -H "X-Service: notification" \
-    -H "X-Resource: sendMsg" \
-    -H "Content-Type: application/json" \
-    -d "$PAYLOAD"
-fi
+# Send email
+curl -s -X POST "$BASE_URL" \
+  -H "X-Service: notification" \
+  -H "X-Resource: send-email" \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $AUTH_TOKEN" \
+  -d '{
+    "to": "[email protected]",
+    "cc": "[email protected]",
+    "subject": "System Alert",
+    "body": "CPU usage exceeded 90% threshold"
+  }' | jq .

 echo ""