b8c0a73e89
- 5.7: Enhanced structured logging with userId, productId, cacheHit, tokenCount - 5.8: Metrics module (counters + histograms) + /extract/metrics endpoint - 5.9: Grafana dashboard config for extraction-service (Loki queries) - 5.10: Error mapping — sidecar errors → proper HTTP status codes (408, 429, 502, 503) - 5.11: Circuit breaker for Python sidecar (5 failures → 30s OPEN) - 5.12: Graceful degradation — circuit open returns 503, cached results still served - 46 TS tests passing
96 lines
2.8 KiB
JSON
96 lines
2.8 KiB
JSON
{
|
|
"annotations": { "list": [] },
|
|
"editable": true,
|
|
"fiscalYearStartMonth": 0,
|
|
"graphTooltip": 0,
|
|
"id": null,
|
|
"links": [],
|
|
"panels": [
|
|
{
|
|
"title": "Extraction Requests (Loki logs)",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
|
|
"targets": [
|
|
{
|
|
"datasource": { "type": "loki", "uid": "loki" },
|
|
"expr": "count_over_time({container=\"extraction-service\"} |= \"extraction complete\" [5m])",
|
|
"legendFormat": "Extractions / 5m"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Cache Hits vs Misses",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
|
|
"targets": [
|
|
{
|
|
"datasource": { "type": "loki", "uid": "loki" },
|
|
"expr": "count_over_time({container=\"extraction-service\"} |= \"cache hit\" [5m])",
|
|
"legendFormat": "Cache Hits / 5m"
|
|
},
|
|
{
|
|
"datasource": { "type": "loki", "uid": "loki" },
|
|
"expr": "count_over_time({container=\"extraction-service\"} |= \"extraction complete\" |= \"cacheHit\":false [5m])",
|
|
"legendFormat": "Cache Misses / 5m"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Errors",
|
|
"type": "timeseries",
|
|
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
|
|
"targets": [
|
|
{
|
|
"datasource": { "type": "loki", "uid": "loki" },
|
|
"expr": "count_over_time({container=\"extraction-service\"} |= \"error\" [5m])",
|
|
"legendFormat": "Errors / 5m"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Quota Exceeded (429s)",
|
|
"type": "stat",
|
|
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
|
|
"targets": [
|
|
{
|
|
"datasource": { "type": "loki", "uid": "loki" },
|
|
"expr": "count_over_time({container=\"extraction-service\"} |= \"quota exceeded\" [24h])",
|
|
"legendFormat": "429s Today"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Python Sidecar Health",
|
|
"type": "stat",
|
|
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 16 },
|
|
"targets": [
|
|
{
|
|
"datasource": { "type": "loki", "uid": "loki" },
|
|
"expr": "count_over_time({container=\"extraction-service\"} |= \"Sidecar unavailable\" [1h])",
|
|
"legendFormat": "Sidecar Errors (1h)"
|
|
}
|
|
]
|
|
},
|
|
{
|
|
"title": "Extraction Logs",
|
|
"type": "logs",
|
|
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 20 },
|
|
"targets": [
|
|
{
|
|
"datasource": { "type": "loki", "uid": "loki" },
|
|
"expr": "{container=\"extraction-service\"}"
|
|
}
|
|
]
|
|
}
|
|
],
|
|
"schemaVersion": 39,
|
|
"tags": ["extraction", "lysnrai"],
|
|
"templating": { "list": [] },
|
|
"time": { "from": "now-6h", "to": "now" },
|
|
"timepicker": {},
|
|
"timezone": "",
|
|
"title": "Extraction Service",
|
|
"uid": "extraction-service",
|
|
"version": 1
|
|
}
|