Files
aoc/backend/routes/fetch.py
Tomas Kracmar b0198012eb
Some checks failed
CI / lint-and-test (push) Has been cancelled
feat: implement Phase 3 scaling
- Replace skip-based pagination with cursor-based pagination (timestamp|_id cursors)
- Add Prometheus /metrics endpoint with request latency, fetch volume, and error counters
- Implement incremental fetch watermarking per source (watermarks collection in MongoDB)
- Add Graph change notification webhook endpoint (/api/webhooks/graph)
- Add correlation ID middleware for distributed tracing (x-request-id header)
- Update frontend to use cursor-based pagination with Prev/Next navigation
- Update tests for cursor pagination, metrics, webhooks, and watermark mocking
2026-04-14 14:58:50 +02:00

64 lines
2.4 KiB
Python

import time
from auth import require_auth
from database import events_collection
from fastapi import APIRouter, Depends, HTTPException, Query
from graph.audit_logs import fetch_audit_logs
from metrics import track_fetch, track_fetch_duration, track_fetch_error
from models.api import FetchAuditLogsResponse
from models.event_model import normalize_event
from pymongo import UpdateOne
from sources.intune_audit import fetch_intune_audit
from sources.unified_audit import fetch_unified_audit
from watermark import get_watermark, set_watermark
router = APIRouter(dependencies=[Depends(require_auth)])
def run_fetch(hours: int = 168):
from datetime import datetime
window = max(1, min(hours, 720)) # cap to 30 days for sanity
now = datetime.utcnow().isoformat() + "Z"
logs = []
errors = []
def fetch_source(fn, label, source_key):
start_time = time.time()
try:
since = get_watermark(source_key)
result = fn(since=since) if since else fn(hours=window)
set_watermark(source_key, now)
track_fetch(source_key, len(result))
return result
except Exception as exc:
errors.append(f"{label}: {exc}")
track_fetch_error(source_key)
return []
finally:
track_fetch_duration(source_key, time.time() - start_time)
logs.extend(fetch_source(fetch_audit_logs, "Directory audit", "directory"))
logs.extend(fetch_source(fetch_unified_audit, "Unified audit", "unified"))
logs.extend(fetch_source(fetch_intune_audit, "Intune audit", "intune"))
normalized = [normalize_event(e) for e in logs]
if normalized:
ops = []
for doc in normalized:
key = doc.get("dedupe_key")
if key:
ops.append(UpdateOne({"dedupe_key": key}, {"$set": doc}, upsert=True))
else:
ops.append(UpdateOne({"id": doc.get("id"), "timestamp": doc.get("timestamp")}, {"$set": doc}, upsert=True))
events_collection.bulk_write(ops, ordered=False)
return {"stored_events": len(normalized), "errors": errors}
@router.get("/fetch-audit-logs", response_model=FetchAuditLogsResponse)
def fetch_logs(hours: int = Query(default=168, ge=1, le=720)):
try:
return run_fetch(hours=hours)
except Exception as exc:
raise HTTPException(status_code=502, detail=str(exc)) from exc