ocr-service/main.py

@@ -20,6 +20,7 @@ import pypdfium2 as pdfium
 from fastapi import FastAPI, Form, Header, HTTPException, UploadFile
 from fastapi.responses import StreamingResponse
 from PIL import Image
+from prometheus_fastapi_instrumentator import Instrumentator
 
 from confidence import apply_confidence_markers, get_threshold
 from spell_check import correct_text, load_spell_checker
@@ -72,6 +73,8 @@ async def lifespan(app: FastAPI):
 
 app = FastAPI(title="Familienarchiv OCR Service", lifespan=lifespan)
 
+Instrumentator(excluded_handlers=["/health", "/metrics"]).instrument(app).expose(app)
+
 
 @app.get("/health")
 def health():

ocr-service/requirements.txt

@@ -10,3 +10,4 @@ pyvips>=2.2.0
 httpx==0.28.1
 pyspellchecker==0.9.0
 opencv-python-headless==4.11.0.86
+prometheus-fastapi-instrumentator==7.0.0

ocr-service/test_metrics.py

@@ -0,0 +1,24 @@
+"""Tests for Prometheus metrics exposed by the OCR service.
+
+Each test that asserts on a counter/gauge value uses a fresh CollectorRegistry
+(see decision #3 on issue #652) to keep the metrics isolated between tests.
+"""
+
+from unittest.mock import patch
+
+import pytest
+from httpx import ASGITransport, AsyncClient
+
+from main import app
+
+
+@pytest.mark.asyncio
+async def test_metrics_endpoint_returns_200():
+    """`GET /metrics` returns 200 with Prometheus exposition content."""
+    with patch("main.kraken_engine.load_models"), \
+         patch("main.load_spell_checker"):
+        async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as client:
+            response = await client.get("/metrics")
+
+    assert response.status_code == 200
+    assert "text/plain" in response.headers.get("content-type", "")