ocr-service/test_metrics.py

@@ -4,10 +4,11 @@ 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
+from unittest.mock import AsyncMock, patch
 
 import pytest
 from httpx import ASGITransport, AsyncClient
+from PIL import Image
 
 from main import app
 
@@ -22,3 +23,36 @@ async def test_metrics_endpoint_returns_200():
 
     assert response.status_code == 200
     assert "text/plain" in response.headers.get("content-type", "")
+
+
+@pytest.mark.asyncio
+async def test_metrics_includes_http_request_metrics_after_ocr_call():
+    """After a request to /ocr, `/metrics` exposes auto-instrumented http_* metrics."""
+    mock_images = [Image.new("RGB", (100, 100))]
+    mock_blocks = [{"pageNumber": 1, "x": 0.0, "y": 0.0, "width": 1.0, "height": 1.0,
+                    "polygon": None, "text": "hi", "words": []}]
+
+    with patch("main.kraken_engine.load_models"), \
+         patch("main.load_spell_checker"), \
+         patch("main._download_and_convert_pdf", new_callable=AsyncMock, return_value=mock_images), \
+         patch("main.preprocess_page", side_effect=lambda img: img), \
+         patch("main.surya_engine.extract_blocks", return_value=mock_blocks):
+        async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as client:
+            # Models need to be loaded for /ocr to accept requests; force the flag.
+            import main as main_module
+            main_module._models_ready = True
+            try:
+                ocr_response = await client.post("/ocr", json={
+                    "pdfUrl": "http://minio/doc.pdf",
+                    "scriptType": "TYPEWRITER",
+                    "language": "de",
+                })
+                assert ocr_response.status_code == 200, ocr_response.text
+
+                metrics_response = await client.get("/metrics")
+            finally:
+                main_module._models_ready = False
+
+    body = metrics_response.text
+    assert "http_requests_total" in body
+    assert "http_request_duration_seconds" in body