feat(ocr): add metrics.py factory with test-scoped CollectorRegistry support

Encapsulates every custom OCR metric in an OcrMetrics frozen dataclass and
exposes a `build_metrics(registry)` factory. Production main.py binds against
the default REGISTRY; tests construct a fresh CollectorRegistry per case and
monkeypatch main.metrics, so counter values stay isolated between tests
(decision #3 on issue #652, Option A).

Refs #652

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

ocr-service/test_metrics.py

@@ -9,8 +9,19 @@ from unittest.mock import AsyncMock, patch
 import pytest
 from httpx import ASGITransport, AsyncClient
 from PIL import Image
+from prometheus_client import CollectorRegistry
 
 from main import app
+from metrics import build_metrics
+
+
+@pytest.fixture
+def fresh_metrics(monkeypatch):
+    """Replace the module-level `main.metrics` with one bound to a fresh registry."""
+    registry = CollectorRegistry()
+    test_metrics = build_metrics(registry)
+    monkeypatch.setattr("main.metrics", test_metrics)
+    return test_metrics
 
 
 @pytest.mark.asyncio
@@ -56,3 +67,27 @@ async def test_metrics_includes_http_request_metrics_after_ocr_call():
     body = metrics_response.text
     assert "http_requests_total" in body
     assert "http_request_duration_seconds" in body
+
+
+def test_build_metrics_registers_all_custom_metrics_on_given_registry():
+    """`build_metrics` returns an OcrMetrics bound to the supplied registry."""
+    registry = CollectorRegistry()
+    metrics = build_metrics(registry)
+
+    metric_names = {m.name for m in registry.collect()}
+    expected = {
+        "ocr_jobs",
+        "ocr_pages",
+        "ocr_skipped_pages",
+        "ocr_words",
+        "ocr_illegible_words",
+        "ocr_processing_seconds",
+        "ocr_training_runs",
+        "ocr_model_accuracy",
+        "ocr_models_ready",
+    }
+    assert expected <= metric_names, f"missing: {expected - metric_names}"
+
+    # A second registry yields a separate container — no shared state.
+    other_metrics = build_metrics(CollectorRegistry())
+    assert metrics is not other_metrics