feat: add tests and integrate dots.ocr model

G.2.5 - Tests:
- Add pytest test suite with fixtures
- test_preprocessing.py - PDF/image loading, normalization, validation
- test_postprocessing.py - chunks, QA pairs, markdown generation
- test_inference.py - dummy parser and inference functions
- test_api.py - API endpoint tests
- Add pytest.ini configuration

G.1.3 - dots.ocr Integration:
- Update model_loader.py with real model loading code
  - Support for AutoModelForVision2Seq and AutoProcessor
  - Device handling (CUDA/CPU/MPS) with fallback
  - Error handling with dummy fallback option
- Update inference.py with real model inference
  - Process images through model
  - Generate and decode outputs
  - Parse model output to blocks
- Add model_output_parser.py
  - Parse JSON or plain text model output
  - Convert to structured blocks
  - Layout detection support (placeholder)

Dependencies:
- Add pytest, pytest-asyncio, httpx for testing

services/parser-service/tests/test_api.py

@@ -0,0 +1,109 @@
+"""
+Tests for API endpoints
+"""
+
+import pytest
+from fastapi.testclient import TestClient
+from PIL import Image
+import io
+
+from app.main import app
+
+client = TestClient(app)
+
+
+class TestHealthEndpoint:
+    """Tests for health check endpoint"""
+    
+    def test_health(self):
+        """Test health endpoint"""
+        response = client.get("/health")
+        assert response.status_code == 200
+        data = response.json()
+        assert data["status"] == "healthy"
+        assert data["service"] == "parser-service"
+
+
+class TestParseEndpoint:
+    """Tests for parse endpoint"""
+    
+    def test_parse_no_file(self):
+        """Test parse without file"""
+        response = client.post("/ocr/parse")
+        assert response.status_code == 400
+    
+    def test_parse_image(self):
+        """Test parsing image"""
+        # Create test image
+        img = Image.new('RGB', (800, 600), color='white')
+        buffer = io.BytesIO()
+        img.save(buffer, format='PNG')
+        buffer.seek(0)
+        
+        response = client.post(
+            "/ocr/parse",
+            files={"file": ("test.png", buffer, "image/png")},
+            data={"output_mode": "raw_json"}
+        )
+        
+        assert response.status_code == 200
+        data = response.json()
+        assert "document" in data or "chunks" in data or "markdown" in data
+    
+    def test_parse_chunks_mode(self):
+        """Test parsing in chunks mode"""
+        img = Image.new('RGB', (800, 600), color='white')
+        buffer = io.BytesIO()
+        img.save(buffer, format='PNG')
+        buffer.seek(0)
+        
+        response = client.post(
+            "/ocr/parse",
+            files={"file": ("test.png", buffer, "image/png")},
+            data={"output_mode": "chunks", "dao_id": "test-dao"}
+        )
+        
+        assert response.status_code == 200
+        data = response.json()
+        assert "chunks" in data
+    
+    def test_parse_markdown_mode(self):
+        """Test parsing in markdown mode"""
+        img = Image.new('RGB', (800, 600), color='white')
+        buffer = io.BytesIO()
+        img.save(buffer, format='PNG')
+        buffer.seek(0)
+        
+        response = client.post(
+            "/ocr/parse",
+            files={"file": ("test.png", buffer, "image/png")},
+            data={"output_mode": "markdown"}
+        )
+        
+        assert response.status_code == 200
+        data = response.json()
+        assert "markdown" in data
+
+
+class TestParseChunksEndpoint:
+    """Tests for parse_chunks endpoint"""
+    
+    def test_parse_chunks(self):
+        """Test parse_chunks endpoint"""
+        img = Image.new('RGB', (800, 600), color='white')
+        buffer = io.BytesIO()
+        img.save(buffer, format='PNG')
+        buffer.seek(0)
+        
+        response = client.post(
+            "/ocr/parse_chunks",
+            files={"file": ("test.png", buffer, "image/png")},
+            data={"dao_id": "test-dao"}
+        )
+        
+        assert response.status_code == 200
+        data = response.json()
+        assert "chunks" in data
+        assert "total_chunks" in data
+        assert data["dao_id"] == "test-dao"
+