All make command tests pass

Author: kazmer97

.python-version

@@ -0,0 +1 @@
+3.12

idp_cli/tests/test_progress_monitor.py

@@ -28,6 +28,7 @@ def test_init_success(self, mock_boto_client):
         assert monitor.stack_name == "test-stack"
         assert monitor.lookup_function == "test-lookup-function"
 
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     def test_init_missing_lookup_function(self):
         """Test initialization fails without LookupFunctionName"""
         resources = {}

idp_cli/tests/test_rerun_processor.py

@@ -11,8 +11,10 @@
 class TestRerunProcessor:
     """Test rerun processing functionality"""
 
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     @patch("idp_cli.stack_info.StackInfo")
     @patch("boto3.client")
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     def test_init_success(self, mock_boto_client, mock_stack_info_class):
         """Test successful initialization"""
         from idp_cli.rerun_processor import RerunProcessor
@@ -31,8 +33,10 @@ def test_init_success(self, mock_boto_client, mock_stack_info_class):
         assert processor.stack_name == "test-stack"
         assert processor.resources["DocumentQueue"] is not None
 
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     @patch("idp_cli.stack_info.StackInfo")
     @patch("boto3.client")
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     def test_prepare_for_classification_rerun(
         self, mock_boto_client, mock_stack_info_class
     ):
@@ -85,6 +89,7 @@ def test_prepare_for_classification_rerun(
         assert result.status == Status.QUEUED
         assert result.start_time is None
 
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     @patch("idp_cli.stack_info.StackInfo")
     @patch("boto3.client")
     def test_prepare_for_extraction_rerun(
@@ -141,6 +146,7 @@ def test_prepare_for_extraction_rerun(
         # Verify status reset
         assert result.status == Status.QUEUED
 
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     @patch("idp_cli.stack_info.StackInfo")
     @patch("boto3.client")
     def test_send_to_queue(self, mock_boto_client, mock_stack_info_class):
@@ -176,6 +182,7 @@ def test_send_to_queue(self, mock_boto_client, mock_stack_info_class):
         )
         assert "test-doc" in call_args[1]["MessageBody"]
 
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     @patch("idp_cli.stack_info.StackInfo")
     @patch("idp_cli.rerun_processor.RerunProcessor._get_document")
     @patch("idp_cli.rerun_processor.RerunProcessor._send_to_queue")
@@ -225,6 +232,7 @@ def test_rerun_documents_classification(
         # Verify send_to_queue was called
         mock_send_to_queue.assert_called_once()
 
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     @patch("idp_cli.stack_info.StackInfo")
     @patch("idp_cli.rerun_processor.RerunProcessor._get_document")
     @patch("boto3.client")
@@ -257,6 +265,7 @@ def test_rerun_documents_document_not_found(
         assert len(results["failed_documents"]) == 1
         assert results["failed_documents"][0]["object_key"] == "missing-doc"
 
+    @patch.dict("os.environ", {"AWS_DEFAULT_REGION": "us-east-1"})
     @patch("idp_cli.stack_info.StackInfo")
     @patch("idp_cli.batch_processor.BatchProcessor")
     @patch("boto3.client")

lib/idp_common_pkg/idp_common/classification/service.py

@@ -224,17 +224,12 @@ def _limit_pages_for_classification(self, document: Document) -> Document:
         Returns:
             Document with limited pages for classification
         """
-        if self.max_pages_for_classification == "ALL":
+        # 0 or negative means ALL pages
+        if self.max_pages_for_classification <= 0:
             return document
 
+        max_pages = self.max_pages_for_classification
         try:
-            max_pages = int(self.max_pages_for_classification)
-            if max_pages <= 0:
-                logger.warning(
-                    f"Invalid maxPagesForClassification value: {max_pages}, using ALL pages"
-                )
-                return document
-
             if len(document.pages) <= max_pages:
                 return document
 
@@ -1557,7 +1552,8 @@ def classify_document(self, document: Document) -> Document:
             return document
 
         # Check for limited page classification
-        if self.max_pages_for_classification != "ALL":
+        # 0 or negative means ALL pages
+        if self.max_pages_for_classification > 0:
             logger.info(
                 f"Using limited page classification: {self.max_pages_for_classification} pages"
             )

lib/idp_common_pkg/idp_common/config/models.py

@@ -43,8 +43,14 @@ def parse_dimensions(cls, v: Any) -> Optional[int]:
         if v is None or (isinstance(v, str) and not v.strip()):
             return None
         if isinstance(v, str):
-            return int(v) if v else None
-        return int(v)
+            try:
+                return int(v) if v else None
+            except ValueError:
+                return None  # Invalid value, return None
+        try:
+            return int(v)
+        except (ValueError, TypeError):
+            return None
 
     @field_validator("dpi", mode="before")
     @classmethod
@@ -132,8 +138,9 @@ class ClassificationConfig(BaseModel):
     top_p: float = Field(default=0.1, ge=0.0, le=1.0)
     top_k: float = Field(default=5.0, ge=0.0)
     max_tokens: int = Field(default=4096, gt=0)
-    maxPagesForClassification: Union[int, str] = Field(
-        default=1, description="Max pages to use for classification (int or 'ALL')"
+    maxPagesForClassification: int = Field(
+        default=0,
+        description="Max pages to use for classification. 0 or negative = ALL pages, positive = limit to N pages",
     )
     classificationMethod: str = Field(default="multimodalPageLevelClassification")
     image: ImageConfig = Field(default_factory=ImageConfig)
@@ -156,12 +163,12 @@ def parse_int(cls, v: Any) -> int:
 
     @field_validator("maxPagesForClassification", mode="before")
     @classmethod
-    def parse_max_pages(cls, v: Any) -> Union[int, str]:
-        """Parse maxPagesForClassification - can be int or 'ALL'"""
+    def parse_max_pages(cls, v: Any) -> int:
+        """Parse maxPagesForClassification - can be int or 'ALL' string (converted to 0)"""
         if isinstance(v, str):
             if v.upper() == "ALL":
-                return "ALL"
-            return int(v) if v else 1
+                return 0  # 0 means ALL pages
+            return int(v) if v else 0
         return int(v)
 
 
@@ -226,7 +233,7 @@ def parse_int(cls, v: Any) -> int:
 class SummarizationConfig(BaseModel):
     """Document summarization configuration"""
 
-    enabled: bool = Field(default=False, description="Enable summarization")
+    enabled: bool = Field(default=True, description="Enable summarization")
     model: str = Field(
         default="us.amazon.nova-premier-v1:0",
         description="Bedrock model ID for summarization",

lib/idp_common_pkg/idp_common/extraction/service.py

@@ -14,7 +14,7 @@
 import logging
 import os
 import time
-from typing import Any, Dict, List, Optional, Type
+from typing import Any, Dict, List, Union
 
 from idp_common import bedrock, image, metrics, s3, utils
 from idp_common.config.models import IDPConfig
@@ -24,16 +24,14 @@
     X_AWS_IDP_DOCUMENT_TYPE,
 )
 from idp_common.models import Document
-from idp_common.schema import create_pydantic_model_from_json_schema
 from idp_common.utils.few_shot_example_builder import (
     build_few_shot_extraction_examples_content,
 )
 
 # Conditional import for agentic extraction (requires Python 3.10+ dependencies)
 try:
-    from pydantic import BaseModel, Field, create_model
-
     from idp_common.extraction.agentic_idp import structured_output
+    from idp_common.schema import create_pydantic_model_from_json_schema
 
     AGENTIC_AVAILABLE = True
 except ImportError:

lib/idp_common_pkg/tests/integration/test_discovery_config_integration.py

@@ -43,10 +43,14 @@ def setUp(self):
   output_format:
     sample_json: |
       {
-        "document_class": "TestForm",
-        "document_description": "Test form description",
-        "groups": []
-      }
+                                        "$schema": "http://json-schema.org/draft-07/schema#",
+                                        "$id": "testform",
+                                        "type": "object",
+                                        "title": "TestForm",
+                                        "description": "Test form description",
+                                        "x-aws-idp-document-type": "TestForm",
+                                        "properties": {}
+                                    }
 """
 
         self.config_dict = yaml.safe_load(self.yaml_config)

lib/idp_common_pkg/tests/unit/assessment/test_assessment_enabled_property.py

@@ -99,11 +99,17 @@ def test_assessment_enabled_true(self):
 
             # Mock Bedrock response
             mock_invoke_model.return_value = {
-                "content": [
-                    {
-                        "text": '{"invoice_number": {"confidence": 0.95, "confidence_reason": "Clear text"}}'
+                "response": {
+                    "output": {
+                        "message": {
+                            "content": [
+                                {
+                                    "text": '{"invoice_number": {"confidence": 0.95, "confidence_reason": "Clear text"}}'
+                                }
+                            ]
+                        }
                     }
-                ],
+                },
                 "metering": {
                     "inputTokens": 1000,
                     "outputTokens": 200,
@@ -225,11 +231,17 @@ def test_assessment_enabled_string_true(self):
 
             # Mock Bedrock response
             mock_invoke_model.return_value = {
-                "content": [
-                    {
-                        "text": '{"invoice_number": {"confidence": 0.95, "confidence_reason": "Clear text"}}'
+                "response": {
+                    "output": {
+                        "message": {
+                            "content": [
+                                {
+                                    "text": '{"invoice_number": {"confidence": 0.95, "confidence_reason": "Clear text"}}'
+                                }
+                            ]
+                        }
                     }
-                ],
+                },
                 "metering": {
                     "inputTokens": 1000,
                     "outputTokens": 200,
@@ -242,7 +254,7 @@ def test_assessment_enabled_string_true(self):
                 self.document, self.section_id
             )
 
-            # Verify the service processed normally
+            # Verify the service processed normally (defaults to enabled)
             self.assertIsNotNone(result_document)
             mock_invoke_model.assert_called_once()
             mock_write_content.assert_called_once()
@@ -302,11 +314,17 @@ def test_assessment_missing_config_section(self):
 
             # Mock Bedrock response
             mock_invoke_model.return_value = {
-                "content": [
-                    {
-                        "text": '{"invoice_number": {"confidence": 0.95, "confidence_reason": "Clear text"}}'
+                "response": {
+                    "output": {
+                        "message": {
+                            "content": [
+                                {
+                                    "text": '{"invoice_number": {"confidence": 0.95, "confidence_reason": "Clear text"}}'
+                                }
+                            ]
+                        }
                     }
-                ],
+                },
                 "metering": {
                     "inputTokens": 1000,
                     "outputTokens": 200,

lib/idp_common_pkg/tests/unit/assessment/test_assessment_service.py

@@ -188,7 +188,9 @@ def test_init(self, mock_config):
         service = AssessmentService(region="us-west-2", config=mock_config)
 
         assert service.region == "us-west-2"
-        assert service.config == mock_config
+        # Config is converted to IDPConfig model, verify it has the expected structure
+        assert hasattr(service.config, "assessment")
+        assert service.config.assessment.model == mock_config["assessment"]["model"]
 
     def test_get_class_schema(self, service):
         """Test getting schema for a document class."""

lib/idp_common_pkg/tests/unit/bda/test_bda_blueprint_service.py

@@ -259,10 +259,10 @@ def test_create_blueprints_from_custom_configuration_partial_failure(
         self, service, mock_custom_configuration
     ):
         """Test handling when one blueprint succeeds and another fails."""
-        # Mock configuration retrieval
-        service.config_manager.get_configuration.return_value = (
-            mock_custom_configuration
-        )
+        # Mock configuration retrieval - wrap dict in object with classes attribute
+        config_obj = MagicMock()
+        config_obj.classes = mock_custom_configuration["classes"]
+        service.config_manager.get_configuration.return_value = config_obj
 
         # Mock first blueprint creation success, second failure
         success_response = {