Update changelog and fix test dependencies for bedrock utils

Author: Bob Strahan

CHANGELOG.md

@@ -16,6 +16,19 @@ SPDX-License-Identifier: MIT-0
   - **Automatic Integration**: Integrates with evaluation service when ground truth and predicted sections are available
   - **Documentation**: Guide in `lib/idp_common_pkg/idp_common/evaluation/README.md` with usage examples, metric explanations, and best practices
 
+- **Caching improvements to Agentic Extraction Service**
+  - Optimized prompt caching by caching document context (text/images) on first LLM call, reducing token costs and quota consumption
+
+- **Enhanced Bedrock Retry Logic for Agentic Extraction**
+  - New `bedrock_utils.py` module with exponential backoff and comprehensive error handling
+  - Improves agentic extraction reliability for transient failures and rate limiting
+
+- **Review Agent Model Configuration**
+  - Added `review_agent_model` parameter to enable separate model for reviewing extraction work
+  - Defaults to main extraction model if not specified
+  - Configurable through Web UI extraction settings
+
+
 ### Fixed
 
 - **Evaluation Output URI Fields Lost Across All Patterns - causing (a) missing Page Text Confidence content in UI, (2) failed Assessment step when reprocessing document after editing classes (No module named 'fitz')**
@@ -29,6 +42,10 @@ SPDX-License-Identifier: MIT-0
 - **UI: Estimated Cost Panel Arrow Misalignment**
   - Fixed expand/contract arrow displaying above "Estimated Cost" heading
 
+- **Agentic Extraction Reliability Improvements**
+  - Updated Pydantic model serialization to use `model_dump(mode="json")` for proper JSON handling
+  - Resolved linting issues and improved code quality across extraction modules
+
 ### Templates
    - us-west-2: `https://s3.us-west-2.amazonaws.com/aws-ml-blog-us-west-2/artifacts/genai-idp/idp-main_0.4.5.yaml`
    - us-east-1: `https://s3.us-east-1.amazonaws.com/aws-ml-blog-us-east-1/artifacts/genai-idp/idp-main_0.4.5.yaml`

lib/idp_common_pkg/pyproject.toml

@@ -142,6 +142,7 @@ test = [
   "ruff>=0.14.0",
   "deepdiff>=6.0.0",                    # Required for BDA blueprint service tests
   "datamodel-code-generator>=0.25.0",   # Required for schema/pydantic generator tests
+  "mypy-boto3-bedrock-runtime>=1.39.0", # Required for bedrock_utils tests
   # Evaluation module dependencies (from evaluation group)
   "stickler-eval==0.1.3",
   "genson==1.3.0",

memory-bank/activeContext.md

@@ -2,13 +2,42 @@
 
 ## Current Task Status
 
-**ProcessChanges Resolver Fix & Agent Analytics Optimization**: ✅ **COMPLETED** - 2-Phase Schema Knowledge Optimization
+**Test Suite Dependency Fix**: ✅ **COMPLETED** - Fixed Missing Type Stubs Dependency
 
 **Previous Tasks**: 
+- ✅ **COMPLETED** - ProcessChanges Resolver Fix & Agent Analytics Optimization
 - ✅ **COMPLETED** - Section Edit Mode Performance Optimization  
 - ✅ **COMPLETED** - IDP CLI Dependency Security Updates
 - ✅ **COMPLETED** - Service Principal GovCloud Compatibility Updates
 
+## Test Suite Dependency Fix
+
+Successfully resolved test collection failure caused by missing type stubs dependency for Bedrock Runtime client.
+
+### Issue Identified
+- **Error**: `ModuleNotFoundError: No module named 'mypy_boto3_bedrock_runtime'` during test collection
+- **Location**: `lib/idp_common_pkg/idp_common/utils/bedrock_utils.py`
+- **Root Cause**: Type stubs dependency was only in `agentic-extraction` optional dependencies, not in `test` dependencies
+
+### Solution Implemented
+- **Added Dependency**: `mypy-boto3-bedrock-runtime>=1.39.0` to test dependencies in `pyproject.toml`
+- **File Modified**: `lib/idp_common_pkg/pyproject.toml`
+- **Rationale**: The `bedrock_utils.py` module imports `mypy_boto3_bedrock_runtime` for type hints on BedrockRuntimeClient, and these type stubs are required for the `test_bedrock_utils.py` unit tests to import and run
+
+### Test Results
+- **idp_common_pkg**: ✅ 428 passed, 20 skipped
+- **idp_cli**: ✅ 61 passed
+- **Total Time**: ~8.44 seconds
+- **Status**: All tests passing successfully
+
+### Technical Details
+The type stubs package `mypy-boto3-bedrock-runtime` provides type information for boto3's bedrock-runtime client, enabling:
+1. Better IDE autocomplete and type checking
+2. Type-safe wrapper class implementation in `BedrockClientWrapper`
+3. Proper type hints for invoke_model, converse, and converse_stream methods
+
+This dependency was already present in `agentic-extraction` dependencies but was missing from the `test` group, causing test collection to fail when importing the module.
+
 ## ProcessChanges Resolver Fix & Agent Analytics Optimization Overview
 
 Successfully implemented comprehensive optimization techniques using a **2-phase schema knowledge approach** to dramatically improve agent analytics performance and resolve resolver failures: