test: Add regression tests and coverage analysis for production bugs

test: Add comprehensive tests for new infrastructure

Fix remaining tests for refactored API

Fix tests to work with refactored API

Phase 4: Extract combat attack calculation to CombatManager

Phase 2: Extract ConversationHistoryManager from GameMaster

Phase 1: Extract RAGRetriever from GameMaster

Fix load_character_with_location testing helper and update tests

Add comprehensive unit tests for Command Pattern implementation

Rename gm_dialogue.py to gm_dialogue_cli.py for clarity

Add inventory persistence test - PASSES ✅

WIP: Shop test improvements + identify inventory persistence bug

Fix combat bugs: round announcements, prompt leakage, duplicates

Update test infrastructure and dependencies

Add comprehensive character creation tests for all classes/races

Fix flaky test: Handle LLM non-determinism in damage extraction

Add RAG-enhanced character creation with SRD data integration

docs: Consolidate documentation and fix flaky test

refactor: Consolidate all RAG source data into organized structure

refactor: Move equipment.txt to proper RAG data directory

fix: Resolve E2E test bugs in combat and character validation

fix: Replace "Goblin Scout" with "Goblin" in tests to reduce brittleness

docs: Move equipment system to DONE.md and organize test files

feat: Add complete equipment system with magic items and class features

fix: Clean up all broken tests in test_party_member_interactions.py

fix: Add spell_level parameter to upcast healing test

docs: Document party member healing system and add tests

feat: Add DM Guide RAG ingestion with comprehensive quality tests

feat: Add level-up system and comprehensive spell manager tests

feat: Add comprehensive spell casting, rest mechanics, and XP system

fix: Revert is_discovered behavior and update test expectations

Fix test_lazy_generation.py: explored locations should be discovered

Move test_steal_detection.py to tests/ directory

Fix all test import errors and upgrade mechanics extraction model

Fix critical bugs: steal mechanics, combat damage, inventory display

fix: Critical encounter cooldown bug preventing NPC deaths in combat

feat: Implement flexible E2E testing system with optional NPC spawning

fix: Add missing pytest fixture for RAG search tests

refactor: Remove duplicate gold tracking - use single source of truth

feat: Implement NPC combat AI and auto-population system

chore: Reorganize test files into tests/ directory

feat: Implement RAG-based racial bonuses for character creation

test: Add comprehensive tests for random stat rolling

feat: Add epic D&D combat simulator

feat: Add comprehensive D&D 5e game state management system

refactor: Reorganize project structure and enhance Gradio app