Deduplicate and refocus documentation

Restructured README.md and AGENTS.md to eliminate duplication:

README.md (user-focused):
- Simplified to focus on project description and usage
- Quick start guide with installation steps
- API usage examples with curl commands
- Open WebUI integration guide
- Troubleshooting section
- Deployment recommendations
- Removed internal architectural details

AGENTS.md (LLM agent instructions):
- Retained detailed architectural decisions and rationale
- FastAPI best practices and patterns
- Development guidelines and code structure
- Documentation references for frameworks
- Testing strategy and coverage details
- Updated test coverage: 78.95% (95 tests)
- Common implementation patterns

Changes:
- README.md: Streamlined from 497 to 310 lines
- AGENTS.md: Updated test coverage numbers
- Clear separation: README for users, AGENTS for AI developers

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

AGENTS.md

@@ -201,10 +201,11 @@ Agent Interface (lorem-tester, tatlock)
     - OpenAI-compatible error format
     - Error triggers in lorem-tester for testing
   - ✅ **Testing Infrastructure**:
-    - 75 tests (78.95% coverage)
+    - 95 tests (78.95% coverage)
     - Unit tests for all components
     - Integration tests for API endpoints
     - Streaming tests for SSE functionality
+    - Main application and wrapper tests
 
 ## FastAPI Best Practices
 
@@ -402,12 +403,14 @@ app = create_application()
 - 🚧 Implement rate limiting for API endpoints (future)
 - 🚧 Add authentication/API keys (future)
 
-### Testing (Current Coverage: 62%)
+### Testing (Current Coverage: 78.95%, 95 tests)
 - ✅ Integration tests for API endpoints
 - ✅ Streaming functionality with 20s timeout protection
 - ✅ Async test support with pytest-asyncio
 - ✅ Validate OpenAI API compatibility
 - ✅ Mock responses for all endpoints
+- ✅ Main application tests (CORS, exception handlers, lifespan)
+- ✅ Chat streaming wrapper tests
 - 🚧 Future: Mock Ollama responses when integrated
 
 ### Configuration