feat(llvm): Comprehensive LLVM backend improvements by ChatGPT

Major enhancements to LLVM code generation and type handling:

1. String Operations:
   - Added StringBox length fast-path (length/len methods)
   - Converts i8* to handle when needed for len_h call
   - Consistent handle-based string operations

2. Array/Map Fast-paths:
   - ArrayBox: get/set/push/length operations
   - MapBox: get/set/has/size with handle-based keys
   - Optimized paths for common collection operations

3. Field Access:
   - getField/setField implementation with handle conversion
   - Proper i64 handle to pointer conversions

4. NewBox Improvements:
   - StringBox/IntegerBox pass-through optimizations
   - Fallback to env.box.new when type_id unavailable
   - Support for dynamic box creation

5. Documentation:
   - Added ARCHITECTURE.md for overall design
   - Added EXTERNCALL.md for external call specs
   - Added LOWERING_LLVM.md for LLVM lowering rules
   - Added PLUGIN_ABI.md for plugin interface

6. Type System:
   - Added UserBox type registration in nyash_box.toml
   - Consistent handle (i64) representation across system

Results: More robust LLVM code generation with proper type handling

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

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

nyash_box.toml

@@ -32,3 +32,15 @@ returns = { type = "string" }
 
 [FileBox.methods.exists]
 returns = { type = "bool" }
+
+[ArrayBox]
+type_id = 3
+
+[ArrayBox.methods.length]
+returns = { type = "i64" }
+
+[MapBox]
+type_id = 11
+
+[MapBox.methods.size]
+returns = { type = "i64" }