Smart-AI-Memory/empathy-framework

v3.7.0 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 4mo AI Coding Tools

View tool

✓ No known CVEs patched

Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

ai ai-collaboration anthropic anticipatory-ai artificial-intelligence claude-code

+12 more

code-analysis debugging developer-productivity developer-tools developer-tools-monorepo fair-source healthcare-ai large-language-models llm memdocs python testing

Summary

AI summary

XML enhancements deliver up to 35% token reduction and add graceful XML validation with schema support.

Full changelog

🚀 XML-Enhanced Prompting: 15-35% Token Reduction + Graceful Validation

Slash your API costs and eliminate response parsing errors with production-ready XML enhancements.

Key Features

Context Window Optimization ✅

15-35% token reduction depending on compression level
Tag compression: <thinking> → <t>, <answer> → <a>
Whitespace optimization and redundancy elimination
Real-world impact: Integration tests achieved 49.7% reduction
32 comprehensive tests (100% passing)

XML Validation System ✅

Graceful fallback parsing when XML is malformed
Optional XSD schema validation with lxml support
Schema caching for performance optimization
Strict/non-strict modes for flexible error handling
25 comprehensive tests (100% passing)

Workflow Migration Guide 📚

XMLAgent/XMLTask patterns with before/after examples
Configuration options via config.xml.use_xml_structure
Benefits: 40-60% fewer misinterpretations, 20-30% fewer retries

Test Coverage

229 new tests (86 XML enhancement + 143 robustness)
100% passing - production ready
4/4 integration tests passed

Quick Start

from empathy_os.optimization import ContextOptimizer, CompressionLevel
from empathy_os.validation import validate_xml_response

# Optimize prompts
optimizer = ContextOptimizer(CompressionLevel.MODERATE)
optimized = optimizer.optimize(your_xml_prompt)

# Validate responses
result = validate_xml_response(llm_response)

See CHANGELOG.md for full details.

Full Changelog: https://github.com/Smart-AI-Memory/empathy-framework/compare/v3.6.0...v3.7.0

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track Smart-AI-Memory/empathy-framework

Get notified when new releases ship.

About Smart-AI-Memory/empathy-framework

Five-level AI collaboration system with persistent memory and anticipatory capabilities. MCP-native integration for Claude and other LLMs with local-first architecture via MemDocs.

All releases →