Extract key information from the input while maintaining context and relationships.
Focus on creating MEANINGFUL, CONTEXT-RICH memories that preserve complete understanding.

PRINCIPLES FOR MEMORY EXTRACTION:

1. PRESERVE CONTEXT
- Keep related information together
- Maintain relationships between concepts
- Include relevant background and rationale
- Preserve the complete picture

2. MEANINGFUL GROUPING
Instead of fragmenting like this:
❌ "User likes Python"
❌ "User uses Python for development"
❌ "User prefers Python over JavaScript"

Create cohesive memories like this:
✅ "User is a Python developer who prefers it over JavaScript for development work, particularly valuing its strong typing support and extensive data science libraries"

3. MAINTAIN RELATIONSHIPS
- Keep technical knowledge connected to its domain
- Preserve chronological or causal relationships
- Maintain links between preferences and rationale
- Keep workflow steps connected

4. COMPLETE UNDERSTANDING
- Include enough context to be independently valuable
- Preserve decision rationale and trade-offs
- Maintain connections to broader technical ecosystem
- Keep related preferences and traits together

FOCUS AREAS:

1. TECHNICAL KNOWLEDGE
- Complete technology stacks, not isolated tools
- Full architectural decisions with context
- Comprehensive technical preferences
- Complete workflow patterns

2. PROFESSIONAL CONTEXT
- Complete methodologies and approaches
- Full project organization strategies
- Comprehensive quality standards
- Complete collaboration patterns

3. PREFERENCES & TRAITS
- Complete preference sets with rationale
- Full context for technical choices
- Comprehensive working styles
- Complete learning patterns

4. DOMAIN EXPERTISE
- Complete domain knowledge areas
- Full context of experience
- Comprehensive skill sets
- Complete problem-solving patterns

Remember:
- Group related information meaningfully
- Maintain context and relationships
- Include complete rationale
- Create self-contained, valuable memories
