@shakudo/kaji-setup-external 1.0.0

package/assets/skills/context-optimization/skills/context-optimization/scripts/compaction.py

@@ -0,0 +1,379 @@
+"""
+Context Optimization Utilities
+
+This module provides utilities for context compaction, observation masking, and budget management.
+
+PRODUCTION NOTES:
+- Token estimation uses simplified heuristics (~4 chars/token for English).
+  Production systems should use model-specific tokenizers:
+  - OpenAI: tiktoken library
+  - Anthropic: anthropic tokenizer
+  - Local models: HuggingFace tokenizers
+  
+- Summarization functions use simple heuristics for demonstration.
+  Production systems should use:
+  - LLM-based summarization for high-quality compression
+  - Domain-specific summarization models
+  - Schema-based summarization for structured outputs
+  
+- Cache metrics are illustrative. Production systems should integrate
+  with actual inference infrastructure metrics.
+"""
+
+from typing import List, Dict
+import hashlib
+import time
+
+
+def estimate_token_count(text: str) -> int:
+    """
+    Estimate token count for text.
+    
+    Uses approximation: ~4 characters per token for English.
+    
+    WARNING: This is a rough estimate. Actual tokenization varies by:
+    - Model (GPT-5.2, Claude 4.5, Gemini 3 have different tokenizers)
+    - Content type (code typically has higher token density)
+    - Language (non-English may have 2-3x higher token/char ratio)
+    
+    Production usage:
+        import tiktoken
+        enc = tiktoken.encoding_for_model("gpt-4")  # Use appropriate model
+        token_count = len(enc.encode(text))
+    """
+    return len(text) // 4
+
+
+def estimate_message_tokens(messages: list) -> int:
+    """Estimate token count for message list."""
+    total = 0
+    for msg in messages:
+        # Count content
+        content = msg.get("content", "")
+        total += estimate_token_count(content)
+        
+        # Add overhead for role/formatting
+        total += 10
+    
+    return total
+
+
+# Compaction Functions
+
+def categorize_messages(messages: list) -> dict:
+    """
+    Categorize messages for selective compaction.
+    
+    Returns dict mapping category to messages.
+    """
+    categories = {
+        "system_prompt": [],
+        "tool_definition": [],
+        "tool_output": [],
+        "conversation": [],
+        "retrieved_document": [],
+        "other": []
+    }
+    
+    for msg in messages:
+        role = msg.get("role", "user")
+        content = msg.get("content", "")
+        
+        if role == "system":
+            categories["system_prompt"].append({**msg, "category": "system_prompt"})
+        elif "tool_use" in msg.get("type", ""):
+            categories["tool_output"].append({**msg, "category": "tool_output"})
+        elif role == "user":
+            categories["conversation"].append({**msg, "category": "conversation"})
+        elif "retrieved" in msg.get("tags", []):
+            categories["retrieved_document"].append({**msg, "category": "retrieved_document"})
+        else:
+            categories["other"].append({**msg, "category": "other"})
+    
+    return categories
+
+
+def summarize_content(content: str, category: str, max_length: int = 500) -> str:
+    """
+    Summarize content for compaction.
+    
+    Different summarization for different categories.
+    """
+    if category == "tool_output":
+        return summarize_tool_output(content, max_length)
+    elif category == "conversation":
+        return summarize_conversation(content, max_length)
+    elif category == "retrieved_document":
+        return summarize_document(content, max_length)
+    else:
+        return summarize_general(content, max_length)
+
+
+def summarize_tool_output(content: str, max_length: int = 500) -> str:
+    """Summarize tool output."""
+    # Extract key metrics and findings
+    import re
+    
+    # Look for metrics (numbers with context)
+    metrics = re.findall(r'(\w+):\s*([\d.,]+)', content)
+    
+    # Look for key findings (lines with important keywords)
+    keywords = ["result", "found", "total", "success", "error", "value"]
+    findings = []
+    for line in content.split('\n'):
+        if any(kw in line.lower() for kw in keywords):
+            findings.append(line.strip())
+    
+    summary_parts = []
+    if metrics:
+        summary_parts.append(f"Metrics: {', '.join([f'{k}={v}' for k, v in metrics])}")
+    if findings:
+        summary_parts.append("Key findings: " + "; ".join(findings[:3]))
+    
+    result = " | ".join(summary_parts) if summary_parts else "[Tool output summarized]"
+    return result[:max_length]
+
+
+def summarize_conversation(content: str, max_length: int = 500) -> str:
+    """Summarize conversational content."""
+    # Identify key decisions and questions
+    import re
+    
+    decisions = re.findall(r'(?i)(?:decided|decision|chose|chosen)[:\s]+([^.]+)', content)
+    questions = re.findall(r'(?:\?|question)[:\s]+([^.]+)', content)
+    
+    summary_parts = []
+    if decisions:
+        summary_parts.append(f"Decisions: {len(decisions)} made")
+    if questions:
+        summary_parts.append(f"Questions: {len(questions)} raised")
+    
+    result = " | ".join(summary_parts) if summary_parts else "[Conversation summarized]"
+    return result[:max_length]
+
+
+def summarize_document(content: str, max_length: int = 500) -> str:
+    """Summarize document content."""
+    # Extract first paragraph as summary
+    paragraphs = content.split('\n\n')
+    if paragraphs:
+        first_para = paragraphs[0].strip()
+        # Truncate to first few sentences
+        sentences = first_para.split('. ')
+        if len(sentences) > 2:
+            first_para = '. '.join(sentences[:2]) + '.'
+        return first_para[:max_length]
+    return "[Document summarized]"
+
+
+def summarize_general(content: str, max_length: int = 500) -> str:
+    """General purpose summarization."""
+    return content[:max_length] + "..." if len(content) > max_length else content
+
+
+# Observation Masking
+
+class ObservationStore:
+    def __init__(self, max_size=1000):
+        self.observations = {}
+        self.order = []
+        self.max_size = max_size
+    
+    def store(self, content: str, metadata: dict = None) -> str:
+        """Store observation and return reference ID."""
+        ref_id = self._generate_ref_id(content)
+        
+        self.observations[ref_id] = {
+            "content": content,
+            "metadata": metadata or {},
+            "stored_at": time.time(),
+            "last_accessed": time.time()
+        }
+        self.order.append(ref_id)
+        
+        # Evict oldest if over limit
+        if len(self.order) > self.max_size:
+            oldest = self.order.pop(0)
+            del self.observations[oldest]
+        
+        return ref_id
+    
+    def retrieve(self, ref_id: str) -> str:
+        """Retrieve observation by reference ID."""
+        if ref_id in self.observations:
+            self.observations[ref_id]["last_accessed"] = time.time()
+            return self.observations[ref_id]["content"]
+        return None
+    
+    def mask(self, content: str, max_length: int = 200) -> tuple:
+        """
+        Mask observation if longer than max_length.
+        
+        Returns (masked_content, stored_ref_id_or_None).
+        """
+        if len(content) <= max_length:
+            return content, None
+        
+        ref_id = self.store(content)
+        
+        # Extract key point for reference
+        key_point = self._extract_key_point(content)
+        
+        masked = f"[Obs:{ref_id} elided. Key: {key_point}. Full content retrievable.]"
+        return masked, ref_id
+    
+    def _generate_ref_id(self, content: str) -> str:
+        """Generate unique reference ID."""
+        hash_input = f"{content[:100]}{time.time()}"
+        return hashlib.md5(hash_input.encode()).hexdigest()[:8]
+    
+    def _extract_key_point(self, content: str) -> str:
+        """Extract key point from observation."""
+        # First substantial line or sentence
+        lines = [l for l in content.split('\n') if len(l) > 20]
+        if lines:
+            return lines[0][:50] + "..."
+        sentences = content.split('. ')
+        if sentences:
+            return sentences[0][:50] + "..."
+        return content[:50] + "..."
+
+
+# Context Budget Management
+
+class ContextBudget:
+    def __init__(self, total_limit: int):
+        self.total_limit = total_limit
+        self.allocated = {
+            "system_prompt": 0,
+            "tool_definitions": 0,
+            "retrieved_docs": 0,
+            "message_history": 0,
+            "tool_outputs": 0,
+            "other": 0
+        }
+        self.reserved = 5000  # Reserved buffer
+        self.reservation_limit = total_limit - self.reserved
+    
+    def allocate(self, category: str, amount: int) -> bool:
+        """Allocate budget to category. Returns success status."""
+        if category not in self.allocated:
+            category = "other"
+        
+        current = sum(self.allocated.values())
+        proposed = current + amount
+        
+        if proposed > self.reservation_limit:
+            return False
+        
+        self.allocated[category] += amount
+        return True
+    
+    def remaining(self) -> int:
+        """Get remaining unallocated budget."""
+        current = sum(self.allocated.values())
+        return self.reservation_limit - current
+    
+    def get_usage(self) -> dict:
+        """Get current usage breakdown."""
+        total = sum(self.allocated.values())
+        return {
+            "total_used": total,
+            "total_limit": self.total_limit,
+            "remaining": self.remaining(),
+            "by_category": dict(self.allocated),
+            "utilization_ratio": total / self.total_limit
+        }
+    
+    def should_optimize(self, current_usage: int, metrics: dict = None) -> tuple:
+        """
+        Determine if optimization should trigger.
+        
+        Returns (should_optimize, reasons).
+        """
+        reasons = []
+        
+        # Check utilization
+        utilization = current_usage / self.total_limit
+        if utilization > 0.8:
+            reasons.append(("high_utilization", utilization))
+        
+        # Check degradation metrics if provided
+        if metrics:
+            if metrics.get("attention_degradation", 0) > 0.3:
+                reasons.append(("attention_degradation", True))
+            
+            if metrics.get("quality_score", 1.0) < 0.8:
+                reasons.append(("quality_degradation", True))
+        
+        should_optimize = len(reasons) > 0
+        return should_optimize, reasons
+
+
+# Cache Optimization
+
+def design_stable_prompt(template: str, dynamic_values: dict) -> str:
+    """
+    Design prompt to maximize KV-cache stability.
+    
+    Replaces dynamic values with stable placeholders.
+    """
+    result = template
+    
+    # Replace timestamps
+    import re
+    date_pattern = r'\d{4}-\d{2}-\d{2}'
+    result = re.sub(date_pattern, '[DATE_STABLE]', result)
+    
+    # Replace session IDs
+    session_pattern = r'Session \d+'
+    result = re.sub(session_pattern, 'Session [STABLE]', result)
+    
+    # Replace counters
+    counter_pattern = r'\d+/\d+'
+    result = re.sub(counter_pattern, '[COUNTER_STABLE]', result)
+    
+    return result
+
+
+def calculate_cache_metrics(requests: list, cache: dict) -> dict:
+    """
+    Calculate KV-cache hit metrics for request sequence.
+    """
+    hits = 0
+    misses = 0
+    
+    for req in requests:
+        prefix = req.get("prefix_hash", "")
+        token_count = req.get("token_count", 0)
+        
+        if prefix in cache:
+            hits += token_count * cache[prefix].get("hit_ratio", 0)
+        else:
+            misses += token_count
+    
+    total = hits + misses
+    
+    return {
+        "hit_rate": hits / total if total > 0 else 0,
+        "cache_hits": hits,
+        "cache_misses": misses,
+        "recommendations": generate_cache_recommendations(hits, misses)
+    }
+
+
+def generate_cache_recommendations(hits: int, misses: int) -> list:
+    """Generate recommendations for cache optimization."""
+    recommendations = []
+    
+    hit_rate = hits / (hits + misses) if (hits + misses) > 0 else 0
+    
+    if hit_rate < 0.5:
+        recommendations.append("Consider stabilizing system prompts")
+        recommendations.append("Reduce variation in request prefixes")
+    
+    if hit_rate < 0.8:
+        recommendations.append("Group similar requests together")
+        recommendations.append("Use consistent formatting across requests")
+    
+    return recommendations

package/assets/skills/context-optimization/skills/evaluation/SKILL.md

@@ -0,0 +1,231 @@
+---
+name: evaluation
+description: This skill should be used when the user asks to "evaluate agent performance", "build test framework", "measure agent quality", "create evaluation rubrics", or mentions LLM-as-judge, multi-dimensional evaluation, agent testing, or quality gates for agent pipelines.
+---
+
+# Evaluation Methods for Agent Systems
+
+Evaluation of agent systems requires different approaches than traditional software or even standard language model applications. Agents make dynamic decisions, are non-deterministic between runs, and often lack single correct answers. Effective evaluation must account for these characteristics while providing actionable feedback. A robust evaluation framework enables continuous improvement, catches regressions, and validates that context engineering choices achieve intended effects.
+
+## When to Activate
+
+Activate this skill when:
+- Testing agent performance systematically
+- Validating context engineering choices
+- Measuring improvements over time
+- Catching regressions before deployment
+- Building quality gates for agent pipelines
+- Comparing different agent configurations
+- Evaluating production systems continuously
+
+## Core Concepts
+
+Agent evaluation requires outcome-focused approaches that account for non-determinism and multiple valid paths. Multi-dimensional rubrics capture various quality aspects: factual accuracy, completeness, citation accuracy, source quality, and tool efficiency. LLM-as-judge provides scalable evaluation while human evaluation catches edge cases.
+
+The key insight is that agents may find alternative paths to goals—the evaluation should judge whether they achieve right outcomes while following reasonable processes.
+
+**Performance Drivers: The 95% Finding**
+Research on the BrowseComp evaluation (which tests browsing agents' ability to locate hard-to-find information) found that three factors explain 95% of performance variance:
+
+| Factor | Variance Explained | Implication |
+|--------|-------------------|-------------|
+| Token usage | 80% | More tokens = better performance |
+| Number of tool calls | ~10% | More exploration helps |
+| Model choice | ~5% | Better models multiply efficiency |
+
+This finding has significant implications for evaluation design:
+- **Token budgets matter**: Evaluate agents with realistic token budgets, not unlimited resources
+- **Model upgrades beat token increases**: Upgrading to Claude Sonnet 4.5 or GPT-5.2 provides larger gains than doubling token budgets on previous versions
+- **Multi-agent validation**: The finding validates architectures that distribute work across agents with separate context windows
+
+## Detailed Topics
+
+### Evaluation Challenges
+
+**Non-Determinism and Multiple Valid Paths**
+Agents may take completely different valid paths to reach goals. One agent might search three sources while another searches ten. They might use different tools to find the same answer. Traditional evaluations that check for specific steps fail in this context.
+
+The solution is outcome-focused evaluation that judges whether agents achieve right outcomes while following reasonable processes.
+
+**Context-Dependent Failures**
+Agent failures often depend on context in subtle ways. An agent might succeed on simple queries but fail on complex ones. It might work well with one tool set but fail with another. Failures may emerge only after extended interaction when context accumulates.
+
+Evaluation must cover a range of complexity levels and test extended interactions, not just isolated queries.
+
+**Composite Quality Dimensions**
+Agent quality is not a single dimension. It includes factual accuracy, completeness, coherence, tool efficiency, and process quality. An agent might score high on accuracy but low in efficiency, or vice versa.
+
+Evaluation rubrics must capture multiple dimensions with appropriate weighting for the use case.
+
+### Evaluation Rubric Design
+
+**Multi-Dimensional Rubric**
+Effective rubrics cover key dimensions with descriptive levels:
+
+Factual accuracy: Claims match ground truth (excellent to failed)
+
+Completeness: Output covers requested aspects (excellent to failed)
+
+Citation accuracy: Citations match claimed sources (excellent to failed)
+
+Source quality: Uses appropriate primary sources (excellent to failed)
+
+Tool efficiency: Uses right tools reasonable number of times (excellent to failed)
+
+**Rubric Scoring**
+Convert dimension assessments to numeric scores (0.0 to 1.0) with appropriate weighting. Calculate weighted overall scores. Determine passing threshold based on use case requirements.
+
+### Evaluation Methodologies
+
+**LLM-as-Judge**
+LLM-based evaluation scales to large test sets and provides consistent judgments. The key is designing effective evaluation prompts that capture the dimensions of interest.
+
+Provide clear task description, agent output, ground truth (if available), evaluation scale with level descriptions, and request structured judgment.
+
+**Human Evaluation**
+Human evaluation catches what automation misses. Humans notice hallucinated answers on unusual queries, system failures, and subtle biases that automated evaluation misses.
+
+Effective human evaluation covers edge cases, samples systematically, tracks patterns, and provides contextual understanding.
+
+**End-State Evaluation**
+For agents that mutate persistent state, end-state evaluation focuses on whether the final state matches expectations rather than how the agent got there.
+
+### Test Set Design
+
+**Sample Selection**
+Start with small samples during development. Early in agent development, changes have dramatic impacts because there is abundant low-hanging fruit. Small test sets reveal large effects.
+
+Sample from real usage patterns. Add known edge cases. Ensure coverage across complexity levels.
+
+**Complexity Stratification**
+Test sets should span complexity levels: simple (single tool call), medium (multiple tool calls), complex (many tool calls, significant ambiguity), and very complex (extended interaction, deep reasoning).
+
+### Context Engineering Evaluation
+
+**Testing Context Strategies**
+Context engineering choices should be validated through systematic evaluation. Run agents with different context strategies on the same test set. Compare quality scores, token usage, and efficiency metrics.
+
+**Degradation Testing**
+Test how context degradation affects performance by running agents at different context sizes. Identify performance cliffs where context becomes problematic. Establish safe operating limits.
+
+### Continuous Evaluation
+
+**Evaluation Pipeline**
+Build evaluation pipelines that run automatically on agent changes. Track results over time. Compare versions to identify improvements or regressions.
+
+**Monitoring Production**
+Track evaluation metrics in production by sampling interactions and evaluating randomly. Set alerts for quality drops. Maintain dashboards for trend analysis.
+
+## Practical Guidance
+
+### Building Evaluation Frameworks
+
+1. Define quality dimensions relevant to your use case
+2. Create rubrics with clear, actionable level descriptions
+3. Build test sets from real usage patterns and edge cases
+4. Implement automated evaluation pipelines
+5. Establish baseline metrics before making changes
+6. Run evaluations on all significant changes
+7. Track metrics over time for trend analysis
+8. Supplement automated evaluation with human review
+
+### Avoiding Evaluation Pitfalls
+
+Overfitting to specific paths: Evaluate outcomes, not specific steps.
+Ignoring edge cases: Include diverse test scenarios.
+Single-metric obsession: Use multi-dimensional rubrics.
+Neglecting context effects: Test with realistic context sizes.
+Skipping human evaluation: Automated evaluation misses subtle issues.
+
+## Examples
+
+**Example 1: Simple Evaluation**
+```python
+def evaluate_agent_response(response, expected):
+    rubric = load_rubric()
+    scores = {}
+    for dimension, config in rubric.items():
+        scores[dimension] = assess_dimension(response, expected, dimension)
+    overall = weighted_average(scores, config["weights"])
+    return {"passed": overall >= 0.7, "scores": scores}
+```
+
+**Example 2: Test Set Structure**
+
+Test sets should span multiple complexity levels to ensure comprehensive evaluation:
+
+```python
+test_set = [
+    {
+        "name": "simple_lookup",
+        "input": "What is the capital of France?",
+        "expected": {"type": "fact", "answer": "Paris"},
+        "complexity": "simple",
+        "description": "Single tool call, factual lookup"
+    },
+    {
+        "name": "medium_query",
+        "input": "Compare the revenue of Apple and Microsoft last quarter",
+        "complexity": "medium",
+        "description": "Multiple tool calls, comparison logic"
+    },
+    {
+        "name": "multi_step_reasoning",
+        "input": "Analyze sales data from Q1-Q4 and create a summary report with trends",
+        "complexity": "complex",
+        "description": "Many tool calls, aggregation, analysis"
+    },
+    {
+        "name": "research_synthesis",
+        "input": "Research emerging AI technologies, evaluate their potential impact, and recommend adoption strategy",
+        "complexity": "very_complex",
+        "description": "Extended interaction, deep reasoning, synthesis"
+    }
+]
+```
+
+## Guidelines
+
+1. Use multi-dimensional rubrics, not single metrics
+2. Evaluate outcomes, not specific execution paths
+3. Cover complexity levels from simple to complex
+4. Test with realistic context sizes and histories
+5. Run evaluations continuously, not just before release
+6. Supplement LLM evaluation with human review
+7. Track metrics over time for trend detection
+8. Set clear pass/fail thresholds based on use case
+
+## Integration
+
+This skill connects to all other skills as a cross-cutting concern:
+
+- context-fundamentals - Evaluating context usage
+- context-degradation - Detecting degradation
+- context-optimization - Measuring optimization effectiveness
+- multi-agent-patterns - Evaluating coordination
+- tool-design - Evaluating tool effectiveness
+- memory-systems - Evaluating memory quality
+
+## References
+
+Internal reference:
+- [Metrics Reference](./references/metrics.md) - Detailed evaluation metrics and implementation
+
+## References
+
+Internal skills:
+- All other skills connect to evaluation for quality measurement
+
+External resources:
+- LLM evaluation benchmarks
+- Agent evaluation research papers
+- Production monitoring practices
+
+---
+
+## Skill Metadata
+
+**Created**: 2025-12-20
+**Last Updated**: 2025-12-20
+**Author**: Agent Skills for Context Engineering Contributors
+**Version**: 1.0.0