# Semantic Dependency Analysis Report

**Generated**: {{timestamp}}  
**Analysis ID**: {{analysisId}}  
**Confidence Level**: {{overallConfidence}}%

## Executive Summary

The LLM-native analysis identified **{{totalDependencies}} dependencies** across {{workItemCount}} work items, including **{{hiddenCount}} hidden dependencies** that would not be detected by traditional file-based analysis.

### Key Findings

- **Direct File Conflicts**: {{directConflicts}}
- **Semantic Dependencies**: {{semanticDeps}}
- **Architectural Impacts**: {{archImpacts}}
- **Risk Level**: {{riskLevel}} ({{riskReason}})

## Detailed Dependency Analysis

### Work Item Dependencies Matrix

| Work Item | Direct Files | Semantic Dependencies | Hidden Risks | Wave |
| --------- | ------------ | --------------------- | ------------ | ---- |

{{#each workItems}}
| {{description}} | {{files.length}} files | {{semanticDeps.length}} deps | {{risks.level}} | Wave {{wave}} |
{{/each}}

### Hidden Dependencies Discovered

{{#each hiddenDependencies}}

#### {{@index}}. {{title}}

**Type**: {{type}}  
**Affected Components**: {{components.join(", ")}}  
**Discovery Method**: {{method}}  
**Confidence**: {{confidence}}%

**Analysis**:
{{reasoning}}

{{#llm-analyze type confidence}}
Based on the dependency type ({{type}}) and confidence level ({{confidence}}%):

- If business logic dependency with >80% confidence: Provide specific code examples and method signatures that would be affected
- If data flow dependency: Map the complete data transformation pipeline
- If architectural dependency with <60% confidence: List additional investigation steps needed
- If security dependency: Highlight specific vulnerabilities and compliance impacts
  {{/llm-analyze}}

**Impact if Missed**:
{{impact}}

{{#llm-generate risk_level="{{risk}}"}}
Generate detailed impact scenarios:

- If HIGH risk: Provide 3-5 specific failure scenarios with production impact estimates
- If MEDIUM risk: List 2-3 degradation scenarios and user experience impacts
- If LOW risk: Brief confirmation of minimal impact with monitoring recommendations
  {{/llm-generate}}

**Mitigation Strategy**:
{{mitigation}}

{{#llm-enhance mitigation_complexity}}
Enhance the mitigation strategy based on complexity:

- If complex: Break down into numbered step-by-step implementation guide
- If moderate: Provide code snippets or configuration examples
- If simple: Confirm approach with best practice references
  {{/llm-enhance}}

---

{{/each}}

### API Contract Dependencies

{{#each apiDependencies}}

#### {{endpoint}}

**Consumers**: {{consumers.join(", ")}}  
**Contract Changes**: {{changes}}  
**Breaking Change Risk**: {{breakingRisk}}

{{/each}}

## Architectural Impact Assessment

### Service Boundaries

{{architecturalAnalysis.serviceBoundaries}}

### Design Pattern Implications

{{architecturalAnalysis.patternImplications}}

### Performance Considerations

{{architecturalAnalysis.performanceImpact}}

## Wave Planning Rationale

### Recommended Execution Waves

```
{{waveVisualization}}
```

### Wave Composition Reasoning

{{#each waves}}

#### Wave {{number}}: {{title}}

**Work Items**: {{items.join(", ")}}  
**Rationale**: {{reasoning}}  
**Dependencies Resolved**: {{resolved.join(", ")}}  
**Risk Level**: {{risk}}

{{#llm-analyze wave_number="{{number}}" risk_level="{{risk}}" item_count="{{items.length}}"}}
Provide wave-specific insights:

- If Wave 1: Emphasize foundation-setting and risk mitigation strategies
- If final wave: Focus on integration readiness and rollback procedures
- If high risk with >3 items: Suggest sub-wave breakdown with timing
- If low risk: Confirm parallel execution safety with performance benefits
  {{/llm-analyze}}

{{#llm-recommend optimization_potential}}
Based on wave composition, recommend optimizations:

- Check for items that could be promoted to earlier waves
- Identify opportunities for further parallelization within the wave
- Suggest monitoring checkpoints between sub-tasks
- Estimate time savings vs sequential execution
  {{/llm-recommend}}

{{/each}}

## User Review Section

### Dependency Analysis for Review

> 📝 **Instructions**: Please review the analysis below and add your corrections or insights in the marked sections.

{{#each workItems}}

#### Work Item: {{description}}

**AI Analysis**:

- Files to modify: {{predictedFiles.join(", ")}}
- API impacts: {{apiImpacts.join(", ")}}
- Hidden dependencies: {{hiddenDeps.join(", ")}}
- Architectural concerns: {{archConcerns.join(", ")}}

**Your Review**:

```yaml
# Please provide your feedback here
corrections:
  files:
    # Add any files the AI missed
  dependencies:
    # Identify any missed dependencies
  risks:
    # Note any additional risks

agreement_level: # high/medium/low
notes: |
  # Additional insights or corrections
```

---

{{/each}}

### Wave Planning Review

**AI's Proposed Wave Plan**:
{{proposedWavePlan}}

**Your Alternative Suggestion**:

```yaml
# Propose alternative wave composition if needed
alternative_waves:
  wave_1:
    items: []
    reasoning: ""
  wave_2:
    items: []
    reasoning: ""
```

## Confidence Metrics

### Analysis Confidence Breakdown

| Aspect                | Confidence              | Factors             |
| --------------------- | ----------------------- | ------------------- |
| File Dependencies     | {{fileConfidence}}%     | {{fileFactors}}     |
| Semantic Dependencies | {{semanticConfidence}}% | {{semanticFactors}} |
| Hidden Dependencies   | {{hiddenConfidence}}%   | {{hiddenFactors}}   |
| Wave Planning         | {{waveConfidence}}%     | {{waveFactors}}     |

### Areas Needing Human Validation

{{#each lowConfidenceAreas}}

- **{{area}}**: {{reason}} (Confidence: {{confidence}}%)
  {{/each}}

## Learning Opportunities

### Questions for User

{{#each questions}}
{{@index}}. {{question}}

- Context: {{context}}
- Why this helps: {{benefit}}
  {{/each}}

### Pattern Recognition

Based on this analysis, the AI identified these patterns that could improve future analyses:

{{#each patterns}}

- **Pattern**: {{pattern}}
- **Occurrence**: {{occurrence}}
- **Implication**: {{implication}}
  {{/each}}

---

📊 **Next Steps**:

1. Review this analysis for accuracy
2. Provide feedback in [user-review.md](./user-review.md)
3. View machine-readable data in [dependency-matrix.json](./dependency-matrix.json)
4. Proceed with execution or request re-analysis