Layer 1: Categorical Structure
  ↓ YAML Olog with complement_operations section
  
Layer 2: Deterministic Mapping
  ↓ MCP loads YAML, computes antipodes (zero LLM cost)
  
Layer 3: Integration
  ↓ Linear interpolation via integration_level

integrated = persona + (shadow - persona) × integration_level

integration_level ∈ [0, 1]:
  0.0 = pure persona (original aesthetic)
  0.5 = balanced acknowledgment
  1.0 = pure shadow (inverse aesthetic)

# Clone or extract the archive
cd shadow-complement-integration

# Install with pip
pip install -e .

# Or with uv
uv pip install -e .

tar -czf shadow-complement-integration.tar.gz shadow-complement-integration/

{
  "mcpServers": {
    "shadow-complement-integration": {
      "command": "python",
      "args": [
        "-m",
        "shadow_complement_mcp.server"
      ],
      "env": {
        "PYTHONPATH": "/path/to/shadow-complement-integration/src"
      }
    }
  }
}

DOMAIN_OLOG_PATHS = {
    "heraldic_blazonry": "/path/to/heraldic_blazonry_mcp/olog/heraldic_blazonry.yaml",
    "jazz_improvisation": "/path/to/jazz_improvisation_mcp/olog/jazz_improvisation.yaml",
    "cocktail_aesthetics": "/path/to/cocktail_aesthetics_mcp/olog/cocktail_aesthetics.yaml",
}

complement_operations:
  tincture:
    type: categorical
    mapping:
      gules: argent
      azure: or
      sable: argent
    psychological_principle: "Chromatic opposition reveals denied warmth/coolness"
  
  visual_weight:
    type: continuous
    range: [0.0, 1.0]
    operation: "1 - value"
    psychological_principle: "Dominance ↔ submission"

from shadow_complement_mcp import integrate_shadow_complement

# After multi-domain composition
unified_params = {
    "tincture": "gules",
    "visual_weight": 0.85,
    "detail_density": 0.7
}

result = integrate_shadow_complement(
    unified_parameters=unified_params,
    aesthetic_domain="heraldic_blazonry",
    integration_level=0.5
)

# Access results
print(result["persona"])              # Original parameters
print(result["shadow_complements"])   # Computed antipodes
print(result["integrated_parameters"]) # Interpolated result

# Persona-dominant (subtle shadow hints)
result_subtle = integrate_shadow_complement(
    unified_parameters=params,
    aesthetic_domain="heraldic_blazonry",
    integration_level=0.2
)

# Balanced acknowledgment
result_balanced = integrate_shadow_complement(
    unified_parameters=params,
    aesthetic_domain="heraldic_blazonry",
    integration_level=0.5
)

# Shadow-dominant
result_shadow = integrate_shadow_complement(
    unified_parameters=params,
    aesthetic_domain="heraldic_blazonry",
    integration_level=0.8
)

# List configured domains
domains = list_available_domains()
# Returns: {"heraldic_blazonry": "configured", ...}

# Get complement schema
schema = get_complement_operations_schema("heraldic_blazonry")
# Returns parameter types and operations

# Explain specific complement
explanation = explain_shadow_complement(
    parameter_name="tincture",
    parameter_value="gules",
    aesthetic_domain="heraldic_blazonry"
)
# Returns psychological principle and antipode reasoning

Domain A  ──┐
            ├─→ [Colimit Composition] ──→ Unified Parameters
Domain B  ──┤                                    ↓
Domain C  ──┘                          [Shadow Integration]
                                                 ↓
                                          Final Output

# Install dev dependencies
pip install -e ".[dev]"

# Run test suite
pytest tests/

# Run specific test file
pytest tests/test_antipode_computation.py