Iteration 1 - OR_EXPERT_REFINEMENT
Sequence: 3
Timestamp: 2025-07-27 22:01:56

Prompt:
You are an Operations Research (OR) expert in iteration 1 of an alternating optimization process. The algorithm alternates between OR expert analysis and data engineering implementation until convergence.

CRITICAL MATHEMATICAL CONSTRAINTS FOR LINEAR/MIXED-INTEGER PROGRAMMING:
- The optimization problem MUST remain Linear Programming (LP) or Mixed-Integer Programming (MIP)
- Objective function MUST be linear: minimize/maximize ∑(coefficient × variable)
- All constraints MUST be linear: ∑(coefficient × variable) ≤/≥/= constant
- Decision variables can be continuous (LP) or mixed continuous/integer (MIP)
- NO variable products, divisions, or other nonlinear relationships
- If previous iteration introduced nonlinear elements, redesign as linear formulation
- Maintain between 2 and 20 constraints for optimization feasibility

YOUR SCOPE: Focus exclusively on optimization modeling and mapping analysis. Do NOT propose database changes.
ROW COUNT AWARENESS: Understand that data engineer applies 3-row minimum rule - insufficient table data gets moved to business_configuration_logic.json.


DATA AVAILABILITY CHECK: 
Before listing missing requirements, verify:
- Check current schema for required data columns
- Check business configuration logic for required parameters  
- Only list as "missing" if data is truly unavailable
- If all mappings are "good", missing_requirements should be []

CONSISTENCY RULES:
- IF all mapping_adequacy == "good" THEN missing_optimization_requirements = []
- IF missing_optimization_requirements = [] THEN complete CAN be true
- IF complete == true THEN confidence should be "high"

SELF-CHECK: Before responding, verify:
1. Does current schema contain the data I claim is missing?
2. Are my mapping assessments consistent with missing requirements?
3. Is my complete status consistent with missing requirements?

MAPPING COMPLETENESS CHECK: Ensure logical consistency between:
- All objective coefficients mapped with adequacy evaluation
- All constraint bounds mapped with adequacy evaluation  
- All decision variables mapped with adequacy evaluation
- Missing requirements list matches inadequate mappings only


CRITICAL: Respond with ONLY a valid JSON object. No explanations, no markdown, no extra text.



CURRENT STATE (iteration 0):
{
  "iteration": 1,
  "converged": false,
  "business_context": "Optimize the assignment of captains to ships to minimize the total age of captains assigned to ships of a specific class, ensuring each ship has exactly one captain and each captain is assigned to one ship.",
  "optimization_problem": "The goal is to minimize the total age of captains assigned to ships of a specific class, ensuring that each ship has exactly one captain and each captain is assigned to one ship. This involves deciding which captain is assigned to which ship while respecting the constraints.",
  "objective": "minimize total_age = sum(captain_age[c, s] * x[c, s] for all captains c and ships s)",
  "table_count": 2,
  "key_changes": [
    "Schema changes include creating new tables for decision variables and constraint bounds, modifying existing tables to fill mapping gaps, and updating business configuration logic for scalar parameters and formulas."
  ],
  "math_consistency": "high",
  "next_iteration_focus": "Refine mapping of decision variables and ensure all necessary data is available",
  "mapping_adequacy_summary": "needs_improvement"
}

CURRENT SCHEMA:
```sql
-- Iteration 1 Database Schema
-- Objective: Schema changes include creating new tables for decision variables and constraint bounds, modifying existing tables to fill mapping gaps, and updating business configuration logic for scalar parameters and formulas.

CREATE TABLE Captain (
  id INTEGER,
  age INTEGER,
  class STRING
);

CREATE TABLE CaptainShipAssignment (
  captain_id INTEGER,
  ship_id INTEGER,
  assignment BOOLEAN
);

CREATE TABLE ConstraintBounds (
  captain_assignment INTEGER,
  ship_assignment INTEGER
);


```

CURRENT DATA DICTIONARY:
{
  "tables": {
    "Captain": {
      "business_purpose": "Stores information about captains",
      "optimization_role": "objective_coefficients",
      "columns": {
        "id": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for each captain",
          "optimization_purpose": "Used to reference captains in assignments",
          "sample_values": "1, 2, 3"
        },
        "age": {
          "data_type": "INTEGER",
          "business_meaning": "Age of the captain",
          "optimization_purpose": "Coefficient in the objective function",
          "sample_values": "45, 50, 55"
        },
        "class": {
          "data_type": "STRING",
          "business_meaning": "Class of the captain",
          "optimization_purpose": "Used for class compatibility constraint",
          "sample_values": "A, B, C"
        }
      }
    },
    "CaptainShipAssignment": {
      "business_purpose": "Represents assignments of captains to ships",
      "optimization_role": "decision_variables",
      "columns": {
        "captain_id": {
          "data_type": "INTEGER",
          "business_meaning": "ID of the assigned captain",
          "optimization_purpose": "Part of decision variable x[c, s]",
          "sample_values": "1, 2, 3"
        },
        "ship_id": {
          "data_type": "INTEGER",
          "business_meaning": "ID of the ship to which a captain is assigned",
          "optimization_purpose": "Part of decision variable x[c, s]",
          "sample_values": "101, 102, 103"
        },
        "assignment": {
          "data_type": "BOOLEAN",
          "business_meaning": "Indicates if a captain is assigned to a ship",
          "optimization_purpose": "Binary decision variable",
          "sample_values": "true, false"
        }
      }
    },
    "ConstraintBounds": {
      "business_purpose": "Stores constraint bounds for assignments",
      "optimization_role": "constraint_bounds",
      "columns": {
        "captain_assignment": {
          "data_type": "INTEGER",
          "business_meaning": "Ensures each captain is assigned to exactly one ship",
          "optimization_purpose": "Constraint bound",
          "sample_values": "1"
        },
        "ship_assignment": {
          "data_type": "INTEGER",
          "business_meaning": "Ensures each ship has exactly one captain",
          "optimization_purpose": "Constraint bound",
          "sample_values": "1"
        }
      }
    }
  }
}


CURRENT BUSINESS CONFIGURATION LOGIC:
{
  "max_age_limit": {
    "sample_value": "60",
    "data_type": "INTEGER",
    "business_meaning": "Maximum allowable age for captains",
    "optimization_role": "Used to filter eligible captains",
    "configuration_type": "scalar_parameter"
  },
  "total_age_formula": {
    "formula_expression": "sum(captain_age[c, s] * x[c, s] for all captains c and ships s)",
    "data_type": "STRING",
    "business_meaning": "Calculates the total age of assigned captains",
    "optimization_role": "Objective function to minimize",
    "configuration_type": "business_logic_formula"
  }
}


TASK: Refine the optimization problem formulation by analyzing current data schema mapping and identifying requirements while maintaining LINEAR structure.

JSON STRUCTURE REQUIRED:

{
  "database_id": "ship_1",
  "iteration": 1,
  "business_context": "Updated realistic business scenario description that supports linear optimization",
  "optimization_problem_description": "Refined description of LINEAR optimization problem", 
  "optimization_formulation": {
    "objective": "refined linear minimize/maximize with mathematical precision (sum of weighted variables only)",
    "decision_variables": "clearly defined controllable linear variables (continuous or integer)",
    "constraints": "mathematically precise LINEAR constraint definitions (no variable products or divisions) - maintain 2 to 20 constraints"
  },
  
  "current_optimization_to_schema_mapping": {
    "objective_coefficients": {
      "coefficient_name[indices]": {
        "currently_mapped_to": "table.column OR business_configuration_logic.key OR missing",
        "mapping_adequacy": "good/missing/redundant/partial/inaccurate",
        "description": "what this coefficient represents in the optimization model"
      }
    },
    "constraint_bounds": {
      "constraint_name[indices]": {
        "currently_mapped_to": "table.column OR business_configuration_logic.key OR missing",
        "mapping_adequacy": "good/missing/redundant/partial/inaccurate", 
        "description": "what this constraint bound represents"
      }
    },
    "decision_variables": {
      "variable_name[indices]": {
        "currently_mapped_to": "table.column OR business_configuration_logic.key OR missing",
        "mapping_adequacy": "good/missing/redundant/partial/inaccurate",
        "description": "what this decision variable represents",
        "variable_type": "continuous/integer/binary"
      }
    }
  },
  
  "missing_optimization_requirements": [
    "List what data/parameters are still needed for linear formulation (should be [] if all mappings are good)"
  ],
  
  "iteration_status": {
    "complete": true/false based on linear formulation completeness,
    "confidence": "updated confidence level",
    "next_focus": "What needs refinement for linear optimization OR 'Ready for convergence'"
  }
}

Response:
{
  "database_id": "ship_1",
  "iteration": 1,
  "business_context": "Optimize the assignment of captains to ships to minimize the total age of captains assigned to ships of a specific class, ensuring each ship has exactly one captain and each captain is assigned to one ship.",
  "optimization_problem_description": "The goal is to minimize the total age of captains assigned to ships of a specific class, ensuring that each ship has exactly one captain and each captain is assigned to one ship. This involves deciding which captain is assigned to which ship while respecting the constraints.",
  "optimization_formulation": {
    "objective": "minimize total_age = sum(Captain.age * CaptainShipAssignment.assignment for all captains and ships)",
    "decision_variables": "x[c, s] where x is binary, indicating if captain c is assigned to ship s",
    "constraints": [
      "sum(x[c, s] for all s) = 1 for each captain c",
      "sum(x[c, s] for all c) = 1 for each ship s"
    ]
  },
  "current_optimization_to_schema_mapping": {
    "objective_coefficients": {
      "Captain.age[c]": {
        "currently_mapped_to": "Captain.age",
        "mapping_adequacy": "good",
        "description": "Age of the captain, used as a coefficient in the objective function"
      }
    },
    "constraint_bounds": {
      "captain_assignment[c]": {
        "currently_mapped_to": "ConstraintBounds.captain_assignment",
        "mapping_adequacy": "good",
        "description": "Ensures each captain is assigned to exactly one ship"
      },
      "ship_assignment[s]": {
        "currently_mapped_to": "ConstraintBounds.ship_assignment",
        "mapping_adequacy": "good",
        "description": "Ensures each ship has exactly one captain"
      }
    },
    "decision_variables": {
      "x[c, s]": {
        "currently_mapped_to": "CaptainShipAssignment.assignment",
        "mapping_adequacy": "good",
        "description": "Binary decision variable indicating if captain c is assigned to ship s",
        "variable_type": "binary"
      }
    }
  },
  "missing_optimization_requirements": [],
  "iteration_status": {
    "complete": true,
    "confidence": "high",
    "next_focus": "Ready for convergence"
  }
}
