Iteration 2 - OR_EXPERT_REFINEMENT
Sequence: 5
Timestamp: 2025-07-27 22:15:01

Prompt:
You are an Operations Research (OR) expert in iteration 2 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 1):
{
  "iteration": 2,
  "converged": false,
  "business_context": "A university is optimizing the allocation of student advisors to students with pets, ensuring balanced workloads in terms of student numbers and total pet weight.",
  "optimization_problem": "Minimize the maximum workload of any advisor, where workload is a linear combination of the number of students and total pet weight assigned to each advisor. Each student is assigned to exactly one advisor, and each advisor has limits on the number of students and total pet weight they can handle.",
  "objective": "minimize max_workload = max(sum(students_assigned[i] + pet_weight_assigned[i] for each advisor i))",
  "table_count": 1,
  "key_changes": [
    "Schema changes include creating new tables for missing optimization data, modifying existing tables to improve mapping adequacy, and updating business configuration logic for scalar parameters and formulas."
  ],
  "math_consistency": "high",
  "next_iteration_focus": "Refine mapping of decision variables and gather missing data for complete model",
  "mapping_adequacy_summary": "needs_improvement"
}

CURRENT SCHEMA:
```sql
-- Iteration 2 Database Schema
-- Objective: Schema changes include creating new tables for missing optimization data, modifying existing tables to improve mapping adequacy, and updating business configuration logic for scalar parameters and formulas.

CREATE TABLE Has_Pet (
  StuID INTEGER,
  PetID INTEGER,
  AdvisorID INTEGER
);

CREATE TABLE AdvisorConstraints (
  AdvisorID INTEGER,
  MaxStudents INTEGER,
  MaxWeight FLOAT
);

CREATE TABLE PetWeightAssignment (
  AdvisorID INTEGER,
  TotalPetWeight FLOAT
);


```

CURRENT DATA DICTIONARY:
{
  "tables": {
    "Has_Pet": {
      "business_purpose": "Maps students to their pets and advisors",
      "optimization_role": "decision_variables",
      "columns": {
        "StuID": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for each student",
          "optimization_purpose": "Used to assign students to advisors",
          "sample_values": "1, 2, 3"
        },
        "PetID": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for each pet",
          "optimization_purpose": "Links pets to students",
          "sample_values": "101, 102, 103"
        },
        "AdvisorID": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for each advisor",
          "optimization_purpose": "Used to assign students to advisors",
          "sample_values": "201, 202, 203"
        }
      }
    },
    "AdvisorConstraints": {
      "business_purpose": "Stores constraints for advisors",
      "optimization_role": "constraint_bounds",
      "columns": {
        "AdvisorID": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for each advisor",
          "optimization_purpose": "Links constraints to advisors",
          "sample_values": "201, 202, 203"
        },
        "MaxStudents": {
          "data_type": "INTEGER",
          "business_meaning": "Maximum number of students an advisor can handle",
          "optimization_purpose": "Constraint for optimization",
          "sample_values": "5, 6, 7"
        },
        "MaxWeight": {
          "data_type": "FLOAT",
          "business_meaning": "Maximum total pet weight an advisor can handle",
          "optimization_purpose": "Constraint for optimization",
          "sample_values": "100.0, 120.0, 150.0"
        }
      }
    },
    "PetWeightAssignment": {
      "business_purpose": "Stores the total weight of pets assigned to each advisor",
      "optimization_role": "decision_variables",
      "columns": {
        "AdvisorID": {
          "data_type": "INTEGER",
          "business_meaning": "Unique identifier for each advisor",
          "optimization_purpose": "Links pet weight to advisors",
          "sample_values": "201, 202, 203"
        },
        "TotalPetWeight": {
          "data_type": "FLOAT",
          "business_meaning": "Total weight of pets assigned to an advisor",
          "optimization_purpose": "Used to calculate advisor workload",
          "sample_values": "50.0, 60.0, 70.0"
        }
      }
    }
  }
}


CURRENT BUSINESS CONFIGURATION LOGIC:
{
  "workload_coefficient": {
    "sample_value": 1.0,
    "data_type": "FLOAT",
    "business_meaning": "Coefficient for the workload of advisor in the objective function",
    "optimization_role": "Used in the objective function to calculate workload",
    "configuration_type": "scalar_parameter"
  }
}


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

JSON STRUCTURE REQUIRED:

{
  "database_id": "pets_1",
  "iteration": 2,
  "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": "pets_1",
  "iteration": 2,
  "business_context": "A university is optimizing the allocation of student advisors to students with pets, ensuring balanced workloads in terms of student numbers and total pet weight. The goal is to minimize the maximum workload across all advisors.",
  "optimization_problem_description": "Minimize the maximum workload of any advisor, where workload is a linear combination of the number of students and total pet weight assigned to each advisor. Each student is assigned to exactly one advisor, and each advisor has limits on the number of students and total pet weight they can handle.",
  "optimization_formulation": {
    "objective": "minimize max_workload = max(sum(students_assigned[i] + pet_weight_assigned[i] for each advisor i))",
    "decision_variables": {
      "students_assigned[i]": "integer",
      "pet_weight_assigned[i]": "continuous"
    },
    "constraints": {
      "sum(students_assigned[i]) <= MaxStudents[i]": "for each advisor i",
      "sum(pet_weight_assigned[i]) <= MaxWeight[i]": "for each advisor i",
      "sum(students_assigned[i]) = 1": "for each student"
    }
  },
  "current_optimization_to_schema_mapping": {
    "objective_coefficients": {
      "workload_coefficient": {
        "currently_mapped_to": "business_configuration_logic.workload_coefficient",
        "mapping_adequacy": "good",
        "description": "Coefficient for the workload of advisor in the objective function"
      }
    },
    "constraint_bounds": {
      "MaxStudents[i]": {
        "currently_mapped_to": "AdvisorConstraints.MaxStudents",
        "mapping_adequacy": "good",
        "description": "Maximum number of students an advisor can handle"
      },
      "MaxWeight[i]": {
        "currently_mapped_to": "AdvisorConstraints.MaxWeight",
        "mapping_adequacy": "good",
        "description": "Maximum total pet weight an advisor can handle"
      }
    },
    "decision_variables": {
      "students_assigned[i]": {
        "currently_mapped_to": "Has_Pet.StuID",
        "mapping_adequacy": "good",
        "description": "Number of students assigned to advisor i",
        "variable_type": "integer"
      },
      "pet_weight_assigned[i]": {
        "currently_mapped_to": "PetWeightAssignment.TotalPetWeight",
        "mapping_adequacy": "good",
        "description": "Total pet weight assigned to advisor i",
        "variable_type": "continuous"
      }
    }
  },
  "missing_optimization_requirements": [],
  "iteration_status": {
    "complete": true,
    "confidence": "high",
    "next_focus": "Ready for convergence"
  }
}
