Skip to main content

​
Function Signature

def discover_solution(
    evaluator: Callable[[str], Dict[str, Any]],
    initial_solution: Optional[str] = None,
    iterations: int = 100,
    search: Optional[str] = None,
    model: Optional[str] = None,
    **kwargs: Any,
) -> DiscoveryResult

​
Description

A convenience wrapper around run_discovery designed for the common case where:
  • The initial solution is a plain string (not a file path)
  • The evaluator is a Python callable function (not a file path)
This function provides a simpler interface for programmatic use cases where you want to evolve a string-based solution using an in-memory evaluator function.

​
Parameters

​
evaluator
Callable[[str], Dict[str, Any]]
required
A callable function that evaluates a program and returns a metrics dictionary.Function signature: (solution: str) -> Dict[str, Any]The function receives the program as a string and must return a dictionary containing evaluation metrics. The score is extracted using the combined_score key or by aggregating other numeric metrics.
​
initial_solution
Optional[str]
Starting solution as a plain string. If None, the LLM generates a solution from scratch.Default: None
​
iterations
int
Maximum number of iterations to run.Default: 100
​
search
Optional[str]
Search algorithm name.Options:
  • "topk" - Top-K sampling
  • "adaevolve" - Adaptive Evolution
  • "evox" - EvoX backend
  • "openevolve_native" - OpenEvolve native
Default: None (uses config file)
​
model
Optional[str]
Model name(s), comma-separated.Examples:
  • "gpt-5"
  • "gpt-5,gemini/gemini-3-pro"
Default: None (uses config file)
​
**kwargs
Any
Additional keyword arguments passed to run_discovery.Common options:
  • config: Configuration file path or Config object
  • output_dir: Directory for results
  • system_prompt: Domain-specific context for the LLM
  • agentic: Enable agentic mode
  • api_base: Custom API endpoint
  • cleanup: Remove temporary files after completion

​
Returns

​
DiscoveryResult
DiscoveryResult
Result object containing:

​
Examples

​
Basic Usage

from skydiscover import discover_solution

def my_evaluator(solution: str) -> dict:
    """Evaluate solution quality."""
    # Write solution to temporary file and test it
    import tempfile
    import subprocess
    
    with tempfile.NamedTemporaryFile(mode='w', suffix='.py', delete=False) as f:
        f.write(solution)
        temp_path = f.name
    
    try:
        # Run tests
        result = subprocess.run(
            ['python', '-m', 'pytest', temp_path, '--json-report'],
            capture_output=True,
            timeout=30
        )
        
        # Calculate score
        tests_passed = result.returncode == 0
        return {
            'combined_score': 1.0 if tests_passed else 0.0,
            'tests_passed': tests_passed,
        }
    finally:
        import os
        os.unlink(temp_path)

initial_code = '''
def fibonacci(n: int) -> int:
    if n <= 1:
        return n
    return fibonacci(n-1) + fibonacci(n-2)
'''

result = discover_solution(
    evaluator=my_evaluator,
    initial_solution=initial_code,
    model="gpt-5",
    iterations=50,
)

print(f"Improved score: {result.best_score}")
print(f"Initial score: {result.initial_score}")

​
Starting from Scratch

from skydiscover import discover_solution

def evaluate_sorting(solution: str) -> dict:
    """Evaluate a sorting algorithm."""
    import random
    import timeit
    
    # Create a namespace and execute the solution
    namespace = {}
    exec(solution, namespace)
    
    if 'sort' not in namespace:
        return {'combined_score': 0.0, 'error': 'No sort function found'}
    
    sort_func = namespace['sort']
    
    # Test correctness
    test_cases = [
        [3, 1, 4, 1, 5, 9, 2, 6],
        [1],
        [],
        list(range(100, 0, -1)),
    ]
    
    for test in test_cases:
        result = sort_func(test.copy())
        expected = sorted(test)
        if result != expected:
            return {'combined_score': 0.0, 'error': 'Incorrect result'}
    
    # Measure performance
    large_array = [random.randint(0, 1000) for _ in range(1000)]
    time_taken = timeit.timeit(
        lambda: sort_func(large_array.copy()),
        number=100
    )
    
    # Score: lower time is better
    score = 1.0 / (1.0 + time_taken)
    
    return {
        'combined_score': score,
        'time_taken': time_taken,
        'correctness': 1.0,
    }

result = discover_solution(
    evaluator=evaluate_sorting,
    initial_solution=None,  # Generate from scratch
    model="gpt-5",
    iterations=100,
    system_prompt="Create an efficient sorting algorithm optimized for small arrays (< 1000 elements)",
)

print(f"Best sorting algorithm:\n{result.best_solution}")
print(f"Performance score: {result.best_score}")

​
Multi-Objective Optimization

from skydiscover import discover_solution
import ast

def evaluate_code_quality(solution: str) -> dict:
    """Evaluate code on multiple dimensions."""
    metrics = {}
    
    # Parse the code
    try:
        tree = ast.parse(solution)
    except SyntaxError:
        return {'combined_score': 0.0, 'error': 'Syntax error'}
    
    # Count lines (excluding empty lines and comments)
    lines = [l.strip() for l in solution.split('\n') if l.strip() and not l.strip().startswith('#')]
    metrics['brevity'] = 1.0 / (1.0 + len(lines) / 10.0)  # Prefer shorter code
    
    # Count complexity (number of nodes)
    num_nodes = sum(1 for _ in ast.walk(tree))
    metrics['simplicity'] = 1.0 / (1.0 + num_nodes / 20.0)  # Prefer simpler code
    
    # Check for docstrings
    has_docstrings = any(
        isinstance(node, (ast.FunctionDef, ast.ClassDef)) and
        ast.get_docstring(node)
        for node in ast.walk(tree)
    )
    metrics['documentation'] = 1.0 if has_docstrings else 0.5
    
    # Run functionality tests
    namespace = {}
    exec(solution, namespace)
    
    if 'process' not in namespace:
        return {'combined_score': 0.0, 'error': 'No process function'}
    
    try:
        result = namespace['process']('test input')
        metrics['correctness'] = 1.0 if result else 0.5
    except Exception as e:
        metrics['correctness'] = 0.0
        metrics['error'] = str(e)
    
    # Combined score (weighted average)
    metrics['combined_score'] = (
        0.4 * metrics['correctness'] +
        0.3 * metrics['brevity'] +
        0.2 * metrics['simplicity'] +
        0.1 * metrics['documentation']
    )
    
    return metrics

initial_code = '''
def process(input_text: str) -> str:
    """Process the input text."""
    # Basic implementation
    result = input_text.upper()
    result = result.replace(' ', '_')
    return result
'''

result = discover_solution(
    evaluator=evaluate_code_quality,
    initial_solution=initial_code,
    model="gpt-5",
    iterations=75,
)

print(f"Improved solution:\n{result.best_solution}")
print(f"\nMetrics: {result.metrics}")

​
With Custom Configuration

from skydiscover import discover_solution

def simple_evaluator(solution: str) -> dict:
    """Simple length-based evaluator."""
    lines = solution.strip().split('\n')
    return {'combined_score': len(lines) / 100.0}

result = discover_solution(
    evaluator=simple_evaluator,
    initial_solution="def hello(): pass",
    model="gpt-5",
    iterations=50,
    output_dir="./my_results",
    cleanup=False,
    system_prompt="Create comprehensive documentation",
)

print(f"Results saved to: {result.output_dir}")

​
Different Search Algorithms

from skydiscover import discover_solution

def my_evaluator(solution: str) -> dict:
    # Evaluation logic
    return {'combined_score': len(solution) / 1000.0}

# Try different search algorithms
for search_type in ['topk', 'adaevolve']:
    result = discover_solution(
        evaluator=my_evaluator,
        initial_solution="# Starting code",
        model="gpt-5",
        search=search_type,
        iterations=50,
    )
    print(f"{search_type}: {result.best_score:.4f}")

​
Error Handling

​
Invalid Evaluator Return Type

from skydiscover import discover_solution

def bad_evaluator(solution: str) -> float:
    """This evaluator returns a float instead of dict."""
    return 0.5  # Wrong! Should return a dict

try:
    result = discover_solution(
        evaluator=bad_evaluator,
        model="gpt-5",
    )
except (TypeError, KeyError) as e:
    print(f"Error: Evaluator must return a dictionary with metrics")

​
Evaluator Timeout

from skydiscover import discover_solution
import time

def slow_evaluator(solution: str) -> dict:
    """Evaluator with timeout protection."""
    import signal
    
    def timeout_handler(signum, frame):
        raise TimeoutError("Evaluation timeout")
    
    # Set 10 second timeout
    signal.signal(signal.SIGALRM, timeout_handler)
    signal.alarm(10)
    
    try:
        # Your evaluation logic here
        namespace = {}
        exec(solution, namespace)
        # ... more evaluation
        return {'combined_score': 0.5}
    except TimeoutError:
        return {'combined_score': 0.0, 'error': 'timeout'}
    finally:
        signal.alarm(0)  # Cancel alarm

result = discover_solution(
    evaluator=slow_evaluator,
    model="gpt-5",
    iterations=50,
)

​
Notes

  • This function is a thin wrapper around run_discovery for convenience
  • The evaluator function receives the solution as a string (not a file path)
  • The evaluator must return a dictionary; the score is derived from:
    • combined_score key (if present), or
    • Aggregation of other numeric values
  • Use run_discovery directly if you need more control or file-based workflows
  • The evaluator function is automatically converted to a file-based evaluator internally

​
See Also