Feedback Generator

@dataclass
class FeedbackResult:
    stop: bool                      # Whether to stop iteration
    evaluation_valid: bool          # Whether evaluation is fair/correct
    feedback: str                   # Actionable feedback for next iteration
    score: Optional[float] = None   # Extracted evaluation score

# Example evaluation output
"Training complete. Accuracy: 0.95, F1: 0.92"

# Extracted score
score = 0.95  # Primary metric

feedback = """
Current accuracy is 0.85, target is 0.9.
Suggestions:
1. Try increasing the number of estimators in the random forest
2. Consider feature engineering to improve signal
3. Check for class imbalance and apply SMOTE if needed
"""

solution = kapso.evolve(
    goal="Build a classifier with accuracy > 0.9",
    max_iterations=10,
)

# Check if goal was achieved
if solution.succeeded:
    print(f"Goal achieved with score: {solution.final_score}")
else:
    print(f"Final feedback: {solution.final_feedback.feedback}")

from kapso.execution.search_strategies.generic import FeedbackGenerator, FeedbackResult

# Create feedback generator (uses claude_code by default)
feedback_gen = FeedbackGenerator()

# Generate feedback
result = feedback_gen.generate(
    goal="Build a classifier with accuracy > 0.9",
    idea="Use random forest with hyperparameter tuning",
    implementation="...",  # Code diff
    evaluation_code="...",  # Contents of kapso_evaluation/evaluate.py
    evaluation_result={
        "output": "Accuracy: 0.85",
        "score": 0.85,
    },
)

if result.stop:
    print("Goal achieved!")
else:
    print(f"Continue with feedback: {result.feedback}")

search_strategy:
  type: "generic"
  params:
    idea_generation_model: "us.anthropic.claude-opus-4-5-20251101-v1:0"
    implementation_model: "us.anthropic.claude-opus-4-5-20251101-v1:0"

# In SearchStrategy.run()
def run(self, context, budget_progress):
    # 1. Generate solution
    solution = self._generate_solution(context)
    
    # 2. Implement and run evaluation
    node = self._implement_n_debug(solution, context, branch_name)
    
    # 3. Generate feedback
    feedback_result = self._generate_feedback(node)
    
    # 4. Update node with feedback
    node.feedback = feedback_result.feedback
    node.score = feedback_result.score
    node.should_stop = feedback_result.stop
    
    return node

# Good: Clear criteria
goal = "Build a classifier with accuracy > 0.9 and F1 > 0.85"

# Less good: Vague criteria
goal = "Build a good classifier"

# Agent builds evaluation dynamically
solution = kapso.evolve(
    goal="Optimize inference speed to < 10ms per sample",
    max_iterations=10,
)

Iteration 1: Accuracy 0.75
Feedback: "Try ensemble methods and feature selection"

Iteration 2: Accuracy 0.88
Feedback: "Close to target. Try hyperparameter tuning"

Iteration 3: Accuracy 0.92
Feedback: "Goal achieved! Accuracy 0.92 > 0.9 target"