mirror of
https://github.com/MervinPraison/PraisonAI.git
synced 2026-11-07 12:47:55 -10:00
praisonai-triage-agent[bot]andpraisonai-triage-agent[bot]
8d79da273a
Add LoopEvaluator + LoopHealthResult to praisonaiagents.eval to score loop *health* (convergence, wasted iterations, doom-loop guard events) on top of EvaluationLoop's output-quality scoring. - eval/loop_eval.py: LoopEvaluator (BaseEvaluator subclass) + LoopHealthResult - eval/__init__.py: lazy exports for LoopEvaluator, LoopHealthResult - tests/unit/eval/test_loop_eval.py: convergence, waste, doom-loop coverage - examples/python/eval/loop_health_eval.py: usage example Co-authored-by: praisonai-triage-agent[bot] <praisonai-triage-agent[bot]@users.noreply.github.com>
EvaluationLoop Examples
Examples demonstrating iterative evaluation and improvement patterns.
Quick Start
pip install praisonaiagents
export OPENAI_API_KEY=your-key
Examples
| File | Description |
|---|---|
basic_evaluation_loop.py |
Simple loop: Run → Judge → Improve |
multi_step_task_loop.py |
Sequential tasks with context passing |
recipe_optimization_loop.py |
CLI-based recipe optimization |
Pattern
┌─────────┐ ┌─────────┐ ┌──────────┐
│ Agent │ ──► │ Judge │ ──► │ Feedback │
│ runs │ │ scores │ │ improves │
└─────────┘ └─────────┘ └──────────┘
▲ │
└───────────────────────────────┘
(repeat until 8.0+)
Run Examples
# Basic loop
python basic_evaluation_loop.py
# Multi-step with context
python multi_step_task_loop.py
# CLI recipe loop
python recipe_optimization_loop.py "research AI trends"