#!/usr/bin/env bash # Agentic evaluation dispatcher set -euo pipefail SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/.." && pwd)" case "${1:-help}" in setup) exec bash "$SCRIPT_DIR/scripts/agentic/setup.sh" ;; run) exec bash "$SCRIPT_DIR/scripts/agentic/run-eval.sh" "${@:2}" ;; quick) exec bash "$SCRIPT_DIR/scripts/agentic/run-eval.sh" --suite quick "${@:2}" ;; code) exec bash "$SCRIPT_DIR/scripts/agentic/run-eval.sh" --suite code "${@:2}" ;; tooluse) exec bash "$SCRIPT_DIR/scripts/agentic/run-eval.sh" --suite tooluse "${@:2}" ;; full) exec bash "$SCRIPT_DIR/scripts/agentic/run-eval.sh" --suite full "${@:2}" ;; *) echo "Usage: agentic [options]" echo "" echo "Commands:" echo " setup Install evaluation frameworks (inspect-ai, evalplus, bigcodebench)" echo " quick EvalPlus HumanEval+ + IFEval (~1 hour)" echo " code EvalPlus + BigCodeBench (~2-3 hours)" echo " tooluse BFCL function calling evaluation (~1-2 hours)" echo " full All evaluations (~5-6 hours)" echo " run Custom run (--suite SUITE --model NAME --endpoint URL)" echo "" echo "All commands require --model NAME. Examples:" echo " agentic quick --model qwen3.5:35b-a3b-q8_0" echo " agentic full --model qwen3-coder:30b-a3b --endpoint http://localhost:8080/v1" exit 1 ;; esac