Fix issue #5222: [Refactor]: Refactor the evaluation directory (#5223)

Co-authored-by: Engel Nyst <enyst@users.noreply.github.com>

evaluation/benchmarks/agent_bench/scripts/run_infer.sh

@@ -0,0 +1,42 @@
+#!/bin/bash
+set -eo pipefail
+
+source "evaluation/utils/version_control.sh"
+
+MODEL_CONFIG=$1
+COMMIT_HASH=$2
+AGENT=$3
+EVAL_LIMIT=$4
+NUM_WORKERS=$5
+
+if [ -z "$NUM_WORKERS" ]; then
+  NUM_WORKERS=1
+  echo "Number of workers not specified, use default $NUM_WORKERS"
+fi
+checkout_eval_branch
+
+if [ -z "$AGENT" ]; then
+  echo "Agent not specified, use default CodeActAgent"
+  AGENT="CodeActAgent"
+fi
+
+get_agent_version
+
+echo "AGENT: $AGENT"
+echo "AGENT_VERSION: $AGENT_VERSION"
+echo "MODEL_CONFIG: $MODEL_CONFIG"
+
+COMMAND="export PYTHONPATH=evaluation/benchmarks/agent_bench:\$PYTHONPATH && poetry run python evaluation/benchmarks/agent_bench/run_infer.py \
+  --agent-cls $AGENT \
+  --llm-config $MODEL_CONFIG \
+  --max-iterations 30 \
+  --eval-num-workers $NUM_WORKERS \
+  --eval-note $AGENT_VERSION"
+
+if [ -n "$EVAL_LIMIT" ]; then
+  echo "EVAL_LIMIT: $EVAL_LIMIT"
+  COMMAND="$COMMAND --eval-n-limit $EVAL_LIMIT"
+fi
+
+# Run the command
+eval $COMMAND