Add token tracking and benchmark tool

- Add LLMResponse type to core package with token usage fields
- Update LLMClient interface to return LLMResponse with token counts
- Aggregate tokens from both root LLM and sub-LLM (Query/QueryBatched) calls
- Expand system prompts with detailed examples for better structured output
- Add benchmark tool for comparing RLM vs baseline performance
- Include OOLONG dataset export script for benchmark data
- Update all tests to use new LLMResponse return type

Author: XiaoConstantine

cmd/benchmark/export_oolong.py

@@ -0,0 +1,50 @@
+#!/usr/bin/env python3
+"""Export OOLONG dataset to JSON for Go benchmark."""
+
+import json
+import sys
+from pathlib import Path
+
+
+def main():
+    try:
+        from datasets import load_dataset
+    except ImportError:
+        print("Error: datasets library not installed")
+        print("Install with: pip install datasets")
+        sys.exit(1)
+
+    num_tasks = int(sys.argv[1]) if len(sys.argv) > 1 else 10
+    output_file = sys.argv[2] if len(sys.argv) > 2 else "oolong_tasks.json"
+
+    print(f"Loading OOLONG dataset ({num_tasks} tasks)...")
+    dataset = load_dataset("oolongbench/oolong-synth", split="test")
+
+    tasks = []
+    for i, item in enumerate(dataset):
+        if i >= num_tasks:
+            break
+
+        answer = item.get("answer", "")
+        if isinstance(answer, list) and len(answer) > 0:
+            answer = str(answer[0])
+        elif isinstance(answer, str):
+            answer = answer.strip()
+
+        tasks.append({
+            "task_id": f"oolong_{i}",
+            "context": item.get("context_window_text", ""),
+            "question": item.get("question", ""),
+            "answer": answer,
+        })
+
+    print(f"Loaded {len(tasks)} tasks")
+
+    with open(output_file, "w") as f:
+        json.dump(tasks, f, indent=2)
+
+    print(f"Exported to: {output_file}")
+
+
+if __name__ == "__main__":
+    main()