feat: add Oolong benchmark example with recursive rollouts

[alt-glitch]

hey @alexzhang13! adding an example from oolong bench to the examples/.
running this gives a proper RLM rollout that people can look at and play with.

PR Summary

• Adds an example demonstrating recursive RLM rollouts on the Oolong benchmark
• Previously, examples lacked coverage of recursive calls
• Loads context and question from oolongbench/oolong-real dataset
• Runs RLM completion with logging enabled
• Validates response against expected answer

[fundthmcalculus]

Suggested change

	def load_oolong_row(index: int = 1) -> dict:
	"""Load a single row from the Oolong benchmark."""
	streaming_ds = load_dataset("oolongbench/oolong-real", "toy_dnd", split="test", streaming=True)
	row = next(islice(streaming_ds, index, index + 1))
	return row
	def cp1252_fix(row: dict | str) -> dict | str:
	"""Fixes cp1252 encoding issues in dataset rows."""
	if isinstance(row, dict):
	for key, value in row.items():
	if isinstance(value, str):
	row[key] = value.encode('cp1252','replace').decode('cp1252')
	else:
	row = row.encode('cp1252','replace').decode('cp1252')
	return row
	def load_oolong_row(index: int = 1) -> dict:
	"""Load a single row from the Oolong benchmark."""
	streaming_ds = load_dataset("oolongbench/oolong-real", "toy_dnd", split="test", streaming=True)
	row = next(islice(streaming_ds, index, index + 1))
	return cp1252_fix(row)

Thanks for sharing this example! I noticed that cp1252 decoding is broken on windows, so here's a quick fix for that.