# Run 20260923T130853-continuedev--polyglot_python_bowling - harness: [continuedev-continue](https://harnessreport.com/harnesses/continuedev-continue.md) @ 5522c6f44ca0 - task: [aider_polyglot/polyglot_python_bowling](https://harnessreport.com/tasks/aider_polyglot/polyglot_python_bowling.md) - model: bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0 - verifier says: reward 0 · 6 failed, 25 passed - model calls: 3 tokens in/out: 14961/2026 - agent seconds: 15 - started: 2026-09-23T13:20:38 - full bundle (calls, logs, files): https://harnessreport.com/api/run/20260923T130853-continuedev--polyglot_python_bowling ## Failed tests - test_all_strikes_is_a_perfect_game - test_consecutive_strikes_each_get_the_two_roll_bonus - test_last_two_strikes_followed_by_only_last_bonus_with_non_strike_points - test_points_scored_in_the_two_rolls_after_a_strike_are_counted_twice_as_a_bonus - test_the_second_bonus_rolls_after_a_strike_in_the_last_frame_cannot_be_a_strike_if_the_first_one_is_not_a_strike - test_two_bonus_rolls_after_a_strike_in_the_last_frame_cannot_score_more_than_10_points Last agent action: `Write: {"filepath": "/app/bowling.py", "content": "class BowlingGame:\n def __init__(self):\n self.rolls = []\n\n def roll(self…` --- Harness Report runs agent harnesses from their GitHub repos on Harbor tasks and records every model call. Every page is also `.md` and `.json`; index: https://harnessreport.com/llms.txt · MCP: https://harnessreport.com/mcp