# Run 20260924T154403-swe-agent-sw-polyglot_python_bowling

- harness: [swe-agent-swe-agent](https://harnessreport.com/harnesses/swe-agent-swe-agent.md) @ 3ea751c087f3
- 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 · 10 failed, 21 passed
- model calls: 42  tokens in/out: 395498/10332
- agent seconds: 108
- started: 2026-09-24T15:44:05
- full bundle (calls, logs, files): https://harnessreport.com/api/run/20260924T154403-swe-agent-sw-polyglot_python_bowling

## Failed tests

- test_a_roll_cannot_score_more_than_10_points
- test_bonus_roll_after_a_strike_in_the_last_frame_cannot_score_more_than_10_points
- test_cannot_roll_after_bonus_roll_for_spare
- test_cannot_roll_after_bonus_rolls_for_strike
- test_cannot_roll_if_game_already_has_ten_frames
- test_rolls_cannot_score_negative_points
- test_second_bonus_roll_after_a_strike_in_the_last_frame_cannot_score_more_than_10_points
- 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
- test_two_rolls_in_a_frame_cannot_score_more_than_10_points

Last agent action: `submit: {}`
---
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