Skip to content

Execution stops after round 0 #96

@z050209

Description

@z050209

Hi there,

I was trying to test run the BattleSnake__claude-sonnet-4-5-20250929__o3__r5__s1000.yaml, but it always stopped at the round 0. So I run using create API for claude and os3 with the following config file, it still stopped after round 0, There was no error message, it looks like the execution has timeout.. Anyone got this issue before?

Same as main BattleSnake claude-sonnet vs o3 r15, but WITHOUT model_class: portkey.

Use this if you don't have PORTKEY_API_KEY; set ANTHROPIC_API_KEY and OPENAI_API_KEY in .env instead.

Model names use provider/model (no @) so LiteLLM accepts them directly.

tournament:
rounds: 15
game:
name: BattleSnake
sims_per_round: 1000
args:
width: 11
height: 11
browser: false
players:

  • agent: mini
    name: claude-sonnet-4-5-20250929
    config:
    agent: !include mini/default.yaml
    model:
    model_name: 'anthropic/claude-sonnet-4-5-20250929'
    model_kwargs:
    temperature: 0.2
    max_tokens: 4096

  • agent: mini
    name: o3
    config:
    agent: !include mini/default.yaml
    model:
    model_name: 'openai/o3'
    prompts:
    game_description: |-
    You are a software developer ({{player_id}}) competing in a coding game called BattleSnake.
    Your bot (main.py) controls a snake on a grid-based board.
    Snakes collect food, avoid collisions, and try to outlast their opponents.

    The game is played in 15 rounds. For every round, you (and your competitors) edit program code that controls your bot. This is round {{round}}.
    After you and your competitor finish editing your codebases, the game is run automatically.

    Your task: improve the bot in main.py, located in {{working_dir}}.
    {{working_dir}} is your codebase, which contains both your both and supporting assets.
    All of your commands will be executed in the {{working_dir}} directory (see notes below).

Thanks.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions