Skip to main content
This page describes how a submitted agent is structured and executed — from the fixed entrypoint contract enforced by the challenge to the autonomous loop inside the baseagent template.

​
The entrypoint contract

The Agent Challenge enforces a fixed entrypoint. Every submitted ZIP “must include agent.py at the archive root, and that file must define a top-level class Agent.” Production validators import agent:Agent; submitted_agent.py is not accepted as the entrypoint. (agent-challenge/docs/miner/README.md:106-108) The own-runner driver constructs the agent as Agent(logs_dir=, model_name=, **extra) (where extra may carry extra_env), then calls setup once before run. (agent-challenge/scripts/example_agent/agent.py:9-12) The contract method is (agent-challenge/scripts/example_agent/agent.py:53): 
async def run(self, instruction, environment, context):
    ...
environment.exec runs commands inside the task container, which is how an agent observes and modifies the task workspace. (agent-challenge/scripts/example_agent/agent.py:53-63)

​
The baseagent loop

The baseagent template runs an autonomous loop driven entirely by the model. Its Agent.run builds an LLMClient for the configured model, wires a HarborToolRegistry whose tools execute through environment.exec, and runs the agent loop until the task completes. (baseagent/agent.py:128-175) The high-level flow is (baseagent/README.md:135-167):
1

Initialize the session and build initial messages

The loop seeds the conversation and reads the terminal state.
2

Manage context

Prune or compact messages when the context grows too large, then apply prompt caching.
3

Call the model

The loop calls deepseek-v4-pro for the next action. (baseagent/README.md:147)
4

Execute tool calls

If the model returns tool calls, the loop executes them and feeds results back.
5

Self-verify and complete

With no tool calls, the loop injects a verification prompt; on the second pass it marks the task complete. (baseagent/README.md:155-165)

​
Context management

For long tasks the template estimates token usage and, when messages exceed 85% of usable context, scans backwards, protects the most recent 40,000 tool-output tokens, clears old outputs, and — if still over threshold — applies AI summarization. (baseagent/README.md:283-317, baseagent/src/config/defaults.py:46-53)

​
The isolated runtime

Agents are evaluated in isolated environments. The only secrets handed to the agent are the DeepSeek configuration variables, supplied through context.env: DEEPSEEK_API_KEY, DEEPSEEK_BASE_URL, LLM_MODEL, and LLM_COST_LIMIT. (agent-challenge/src/agent_challenge/evaluation/own_runner/isolation.py:13-15,64-67) Terminal-Bench production runs through own_runner, the only execution backend, which executes the runner image’s native Docker environment inside a privileged Docker-in-Docker runner launched as a broker job. (agent-challenge/README.md:92-95) Task containers run --network none unless a task opts in. (agent-challenge/README.md:265)
The agent reads DeepSeek configuration from context.env (and the process environment) — see Agent configuration for the exact variables.

​
Next steps

Tools & capabilities

The tool surface available to the agent.

How agents are evaluated

The submission lifecycle and isolated evaluation.