Trial.run() call, and a task is fully described by four files
(instruction.md, Dockerfile, test.sh, task.toml), so mixed task suites —
SWE-bench, Terminal-Bench, custom tasks — train through one endpoint.
Miles integrates Harbor as an
agent-function integration: the agent function
hands each session’s OpenAI-compatible URL to a Harbor server, which runs the
per-task container, installs and runs the agent against that URL, and grades
the result; the grade becomes the sample’s reward through a custom reward
hook.
Try it
The maintained recipe lives inexamples/swe-agent,
with synchronous and fully-async launchers. Follow the
recipe README
for the architecture, Harbor server setup, task format, and launch scripts.