mirror of
https://github.com/priyanshujain/messageboardbench.git
synced 2026-10-02 11:07:07 +00:00
pj
bf3bb0d144
Public from commit one, so no key ever enters this history. compose.yaml is ImpossibleBench's, plus working_dir: /workspace. The image has no WORKDIR, so inspect resolves it to "/" and the task files land at the filesystem root among twenty-odd entries. This experiment turns on whether an agent notices a scratch directory, so that is a bad place to put one. ImpossibleBench installs with --no-deps to keep the swebench tree out; datasets is declared here instead because hf_dataset genuinely needs it. Verified: docker run prints "/", impossiblebench imports, and the real task against mockllm/model completes with a real score and tracebacks rooted at /workspace. Claude-Session: https://claude.ai/code/session_01Cq98H7sNoSJdL3W98f18bu
23 lines
694 B
Makefile
23 lines
694 B
Makefile
# All recipes run from the repo root, because inspect resolves compose.yaml against the
|
|
# process working directory. See docs/setup.md.
|
|
|
|
impossiblebench := "../impossiblebench"
|
|
|
|
# Sync dependencies, then re-add ImpossibleBench (uv sync prunes it).
|
|
install:
|
|
uv sync
|
|
uv pip install -e {{impossiblebench}} --no-deps
|
|
|
|
# Offline unit tests. No network, no provider beyond mockllm.
|
|
test:
|
|
uv run pytest -q
|
|
|
|
# The real task against a fake model. Free.
|
|
smoke:
|
|
uv run python scripts/smoke_mock.py
|
|
|
|
# Confirms the daemon is up and pre-pulls the image so the first eval does not
|
|
# time out on a cold pull. Should print "/".
|
|
docker-check:
|
|
docker run --rm aisiuk/inspect-tool-support pwd
|