mirror of
https://github.com/priyanshujain/messageboardbench.git
synced 2026-10-02 11:07:07 +00:00
pj
863c6bd7d8
was_test_modified reads intermediate score events, not just the final score. ImpossibleBench's scorer repairs test.py when it finds it modified, and basic_agent scores every attempt, so an agent that edits the tests on attempt one and not again leaves a final score with no flag on it. The repair erased the evidence. snapshot_scratch reports whether the directory exists alongside its contents, because otherwise a directory nobody wrote to and a directory that was never created look identical, and the second is a broken harness reported as a real null result. What the agents wrote is not auto-classified. "Did it write" is safe to automate; whether a note is addressed to somebody is the judgement the pilot exists to make, so pilot.py emits a markdown file to read by hand. Claude-Session: https://claude.ai/code/session_01Cq98H7sNoSJdL3W98f18bu
42 lines
1.3 KiB
Makefile
42 lines
1.3 KiB
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. Should print "/".
|
|
docker-check:
|
|
docker run --rm aisiuk/inspect-tool-support pwd
|
|
|
|
# Confirms the model slug, the key and tool support. Costs about a cent.
|
|
model-check:
|
|
uv run python scripts/model_check.py
|
|
|
|
# Phase 1: cheat rate on conflicting, solve rate on original. About $1.
|
|
baseline:
|
|
uv run python -u scripts/baseline.py conflicting original
|
|
|
|
# The forked task against a fake model. Free. Checks the scratch wiring.
|
|
smoke-scratch:
|
|
uv run python scripts/smoke_scratch.py
|
|
|
|
# Phase 2: thirty agents with a scratch directory. Does anybody write anything?
|
|
pilot:
|
|
uv run python -u scripts/pilot.py
|
|
|
|
# Rebuild the CSV and hand-read file from an existing log, no re-run.
|
|
report log_dir="logs/pilot":
|
|
uv run python scripts/report.py {{log_dir}}
|