unseen-eval groups 4-6: generic AX batch dispatcher (engine_trace on it), replay task and image stage, scorer with adoption gate

Implemented with Codex.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
Marius Ciepluch
2026-10-04 20:19:14 +02:00
co-authored by Claude Opus 5.5
parent 48ae918dec
commit c6e87a8517
20 changed files with 2952 additions and 305 deletions
+9 -1
View File
@@ -2,7 +2,7 @@
# preserve its runner as PID 1 and put the engine command in the Task manifest.
FROM eclipse-temurin:21-jre-jammy AS jre
FROM ghcr.io/norandom/ax-task-runner:v0.3.1
FROM ghcr.io/norandom/ax-task-runner:v0.3.1 AS engine
LABEL org.opencontainers.image.licenses="Apache-2.0" \
org.opencontainers.image.source="https://github.com/norandom/OpenUltraSAST"
@@ -50,3 +50,11 @@ RUN python3 -m venv /venv \
&& /venv/bin/python -I -c 'import pathlib, runpy, sys; sys.modules.update(yaml=None, boto3=None); sys.path.insert(0, "/app/benchmarks/learn"); p = pathlib.Path("/app/benchmarks/learn/engine_trace_worker.py"); print("Worker import smoke bytes:", len(p.read_bytes())); runpy.run_path(str(p), run_name="engine_worker_import_smoke")'
# Do not set ENTRYPOINT or CMD: both belong to the upstream AX runner.
FROM engine AS replay
RUN apt-get update \
&& apt-get install -y --no-install-recommends git \
&& rm -rf /var/lib/apt/lists/*
COPY benchmarks/unseen/replay_entry.py ./benchmarks/unseen/replay_entry.py
RUN /venv/bin/pip install --no-cache-dir . \
&& /venv/bin/ousast pre-push --help > /dev/null