Jonathan KirkwoodandClaude Fable 5
b1d7aed9f4
- Deterministic scoring.py (quant 60 / qual 40 / flags -15, profitability heaviest) - Per-company JSON ledger with forecast-target chaining deck N-1 -> N - Single-shot sandbox agent with guided-JSON fallback ladder (no tool loop) - Portfolio dashboard with sparklines, KPI hit rates, BDEF category bars - 48 unit tests green; endpoints smoke-tested; npm check+build green Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
31 lines
1.4 KiB
Docker
31 lines
1.4 KiB
Docker
# Boardroom Map grader image — BUILT ON THE HEAD SPARK (aarch64), not packed into the
|
|
# s9pk (the orchestrator ships this build context and builds it on the Spark; see
|
|
# graders.ensure_grader_image).
|
|
#
|
|
# One-shot, read-only role agent (grader_agent.py; BM_ROLE = extractor | grader |
|
|
# adjudicator) speaking the OpenAI-compatible API directly — a lean pure-Python
|
|
# image that builds fast.
|
|
#
|
|
# At RUN time the orchestrator launches this HARDENED (non-root, --cap-drop ALL,
|
|
# --security-opt no-new-privileges, read-only rootfs, no docker socket, only
|
|
# /docs (ro), /BDEF.md (ro), /schema.json (ro), /persona (ro) and /out (rw)
|
|
# mounted — the adjudicator instead gets /grades (ro) + /extraction.json (ro) —
|
|
# cpu/mem/pid caps) and attached to the per-job network. In air-gapped mode that
|
|
# network is --internal, so the container can reach ONLY the on-Spark model proxy.
|
|
FROM python:3.11-slim
|
|
|
|
RUN apt-get update && apt-get install -y --no-install-recommends \
|
|
ca-certificates curl && \
|
|
rm -rf /var/lib/apt/lists/*
|
|
|
|
# Non-root user matching the orchestrator's --user 1000:1000 (HOME=/home/rev,
|
|
# mounted as a writable tmpfs at run time).
|
|
RUN useradd -u 1000 -m -d /home/rev -s /bin/bash reviewer || true
|
|
|
|
COPY grader_agent.py /opt/boardroom/grader_agent.py
|
|
|
|
WORKDIR /out
|
|
ENV PYTHONUNBUFFERED=1
|
|
# grader_agent.py uses only the Python stdlib (urllib) — no pip deps to install.
|
|
ENTRYPOINT ["python3", "/opt/boardroom/grader_agent.py"]
|