Skip to content

eval: add discoverable DeltaWire v7 pair boundary #1

eval: add discoverable DeltaWire v7 pair boundary

eval: add discoverable DeltaWire v7 pair boundary #1

Workflow file for this run

name: DeltaWire v7 no-live validation
on:
push:
branches: [eval/deltawire-v7]
paths:
- "labs/20-deltawire/**"
- ".github/workflows/deltawire-v7.yml"
pull_request:
paths:
- "labs/20-deltawire/**"
- ".github/workflows/deltawire-v7.yml"
permissions:
contents: read
jobs:
validate-v7:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v7
with:
fetch-depth: 0
- uses: actions/setup-go@v6
with:
go-version-file: labs/20-deltawire/go.mod
cache-dependency-path: labs/20-deltawire/go.sum
- uses: actions/setup-python@v6
with:
python-version: "3.12"
- uses: astral-sh/setup-uv@v7
- name: Build and stage the frozen Linux binary
run: |
cd labs/20-deltawire
mkdir -p eval/.generated eval/pairs/range-large-v7-r1/environment/.generated
GOWORK=off CGO_ENABLED=0 GOOS=linux GOARCH=amd64 go build -trimpath -o eval/.generated/deltawire-linux-amd64 ./cmd/deltawire
cp eval/.generated/deltawire-linux-amd64 eval/pairs/range-large-v7-r1/environment/.generated/deltawire
test "$(sha256sum eval/.generated/deltawire-linux-amd64 | cut -d' ' -f1)" = e5198d15000e093a2a28e57ad4a093dde8f66bcab21462549ddf9114064c25f4
- name: Validate skill examples using the actual Linux binary
run: |
python3 labs/20-deltawire/eval/scripts/v7/skill_conformance.py \
--skill labs/20-deltawire/eval/pairs/range-large-v7-r1/skill/deltawire \
--binary labs/20-deltawire/eval/.generated/deltawire-linux-amd64 \
--report /tmp/skill-conformance.json
if test -f labs/20-deltawire/eval/results/preflight-v7/skill-conformance.json; then
cmp /tmp/skill-conformance.json labs/20-deltawire/eval/results/preflight-v7/skill-conformance.json
fi
- name: No-live v7 validation
run: bash labs/20-deltawire/eval/scripts/v7/validate.sh
- name: Prove workflow has no model invocation
run: |
! grep -E 'runner.py .*pair-v7|harbor run|GEMINI_API_KEY' .github/workflows/deltawire-v7.yml