74 lines
2.7 KiB
YAML
74 lines
2.7 KiB
YAML
name: AetherArena harness gate (ADR-149)
|
|
|
|
# Runs the AetherArena scoring harness as a PR build gate. Every PR that touches
|
|
# the scorer, the metrics, or the benchmark scaffold must keep the deterministic
|
|
# score hash stable (ADR-149 §2.5 determinism_gate). If the scoring maths changes,
|
|
# the hash moves and this gate fails until `expected_score.sha256` is regenerated
|
|
# and reviewed — so scorer drift can never land silently.
|
|
#
|
|
# This is the "a PR that runs the harness as part of the build process" requirement.
|
|
|
|
on:
|
|
pull_request:
|
|
paths:
|
|
- 'v2/crates/wifi-densepose-train/src/ruview_metrics.rs'
|
|
- 'v2/crates/wifi-densepose-train/src/ablation.rs'
|
|
- 'v2/crates/wifi-densepose-train/src/bin/aa_score_runner.rs'
|
|
- 'aether-arena/**'
|
|
- '.github/workflows/aether-arena-harness.yml'
|
|
push:
|
|
branches: ['feat/adr-149-aether-arena']
|
|
workflow_dispatch:
|
|
|
|
permissions:
|
|
contents: read
|
|
pull-requests: write
|
|
|
|
jobs:
|
|
harness-gate:
|
|
name: Run AA scorer harness (determinism gate)
|
|
runs-on: ubuntu-latest
|
|
defaults:
|
|
run:
|
|
working-directory: v2
|
|
steps:
|
|
- uses: actions/checkout@v4
|
|
|
|
- name: Install Rust toolchain
|
|
run: rustup show && rustc --version
|
|
|
|
- name: Cache cargo
|
|
uses: actions/cache@v4
|
|
with:
|
|
path: |
|
|
~/.cargo/registry
|
|
~/.cargo/git
|
|
v2/target
|
|
key: aa-harness-${{ runner.os }}-${{ hashFiles('v2/Cargo.lock') }}
|
|
|
|
# 1. Build the pure-Rust scorer (no torch / no GPU → fast PR gate).
|
|
- name: Build AA score runner
|
|
run: cargo build -p wifi-densepose-train --bin aa_score_runner --no-default-features
|
|
|
|
# 2. Determinism gate: the committed expected hash must still match. A
|
|
# non-zero exit here fails the PR.
|
|
- name: Run determinism gate
|
|
run: cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features
|
|
|
|
# 3. Emit the score row into the PR run summary (leaderboard-ledger shape).
|
|
- name: Score row → job summary
|
|
if: always()
|
|
run: |
|
|
ROW=$(cargo run -q -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --json)
|
|
{
|
|
echo "## AetherArena harness gate"
|
|
echo ""
|
|
echo "Deterministic score row (ADR-149 §2.2):"
|
|
echo '```json'
|
|
echo "$ROW"
|
|
echo '```'
|
|
echo ""
|
|
echo "If the determinism gate failed, the scoring maths changed: regenerate with"
|
|
echo '`cargo run -p wifi-densepose-train --bin aa_score_runner --no-default-features -- --generate-hash > aether-arena/fixtures/expected_score.sha256` and review the diff.'
|
|
} >> "$GITHUB_STEP_SUMMARY"
|