ahbg

fix(ahbg): implement war_v3 resolver, canonical UCNS/corpus, truthful artifacts #16

	name: ahbg

	on:
	push:
	paths:
	- "ahbg/**"
	- "libs/ucns/**"
	- ".github/workflows/ahbg.yml"
	pull_request:
	paths:
	- "ahbg/**"
	- "libs/ucns/**"
	- ".github/workflows/ahbg.yml"

	permissions:
	contents: read

	jobs:
	grok-gates:
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v6
	- uses: actions/setup-python@v6
	with:
	python-version: "3.12"

	- name: Grok a0 tests
	working-directory: ahbg/grok
	run: python -m unittest discover -s a0/tests -p 'test*.py'

	- name: Grok ahbg tests
	working-directory: ahbg/grok
	run: python -m unittest discover -s ahbg/tests -p 'test*.py'

	- name: Grok common-corpus tests
	working-directory: ahbg/grok
	run: python -m unittest discover -s tests -p 'test*.py'

	- name: Grok smoke epoch run
	working-directory: ahbg/grok
	run: python run.py

	- name: Grok common corpus run (35 scenarios, temp output)
	working-directory: ahbg/grok
	shell: bash
	run: \|
	set -euo pipefail
	python run_common_corpus.py --output /tmp/ahbg-grok-corpus-run
	python - <<'PY'
	import json
	from pathlib import Path

	result = json.loads(
	Path("/tmp/ahbg-grok-corpus-run/CALIBRATION_RESULT.json").read_text(encoding="utf-8")
	)
	summary = result.get("summary", {})
	expected = {
	"survived": 35,
	"falsified": 0,
	"unresolved": 0,
	"blocked": 0,
	}
	if summary != expected or len(result.get("results", [])) != 35:
	raise SystemExit(
	f"common corpus is not clean: summary={summary!r}, results={len(result.get('results', []))}"
	)
	if not all(row.get("replay_equal") is True for row in result["results"]):
	raise SystemExit("common corpus contains a non-replay-equal scenario")
	PY

Navigation Menu