0390491c93
First concrete domain claim under ADR-0091's Domain Pack Contract v1. en_mathematics_logic_v1 is now formally ratified as reasoning-capable in the capability ledger: 9/9 ADR-0091 predicates pass. ADR-0097 §"No code changes outside pack artifacts and corpus" relaxed to include two latent bug fixes that ADR-0093's predicate enforcement just exposed: 1. language_packs/schema.py: LanguageRole enum widened to include DOMAIN_SEED. Three in-tree packs (en_mathematics_logic_v1, en_physics_v1, en_systems_software_v1) have declared role="domain_seed" since landing but the enum was never updated; load_pack() always raised on them. ADR-0093's P1 predicate exposed the mismatch. 2. core/capability/domain_contract_predicates.py: P2 (gloss checksum) was reading manifest["checksums"]["glosses_sha256"]; the canonical in-tree location is manifest["glosses_checksum"] (top-level). Fixed to prefer the canonical key and fall back to the nested form for forward compatibility. ADR-0097 manifest additions to en_mathematics_logic_v1: - domain_contract_version: 1 - domain_id: "mathematics_logic" - axioms: null (rules in v1 — pack proves reasoning via chain composition, not declarative axioms) - rules: null - teaching_chains: ["mathematics_logic_chains_v1"] - eval_lanes: three lanes with dev/public/holdout (elementary_mathematics_ood, inference_closure, fabrication_control) - reviewers: ["shay-j"] (resolved via ADR-0092 registry) - known_gaps: [] (all math/logic gaps in docs/gaps.md were [x]) - provenance: "adr-0097:reviewed:2026-05-21" Verified evidence: - core capability domain-contract --pack-id en_mathematics_logic_v1 → all_passed=True (P1-P9 all pass) - core capability ledger → mathematics_logic row shows status=reasoning-capable, predicates.reasoning_capable=True, predicates.expert_demo=False, open_gaps=[], operator_chain_coverage all ready=True (8 chains each), intent_shapes_present=5 - 14 ADR-0097 invariant tests in test_adr_0097_mathematics_logic_ratification.py pin status/provenance/expert-demo-gate/contract shape Two pre-existing tests updated for the new CLI default (predicate-running, non-zero on missing contract): - test_capability_domain_contract_json_absent_contract_is_noop now uses --structural-only to assert legacy parse-only shape - test_cli_returns_nonzero_on_missing_contract switched its fixture pack from en_mathematics_logic_v1 (now has a contract) to en_core_cognition_v1 (no contract) The pre-existing test_flag_report_tracks_default_off_flags failure (discourse_planner flag default mismatch, seen since ADR-0092) is unchanged and unrelated. Smoke 67/67, packs 6/6, capability tests 49/50, cognition eval byte-identical 100/100/100/100; lanes byte-identical: reviewer_registry 6/6, miner_loop_closure 6/6, domain_contract_validation 9/9, fabrication_control dev 12/12 + public 9/9.
129 lines
4.1 KiB
Python
129 lines
4.1 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
import subprocess
|
|
import sys
|
|
|
|
|
|
def _run(*args: str) -> subprocess.CompletedProcess[str]:
|
|
return subprocess.run(
|
|
[sys.executable, "-m", "core.cli", *args],
|
|
text=True,
|
|
capture_output=True,
|
|
check=False,
|
|
)
|
|
|
|
|
|
def test_capability_chains_json() -> None:
|
|
res = _run("capability", "chains", "--json")
|
|
assert res.returncode == 0, res.stderr
|
|
body = json.loads(res.stdout)
|
|
assert "active_chains" in body
|
|
assert "formula" in body
|
|
assert body["formula"]["chains_required"] == 200
|
|
assert body["formula"]["chains_present"] == body["active_chains"]
|
|
assert body["missing_target_intent_shapes"] == []
|
|
assert body["by_domain_operator_family"]["hebrew_greek_textual_reasoning"]["causal"] >= 8
|
|
assert body["by_domain_operator_family"]["hebrew_greek_textual_reasoning"]["contradiction"] >= 8
|
|
assert body["by_domain_operator_family"]["philosophy_theology"]["modal"] >= 8
|
|
assert body["by_domain_operator_family"]["philosophy_theology"]["contradiction"] >= 8
|
|
|
|
|
|
def test_capability_flags_json() -> None:
|
|
res = _run("capability", "flags", "--json")
|
|
assert res.returncode == 0, res.stderr
|
|
body = json.loads(res.stdout)
|
|
assert "flag_shipped_default_off" in body
|
|
|
|
|
|
def test_capability_ledger_json() -> None:
|
|
res = _run("capability", "ledger", "--json")
|
|
assert res.returncode == 0, res.stderr
|
|
body = json.loads(res.stdout)
|
|
assert "domains" in body
|
|
assert isinstance(body["domains"], list)
|
|
by_domain = {row["domain"]: row for row in body["domains"]}
|
|
for domain in (
|
|
"systems_software",
|
|
"mathematics_logic",
|
|
"physics",
|
|
"hebrew_greek_textual_reasoning",
|
|
"philosophy_theology",
|
|
):
|
|
assert by_domain[domain]["status"] == "reasoning-capable"
|
|
assert by_domain[domain]["open_gaps"] == []
|
|
he_grc = by_domain["hebrew_greek_textual_reasoning"]
|
|
assert he_grc["predicates"]["seeded"] is True
|
|
assert he_grc["status"] == "reasoning-capable"
|
|
assert "gap:grc_he_glosses_absent" not in he_grc["open_gaps"]
|
|
assert "gap:he_core_cognition_v1_gloss_coverage_below_threshold" not in he_grc["open_gaps"]
|
|
assert he_grc["open_gaps"] == []
|
|
assert all(
|
|
"chains_present" in coverage and "chains_required" in coverage
|
|
for coverage in he_grc["operator_chain_coverage"].values()
|
|
)
|
|
|
|
|
|
def test_capability_artifact_json_404() -> None:
|
|
res = _run(
|
|
"capability",
|
|
"artifact",
|
|
"--lane",
|
|
"cognition",
|
|
"--split",
|
|
"public",
|
|
"--version",
|
|
"v999",
|
|
"--json",
|
|
)
|
|
assert res.returncode == 0, res.stderr
|
|
body = json.loads(res.stdout)
|
|
assert body["exists"] is False
|
|
assert "artifact_id" in body
|
|
|
|
|
|
def test_capability_artifact_json_existing_is_content_addressed() -> None:
|
|
res = _run(
|
|
"capability",
|
|
"artifact",
|
|
"--lane",
|
|
"cognition",
|
|
"--split",
|
|
"public",
|
|
"--version",
|
|
"v1",
|
|
"--json",
|
|
)
|
|
assert res.returncode == 0, res.stderr
|
|
body = json.loads(res.stdout)
|
|
assert body["exists"] is True
|
|
assert len(body["artifact_id"]) == 64
|
|
assert len(body["result_sha256"]) == 64
|
|
|
|
|
|
def test_capability_domain_contract_json_absent_contract_is_noop() -> None:
|
|
"""Packs without a domain contract pass the legacy structural-only
|
|
path. ADR-0093 added the default predicate-running mode; this test
|
|
pins the legacy shape under ``--structural-only``.
|
|
"""
|
|
res = _run(
|
|
"capability",
|
|
"domain-contract",
|
|
"--pack-id",
|
|
"en_core_cognition_v1",
|
|
"--json",
|
|
"--structural-only",
|
|
)
|
|
assert res.returncode == 0, res.stderr
|
|
body = json.loads(res.stdout)
|
|
assert body["present"] is False
|
|
assert body["valid"] is True
|
|
|
|
|
|
def test_capability_evidence_plan_json() -> None:
|
|
res = _run("capability", "evidence-plan", "--json")
|
|
assert res.returncode == 0, res.stderr
|
|
body = json.loads(res.stdout)
|
|
assert body["workers_promote_packs"] is False
|
|
assert body["jobs"]
|
|
assert all(job["mutates_packs"] is False for job in body["jobs"])
|