feat(pair-corpus-honesty): score non-vendored pointer pairs through a local cache

Task 8.3 (Req 10.1-10.5).

- pairs.py: catalog rows with vendored = false carry their harvest recipe
  and no excerpts; evaluate_catalog harvests them into
  OPENULTRASAST_PAIR_CACHE (default ~/.cache/openultrasast/pairs) only
  when `pairs --pointers` or OPENULTRASAST_PAIRS_NETWORK=1 allows the
  network, otherwise records pointer_pair_skipped (a failed fetch is
  pointer_pair_fetch_failed with detail); a warm cache never scores
  without the switch. select_vendored for tests and gates.
- harvest.py: materialize_pointer harvests into the cache without the
  license requirement (nothing is redistributed); redaction applies.
- catalog_gen.py: emits pointer rows with recipe fields; training
  manifests skip them.
- pair_gate and improve/evolve.evaluate_profiles score vendored pairs
  only; cli `pairs --pointers`; .gitignore covers the cache path.
- tests: loader, skip/degradation, cache hit, fetch failure, warm cache
  with network off, profile gate exclusion, harvest and generator paths;
  conftest keeps every test offline whatever the shell exports.

Co-Authored-By: Claude Fable 5.1 <[email protected]>
Claude-Session: https://claude.ai/code/session_01T7XD7x5KonMdmGRkp63EQG
This commit is contained in:
Marius Ciepluch
2026-09-05 10:45:43 +02:00
co-authored by Claude Fable 5.1
parent 7d238f2400
commit 4102404442
13 changed files with 405 additions and 21 deletions
+29
View File
@@ -293,3 +293,32 @@ def test_profile_gate_ignores_title_and_advisory_tiers(tmp_path: Path) -> None:
)
assert not outcome.accepted and outcome.reason == "profile_regression:agent"
assert outcome.per_profile_before["agent"]["pairs"] == 5.0 # the five title pairs are scored elsewhere, never here
def test_profile_gate_scores_vendored_pairs_only(tmp_path: Path, monkeypatch: pytest.MonkeyPatch) -> None:
"""Req 10.4 / design: gates call select_vendored; a pointer pair never reaches the improve gate, cached or not."""
from openultrasast.improve.evolve import evaluate_profiles
from openultrasast.pairs import PairCase
from openultrasast.ruleset import load_ruleset
monkeypatch.setenv("OPENULTRASAST_PAIRS_NETWORK", "1")
vendored = _pair(
tmp_path, "v", "def h(y):\n return eval(y)\n", "def h(y):\n return y\n", "python-unsafe-eval", "eval", provenance="human"
)
pointer_src = tmp_path / "cache" / "github" / "p"
pointer_src.mkdir(parents=True)
(pointer_src / "vuln.py").write_text("def h(y):\n return eval(y)\n")
(pointer_src / "fixed.py").write_text("def h(y):\n return y\n")
pointer = PairCase(
**{
**vendored.__dict__,
"name": "p",
"provenance": "agent",
"vendored": False,
"vuln_file": pointer_src / "vuln.py",
"fixed_file": pointer_src / "fixed.py",
"recipe": (("repo", "o/r"), ("parent", "a"), ("commit", "b"), ("path", "app.py"), ("mode", "name")),
}
)
profiles = evaluate_profiles([vendored, pointer], load_ruleset())
assert set(profiles) == {"human"} # the agent pointer pair is scored by `pairs --pointers`, never by the gate