mirror of
https://github.com/morluto/rea.git
synced 2026-11-12 09:52:27 +00:00
morlutoandCursor Agent
66498b4f7c
* fix(agentenv): bind solve results to the named verifier * fix(agentenv): retain a planned solve pass through selected-verifier binding Cleanup and cancellation tests plan a completed pass with no criterion rows. An empty selected-verifier result list is unscored, so those reports lost outcome passed even though sandbox retention and the cancellation cause were unchanged. Record one selected result for a planned pass or miss so the bound outcome stays the planned one. --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com>
73 lines
3.8 KiB
Python
73 lines
3.8 KiB
Python
"""Project selected verifier facts without importing or running agentenv."""
|
|
|
|
import unittest
|
|
from types import SimpleNamespace
|
|
|
|
from bridge.agentenv.solve import _solve_facts
|
|
|
|
|
|
def run_with(verifications, outcome="passed"):
|
|
return SimpleNamespace(context={"metadata": {"verifications": verifications}},
|
|
outcome=SimpleNamespace(value=outcome))
|
|
|
|
|
|
class SolveFactsTest(unittest.TestCase):
|
|
def test_matching_verifier_success_and_failure(self):
|
|
for passed, score, outcome in ((True, 1.0, "passed"), (False, 0.0, "scored below 1")):
|
|
with self.subTest(passed=passed):
|
|
run = run_with({"wanted": {"results": [{"id": "selected", "result": passed}],
|
|
"score": score}})
|
|
self.assertEqual(_solve_facts(run, "wanted"),
|
|
(outcome, [{"id": "selected", "passed": passed, "description": ""}]))
|
|
|
|
def test_missing_empty_and_unscored_selected_verifier_do_not_borrow_success(self):
|
|
other = {"results": [{"id": "unrelated", "result": True}], "score": 1.0}
|
|
for selected in (None, {}, {"results": [], "score": 1.0},
|
|
{"results": [{"id": 0, "result": False}]}):
|
|
for reversed_order in (False, True):
|
|
with self.subTest(selected=selected, reversed_order=reversed_order):
|
|
entries = [("other", other)]
|
|
if selected is not None:
|
|
entries.append(("wanted", selected))
|
|
if reversed_order:
|
|
entries.reverse()
|
|
expected = ([{"id": "0", "passed": False, "description": ""}]
|
|
if selected and selected.get("results") else [])
|
|
self.assertEqual(_solve_facts(run_with(dict(entries)), "wanted"),
|
|
("unscored", expected))
|
|
|
|
def test_selected_score_owns_outcome_and_checks_preserve_false_and_zero(self):
|
|
# A weighted/any-pass verifier's recorded score can pass despite a failed
|
|
# criterion; an unrelated failing score cannot override the selected one.
|
|
rows = [{"id": 0, "result": False}, {"id": "zero", "result": 0},
|
|
{"id": "yes", "result": True}]
|
|
checks = [{"id": "0", "passed": False, "description": ""},
|
|
{"id": "zero", "passed": False, "description": ""},
|
|
{"id": "yes", "passed": True, "description": ""}]
|
|
for score, expected in ((0, "scored below 1"), (0.5, "scored below 1"),
|
|
(1, "passed"), (1.5, "passed")):
|
|
with self.subTest(score=score):
|
|
verifications = {"other": {"score": 0},
|
|
"wanted": {"results": rows, "score": score}}
|
|
self.assertEqual(_solve_facts(run_with(verifications, "scored below 1"), "wanted"),
|
|
(expected, checks))
|
|
|
|
def test_failure_and_cancellation_preserve_partial_named_checks(self):
|
|
for outcome in ("failed", "cancelled"):
|
|
with self.subTest(outcome=outcome):
|
|
run = run_with({"wanted": {"results": [{"id": "partial", "result": True}],
|
|
"score": 1.0}}, outcome)
|
|
self.assertEqual(_solve_facts(run, "wanted"),
|
|
(outcome, [{"id": "partial", "passed": True, "description": ""}]))
|
|
|
|
def test_non_numeric_or_nonfinite_scores_remain_unscored(self):
|
|
for score in (None, True, "1", float("nan"), float("inf")):
|
|
with self.subTest(score=score):
|
|
run = run_with({"wanted": {"results": [{"id": "yes", "result": True}],
|
|
"score": score}})
|
|
self.assertEqual(_solve_facts(run, "wanted")[0], "unscored")
|
|
|
|
|
|
if __name__ == "__main__":
|
|
unittest.main()
|