Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 6 additions & 1 deletion src/coder_eval/criteria/cli_called.py
Original file line number Diff line number Diff line change
Expand Up @@ -170,7 +170,12 @@ def _check_impl(
facets.append(f"flags={sorted(criterion.flags)}")
wanted = ", ".join(facets)

if score == 1.0:
if score == 1.0 and count == 0 and criterion.max_count == 0:
details = (
f"0 invocation(s) matched ({wanted}); guard unproven: a typo in verb, tool or flags "
"would also match nothing"
)
elif score == 1.0:
details = f"{count} invocation(s) matched ({wanted}); satisfies {bound}"
elif not within_lower:
# A bare count sends the reader to the sandbox; this criterion exists
Expand Down
13 changes: 12 additions & 1 deletion tests/test_cli_called_criterion.py
Original file line number Diff line number Diff line change
Expand Up @@ -237,7 +237,18 @@ def test_max_count_zero_is_the_negative_guard(self, sandbox_with_log):
min_count=0,
max_count=0,
)
assert SuccessChecker(sandbox).check(forbidden).score == 1.0
result = SuccessChecker(sandbox).check(forbidden)
assert result.score == 1.0
assert "guard unproven" in (result.details or "")
assert "satisfies" not in (result.details or "")

def test_positive_match_keeps_satisfies_wording(self, sandbox_with_log):
sandbox, sandbox_dir = sandbox_with_log
_write_log(sandbox_dir, [_call(["ixp", "fields", "rename", "proj-1"])])
criterion = CliCalledCriterion(description="renamed the field", log=LOG, verb="ixp fields rename")
result = SuccessChecker(sandbox).check(criterion)
assert result.score == 1.0
assert result.details == "1 invocation(s) matched (verb='ixp fields rename'); satisfies min_count=1"

def test_max_count_zero_fails_when_called(self, sandbox_with_log):
sandbox, sandbox_dir = sandbox_with_log
Expand Down
Loading