From 830f156c6743ce3404ffafc84d1ede8301fb6c56 Mon Sep 17 00:00:00 2001 From: jon-devlapaz Date: Wed, 2 Sep 2026 00:38:37 -0500 Subject: [PATCH] fix: pass the CI git whitespace check Main's validate job failed git diff --check on trailing spaces and extra blank lines at EOF. Strip those without changing behavior. Co-authored-by: Cursor --- AGENTS.md | 3 --- docs/ux-ergonomics-and-harness-friction-spec.md | 10 +++++----- tests/helpers.py | 1 - tests/test_calibration.py | 1 - tests/test_harnesses.py | 3 +-- tests/test_judging.py | 3 +-- tests/test_review.py | 1 - tests/test_tasks.py | 1 - 8 files changed, 7 insertions(+), 16 deletions(-) diff --git a/AGENTS.md b/AGENTS.md index 16a2253..a4cc248 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -3,6 +3,3 @@ ## Maintainability Follow the maintainability principles in [ZEN.md](ZEN.md). - - - diff --git a/docs/ux-ergonomics-and-harness-friction-spec.md b/docs/ux-ergonomics-and-harness-friction-spec.md index fa959cc..eddd76b 100644 --- a/docs/ux-ergonomics-and-harness-friction-spec.md +++ b/docs/ux-ergonomics-and-harness-friction-spec.md @@ -1,8 +1,8 @@ # RFC: Evaluator UX Ergonomics & Multi-Harness Operational Polish -**Status**: Implemented (2026-09-01) -**Date**: 2026-08-31 -**Author**: Antigravity Agent +**Status**: Implemented (2026-09-01) +**Date**: 2026-08-31 +**Author**: Antigravity Agent **Context**: Post-Phase 2 dogfooding findings against live agent CLIs (`cursor-agent`, `muse`, `codex`) Implemented against the 2026-09-01 harness-agnostic runner. Deviations from the @@ -82,7 +82,7 @@ def discover_executable(executable_name: str) -> str: found = shutil.which(executable_name) if found: return found - + # 2. Known standard user/system bin directories candidates = [ Path.home() / ".local" / "bin", @@ -99,7 +99,7 @@ def discover_executable(executable_name: str) -> str: target = directory / executable_name if target.is_file() and os.access(target, os.X_OK): return str(target) - + raise ValueError( f"executable {executable_name!r} not found in PATH or standard binary locations (~/.local/bin, /opt/homebrew/bin, etc.). " f"Please supply --harness-bin /path/to/{executable_name}" diff --git a/tests/helpers.py b/tests/helpers.py index 5c92868..3489b45 100644 --- a/tests/helpers.py +++ b/tests/helpers.py @@ -180,4 +180,3 @@ def run_calibrate( env=self.isolated_env(root, extra_env), ) return result, output - diff --git a/tests/test_calibration.py b/tests/test_calibration.py index 2684a2c..7832d69 100644 --- a/tests/test_calibration.py +++ b/tests/test_calibration.py @@ -459,4 +459,3 @@ def test_react_v2_tasks_require_react_review_calibration_dimensions(self) -> Non ) self.assertEqual(result.returncode, 2, result.stderr) self.assertIn("primary_diagnosis", result.stderr) - diff --git a/tests/test_harnesses.py b/tests/test_harnesses.py index d3fe223..a1c13dd 100644 --- a/tests/test_harnesses.py +++ b/tests/test_harnesses.py @@ -697,7 +697,7 @@ def test_script_harness_live_execution(self) -> None: skill = self.make_skill(root) tasks = root / "tasks.jsonl" tasks.write_text(json.dumps({"id": "t1", "prompt": "say hello", "graders": [{"type": "response_not_empty"}]}) + "\n", encoding="utf-8") - + runner_script = root / "custom_runner.py" runner_script.write_text( '#!/usr/bin/env python3\n' @@ -1008,4 +1008,3 @@ def test_long_invocation_emits_stderr_heartbeats(self) -> None: self.assertIn(result.returncode, {0, 1}, result.stderr) self.assertIn("still running... (elapsed:", result.stderr) self.assertRegex(result.stderr, r"elapsed: 1[5-9]s") - diff --git a/tests/test_judging.py b/tests/test_judging.py index 9802160..83b7816 100644 --- a/tests/test_judging.py +++ b/tests/test_judging.py @@ -299,7 +299,7 @@ def test_extract_json_payload_handles_markdown_fences(self) -> None: self.assertEqual(evaluator.extract_json_payload(raw_json), raw_json) self.assertEqual(evaluator.extract_json_payload(fenced_json), raw_json) self.assertEqual(evaluator.extract_json_payload(fenced_plain), raw_json) - + parsed = evaluator.load_judge_json(fenced_json) self.assertEqual(parsed["dimensions"][0]["name"], "safe choice") @@ -409,4 +409,3 @@ def test_cross_harness_judge_produces_independent_quality_evidence(self) -> None pairwise = pair_report["pairwise"][0] self.assertEqual(pairwise["status"], "independent") self.assertEqual(pairwise["reason"], "cross_provider_independent_judge") - diff --git a/tests/test_review.py b/tests/test_review.py index 189a73d..d0e87a1 100644 --- a/tests/test_review.py +++ b/tests/test_review.py @@ -212,4 +212,3 @@ def test_finalize_review_rejects_incomplete_or_non_independent_labels(self) -> N tampered = self.run_cli(*arguments) self.assertEqual(tampered.returncode, 1) self.assertIn("prompt hash does not match the manifest", tampered.stderr) - diff --git a/tests/test_tasks.py b/tests/test_tasks.py index c60ae87..b3b2af2 100644 --- a/tests/test_tasks.py +++ b/tests/test_tasks.py @@ -561,4 +561,3 @@ def test_react_v2_quality_suite_dry_run_without_calibration(self) -> None: for dimension in grader["dimensions"] } self.assertEqual(names, {"primary_diagnosis", "actionable_fix", "grounded_claims"}) -