Files
llm-intelligence/scripts/review/review_truth_guard_test.sh

63 lines
2.0 KiB
Bash
Raw Normal View History

#!/usr/bin/env bash
set -euo pipefail
ROOT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd)"
cd "$ROOT_DIR"
TMP_DIR="$(mktemp -d)"
trap 'rm -rf "$TMP_DIR"' EXIT
BAD_REPORT="$TMP_DIR/bad-review.md"
cat > "$BAD_REPORT" <<'EOF'
## Evidence
### Incomplete
- 未完成项:外部文档源仍不稳定
- 当前状态:已经恢复绿色
EOF
set +e
bash scripts/review/review_truth_guard.sh "$BAD_REPORT" >/tmp/review_truth_bad.out 2>&1
BAD_RC=$?
set -e
[[ "$BAD_RC" -ne 0 ]]
grep -q 'missing truth label' /tmp/review_truth_bad.out
GOOD_REPORT="$TMP_DIR/good-review.md"
cat > "$GOOD_REPORT" <<'EOF'
## Evidence
### Incomplete
- 未完成项:外部文档源仍不稳定
- 当前状态:`runtime-verified`;最近一轮 `verify_phase6.sh` 已通过,但此条仅代表当前快照,不代表历史报告中的旧 FAIL 仍然成立。
EOF
bash scripts/review/review_truth_guard.sh "$GOOD_REPORT" >/tmp/review_truth_good.out 2>&1
DRIFT_REPORT="$TMP_DIR/drift-review.md"
cat > "$DRIFT_REPORT" <<'EOF'
## Evidence
### Inconsistencies
- 伪进展或文档/实现不一致项:历史 review 仍保留旧 FAIL
- 证据:上一轮 review 写了 FAIL
- 当前状态:`runtime-verified`;当前 verify_phase6 已通过
EOF
set +e
bash scripts/review/review_truth_guard.sh "$DRIFT_REPORT" >/tmp/review_truth_drift.out 2>&1
DRIFT_RC=$?
set -e
[[ "$DRIFT_RC" -ne 0 ]]
grep -q 'missing truth label: historical status' /tmp/review_truth_drift.out
GOOD_DRIFT_REPORT="$TMP_DIR/good-drift-review.md"
cat > "$GOOD_DRIFT_REPORT" <<'EOF'
## Evidence
### Inconsistencies
- 伪进展或文档/实现不一致项:历史 review 仍保留旧 FAIL
- 历史状态:上一轮 review 记录为 FAIL
- 当前状态:`runtime-verified`;当前 verify_phase6 已通过
EOF
bash scripts/review/review_truth_guard.sh "$GOOD_DRIFT_REPORT" >/tmp/review_truth_good_drift.out 2>&1
grep -q 'REVIEW_TRUTH_GUARD: PASS' /tmp/review_truth_good_drift.out
grep -q 'REVIEW_TRUTH_GUARD: PASS' /tmp/review_truth_good.out