feat: 全量標註的檢查、重標與合併工具 (#5)

verify_batches.py 逐批比對 id；make_relabel.py 挑出需重標的 none；
merge_labels.py 支援多個目錄覆蓋與 confidence 縮寫；worry 加入情緒白名單。

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

tools/corpus/merge_labels.py

@@ -22,6 +22,16 @@ def read_jsonl(path):
     return [json.loads(line) for line in Path(path).read_text(encoding="utf-8").splitlines() if line.strip()]
 
 
+# 有的批次輸出把 confidence 縮寫成一個字母；明確對應才轉換，其他值照常丟棄。
+CONFIDENCE_ALIASES = {"h": "high", "m": "medium", "l": "low"}
+
+
+def normalize(label):
+    if label.get("confidence") in CONFIDENCE_ALIASES:
+        return {**label, "confidence": CONFIDENCE_ALIASES[label["confidence"]]}
+    return label
+
+
 def check(label):
     errs = []
     if set(label) != KEYS:
@@ -38,14 +48,16 @@ def check(label):
 def main():
     ap = argparse.ArgumentParser()
     ap.add_argument("dialogues")
-    ap.add_argument("labels_dir")
+    ap.add_argument("labels_dir", help="標註輸出目錄；可用逗號接多個，後面的覆蓋前面的（用於重標）")
     ap.add_argument("out")
     ap.add_argument("--review-dir")
     a = ap.parse_args()
     recs = {r["id"]: r for r in read_jsonl(a.dialogues)}
     labels, rejected = {}, []
-    for f in sorted(Path(a.labels_dir).glob("*.jsonl")):
+    files = [f for d in a.labels_dir.split(",") for f in sorted(Path(d).glob("*.jsonl"))]
+    for f in files:
         for lb in read_jsonl(f):
+            lb = normalize(lb)
             errs = check(lb)
             if lb.get("id") not in recs:
                 errs.append("id 不存在")