fix: 缺省匹配年度收敛最新年度 + 批量坏文件跳过 + 匹配理由据实化 + 职称档位补全（P1+P2）

scripts/service/match_service.py

@@ -28,19 +28,28 @@ TIER_NOT = "不建议"
 
 _TIER_RANK = {TIER_NOT: 0, TIER_TRY: 1, TIER_STRONG: 2}
 
-# 职称档位：数值越大越高职称；门槛 min_title 使用"X及以上"档位
+# 职称档位：数值越大越高职称；门槛 min_title 使用"X及以上"档位。
+# 助理教授按中级档从审处理（预聘制档次各校不一，宁缺勿滥）；
+# 未识别职称遇门槛赛道一律剔除并说明原因（审慎非激进）。
 _TITLE_RANK = {
     "助教": 0,
+    "初级": 0,
     "讲师": 1,
+    "中级": 1,
     "助理研究员": 1,
+    "助理教授": 1,
+    "工程师": 1,
     "博士后": 1,
     "副高及以上": 2,
     "副教授": 2,
     "副研究员": 2,
     "高级实验师": 2,
+    "高级工程师": 2,
     "正高及以上": 3,
     "教授": 3,
     "研究员": 3,
+    "教授级高级工程师": 3,
+    "正高级工程师": 3,
 }
 
 _STRONG_THRESHOLD = 80
@@ -197,7 +206,7 @@ def match_teacher(teacher: dict[str, Any], tracks: list[dict[str, Any]], season:
         if min_sci > 0:
             reasons.append(f"SCI一区余量：现有 {sci_q1} 篇 / 要求 {min_sci} 篇")
         if not reasons:
-            reasons.append("与赛道方向存在部分相关性")
+            reasons.append("现有研究标签与该赛道需求标签暂无重合，补充研究标签后可能改善匹配")
 
         if match_pct >= _STRONG_THRESHOLD:
             tier = TIER_STRONG
@@ -346,14 +355,17 @@ def run_match(
 
 
 def load_tracks(year: Optional[int] = None) -> list[dict[str, Any]]:
-    """读取赛道库（缺省全部年度；可按年度筛选）。"""
+    """读取赛道库（缺省取赛道库最新年度，与 actions.json 契约一致；显式传 year 按年度筛选）。"""
     conn = get_conn()
     try:
         cur = conn.cursor()
-        if year:
-            cur.execute("SELECT * FROM guide_tracks WHERE year = ? ORDER BY id", (year,))
-        else:
-            cur.execute("SELECT * FROM guide_tracks ORDER BY year DESC, id")
+        if year is None:
+            cur.execute("SELECT MAX(year) FROM guide_tracks")
+            row = cur.fetchone()
+            if not row or row[0] is None:
+                return []
+            year = int(row[0])
+        cur.execute("SELECT * FROM guide_tracks WHERE year = ? ORDER BY id", (year,))
         columns = [d[0] for d in cur.description]
         rows = [dict(zip(columns, row)) for row in cur.fetchall()]
     finally:
@@ -361,6 +373,35 @@ def load_tracks(year: Optional[int] = None) -> list[dict[str, Any]]:
     return rows
 
 
+def collect_input_teachers(input_dir: str) -> tuple[list[dict[str, Any]], list[dict[str, str]]]:
+    """读取 input/ 目录下的教师画像 JSON；坏文件跳过并记录原因，不中断整批。
+
+    返回 (教师列表, 跳过文件列表)；跳过文件形如 {"file": 名称, "reason": 原因}。
+    """
+    import os
+
+    files = sorted(
+        os.path.join(input_dir, name)
+        for name in os.listdir(input_dir)
+        if name.lower().endswith(".json")
+    )
+    teachers: list[dict[str, Any]] = []
+    skipped_files: list[dict[str, str]] = []
+    for path in files:
+        name = os.path.basename(path)
+        try:
+            with open(path, encoding="utf-8") as f:
+                payload = json.load(f)
+            if isinstance(payload, dict):
+                payload = payload.get("teachers") or [payload]
+            if not isinstance(payload, list):
+                raise ValueError("内容不是教师对象数组")
+            teachers.extend(item for item in payload if isinstance(item, dict))
+        except (OSError, ValueError) as exc:
+            skipped_files.append({"file": name, "reason": str(exc)})
+    return teachers, skipped_files
+
+
 def load_teachers(teacher_name: str = "") -> list[dict[str, Any]]:
     """读取教师画像（可按姓名精确筛选）。"""
     conn = get_conn()