feat: 补 MIT 许可、自动抓取工具与学科覆盖元数据

登记 chinese-poetry / ck12 / phet，并让 source schema、lint 与 INDEX 能按学科和抓取进度消费。

Co-authored-by: Cursor <cursoragent@cursor.com>

sources/exams/cepoc.yaml

@@ -8,23 +8,27 @@ sources:
     license_note: "研究/教育用途，非商业（见仓库 licence.txt）"
     fetch_method: git-clone
     status: fetched
+    subjects: [ket, pet, fce, english]
+    stages: [primary, junior]
     fetched_at: "2026-08-21"
     items:
       - id: cepoc-ket-json
-        title: KET.json（6套68空）
+        title: KET.json（6套完形）
         oss_key: edu-raw/exams/ket/questions/cepoc/KET.json
+        src_path: KET.json
         sha256: null
         size: null
         media_type: application/json
         fetch_date: "2026-08-21"
         status: planned
-        note: "latin1 编码；清洗为 qb-1.1 落 structured/exams/ket/questions/cepoc-a2-key.jsonl"
+        note: "latin1 编码 JSONL；清洗为 qb-1.1 落 structured/exams/ket/questions/cepoc-a2-key.jsonl"
       - id: cepoc-b1-json
-        title: B1 Preliminary.json（含 FCE 36套360空）
-        oss_key: edu-raw/exams/pet/questions/cepoc/B1-Preliminary.json
+        title: PET.json（21套完形，即 B1 Preliminary）
+        oss_key: edu-raw/exams/pet/questions/cepoc/PET.json
+        src_path: PET.json
         sha256: null
         size: null
         media_type: application/json
         fetch_date: "2026-08-21"
         status: planned
-        note: "清洗为 qb-1.1 落 structured/exams/pet/questions/cepoc-b1-preliminary.jsonl"
+        note: "repo 实际文件名为 PET.json（此前误登记为 B1-Preliminary.json）；清洗落 structured/exams/pet/questions/cepoc-b1-preliminary.jsonl"