auto backup: 2026-05-30 08:10:01

business_production/组件配置/interactive-component-json/scripts/match_component.py

@@ -94,6 +94,10 @@ def match_component_type(type_text: str) -> dict:
         has_image = True
         text = text.replace("+图片", "").strip()
     
+    # 剥离任意"-"前缀（如 "核心互动-听力选择" → "听力选择"，"-配图"/"+图片"已在上方处理）
+    if '-' in text:
+        text = text.split('-', 1)[1].strip()
+
     # 优先匹配中互动
     if text in MID_INTERACTION_TYPES:
         info = MID_INTERACTION_TYPES[text]

business_production/组件配置/interactive-component-json/scripts/parse_script.py

@@ -243,10 +243,29 @@ def extract_component_id(type_cell):
     # --- 策略3: 经典单行格式（只有一行，ID在第二行）---
     if cId is None and len(lines) >= 2:
         id_candidate = lines[1]
-        if re.match(r'^\d+$', id_candidate):
+        if re.match(r'^\d{5,}$', id_candidate):
             cId = id_candidate
             type_part = lines[0]
 
+    # --- 策略4: 单行 "【核心互动：X】N" 格式 (如 "【核心互动：写作】15") ---
+    if cId is None and len(lines) == 1:
+        m = re.match(r'^[【\[]\s*核心互动[：:]\s*(.+?)[】\]]\s*(\d{1,4})$', lines[0])
+        if m:
+            type_part = m.group(1).strip()
+            cId = m.group(2)
+
+    # --- 策略5: 单行 "类型名N" 格式 (如 "对话朗读1", "图片多选3", "对话挖空11") ---
+    if cId is None and len(lines) == 1:
+        m = re.match(r'^(.+?)(\d{1,4})$', lines[0])
+        if m:
+            candidate = m.group(1).strip()
+            cId = m.group(2)
+            # 仅当候选类型包含中文且不在非组件标记中
+            if re.search(r'[\u4e00-\u9fff]', candidate) and candidate not in non_component_markers:
+                type_part = candidate
+            else:
+                cId = None
+
     # 如果依然无 type_part，用第一行
     if type_part is None and lines:
         type_part = lines[0]
@@ -391,41 +410,146 @@ def extract_section_character_map(markdown):
     # Parse table rows
     rows = re.findall(r'<lark-tr>(.*?)</lark-tr>', table_html, re.DOTALL)
 
-    char_pattern = re.compile(r'(\d{2,})[-_]([A-Za-z]{2,})')
+    char_pattern = re.compile(r'(\d{2,})[-_]([A-Za-z]{2,}(?:[（(][^)）]+[)）])?)')
     section_range_pattern = re.compile(r'S(\d+)(?:\s*-\s*S(\d+))?', re.IGNORECASE)
+    # Mode 2: separate columns "Vicky" | "658"
+    name_only_pattern = re.compile(r'^[A-Za-z]{2,}(?:[（(][^)）]+[)）])?$')
+    id_only_pattern = re.compile(r'^\d{2,}$')
 
     entries = []
     current_sections = []  # carry forward from previous row if empty
 
+    # Auto-detect table format by checking first data row
+    # Mode 1: "658-Vicky" in one cell (char_pattern matches)
+    # Mode 2: "Vicky" | "658" separate columns (name_only + id_only)
+    # Within mode 1, also detect swapped (char, section) column order
+    table_mode = None  # "combined" or "separate"
+    swapped = False
+    for row_html in rows:
+        cells = re.findall(r'<lark-td>(.*?)</lark-td>', row_html, re.DOTALL)
+        if len(cells) < 2:
+            continue
+        c0, c1 = cells[0].strip(), cells[1].strip()
+        if not c0 and not c1:
+            continue
+        # Check mode 2 first: separate name and id columns
+        if name_only_pattern.match(c0) and id_only_pattern.match(c1):
+            table_mode = "separate"
+            logger.info("角色-section表格格式为分列 (名称 | ID)，自动适配")
+            break
+        if id_only_pattern.match(c0) and name_only_pattern.match(c1):
+            table_mode = "separate_swapped"
+            logger.info("角色-section表格格式为分列 (ID | 名称)，自动适配")
+            break
+        # Check mode 1: combined pattern
+        if char_pattern.search(c0) or char_pattern.search(c1):
+            table_mode = "combined"
+            if char_pattern.search(c0) and not char_pattern.search(c1):
+                swapped = True
+                logger.info("角色-section表格列序为 (角色, section)，自动交换")
+            break
+        break
+
     for row_html in rows:
         cells = re.findall(r'<lark-td>(.*?)</lark-td>', row_html, re.DOTALL)
         if len(cells) < 2:
             continue
 
-        section_cell = cells[0].strip()
+        if table_mode == "separate":
-        char_cell = cells[1].strip()
+            # Mode 2: col 0 = name, col 1 = id, col 2 (if exists) = section
-
+            name_cell, id_cell = cells[0].strip(), cells[1].strip()
-        # Parse section range
+            section_cell = cells[2].strip() if len(cells) > 2 else ""
-        if section_cell:
+            char_name = name_cell
-            sections = []
+            # Normalize Chinese brackets
-            for sm in section_range_pattern.finditer(section_cell):
+            char_name = char_name.replace('（', '(').replace('）', ')')
-                start = int(sm.group(1))
+            # Capitalize base name, preserve case inside parens
-                end = int(sm.group(2)) if sm.group(2) else start
+            paren_idx = char_name.find('(')
-                for s in range(start, end + 1):
+            if paren_idx > 0:
-                    sections.append(f"S{s}")
+                char_name = char_name[:paren_idx].capitalize() + char_name[paren_idx:]
-            if sections:
+            else:
-                current_sections = sections
+                char_name = char_name.capitalize()
-
+            if not char_name or not id_cell:
-        # Parse character
+                continue
-        char_match = char_pattern.search(char_cell)
+            char_id = int(id_cell)
-        if char_match:
+            # Parse section range if present
-            char_id = int(char_match.group(1))
+            if section_cell:
-            char_name = char_match.group(2).capitalize()
+                sections = []
+                for sm in section_range_pattern.finditer(section_cell):
+                    start = int(sm.group(1))
+                    end = int(sm.group(2)) if sm.group(2) else start
+                    for s in range(start, end + 1):
+                        sections.append(f"S{s}")
+                if sections:
+                    current_sections = sections
             entries.append({
                 "sections": list(current_sections),
                 "characters": {char_name: char_id},
             })
 
+        elif table_mode == "separate_swapped":
+            # Mode 2 swapped: col 0 = id, col 1 = name
+            id_cell, name_cell = cells[0].strip(), cells[1].strip()
+            section_cell = cells[2].strip() if len(cells) > 2 else ""
+            char_name = name_cell
+            char_name = char_name.replace('（', '(').replace('）', ')')
+            paren_idx = char_name.find('(')
+            if paren_idx > 0:
+                char_name = char_name[:paren_idx].capitalize() + char_name[paren_idx:]
+            else:
+                char_name = char_name.capitalize()
+            if not char_name or not id_cell:
+                continue
+            char_id = int(id_cell)
+            if section_cell:
+                sections = []
+                for sm in section_range_pattern.finditer(section_cell):
+                    start = int(sm.group(1))
+                    end = int(sm.group(2)) if sm.group(2) else start
+                    for s in range(start, end + 1):
+                        sections.append(f"S{s}")
+                if sections:
+                    current_sections = sections
+            entries.append({
+                "sections": list(current_sections),
+                "characters": {char_name: char_id},
+            })
+
+        else:
+            # Mode 1: combined pattern in one cell
+            if swapped:
+                char_cell, section_cell = cells[0].strip(), cells[1].strip()
+            else:
+                section_cell, char_cell = cells[0].strip(), cells[1].strip()
+
+            # Parse section range
+            if section_cell:
+                sections = []
+                for sm in section_range_pattern.finditer(section_cell):
+                    start = int(sm.group(1))
+                    end = int(sm.group(2)) if sm.group(2) else start
+                    for s in range(start, end + 1):
+                        sections.append(f"S{s}")
+                if sections:
+                    current_sections = sections
+
+            # Parse character (capture optional parenthetical suffix like "May（NoDiDi）")
+            char_match = char_pattern.search(char_cell)
+            if char_match:
+                char_id = int(char_match.group(1))
+                raw_name = char_match.group(2)
+                # Normalize Chinese brackets to ASCII for consistency
+                raw_name = raw_name.replace('（', '(').replace('）', ')')
+                # Capitalize the base name but preserve case inside parentheses
+                paren_idx = raw_name.find('(')
+                if paren_idx > 0:
+                    char_name = raw_name[:paren_idx].capitalize() + raw_name[paren_idx:]
+                else:
+                    char_name = raw_name.capitalize()
+                entries.append({
+                    "sections": list(current_sections),
+                    "characters": {char_name: char_id},
+                })
+
     logger.info(f"提取角色-section对应: {len(entries)} 条记录")
     return entries
 
@@ -479,7 +603,7 @@ def extract_character_map(sheet_rows):
     char_map = {}
     # 正则匹配 "数字-名字" 或 "数字_名字" 模式
     # 名字至少2个字母，避免匹配 L1_S02 之类的剧本标记
-    pattern = re.compile(r'(\d{2,})[-_]([A-Za-z]{2,})')
+    pattern = re.compile(r'(\d{2,})[-_]([A-Za-z]{2,}(?:[（(][^)）]+[)）])?)')
 
     for row in sheet_rows[:30]:  # 角色表通常在前 30 行
         for cell in row:
@@ -491,8 +615,13 @@ def extract_character_map(sheet_rows):
                 # 过滤掉明显不是角色名的（纯大写短标记如 "TA"）
                 if len(char_name) <= 2 and char_name.isupper():
                     continue
-                # 统一首字母大写
+                # 统一首字母大写，标准化括号
-                normalized = char_name.capitalize()
+                raw = char_name.replace('（', '(').replace('）', ')')
+                paren_idx = raw.find('(')
+                if paren_idx > 0:
+                    normalized = raw[:paren_idx].capitalize() + raw[paren_idx:]
+                else:
+                    normalized = raw.capitalize()
                 if normalized not in char_map:
                     char_map[normalized] = char_id
 
@@ -573,6 +702,12 @@ def parse_sheet_rows(sheet_rows, llm_client=None):
         type_cell = row[type_col] if len(row) > type_col else None
         comp_info = extract_component_id_with_llm_fallback(type_cell, llm_client)
 
+        # 如果类型列提取的cId是短序号（<5位，如1/2/3），但有独立ID列，优先用独立ID列覆盖
+        if comp_info is not None and id_col is not None and len(comp_info.get("cId", "")) < 5:
+            raw_id = str(row[id_col]).strip() if len(row) > id_col and row[id_col] else ""
+            if raw_id and re.match(r'^\d{5,}$', raw_id):
+                comp_info["cId"] = raw_id
+
         # 如果类型列没有嵌入式ID，但有独立ID列且类型名是纯中文组件名
         if comp_info is None and id_col is not None:
             raw_cell = str(row[id_col]).strip() if len(row) > id_col and row[id_col] else ""

business_production/组件配置/interactive-component-json/scripts/pipeline.py

@@ -197,7 +197,7 @@ def _ensure_proxy_running():
     return proxy_url
 
 
-def process_script(wiki_url_or_token, db_path=None, dry_run=False):
+def process_script(wiki_url_or_token, db_path=None, dry_run=False, target_cids=None):
     """
     端到端处理一个剧本文档
 
@@ -205,6 +205,7 @@ def process_script(wiki_url_or_token, db_path=None, dry_run=False):
         wiki_url_or_token: 飞书 wiki URL 或 wiki_token
         db_path: SQLite 数据库路径（默认使用 db/components.db）
         dry_run: 如果为 True，只生成不写入DB
+        target_cids: 可选的组件 ID 集合，仅处理这些 ID 的组件
 
     Returns:
         dict: 处理报告
@@ -280,11 +281,25 @@ def process_script(wiki_url_or_token, db_path=None, dry_run=False):
     parsed = best_parsed
     character_map = parsed["character_map"]
     section_char_map = parsed.get("section_char_map", [])
+
+    # 如果 sheet 中没有角色信息，从 section_char_map 中合并
+    if not character_map and section_char_map:
+        for entry in section_char_map:
+            for name, cid in (entry.get("characters", {})).items():
+                if name not in character_map:
+                    character_map[name] = cid
+        if character_map:
+            logger.info(f"从 section_char_map 合并角色映射: {character_map}")
     components = parsed["components"]
     # 更新 doc_data 中的 sheet_rows 为匹配到的那个
     if best_sheet_rows is not None:
         doc_data["sheet_rows"] = best_sheet_rows
     report["total_components"] = len(components)
+    if target_cids:
+        target_set = set(int(c) if isinstance(c, str) else c for c in target_cids)
+        components = [c for c in components if int(c.get("cId", 0)) in target_set]
+        logger.info(f"按 --cids 过滤后: {len(components)} 个组件, 目标ID: {target_set}")
+        report["total_components"] = len(components)
     logger.info(f"最终识别到 {len(components)} 个组件, 角色映射: {character_map}, section映射: {len(section_char_map)}条")
 
     # Step 3: 初始化DB
@@ -292,8 +307,17 @@ def process_script(wiki_url_or_token, db_path=None, dry_run=False):
         init_db()
         logger.info(f"数据库已初始化")
 
+    if not components:
+        logger.warning("没有组件需要处理")
+        report["success"] = 0
+        report["failed"] = 0
+        report["skipped"] = 0
+        report["results"] = []
+        return report
+
     # Step 4: 并行组件生成
-    logger.info(f"=== Step 3: 并行组件生成 jsonData/kpInfo (workers=4) ===")
+    max_workers = min(4, len(components))
+    logger.info(f"=== Step 3: 并行组件生成 jsonData/kpInfo (workers={max_workers}) ===")
 
     # 提取元数据
     metadata = parsed.get("metadata", {})
@@ -668,6 +692,13 @@ if __name__ == "__main__":
         if idx + 1 < len(sys.argv):
             limit = int(sys.argv[idx + 1])
 
+    # 支持 --cids 1218101,1218102 参数（按组件ID过滤）
+    target_cids = None
+    if "--cids" in sys.argv:
+        idx = sys.argv.index("--cids")
+        if idx + 1 < len(sys.argv):
+            target_cids = set(int(c) for c in sys.argv[idx + 1].split(",") if c.strip())
+
     # 支持 --send-to <user_id> 参数
     send_to_user = None
     if "--send-to" in sys.argv:
@@ -692,7 +723,7 @@ if __name__ == "__main__":
         parse_script.parse_script_from_sheet = limited_parse
         globals()["parse_script_from_sheet"] = limited_parse
 
-    report = process_script(wiki_input, dry_run=dry_run)
+    report = process_script(wiki_input, dry_run=dry_run, target_cids=target_cids)
 
     # 输出日志和HTML路径
     if report.get("log_path"):

memory/.dreams/events.jsonl

@@ -76,3 +76,6 @@
 {"type":"memory.recall.recorded","timestamp":"2026-05-28T03:07:46.098Z","query":"6题 刘彦江 看图拼词 imgMakeWord","resultCount":1,"results":[{"path":"memory/2026-05-12.md","startLine":137,"endLine":149,"score":1}]}
 {"type":"memory.recall.recorded","timestamp":"2026-05-28T03:08:15.128Z","query":"看图拼词 imgMakeWord 样例 6题 刘彦江 2026-05-25","resultCount":1,"results":[{"path":"memory/2026-05-07.md","startLine":1,"endLine":20,"score":1}]}
 {"type":"memory.recall.recorded","timestamp":"2026-05-28T10:04:34.024Z","query":"李若松 身份 user_id","resultCount":2,"results":[{"path":"memory/2026-04-30.md","startLine":50,"endLine":63,"score":1},{"path":"memory/2026-05-08.md","startLine":18,"endLine":38,"score":1}]}
+{"type":"memory.recall.recorded","timestamp":"2026-05-29T00:23:17.391Z","query":"输出文本和JSON 题型 单元挑战 questionSet 看图组词 单词释义","resultCount":1,"results":[{"path":"memory/2026-05-28.md","startLine":46,"endLine":62,"score":1}]}
+{"type":"memory.recall.recorded","timestamp":"2026-05-29T00:23:17.392Z","query":"reading_pic_makeWord reading_word_definition listening_listenWrite reading_select_cloze 修正","resultCount":5,"results":[{"path":"memory/2026-05-07.md","startLine":1,"endLine":20,"score":1},{"path":"memory/2026-05-11.md","startLine":1,"endLine":25,"score":1},{"path":"memory/2026-05-17.md","startLine":19,"endLine":41,"score":1},{"path":"memory/2026-05-12.md","startLine":170,"endLine":193,"score":1},{"path":"memory/2026-05-21.md","startLine":52,"endLine":67,"score":1}]}
+{"type":"memory.recall.recorded","timestamp":"2026-05-29T02:33:30.526Z","query":"梁晨 l1_pedagogy_rules pedagogy rules JS文件","resultCount":6,"results":[{"path":"memory/2026-05-26.md","startLine":130,"endLine":166,"score":1},{"path":"memory/2026-05-28.md","startLine":46,"endLine":62,"score":1},{"path":"memory/2026-05-25.md","startLine":283,"endLine":302,"score":1},{"path":"memory/2026-05-25.md","startLine":118,"endLine":137,"score":1},{"path":"memory/2026-05-28.md","startLine":60,"endLine":66,"score":1},{"path":"memory/2026-05-20.md","startLine":1,"endLine":31,"score":1}]}

memory/.dreams/short-term-recall.json

@@ -1,6 +1,6 @@
 {
   "version": 1,
-  "updatedAt": "2026-05-28T10:04:34.024Z",
+  "updatedAt": "2026-05-29T02:33:30.526Z",
   "entries": {
     "memory:memory/2026-05-07.md:57:74": {
       "key": "memory:memory/2026-05-07.md:57:74",
@@ -117,13 +117,13 @@
       "endLine": 20,
       "source": "memory",
       "snippet": "# 2026-05-07 工作日志 ## 会话记录 ### 刘彦江 (ou_5af74c1fb96042e33cc0f16b5ca02cf4) — 单元挑战新增3个题型 - **时间：** 11:19 ~ 11:28 - **需求：** 单元挑战新增3个题型：阅读看图回答题（reading_pic_qa）、阅读看图判断题（reading_pic_judge）、写作看图回答题（writing_pic_qa） - **状态：** ✅ 已完成题型规范落地 - **交付内容：** 1. 创建3个题型SKILL.md： - `reading/common/reading_pic_qa/SKILL.md` — 阅读看图回答题（共享大图+多题Yes/No判断） - `reading/common/reading_pic_judge/SKILL.md` — 阅读看图判断题（每题独立配图+Yes/No判断） - `writing/common/writing_pic_qa/SKILL.md` — 写作看图回答题（看图+提示答案开头+填空） 2. 更新 `MEMORY.md` 全题型阶段归属规则 3. 明确题型JSON结构、难度等级（A/B/C/D四级）、能力标签、校验规则 - **关键决策：** 3个题型均为 L1&L2 共用，通过难度参数区分阶段；reading_pic_qa 共享大图，reading_pic_judge 每题独立配图 ### 李应瑛 (ou_1bd7317ae2ccfeb57e1132028847279e) — 单词表对比请求",
-      "recallCount": 11,
+      "recallCount": 12,
       "dailyCount": 0,
       "groundedCount": 0,
-      "totalScore": 11,
+      "totalScore": 12,
       "maxScore": 1,
       "firstRecalledAt": "2026-05-08T01:18:18.412Z",
-      "lastRecalledAt": "2026-05-28T03:08:15.128Z",
+      "lastRecalledAt": "2026-05-29T00:23:17.392Z",
       "queryHashes": [
         "390d35f8d143",
         "fd4c9b7de37b",
@@ -135,7 +135,8 @@
         "d592c9ed5e0a",
         "5f858a7d5e0b",
         "ab90b7e9cde8",
-        "fbf96ac9320e"
+        "fbf96ac9320e",
+        "bd790c7e2a35"
       ],
       "recallDays": [
         "2026-05-08",
@@ -145,7 +146,8 @@
         "2026-05-14",
         "2026-05-17",
         "2026-05-26",
-        "2026-05-28"
+        "2026-05-28",
+        "2026-05-29"
       ],
       "conceptTags": [
         "reading-pic-qa",
@@ -795,25 +797,27 @@
       "endLine": 193,
       "source": "memory",
       "snippet": "- 每个题型：cType + bitable 定位 + JSON 字段表 + 结构特点 + 与同类题型的差异说明 #### 发现 - 写作互动和邮件组句 cType 相同（`core_writing_questionMakeSentence`），通过 textInfo 区分素材 - 口语快答/妙问 JSON 结构几乎相同，差异在 prompt 配置和对话样例内容 - 合作阅读和合作听力的核心差异：`textData.text[]` ↔ `textData.audio[]` - meaning 标签（合作阅读）为开放型自由文本，非受控词表 #### 产出文件 - `skills/bitable-reader/SKILL.md` — 通用 bitable 读取技能（164行） - `skills/core-content-json-standard/SKILL.md` — 全题型 JSON 标准 v2.0（393行） - `scripts/audit_core_reading_S0.py` — 合作阅读 S0 审校脚本（含审校发现） # 2026-05-12 工作日志 ## 会话记录 ### 刘彦江 — 021301-021801 图片描述修正 + 技能更新（09:35 ~ 09:45） - **问题：** 021301-021801 信息匹配题的图片描述缺少 `【Notice Type】` 标签 - **处理：** 批量更新6条记录的图片描述字段，全部10个标签验证通过 - **脚本：** `scripts/fix_matchInfo_0213_0218_desc.py`",
-      "recallCount": 5,
+      "recallCount": 6,
       "dailyCount": 0,
       "groundedCount": 0,
-      "totalScore": 5,
+      "totalScore": 6,
       "maxScore": 1,
       "firstRecalledAt": "2026-05-14T02:49:02.264Z",
-      "lastRecalledAt": "2026-05-22T07:04:01.804Z",
+      "lastRecalledAt": "2026-05-29T00:23:17.392Z",
       "queryHashes": [
         "d592c9ed5e0a",
         "5f858a7d5e0b",
         "34bf2e5fbdee",
         "3f9471df9e50",
-        "d13d58b4704a"
+        "d13d58b4704a",
+        "bd790c7e2a35"
       ],
       "recallDays": [
         "2026-05-14",
         "2026-05-17",
         "2026-05-19",
-        "2026-05-22"
+        "2026-05-22",
+        "2026-05-29"
       ],
       "conceptTags": [
         "口语快答/妙问",
@@ -1031,20 +1035,22 @@
       "endLine": 41,
       "source": "memory",
       "snippet": "- `raw_content` API 不暴露此类嵌入 Sheet，需通过 blocks API 查找 `block_type=30` 的 grid_column 节点来发现 sheet token - 该文档含 2 个嵌入 Sheet：`zbfYO4`（知识点区）和 `Nr3Ovs`（243 行 × 8 列脚本表） ### 已完成的组件回填（14/14 对话组件） | 组件类型 | 数量 | 所用 skill | |---------|:--:|-----------| | 对话朗读 | 6 | dialogue-reading-config | | 对话朗读-配图 | 2 | dialogue-reading-config | | 对话挖空 | 2 | dialogue-fill-in-blanks-config | | 对话挖空-配图 | 1 | dialogue-fill-in-blanks-config | | 对话选择-配图 | 1 | dialogue-choose-config | | 对话选读 | 1 | **dialogue-selective-reading-config（新建）** | | 对话组句 | 1 | dialogue-sentence-building-config | ### Skill 库补全 - **新建 skill**：`~/.openclaw/workspace-xiaoyan/skills/dialogue-selective-reading-config/SKILL.md` - 格式来源：`dialogue-inter",
-      "recallCount": 2,
+      "recallCount": 3,
       "dailyCount": 0,
       "groundedCount": 0,
-      "totalScore": 2,
+      "totalScore": 3,
       "maxScore": 1,
       "firstRecalledAt": "2026-05-18T02:42:25.325Z",
-      "lastRecalledAt": "2026-05-21T02:47:59.335Z",
+      "lastRecalledAt": "2026-05-29T00:23:17.392Z",
       "queryHashes": [
         "eb45753e9aa6",
-        "09344f87b646"
+        "09344f87b646",
+        "bd790c7e2a35"
       ],
       "recallDays": [
         "2026-05-18",
-        "2026-05-21"
+        "2026-05-21",
+        "2026-05-29"
       ],
       "conceptTags": [
         "raw-content",
@@ -1957,20 +1963,22 @@
       "endLine": 31,
       "source": "memory",
       "snippet": "# 2026-05-20 工作日志 ## [童瑶] L1-S2-U17-L2 迟到的包裹 — 英文台词润色 - 134行对话台词全部润色完成，写入H列 - S2标准：句长≤8词、英式拼写、口语化、知识点保留 - 详情见 `business_production/英文台词/memory/2026-05-20.md` ## [童瑶] L1-S2-U17-L1 摩托怪客 — 组件配置JSON - 16个互动组件，14个成功生成JSON，2个跳过 - 跳过：图片无序多选（注册表无匹配）、阅读理解（核心互动未注册） - HTML报告已通过飞书Bot发送给童瑶 ## [童瑶] L1-S2-U17-L4 捉迷藏 — 组件生产（第111行起） - **文档**: SAadwW8YaiObl8k4op3c6vs8nqb | **Sheet**: wMQVyV | **Spreadsheet**: It4AsFkC7hXHc4te9yUcyLHRnOe - 从第111行起识别9个互动组件，全部完成F列回填，最终验证通过 - 最终组件行及对应关系： | 行号 | 组件类型 | 组件ID | |------|---------|--------| | 111 | 对话选择-配图 | 1217408 | | 119 | 对话选择-配图 | 1217409 | | 127 | 对话挖空-配图 | 1217410 | | 130 | 对话组句-配图 | 1217411 | | 141 | 对话组句-配图 | 1217412 | | 150 | 看图拼词 | 1217413 | | 166 | 对话",
-      "recallCount": 2,
+      "recallCount": 3,
       "dailyCount": 0,
       "groundedCount": 0,
-      "totalScore": 2,
+      "totalScore": 3,
       "maxScore": 1,
       "firstRecalledAt": "2026-05-21T07:31:52.322Z",
-      "lastRecalledAt": "2026-05-27T07:13:57.033Z",
+      "lastRecalledAt": "2026-05-29T02:33:30.526Z",
       "queryHashes": [
         "03b71fab8fb9",
-        "62070213f719"
+        "62070213f719",
+        "4aa0ef719160"
       ],
       "recallDays": [
         "2026-05-21",
-        "2026-05-27"
+        "2026-05-27",
+        "2026-05-29"
       ],
       "conceptTags": [
         "l1-s2-u17-l2",
@@ -2639,6 +2647,224 @@
         "对话挖空-配图",
         "对话选择-配图"
       ]
+    },
+    "memory:memory/2026-05-28.md:46:62": {
+      "key": "memory:memory/2026-05-28.md:46:62",
+      "path": "memory/2026-05-28.md",
+      "startLine": 46,
+      "endLine": 62,
+      "source": "memory",
+      "snippet": "- B级规则：听力句子 5-8 词（均 7 词），每组 3 张同类物品不同属性图片 - 能力标签：显性事实理解｜关键词识别 ×2 + 基础语境理解｜场景/物品/动作识别 ## 梁辰（user_id: ou_28f02dcada1193913cfbb6310f8daf07）— HTML 诊断页面教研规则 JS 文件 - 用户有一个 L1 关卡诊断工作台 HTML 页面（部署在腾讯云空间），当前只做数量级统计，缺少教研规则校验 - 需求：提供可嵌入 HTML 的前端 JS 校验规则文件，使诊断有据可依 - 输出：`output/l1_pedagogy_rules.js`（42KB），包含 8 个校验维度： 1. 词汇超纲检测（基于 L1/L2 词库） 2. 英式拼写检测（color→colour 等 115 组映射） 3. Markdown 标记检测（`**`/`#`/`>` 等） 4. 标点规范检测（全角混入、`～`、`!!!`） 5. 题型-阶段匹配校验（20 种题型对应的 L1/L2 阶段映射） 6. 台词质量分析（句子长度、负面评价） 7. 知识点曝光度 8. 句型合规检测 - 接入方式：`<script src=\"l1_pedagogy_rules.js\"></script>` + 调用 `PedagogyRules.validate(summary, level)` - 数据源：L1 词库 147 词（过滤 enabled=true）、L2 词库 52 词、L1 句型 8 个、L2 句型（从 437MB bitable 导出中提取唯一结",
+      "recallCount": 2,
+      "dailyCount": 0,
+      "groundedCount": 0,
+      "totalScore": 2,
+      "maxScore": 1,
+      "firstRecalledAt": "2026-05-29T00:23:17.391Z",
+      "lastRecalledAt": "2026-05-29T02:33:30.526Z",
+      "queryHashes": [
+        "c1d4076205e1",
+        "4aa0ef719160"
+      ],
+      "recallDays": [
+        "2026-05-29"
+      ],
+      "conceptTags": [
+        "5-8",
+        "场景/物品/动作识别",
+        "user-id",
+        "output/l1-pedagogy-rules.js",
+        "l1/l2",
+        "题型-阶段匹配校验",
+        "l1-pedagogy-rules.js",
+        "pedagogyrules.validate"
+      ]
+    },
+    "memory:memory/2026-05-11.md:1:25": {
+      "key": "memory:memory/2026-05-11.md:1:25",
+      "path": "memory/2026-05-11.md",
+      "startLine": 1,
+      "endLine": 25,
+      "source": "memory",
+      "snippet": "### 刘彦江 — reading_pic_judge 看图判断题批量生产（4套，17:28 ~ 17:35） - **需求：** 4套 reading_pic_judge，L1 A级，能力标签 图文匹配 - **题型特点：** 每题独立配图（questionImage），first/second双题组包裹 - **状态：** ✅ 已完成，4套全部入库+图片描述回填验证通过 - **脚本：** `scripts/batch_reading_pic_judge.py`、`scripts/update_pic_judge_descriptions.py` | ID | 题组1 | 题组2 | Y/N | 图片描述 | |----|-------|-------|-----|---------| | 121301 | home/house/sofa/cupboard/bedroom | zoo/hippo/bear/jeans/sock | 3Y2N | ✅ 596chars | | 121401 | student/school/teacher/crayon/board | mat/letter/desk/schoolbag/handbag | 3Y2N | ✅ 562chars | | 121501 | body/head/mouth/ear/friend | camera/boy/girl/skateboarding/skateboard | 3Y2N | ✅ 553chars | | 121601 | summer/autumn/winter/cold/spring |",
+      "recallCount": 1,
+      "dailyCount": 0,
+      "groundedCount": 0,
+      "totalScore": 1,
+      "maxScore": 1,
+      "firstRecalledAt": "2026-05-29T00:23:17.392Z",
+      "lastRecalledAt": "2026-05-29T00:23:17.392Z",
+      "queryHashes": [
+        "bd790c7e2a35"
+      ],
+      "recallDays": [
+        "2026-05-29"
+      ],
+      "conceptTags": [
+        "reading-pic-judge",
+        "first/second双题组包裹",
+        "y/n",
+        "home/house/sofa/cupboard/bedroom",
+        "zoo/hippo/bear/jeans/sock",
+        "body/head/mouth/ear/friend",
+        "summer/autumn/winter/cold/spring",
+        "彦江"
+      ]
+    },
+    "memory:memory/2026-05-21.md:52:67": {
+      "key": "memory:memory/2026-05-21.md:52:67",
+      "path": "memory/2026-05-21.md",
+      "startLine": 52,
+      "endLine": 67,
+      "source": "memory",
+      "snippet": "- 共 17 个互动行：对话朗读-配图(6) / 对话朗读(1) / 对话挖空-配图(1) / 对话挖空(4) / 对话选择-配图(1) / 对话选读(2) / 对话组句-配图(1) / 对话组句(1) / 看图说话(1) #### 组件类型 A 列取值与技能映射（新增类型） | A列类型 | 对应技能 | 备注 | |---------|---------|------| | 对话朗读 / 对话朗读-配图 | dialogue-reading-config | -配图需加图片时机和音频载体 | | 对话挖空 / 对话挖空-配图 | dialogue-fill-in-blanks-config | 同上 | | 对话选择 / 对话选择-配图 | dialogue-choose-config | 同上 | | **对话选读** | dialogue-selective-reading-config | 开放表达，无正确选项，每选项必带反馈 | | **对话组句** | dialogue-sentence-building-config | 单词排序组句，含答案+辅助信息 | | **看图说话** | dialogue-image-description-config | 导览配置+对话配置，含Q&A/通过规则/示例对话 | #### 类型区别关键点 - **对话选择 vs 对话选读**：前者有对错判断（正确选项标注），后者开放表达（无正确选项，每选项均带反馈） - **对话挖空**：`___` 必需三下划线，选项2-3个，反馈角色非 User - **对话组句**：选项为独立",
+      "recallCount": 1,
+      "dailyCount": 0,
+      "groundedCount": 0,
+      "totalScore": 1,
+      "maxScore": 1,
+      "firstRecalledAt": "2026-05-29T00:23:17.392Z",
+      "lastRecalledAt": "2026-05-29T00:23:17.392Z",
+      "queryHashes": [
+        "bd790c7e2a35"
+      ],
+      "recallDays": [
+        "2026-05-29"
+      ],
+      "conceptTags": [
+        "对话朗读-配图",
+        "对话挖空-配图",
+        "对话选择-配图",
+        "对话组句-配图",
+        "dialogue-reading-config",
+        "dialogue-fill-in-blanks-config",
+        "dialogue-choose-config",
+        "a/通过规则/示例对话"
+      ]
+    },
+    "memory:memory/2026-05-26.md:130:166": {
+      "key": "memory:memory/2026-05-26.md:130:166",
+      "path": "memory/2026-05-26.md",
+      "startLine": 130,
+      "endLine": 166,
+      "source": "memory",
+      "snippet": "## 英文台词生产 [童瑶] — L1-S2-U20 全系列 ### L1-S2-U20-L1 冠军计划 - **文档：** `EbkUwEjaticOkHknf0icsQ2Yn4Q` | Sheet `6aqvM2` - 对话 148 行，写入 E 列 ✅ ### L1-S2-U20-L2 发球大战 - **文档：** `BvSyw1vlfiwCr5kjkPmcUYXynZd` | Sheet `wMQVyV` - 对话 135 行，写入 F 列 ✅ ### L1-S2-U20-L3 曲棍球练习赛 - **文档：** `MrsAwcYq2iCy7Tkk3dkclS0mnlg` | Sheet `6aqvM2` - 对话 149 行，28 行修改，写入 F 列 ✅ - 知识点：hockey/interesting/one/try + `have a try`/`One...the other...` ### L1-S2-U20-L4 网球明星 - **文档：** `GT4awLQx9iOfWHk00ZFcHQzbnzT` | Sheet `wMQVyV` - 对话 112 行，26 行修改，写入 F 列 ✅ - 知识点：tennis/tennis racket/bounce/wave + `wave(s) to`/`Hit the ball!` ### L1-S2-U20-L5 足球接力赛 - **文档：** `VEGwwoVdTiFu00koNoOc1MGhnec` | Sheet `AV1gO0` - 对话 137 行，28 行修改，写入 F 列 ✅ - 知识点：",
+      "recallCount": 1,
+      "dailyCount": 0,
+      "groundedCount": 0,
+      "totalScore": 1,
+      "maxScore": 1,
+      "firstRecalledAt": "2026-05-29T02:33:30.526Z",
+      "lastRecalledAt": "2026-05-29T02:33:30.526Z",
+      "queryHashes": [
+        "4aa0ef719160"
+      ],
+      "recallDays": [
+        "2026-05-29"
+      ],
+      "conceptTags": [
+        "l1-s2-u20",
+        "l1-s2-u20-l1",
+        "l1-s2-u20-l2",
+        "l1-s2-u20-l3",
+        "hockey/interesting/one/try",
+        "l1-s2-u20-l4",
+        "tennis/tennis",
+        "racket/bounce/wave"
+      ]
+    },
+    "memory:memory/2026-05-25.md:283:302": {
+      "key": "memory:memory/2026-05-25.md:283:302",
+      "path": "memory/2026-05-25.md",
+      "startLine": 283,
+      "endLine": 302,
+      "source": "memory",
+      "snippet": "- 14 阶段 4 科目全部重写，目标文档: `W5Vjw2fLiiCqfck0Mfzc0xkrnte` - L2 阶段1-2 阅读/写作从\"无\"补为实际技能点（刘彦江确认\"L2 阶段1-2 阅读和写作都是有题型的\"） - L1 阶段1 阅读/写作也从\"无\"补为实际技能点 - 0 个\"无\"，全量覆盖 - 生成脚本: `tmp/build_skill_points.py` ## 生产覆盖范围修正 [刘彦江] - L1 生产到 **U16**（非 U33） - L2 生产到 **U29**（非 U16） - 已同步更新 `business_knowledge/单元挑战全貌.md` ## 单元挑战全貌文档 [刘彦江] - 创建 `business_knowledge/单元挑战全貌.md` - 覆盖九大板块：业务定位、阶段划分、题型体系（18种）、能力标签（45个）、生产流程（ID规则/标准/写入陷阱）、审校体系（7+4项检查）、生产覆盖现状、模块关联、快速链接 ## L1/L2 难度等级映射 [刘彦江] ✅已确认 - L1-A: Starters入门+基础 (U1-U16) | L1-B: Starters达标 (U17-U24) | L1-C: Movers入门+基础 (U25-U40) | L1-D: Movers达标 (U41-U48) - L2-A: Flyers入门+基础 (U1-U12) | L2-B: Flyers达标 (U13-U18) | L2-C: KET入门+基础 (U19-U30) | L2-D: KET强化+高位+达标 (U31-U48) - 已写入",
+      "recallCount": 1,
+      "dailyCount": 0,
+      "groundedCount": 0,
+      "totalScore": 1,
+      "maxScore": 1,
+      "firstRecalledAt": "2026-05-29T02:33:30.526Z",
+      "lastRecalledAt": "2026-05-29T02:33:30.526Z",
+      "queryHashes": [
+        "4aa0ef719160"
+      ],
+      "recallDays": [
+        "2026-05-29"
+      ],
+      "conceptTags": [
+        "阶段1-2",
+        "阅读/写作从",
+        "阅读/写作也从",
+        "tmp/build-skill-points.py",
+        "business-knowledge/单元挑战全貌.md",
+        "id规则/标准/写入陷阱",
+        "l1/l2",
+        "l1-a"
+      ]
+    },
+    "memory:memory/2026-05-25.md:118:137": {
+      "key": "memory:memory/2026-05-25.md:118:137",
+      "path": "memory/2026-05-25.md",
+      "startLine": 118,
+      "endLine": 137,
+      "source": "memory",
+      "snippet": "- 生成脚本: `tmp/build_skill_points.py` ## 生产覆盖范围修正 [刘彦江] - L1 生产到 **U16**（非 U33） - L2 生产到 **U29**（非 U16） - 已同步更新 `business_knowledge/单元挑战全貌.md` ## 单元挑战全貌文档 [刘彦江] - 创建 `business_knowledge/单元挑战全貌.md` - 覆盖九大板块：业务定位、阶段划分、题型体系（18种）、能力标签（45个）、生产流程（ID规则/标准/写入陷阱）、审校体系（7+4项检查）、生产覆盖现状、模块关联、快速链接 ## L1/L2 难度等级映射 [刘彦江] ✅已确认 - L1-A: Starters入门+基础 (U1-U16) | L1-B: Starters达标 (U17-U24) | L1-C: Movers入门+基础 (U25-U40) | L1-D: Movers达标 (U41-U48) - L2-A: Flyers入门+基础 (U1-U12) | L2-B: Flyers达标 (U13-U18) | L2-C: KET入门+基础 (U19-U30) | L2-D: KET强化+高位+达标 (U31-U48) - 已写入 `business_knowledge/单元挑战全貌.md` §5.3 # 2026-05-25 工作日志 ## 组件配置 pipeline：单独重试 cId=1217214 - [童瑶] 请求单独重试 pipeline 中的失败组件 cId=1217214（听力拖拽 / core_listenin",
+      "recallCount": 1,
+      "dailyCount": 0,
+      "groundedCount": 0,
+      "totalScore": 1,
+      "maxScore": 1,
+      "firstRecalledAt": "2026-05-29T02:33:30.526Z",
+      "lastRecalledAt": "2026-05-29T02:33:30.526Z",
+      "queryHashes": [
+        "4aa0ef719160"
+      ],
+      "recallDays": [
+        "2026-05-29"
+      ],
+      "conceptTags": [
+        "tmp/build-skill-points.py",
+        "business-knowledge/单元挑战全貌.md",
+        "id规则/标准/写入陷阱",
+        "l1/l2",
+        "l1-a",
+        "u1-u16",
+        "l1-b",
+        "u17-u24"
+      ]
+    },
+    "memory:memory/2026-05-28.md:60:66": {
+      "key": "memory:memory/2026-05-28.md:60:66",
+      "path": "memory/2026-05-28.md",
+      "startLine": 60,
+      "endLine": 66,
+      "source": "memory",
+      "snippet": "8. 句型合规检测 - 接入方式：`<script src=\"l1_pedagogy_rules.js\"></script>` + 调用 `PedagogyRules.validate(summary, level)` - 数据源：L1 词库 147 词（过滤 enabled=true）、L2 词库 52 词、L1 句型 8 个、L2 句型（从 437MB bitable 导出中提取唯一结构） - 技术注意：L2_pattern_list.json 体积 437MB（1,082,450 条记录），直接嵌入前端不可行，已提取唯一句型结构后嵌入 - 所有 6 个测试用例通过 - 用户后续想尝试其他对接方式（API 模式 / 飞书 Bot 联动 / CI 集成）",
+      "recallCount": 1,
+      "dailyCount": 0,
+      "groundedCount": 0,
+      "totalScore": 1,
+      "maxScore": 1,
+      "firstRecalledAt": "2026-05-29T02:33:30.526Z",
+      "lastRecalledAt": "2026-05-29T02:33:30.526Z",
+      "queryHashes": [
+        "4aa0ef719160"
+      ],
+      "recallDays": [
+        "2026-05-29"
+      ],
+      "conceptTags": [
+        "l1-pedagogy-rules.js",
+        "pedagogyrules.validate",
+        "l2-pattern-list.json",
+        "句型",
+        "检测",
+        "方式",
+        "script",
+        "src"
+      ]
     }
   }
 }

memory/2026-05-29-1111.md

@@ -0,0 +1,15 @@
+# Session: 2026-05-29 11:11:18 GMT+8
+
+- **Session Key**: agent:xiaoyan:feishu:direct:ou_8b79b7f711e42a4004f3f3c225a1a99c
+- **Session ID**: 06d2876f-1302-4e15-946e-da689c2788bb
+- **Source**: feishu
+
+## Conversation Summary
+
+user: 组件配置-json https://makee-interactive.feishu.cn/wiki/KNAZwTYXsib2Ijk6BrGciRelnSf?from=from_copylink
+assistant: 张昆鹏，开始处理。执行 pipeline：
+
+
+assistant: 处理被中断了，重跑一次，加大超时。
+
+

memory/2026-05-29-1120.md

@@ -0,0 +1,28 @@
+# Session: 2026-05-29 11:20:57 GMT+8
+
+- **Session Key**: agent:xiaoyan:feishu:direct:ou_8b79b7f711e42a4004f3f3c225a1a99c
+- **Session ID**: 14f433f3-d123-4c62-8331-096fb7992bbf
+- **Source**: feishu
+
+## Conversation Summary
+
+user: 组件配置-json https://makee-interactive.feishu.cn/wiki/KNAZwTYXsib2Ijk6BrGciRelnSf?from=from_copylink
+assistant: 根据 `interactive-component-json` 技能，执行组件配置 JSON 生成流水线。
+
+张昆鹏（技术负责人，`7f5cd711`），开始处理。
+
+
+assistant: ✅ 处理完成！**L1-S2-U18-L2 登龙秘笈** — 17/17 组件全部生成成功，HTML 报告已通过飞书 Bot 发送给你。
+
+| 类型 | 数量 | 状态 |
+|------|------|------|
+| 对话朗读 (mid_dialog_repeat) | 5 | ✅ |
+| 对话挖空 (mid_dialog_fillin) | 4 | ✅ |
+| 对话组句 (mid_dialog_sentence) | 2 | ✅ |
+| 对话选读 (mid_dialog_select) | 2 | ✅ |
+| 对话选择 (mid_dialog_choose) | 1 | ✅ |
+| 对话表达 (mid_dialog_express) | 1 | ✅ |
+| 图片单选 (mid_image_choose) | 1 | ✅ |
+| 听力选择 (core_listening_choose) | 1 | ✅ |
+
+⚠️ 部分组件的知识点未在 MySQL 词库中匹配到（如 `blackboard`、`Take... as an example.`、`... in line.` 等），建议确认这些知识点在词库中的录入情况。

memory/2026-05-29-1125.md

@@ -0,0 +1,30 @@
+# Session: 2026-05-29 11:25:02 GMT+8
+
+- **Session Key**: agent:xiaoyan:feishu:direct:ou_8b79b7f711e42a4004f3f3c225a1a99c
+- **Session ID**: 2bc6e1f4-5d44-4513-ba43-7decd534dcc1
+- **Source**: feishu
+
+## Conversation Summary
+
+user: 组件配置-json https://makee-interactive.feishu.cn/wiki/KNAZwTYXsib2Ijk6BrGciRelnSf?from=from_copylink
+assistant: 张昆鹏（技术负责人），正在启动组件配置JSON生成流水线。
+
+
+assistant: 处理完成！**L1-S2-U18-L2 登龙秘笈** — 17/17 组件全部生成成功，HTML 报告已发送给你。
+
+| 组件类型 | 数量 | 状态 |
+|----------|------|------|
+| 对话朗读 (mid_dialog_repeat) | 5 | ✅ |
+| 对话挖空 (mid_dialog_fillin) | 4 | ✅ |
+| 对话选读 (mid_dialog_select) | 2 | ✅ |
+| 对话组句 (mid_dialog_sentence) | 2 | ✅ |
+| 对话选择 (mid_dialog_choose) | 1 | ✅ |
+| 对话表达 (mid_dialog_express) | 1 | ✅ |
+| 图片单选 (mid_image_choose) | 1 | ✅ |
+| 核心互动-听力选择 (core_listening_choose) | 1 | ✅ |
+
+⚠️ 注意：部分知识点的 kpId 未匹配到（如 `blackboard`、`Take... as an example.` 等），需手动核对知识点关联。
+user: cId全部错误
+assistant: 让我查看原始 sheet 数据和生成的 cId，定位问题。
+
+

memory/2026-05-29.md

@@ -0,0 +1,13 @@
+
+## [梁晨] L1 Pedagogy Rules v4.0.0 交付
+- 在 v3 基础上新增 5 个校验维度（来自 16 个教研 skill 规则提取）：
+  6. 组件合规性（12 种题型规则，来自 11 个 dialogue/info config skills）
+  7. 字段完整性（7 项自动检查，来自 audit_l1_config）
+  8. 掌握度预测（W_i×M_i 加权公式，来自 knowledge-mastery-calculator）
+  9. 格式规范（标题/Markdown/标点/英式拼写/价值观，来自全量文本规范）
+  10. 语法检测（三单/主谓一致/双重否定，来自 audit_l1_config）
+- 输出：`output/l1_pedagogy_rules_v4.js`（59KB）
+- 数据：L1 147 词、L2 52 词、L1 8 句型、L2 1 句型、89 组英式拼写映射、12 种题型规则
+- 已通过飞书 Bot 发送给梁晨
+- API 兼容 v3：不加 options 参数即为原行为；加 component/componentExposures 启用新维度
+- 能力边界：内容质量诊断（第一层筛选），不是全链路归因（看不到 UX/服务端/学生侧因素）