diff --git a/.vala_skill_hashes b/.vala_skill_hashes index 913b9bd..af59d76 100644 --- a/.vala_skill_hashes +++ b/.vala_skill_hashes @@ -11,3 +11,4 @@ vala-component-oops-stat 2e3a3dc8ee252f133256ec5fb8edc031fc25ff602158fd2ddf778ce vala-component-practice-stat 8e768e2641019d27bd41f4647d2d90f24182a0554dad5ad9f4136e9ce0bae147 cron-schedule e103cbb1806b28c891b9c856963325086ecaff32edec208f0a841865f26e8f3e refund-user-learning-analysis 648fd4ae2b29167fd66eab4245bdaaef00242db3131f4919cc02f07ca2a9b59c +phone-chapter-query ac429b4da5a89db16efdf1066edf4ecb1c050b93aff20dd4c652af5f5568e44f diff --git a/AGENTS.md b/AGENTS.md index 9456509..a7f1f91 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -157,9 +157,10 @@ System: [...] Feishu[xiaobian] group oc_xxx | 发送者 (ou_xxx) [msg:om_xxx] 1. **脚本文件** → 始终创建在 `scripts/` 目录下，绝不放在根目录 2. **输出文件**（xlsx/csv/log/报表等）→ 始终创建在 `output/` 目录下，绝不放在根目录 -3. **业务知识** → 统一记录到 `business_knowledge/` 目录 -4. **新增子目录** → 禁止在根目录下随意创建新子目录。如有特殊需要，须经技术负责人确认 -5. **临时文件** → 使用 `tmp/`，用完即清 +3. **定时任务/脚本生成的文件** → 默认也输出到 `output/` 目录下，可根据需求在 `output/` 内创建子目录分类存放（如 `output/daily_reports/`），**绝不放在根目录** +4. **业务知识** → 统一记录到 `business_knowledge/` 目录 +5. **新增子目录** → 禁止在根目录下随意创建新子目录。如有特殊需要，须经技术负责人确认 +6. **临时文件** → 使用 `tmp/`，用完即清 ## 工具 diff --git a/memory/2026-04-20-gmv-query.md b/memory/2026-04-20-gmv-query.md new file mode 100644 index 0000000..8b27516 --- /dev/null +++ b/memory/2026-04-20-gmv-query.md @@ -0,0 +1,41 @@ +# Session: 2026-04-20 04:17:26 UTC + +- **Session Key**: agent:main:feishu:direct:ou_9cb5bc9a5f1b6cab2d78fd36139ecb87 +- **Session ID**: b0bb1c0e-ec5a-48b3-92c1-c0eb4104f612 +- **Source**: feishu + +## Conversation Summary + +user: System: [2026-04-15 19:58:16 GMT+8] Feishu[default] DM | 李若松 (ou_9cb5bc9a5f1b6cab2d78fd36139ecb87) [msg:om_x100b52c39bb8807cc2efa6a35fb57e4] +System: [2026-04-15 19:58:16 GMT+8] Model switched to doubao (volcengine/doubao-seed-2-0-pro-260215). +System: [2026-04-20 10:06:37 GMT+8] Feishu[default] DM | 李若松 (ou_9cb5bc9a5f1b6cab2d78fd36139ecb87) [msg:om_x100b516cec07b4acb2bf0be36392549] + +Conversation info (untrusted metadata): +```json +{ + "message_id": "om_x100b516cec07b4acb2bf0be36392549", + "sender_id": "ou_9cb5bc9a5f1b6cab2d78fd36139ecb87", + "sender": "李若松", + "timestamp": "Mon 2026-04-20 10:06 GMT+8" +} +``` + +Sender (untrusted metadata): +```json +{ + "label": "李若松 (ou_9cb5bc9a5f1b6cab2d78fd36139ecb87)", + "id": "ou_9cb5bc9a5f1b6cab2d78fd36139ecb87", + "name": "李若松" +} +``` + +查看一下本月GMV +assistant: 截至2026年4月20日，本月（4月）核心业务指标如下： +| 指标 | 数值 | +|------|------| +| 总订单数 | 1338 单 | +| GMV | 3,997,852.00 元（约399.8万元） | +| GSV（剔除退费后实际收入） | 2,300,478.00 元（约230.0万元） | +| 退费率 | 41.1% | + +✅ 数据已自动剔除测试账号，符合业务统计口径。 diff --git a/memory/2026-04-20-phone-query.md b/memory/2026-04-20-phone-query.md new file mode 100644 index 0000000..77ed9be --- /dev/null +++ b/memory/2026-04-20-phone-query.md @@ -0,0 +1,165 @@ +# Session: 2026-04-20 03:21:29 UTC + +- **Session Key**: agent:main:feishu:direct:ou_e63ce6b760ad39382852472f28fbe2a2 +- **Session ID**: 314d25e7-4721-435c-b121-bae687a6520c +- **Source**: feishu + +## Conversation Summary + +assistant: ✅ New session started · model: cloudsway/MaaS_Cl_Opus_4.6_20260205_cache (default: volcengine/doubao-seed-2-0-pro-260215) +user: System: [2026-04-20 10:21:09 GMT+8] Feishu[default] DM | 李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2) [msg:om_x100b516c978918a0b4b6d555d6d9512] + +A new session was started via /new or /reset. Run your Session Startup sequence - read the required files before responding to the user. Then greet the user in your configured persona, if one is provided. Be yourself - use your defined voice, mannerisms, and mood. Keep it to 1-3 sentences and ask what they want to do. If the runtime model differs from default_model in the system prompt, mention the default model. Do not mention internal steps, files, tools, or reasoning. +Current time: Monday, April 20th, 2026 — 10:21 AM (Asia/Shanghai) / 2026-04-20 02:21 UTC +assistant: 承龙早上好 ☀️ 刚上线，今天周一，有什么需要我帮忙的吗？ +user: System: [2026-04-20 10:41:00 GMT+8] Feishu[default] DM | 李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2) [msg:om_x100b516d6d74bca8b2cd4a5ddd9a1cb] + +Conversation info (untrusted metadata): +```json +{ + "message_id": "om_x100b516d6d74bca8b2cd4a5ddd9a1cb", + "sender_id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "sender": "李承龙", + "timestamp": "Mon 2026-04-20 10:40 GMT+8" +} +``` + +Sender (untrusted metadata): +```json +{ + "label": "李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2)", + "id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "name": "李承龙" +} +``` + +你能查询到用户的手机号明文么 +assistant: [[reply_to_current]]承龙，可以的。`bi_vala_app_account` 表中有用户手机号字段，我能查询到明文手机号。 + +你需要查哪个用户的？提供 account_id、用户名或其他标识信息就行。 +user: System: [2026-04-20 10:44:48 GMT+8] Feishu[xiaoxi] DM | 李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2) [msg:om_x100b516d7f3cb044b37b6d0f9fb4af0] + +Conversation info (untrusted metadata): +```json +{ + "message_id": "om_x100b516d7f3cb044b37b6d0f9fb4af0", + "sender_id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "sender": "李承龙", + "timestamp": "Mon 2026-04-20 10:44 GMT+8" +} +``` + +Sender (untrusted metadata): +```json +{ + "label": "李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2)", + "id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "name": "李承龙" +} +``` + +account_id=57，查一下手机号明文 +assistant: [[reply_to_current]]承龙，account_id=57 的手机号信息如下： + +- **脱敏手机号：** 159****1022 +- **加密手机号：** 5WeooSK74KICOTX-LDEGhg.. + +数据库中 `tel` 字段存的是脱敏格式（中间四位打码），`tel_encrypt` 是加密后的密文。**没有明文手机号字段**，明文在入库前就已经做了脱敏和加密处理。 + +所以我这边无法直接查到完整的手机号明文，需要通过后端解密服务才能还原。要不要让技术同事协助解密？ +user: System: [2026-04-20 10:46:28 GMT+8] Feishu[xiaoxi] DM | 李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2) [msg:om_x100b516d768f3844b3fcabde789bfd7] + +Conversation info (untrusted metadata): +```json +{ + "message_id": "om_x100b516d768f3844b3fcabde789bfd7", + "sender_id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "sender": "李承龙", + "timestamp": "Mon 2026-04-20 10:46 GMT+8" +} +``` + +Sender (untrusted metadata): +```json +{ + "label": "李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2)", + "id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "name": "李承龙" +} +``` + +如果我给你手机号明文，你可以通过脱敏手机号字段进行模糊查询么 +assistant: +[[reply_to_current]]可以的。你给我明文手机号，我用前三位和后四位去 `tel` 字段匹配就行，比如手机号是 `13912345678`，我就查： + +```sql +WHERE tel LIKE '139****5678' +``` + +你发手机号过来吧。 +user: System: [2026-04-20 10:47:36 GMT+8] Feishu[xiaoxi] DM | 李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2) [msg:om_x100b516d72b2a934b3450fee9dcf8bd] + +Conversation info (untrusted metadata): +```json +{ + "message_id": "om_x100b516d72b2a934b3450fee9dcf8bd", + "sender_id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "sender": "李承龙", + "timestamp": "Mon 2026-04-20 10:47 GMT+8" +} +``` + +Sender (untrusted metadata): +```json +{ + "label": "李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2)", + "id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "name": "李承龙" +} +``` + +15944281022 +assistant: [[reply_to_current]]查到了，`159****1022` 对应的就是 **account_id = 57**，和你之前查的一致。 + +| 字段 | 值 | +|------|------| +| account_id | 57 | +| 脱敏手机号 | 159****1022 | +| status | 2（测试账号） | +| pay_status | 1 | +| 注册时间 | 2025-03-08 14:38 | + +需要进一步查这个用户的其他信息吗？ +user: [media attached: /root/.openclaw/media/inbound/ã_å_é_ä_人è_ä_å_ã_-ç_æ_è_è_è_å_è_¾æ_å---b57dacbc-6eac-4b04-b1b2-385562af4ece.xlsx (application/vnd.openxmlformats-officedocument.spreadsheetml.sheet) | /root/.openclaw/media/inbound/ã_å_é_ä_人è_ä_å_ã_-ç_æ_è_è_è_å_è_¾æ_å---b57dacbc-6eac-4b04-b1b2-385562af4ece.xlsx] +To send an image back, prefer the message tool (media/path/filePath). If you must inline, use MEDIA:https://example.com/image.jpg (spaces ok, quote if needed) or a safe relative path like MEDIA:./image.jpg. Avoid absolute paths (MEDIA:/...) and ~ paths — they are blocked for security. Keep caption in the text body. +System: [2026-04-20 11:16:56 GMT+8] Feishu[xiaoxi] DM | 李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2) [msg:om_x100b516de4a728a0b3d8cfdfa5c66a4, file, 1 attachment(s)] + +Conversation info (untrusted metadata): +```json +{ + "message_id": "om_x100b516de4a728a0b3d8cfdfa5c66a4", + "sender_id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "sender": "李承龙", + "timestamp": "Mon 2026-04-20 11:16 GMT+8" +} +``` + +Sender (untrusted metadata): +```json +{ + "label": "李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2)", + "id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "name": "李承龙" +} +``` + +[File: /root/.openclaw/media/inbound/ã_å_é_ä_人è_ä_å_ã_-ç_æ_è_è_è_å_è_¾æ_å---b57dacbc-6eac-4b04-b1b2-385562af4ece.xlsx] +assistant: [[reply_to_current]]收到，文件是**「学霸三人行专属」瓦拉英语试听课报名收集结果**，共 **774 条手机号**。 + +你需要我做什么？常见的操作比如： + +1. **匹配注册用户** — 用这些手机号去 `bi_vala_app_account` 表查哪些已注册 +2. **匹配付费用户** — 进一步关联订单表，看哪些已付费购课 +3. **整体转化漏斗** — 报名 → 注册 → 付费 的转化率统计 + +你说下需求，我来跑。 diff --git a/memory/2026-04-20-request-timed-out-before-a-res.md b/memory/2026-04-20-request-timed-out-before-a-res.md new file mode 100644 index 0000000..4c2b417 --- /dev/null +++ b/memory/2026-04-20-request-timed-out-before-a-res.md @@ -0,0 +1,88 @@ +# Session: 2026-04-20 04:08:35 UTC + +- **Session Key**: agent:main:feishu:direct:ou_e63ce6b760ad39382852472f28fbe2a2 +- **Session ID**: f1d7ceb4-fec0-4194-aa52-bec22f19ac06 +- **Source**: feishu + +## Conversation Summary + +assistant: + +有道理。改脚本，把脱敏手机号替换为明文。 +assistant: 核心改动：SQL 查询返回的是脱敏手机号，需要在 Python 层用 `masked→original` 映射表替换回明文。 +assistant: 测试一下： +assistant: 手机号已经是明文了。发文件给你： +assistant: phone_chapter_query_20260420_115730.xlsx +assistant: [[reply_to_current]]已改好，"脱敏手机号"列改成了"手机号"明文列。逻辑是：数据库查出脱敏格式后，在 Python 层用文件中的原始手机号映射回明文写入 xlsx。末尾未匹配的也是明文手机号。 + +文件已发，你看下格式对不对。 +user: System: [2026-04-20 12:00:50 GMT+8] Feishu[default] DM | 李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2) [msg:om_x100b516e01eda0b0b3f98a073c8edb3] + +Conversation info (untrusted metadata): +```json +{ + "message_id": "om_x100b516e01eda0b0b3f98a073c8edb3", + "sender_id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "sender": "李承龙", + "timestamp": "Mon 2026-04-20 12:00 GMT+8" +} +``` + +Sender (untrusted metadata): +```json +{ + "label": "李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2)", + "id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "name": "李承龙" +} +``` + +在这个skill里面添加，生成的文档发送到oc_616882799f1910b85a248b74f44c3be5这个群里 +assistant: 这个发送功能不适合放在 Python 脚本里（需要通过飞书 Bot 发送文件），更合适的方式是在 SKILL.md 的流程说明中加上发送步骤，我运行脚本后自动发到群里。 +assistant: 现在用刚才的结果文件测试一下发送到群里： +assistant: 现在把发送逻辑也集成到 SKILL.md 的流程中，确保我执行 skill 时自动完成。让我先验证发送到群里是否能成功： +assistant: 发送成功。现在我把这个发送逻辑也封装进脚本，让它一键完成查询+发送： +assistant: 测试完整流程： +assistant: 全流程通过 ✅ + +[[reply_to_current]]已更新 skill，现在脚本执行完会自动把 xlsx 文件发送到群 `oc_616882799f1910b85a248b74f44c3be5`。刚才用你的文件完整跑了一遍，文件已经发到群里了，你去看下。 + +新增功能： +- 默认查询完自动发送到目标群 +- 加了 `--no-send` 参数，如果只想生成文件不发群可以用： +```bash +python3 skills/phone-chapter-query/scripts/phone_chapter_query.py <文件> --no-send +``` +user: System: [2026-04-20 12:05:12 GMT+8] Feishu[xiaoxi] DM | 李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2) [msg:om_x100b516e11b36d3cb358895c6205a78] + +Conversation info (untrusted metadata): +```json +{ + "message_id": "om_x100b516e11b36d3cb358895c6205a78", + "sender_id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "sender": "李承龙", + "timestamp": "Mon 2026-04-20 12:05 GMT+8" +} +``` + +Sender (untrusted metadata): +```json +{ + "label": "李承龙 (ou_e63ce6b760ad39382852472f28fbe2a2)", + "id": "ou_e63ce6b760ad39382852472f28fbe2a2", + "name": "李承龙" +} +``` + +给我发一下这个skill的路径 +assistant: + +[[reply_to_current]]`/root/.openclaw/workspace/skills/phone-chapter-query/` + +文件结构： +``` +skills/phone-chapter-query/ +├── SKILL.md +└── scripts/ + └── phone_chapter_query.py +``` diff --git a/scripts/query_chapter_play.sh b/scripts/query_chapter_play.sh new file mode 100755 index 0000000..46a6d90 --- /dev/null +++ b/scripts/query_chapter_play.sh @@ -0,0 +1,178 @@ +#!/bin/bash +# 课时完成记录查询脚本 +# 查询指定课时(chapter_id)的首次完成记录，包含角色信息、最近登录、课程耗时 +# 数据库：线上 PostgreSQL (vala_bi) +# 输出：xlsx 格式 +# 用法：bash scripts/query_chapter_play.sh + +set -euo pipefail + +SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)" +source "${SCRIPT_DIR}/../secrets.env" + +DB_HOST="bj-postgres-16pob4sg.sql.tencentcdb.com" +DB_PORT="28591" +DB_USER="ai_member" +DB_NAME="vala_bi" + +OUTPUT_DIR="${SCRIPT_DIR}/../output" +mkdir -p "$OUTPUT_DIR" + +TIMESTAMP=$(date +%Y%m%d_%H%M%S) +CSV_TMP="${OUTPUT_DIR}/.chapter_play_${TIMESTAMP}.csv" +OUTPUT_FILE="${OUTPUT_DIR}/chapter_play_${TIMESTAMP}.xlsx" + +SQL=$(cat <<'EOF' +WITH chapter_play AS ( + SELECT user_id, chapter_id, chapter_unique_id, date(updated_at) AS finish_date + FROM bi_user_chapter_play_record_0 + WHERE chapter_id IN (55,56,57,58,59,343,344,345,346,348) AND play_status = 1 + UNION ALL + SELECT user_id, chapter_id, chapter_unique_id, date(updated_at) + FROM bi_user_chapter_play_record_1 + WHERE chapter_id IN (55,56,57,58,59,343,344,345,346,348) AND play_status = 1 + UNION ALL + SELECT user_id, chapter_id, chapter_unique_id, date(updated_at) + FROM bi_user_chapter_play_record_2 + WHERE chapter_id IN (55,56,57,58,59,343,344,345,346,348) AND play_status = 1 + UNION ALL + SELECT user_id, chapter_id, chapter_unique_id, date(updated_at) + FROM bi_user_chapter_play_record_3 + WHERE chapter_id IN (55,56,57,58,59,343,344,345,346,348) AND play_status = 1 + UNION ALL + SELECT user_id, chapter_id, chapter_unique_id, date(updated_at) + FROM bi_user_chapter_play_record_4 + WHERE chapter_id IN (55,56,57,58,59,343,344,345,346,348) AND play_status = 1 + UNION ALL + SELECT user_id, chapter_id, chapter_unique_id, date(updated_at) + FROM bi_user_chapter_play_record_5 + WHERE chapter_id IN (55,56,57,58,59,343,344,345,346,348) AND play_status = 1 + UNION ALL + SELECT user_id, chapter_id, chapter_unique_id, date(updated_at) + FROM bi_user_chapter_play_record_6 + WHERE chapter_id IN (55,56,57,58,59,343,344,345,346,348) AND play_status = 1 + UNION ALL + SELECT user_id, chapter_id, chapter_unique_id, date(updated_at) + FROM bi_user_chapter_play_record_7 + WHERE chapter_id IN (55,56,57,58,59,343,344,345,346,348) AND play_status = 1 +), +comp_time AS ( + SELECT chapter_unique_id, SUM(interval_time) AS total_interval + FROM ( + SELECT chapter_unique_id, interval_time FROM bi_user_component_play_record_0 + UNION ALL + SELECT chapter_unique_id, interval_time FROM bi_user_component_play_record_1 + UNION ALL + SELECT chapter_unique_id, interval_time FROM bi_user_component_play_record_2 + UNION ALL + SELECT chapter_unique_id, interval_time FROM bi_user_component_play_record_3 + UNION ALL + SELECT chapter_unique_id, interval_time FROM bi_user_component_play_record_4 + UNION ALL + SELECT chapter_unique_id, interval_time FROM bi_user_component_play_record_5 + UNION ALL + SELECT chapter_unique_id, interval_time FROM bi_user_component_play_record_6 + UNION ALL + SELECT chapter_unique_id, interval_time FROM bi_user_component_play_record_7 + ) t + GROUP BY chapter_unique_id +), +course_detail AS ( + SELECT + cp.user_id, + cp.chapter_id, + FORMAT('%s-%s-%s-%s', l.course_level, l.course_season, l.course_unit, l.course_lesson) AS course_id, + cp.finish_date, + FORMAT('%s:%s', + FLOOR(ct.total_interval / 1000 / 60), + LPAD(CAST(MOD(ct.total_interval / 1000, 60) AS TEXT), 2, '0') + ) AS finish_time + FROM ( + SELECT user_id, chapter_id, chapter_unique_id, finish_date, + ROW_NUMBER() OVER (PARTITION BY user_id, chapter_id ORDER BY finish_date) AS rn + FROM chapter_play + ) cp + LEFT JOIN bi_level_unit_lesson l ON cp.chapter_id = l.id + LEFT JOIN comp_time ct ON cp.chapter_unique_id = ct.chapter_unique_id + WHERE cp.rn = 1 +) + +SELECT + a.account_id AS "账号ID", + a.id AS "角色ID", + DATE(a.created_at) AS "注册日期", + DATE(TO_TIMESTAMP(b.latest_active_time)) AS "最近登录时间", + c.course_id AS "课程名称", + c.finish_date AS "课程完成时间", + c.finish_time AS "课程耗时" +FROM bi_vala_app_character a +LEFT JOIN user_detail_info b ON a.id = b.user_id +LEFT JOIN course_detail c ON a.id = c.user_id +WHERE a.status = 1 +ORDER BY a.id, c.course_id; +EOF +) + +echo "正在查询..." +PGPASSWORD="$PG_ONLINE_PASSWORD" psql \ + -h "$DB_HOST" \ + -p "$DB_PORT" \ + -U "$DB_USER" \ + -d "$DB_NAME" \ + --csv \ + -c "$SQL" \ + > "$CSV_TMP" + +ROW_COUNT=$(tail -n +2 "$CSV_TMP" | wc -l) +echo "查询完成，共 ${ROW_COUNT} 条记录，正在转换为 xlsx..." + +python3 - "$CSV_TMP" "$OUTPUT_FILE" <<'PYEOF' +import csv, sys +from openpyxl import Workbook +from openpyxl.styles import Font, Alignment, PatternFill + +csv_path, xlsx_path = sys.argv[1], sys.argv[2] + +wb = Workbook() +ws = wb.active +ws.title = "课时完成记录" + +# 读取 CSV +with open(csv_path, 'r', encoding='utf-8') as f: + reader = csv.reader(f) + for row in reader: + ws.append(row) + +# 表头样式 +header_font = Font(bold=True, color="FFFFFF", size=11) +header_fill = PatternFill(start_color="4472C4", end_color="4472C4", fill_type="solid") +header_align = Alignment(horizontal="center", vertical="center") + +for cell in ws[1]: + cell.font = header_font + cell.fill = header_fill + cell.alignment = header_align + +# 自动列宽 +for col in ws.columns: + max_len = 0 + col_letter = col[0].column_letter + for cell in col: + val = str(cell.value) if cell.value else "" + # 中文字符算 2 宽度 + width = sum(2 if ord(c) > 127 else 1 for c in val) + if width > max_len: + max_len = width + ws.column_dimensions[col_letter].width = min(max_len + 3, 30) + +# 冻结首行 +ws.freeze_panes = "A2" + +wb.save(xlsx_path) +print(f"xlsx 已保存: {xlsx_path}") +PYEOF + +# 清理临时 CSV +rm -f "$CSV_TMP" + +echo "完成！结果已保存至: ${OUTPUT_FILE}" diff --git a/scripts/run_component_practice_stat_daily.sh b/scripts/run_component_practice_stat_daily.sh index 52c6f89..a31747d 100755 --- a/scripts/run_component_practice_stat_daily.sh +++ b/scripts/run_component_practice_stat_daily.sh @@ -22,7 +22,7 @@ OUTPUT_CSV_L1_OOPS="/tmp/l1_oops_${TODAY}.csv" OUTPUT_CSV_L2_OOPS="/tmp/l2_oops_${TODAY}.csv" OUTPUT_CSV_L1_EXIT="/tmp/l1_exit_${TODAY}.csv" OUTPUT_CSV_L2_EXIT="/tmp/l2_exit_${TODAY}.csv" -OUTPUT_EXCEL="/root/.openclaw/workspace/组件练习质量统计_${TODAY}.xlsx" +OUTPUT_EXCEL="/root/.openclaw/workspace/output/组件练习质量统计_${TODAY}.xlsx" TARGET_CHAT="chat:oc_248d0efbc02d97d81d592d0417b6b296" LOG_FILE="/var/log/component_oops_stat.log" diff --git a/scripts/run_user_course_stat.sh b/scripts/run_user_course_stat.sh index ec4b075..ff33348 100755 --- a/scripts/run_user_course_stat.sh +++ b/scripts/run_user_course_stat.sh @@ -11,7 +11,7 @@ DB_USER="ai_member" DB_PASS="LdfjdjL83h3h3^$&**YGG*" SQL_PATH="/root/.openclaw/workspace/scripts/用户购课完课统计.sql" OUTPUT_CSV="/tmp/user_course_stat_$(date +%Y%m%d).csv" -OUTPUT_EXCEL="/root/.openclaw/workspace/用户购课完课统计_$(date +%Y%m%d).xlsx" +OUTPUT_EXCEL="/root/.openclaw/workspace/output/用户购课完课统计_$(date +%Y%m%d).xlsx" TARGET_CHAT="chat:oc_af81515caefe26918736ad1941286224" LOG_FILE="/var/log/user_course_stat.log" diff --git a/scripts/xueersi_weekly_report.sh b/scripts/xueersi_weekly_report.sh index 0a2c727..9db06a8 100755 --- a/scripts/xueersi_weekly_report.sh +++ b/scripts/xueersi_weekly_report.sh @@ -18,14 +18,13 @@ START_DATE=$(date -d "last sunday -6 days" +%Y-%m-%d) END_DATE=$(date -d "last sunday" +%Y-%m-%d) REPORT_DATE=$(date +%Y%m%d) CSV_PATH="/tmp/xueersi_weekly_data_${REPORT_DATE}.csv" -# 提取月日，去掉前导零，生成文件名 +# 提取月日，去掉前导零，生成文件名（使用"月""日"格式避免斜杠被截断） START_MONTH=$(date -d "${START_DATE}" +%-m) START_DAY=$(date -d "${START_DATE}" +%-d) END_MONTH=$(date -d "${END_DATE}" +%-m) END_DAY=$(date -d "${END_DATE}" +%-d) -# 本地保存路径用横杠避免路径问题，上传飞书时用带斜杠的显示名 -EXCEL_PATH="/tmp/学而思-瓦拉英语${START_MONTH}-${START_DAY}-${END_MONTH}-${END_DAY}.xlsx" -FEISHU_FILE_NAME="学而思-瓦拉英语${START_MONTH}/${START_DAY}-${END_MONTH}/${END_DAY}.xlsx" +EXCEL_PATH="/tmp/学而思-瓦拉英语${START_MONTH}月${START_DAY}日-${END_MONTH}月${END_DAY}日.xlsx" +FEISHU_FILE_NAME="学而思-瓦拉英语${START_MONTH}月${START_DAY}日-${END_MONTH}月${END_DAY}日.xlsx" # 1. 查询数据导出CSV PGPASSWORD="${PG_PASSWORD}" psql -h bj-postgres-16pob4sg.sql.tencentcdb.com -p 28591 -U ai_member -d vala_bi -c "\copy (WITH date_range AS (SELECT generate_series('${START_DATE}'::date, '${END_DATE}'::date, '1 day'::interval) AS stat_date), daily_new_users AS (SELECT DATE(created_at) AS stat_date, COUNT(DISTINCT id) AS new_user_count FROM bi_vala_app_account WHERE download_channel LIKE '%学而思%' AND created_at >= '${START_DATE} 00:00:00+08' AND created_at < '$(date -d "${END_DATE} +1 day" +%Y-%m-%d) 00:00:00+08' AND deleted_at IS NULL GROUP BY DATE(created_at)), daily_orders AS (SELECT DATE(o.pay_success_date) AS stat_date, COUNT(DISTINCT o.id) AS total_order_count, COUNT(DISTINCT CASE WHEN r.status = 3 AND o.order_status = 4 THEN o.id END) AS refund_order_count, ROUND(SUM(o.pay_amount_int)/100.0, 2) AS gmv, ROUND(SUM(o.pay_amount_int)/100.0 - COALESCE(SUM(CASE WHEN r.status = 3 AND o.order_status = 4 THEN r.refund_amount_int ELSE 0 END)/100.0, 0), 2) AS gsv FROM bi_vala_order o LEFT JOIN bi_refund_order r ON o.out_trade_no = r.out_trade_no WHERE o.key_from = 'app-active-h5-0-0' AND o.sale_channel = 21 AND o.pay_success_date >= '${START_DATE} 00:00:00+08' AND o.pay_success_date < '$(date -d "${END_DATE} +1 day" +%Y-%m-%d) 00:00:00+08' AND o.pay_success_date IS NOT NULL GROUP BY DATE(o.pay_success_date)), daily_data AS (SELECT TO_CHAR(d.stat_date, 'YYYY-MM-DD') AS 日期, COALESCE(u.new_user_count, 0) AS 新增用户数, COALESCE(o.total_order_count - o.refund_order_count, 0) AS 有效订单数, COALESCE(o.gsv, 0) AS GSV_元 FROM date_range d LEFT JOIN daily_new_users u ON d.stat_date = u.stat_date LEFT JOIN daily_orders o ON d.stat_date = o.stat_date) SELECT * FROM daily_data UNION ALL SELECT '合计' AS 日期, SUM(新增用户数) AS 新增用户数, SUM(有效订单数) AS 有效订单数, SUM(GSV_元) AS GSV_元 FROM daily_data ORDER BY 日期) TO '${CSV_PATH}' WITH (FORMAT csv, HEADER true, ENCODING 'UTF8');" diff --git a/skills/phone-chapter-query/SKILL.md b/skills/phone-chapter-query/SKILL.md new file mode 100644 index 0000000..d4dfe09 --- /dev/null +++ b/skills/phone-chapter-query/SKILL.md @@ -0,0 +1,62 @@ +--- +name: phone-chapter-query +description: | + 通过手机号文件查询用户课时完成记录。从 Excel/CSV 文件中提取手机号，匹配瓦拉账号， + 查询指定课时的首次完成记录（含课程耗时），输出带手机号明文的 xlsx 报表， + 并自动发送到指定飞书群。未匹配到账号的手机号追加在表尾。 + + **触发场景**: + (1) 用户发送包含手机号的 Excel/CSV 文件，要求查询课时完成记录 + (2) 用户提到"手机号"+"课时"/"学习记录"/"完成记录"的组合 + (3) 需要批量通过手机号关联账号并查询学习数据 +--- + +# 手机号课时完成记录查询 + +## 完整流程 + +1. 用户发送包含手机号的 Excel(.xlsx) 或 CSV(.csv) 文件 +2. 运行脚本：提取手机号 → 脱敏匹配账号 → 查询课时记录 → 生成 xlsx +3. 将生成的 xlsx 文件发送到飞书群 `oc_616882799f1910b85a248b74f44c3be5` +4. 同时回复用户确认结果 + +## 步骤1: 运行查询脚本 + +```bash +python3 skills/phone-chapter-query/scripts/phone_chapter_query.py [--output ] +``` + +- `input_file`: 包含手机号的文件路径（支持 .xlsx 和 .csv） +- `--output`: 可选，指定输出路径，默认 `output/phone_chapter_query_时间戳.xlsx` + +## 步骤2: 发送结果到飞书群 + +脚本执行完成后，使用 `lark-send-message-as-bot` skill 将生成的 xlsx 文件发送到目标群： + +- **目标群 chat_id**: `oc_616882799f1910b85a248b74f44c3be5` +- **发送方式**: Bot 身份发送文件消息 + +## 输出字段 + +| 字段 | 说明 | +|------|------| +| 账号ID | bi_vala_app_account.id | +| 手机号 | 明文手机号（来自输入文件） | +| 角色ID | bi_vala_app_character.id | +| 注册日期 | 角色创建时间 | +| 最近登录时间 | user_detail_info.latest_active_time | +| 课程名称 | 等级-季-单元-课时 格式 | +| 课程完成时间 | 首次完成日期 | +| 课程耗时 | 分:秒 格式 | + +未匹配到账号的手机号追加在表尾，仅手机号列有值。 + +## 匹配规则 + +- 自动识别文件中所有 `1` 开头的 11 位数字作为手机号 +- 脱敏后用 `bi_vala_app_account.tel` 字段 IN 匹配 +- 仅匹配 `status = 1` 且 `deleted_at IS NULL` 的账号 + +## 可配置项 + +脚本顶部的 `CHAPTER_IDS` 变量控制查询的课时范围，按需修改。 diff --git a/skills/phone-chapter-query/scripts/phone_chapter_query.py b/skills/phone-chapter-query/scripts/phone_chapter_query.py new file mode 100644 index 0000000..b7535e0 --- /dev/null +++ b/skills/phone-chapter-query/scripts/phone_chapter_query.py @@ -0,0 +1,413 @@ +#!/usr/bin/env python3 +""" +手机号 → 账号ID → 课时完成记录查询脚本 + +用法: + python3 scripts/phone_chapter_query.py [--output ] + +参数: + input_file 包含手机号的 Excel(.xlsx) 或 CSV(.csv) 文件路径 + --output 输出 xlsx 文件路径（可选，默认 output/phone_chapter_query_时间戳.xlsx） + +流程: + 1. 从文件中提取所有11位手机号（自动识别列） + 2. 脱敏后匹配 bi_vala_app_account（status=1 且未删除）获取 account_id + 3. 用 account_id 关联角色表，查询指定课时的首次完成记录（含耗时） + 4. 输出带手机号明文列的 xlsx 文件，未匹配手机号追加在末尾 +""" + +import argparse +import csv +import io +import json +import os +import re +import subprocess +import sys +import urllib.request +from datetime import datetime + +try: + import openpyxl + from openpyxl.styles import Font, Alignment, PatternFill +except ImportError: + print("ERROR: 需要 openpyxl 库，请运行: pip3 install openpyxl") + sys.exit(1) + + +# ─── 配置 ─────────────────────────────────────────────── +SCRIPT_DIR = os.path.dirname(os.path.abspath(__file__)) +# 工作区根目录：scripts/ -> phone-chapter-query/ -> skills/ -> workspace/ +WORKSPACE_DIR = os.path.dirname(os.path.dirname(os.path.dirname(SCRIPT_DIR))) +SECRETS_FILE = os.path.join(WORKSPACE_DIR, "secrets.env") +OUTPUT_DIR = os.path.join(WORKSPACE_DIR, "output") + +DB_HOST = "bj-postgres-16pob4sg.sql.tencentcdb.com" +DB_PORT = "28591" +DB_USER = "ai_member" +DB_NAME = "vala_bi" + +# 要查询的课时 ID，按需修改 +CHAPTER_IDS = "55,56,57,58,59,343,344,345,346,348" +# 分表数量（0-7） +SHARD_COUNT = 8 + +# 飞书发送配置 +LARK_CREDENTIALS = "/root/.openclaw/credentials/xiaoxi/config.json" +LARK_TARGET_CHAT_ID = "oc_616882799f1910b85a248b74f44c3be5" + + +def load_pg_password(): + """从 secrets.env 读取 PostgreSQL 密码""" + with open(SECRETS_FILE, "r") as f: + for line in f: + if line.startswith("PG_ONLINE_PASSWORD="): + return line.split("=", 1)[1].strip().strip("'\"") + raise RuntimeError("secrets.env 中未找到 PG_ONLINE_PASSWORD") + + +def extract_phones(file_path): + """从 xlsx 或 csv 文件中提取所有11位手机号""" + phones = [] + ext = os.path.splitext(file_path)[1].lower() + + if ext in (".xlsx", ".xls"): + wb = openpyxl.load_workbook(file_path, read_only=True) + for ws in wb: + for row in ws.iter_rows(values_only=True): + for cell in row: + if cell is not None: + val = str(int(cell)) if isinstance(cell, float) else str(cell) + val = val.strip() + if re.match(r"^1\d{10}$", val): + phones.append(val) + elif ext == ".csv": + with open(file_path, "r", encoding="utf-8-sig") as f: + reader = csv.reader(f) + for row in reader: + for cell in row: + val = cell.strip() + if re.match(r"^1\d{10}$", val): + phones.append(val) + else: + raise ValueError(f"不支持的文件格式: {ext}，仅支持 .xlsx 和 .csv") + + # 去重并保持顺序 + seen = set() + unique = [] + for p in phones: + if p not in seen: + seen.add(p) + unique.append(p) + return unique + + +def mask_phone(phone): + """手机号脱敏：前3 + **** + 后4""" + return f"{phone[:3]}****{phone[-4:]}" + + +def run_sql(sql, pg_password): + """执行 SQL 并返回 CSV 格式的结果""" + env = os.environ.copy() + env["PGPASSWORD"] = pg_password + result = subprocess.run( + ["psql", "-h", DB_HOST, "-p", DB_PORT, "-U", DB_USER, "-d", DB_NAME, "--csv", "-c", sql], + capture_output=True, text=True, env=env, timeout=300, + ) + if result.returncode != 0: + raise RuntimeError(f"SQL 执行失败:\n{result.stderr}") + return result.stdout + + +def step1_match_accounts(phones, pg_password): + """步骤1: 手机号脱敏后匹配 account_id，返回匹配结果和映射表""" + # masked -> [original1, original2, ...] （不同明文可能脱敏后相同） + masked_to_originals = {} + for p in phones: + m = mask_phone(p) + masked_to_originals.setdefault(m, []).append(p) + + conditions = ", ".join(f"'{m}'" for m in masked_to_originals) + sql = f""" + SELECT id AS account_id, tel AS masked_phone + FROM bi_vala_app_account + WHERE tel IN ({conditions}) + AND status = 1 + AND deleted_at IS NULL + ORDER BY id; + """ + output = run_sql(sql, pg_password) + + # 解析结果，构建 account_id -> 明文手机号 映射 + account_to_phone = {} # account_id -> original_phone + matched_masks = set() + reader = csv.DictReader(io.StringIO(output)) + for row in reader: + aid = row["account_id"] + masked = row["masked_phone"] + matched_masks.add(masked) + # 取该脱敏格式对应的第一个明文 + if masked in masked_to_originals: + account_to_phone[aid] = masked_to_originals[masked][0] + + account_ids = list(account_to_phone.keys()) + + # 未匹配的手机号（明文） + unmatched = [] + for m, originals in masked_to_originals.items(): + if m not in matched_masks: + unmatched.extend(originals) + + return account_ids, account_to_phone, unmatched + + +def build_union_sql(table_prefix, columns, where_clause, shard_count): + """生成分表 UNION ALL SQL""" + parts = [] + for i in range(shard_count): + parts.append(f"SELECT {columns} FROM {table_prefix}_{i} {where_clause}") + return " UNION ALL ".join(parts) + + +def step2_query_chapter_play(account_ids, pg_password): + """步骤2: 用 account_id 查询课时完成记录""" + if not account_ids: + return "" + + aid_list = ", ".join(account_ids) + + chapter_union = build_union_sql( + "bi_user_chapter_play_record", + "user_id, chapter_id, chapter_unique_id, date(updated_at) AS finish_date", + f"WHERE chapter_id IN ({CHAPTER_IDS}) AND play_status = 1", + SHARD_COUNT, + ) + + comp_union = build_union_sql( + "bi_user_component_play_record", + "chapter_unique_id, interval_time", + "", + SHARD_COUNT, + ) + + sql = f""" +WITH chapter_play AS ( + {chapter_union} +), +comp_time AS ( + SELECT chapter_unique_id, SUM(interval_time) AS total_interval + FROM ({comp_union}) t + GROUP BY chapter_unique_id +), +course_detail AS ( + SELECT + cp.user_id, + cp.chapter_id, + FORMAT('%s-%s-%s-%s', l.course_level, l.course_season, l.course_unit, l.course_lesson) AS course_id, + cp.finish_date, + FORMAT('%s:%s', + FLOOR(ct.total_interval / 1000 / 60), + LPAD(CAST(MOD(ct.total_interval / 1000, 60) AS TEXT), 2, '0') + ) AS finish_time + FROM ( + SELECT user_id, chapter_id, chapter_unique_id, finish_date, + ROW_NUMBER() OVER (PARTITION BY user_id, chapter_id ORDER BY finish_date) AS rn + FROM chapter_play + ) cp + LEFT JOIN bi_level_unit_lesson l ON cp.chapter_id = l.id + LEFT JOIN comp_time ct ON cp.chapter_unique_id = ct.chapter_unique_id + WHERE cp.rn = 1 +) + +SELECT + a.account_id AS "账号ID", + CAST(a.account_id AS TEXT) AS "account_id_str", + a.id AS "角色ID", + DATE(a.created_at) AS "注册日期", + DATE(TO_TIMESTAMP(b.latest_active_time)) AS "最近登录时间", + c.course_id AS "课程名称", + c.finish_date AS "课程完成时间", + c.finish_time AS "课程耗时" +FROM bi_vala_app_character a +JOIN bi_vala_app_account acct ON a.account_id = acct.id +LEFT JOIN user_detail_info b ON a.id = b.user_id +LEFT JOIN course_detail c ON a.id = c.user_id +WHERE a.status = 1 + AND acct.id IN ({aid_list}) +ORDER BY a.id, c.course_id; +""" + return run_sql(sql, pg_password) + + +def write_xlsx(csv_data, account_to_phone, unmatched_phones, output_path): + """将查询结果写入 xlsx，用明文手机号替换脱敏手机号""" + wb = openpyxl.Workbook() + ws = wb.active + ws.title = "课时完成记录" + + # 表头 + ws.append(["账号ID", "手机号", "角色ID", "注册日期", "最近登录时间", "课程名称", "课程完成时间", "课程耗时"]) + + if csv_data: + reader = csv.DictReader(io.StringIO(csv_data)) + for row in reader: + aid = row["账号ID"] + phone = account_to_phone.get(aid, "") + ws.append([ + aid, + phone, + row["角色ID"], + row["注册日期"], + row["最近登录时间"], + row["课程名称"], + row["课程完成时间"], + row["课程耗时"], + ]) + + # 追加未匹配手机号（明文） + for p in sorted(unmatched_phones): + ws.append(["", p, "", "", "", "", "", ""]) + + # 表头样式 + hf = Font(bold=True, color="FFFFFF", size=11) + hfill = PatternFill(start_color="4472C4", end_color="4472C4", fill_type="solid") + ha = Alignment(horizontal="center", vertical="center") + for cell in ws[1]: + cell.font = hf + cell.fill = hfill + cell.alignment = ha + + # 自动列宽 + for col in ws.columns: + max_w = 0 + cl = col[0].column_letter + for cell in col: + v = str(cell.value) if cell.value else "" + w = sum(2 if ord(c) > 127 else 1 for c in v) + if w > max_w: + max_w = w + ws.column_dimensions[cl].width = min(max_w + 3, 30) + + ws.freeze_panes = "A2" + wb.save(output_path) + + +def get_lark_token(): + """获取飞书 tenant_access_token""" + with open(LARK_CREDENTIALS, "r") as f: + config = json.load(f) + app_id = config["apps"][0]["appId"] + app_secret = config["apps"][0]["appSecret"] + + data = json.dumps({"app_id": app_id, "app_secret": app_secret}).encode() + req = urllib.request.Request( + "https://open.feishu.cn/open-apis/auth/v3/tenant_access_token/internal", + data=data, + headers={"Content-Type": "application/json"}, + ) + with urllib.request.urlopen(req, timeout=10) as resp: + result = json.loads(resp.read()) + return result["tenant_access_token"] + + +def send_file_to_chat(file_path, file_name, chat_id): + """上传文件并发送到飞书群""" + token = get_lark_token() + + # 上传文件 + upload_cmd = [ + "curl", "-s", "-X", "POST", + "https://open.feishu.cn/open-apis/im/v1/files", + "-H", f"Authorization: Bearer {token}", + "-F", "file_type=xls", + "-F", f"file_name={file_name}", + "-F", f"file=@{file_path}", + ] + result = subprocess.run(upload_cmd, capture_output=True, text=True, timeout=60) + upload_resp = json.loads(result.stdout) + if upload_resp.get("code") != 0: + raise RuntimeError(f"文件上传失败: {upload_resp}") + file_key = upload_resp["data"]["file_key"] + + # 发送文件消息 + send_data = json.dumps({ + "receive_id": chat_id, + "msg_type": "file", + "content": json.dumps({"file_key": file_key}), + }) + req = urllib.request.Request( + f"https://open.feishu.cn/open-apis/im/v1/messages?receive_id_type=chat_id", + data=send_data.encode(), + headers={ + "Authorization": f"Bearer {token}", + "Content-Type": "application/json", + }, + ) + with urllib.request.urlopen(req, timeout=10) as resp: + send_resp = json.loads(resp.read()) + if send_resp.get("code") != 0: + raise RuntimeError(f"消息发送失败: {send_resp}") + return send_resp["data"]["message_id"] + + +def main(): + parser = argparse.ArgumentParser(description="手机号 → 课时完成记录查询") + parser.add_argument("input_file", help="包含手机号的 Excel 或 CSV 文件") + parser.add_argument("--output", "-o", help="输出 xlsx 文件路径") + parser.add_argument("--no-send", action="store_true", help="不发送到飞书群（仅生成文件）") + args = parser.parse_args() + + os.makedirs(OUTPUT_DIR, exist_ok=True) + if args.output: + output_path = args.output + else: + ts = datetime.now().strftime("%Y%m%d_%H%M%S") + output_path = os.path.join(OUTPUT_DIR, f"phone_chapter_query_{ts}.xlsx") + + # 加载密码 + print("读取数据库配置...") + pg_password = load_pg_password() + + # 提取手机号 + print(f"读取文件: {args.input_file}") + phones = extract_phones(args.input_file) + print(f"提取到 {len(phones)} 个手机号（去重后）") + if not phones: + print("ERROR: 未提取到任何手机号") + sys.exit(1) + + # 匹配 account_id + print("匹配账号...") + account_ids, account_to_phone, unmatched = step1_match_accounts(phones, pg_password) + print(f"已匹配: {len(account_ids)} 个账号，未匹配: {len(unmatched)} 个手机号") + + # 查询课时完成记录 + if account_ids: + print(f"查询课时完成记录（{len(account_ids)} 个账号）...") + csv_data = step2_query_chapter_play(account_ids, pg_password) + row_count = csv_data.strip().count("\n") + print(f"查询到 {row_count} 条记录") + else: + csv_data = "" + print("无匹配账号，跳过课时查询") + + # 生成 xlsx + print("生成 xlsx...") + write_xlsx(csv_data, account_to_phone, unmatched, output_path) + print(f"文件保存至: {output_path}") + + # 发送到飞书群 + if not args.no_send: + print(f"发送到飞书群 {LARK_TARGET_CHAT_ID}...") + file_name = os.path.basename(output_path) + msg_id = send_file_to_chat(output_path, file_name, LARK_TARGET_CHAT_ID) + print(f"发送成功！message_id: {msg_id}") + else: + print("跳过飞书发送（--no-send）") + + print("全部完成！") + + +if __name__ == "__main__": + main()