tg-responder

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

tg-responder — Telegram Communications Assistant

tg-responder — Telegram通讯助手

Review pending response drafts and manage the Telegram response queue.

审核待处理的回复草稿，管理Telegram回复队列。

Commands

命令

review — Approve pending drafts

review — 审核待处理草稿

Read the responder queue and present drafts for approval:

bash

python3 ~/.claude/skills/tg-responder/scripts/schema.py  # ensure DB exists

Then query the database:

sql

-- Pending drafts needing approval
SELECT o.id, o.chat_id, o.draft_text, o.draft_reason, o.source,
       i.sender_name, i.text as original_text, i.urgency, i.category,
       datetime(i.received_at, 'unixepoch') as received
FROM outbox o
JOIN inbox i ON o.inbox_id = i.id
WHERE o.status = 'draft'
ORDER BY
  CASE i.urgency WHEN 'urgent' THEN 0 WHEN 'normal' THEN 1 ELSE 2 END,
  o.created_at ASC;

For each draft, present to the user:

Original message — who sent it, when, what they said
Draft response — the proposed reply
Options: approve (send as-is), edit (modify then send), skip

To approve and send a draft:

Update outbox:

UPDATE outbox SET status = 'approved', final_text = draft_text, approved_at = strftime('%s','now') WHERE id = ?

Send via telegram skill:

python3 ~/.claude/skills/telegram/scripts/telegram_fetch.py send --chat-id CHAT_ID --text "THE_TEXT"

Update outbox with sent status and message_id

To skip:

UPDATE outbox SET status = 'skipped', updated_at = strftime('%s','now') WHERE id = ?

读取回复队列并展示待审核草稿：

bash

python3 ~/.claude/skills/tg-responder/scripts/schema.py  # ensure DB exists

随后查询数据库：

sql

-- Pending drafts needing approval
SELECT o.id, o.chat_id, o.draft_text, o.draft_reason, o.source,
       i.sender_name, i.text as original_text, i.urgency, i.category,
       datetime(i.received_at, 'unixepoch') as received
FROM outbox o
JOIN inbox i ON o.inbox_id = i.id
WHERE o.status = 'draft'
ORDER BY
  CASE i.urgency WHEN 'urgent' THEN 0 WHEN 'normal' THEN 1 ELSE 2 END,
  o.created_at ASC;

针对每个草稿，向用户展示以下内容：

原始消息 — 发送人、发送时间、消息内容
回复草稿 — 拟回复内容
操作选项：批准（直接发送）、编辑（修改后发送）、跳过

批准并发送草稿的步骤：

更新发件箱：

UPDATE outbox SET status = 'approved', final_text = draft_text, approved_at = strftime('%s','now') WHERE id = ?

通过Telegram技能发送：

python3 ~/.claude/skills/telegram/scripts/telegram_fetch.py send --chat-id CHAT_ID --text "THE_TEXT"

更新发件箱状态为已发送，并记录message_id

跳过操作：

UPDATE outbox SET status = 'skipped', updated_at = strftime('%s','now') WHERE id = ?

status — Queue statistics

status — 队列统计

sql

-- Inbox stats
SELECT status, count(*) FROM inbox GROUP BY status;

-- Outbox stats
SELECT status, count(*) FROM outbox GROUP BY status;

-- Recent activity
SELECT sender_name, route, status, datetime(created_at, 'unixepoch')
FROM inbox ORDER BY created_at DESC LIMIT 10;

Report: pending count, drafts waiting, sent today, failed items.

sql

-- Inbox stats
SELECT status, count(*) FROM inbox GROUP BY status;

-- Outbox stats
SELECT status, count(*) FROM outbox GROUP BY status;

-- Recent activity
SELECT sender_name, route, status, datetime(created_at, 'unixepoch')
FROM inbox ORDER BY created_at DESC LIMIT 10;

统计报告内容：待处理数量、待审核草稿数、今日已发送数、失败项数。

follow-ups — Track unanswered outbound messages

follow-ups — 追踪未回复的外发消息

Scan for people who haven't replied, send reminders with exponential backoff.

bash

undefined

扫描未回复用户，按照指数退避规则发送提醒。

bash

undefined

Scan for new unanswered messages (needs Telethon session — stop daemon first)

python3 ~/.claude/skills/tg-responder/scripts/follow_ups.py scan

Process due reminders (drafts to Telegram or outbox)

python3 ~/.claude/skills/tg-responder/scripts/follow_ups.py remind

List active follow-ups

python3 ~/.claude/skills/tg-responder/scripts/follow_ups.py list

Archive expired follow-ups

python3 ~/.claude/skills/tg-responder/scripts/follow_ups.py archive

Run all (scan + check replies + remind + archive)

python3 ~/.claude/skills/tg-responder/scripts/follow_ups.py all


Also query directly:
```sql
SELECT sender_name, outbound_text, reminder_count, max_reminders,
       datetime(outbound_at, 'unixepoch') as sent,
       datetime(next_reminder_at, 'unixepoch') as next_ping,
       status
FROM follow_ups
WHERE status = 'active'
ORDER BY next_reminder_at;

Schedule: exponential (3d → 6d → 12d), fixed (every Nd), or custom per contact. After max_reminders → archived. If they reply → auto-resolved.

python3 ~/.claude/skills/tg-responder/scripts/follow_ups.py all


也可直接查询数据库：
```sql
SELECT sender_name, outbound_text, reminder_count, max_reminders,
       datetime(outbound_at, 'unixepoch') as sent,
       datetime(next_reminder_at, 'unixepoch') as next_ping,
       status
FROM follow_ups
WHERE status = 'active'
ORDER BY next_reminder_at;

提醒计划：指数退避（3天→6天→12天）、固定间隔（每N天）或按联系人自定义。达到最大提醒次数后自动归档；若用户回复则自动标记为已解决。

Database

数据库

Located at

~/Brains/data/telegram/responder.db

数据库路径：

~/Brains/data/telegram/responder.db

。

Config

配置文件

Located at

~/.claude/skills/tg-responder/config.yaml

. Edit contacts, modes, and ignore lists there.

配置文件路径：

~/.claude/skills/tg-responder/config.yaml

。可在此编辑联系人、模式和忽略列表。

Worker

工作进程

Start:

python3 ~/.claude/skills/tg-responder/scripts/worker.py

One-shot:

python3 ~/.claude/skills/tg-responder/scripts/worker.py --once

启动命令：

python3 ~/.claude/skills/tg-responder/scripts/worker.py

单次执行：

python3 ~/.claude/skills/tg-responder/scripts/worker.py --once