agent-messenger 2.30.0 → 2.32.0

package/docs/content/docs/sdk/discord.mdx

@@ -144,8 +144,19 @@ const dm = await client.createDM(userId)
 const mentions = await client.getMentions()
 const filtered = await client.getMentions({ limit: 10, guildId: serverId })
 // → DiscordMention[]
+
+// Get only unread mentions — the messages behind Discord's unread-mention badge
+const unread = await client.getUnreadMentions()
+const scoped = await client.getUnreadMentions({ guildId: serverId, limit: 200 })
+// → DiscordUnreadMentionsResult { mentions, count, badgeCount, complete, windowDays }
+
+// Snapshot per-channel read state directly (one-shot gateway connect)
+const readState = await client.fetchReadState()
+// → DiscordReadState[] { channelId, lastMessageId, mentionCount }
 ```
 
+`getUnreadMentions` correlates recent mention history (Discord's 7-day window) with per-channel read state, returning only mentions newer than each channel's read marker. `count` is the number of enumerated unread mentions; `badgeCount` is Discord's own account-wide unread-mention badge total (not narrowed by `guildId`, since read states carry no guild association); `complete` is `true` when the scan exhausted all available mention history (Discord's 7-day window) and `false` when it stopped early at `limit` or a non-advancing cursor.
+
 ### User Notes
 
 ```typescript
@@ -345,6 +356,9 @@ import type {
   DiscordReaction,
   DiscordFile,
   DiscordMention,
+  DiscordReadState,
+  DiscordUnreadMention,
+  DiscordUnreadMentionsResult,
   DiscordUserNote,
   DiscordSearchResult,
   DiscordSearchResponse,
@@ -478,6 +492,30 @@ for (const mention of mentions) {
 }
 ```
 
+### Unread Mentions Digest
+
+Fetch only unread mentions, reply to each, and mark them read.
+
+```typescript
+import { DiscordClient } from 'agent-messenger/discord'
+
+const client = await new DiscordClient().login({ token })
+
+const { mentions, count, badgeCount, complete } = await client.getUnreadMentions()
+
+console.log(`${count} unread mentions fetched (badge shows ${badgeCount})`)
+if (!complete) {
+  console.log('The scan hit the limit — some unread mentions may not have been fetched')
+}
+
+for (const mention of mentions) {
+  await client.sendMessage(mention.channel_id, `On it <@${mention.author.id}>!`)
+
+  // Mark the message read so it drops off the unread badge
+  await client.ackMessage(mention.channel_id, mention.id)
+}
+```
+
 ### Search Triage
 
 Search for urgent messages, acknowledge with a reaction, and reply with a follow-up.

package/docs/content/docs/sdk/kakaotalk.mdx

@@ -126,6 +126,43 @@ await client.sendAttachment('9876543210', [
 
 The typed helpers `sendPhoto`, `sendVideo`, `sendAudio`, `sendFile`, and `sendMultiPhoto` remain available when you want to bypass MIME sniffing and dispatch to a specific message_type explicitly.
 
+### Leave Chat
+
+```typescript
+const result = await client.leaveChat('9876543210')
+// → { success: true, status_code: 0, chat_id: '9876543210' }
+```
+
+Leaves a chat room by its chat ID. Works on 1:1, group, open, and PlusChat rooms. Returns `success: true` on a successful leave. The departed chat is immediately evicted from the client's cached chat list — a subsequent `getChats()` call will not include it.
+
+### Typing Indicator
+
+```typescript
+// Fire a single typing pulse — the recipient sees the animated "…" dots
+const result = await client.sendTyping('9876543210')
+// → KakaoTypingResult { success: true, status_code: 0, chat_id: '9876543210' }
+
+// For OpenChat rooms, pass the linkId
+await client.sendTyping('9876543210', { linkId: '77777' })
+```
+
+The KakaoTalk client-side lifetime is ~5s per pulse — to keep the indicator visible while generating a long reply, re-fire faster than that (e.g. every 3s):
+
+```typescript
+const interval = setInterval(() => {
+  client.sendTyping('9876543210').catch(() => {}) // ignore transient errors
+}, 3000)
+
+try {
+  const reply = await generateReply()
+  await client.sendMessage('9876543210', reply)
+} finally {
+  clearInterval(interval)
+}
+```
+
+Errors follow the same shape as `markRead`: transport-level failures (non-zero `statusCode`, including the synthetic `-1` LocoConnection emits on disconnect) throw `KakaoTalkError('send_typing_failed')` so `executeWithReconnect` can retry on a fresh session. Non-numeric `chatId` / `linkId` throw `invalid_chat_id` / `invalid_link_id`.
+
 ### Cleanup
 
 ```typescript
@@ -239,6 +276,7 @@ import type {
   KakaoMember,
   KakaoMessage,
   KakaoSendResult,
+  KakaoTypingResult,
   KakaoAccountCredentials,
   KakaoConfig,
   KakaoDeviceType,
@@ -256,6 +294,7 @@ import {
   KakaoMemberSchema,
   KakaoMessageSchema,
   KakaoSendResultSchema,
+  KakaoTypingResultSchema,
   KakaoAccountCredentialsSchema,
   KakaoConfigSchema,
 } from 'agent-messenger/kakaotalk'

package/e2e/README.md

@@ -199,10 +199,10 @@ When triggering manually, you can select which platform to test:
 | ------------- | ------------------------------------------ |
 | `auth`        | status                                     |
 | `server`      | list, current, info                        |
-| `message`     | send, list, get\*, delete, ack, search     |
+| `message`     | send, list, get, delete, ack, search       |
 | `channel`     | list, info, history                        |
 | `user`        | list\*, me, info                           |
-| `reaction`    | add\*, list\*, remove\*                    |
+| `reaction`    | add, list, remove                           |
 | `file`        | upload, list, info                         |
 | `snapshot`    | default\*, --channels-only, --users-only\* |
 

package/e2e/discord.e2e.test.ts

@@ -83,7 +83,7 @@ describe('Discord E2E Tests', () => {
       expect(Array.isArray(data)).toBe(true)
     })
 
-    it.skip('message get retrieves specific message (requires bot token)', async () => {
+    it('message get retrieves specific message', async () => {
       const testId = generateTestId()
       const { id } = await createTestMessage('discord', DISCORD_TEST_CHANNEL_ID, `Get test ${testId}`)
       testMessages.push(id)
@@ -194,7 +194,7 @@ describe('Discord E2E Tests', () => {
   })
 
   describe('reaction', () => {
-    it.skip('reaction add/list/remove lifecycle (requires bot token)', async () => {
+    it('reaction add/list/remove lifecycle', async () => {
       const testId = generateTestId()
       const { id } = await createTestMessage('discord', DISCORD_TEST_CHANNEL_ID, `Reaction test ${testId}`)
       testMessages.push(id)
@@ -210,12 +210,26 @@ describe('Discord E2E Tests', () => {
       // List reactions
       const listResult = await runCLI('discord', ['reaction', 'list', DISCORD_TEST_CHANNEL_ID, id])
       expect(listResult.exitCode).toBe(0)
+      const listed = parseJSON<{ reactions: Array<{ emoji: { name: string | null }; count: number }> }>(
+        listResult.stdout,
+      )
+      const addedReaction = listed?.reactions.find((reaction) => reaction.emoji.name === '👍')
+      expect(addedReaction?.count).toBeGreaterThan(0)
 
       await waitForRateLimit()
 
       // Remove reaction
       const removeResult = await runCLI('discord', ['reaction', 'remove', DISCORD_TEST_CHANNEL_ID, id, '👍'])
       expect(removeResult.exitCode).toBe(0)
+
+      await waitForRateLimit()
+
+      const afterRemoveResult = await runCLI('discord', ['reaction', 'list', DISCORD_TEST_CHANNEL_ID, id])
+      expect(afterRemoveResult.exitCode).toBe(0)
+      const afterRemove = parseJSON<{ reactions: Array<{ emoji: { name: string | null }; count: number }> }>(
+        afterRemoveResult.stdout,
+      )
+      expect(afterRemove?.reactions.find((reaction) => reaction.emoji.name === '👍')).toBeUndefined()
     }, 15000) // Longer timeout for multiple operations
   })
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-messenger",
-  "version": "2.30.0",
+  "version": "2.32.0",
   "description": "Multi-platform messaging CLI for AI agents (Slack, Discord, Teams, Webex, Telegram, Telegram Bot, WhatsApp, LINE, iMessage, Instagram, KakaoTalk, Channel Talk)",
   "repository": {
     "type": "git",
@@ -211,7 +211,7 @@
     "oxlint": "^1.51.0",
     "tsc-alias": "^1.8.16",
     "tsx": "^4.21.0",
-    "typescript": "^5.9.3"
+    "typescript": "^7.0.2"
   },
   "optionalDependencies": {
     "koffi": "^2.15.2",

package/skills/agent-channeltalk/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-channeltalk
 description: Interact with Channel Talk using extracted desktop app or browser credentials - read chats, send messages, search messages, manage groups
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-channeltalk:*)
 metadata:
   openclaw:

package/skills/agent-channeltalkbot/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-channeltalkbot
 description: Interact with Channel Talk workspaces using API credentials - send messages, read chats, manage groups and bots
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-channeltalkbot:*)
 metadata:
   openclaw:

package/skills/agent-discord/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-discord
 description: Interact with Discord servers - send messages, read channels, manage reactions
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-discord:*)
 metadata:
   openclaw:
@@ -269,8 +269,20 @@ agent-discord dm create <user-id>
 agent-discord mention list
 agent-discord mention list --limit 50
 agent-discord mention list --guild <server-id>
+
+# List only unread mentions (the app's unread-mention badge)
+agent-discord mention unread
+agent-discord mention unread --guild <server-id>
+agent-discord mention unread --limit 200
 ```
 
+`mention unread` correlates your recent mention history (last 7 days) with Discord's
+per-channel read state, returning only mentions newer than each channel's read marker.
+Output includes `count` (enumerated unread mentions), `badge_count` (Discord's own
+account-wide unread-mention badge total — not narrowed by `--guild`), and `complete`
+(whether the scan reached the end of history within the 7-day window). `badge_count`
+can exceed `count` when unread mentions fall outside the 7-day window.
+
 ### Friend Commands
 
 ```bash
@@ -503,6 +515,12 @@ const { results } = await client.searchMessages(serverId, 'deployment', {
   limit: 5,
 })
 
+// List unread mentions (correlates mention history with per-channel read state)
+const { mentions, count, badgeCount, complete } = await client.getUnreadMentions()
+// count = enumerated unread mentions; badgeCount = account-wide badge total;
+// complete = true when all available mentions (7-day window) were scanned,
+// false when the scan stopped early at the limit or a non-advancing cursor
+
 // Create a thread
 const thread = await client.createThread(channelId, 'Discussion Topic')
 await client.sendMessage(thread.id, 'First message in thread')

package/skills/agent-discordbot/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-discordbot
 description: Interact with Discord servers using bot tokens - send messages, read channels, manage reactions
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-discordbot:*)
 metadata:
   openclaw:

package/skills/agent-imessage/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-imessage
 description: Interact with iMessage on a Mac via the imsg tool - send messages, read chats, watch for new messages
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-imessage:*)
 metadata:
   openclaw:

package/skills/agent-instagram/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-instagram
 description: Interact with Instagram DMs - send messages, read conversations, manage accounts
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-instagram:*)
 metadata:
   openclaw:

package/skills/agent-kakaotalk/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-kakaotalk
 description: Interact with KakaoTalk - send messages, read chats, manage conversations
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-kakaotalk:*)
 metadata:
   openclaw:
@@ -303,6 +303,23 @@ Output includes:
 - `unread_count` — unread message count
 - `last_message` — most recent message preview, including `author_name` when the sender's nickname is known from the chat list (otherwise `null`)
 
+### Chat Leave
+
+```bash
+# Leave a chat room (works on 1:1, group, open, and PlusChat rooms)
+agent-kakaotalk chat leave <chat-id>
+agent-kakaotalk chat leave <chat-id> --pretty
+agent-kakaotalk chat leave <chat-id> --account <account-id>
+```
+
+Output (JSON by default; `--pretty` pretty-prints the same JSON):
+
+```json
+{ "success": true, "status_code": 0, "chat_id": "9876543210" }
+```
+
+The process exits non-zero when `success` is `false`.
+
 ### Member Commands
 
 ```bash
@@ -623,7 +640,7 @@ See the [KakaoTalk SDK documentation](https://agent-messenger.dev/docs/sdk/kakao
 ## Limitations
 
 - Auto-extraction of email/password from the desktop app is **macOS and Windows only** (KakaoTalk desktop is not available on Linux). Linux users must pass `--email` and `--password` (or `--password-file`) explicitly — the LOCO protocol, login flow, and all messaging features work on Linux.
-- No channel/chat room creation or management
+- No chat room creation
 - No friend list management
 - No reactions or emoji
 - No message editing or deletion

package/skills/agent-line/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-line
 description: Interact with LINE - send messages, read chats, manage conversations
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-line:*)
 metadata:
   openclaw:

package/skills/agent-slack/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-slack
 description: Interact with Slack workspaces - send messages, read channels, manage reactions
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-slack:*)
 metadata:
   openclaw:

package/skills/agent-slackbot/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-slackbot
 description: Interact with Slack workspaces using bot tokens - send messages, read channels, manage reactions
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-slackbot:*)
 metadata:
   openclaw:

package/skills/agent-teams/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-teams
 description: Interact with Microsoft Teams - send messages, read channels, manage reactions
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-teams:*)
 metadata:
   openclaw:

package/skills/agent-telegram/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-telegram
 description: Interact with Telegram through TDLib - authenticate, inspect chats, and send messages
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-telegram:*)
 ---
 

package/skills/agent-telegrambot/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-telegrambot
 description: Interact with Telegram using bot tokens - send messages, read chats, manage reactions
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-telegrambot:*)
 metadata:
   openclaw:

package/skills/agent-webex/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-webex
 description: Interact with Cisco Webex - send messages, read spaces, manage memberships
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-webex:*)
 metadata:
   openclaw:

package/skills/agent-webexbot/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-webexbot
 description: Interact with Cisco Webex using bot tokens - send messages, reply in threads, upload and download files, look up people, read spaces, manage memberships, stream real-time events
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-webexbot:*)
 metadata:
   openclaw:

package/skills/agent-wechatbot/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-wechatbot
 description: Interact with WeChat Official Account using API credentials - send messages, manage templates, list followers
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-wechatbot:*)
 metadata:
   openclaw:

package/skills/agent-whatsapp/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-whatsapp
 description: Interact with WhatsApp - send messages, read chats, manage conversations
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-whatsapp:*)
 metadata:
   openclaw:

package/skills/agent-whatsappbot/SKILL.md

@@ -1,7 +1,7 @@
 ---
 name: agent-whatsappbot
 description: Interact with WhatsApp using Cloud API credentials - send messages, manage templates
-version: 2.30.0
+version: 2.32.0
 allowed-tools: Bash(agent-whatsappbot:*)
 metadata:
   openclaw: