telegram/discord: make state dir configurable via env var

Hardcoded ~/.claude/channels/<name>/ meant only one bot per machine.
Respect TELEGRAM_STATE_DIR / DISCORD_STATE_DIR so users can run
multiple bots with separate tokens and allowlists.

Also fixed README path ('in your project' -> '~/...') to match the code.

Fixes #792

external_plugins/discord/README.md

@@ -55,7 +55,9 @@ Install the plugin:
 /discord:configure MTIz...
 ```
 
-Writes `DISCORD_BOT_TOKEN=...` to `.claude/channels/discord/.env` in your project. You can also write that file by hand, or set the variable in your shell environment — shell takes precedence.
+Writes `DISCORD_BOT_TOKEN=...` to `~/.claude/channels/discord/.env`. You can also write that file by hand, or set the variable in your shell environment — shell takes precedence.
+
+> To run multiple bots on one machine (different tokens, separate allowlists), point `DISCORD_STATE_DIR` at a different directory per instance.
 
 **6. Relaunch with the channel flag.**
 

external_plugins/discord/server.ts

@@ -29,7 +29,7 @@ import { readFileSync, writeFileSync, mkdirSync, readdirSync, rmSync, statSync,
 import { homedir } from 'os'
 import { join, sep } from 'path'
 
-const STATE_DIR = join(homedir(), '.claude', 'channels', 'discord')
+const STATE_DIR = process.env.DISCORD_STATE_DIR ?? join(homedir(), '.claude', 'channels', 'discord')
 const ACCESS_FILE = join(STATE_DIR, 'access.json')
 const APPROVED_DIR = join(STATE_DIR, 'approved')
 const ENV_FILE = join(STATE_DIR, '.env')
@@ -423,7 +423,7 @@ const mcp = new Server(
       '',
       'Messages from Discord arrive as <channel source="discord" chat_id="..." message_id="..." user="..." ts="...">. If the tag has attachment_count, the attachments attribute lists name/type/size — call download_attachment(chat_id, message_id) to fetch them. Reply with the reply tool — pass chat_id back. Use reply_to (set to a message_id) only when replying to an earlier message; the latest message doesn\'t need a quote-reply, omit reply_to for normal responses.',
       '',
-      'reply accepts file paths (files: ["/abs/path.png"]) for attachments. Use react to add emoji reactions, and edit_message for interim progress updates. Edits don\'t trigger push notifications — when a long task completes, send a new reply so the user\'s device pings.',
+      'reply accepts file paths (files: ["/abs/path.png"]) for attachments. Use react to add emoji reactions, and edit_message to update a message you previously sent (e.g. progress → result).',
       '',
       "fetch_messages pulls real Discord history. Discord's search API isn't available to bots — if the user asks you to find an old message, fetch more history or ask them roughly when it was.",
       '',
@@ -471,7 +471,7 @@ mcp.setRequestHandler(ListToolsRequestSchema, async () => ({
     },
     {
       name: 'edit_message',
-      description: 'Edit a message the bot previously sent. Useful for interim progress updates. Edits don\'t trigger push notifications — send a new reply when a long task completes so the user\'s device pings.',
+      description: 'Edit a message the bot previously sent. Useful for progress updates (send "working…" then edit to the result).',
       inputSchema: {
         type: 'object',
         properties: {

external_plugins/telegram/README.md

@@ -35,7 +35,9 @@ Install the plugin:
 /telegram:configure 123456789:AAHfiqksKZ8...
 ```
 
-Writes `TELEGRAM_BOT_TOKEN=...` to `.claude/channels/telegram/.env` in your project. You can also write that file by hand, or set the variable in your shell environment — shell takes precedence.
+Writes `TELEGRAM_BOT_TOKEN=...` to `~/.claude/channels/telegram/.env`. You can also write that file by hand, or set the variable in your shell environment — shell takes precedence.
+
+> To run multiple bots on one machine (different tokens, separate allowlists), point `TELEGRAM_STATE_DIR` at a different directory per instance.
 
 **4. Relaunch with the channel flag.**
 

external_plugins/telegram/server.ts

@@ -22,7 +22,7 @@ import { readFileSync, writeFileSync, mkdirSync, readdirSync, rmSync, statSync,
 import { homedir } from 'os'
 import { join, extname, sep } from 'path'
 
-const STATE_DIR = join(homedir(), '.claude', 'channels', 'telegram')
+const STATE_DIR = process.env.TELEGRAM_STATE_DIR ?? join(homedir(), '.claude', 'channels', 'telegram')
 const ACCESS_FILE = join(STATE_DIR, 'access.json')
 const APPROVED_DIR = join(STATE_DIR, 'approved')
 const ENV_FILE = join(STATE_DIR, '.env')
@@ -343,7 +343,7 @@ const mcp = new Server(
       '',
       'Messages from Telegram arrive as <channel source="telegram" chat_id="..." message_id="..." user="..." ts="...">. If the tag has an image_path attribute, Read that file — it is a photo the sender attached. Reply with the reply tool — pass chat_id back. Use reply_to (set to a message_id) only when replying to an earlier message; the latest message doesn\'t need a quote-reply, omit reply_to for normal responses.',
       '',
-      'reply accepts file paths (files: ["/abs/path.png"]) for attachments. Use react to add emoji reactions, and edit_message for interim progress updates. Edits don\'t trigger push notifications — when a long task completes, send a new reply so the user\'s device pings.',
+      'reply accepts file paths (files: ["/abs/path.png"]) for attachments. Use react to add emoji reactions, and edit_message to update a message you previously sent (e.g. progress → result).',
       '',
       "Telegram's Bot API exposes no history or search — you only see messages as they arrive. If you need earlier context, ask the user to paste it or summarize.",
       '',
@@ -391,7 +391,7 @@ mcp.setRequestHandler(ListToolsRequestSchema, async () => ({
     },
     {
       name: 'edit_message',
-      description: 'Edit a message the bot previously sent. Useful for interim progress updates. Edits don\'t trigger push notifications — send a new reply when a long task completes so the user\'s device pings.',
+      description: 'Edit a message the bot previously sent. Useful for progress updates (send "working…" then edit to the result).',
       inputSchema: {
         type: 'object',
         properties: {