<feed xmlns='http://www.w3.org/2005/Atom'>
<title>claude-plugins-official.git/external_plugins/discord/server.ts, branch add-cloud-sql-sqlserver</title>
<subtitle>Official Claude Code plugin directory
</subtitle>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/'/>
<entry>
<title>fix(discord): use cached author.id when DMChannel.recipientId is null (#1365)</title>
<updated>2026-04-14T21:46:42+00:00</updated>
<author>
<name>Daisy S. Hollman</name>
<email>thewholedaisy@gmail.com</email>
</author>
<published>2026-04-14T21:46:42+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=48aa43517886014e90ee80a6461f9de75045369d'/>
<id>48aa43517886014e90ee80a6461f9de75045369d</id>
<content type='text'>
DMChannel.recipientId can be null when client.channels.fetch() returns
a DM channel with a cold cache. The inbound gate correctly uses
msg.author.id, but fetchAllowedChannel relied on recipientId, so
replies to allowlisted DMs intermittently failed with "channel not
allowlisted" after session restart.

Maintain a channelId→userId map populated during inbound handling and
fall back to it when recipientId is null.

Fixes anthropics/claude-code#40576
Fixes anthropics/claude-code#41647

:house: Remote-Dev: homespace</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
DMChannel.recipientId can be null when client.channels.fetch() returns
a DM channel with a cold cache. The inbound gate correctly uses
msg.author.id, but fetchAllowedChannel relied on recipientId, so
replies to allowlisted DMs intermittently failed with "channel not
allowlisted" after session restart.

Maintain a channelId→userId map populated during inbound handling and
fall back to it when recipientId is null.

Fixes anthropics/claude-code#40576
Fixes anthropics/claude-code#41647

:house: Remote-Dev: homespace</pre>
</div>
</content>
</entry>
<entry>
<title>feat(telegram,discord): compact permission messages with expandable details (#952)</title>
<updated>2026-03-24T05:53:47+00:00</updated>
<author>
<name>Noah Zweben</name>
<email>noahz@anthropic.com</email>
</author>
<published>2026-03-24T05:53:47+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=4b1e2a28ceab32b49b447d6255d6f3c4fa8774de'/>
<id>4b1e2a28ceab32b49b447d6255d6f3c4fa8774de</id>
<content type='text'>
* feat(telegram,discord): compact permission messages with expandable details

Replace verbose permission request messages with a compact format showing
only the tool name. Adds a "See more" button that expands inline to show
tool_name, description, and pretty-printed input_preview JSON. Yes/No
buttons replace Allow/Deny. Bump plugin versions to 0.0.4.

* revert: restore Allow/Deny button labels</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
* feat(telegram,discord): compact permission messages with expandable details

Replace verbose permission request messages with a compact format showing
only the tool name. Adds a "See more" button that expands inline to show
tool_name, description, and pretty-printed input_preview JSON. Yes/No
buttons replace Allow/Deny. Bump plugin versions to 0.0.4.

* revert: restore Allow/Deny button labels</pre>
</div>
</content>
</entry>
<entry>
<title>feat(telegram,discord): inline buttons for permission approval (#945)</title>
<updated>2026-03-24T05:19:51+00:00</updated>
<author>
<name>Daisy S. Hollman</name>
<email>thewholedaisy@gmail.com</email>
</author>
<published>2026-03-24T05:19:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=b3a0714d7ffc4dec08b8d0dad2aa3dc09b000e98'/>
<id>b3a0714d7ffc4dec08b8d0dad2aa3dc09b000e98</id>
<content type='text'>
Replace "Reply 'yes abcde' to allow" text instruction with native
inline buttons (Telegram InlineKeyboard, Discord ButtonBuilder).
One tap to approve/deny instead of typing a 5-char ID.

- Telegram: callback_query handler with allowFrom gate, edits message
  to show outcome and remove buttons after decision
- Discord: interactionCreate handler with allowFrom gate, updates
  interaction with outcome and clears components
- Text-reply path (PERMISSION_REPLY_RE) kept as fallback
- Bump both plugins to v0.0.3

:house: Remote-Dev: homespace</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Replace "Reply 'yes abcde' to allow" text instruction with native
inline buttons (Telegram InlineKeyboard, Discord ButtonBuilder).
One tap to approve/deny instead of typing a 5-char ID.

- Telegram: callback_query handler with allowFrom gate, edits message
  to show outcome and remove buttons after decision
- Discord: interactionCreate handler with allowFrom gate, updates
  interaction with outcome and clears components
- Text-reply path (PERMISSION_REPLY_RE) kept as fallback
- Bump both plugins to v0.0.3

:house: Remote-Dev: homespace</pre>
</div>
</content>
</entry>
<entry>
<title>feat(telegram,discord): permission-relay capability + bidirectional handlers</title>
<updated>2026-03-23T08:59:02+00:00</updated>
<author>
<name>Daisy Hollman</name>
<email>daisy@anthropic.com</email>
</author>
<published>2026-03-20T22:44:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=daa84c99c815fb2832ecb5df80613e2088af0191'/>
<id>daa84c99c815fb2832ecb5df80613e2088af0191</id>
<content type='text'>
Complete the plugin side of anthropics/claude-cli-internal#23061 (permission
prompts over channels).

Capability: both servers now declare
  experimental["claude/channel/permission"]
which tells CC they can relay permission requests. This capability asserts the
server authenticates the replier — gate()/access.allowFrom filters
non-allowlisted senders before handleInbound runs.

Outbound (CC → user): setNotificationHandler for
  notifications/claude/channel/permission_request
formats the tool name, description, and input preview into a human-readable
message and sends it to every allowlisted DM. Groups are excluded — the
security thread resolution was "single-user mode for official plugins."

Inbound (user → CC): PERMISSION_REPLY_RE intercept in handleInbound catches
"yes xxxxx" / "no xxxxx" replies, emits the structured
  notifications/claude/channel/permission
event with {request_id, behavior}, reacts with checkmark/cross, and returns
without relaying the text to Claude as a chat message.

The regex is inlined from channelPermissions.ts (no cross-repo dep). IDs are
lowercased at the plugin boundary per the case-insensitive spec.

Version bumped 0.0.1 → 0.0.2 so the plugin reconciler picks up the change.

:house: Remote-Dev: homespace
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Complete the plugin side of anthropics/claude-cli-internal#23061 (permission
prompts over channels).

Capability: both servers now declare
  experimental["claude/channel/permission"]
which tells CC they can relay permission requests. This capability asserts the
server authenticates the replier — gate()/access.allowFrom filters
non-allowlisted senders before handleInbound runs.

Outbound (CC → user): setNotificationHandler for
  notifications/claude/channel/permission_request
formats the tool name, description, and input preview into a human-readable
message and sends it to every allowlisted DM. Groups are excluded — the
security thread resolution was "single-user mode for official plugins."

Inbound (user → CC): PERMISSION_REPLY_RE intercept in handleInbound catches
"yes xxxxx" / "no xxxxx" replies, emits the structured
  notifications/claude/channel/permission
event with {request_id, behavior}, reacts with checkmark/cross, and returns
without relaying the text to Claude as a chat message.

The regex is inlined from channelPermissions.ts (no cross-repo dep). IDs are
lowercased at the plugin boundary per the case-insensitive spec.

Version bumped 0.0.1 → 0.0.2 so the plugin reconciler picks up the change.

:house: Remote-Dev: homespace
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge remote-tracking branch 'origin/kenneth/discord-resilience' into kenneth/channels-rollup</title>
<updated>2026-03-20T20:13:08+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-20T20:13:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=87e0f09336e25874bc3b17c4328e2ed391f6a2a5'/>
<id>87e0f09336e25874bc3b17c4328e2ed391f6a2a5</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge remote-tracking branch 'origin/kenneth/discord-edit-notif-guidance' into kenneth/channels-rollup</title>
<updated>2026-03-20T20:13:08+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-20T20:13:08+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=aa4f7c4fb0a60b07ae8219162c2c739de26f3f3c'/>
<id>aa4f7c4fb0a60b07ae8219162c2c739de26f3f3c</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>discord: port resilience fixes from telegram</title>
<updated>2026-03-20T18:28:51+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-20T18:28:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=aa71c24314ab2336e4ae55d59490180822789d49'/>
<id>aa71c24314ab2336e4ae55d59490180822789d49</id>
<content type='text'>
Same patterns as #812/#813 for the discord channel:
- process-level unhandledRejection/uncaughtException handlers
- client.on('error') to log discord.js errors
- mcp.notification().catch() so inbound delivery failures surface
- stdin close / SIGTERM -&gt; client.destroy() + exit (zombie fix)
- .unref() the approval-check interval
- client.login().catch() to log+exit on bad token instead of crashing

Discord is inherently more resilient than telegram (discord.js
auto-reconnects, no 409 equivalent), but these gaps were still there.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Same patterns as #812/#813 for the discord channel:
- process-level unhandledRejection/uncaughtException handlers
- client.on('error') to log discord.js errors
- mcp.notification().catch() so inbound delivery failures surface
- stdin close / SIGTERM -&gt; client.destroy() + exit (zombie fix)
- .unref() the approval-check interval
- client.login().catch() to log+exit on bad token instead of crashing

Discord is inherently more resilient than telegram (discord.js
auto-reconnects, no 409 equivalent), but these gaps were still there.
</pre>
</div>
</content>
</entry>
<entry>
<title>discord/telegram: guide assistant to send new reply on completion</title>
<updated>2026-03-20T18:27:09+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-20T18:27:09+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=5c58308be4c6f234a90bc93464bc2c065c4a54f0'/>
<id>5c58308be4c6f234a90bc93464bc2c065c4a54f0</id>
<content type='text'>
Message edits don't trigger push notifications on the user's device.
Update system instructions and edit_message tool description to steer
the assistant toward edit-for-progress + new-reply-on-completion.

Fixes #786
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Message edits don't trigger push notifications on the user's device.
Update system instructions and edit_message tool description to steer
the assistant toward edit-for-progress + new-reply-on-completion.

Fixes #786
</pre>
</div>
</content>
</entry>
<entry>
<title>telegram/discord: make state dir configurable via env var</title>
<updated>2026-03-20T17:56:57+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-20T17:56:57+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=14927ff475758115791aceb4b53c0aadce8db4d8'/>
<id>14927ff475758115791aceb4b53c0aadce8db4d8</id>
<content type='text'>
Hardcoded ~/.claude/channels/&lt;name&gt;/ 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' -&gt; '~/...') to match the code.

Fixes #792
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Hardcoded ~/.claude/channels/&lt;name&gt;/ 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' -&gt; '~/...') to match the code.

Fixes #792
</pre>
</div>
</content>
</entry>
<entry>
<title>Lock telegram/discord .env files to owner (chmod 600)</title>
<updated>2026-03-20T17:37:13+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-20T17:37:13+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=8140fbad22814b99ad56e1161a43ec203da669d8'/>
<id>8140fbad22814b99ad56e1161a43ec203da669d8</id>
<content type='text'>
The bot token is a credential. Tighten perms on load so hand-written
or pre-existing .env files get locked down, and update the configure
skill to chmod after writing. No-op on Windows.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The bot token is a credential. Tighten perms on load so hand-written
or pre-existing .env files get locked down, and update the configure
skill to chmod after writing. No-op on Windows.
</pre>
</div>
</content>
</entry>
</feed>
