<feed xmlns='http://www.w3.org/2005/Atom'>
<title>claude-plugins-official.git/external_plugins/imessage, branch bump/cloud-sql-postgresql</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>imessage: surface every inbound image, not just the first</title>
<updated>2026-09-30T19:34:53+00:00</updated>
<author>
<name>dltn</name>
<email>6599399+dltn@users.noreply.github.com</email>
</author>
<published>2026-09-30T19:34:53+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=b6041c772138cdb3408fb4d93accd770f0ec56a1'/>
<id>b6041c772138cdb3408fb4d93accd770f0ec56a1</id>
<content type='text'>
An iMessage with several photos arrived with only the first one in the
channel tag: handleInbound took the first image attachment and stopped.
Collect every image attachment instead (same filters as before) and pass
each path in the notification meta as image_path, image_path_2,
image_path_3, ... so the model can Read all of them. A single image still
produces exactly image_path, so existing behaviour is unchanged.

Numbered keys rather than an array or a joined list: Claude Code accepts
only string values in channel meta and renders each key as an attribute
on the &lt;channel&gt; tag, so keys must be plain identifiers; one key per path
also avoids inventing a delimiter for sender-controlled filenames. The
attachments query gains ORDER BY a.ROWID so the numbering follows
attachment ROWID (creation) order. Instructions and README updated to
match; version 0.1.0 -&gt; 0.2.0 in plugin.json and package.json.

Known limits, unchanged by this patch: attachments still downloading
when the message row is first polled (filename NULL) are skipped and,
since the poll watermark has already passed the message, never picked up
later; HEIC is passed through unconverted; attachments with a NULL
mime_type still pass the image filter; no cap on images per message.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
An iMessage with several photos arrived with only the first one in the
channel tag: handleInbound took the first image attachment and stopped.
Collect every image attachment instead (same filters as before) and pass
each path in the notification meta as image_path, image_path_2,
image_path_3, ... so the model can Read all of them. A single image still
produces exactly image_path, so existing behaviour is unchanged.

Numbered keys rather than an array or a joined list: Claude Code accepts
only string values in channel meta and renders each key as an attribute
on the &lt;channel&gt; tag, so keys must be plain identifiers; one key per path
also avoids inventing a delimiter for sender-controlled filenames. The
attachments query gains ORDER BY a.ROWID so the numbering follows
attachment ROWID (creation) order. Instructions and README updated to
match; version 0.1.0 -&gt; 0.2.0 in plugin.json and package.json.

Known limits, unchanged by this patch: attachments still downloading
when the message row is first polled (filename NULL) are skipped and,
since the poll watermark has already passed the message, never picked up
later; HEIC is passed through unconverted; attachments with a NULL
mime_type still pass the image filter; no cap on images per message.
</pre>
</div>
</content>
</entry>
<entry>
<title>Merge pull request #1055 from anthropics/kenneth/imessage-permission-selfchat-only</title>
<updated>2026-03-30T21:08:48+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-30T21:08:48+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=31e7200b33db954ec45cae5dd1bed9bd6611bbe3'/>
<id>31e7200b33db954ec45cae5dd1bed9bd6611bbe3</id>
<content type='text'>
imessage: restrict permission relay to self-chat, fix echo filter &amp; tapback noise</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
imessage: restrict permission relay to self-chat, fix echo filter &amp; tapback noise</pre>
</div>
</content>
</entry>
<entry>
<title>feat(imessage): add IMESSAGE_DB_PATH env var for testing</title>
<updated>2026-03-27T20:45:56+00:00</updated>
<author>
<name>Russell Coleman</name>
<email>russell@anthropic.com</email>
</author>
<published>2026-03-27T20:45:56+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=a1ffbcc771d406a0945669e644cc7b7bb17bb913'/>
<id>a1ffbcc771d406a0945669e644cc7b7bb17bb913</id>
<content type='text'>
Mirrors the existing IMESSAGE_STATE_DIR override. Lets a mock sqlite
chat.db stand in for ~/Library/Messages/chat.db so chat_messages can be
tested without macOS + Full Disk Access + real iMessage history.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Mirrors the existing IMESSAGE_STATE_DIR override. Lets a mock sqlite
chat.db stand in for ~/Library/Messages/chat.db so chat_messages can be
tested without macOS + Full Disk Access + real iMessage history.
</pre>
</div>
</content>
</entry>
<entry>
<title>imessage: bump to 0.1.0</title>
<updated>2026-03-27T06:43:51+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-27T06:43:51+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=22bd61d01feca3d17b70ebb933ba3ea82f6b2bc9'/>
<id>22bd61d01feca3d17b70ebb933ba3ea82f6b2bc9</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>imessage: drop SMS/RCS by default, opt-in via IMESSAGE_ALLOW_SMS</title>
<updated>2026-03-27T06:41:39+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-27T06:41:39+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=60c3fc36ede027ae31403dda501c99ac96f4afd7'/>
<id>60c3fc36ede027ae31403dda501c99ac96f4afd7</id>
<content type='text'>
SMS sender IDs are spoofable; iMessage is Apple-ID-authenticated and
end-to-end encrypted. The plugin previously treated both identically,
so a forged SMS from the owner's own number would match SELF, bypass
the access gate, and inherit owner-level trust — including permission
approval.

handleInbound now drops anything with service != 'iMessage' unless
IMESSAGE_ALLOW_SMS=true. Default is the safe path; users who want SMS
can opt in after reading the warning in README.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
SMS sender IDs are spoofable; iMessage is Apple-ID-authenticated and
end-to-end encrypted. The plugin previously treated both identically,
so a forged SMS from the owner's own number would match SELF, bypass
the access gate, and inherit owner-level trust — including permission
approval.

handleInbound now drops anything with service != 'iMessage' unless
IMESSAGE_ALLOW_SMS=true. Default is the safe path; users who want SMS
can opt in after reading the warning in README.
</pre>
</div>
</content>
</entry>
<entry>
<title>imessage: trim comment cruft</title>
<updated>2026-03-27T06:16:27+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-27T06:16:27+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=c4274521decb8ced6f2bdcff5fb32273ed3296d9'/>
<id>c4274521decb8ced6f2bdcff5fb32273ed3296d9</id>
<content type='text'>
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
</pre>
</div>
</content>
</entry>
<entry>
<title>imessage: harden echo filter normalization</title>
<updated>2026-03-27T06:12:19+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-27T06:12:19+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=8dfc27925804e1a1b51eaf1afc53892ebc77ae71'/>
<id>8dfc27925804e1a1b51eaf1afc53892ebc77ae71</id>
<content type='text'>
The self-chat echo filter matches outbound text against what chat.db
stores on round-trip. Three divergence sources caused false negatives
and duplicate bubbles:

- Signature suffix: "\nSent by Claude" is appended on send, but the
  \n may not round-trip identically through attributedBody
- Emoji variation selectors (U+FE00-FE0F) and ZWJ (U+200D): chat.db
  can add or drop these on emoji characters
- Smart quotes: macOS auto-substitutes straight quotes on the way in

Strip/normalize all three in echoKey() before the existing whitespace
collapse.

Fixes #1024
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
The self-chat echo filter matches outbound text against what chat.db
stores on round-trip. Three divergence sources caused false negatives
and duplicate bubbles:

- Signature suffix: "\nSent by Claude" is appended on send, but the
  \n may not round-trip identically through attributedBody
- Emoji variation selectors (U+FE00-FE0F) and ZWJ (U+200D): chat.db
  can add or drop these on emoji characters
- Smart quotes: macOS auto-substitutes straight quotes on the way in

Strip/normalize all three in echoKey() before the existing whitespace
collapse.

Fixes #1024
</pre>
</div>
</content>
</entry>
<entry>
<title>imessage: drop whitespace-only messages from tapbacks/receipts</title>
<updated>2026-03-27T06:11:49+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-27T06:11:49+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=c29338f2762a2c6e531c2bb781841319a538ed63'/>
<id>c29338f2762a2c6e531c2bb781841319a538ed63</id>
<content type='text'>
Tapback reactions and read receipts synced from linked devices arrive
as chat.db rows with whitespace-only text. The existing empty-check
used falsy comparison which doesn't catch ' ' or invisible chars,
causing unsolicited replies to reaction taps.

Fixes #1041
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Tapback reactions and read receipts synced from linked devices arrive
as chat.db rows with whitespace-only text. The existing empty-check
used falsy comparison which doesn't catch ' ' or invisible chars,
causing unsolicited replies to reaction taps.

Fixes #1041
</pre>
</div>
</content>
</entry>
<entry>
<title>imessage: restrict permission relay to self-chat only</title>
<updated>2026-03-27T06:11:29+00:00</updated>
<author>
<name>Kenneth Lien</name>
<email>kenneth@anthropic.com</email>
</author>
<published>2026-03-27T06:11:29+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=03a685d5f612f890dbe63446dae2f762a3e7e65e'/>
<id>03a685d5f612f890dbe63446dae2f762a3e7e65e</id>
<content type='text'>
Permission prompts were being broadcast to all allowlisted contacts plus
every DM resolvable from the SELF address set. Two compounding bugs:

1. SELF was polluted by chat.last_addressed_handle, which on machines
   with SMS history returns short codes, business handles, and other
   contacts' numbers — not just the owner's addresses. One reporter's
   query returned 50 addresses (2 actually theirs) resolving to 148 DM
   chats, all of which received permission prompts.

2. Even with a clean SELF, the handler sent to allowFrom + SELF, so
   every allowlisted contact received the prompt and could reply to
   approve tool execution on the owner's machine.

Fix:
- Build SELF from message.account WHERE is_from_me=1 only
- Send permission prompts to self-chat only, not allowFrom
- Accept permission replies from self-chat only

Fixes #1048
Fixes #1010
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Permission prompts were being broadcast to all allowlisted contacts plus
every DM resolvable from the SELF address set. Two compounding bugs:

1. SELF was polluted by chat.last_addressed_handle, which on machines
   with SMS history returns short codes, business handles, and other
   contacts' numbers — not just the owner's addresses. One reporter's
   query returned 50 addresses (2 actually theirs) resolving to 148 DM
   chats, all of which received permission prompts.

2. Even with a clean SELF, the handler sent to allowFrom + SELF, so
   every allowlisted contact received the prompt and could reply to
   approve tool execution on the owner's machine.

Fix:
- Build SELF from message.account WHERE is_from_me=1 only
- Send permission prompts to self-chat only, not allowFrom
- Accept permission replies from self-chat only

Fixes #1048
Fixes #1010
</pre>
</div>
</content>
</entry>
<entry>
<title>feat(imessage): conversational format for chat_messages</title>
<updated>2026-03-25T23:50:00+00:00</updated>
<author>
<name>Russell Coleman</name>
<email>russell@anthropic.com</email>
</author>
<published>2026-03-25T23:50:00+00:00</published>
<link rel='alternate' type='text/html' href='https://git.1991861.xyz/claude-plugins-official.git/commit/?id=28f743438419dfc122180b4c0d723f1e94374d96'/>
<id>28f743438419dfc122180b4c0d723f1e94374d96</id>
<content type='text'>
Reformat chat_messages output from flat per-message lines to grouped
conversation threads. Each thread gets a header labelling it DM or Group
with its participant list, date-separator lines when the calendar day
rolls over, and [HH:MM] local-time stamps instead of full ISO.

chat_guid is now optional — omit to dump every allowlisted chat at once
for a quick multi-thread overview. Default limit raised 20→100 per chat,
capped at 500.

New queries: qChatParticipants (handle list per chat) and qChatInfo
(display_name + style to distinguish DM/group). renderMsg replaced by
conversationHeader + renderConversation.
</content>
<content type='xhtml'>
<div xmlns='http://www.w3.org/1999/xhtml'>
<pre>
Reformat chat_messages output from flat per-message lines to grouped
conversation threads. Each thread gets a header labelling it DM or Group
with its participant list, date-separator lines when the calendar day
rolls over, and [HH:MM] local-time stamps instead of full ISO.

chat_guid is now optional — omit to dump every allowlisted chat at once
for a quick multi-thread overview. Default limit raised 20→100 per chat,
capped at 500.

New queries: qChatParticipants (handle list per chat) and qChatInfo
(display_name + style to distinguish DM/group). renderMsg replaced by
conversationHeader + renderConversation.
</pre>
</div>
</content>
</entry>
</feed>
