chore(sync): mirror docs from openclaw/openclaw@b5f25de352

.openclaw-sync/source.json

@@ -1,5 +1,5 @@
 {
   "repository": "openclaw/openclaw",
-  "sha": "5c85624eeba4e5cbd3a14344dfadbee89623016c",
-  "syncedAt": "2026-04-21T02:22:37.690Z"
+  "sha": "b5f25de3520e7468d599613514e1f2406a1239f8",
+  "syncedAt": "2026-04-21T03:01:49.874Z"
 }

docs/.generated/config-baseline.sha256

@@ -1,4 +1,4 @@
-ab40431597e9f7c09a9f010f267bab250c7f9c570c4a100776de98869f589a92  config-baseline.json
+580abc79677d84fa66cb55e42ea093bfa9681655861166c02dfaa5a313d44310  config-baseline.json
 04a82c2208bf69e0a195e7712e3a518a8255c1bb002c31f712cb95003325635b  config-baseline.core.json
 e239cc20f20f8d0172812bc0ad3ee6df52da88e2e2702e3d03a47e01561132ae  config-baseline.channel.json
-b695cb31b4c0cf1d31f842f2892e99cc3ff8d84263ae72b72977cae844b81d6e  config-baseline.plugin.json
+8fb3a1cf5fe56ab8fc2cb46341c3403aed32b0d1f0aaeac0e96cd3599db4f06e  config-baseline.plugin.json

docs/channels/bluebubbles.md

@@ -217,6 +217,54 @@ Per-group configuration:
 - Uses `allowFrom` and `groupAllowFrom` to determine command authorization.
 - Authorized senders can run control commands even without mentioning in groups.
 
+### Per-group system prompt
+
+Each entry under `channels.bluebubbles.groups.*` accepts an optional `systemPrompt` string. The value is injected into the agent's system prompt on every turn that handles a message in that group, so you can set per-group persona or behavioral rules without editing agent prompts:
+
+```json5
+{
+  channels: {
+    bluebubbles: {
+      groups: {
+        "iMessage;-;chat123": {
+          systemPrompt: "Keep responses under 3 sentences. Mirror the group's casual tone.",
+        },
+      },
+    },
+  },
+}
+```
+
+The key matches whatever BlueBubbles reports as `chatGuid` / `chatIdentifier` / numeric `chatId` for the group, and a `"*"` wildcard entry provides a default for every group without an exact match (same pattern used by `requireMention` and per-group tool policies). Exact matches always win over the wildcard. DMs ignore this field; use agent-level or account-level prompt customization instead.
+
+#### Worked example: threaded replies and tapback reactions (Private API)
+
+With the BlueBubbles Private API enabled, inbound messages arrive with short message IDs (for example `[[reply_to:5]]`) and the agent can call `action=reply` to thread into a specific message or `action=react` to drop a tapback. A per-group `systemPrompt` is a reliable way to keep the agent choosing the right tool:
+
+```json5
+{
+  channels: {
+    bluebubbles: {
+      groups: {
+        "iMessage;+;chat-family": {
+          systemPrompt: [
+            "When replying in this group, always call action=reply with the",
+            "[[reply_to:N]] messageId from context so your response threads",
+            "under the triggering message. Never send a new unlinked message.",
+            "",
+            "For short acknowledgements ('ok', 'got it', 'on it'), use",
+            "action=react with an appropriate tapback emoji (❤️, 👍, 😂, ‼️, ❓)",
+            "instead of sending a text reply.",
+          ].join(" "),
+        },
+      },
+    },
+  },
+}
+```
+
+Tapback reactions and threaded replies both require the BlueBubbles Private API; see [Advanced actions](#advanced-actions) and [Message IDs](#message-ids-short-vs-full) for the underlying mechanics.
+
 ## ACP conversation bindings
 
 BlueBubbles chats can be turned into durable ACP workspaces without changing the transport layer.