fix(whatsapp): drop status broadcasts and channel newsletters before agent dispatch (#25845)

WhatsApp pseudo-chats (Status updates / Stories, Channels / Newsletters,
broadcast lists) were being routed through the full agent pipeline. A
user's gateway.log showed the agent replying to a contact's Story
('status@broadcast') with 345 chars plus title-generation cost, which
also shows up in the contact's status feed.

Drop these JIDs at _should_process_message() before the policy gate so
they're filtered regardless of dm_policy or allowlist state. Covers:
- status@broadcast (Stories)
- *@newsletter (Channels)
- *@broadcast (broadcast lists, future-proofing)

The bridge.js already filters these on the fromMe outbound path, but
inbound events on self-chat mode skipped that check.

Tests:
- status@broadcast dropped on open policy
- broadcast filter wins over allowlisted senders
- real DMs still pass through
- helper unit cases (case-insensitive, whitespace-tolerant)

26/26 tests/gateway/test_whatsapp_group_gating.py pass; 59/59 adjacent
WhatsApp test suites pass.
This commit is contained in:
Teknium 2026-05-14 09:59:03 -07:00 committed by GitHub
parent b08f53a758
commit 9ed751b967
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 103 additions and 1 deletions

View file

@ -322,6 +322,26 @@ class WhatsAppAdapter(BasePlatformAdapter):
return {str(part).strip() for part in raw if str(part).strip()}
return {part.strip() for part in str(raw).split(",") if part.strip()}
@staticmethod
def _is_broadcast_chat(chat_id: str) -> bool:
"""True for WhatsApp pseudo-chats that aren't real conversations.
Covers Status updates (Stories) and Channel/Newsletter broadcasts.
These show up as inbound messages on Baileys but the agent should
never reply answering a Story update spams the contact's status
feed, and Channel posts aren't addressable in the first place.
"""
if not chat_id:
return False
cid = chat_id.strip().lower()
if cid == "status@broadcast":
return True
# @broadcast suffix covers status@broadcast plus any future
# broadcast-list variants. @newsletter is the Channel JID suffix.
if cid.endswith("@broadcast") or cid.endswith("@newsletter"):
return True
return False
def _is_dm_allowed(self, sender_id: str) -> bool:
"""Check whether a DM from the given sender should be processed."""
if self._dm_policy == "disabled":
@ -432,9 +452,16 @@ class WhatsAppAdapter(BasePlatformAdapter):
return cleaned.strip() or text
def _should_process_message(self, data: Dict[str, Any]) -> bool:
chat_id_raw = str(data.get("chatId") or "")
# WhatsApp uses pseudo-chats for Status updates (Stories) and
# Channel/Newsletter broadcasts. These are not real conversations
# and the agent should never reply to them — even in self-chat mode
# where the bridge may surface them as "fromMe" events.
if self._is_broadcast_chat(chat_id_raw):
return False
is_group = data.get("isGroup", False)
if is_group:
chat_id = str(data.get("chatId") or "")
chat_id = chat_id_raw
if not self._is_group_allowed(chat_id):
return False
else:

View file

@ -296,3 +296,78 @@ def test_config_bridges_whatsapp_allow_from(monkeypatch, tmp_path):
assert config.platforms[Platform.WHATSAPP].extra["allow_from"] == ["6281234567890@s.whatsapp.net"]
assert __import__("os").environ["WHATSAPP_DM_POLICY"] == "allowlist"
assert __import__("os").environ["WHATSAPP_ALLOWED_USERS"] == "6281234567890@s.whatsapp.net"
# --- Broadcast / status / newsletter pseudo-chats are always dropped ---
def test_status_broadcast_chats_are_always_dropped():
"""Felipe's gateway.log showed the agent replying to status@broadcast
(a contact's WhatsApp Story update). These pseudo-chats aren't real
conversations and the adapter must drop them regardless of dm_policy.
"""
from gateway.platforms.whatsapp import WhatsAppAdapter
# Even on the most permissive config — open DMs, no allowlist — Stories
# and Channel posts must not reach the agent.
adapter = _make_adapter(dm_policy="open")
# Classic Story update — what Felipe was seeing in production.
status_msg = _dm_message(
body="[video received]",
chatId="status@broadcast",
senderId="34612345678@s.whatsapp.net",
)
assert adapter._should_process_message(status_msg) is False
# Channel / Newsletter broadcast posts.
newsletter_msg = _dm_message(
body="check out our latest post",
chatId="120363999999999999@newsletter",
senderId="120363999999999999@newsletter",
)
assert adapter._should_process_message(newsletter_msg) is False
def test_broadcast_filter_runs_before_allowlist():
"""A status@broadcast message from an allowlisted sender still drops —
we never want to reply to Stories, even from authorized contacts.
"""
adapter = _make_adapter(
dm_policy="allowlist",
allow_from=["34612345678@s.whatsapp.net"],
)
msg = _dm_message(
body="[image received]",
chatId="status@broadcast",
senderId="34612345678@s.whatsapp.net",
)
assert adapter._should_process_message(msg) is False
def test_real_dm_still_processed_after_broadcast_filter():
"""Sanity check: the broadcast filter doesn't accidentally drop real DMs."""
adapter = _make_adapter(dm_policy="open")
msg = _dm_message(
body="hello",
chatId="34612345678@s.whatsapp.net",
senderId="34612345678@s.whatsapp.net",
)
assert adapter._should_process_message(msg) is True
def test_is_broadcast_chat_helper_recognizes_common_jids():
from gateway.platforms.whatsapp import WhatsAppAdapter
assert WhatsAppAdapter._is_broadcast_chat("status@broadcast") is True
assert WhatsAppAdapter._is_broadcast_chat("STATUS@BROADCAST") is True
assert WhatsAppAdapter._is_broadcast_chat(" status@broadcast ") is True
assert WhatsAppAdapter._is_broadcast_chat("120363999999999999@newsletter") is True
assert WhatsAppAdapter._is_broadcast_chat("1234@broadcast") is True # broadcast list
# Real chats must not match.
assert WhatsAppAdapter._is_broadcast_chat("34612345678@s.whatsapp.net") is False
assert WhatsAppAdapter._is_broadcast_chat("120363001234567890@g.us") is False
assert WhatsAppAdapter._is_broadcast_chat("") is False
assert WhatsAppAdapter._is_broadcast_chat(None) is False # type: ignore[arg-type]