Merge d999f35eb5 into fd10463069

gateway/platforms/signal.py

@@ -530,6 +530,8 @@ class SignalAdapter(BasePlatformAdapter):
                 msg_type = MessageType.VOICE
             elif any(mt.startswith("image/") for mt in media_types):
                 msg_type = MessageType.PHOTO
+            elif any(mt.startswith("application/") or mt.startswith("text/") for mt in media_types):
+                msg_type = MessageType.DOCUMENT
 
         # Parse timestamp from envelope data (milliseconds since epoch)
         ts_ms = envelope_data.get("timestamp", 0)

tests/gateway/test_signal.py

@@ -760,6 +760,122 @@ class TestSignalMediaExtraction:
         assert type(adapter).send_image is not BasePlatformAdapter.send_image
 
 
+# ---------------------------------------------------------------------------
+# Inbound attachment message type classification
+# ---------------------------------------------------------------------------
+
+def _make_dm_envelope(sender: str, attachments: list, text: str = "") -> dict:
+    """Build a minimal signal-cli DM envelope with the given attachments."""
+    return {
+        "envelope": {
+            "sourceNumber": sender,
+            "sourceName": "Test User",
+            "sourceUuid": "aaaaaaaa-0000-0000-0000-000000000001",
+            "timestamp": 1700000000000,
+            "dataMessage": {
+                "timestamp": 1700000000000,
+                "message": text,
+                "expiresInSeconds": 0,
+                "viewOnce": False,
+                "attachments": attachments,
+            },
+        }
+    }
+
+
+class TestSignalInboundMessageTypeClassification:
+    """_handle_envelope must set MessageType.DOCUMENT for application/* and text/* attachments.
+
+    Before the fix, PDFs and other documents left msg_type as MessageType.TEXT,
+    so run.py's document-context injection (which gates on MessageType.DOCUMENT)
+    silently dropped the file and the agent never saw it.
+    """
+
+    async def _dispatch_single_attachment(self, monkeypatch, content_type: str,
+                                          att_id: str, fetch_path: str, fetch_ext: str):
+        """Helper: run _handle_envelope with one attachment and return the dispatched event."""
+        envelope = _make_dm_envelope(
+            sender="+15559876543",
+            attachments=[{
+                "contentType": content_type,
+                "id": att_id,
+                "size": 1024,
+                "filename": None,
+                "width": None,
+                "height": None,
+                "caption": None,
+                "uploadTimestamp": 1700000000000,
+            }],
+        )
+        adapter = _make_signal_adapter(monkeypatch)
+        adapter._rpc, _ = _stub_rpc(None)
+        dispatched = []
+
+        async def _fake_handle_message(event):
+            dispatched.append(event)
+
+        adapter.handle_message = _fake_handle_message
+        adapter._fetch_attachment = AsyncMock(return_value=(fetch_path, fetch_ext))
+        await adapter._handle_envelope(envelope)
+        assert dispatched, "_handle_envelope did not dispatch any event"
+        return dispatched[0]
+
+    @pytest.mark.asyncio
+    async def test_pdf_attachment_sets_document_type(self, monkeypatch):
+        """A PDF attachment (application/pdf) must produce MessageType.DOCUMENT, not TEXT."""
+        from gateway.platforms.base import MessageType
+
+        event = await self._dispatch_single_attachment(
+            monkeypatch,
+            content_type="application/pdf",
+            att_id="6zLO3b-6Yf3zVWeLDctA.pdf",
+            fetch_path="/tmp/report.pdf",
+            fetch_ext=".pdf",
+        )
+
+        assert event.message_type == MessageType.DOCUMENT, (
+            f"Expected DOCUMENT, got {event.message_type}. "
+            "PDFs must be classified as DOCUMENT so run.py injects file context."
+        )
+        assert "/tmp/report.pdf" in event.media_urls
+
+    @pytest.mark.asyncio
+    async def test_text_plain_attachment_sets_document_type(self, monkeypatch):
+        """A text/plain attachment must produce MessageType.DOCUMENT, not TEXT."""
+        from gateway.platforms.base import MessageType
+
+        event = await self._dispatch_single_attachment(
+            monkeypatch,
+            content_type="text/plain",
+            att_id="notes.txt",
+            fetch_path="/tmp/notes.txt",
+            fetch_ext=".txt",
+        )
+
+        assert event.message_type == MessageType.DOCUMENT, (
+            f"Expected DOCUMENT, got {event.message_type}. "
+            "text/plain must be classified as DOCUMENT so run.py injects file context."
+        )
+
+    @pytest.mark.asyncio
+    async def test_text_html_attachment_sets_document_type(self, monkeypatch):
+        """A text/html attachment must produce MessageType.DOCUMENT (covers the text/* wildcard)."""
+        from gateway.platforms.base import MessageType
+
+        event = await self._dispatch_single_attachment(
+            monkeypatch,
+            content_type="text/html",
+            att_id="page.html",
+            fetch_path="/tmp/page.html",
+            fetch_ext=".html",
+        )
+
+        assert event.message_type == MessageType.DOCUMENT, (
+            f"Expected DOCUMENT, got {event.message_type}. "
+            "text/html must be classified as DOCUMENT so run.py injects file context."
+        )
+
+
 # ---------------------------------------------------------------------------
 # send_document now routes through _send_attachment (#5105 bonus)
 # ---------------------------------------------------------------------------