fix: media_paths NameError, import order, add error logging and tests

- Move media_paths assignment before voice message handling to prevent
  NameError at runtime
- Fix broken import layout in transcription.py (httpx/loguru after class)
- Add error logging to OpenAITranscriptionProvider matching Groq style
- Add regression tests for voice transcription and no-media fallback

Made-with: Cursor

nanobot/channels/whatsapp.py

@@ -236,6 +236,9 @@ class WhatsAppChannel(BaseChannel):
             sender_id = user_id.split("@")[0] if "@" in user_id else user_id
             logger.info("Sender {}", sender)
 
+            # Extract media paths (images/documents/videos downloaded by the bridge)
+            media_paths = data.get("media") or []
+
             # Handle voice transcription if it's a voice message
             if content == "[Voice Message]":
                 if media_paths:
@@ -249,9 +252,6 @@ class WhatsAppChannel(BaseChannel):
                 else:
                     content = "[Voice Message: Audio not available]"
 
-            # Extract media paths (images/documents/videos downloaded by the bridge)
-            media_paths = data.get("media") or []
-
             # Build content tags matching Telegram's pattern: [image: /path] or [file: /path]
             if media_paths:
                 for p in media_paths:

nanobot/providers/transcription.py

@@ -3,6 +3,9 @@
 import os
 from pathlib import Path
 
+import httpx
+from loguru import logger
+
 
 class OpenAITranscriptionProvider:
     """Voice transcription provider using OpenAI's Whisper API."""
@@ -13,12 +16,13 @@ class OpenAITranscriptionProvider:
 
     async def transcribe(self, file_path: str | Path) -> str:
         if not self.api_key:
+            logger.warning("OpenAI API key not configured for transcription")
             return ""
         path = Path(file_path)
         if not path.exists():
+            logger.error("Audio file not found: {}", file_path)
             return ""
         try:
-            import httpx
             async with httpx.AsyncClient() as client:
                 with open(path, "rb") as f:
                     files = {"file": (path.name, f), "model": (None, "whisper-1")}
@@ -28,12 +32,10 @@ class OpenAITranscriptionProvider:
                     )
                     response.raise_for_status()
                     return response.json().get("text", "")
-        except Exception:
+        except Exception as e:
+            logger.error("OpenAI transcription error: {}", e)
             return ""
 
-import httpx
-from loguru import logger
-
 
 class GroqTranscriptionProvider:
     """

tests/channels/test_whatsapp_channel.py

@@ -163,6 +163,54 @@ async def test_group_policy_mention_accepts_mentioned_group_message():
     assert kwargs["sender_id"] == "user"
 
 
+@pytest.mark.asyncio
+async def test_voice_message_transcription_uses_media_path():
+    """Voice messages are transcribed when media path is available."""
+    ch = WhatsAppChannel(
+        {"enabled": True, "transcriptionProvider": "openai", "transcriptionApiKey": "sk-test"},
+        MagicMock(),
+    )
+    ch._handle_message = AsyncMock()
+    ch.transcribe_audio = AsyncMock(return_value="Hello world")
+
+    await ch._handle_bridge_message(
+        json.dumps({
+            "type": "message",
+            "id": "v1",
+            "sender": "12345@s.whatsapp.net",
+            "pn": "",
+            "content": "[Voice Message]",
+            "timestamp": 1,
+            "media": ["/tmp/voice.ogg"],
+        })
+    )
+
+    ch.transcribe_audio.assert_awaited_once_with("/tmp/voice.ogg")
+    kwargs = ch._handle_message.await_args.kwargs
+    assert kwargs["content"].startswith("Hello world")
+
+
+@pytest.mark.asyncio
+async def test_voice_message_no_media_shows_not_available():
+    """Voice messages without media produce a fallback placeholder."""
+    ch = WhatsAppChannel({"enabled": True}, MagicMock())
+    ch._handle_message = AsyncMock()
+
+    await ch._handle_bridge_message(
+        json.dumps({
+            "type": "message",
+            "id": "v2",
+            "sender": "12345@s.whatsapp.net",
+            "pn": "",
+            "content": "[Voice Message]",
+            "timestamp": 1,
+        })
+    )
+
+    kwargs = ch._handle_message.await_args.kwargs
+    assert kwargs["content"] == "[Voice Message: Audio not available]"
+
+
 def test_load_or_create_bridge_token_persists_generated_secret(tmp_path):
     token_path = tmp_path / "whatsapp-auth" / "bridge-token"