Merge remote-tracking branch 'origin/main'

nanobot/channels/feishu.py

@@ -362,8 +362,8 @@ class FeishuChannel(BaseChannel):
             mid = getattr(mention, "id", None)
             if not mid:
                 continue
-            # Bot mentions have an empty user_id with a valid open_id
+            # Bot mentions have no user_id (None or "") but a valid open_id
-            if getattr(mid, "user_id", None) == "" and (getattr(mid, "open_id", None) or "").startswith("ou_"):
+            if not getattr(mid, "user_id", None) and (getattr(mid, "open_id", None) or "").startswith("ou_"):
                 return True
         return False
 

nanobot/channels/telegram.py

@@ -20,6 +20,7 @@ from nanobot.config.schema import TelegramConfig
 from nanobot.utils.helpers import split_message
 
 TELEGRAM_MAX_MESSAGE_LEN = 4000  # Telegram message character limit
+TELEGRAM_REPLY_CONTEXT_MAX_LEN = TELEGRAM_MAX_MESSAGE_LEN  # Max length for reply context in user message
 
 
 def _strip_md(s: str) -> str:
@@ -453,6 +454,7 @@ class TelegramChannel(BaseChannel):
     @staticmethod
     def _build_message_metadata(message, user) -> dict:
         """Build common Telegram inbound metadata payload."""
+        reply_to = getattr(message, "reply_to_message", None)
         return {
             "message_id": message.message_id,
             "user_id": user.id,
@@ -461,8 +463,73 @@ class TelegramChannel(BaseChannel):
             "is_group": message.chat.type != "private",
             "message_thread_id": getattr(message, "message_thread_id", None),
             "is_forum": bool(getattr(message.chat, "is_forum", False)),
+            "reply_to_message_id": getattr(reply_to, "message_id", None) if reply_to else None,
         }
 
+    @staticmethod
+    def _extract_reply_context(message) -> str | None:
+        """Extract text from the message being replied to, if any."""
+        reply = getattr(message, "reply_to_message", None)
+        if not reply:
+            return None
+        text = getattr(reply, "text", None) or getattr(reply, "caption", None) or ""
+        if len(text) > TELEGRAM_REPLY_CONTEXT_MAX_LEN:
+            text = text[:TELEGRAM_REPLY_CONTEXT_MAX_LEN] + "..."
+        return f"[Reply to: {text}]" if text else None
+
+    async def _download_message_media(
+        self, msg, *, add_failure_content: bool = False
+    ) -> tuple[list[str], list[str]]:
+        """Download media from a message (current or reply). Returns (media_paths, content_parts)."""
+        media_file = None
+        media_type = None
+        if getattr(msg, "photo", None):
+            media_file = msg.photo[-1]
+            media_type = "image"
+        elif getattr(msg, "voice", None):
+            media_file = msg.voice
+            media_type = "voice"
+        elif getattr(msg, "audio", None):
+            media_file = msg.audio
+            media_type = "audio"
+        elif getattr(msg, "document", None):
+            media_file = msg.document
+            media_type = "file"
+        elif getattr(msg, "video", None):
+            media_file = msg.video
+            media_type = "video"
+        elif getattr(msg, "video_note", None):
+            media_file = msg.video_note
+            media_type = "video"
+        elif getattr(msg, "animation", None):
+            media_file = msg.animation
+            media_type = "animation"
+        if not media_file or not self._app:
+            return [], []
+        try:
+            file = await self._app.bot.get_file(media_file.file_id)
+            ext = self._get_extension(
+                media_type,
+                getattr(media_file, "mime_type", None),
+                getattr(media_file, "file_name", None),
+            )
+            media_dir = get_media_dir("telegram")
+            file_path = media_dir / f"{media_file.file_id[:16]}{ext}"
+            await file.download_to_drive(str(file_path))
+            path_str = str(file_path)
+            if media_type in ("voice", "audio"):
+                transcription = await self.transcribe_audio(file_path)
+                if transcription:
+                    logger.info("Transcribed {}: {}...", media_type, transcription[:50])
+                    return [path_str], [f"[transcription: {transcription}]"]
+                return [path_str], [f"[{media_type}: {path_str}]"]
+            return [path_str], [f"[{media_type}: {path_str}]"]
+        except Exception as e:
+            logger.warning("Failed to download message media: {}", e)
+            if add_failure_content:
+                return [], [f"[{media_type}: download failed]"]
+            return [], []
+
     async def _ensure_bot_identity(self) -> tuple[int | None, str | None]:
         """Load bot identity once and reuse it for mention/reply checks."""
         if self._bot_user_id is not None or self._bot_username is not None:
@@ -547,7 +614,7 @@ class TelegramChannel(BaseChannel):
         await self._handle_message(
             sender_id=self._sender_id(user),
             chat_id=str(message.chat_id),
-            content=message.text,
+            content=message.text or "",
             metadata=self._build_message_metadata(message, user),
             session_key=self._derive_topic_session_key(message),
         )
@@ -579,54 +646,26 @@ class TelegramChannel(BaseChannel):
         if message.caption:
             content_parts.append(message.caption)
 
-        # Handle media files
+        # Download current message media
-        media_file = None
+        current_media_paths, current_media_parts = await self._download_message_media(
-        media_type = None
+            message, add_failure_content=True
-
-        if message.photo:
-            media_file = message.photo[-1]  # Largest photo
-            media_type = "image"
-        elif message.voice:
-            media_file = message.voice
-            media_type = "voice"
-        elif message.audio:
-            media_file = message.audio
-            media_type = "audio"
-        elif message.document:
-            media_file = message.document
-            media_type = "file"
-
-        # Download media if present
-        if media_file and self._app:
-            try:
-                file = await self._app.bot.get_file(media_file.file_id)
-                ext = self._get_extension(
-                    media_type,
-                    getattr(media_file, 'mime_type', None),
-                    getattr(media_file, 'file_name', None),
         )
-                media_dir = get_media_dir("telegram")
+        media_paths.extend(current_media_paths)
-
+        content_parts.extend(current_media_parts)
-                file_path = media_dir / f"{media_file.file_id[:16]}{ext}"
+        if current_media_paths:
-                await file.download_to_drive(str(file_path))
+            logger.debug("Downloaded message media to {}", current_media_paths[0])
-
-                media_paths.append(str(file_path))
-
-                if media_type in ("voice", "audio"):
-                    transcription = await self.transcribe_audio(file_path)
-                    if transcription:
-                        logger.info("Transcribed {}: {}...", media_type, transcription[:50])
-                        content_parts.append(f"[transcription: {transcription}]")
-                    else:
-                        content_parts.append(f"[{media_type}: {file_path}]")
-                else:
-                    content_parts.append(f"[{media_type}: {file_path}]")
-
-                logger.debug("Downloaded {} to {}", media_type, file_path)
-            except Exception as e:
-                logger.error("Failed to download media: {}", e)
-                content_parts.append(f"[{media_type}: download failed]")
 
+        # Reply context: text and/or media from the replied-to message
+        reply = getattr(message, "reply_to_message", None)
+        if reply is not None:
+            reply_ctx = self._extract_reply_context(message)
+            reply_media, reply_media_parts = await self._download_message_media(reply)
+            if reply_media:
+                media_paths = reply_media + media_paths
+                logger.debug("Attached replied-to media: {}", reply_media[0])
+            tag = reply_ctx or (f"[Reply to: {reply_media_parts[0]}]" if reply_media_parts else None)
+            if tag:
+                content_parts.insert(0, tag)
         content = "\n".join(content_parts) if content_parts else "[empty message]"
 
         logger.debug("Telegram message from {}: {}...", sender_id, content[:50])

tests/test_telegram_channel.py

@@ -1,10 +1,13 @@
+import asyncio
+from pathlib import Path
 from types import SimpleNamespace
+from unittest.mock import AsyncMock
 
 import pytest
 
 from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
-from nanobot.channels.telegram import TelegramChannel
+from nanobot.channels.telegram import TELEGRAM_REPLY_CONTEXT_MAX_LEN, TelegramChannel
 from nanobot.config.schema import TelegramConfig
 
 
@@ -42,6 +45,12 @@ class _FakeBot:
     async def send_chat_action(self, **kwargs) -> None:
         pass
 
+    async def get_file(self, file_id: str):
+        """Return a fake file that 'downloads' to a path (for reply-to-media tests)."""
+        async def _fake_download(path) -> None:
+            pass
+        return SimpleNamespace(download_to_drive=_fake_download)
+
 
 class _FakeApp:
     def __init__(self, on_start_polling) -> None:
@@ -336,3 +345,255 @@ async def test_group_policy_open_accepts_plain_group_message() -> None:
 
     assert len(handled) == 1
     assert channel._app.bot.get_me_calls == 0
+
+
+def test_extract_reply_context_no_reply() -> None:
+    """When there is no reply_to_message, _extract_reply_context returns None."""
+    message = SimpleNamespace(reply_to_message=None)
+    assert TelegramChannel._extract_reply_context(message) is None
+
+
+def test_extract_reply_context_with_text() -> None:
+    """When reply has text, return prefixed string."""
+    reply = SimpleNamespace(text="Hello world", caption=None)
+    message = SimpleNamespace(reply_to_message=reply)
+    assert TelegramChannel._extract_reply_context(message) == "[Reply to: Hello world]"
+
+
+def test_extract_reply_context_with_caption_only() -> None:
+    """When reply has only caption (no text), caption is used."""
+    reply = SimpleNamespace(text=None, caption="Photo caption")
+    message = SimpleNamespace(reply_to_message=reply)
+    assert TelegramChannel._extract_reply_context(message) == "[Reply to: Photo caption]"
+
+
+def test_extract_reply_context_truncation() -> None:
+    """Reply text is truncated at TELEGRAM_REPLY_CONTEXT_MAX_LEN."""
+    long_text = "x" * (TELEGRAM_REPLY_CONTEXT_MAX_LEN + 100)
+    reply = SimpleNamespace(text=long_text, caption=None)
+    message = SimpleNamespace(reply_to_message=reply)
+    result = TelegramChannel._extract_reply_context(message)
+    assert result is not None
+    assert result.startswith("[Reply to: ")
+    assert result.endswith("...]")
+    assert len(result) == len("[Reply to: ]") + TELEGRAM_REPLY_CONTEXT_MAX_LEN + len("...")
+
+
+def test_extract_reply_context_no_text_returns_none() -> None:
+    """When reply has no text/caption, _extract_reply_context returns None (media handled separately)."""
+    reply = SimpleNamespace(text=None, caption=None)
+    message = SimpleNamespace(reply_to_message=reply)
+    assert TelegramChannel._extract_reply_context(message) is None
+
+
+@pytest.mark.asyncio
+async def test_on_message_includes_reply_context() -> None:
+    """When user replies to a message, content passed to bus starts with reply context."""
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    reply = SimpleNamespace(text="Hello", message_id=2, from_user=SimpleNamespace(id=1))
+    update = _make_telegram_update(text="translate this", reply_to_message=reply)
+    await channel._on_message(update, None)
+
+    assert len(handled) == 1
+    assert handled[0]["content"].startswith("[Reply to: Hello]")
+    assert "translate this" in handled[0]["content"]
+
+
+@pytest.mark.asyncio
+async def test_download_message_media_returns_path_when_download_succeeds(
+    monkeypatch, tmp_path
+) -> None:
+    """_download_message_media returns (paths, content_parts) when bot.get_file and download succeed."""
+    media_dir = tmp_path / "media" / "telegram"
+    media_dir.mkdir(parents=True)
+    monkeypatch.setattr(
+        "nanobot.channels.telegram.get_media_dir",
+        lambda channel=None: media_dir if channel else tmp_path / "media",
+    )
+
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"]),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    channel._app.bot.get_file = AsyncMock(
+        return_value=SimpleNamespace(download_to_drive=AsyncMock(return_value=None))
+    )
+
+    msg = SimpleNamespace(
+        photo=[SimpleNamespace(file_id="fid123", mime_type="image/jpeg")],
+        voice=None,
+        audio=None,
+        document=None,
+        video=None,
+        video_note=None,
+        animation=None,
+    )
+    paths, parts = await channel._download_message_media(msg)
+    assert len(paths) == 1
+    assert len(parts) == 1
+    assert "fid123" in paths[0]
+    assert "[image:" in parts[0]
+
+
+@pytest.mark.asyncio
+async def test_on_message_attaches_reply_to_media_when_available(monkeypatch, tmp_path) -> None:
+    """When user replies to a message with media, that media is downloaded and attached to the turn."""
+    media_dir = tmp_path / "media" / "telegram"
+    media_dir.mkdir(parents=True)
+    monkeypatch.setattr(
+        "nanobot.channels.telegram.get_media_dir",
+        lambda channel=None: media_dir if channel else tmp_path / "media",
+    )
+
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    app = _FakeApp(lambda: None)
+    app.bot.get_file = AsyncMock(
+        return_value=SimpleNamespace(download_to_drive=AsyncMock(return_value=None))
+    )
+    channel._app = app
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    reply_with_photo = SimpleNamespace(
+        text=None,
+        caption=None,
+        photo=[SimpleNamespace(file_id="reply_photo_fid", mime_type="image/jpeg")],
+        document=None,
+        voice=None,
+        audio=None,
+        video=None,
+        video_note=None,
+        animation=None,
+    )
+    update = _make_telegram_update(
+        text="what is the image?",
+        reply_to_message=reply_with_photo,
+    )
+    await channel._on_message(update, None)
+
+    assert len(handled) == 1
+    assert handled[0]["content"].startswith("[Reply to: [image:")
+    assert "what is the image?" in handled[0]["content"]
+    assert len(handled[0]["media"]) == 1
+    assert "reply_photo_fid" in handled[0]["media"][0]
+
+
+@pytest.mark.asyncio
+async def test_on_message_reply_to_media_fallback_when_download_fails() -> None:
+    """When reply has media but download fails, no media attached and no reply tag."""
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    channel._app.bot.get_file = None
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    reply_with_photo = SimpleNamespace(
+        text=None,
+        caption=None,
+        photo=[SimpleNamespace(file_id="x", mime_type="image/jpeg")],
+        document=None,
+        voice=None,
+        audio=None,
+        video=None,
+        video_note=None,
+        animation=None,
+    )
+    update = _make_telegram_update(text="what is this?", reply_to_message=reply_with_photo)
+    await channel._on_message(update, None)
+
+    assert len(handled) == 1
+    assert "what is this?" in handled[0]["content"]
+    assert handled[0]["media"] == []
+
+
+@pytest.mark.asyncio
+async def test_on_message_reply_to_caption_and_media(monkeypatch, tmp_path) -> None:
+    """When replying to a message with caption + photo, both text context and media are included."""
+    media_dir = tmp_path / "media" / "telegram"
+    media_dir.mkdir(parents=True)
+    monkeypatch.setattr(
+        "nanobot.channels.telegram.get_media_dir",
+        lambda channel=None: media_dir if channel else tmp_path / "media",
+    )
+
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    app = _FakeApp(lambda: None)
+    app.bot.get_file = AsyncMock(
+        return_value=SimpleNamespace(download_to_drive=AsyncMock(return_value=None))
+    )
+    channel._app = app
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+    channel._start_typing = lambda _chat_id: None
+
+    reply_with_caption_and_photo = SimpleNamespace(
+        text=None,
+        caption="A cute cat",
+        photo=[SimpleNamespace(file_id="cat_fid", mime_type="image/jpeg")],
+        document=None,
+        voice=None,
+        audio=None,
+        video=None,
+        video_note=None,
+        animation=None,
+    )
+    update = _make_telegram_update(
+        text="what breed is this?",
+        reply_to_message=reply_with_caption_and_photo,
+    )
+    await channel._on_message(update, None)
+
+    assert len(handled) == 1
+    assert "[Reply to: A cute cat]" in handled[0]["content"]
+    assert "what breed is this?" in handled[0]["content"]
+    assert len(handled[0]["media"]) == 1
+    assert "cat_fid" in handled[0]["media"][0]
+
+
+@pytest.mark.asyncio
+async def test_forward_command_does_not_inject_reply_context() -> None:
+    """Slash commands forwarded via _forward_command must not include reply context."""
+    channel = TelegramChannel(
+        TelegramConfig(enabled=True, token="123:abc", allow_from=["*"], group_policy="open"),
+        MessageBus(),
+    )
+    channel._app = _FakeApp(lambda: None)
+    handled = []
+    async def capture_handle(**kwargs) -> None:
+        handled.append(kwargs)
+    channel._handle_message = capture_handle
+
+    reply = SimpleNamespace(text="some old message", message_id=2, from_user=SimpleNamespace(id=1))
+    update = _make_telegram_update(text="/new", reply_to_message=reply)
+    await channel._forward_command(update, None)
+
+    assert len(handled) == 1
+    assert handled[0]["content"] == "/new"