Merge PR #1567: refactor(channels): extract split_message utility to reduce duplication

nanobot/channels/discord.py

@@ -13,34 +13,13 @@ from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.schema import DiscordConfig
+from nanobot.utils.helpers import split_message
 
 DISCORD_API_BASE = "https://discord.com/api/v10"
 MAX_ATTACHMENT_BYTES = 20 * 1024 * 1024  # 20MB
 MAX_MESSAGE_LEN = 2000  # Discord message character limit
 
 
-def _split_message(content: str, max_len: int = MAX_MESSAGE_LEN) -> list[str]:
-    """Split content into chunks within max_len, preferring line breaks."""
-    if not content:
-        return []
-    if len(content) <= max_len:
-        return [content]
-    chunks: list[str] = []
-    while content:
-        if len(content) <= max_len:
-            chunks.append(content)
-            break
-        cut = content[:max_len]
-        pos = cut.rfind('\n')
-        if pos <= 0:
-            pos = cut.rfind(' ')
-        if pos <= 0:
-            pos = max_len
-        chunks.append(content[:pos])
-        content = content[pos:].lstrip()
-    return chunks
-
-
 class DiscordChannel(BaseChannel):
     """Discord channel using Gateway websocket."""
 
@@ -105,7 +84,7 @@ class DiscordChannel(BaseChannel):
         headers = {"Authorization": f"Bot {self.config.token}"}
 
         try:
-            chunks = _split_message(msg.content or "")
+            chunks = split_message(msg.content or "", MAX_MESSAGE_LEN)
             if not chunks:
                 return
 

nanobot/channels/telegram.py

@@ -14,6 +14,9 @@ from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.schema import TelegramConfig
+from nanobot.utils.helpers import split_message
+
+TELEGRAM_MAX_MESSAGE_LEN = 4000  # Telegram message character limit
 
 
 def _markdown_to_telegram_html(text: str) -> str:
@@ -79,26 +82,6 @@ def _markdown_to_telegram_html(text: str) -> str:
     return text
 
 
-def _split_message(content: str, max_len: int = 4000) -> list[str]:
-    """Split content into chunks within max_len, preferring line breaks."""
-    if len(content) <= max_len:
-        return [content]
-    chunks: list[str] = []
-    while content:
-        if len(content) <= max_len:
-            chunks.append(content)
-            break
-        cut = content[:max_len]
-        pos = cut.rfind('\n')
-        if pos == -1:
-            pos = cut.rfind(' ')
-        if pos == -1:
-            pos = max_len
-        chunks.append(content[:pos])
-        content = content[pos:].lstrip()
-    return chunks
-
-
 class TelegramChannel(BaseChannel):
     """
     Telegram channel using long polling.
@@ -273,8 +256,8 @@ class TelegramChannel(BaseChannel):
         if msg.content and msg.content != "[empty message]":
             is_progress = msg.metadata.get("_progress", False)
             draft_id = msg.metadata.get("message_id")
-            
+
-            for chunk in _split_message(msg.content):
+            for chunk in split_message(msg.content, TELEGRAM_MAX_MESSAGE_LEN):
                 try:
                     html = _markdown_to_telegram_html(chunk)
                     if is_progress and draft_id:

nanobot/utils/helpers.py

@@ -47,6 +47,38 @@ def safe_filename(name: str) -> str:
     return _UNSAFE_CHARS.sub("_", name).strip()
 
 
+def split_message(content: str, max_len: int = 2000) -> list[str]:
+    """
+    Split content into chunks within max_len, preferring line breaks.
+
+    Args:
+        content: The text content to split.
+        max_len: Maximum length per chunk (default 2000 for Discord compatibility).
+
+    Returns:
+        List of message chunks, each within max_len.
+    """
+    if not content:
+        return []
+    if len(content) <= max_len:
+        return [content]
+    chunks: list[str] = []
+    while content:
+        if len(content) <= max_len:
+            chunks.append(content)
+            break
+        cut = content[:max_len]
+        # Try to break at newline first, then space, then hard break
+        pos = cut.rfind('\n')
+        if pos <= 0:
+            pos = cut.rfind(' ')
+        if pos <= 0:
+            pos = max_len
+        chunks.append(content[:pos])
+        content = content[pos:].lstrip()
+    return chunks
+
+
 def sync_workspace_templates(workspace: Path, silent: bool = False) -> list[str]:
     """Sync bundled templates to workspace. Only creates missing files."""
     from importlib.resources import files as pkg_files