feat(channel): add message send retry mechanism with exponential backoff

- Add send_max_retries config option (default: 3, range: 0-10)
- Implement _send_with_retry in ChannelManager with 1s/2s/4s backoff
- Propagate CancelledError for graceful shutdown
- Fix telegram send_delta to raise exceptions for Manager retry
- Add comprehensive tests for retry logic
- Document channel settings in README

nanobot/channels/manager.py

@@ -7,10 +7,14 @@ from typing import Any
 
 from loguru import logger
 
+from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
 from nanobot.config.schema import Config
 
+# Retry delays for message sending (exponential backoff: 1s, 2s, 4s)
+_SEND_RETRY_DELAYS = (1, 2, 4)
+
 
 class ChannelManager:
     """
@@ -129,15 +133,7 @@ class ChannelManager:
 
                 channel = self.channels.get(msg.channel)
                 if channel:
-                    try:
-                        if msg.metadata.get("_stream_delta") or msg.metadata.get("_stream_end"):
-                            await channel.send_delta(msg.chat_id, msg.content, msg.metadata)
-                        elif msg.metadata.get("_streamed"):
-                            pass
-                        else:
-                            await channel.send(msg)
-                    except Exception as e:
-                        logger.error("Error sending to {}: {}", msg.channel, e)
+                    await self._send_with_retry(channel, msg)
                 else:
                     logger.warning("Unknown channel: {}", msg.channel)
 
@@ -146,6 +142,41 @@ class ChannelManager:
             except asyncio.CancelledError:
                 break
 
+    async def _send_with_retry(self, channel: BaseChannel, msg: OutboundMessage) -> None:
+        """Send a message with retry on failure using exponential backoff.
+
+        Note: CancelledError is re-raised to allow graceful shutdown.
+        """
+        max_attempts = max(self.config.channels.send_max_retries, 1)
+
+        for attempt in range(max_attempts):
+            try:
+                if msg.metadata.get("_stream_delta") or msg.metadata.get("_stream_end"):
+                    await channel.send_delta(msg.chat_id, msg.content, msg.metadata)
+                elif msg.metadata.get("_streamed"):
+                    pass
+                else:
+                    await channel.send(msg)
+                return  # Send succeeded
+            except asyncio.CancelledError:
+                raise  # Propagate cancellation for graceful shutdown
+            except Exception as e:
+                if attempt == max_attempts - 1:
+                    logger.error(
+                        "Failed to send to {} after {} attempts: {} - {}",
+                        msg.channel, max_attempts, type(e).__name__, e
+                    )
+                    return
+                delay = _SEND_RETRY_DELAYS[min(attempt, len(_SEND_RETRY_DELAYS) - 1)]
+                logger.warning(
+                    "Send to {} failed (attempt {}/{}): {}, retrying in {}s",
+                    msg.channel, attempt + 1, max_attempts, type(e).__name__, delay
+                )
+                try:
+                    await asyncio.sleep(delay)
+                except asyncio.CancelledError:
+                    raise  # Propagate cancellation during sleep
+
     def get_channel(self, name: str) -> BaseChannel | None:
         """Get a channel by name."""
         return self.channels.get(name)