feat(email): add attachment extraction support

Save inbound email attachments to the media directory with configurable
MIME type filtering (glob patterns like "image/*"), per-attachment size
limits, and max attachment count. Filenames are sanitized to prevent
path traversal. Controlled by allowed_attachment_types — empty (default)
means disabled, non-empty enables extraction for matching types.

nanobot/channels/email.py

@@ -1,6 +1,7 @@
 """Email channel implementation using IMAP polling + SMTP replies."""
 
 import asyncio
+from fnmatch import fnmatch
 import html
 import imaplib
 import re
@@ -14,13 +15,17 @@ from email.parser import BytesParser
 from email.utils import parseaddr
 from typing import Any
 
+from pathlib import Path
+
 from loguru import logger
 from pydantic import Field
 
 from nanobot.bus.events import OutboundMessage
 from nanobot.bus.queue import MessageBus
 from nanobot.channels.base import BaseChannel
+from nanobot.config.paths import get_media_dir
 from nanobot.config.schema import Base
+from nanobot.utils.helpers import safe_filename
 
 
 class EmailConfig(Base):
@@ -55,6 +60,11 @@ class EmailConfig(Base):
     verify_dkim: bool = True   # Require Authentication-Results with dkim=pass
     verify_spf: bool = True    # Require Authentication-Results with spf=pass
 
+    # Attachment handling — set allowed types to enable (e.g. ["application/pdf", "image/*"], or ["*"] for all)
+    allowed_attachment_types: list[str] = Field(default_factory=list)
+    max_attachment_size: int = 2_000_000  # 2MB per attachment
+    max_attachments_per_email: int = 5
+
 
 class EmailChannel(BaseChannel):
     """
@@ -153,6 +163,7 @@ class EmailChannel(BaseChannel):
                         sender_id=sender,
                         chat_id=sender,
                         content=item["content"],
+                        media=item.get("media") or None,
                         metadata=item.get("metadata", {}),
                     )
             except Exception as e:
@@ -404,6 +415,20 @@ class EmailChannel(BaseChannel):
                     f"{body}"
                 )
 
+                # --- Attachment extraction ---
+                attachment_paths: list[str] = []
+                if self.config.allowed_attachment_types:
+                    saved = self._extract_attachments(
+                        parsed,
+                        uid or "noid",
+                        allowed_types=self.config.allowed_attachment_types,
+                        max_size=self.config.max_attachment_size,
+                        max_count=self.config.max_attachments_per_email,
+                    )
+                    for p in saved:
+                        attachment_paths.append(str(p))
+                        content += f"\n[attachment: {p.name} — saved to {p}]"
+
                 metadata = {
                     "message_id": message_id,
                     "subject": subject,
@@ -418,6 +443,7 @@ class EmailChannel(BaseChannel):
                         "message_id": message_id,
                         "content": content,
                         "metadata": metadata,
+                        "media": attachment_paths,
                     }
                 )
 
@@ -537,6 +563,61 @@ class EmailChannel(BaseChannel):
                 dkim_pass = True
         return spf_pass, dkim_pass
 
+    @classmethod
+    def _extract_attachments(
+        cls,
+        msg: Any,
+        uid: str,
+        *,
+        allowed_types: list[str],
+        max_size: int,
+        max_count: int,
+    ) -> list[Path]:
+        """Extract and save email attachments to the media directory.
+
+        Returns list of saved file paths.
+        """
+        if not msg.is_multipart():
+            return []
+
+        saved: list[Path] = []
+        media_dir = get_media_dir("email")
+
+        for part in msg.walk():
+            if len(saved) >= max_count:
+                break
+            if part.get_content_disposition() != "attachment":
+                continue
+
+            content_type = part.get_content_type()
+            if not any(fnmatch(content_type, pat) for pat in allowed_types):
+                logger.debug("Email attachment skipped (type {}): not in allowed list", content_type)
+                continue
+
+            payload = part.get_payload(decode=True)
+            if payload is None:
+                continue
+            if len(payload) > max_size:
+                logger.warning(
+                    "Email attachment skipped: size {} exceeds limit {}",
+                    len(payload),
+                    max_size,
+                )
+                continue
+
+            raw_name = part.get_filename() or "attachment"
+            sanitized = safe_filename(raw_name) or "attachment"
+            dest = media_dir / f"{uid}_{sanitized}"
+
+            try:
+                dest.write_bytes(payload)
+                saved.append(dest)
+                logger.info("Email attachment saved: {}", dest)
+            except Exception as exc:
+                logger.warning("Failed to save email attachment {}: {}", dest, exc)
+
+        return saved
+
     @staticmethod
     def _html_to_text(raw_html: str) -> str:
         text = re.sub(r"<\s*br\s*/?>", "\n", raw_html, flags=re.IGNORECASE)