feat(discord): add document caching and text-file injection (#2503)

- Download and cache .pdf, .docx, .xlsx, .pptx attachments locally
  instead of passing expiring CDN URLs to the agent
- Inject .txt and .md content (≤100 KB) into event.text so the agent
  sees file content without needing to fetch the URL
- Add 20 MB size guard and SUPPORTED_DOCUMENT_TYPES allowlist
- Fix: unsupported types (.zip etc.) no longer get MessageType.DOCUMENT
- Add 9 unit tests in test_discord_document_handling.py

Mirrors the Slack implementation from PR #784. Discord CDN URLs are
publicly accessible so no auth header is needed (unlike Slack).

Co-authored-by: Dilee <uzmpsk.dilekakbas@gmail.com>

gateway/platforms/discord.py

@@ -43,6 +43,8 @@ from pathlib import Path as _Path
 sys.path.insert(0, str(_Path(__file__).resolve().parents[2]))
 
 from gateway.config import Platform, PlatformConfig
+import re
+
 from gateway.platforms.base import (
     BasePlatformAdapter,
     MessageEvent,
@@ -50,6 +52,8 @@ from gateway.platforms.base import (
     SendResult,
     cache_image_from_url,
     cache_audio_from_url,
+    cache_document_from_bytes,
+    SUPPORTED_DOCUMENT_TYPES,
 )
 
 
@@ -1950,7 +1954,12 @@ class DiscordAdapter(BasePlatformAdapter):
                     elif att.content_type.startswith("audio/"):
                         msg_type = MessageType.AUDIO
                     else:
-                        msg_type = MessageType.DOCUMENT
+                        doc_ext = ""
+                        if att.filename:
+                            _, doc_ext = os.path.splitext(att.filename)
+                            doc_ext = doc_ext.lower()
+                        if doc_ext in SUPPORTED_DOCUMENT_TYPES:
+                            msg_type = MessageType.DOCUMENT
                     break
         
         # When auto-threading kicked in, route responses to the new thread
@@ -1987,6 +1996,7 @@ class DiscordAdapter(BasePlatformAdapter):
         # vision tool can access them reliably (Discord CDN URLs can expire).
         media_urls = []
         media_types = []
+        pending_text_injection: Optional[str] = None
         for att in message.attachments:
             content_type = att.content_type or "unknown"
             if content_type.startswith("image/"):
@@ -2018,12 +2028,70 @@ class DiscordAdapter(BasePlatformAdapter):
                     media_urls.append(att.url)
                     media_types.append(content_type)
             else:
-                # Other attachments: keep the original URL
-                media_urls.append(att.url)
-                media_types.append(content_type)
+                # Document attachments: download, cache, and optionally inject text
+                ext = ""
+                if att.filename:
+                    _, ext = os.path.splitext(att.filename)
+                    ext = ext.lower()
+                if not ext and content_type:
+                    mime_to_ext = {v: k for k, v in SUPPORTED_DOCUMENT_TYPES.items()}
+                    ext = mime_to_ext.get(content_type, "")
+                if ext not in SUPPORTED_DOCUMENT_TYPES:
+                    logger.warning(
+                        "[Discord] Unsupported document type '%s' (%s), skipping",
+                        ext or "unknown", content_type,
+                    )
+                else:
+                    MAX_DOC_BYTES = 20 * 1024 * 1024
+                    if att.size and att.size > MAX_DOC_BYTES:
+                        logger.warning(
+                            "[Discord] Document too large (%s bytes), skipping: %s",
+                            att.size, att.filename,
+                        )
+                    else:
+                        try:
+                            import aiohttp
+                            async with aiohttp.ClientSession() as session:
+                                async with session.get(
+                                    att.url,
+                                    timeout=aiohttp.ClientTimeout(total=30),
+                                ) as resp:
+                                    if resp.status != 200:
+                                        raise Exception(f"HTTP {resp.status}")
+                                    raw_bytes = await resp.read()
+                            cached_path = cache_document_from_bytes(
+                                raw_bytes, att.filename or f"document{ext}"
+                            )
+                            doc_mime = SUPPORTED_DOCUMENT_TYPES[ext]
+                            media_urls.append(cached_path)
+                            media_types.append(doc_mime)
+                            logger.info("[Discord] Cached user document: %s", cached_path)
+                            # Inject text content for .txt/.md files (capped at 100 KB)
+                            MAX_TEXT_INJECT_BYTES = 100 * 1024
+                            if ext in (".md", ".txt") and len(raw_bytes) <= MAX_TEXT_INJECT_BYTES:
+                                try:
+                                    text_content = raw_bytes.decode("utf-8")
+                                    display_name = att.filename or f"document{ext}"
+                                    display_name = re.sub(r'[^\w.\- ]', '_', display_name)
+                                    injection = f"[Content of {display_name}]:\n{text_content}"
+                                    if pending_text_injection:
+                                        pending_text_injection = f"{pending_text_injection}\n\n{injection}"
+                                    else:
+                                        pending_text_injection = injection
+                                except UnicodeDecodeError:
+                                    pass
+                        except Exception as e:
+                            logger.warning(
+                                "[Discord] Failed to cache document %s: %s",
+                                att.filename, e, exc_info=True,
+                            )
         
+        event_text = message.content
+        if pending_text_injection:
+            event_text = f"{pending_text_injection}\n\n{event_text}" if event_text else pending_text_injection
+
         event = MessageEvent(
-            text=message.content,
+            text=event_text,
             message_type=msg_type,
             source=source,
             raw_message=message,