feat(telegram): add document file processing for PDF, text, and Office files

Download, cache, and enrich document files sent via Telegram. Supports
.pdf, .md, .txt, .docx, .xlsx, .pptx with size validation, unsupported
type rejection, text content injection for .md/.txt, and hourly cache
cleanup.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

gateway/platforms/base.py

@@ -171,6 +171,74 @@ async def cache_audio_from_url(url: str, ext: str = ".ogg") -> str:
         return cache_audio_from_bytes(response.content, ext)
 
 
+# ---------------------------------------------------------------------------
+# Document cache utilities
+#
+# Same pattern as image/audio cache -- documents from platforms are downloaded
+# here so the agent can reference them by local file path.
+# ---------------------------------------------------------------------------
+
+DOCUMENT_CACHE_DIR = Path(os.path.expanduser("~/.hermes/document_cache"))
+
+SUPPORTED_DOCUMENT_TYPES = {
+    ".pdf": "application/pdf",
+    ".md": "text/markdown",
+    ".txt": "text/plain",
+    ".docx": "application/vnd.openxmlformats-officedocument.wordprocessingml.document",
+    ".xlsx": "application/vnd.openxmlformats-officedocument.spreadsheetml.sheet",
+    ".pptx": "application/vnd.openxmlformats-officedocument.presentationml.presentation",
+}
+
+
+def get_document_cache_dir() -> Path:
+    """Return the document cache directory, creating it if it doesn't exist."""
+    DOCUMENT_CACHE_DIR.mkdir(parents=True, exist_ok=True)
+    return DOCUMENT_CACHE_DIR
+
+
+def cache_document_from_bytes(data: bytes, filename: str) -> str:
+    """
+    Save raw document bytes to the cache and return the absolute file path.
+
+    The cached filename preserves the original human-readable name with a
+    unique prefix: ``doc_{uuid12}_{original_filename}``.
+
+    Args:
+        data: Raw document bytes.
+        filename: Original filename (e.g. "report.pdf").
+
+    Returns:
+        Absolute path to the cached document file as a string.
+    """
+    cache_dir = get_document_cache_dir()
+    safe_name = filename if filename else "document"
+    cached_name = f"doc_{uuid.uuid4().hex[:12]}_{safe_name}"
+    filepath = cache_dir / cached_name
+    filepath.write_bytes(data)
+    return str(filepath)
+
+
+def cleanup_document_cache(max_age_hours: int = 24) -> int:
+    """
+    Delete cached documents older than *max_age_hours*.
+
+    Returns the number of files removed.
+    """
+    import time
+
+    cache_dir = get_document_cache_dir()
+    cutoff = time.time() - (max_age_hours * 3600)
+    removed = 0
+    for f in cache_dir.iterdir():
+        if f.is_file() and f.stat().st_mtime < cutoff:
+            try:
+                f.unlink()
+                removed += 1
+            except OSError:
+                pass
+    return removed
+
+
 class MessageType(Enum):
     """Types of incoming messages."""
     TEXT = "text"