diff --git a/hermes_cli/config.py b/hermes_cli/config.py
index 223d4239f..d5a063a97 100644
--- a/hermes_cli/config.py
+++ b/hermes_cli/config.py
@@ -2037,6 +2037,45 @@ DEFAULT_CONFIG = {
         "trust_recent_files_seconds": 600,
     },
 
+    # Real-time token streaming to messaging platforms (Telegram, Discord,
+    # Slack, etc.). Read at the top level by the gateway; absent this block the
+    # gateway falls back to these same defaults, so adding it here only makes
+    # the feature discoverable in config.yaml — it does not change behavior.
+    #
+    # Disabled by default: streaming costs extra edit/draft API calls per
+    # response. Set ``enabled: true`` and restart the gateway to turn it on.
+    "streaming": {
+        # Master switch. When false, each response is delivered as a single
+        # final message (no progressive updates).
+        "enabled": False,
+        # Transport selection:
+        #   "auto"  — prefer native draft streaming where the platform
+        #             supports it (Telegram DMs via sendMessageDraft,
+        #             Bot API 9.5+) and fall back to edit-based elsewhere.
+        #             Safe global default: platforms without draft support
+        #             (Discord, Slack, Matrix, Telegram groups) transparently
+        #             use the edit path, so "auto" only upgrades chats that
+        #             can render the smoother native preview.
+        #   "draft" — explicitly request native drafts; falls back to edit
+        #             when the platform/chat doesn't support them.
+        #   "edit"  — progressive editMessageText only (legacy behavior).
+        #   "off"   — disable streaming entirely (same as enabled: false).
+        "transport": "auto",
+        # Minimum seconds between progressive edits — tuned for Telegram's
+        # ~1 edit/s flood envelope.
+        "edit_interval": 0.8,
+        # Flush the buffer to the platform once this many characters have
+        # accumulated, so short replies feel near-instant.
+        "buffer_threshold": 24,
+        # Cursor glyph appended to the in-progress message while streaming.
+        "cursor": " \u2589",
+        # When >0, the final edit for a long-running streamed response is
+        # delivered as a fresh message if the preview has been visible at
+        # least this many seconds, so the platform timestamp reflects
+        # completion time. Telegram only; other platforms ignore it.
+        "fresh_final_after_seconds": 60.0,
+    },
+
     # Session storage — controls automatic cleanup of ~/.hermes/state.db.
     # state.db accumulates every session, message, tool call, and FTS5 index
     # entry forever.  Without auto-pruning, a heavy user (gateway + cron)
@@ -3756,7 +3795,7 @@ _KNOWN_ROOT_KEYS = {
     "fallback_providers", "credential_pool_strategies", "toolsets",
     "agent", "terminal", "display", "compression", "delegation",
     "auxiliary", "custom_providers", "context", "memory", "gateway",
-    "sessions",
+    "sessions", "streaming",
 }
 
 # Valid fields inside a custom_providers list entry