From d3687d3e817eaf98f983e8bd6358e825074340c9 Mon Sep 17 00:00:00 2001
From: teknium1 <teknium1@gmail.com>
Date: Mon, 16 Mar 2026 10:22:44 -0700
Subject: [PATCH] docs: document planned live reasoning token display as future
 enhancement

The streaming infrastructure already fires reasoning deltas via
_fire_reasoning_delta() during streaming. The remaining work is the
CLI display layer: a dim reasoning box that opens on first reasoning
token, streams live, then transitions to the response box.

Reference: PR #1214 (raulvidis) for gateway reasoning visibility.
---
 cli.py | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/cli.py b/cli.py
index 4256ac20b3..b02221ec81 100755
--- a/cli.py
+++ b/cli.py
@@ -1413,6 +1413,15 @@ class HermesCLI:
         self._invalidate()
 
     # ── Streaming display ────────────────────────────────────────────────
+    #
+    # Future: When display.show_reasoning is also enabled, stream reasoning
+    # tokens into a dim box above the response (like the existing static
+    # reasoning display, but live). The infrastructure exists — reasoning
+    # deltas fire via _fire_reasoning_delta() during streaming. The display
+    # layer needs: a dim reasoning box that opens on first reasoning token,
+    # accumulates live, then transitions to the response box when content
+    # tokens start arriving. See PR #1214 (raulvidis) for gateway-side
+    # reasoning visibility modes as a reference implementation.
 
     def _stream_delta(self, text: str) -> None:
         """Line-buffered streaming callback for real-time token rendering.