feat(cli): add /reasoning slash command to manage reasoning effort

Cherry-picked from PR #789 by Aum08Desai, rebased onto current main
with conflict resolution and improvements:

- Added /reasoning command: view current level or set to none|low|medium|high|xhigh
- Persists to config via save_config_value, forces agent re-init
- Resolved conflict with COMMANDS_BY_CATEGORY refactor (added to Configuration category)
- Restricted valid levels to none, low, medium, high, xhigh (removed 'minimal')
- Updated _parse_reasoning_config in cli.py and _load_reasoning_config in gateway/run.py
- Improved display messages (show all valid options, clearer defaults/disabled state)
- Added EXPECTED_COMMANDS entry for regression guard
- Expanded test suite: 16 tests covering all levels, rejection, display, case insensitivity,
  config save failure

Co-authored-by: Aum08Desai <145567217+Aum08Desai@users.noreply.github.com>

tests/hermes_cli/test_commands.py

@@ -12,7 +12,7 @@ EXPECTED_COMMANDS = {
     "/personality", "/clear", "/history", "/new", "/reset", "/retry",
     "/undo", "/save", "/config", "/cron", "/skills", "/platforms",
     "/verbose", "/compress", "/title", "/usage", "/insights", "/paste",
-    "/reload-mcp", "/rollback", "/background", "/skin", "/quit",
+    "/reload-mcp", "/rollback", "/background", "/skin", "/reasoning", "/quit",
 }