fix(credits): suppress usage gauge when top-up funds exist + add display.credits_notices toggle (#44716)

The subscription-cap usage gauge (50/75/90% bands) ignored purchased
(top-up) credits: a sub user with top-up funds got a sticky warn banner
at 90% of their cap — permanently at >=100%, alongside grant_spent —
despite being fully able to keep inferencing. The cap is the wrong
denominator for an account that can keep spending.

- evaluate_credits_notices: purchased_micros > 0 suppresses the usage
  band (grant_spent already covers the cap-reached + top-up case with
  the remaining balance). A top-up landing mid-session clears any
  showing band; spending top-up down to 0 resumes the gauge.
- New display.credits_notices config (default true): false silences all
  credits notices. State capture and /usage are unaffected. Read once
  per agent (cached) in _emit_credits_notices, fail-open true.
- Docs: configuration.md display block.

run_agent.py

@@ -2827,6 +2827,8 @@ class AIAgent:
         """
         if getattr(self, "notice_callback", None) is None and getattr(self, "notice_clear_callback", None) is None:
             return
+        if not self._credits_notices_enabled():
+            return
         state = getattr(self, "_credits_state", None)
         if state is None:
             return
@@ -2850,6 +2852,29 @@ class AIAgent:
         except Exception:
             logger.warning("credits notice evaluation/emit failed", exc_info=True)
 
+    def _credits_notices_enabled(self) -> bool:
+        """Whether credits notices are enabled (config display.credits_notices).
+
+        Read once per agent and cached — the policy runs after every API
+        response, and the setting governs UI noise, not correctness, so a
+        config flip applying on the next session is fine.  Fail-open True
+        (preserve current behaviour) on any config error.
+        """
+        cached = getattr(self, "_credits_notices_enabled_cache", None)
+        if cached is not None:
+            return cached
+        enabled = True
+        try:
+            from hermes_cli.config import load_config as _load_config
+            _cfg = _load_config() or {}
+            _display = _cfg.get("display") if isinstance(_cfg, dict) else None
+            if isinstance(_display, dict) and "credits_notices" in _display:
+                enabled = bool(_display.get("credits_notices"))
+        except Exception:
+            enabled = True
+        self._credits_notices_enabled_cache = enabled
+        return enabled
+
     def get_credits_state(self):
         """Return the last captured CreditsState, or None."""
         return self._credits_state