fix(cli): pass custom_providers to resolve_display_context_length (#59314)

The CLI model-switch display (both picker and direct-switch paths)
omitted the custom_providers keyword when calling
resolve_display_context_length(). The function already supports it
(and the gateway correctly passes it), but the CLI call sites relied
on the fallthrough to probe-down default (256K) even when a
custom_providers entry specified a per-model context_length.

Fix: pass agent._custom_providers at both resolve_display_context_length
call sites in HermesCLI._apply_model_switch_result(), matching the
pattern already used for config_context_length.

cli.py

@@ -7844,6 +7844,7 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
                 api_key=result.api_key or self.api_key or "",
                 model_info=mi,
                 config_context_length=getattr(self.agent, "_config_context_length", None) if self.agent else None,
+                custom_providers=getattr(self.agent, "_custom_providers", None) if self.agent else None,
             )
             if ctx:
                 _cprint(f"    Context: {ctx:,} tokens")
@@ -8152,6 +8153,7 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
             api_key=result.api_key or self.api_key or "",
             model_info=mi,
             config_context_length=getattr(self.agent, "_config_context_length", None) if self.agent else None,
+            custom_providers=getattr(self.agent, "_custom_providers", None) if self.agent else None,
         )
         if ctx:
             _cprint(f"    Context: {ctx:,} tokens")

tests/hermes_cli/test_model_switch_context_display.py

@@ -146,3 +146,30 @@ class TestResolveDisplayContextLength:
                 custom_providers=custom_provs,
             )
         assert ctx == 400_000
+
+    def test_without_custom_providers_returns_default_fallback(self):
+        """Regression for #59314: When custom_providers is NOT passed
+        (the bug pre-fix), a custom provider model falls through to
+        probe-down default (256K) instead of the configured per-model
+        context_length."""
+        from unittest.mock import patch as _p
+        from agent import model_metadata as _mm
+        with _p.object(_mm, "get_cached_context_length", return_value=None), \
+             _p.object(_mm, "fetch_endpoint_model_metadata", return_value={}), \
+             _p.object(_mm, "fetch_model_metadata", return_value={}), \
+             _p.object(_mm, "is_local_endpoint", return_value=False), \
+             _p.object(_mm, "_is_known_provider_base_url", return_value=False):
+            # Without custom_providers, the function probes and gets default
+            ctx = resolve_display_context_length(
+                "test-model-unconfigured",
+                "custom",
+                base_url="https://example.invalid/v1",
+                api_key="k",
+                model_info=None,
+            )
+        # Without custom_providers, the function falls to probe-down default
+        assert ctx == 256_000, (
+            "Without custom_providers, an un-cached model gets 256K default. "
+            "The fix ensures custom_providers is passed so per-model overrides "
+            "are honored."
+        )