fix(cli): warn when in-session model switch will preflight-compress

Adds hermes_cli/context_switch_guard.py mirroring the model_cost_guard
pattern. When a user switches models mid-session (Herm TUI picker, CLI,
or /model on Telegram/Discord), the warning surfaces on the existing
ModelSwitchResult.warning_message path used by the expensive-model
guard if the new model's compression threshold is below the current
session size.

Partial fix for #23767 — addresses only the 'user-facing guardrail
when switching from a high-context provider to a substantially
lower-context provider' slice. The other proposed fixes from that
issue (hard preflight token guard, metadata cache invalidation on
switch, compression safety invariant, oversized tool-output handling)
are out of scope for this PR.

cli.py

@@ -6936,6 +6936,19 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
             _cprint(f"  ✗ {result.error_message}")
             return
 
+        if self.agent is not None:
+            try:
+                from hermes_cli.context_switch_guard import merge_preflight_compression_warning
+
+                merge_preflight_compression_warning(
+                    result,
+                    agent=self.agent,
+                    messages=list(self.conversation_history or []),
+                    config_context_length=getattr(self.agent, "_config_context_length", None),
+                )
+            except Exception:
+                pass
+
         old_model = self.model
         self.model = result.new_model
         self.provider = result.target_provider
@@ -7202,6 +7215,19 @@ class HermesCLI(CLIAgentSetupMixin, CLICommandsMixin):
             _cprint(f"  ✗ {result.error_message}")
             return
 
+        if self.agent is not None:
+            try:
+                from hermes_cli.context_switch_guard import merge_preflight_compression_warning
+
+                merge_preflight_compression_warning(
+                    result,
+                    agent=self.agent,
+                    messages=list(self.conversation_history or []),
+                    config_context_length=getattr(self.agent, "_config_context_length", None),
+                )
+            except Exception:
+                pass
+
         if not self._confirm_expensive_model_switch(result):
             _cprint("  Model switch cancelled.")
             return