fix(desktop): keep live model switch metadata truthful

A live config.set model switch already moved the next API call to the new model,
but the conversation could still restore an old sessions.system_prompt snapshot
whose Model/Provider lines named the previous runtime. That made "what model are
you?" answer from stale metadata even while inference ran on the new model.

After a live switch we now refresh the stored system prompt and append a real
system-history pivot (not a fake user turn) so the transcript itself records the
new model/provider. Restore also rejects already-stale prompt snapshots when
their Model/Provider lines disagree with the runtime, so existing bad sessions
self-heal.

tests/agent/test_system_prompt_restore.py

@@ -29,6 +29,7 @@ def _make_agent(session_db=None, prebuilt_prompt: str = "BUILT_PROMPT"):
     agent._cached_system_prompt = None
     agent.session_id = "test-session-id"
     agent.model = "test-model"
+    agent.provider = "openrouter"
     agent.platform = "cli"
     agent._session_db = session_db
     agent._build_system_prompt = MagicMock(return_value=prebuilt_prompt)
@@ -67,6 +68,47 @@ class TestStoredPromptReuse:
         _restore_or_build_system_prompt(agent, None, [{"role": "user", "content": "hi"}])
         assert agent._cached_system_prompt == stored
 
+    def test_present_row_with_stale_runtime_identity_rebuilds(self, caplog):
+        """Stored prompts are cache gold unless their runtime identity is stale.
+
+        A live /model switch updates the agent and DB model_config immediately.
+        If the old system_prompt snapshot still says the previous model,
+        blindly restoring it makes the next turn call the new model while the
+        model reads old `Model:` metadata ("what model are you?" lies).
+        """
+        stored = (
+            "You are Hermes Agent.\n\n"
+            "Conversation started: Tuesday, June 16, 2026\n"
+            "Session ID: test-session-id\n"
+            "Model: anthropic/claude-opus-4.8-fast\n"
+            "Provider: openrouter"
+        )
+        db = MagicMock()
+        db.get_session.return_value = {"system_prompt": stored}
+        agent = _make_agent(
+            session_db=db,
+            prebuilt_prompt=(
+                "You are Hermes Agent.\n\n"
+                "Conversation started: Tuesday, June 16, 2026\n"
+                "Session ID: test-session-id\n"
+                "Model: openai/gpt-5.5\n"
+                "Provider: openrouter"
+            ),
+        )
+        agent.model = "openai/gpt-5.5"
+
+        with caplog.at_level(logging.INFO, logger="agent.conversation_loop"):
+            _restore_or_build_system_prompt(agent, None, [{"role": "user", "content": "hi"}])
+
+        assert agent._cached_system_prompt.endswith(
+            "Model: openai/gpt-5.5\nProvider: openrouter"
+        )
+        agent._build_system_prompt.assert_called_once_with(None)
+        db.update_system_prompt.assert_called_once_with(
+            agent.session_id, agent._cached_system_prompt
+        )
+        assert any("stale runtime identity" in r.getMessage() for r in caplog.records)
+
 
 # ---------------------------------------------------------------------------
 # Legitimate fresh-build paths (no history, no DB)

tests/test_tui_gateway_server.py

@@ -3326,12 +3326,39 @@ def test_config_set_model_switches_agent_without_touching_env(monkeypatch):
         provider = "openai-codex"
         base_url = ""
         api_key = ""
+        session_id = "sid"
+        _cached_system_prompt = "Model: gpt-5.3-codex\nProvider: openai-codex"
 
         def switch_model(self, **kwargs):
             self.model = kwargs["new_model"]
             self.provider = kwargs["new_provider"]
 
+        def _build_system_prompt(self, _system_message=None):
+            return f"Model: {self.model}\nProvider: {self.provider}"
+
+    class SessionDB:
+        def __init__(self):
+            self.model_config = None
+            self.system_prompt = None
+            self.messages = []
+
+        def get_session(self, _session_id):
+            return {"model_config": self.model_config}
+
+        def update_session_meta(self, _session_id, model_config_json, _model=None):
+            self.model_config = model_config_json
+
+        def update_system_prompt(self, _session_id, system_prompt):
+            self.system_prompt = system_prompt
+
+        def append_message(self, session_id, role, content=None, **_kwargs):
+            self.messages.append(
+                {"session_id": session_id, "role": role, "content": content}
+            )
+
     agent = Agent()
+    db = SessionDB()
+    agent._session_db = db
     session = _session(agent=agent)
     server._sessions["sid"] = session
     monkeypatch.setenv("HERMES_TUI_PROVIDER", "openai-codex")
@@ -3373,6 +3400,21 @@ def test_config_set_model_switches_agent_without_touching_env(monkeypatch):
         # ...override recorded on the session...
         assert session["model_override"]["model"] == "anthropic/claude-sonnet-4.6"
         assert session["model_override"]["provider"] == "anthropic"
+        # ...the persisted prompt snapshot tracks the new runtime identity too.
+        # Without this, the next turn restored the old system prompt from the DB:
+        # API calls went to the new model, but "what model are you?" still read
+        # "Model: old/model" from the stored prompt.
+        assert db.system_prompt == (
+            "Model: anthropic/claude-sonnet-4.6\nProvider: anthropic"
+        )
+        assert agent._cached_system_prompt == db.system_prompt
+        assert session["history"][-1]["role"] == "system"
+        assert "changed to anthropic/claude-sonnet-4.6" in session["history"][-1]["content"]
+        assert db.messages[-1] == {
+            "session_id": "session-key",
+            "role": "system",
+            "content": session["history"][-1]["content"],
+        }
         # ...and the shared process env was NOT touched.
         assert os.environ["HERMES_TUI_PROVIDER"] == "openai-codex"
         assert "HERMES_MODEL" not in os.environ