fix(agent): silence quiet_mode in python library use

run_agent.py

@@ -1916,13 +1916,16 @@ class AIAgent:
     def _should_emit_quiet_tool_messages(self) -> bool:
         """Return True when quiet-mode tool summaries should print directly.
 
-        When the caller provides ``tool_progress_callback`` (for example the CLI
-        TUI or a gateway progress renderer), that callback owns progress display.
-        Emitting quiet-mode summary lines here duplicates progress and leaks tool
-        previews into flows that are expected to stay silent, such as
-        ``hermes chat -q``.
+        Quiet mode is used by both the interactive CLI and embedded/library
+        callers. The CLI may still want compact progress hints when no callback
+        owns rendering. Embedded/library callers, on the other hand, expect
+        quiet mode to be truly silent.
         """
-        return self.quiet_mode and not self.tool_progress_callback
+        return (
+            self.quiet_mode
+            and not self.tool_progress_callback
+            and getattr(self, "platform", "") == "cli"
+        )
 
     def _emit_status(self, message: str) -> None:
         """Emit a lifecycle status message to both CLI and gateway channels.
@@ -11184,7 +11187,7 @@ class AIAgent:
                         self._last_content_tools_all_housekeeping = _all_housekeeping
                         if _all_housekeeping and self._has_stream_consumers():
                             self._mute_post_response = True
-                        elif self.quiet_mode:
+                        elif self.quiet_mode and getattr(self, "platform", "") == "cli":
                             clean = self._strip_think_blocks(turn_content).strip()
                             if clean:
                                 relayed = False

tests/run_agent/test_run_agent.py

@@ -1285,6 +1285,7 @@ class TestExecuteToolCalls:
         tc = _mock_tool_call(name="web_search", arguments='{"q":"test"}', call_id="c1")
         mock_msg = _mock_assistant_msg(content="", tool_calls=[tc])
         messages = []
+        agent.platform = "cli"
         agent.tool_progress_callback = None
 
         with patch("run_agent.handle_function_call", return_value="search result"), \
@@ -1296,6 +1297,21 @@ class TestExecuteToolCalls:
         assert len(messages) == 1
         assert messages[0]["role"] == "tool"
 
+    def test_quiet_tool_output_suppressed_without_progress_callback_for_non_cli_agent(self, agent):
+        tc = _mock_tool_call(name="web_search", arguments='{"q":"test"}', call_id="c1")
+        mock_msg = _mock_assistant_msg(content="", tool_calls=[tc])
+        messages = []
+        agent.platform = None
+        agent.tool_progress_callback = None
+
+        with patch("run_agent.handle_function_call", return_value="search result"), \
+             patch.object(agent, "_safe_print") as mock_print:
+            agent._execute_tool_calls(mock_msg, messages, "task-1")
+
+        mock_print.assert_not_called()
+        assert len(messages) == 1
+        assert messages[0]["role"] == "tool"
+
     def test_vprint_suppressed_in_parseable_quiet_mode(self, agent):
         agent.suppress_status_output = True
 
@@ -1876,6 +1892,30 @@ class TestRunConversation:
         assert all("message_count" in c and "messages" not in c for c in pre_request_calls)
         assert all("usage" in c and "response" not in c for c in post_request_calls)
 
+    def test_content_with_tool_calls_stays_silent_for_non_cli_quiet_mode(self, agent):
+        self._setup_agent(agent)
+        agent.platform = None
+        tc = _mock_tool_call(name="web_search", arguments="{}", call_id="c1")
+        resp1 = _mock_response(
+            content="I'll search for that.",
+            finish_reason="tool_calls",
+            tool_calls=[tc],
+        )
+        resp2 = _mock_response(content="Done searching", finish_reason="stop")
+        agent.client.chat.completions.create.side_effect = [resp1, resp2]
+
+        with (
+            patch("run_agent.handle_function_call", return_value="search result"),
+            patch.object(agent, "_safe_print") as mock_print,
+            patch.object(agent, "_persist_session"),
+            patch.object(agent, "_save_trajectory"),
+            patch.object(agent, "_cleanup_task_resources"),
+        ):
+            result = agent.run_conversation("search something")
+
+        assert result["final_response"] == "Done searching"
+        mock_print.assert_not_called()
+
     def test_interrupt_breaks_loop(self, agent):
         self._setup_agent(agent)