fix(agent-runner): package context for plugin execution

tests/unit_tests/agent/test_orchestrator_integration.py

@@ -309,6 +309,62 @@ async def test_orchestrator_runs_fake_plugin_with_authorized_context():
     assert await get_session_registry().get(context["run_id"]) is None
 
 
+@pytest.mark.asyncio
+async def test_orchestrator_packages_legacy_max_round_without_mutating_query():
+    descriptor = make_descriptor()
+    plugin_connector = FakePluginConnector(
+        results=[
+            {
+                "type": "message.completed",
+                "data": {"message": {"role": "assistant", "content": "fake response"}},
+            }
+        ]
+    )
+    ap = FakeApplication(plugin_connector)
+    orchestrator = AgentRunOrchestrator(ap, FakeRegistry(descriptor))
+    query = make_query()
+    query.pipeline_config["ai"]["runner_config"][RUNNER_ID]["max-round"] = 2
+    query.messages = [
+        provider_message.Message(role="user", content="message 1"),
+        provider_message.Message(role="assistant", content="response 1"),
+        provider_message.Message(role="user", content="message 2"),
+        provider_message.Message(role="assistant", content="response 2"),
+        provider_message.Message(role="user", content="message 3"),
+        provider_message.Message(role="assistant", content="response 3"),
+    ]
+
+    messages = [message async for message in orchestrator.run_from_query(query)]
+
+    assert len(messages) == 1
+    context = plugin_connector.contexts[0]
+    assert [message["content"] for message in context["messages"]] == [
+        "message 2",
+        "response 2",
+        "message 3",
+        "response 3",
+    ]
+    assert [message.content for message in query.messages] == [
+        "message 1",
+        "response 1",
+        "message 2",
+        "response 2",
+        "message 3",
+        "response 3",
+    ]
+    assert context["runtime"]["metadata"]["context_packaging"] == {
+        "policy": {
+            "mode": "legacy_max_round",
+            "max_round": 2,
+        },
+        "history": {
+            "source": "query.messages",
+            "source_total_count": 6,
+            "delivered_count": 4,
+            "messages_complete": False,
+        },
+    }
+
+
 @pytest.mark.asyncio
 async def test_orchestrator_streams_fake_plugin_deltas():
     descriptor = make_descriptor()

tests/unit_tests/pipeline/test_msgtrun.py

@@ -48,6 +48,18 @@ def get_round_truncator_module():
 
 def make_truncate_config(max_round: int = 5):
     """Create a pipeline config with max-round setting."""
+    return {
+        'msg-truncate': {
+            'method': 'round',
+            'round': {
+                'max-round': max_round,
+            },
+        },
+    }
+
+
+def make_agent_runner_config(max_round: int = 5):
+    """Create an AgentRunner pipeline config with max-round binding config."""
     return {
         'ai': {
             'runner': {'id': RUNNER_ID},
@@ -137,6 +149,36 @@ class TestRoundTruncatorProcess:
         # All messages should be preserved
         assert len(result.new_query.messages) == 5
 
+    @pytest.mark.asyncio
+    async def test_agent_runner_path_skips_pipeline_truncation(self):
+        """AgentRunner path should leave query.messages intact at pipeline stage."""
+        msgtrun = get_msgtrun_module()
+        entities = get_entities_module()
+
+        app = FakeApp()
+        stage = msgtrun.ConversationMessageTruncator(app)
+
+        pipeline_config = make_agent_runner_config(max_round=1)
+
+        await stage.initialize(pipeline_config)
+
+        query = text_query("current")
+        query.pipeline_config = pipeline_config
+        query.messages = [
+            provider_message.Message(role='user', content='old1'),
+            provider_message.Message(role='assistant', content='old1_resp'),
+            provider_message.Message(role='user', content='current'),
+        ]
+
+        result = await stage.process(query, 'ConversationMessageTruncator')
+
+        assert result.result_type == entities.ResultType.CONTINUE
+        assert [(msg.role, msg.content) for msg in result.new_query.messages] == [
+            ('user', 'old1'),
+            ('assistant', 'old1_resp'),
+            ('user', 'current'),
+        ]
+
     @pytest.mark.asyncio
     async def test_truncate_exceeds_limit(self):
         """Messages exceeding max-round should be truncated precisely.