feat(events): align message events with checkpoint format and add middleware tag injection

- Message events (ai_message, ai_tool_call, tool_result, human_message) now use
  BaseMessage.model_dump() format, matching LangGraph checkpoint values.messages
- on_tool_end extracts tool_call_id/name/status from ToolMessage objects
- on_tool_error now emits tool_result message events with error status
- record_middleware uses middleware:{tag} event_type and middleware category
- Summarization custom events use middleware:summarize category
- TitleMiddleware injects middleware:title tag via get_config() inheritance
- SummarizationMiddleware model bound with middleware:summarize tag
- Worker writes human_message using HumanMessage.model_dump()

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

backend/tests/test_lead_agent_model_resolution.py

@@ -146,8 +146,11 @@ def test_create_summarization_middleware_uses_configured_model_alias(monkeypatch
         lambda: SummarizationConfig(enabled=True, model_name="model-masswork"),
     )
 
+    from unittest.mock import MagicMock
+
     captured: dict[str, object] = {}
-    fake_model = object()
+    fake_model = MagicMock()
+    fake_model.with_config.return_value = fake_model
 
     def _fake_create_chat_model(*, name=None, thinking_enabled, reasoning_effort=None):
         captured["name"] = name
@@ -163,3 +166,4 @@ def test_create_summarization_middleware_uses_configured_model_alias(monkeypatch
     assert captured["name"] == "model-masswork"
     assert captured["thinking_enabled"] is False
     assert middleware["model"] is fake_model
+    fake_model.with_config.assert_called_once_with(tags=["middleware:summarize"])