refactor(journal): fix flush, token tracking, and consolidate tests

RunJournal fixes:
- _flush_sync: retain events in buffer when no event loop instead of
  dropping them; worker's finally block flushes via async flush().
- on_llm_end: add tool_calls filter and caller=="lead_agent" guard for
  ai_message events; mark message IDs for dedup with record_llm_usage.
- worker.py: persist completion data (tokens, message count) to RunStore
  in finally block.

Model factory:
- Auto-inject stream_usage=True for BaseChatOpenAI subclasses with
  custom api_base, so usage_metadata is populated in streaming responses.

Test consolidation:
- Delete test_phase2b_integration.py (redundant with existing tests).
- Move DB-backed lifecycle test into test_run_journal.py.
- Add tests for stream_usage injection in test_model_factory.py.
- Clean up executor/task_tool dead journal references.

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

backend/packages/harness/deerflow/models/factory.py

@@ -77,6 +77,15 @@ def create_chat_model(name: str | None = None, thinking_enabled: bool = False, *
         elif "reasoning_effort" not in model_settings_from_config:
             model_settings_from_config["reasoning_effort"] = "medium"
 
+    # Ensure stream_usage is enabled so that token usage metadata is available
+    # in streaming responses.  LangChain's BaseChatOpenAI only defaults
+    # stream_usage=True when no custom base_url/api_base is set, so models
+    # hitting third-party endpoints (e.g. doubao, deepseek) silently lose
+    # usage data.  We default it to True unless explicitly configured.
+    if "stream_usage" not in model_settings_from_config and "stream_usage" not in kwargs:
+        if "stream_usage" in getattr(model_class, "model_fields", {}):
+            model_settings_from_config["stream_usage"] = True
+
     model_instance = model_class(**kwargs, **model_settings_from_config)
 
     if is_tracing_enabled():