refactor: thread app_config through lead and subagent task path (#2666)

* refactor: thread app config through lead prompt

* fix: honor explicit app config across runtime paths

* style: format subagent executor tests

* fix: thread resolved app config and guard subagents-only fallback

Address two PR review findings:

1. _create_summarization_middleware passed the original (possibly None)
   app_config into create_chat_model, forcing the model factory back to
   ambient get_app_config() and risking config drift between the
   middleware's resolved view and the model's view. Pass the resolved
   AppConfig instance through end-to-end.

2. get_available_subagent_names accepted Any-typed config and forwarded
   it to is_host_bash_allowed, which reads ``.sandbox``. A
   SubagentsAppConfig (also accepted upstream as a sum-type input) has
   no ``.sandbox`` attribute and would be silently treated as "no
   sandbox configured", incorrectly disabling the bash subagent. Guard
   on hasattr and fall back to ambient lookup otherwise.

Adds regression tests for both paths.

* chore: simplify hasattr guard and tighten regression tests

- Collapse if/else into ternary in get_available_subagent_names; hasattr(None, ...) is False so the explicit None check was redundant.
- Drop comments that narrate the change rather than explain non-obvious WHY (test names already convey intent).
- Replace stringly-typed sentinel "no-arg" in regression test with direct args tuple comparison.

---------

Co-authored-by: greatmengqi <chenmengqi.0376@bytedance.com>

backend/tests/test_subagent_executor.py

@@ -204,7 +204,7 @@ class TestAgentConstruction:
 
         SubagentExecutor = classes["SubagentExecutor"]
 
-        app_config = object()
+        app_config = SimpleNamespace(models=[SimpleNamespace(name="default-model")])
         model = object()
         middlewares = [object()]
         agent = object()
@@ -266,6 +266,43 @@ class TestAgentConstruction:
         assert captured["agent"]["tools"] == []
         assert captured["agent"]["system_prompt"] == base_config.system_prompt
 
+    @pytest.mark.anyio
+    async def test_load_skill_messages_uses_explicit_app_config_for_skill_storage(
+        self,
+        classes,
+        base_config,
+        monkeypatch: pytest.MonkeyPatch,
+        tmp_path,
+    ):
+        """Explicit app_config must be threaded into subagent skill storage lookup."""
+        SubagentExecutor = classes["SubagentExecutor"]
+
+        app_config = SimpleNamespace(models=[SimpleNamespace(name="default-model")])
+        skill_dir = tmp_path / "demo-skill"
+        skill_dir.mkdir()
+        skill_file = skill_dir / "SKILL.md"
+        skill_file.write_text("Use demo skill", encoding="utf-8")
+        captured: dict[str, object] = {}
+
+        def fake_get_or_new_skill_storage(*, app_config=None):
+            captured["app_config"] = app_config
+            return SimpleNamespace(load_skills=lambda *, enabled_only: [SimpleNamespace(name="demo-skill", skill_file=skill_file)])
+
+        monkeypatch.setattr("deerflow.skills.storage.get_or_new_skill_storage", fake_get_or_new_skill_storage)
+
+        executor = SubagentExecutor(
+            config=base_config,
+            tools=[],
+            app_config=app_config,
+            thread_id="test-thread",
+        )
+
+        messages = await executor._load_skill_messages()
+
+        assert captured["app_config"] is app_config
+        assert len(messages) == 1
+        assert "Use demo skill" in messages[0].content
+
 
 # -----------------------------------------------------------------------------
 # Async Execution Path Tests