refactor: thread app_config through middleware factories (#2652)

* refactor: thread app_config through middleware factories

Continues the incremental config-refactor sequence (#2611 root, #2612 lead
path) one layer deeper into the middleware factories. Two ambient lookups
inside _build_runtime_middlewares are eliminated and the LLMErrorHandling
band-aid removed:

- _build_runtime_middlewares / build_lead_runtime_middlewares /
  build_subagent_runtime_middlewares now require app_config: AppConfig.
- get_guardrails_config() inside the factory is replaced with
  app_config.guardrails (semantically identical — same default-factory
  GuardrailsConfig — verified by direct equality check).
- LLMErrorHandlingMiddleware.__init__ now requires app_config and reads
  circuit_breaker fields directly. The class-level
  circuit_failure_threshold / circuit_recovery_timeout_sec defaults are
  removed along with the try/except (FileNotFoundError, RuntimeError):
  pass band-aid — the let-it-crash invariant the rest of the refactor
  enforces.

Caller chain (already-resolved app_config sources):
- _build_middlewares in lead_agent/agent.py: reorder so
  resolved_app_config = app_config or get_app_config() is computed BEFORE
  build_lead_runtime_middlewares is called, then passed as kwarg.
- SubagentExecutor: optional app_config parameter (mirrors the lead-agent
  pattern); _create_agent does the same `or get_app_config()` fallback at
  agent-build time, so task_tool callers don't need to plumb app_config
  through yet (typed-context plumbing for tool runtimes is a separate
  refactor).

Tests:
- test_llm_error_handling_middleware: _make_app_config helper using
  AppConfig(sandbox=SandboxConfig(use="test")) — same minimal-config
  pattern conftest already uses. Three direct LLMErrorHandlingMiddleware()
  calls each followed by post-construction circuit_breaker mutation fold
  cleanly into _build_middleware(circuit_failure_threshold=...,
  circuit_recovery_timeout_sec=...).

Verification:
- tests/test_llm_error_handling_middleware.py — 14 passed
- tests/test_subagent_executor.py — 28 passed
- tests/test_tool_error_handling_middleware.py — 6 passed
- tests/test_task_tool_core_logic.py — 18 passed (verifies task_tool
  unchanged behavior)
- Full suite: 2697 passed, 3 skipped. The single intermittent failure in
  tests/test_client_e2e.py::test_tool_call_produces_events is pre-existing
  LLM flakiness (the test asserts the model decided to call a tool;
  reproduces 1/3 on unchanged main as well).

* fix: address middleware app config review comments

* fix: satisfy app config annotation lint

* test: cover explicit app config middleware wiring

---------

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

backend/tests/test_subagent_executor.py

@@ -17,6 +17,7 @@ import asyncio
 import sys
 import threading
 from datetime import datetime
+from types import ModuleType
 from unittest.mock import MagicMock, patch
 
 import pytest
@@ -153,6 +154,13 @@ def mock_agent():
     return agent
 
 
+def _module(name: str, **attrs):
+    module = ModuleType(name)
+    for key, value in attrs.items():
+        setattr(module, key, value)
+    return module
+
+
 # Helper to create real message objects
 class _MsgHelper:
     """Helper to create real message objects from fixture classes."""
@@ -176,6 +184,88 @@ def msg(classes):
     return _MsgHelper(classes)
 
 
+# -----------------------------------------------------------------------------
+# Agent Construction Tests
+# -----------------------------------------------------------------------------
+
+
+class TestAgentConstruction:
+    """Test _create_agent() wiring before execution starts."""
+
+    def test_create_agent_threads_explicit_app_config_to_model_and_middlewares(
+        self,
+        classes,
+        base_config,
+        monkeypatch: pytest.MonkeyPatch,
+    ):
+        """Explicit app_config must flow into both model and middleware factories."""
+        import deerflow.config as config_module
+        from deerflow.subagents import executor as executor_module
+
+        SubagentExecutor = classes["SubagentExecutor"]
+
+        app_config = object()
+        model = object()
+        middlewares = [object()]
+        agent = object()
+        captured: dict[str, dict] = {}
+
+        def fake_get_app_config():
+            raise AssertionError("ambient get_app_config() must not be used when app_config is explicit")
+
+        def fake_create_chat_model(**kwargs):
+            captured["model"] = kwargs
+            return model
+
+        def fake_build_subagent_runtime_middlewares(**kwargs):
+            captured["middlewares"] = kwargs
+            return middlewares
+
+        def fake_create_agent(**kwargs):
+            captured["agent"] = kwargs
+            return agent
+
+        monkeypatch.setattr(config_module, "get_app_config", fake_get_app_config)
+        monkeypatch.setattr(
+            executor_module,
+            "create_chat_model",
+            fake_create_chat_model,
+        )
+        monkeypatch.setattr(executor_module, "create_agent", fake_create_agent)
+        monkeypatch.setitem(
+            sys.modules,
+            "deerflow.agents.middlewares.tool_error_handling_middleware",
+            _module(
+                "deerflow.agents.middlewares.tool_error_handling_middleware",
+                build_subagent_runtime_middlewares=fake_build_subagent_runtime_middlewares,
+            ),
+        )
+
+        executor = SubagentExecutor(
+            config=base_config,
+            tools=[],
+            app_config=app_config,
+            parent_model="parent-model",
+        )
+
+        result = executor._create_agent()
+
+        assert result is agent
+        assert captured["model"] == {
+            "name": "parent-model",
+            "thinking_enabled": False,
+            "app_config": app_config,
+        }
+        assert captured["middlewares"] == {
+            "app_config": app_config,
+            "lazy_init": True,
+        }
+        assert captured["agent"]["model"] is model
+        assert captured["agent"]["middleware"] is middlewares
+        assert captured["agent"]["tools"] == []
+        assert captured["agent"]["system_prompt"] == base_config.system_prompt
+
+
 # -----------------------------------------------------------------------------
 # Async Execution Path Tests
 # -----------------------------------------------------------------------------