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/packages/harness/deerflow/subagents/executor.py

@@ -17,6 +17,7 @@ from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
 from langchain_core.runnables import RunnableConfig
 
 from deerflow.agents.thread_state import SandboxState, ThreadDataState, ThreadState
+from deerflow.config.app_config import AppConfig
 from deerflow.models import create_chat_model
 from deerflow.subagents.config import SubagentConfig
 
@@ -132,6 +133,7 @@ class SubagentExecutor:
         self,
         config: SubagentConfig,
         tools: list[BaseTool],
+        app_config: AppConfig | None = None,
         parent_model: str | None = None,
         sandbox_state: SandboxState | None = None,
         thread_data: ThreadDataState | None = None,
@@ -143,6 +145,9 @@ class SubagentExecutor:
         Args:
             config: Subagent configuration.
             tools: List of all available tools (will be filtered).
+            app_config: Resolved AppConfig; threaded into middleware factories
+                at agent-build time. When None, ``_create_agent`` falls back to
+                ``get_app_config()`` (matches the lead-agent factory's pattern).
             parent_model: The parent agent's model name for inheritance.
             sandbox_state: Sandbox state from parent agent.
             thread_data: Thread data from parent agent.
@@ -150,6 +155,7 @@ class SubagentExecutor:
             trace_id: Trace ID from parent for distributed tracing.
         """
         self.config = config
+        self.app_config = app_config
         self.parent_model = parent_model
         self.sandbox_state = sandbox_state
         self.thread_data = thread_data
@@ -168,13 +174,17 @@ class SubagentExecutor:
 
     def _create_agent(self):
         """Create the agent instance."""
+        # Mirror lead-agent factory pattern: prefer explicit app_config,
+        # fall back to ambient lookup at agent-build time.
+        from deerflow.config import get_app_config
+
+        resolved_app_config = self.app_config or get_app_config()
         model_name = _get_model_name(self.config, self.parent_model)
-        model = create_chat_model(name=model_name, thinking_enabled=False)
+        model = create_chat_model(name=model_name, thinking_enabled=False, app_config=resolved_app_config)
 
         from deerflow.agents.middlewares.tool_error_handling_middleware import build_subagent_runtime_middlewares
 
-        # Reuse shared middleware composition with lead agent.
-        middlewares = build_subagent_runtime_middlewares(lazy_init=True)
+        middlewares = build_subagent_runtime_middlewares(app_config=resolved_app_config, lazy_init=True)
 
         return create_agent(
             model=model,