github/deer-flow
1
0
Fork 0
mirror of https://github.com/bytedance/deer-flow.git synced 2026-06-09 09:02:02 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor(lead-agent): make build_middlewares public to drop the last cross-module private import (#3458)

Browse Source 
`client.py` imported the private `_build_middlewares` from `agent.py` across a
module boundary and called it as public API. Because the `_` name signals
"module-private, no external callers", any future rename or signature change
silently breaks the embedded `DeerFlowClient` path — and the test suite even
monkeypatched `deerflow.client._build_middlewares`, baking the leak in.

`DeerFlowClient` is a lead-agent variant that genuinely needs the lead agent's
full middleware composition, so make the dependency honest: promote the helper
to a documented public entry point `build_middlewares` and update every in-repo
caller. Found during #3341 review; #3341 already removed one such leak
(`_assemble_deferred` -> public `assemble_deferred_tools`) and left this one out
of scope on purpose.

- agent.py: rename def + both internal call sites; expand the docstring into a
  public-entry-point contract and document the previously-undocumented
  model_name / app_config / deferred_setup params
- client.py: import + call site now use the public name (removes the last
  cross-module private import)
- scripts/tool-error-degradation-detection.sh: update its import + call site
- tests (5 files): update monkeypatch/patch targets and direct calls
- docs (backend/CLAUDE.md, plan_mode_usage.md, middlewares.mdx): sync the live
  references that describe the symbol as current API

Pure mechanical rename, no behavior change. Historical design docs (rfc,
superpowers spec) intentionally keep the old name as point-in-time records.

Closes #3431
This commit is contained in:
AochenShen99 2026-06-09 11:56:28 +08:00 committed by GitHub
parent 90e23bfd09
commit 0fb18e368c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
11 changed files with 48 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
backend/CLAUDE.md
View File

@ -192,7 +192,7 @@ from deerflow.config import get_app_config
### Middleware Chain
Lead-agent middlewares are assembled in strict append order across `packages/harness/deerflow/agents/middlewares/tool_error_handling_middleware.py` (`build_lead_runtime_middlewares`) and `packages/harness/deerflow/agents/lead_agent/agent.py` (`_build_middlewares`):
Lead-agent middlewares are assembled in strict append order across `packages/harness/deerflow/agents/middlewares/tool_error_handling_middleware.py` (`build_lead_runtime_middlewares`) and `packages/harness/deerflow/agents/lead_agent/agent.py` (`build_middlewares`):
1. **ThreadDataMiddleware** - Creates per-thread directories under the user's isolation scope (`backend/.deer-flow/users/{user_id}/threads/{thread_id}/user-data/{workspace,uploads,outputs}`); resolves `user_id` via `get_effective_user_id()` (falls back to `"default"` in no-auth mode); Web UI thread deletion now follows LangGraph thread removal with Gateway cleanup of the local thread directory
2. **UploadsMiddleware** - Tracks and injects newly uploaded files into conversation
@ -493,7 +493,7 @@ Both can be modified at runtime via Gateway API endpoints or `DeerFlowClient` me
- `"messages-tuple"` — per-chunk update: for AI text this is a **delta** (concat per `id` to rebuild the full message); tool calls and tool results are emitted once each
- `"custom"` — forwarded from `StreamWriter`
- `"end"` — stream finished (carries cumulative `usage` counted once per message id)
- Agent created lazily via `create_agent()` + `_build_middlewares()`, same as `make_lead_agent`
- Agent created lazily via `create_agent()` + `build_middlewares()`, same as `make_lead_agent`
- Supports `checkpointer` parameter for state persistence across turns
- `reset_agent()` forces agent recreation (e.g. after memory or skill changes)
- See [docs/STREAMING.md](docs/STREAMING.md) for the full design: why Gateway and DeerFlowClient are parallel paths, LangGraph's `stream_mode` semantics, the per-id dedup invariants, and regression testing strategy

8
backend/docs/plan_mode_usage.md
View File

@ -127,8 +127,8 @@ complex_agent = create_agent_for_task("high")
## How It Works
1. When `make_lead_agent(config)` is called, it extracts `is_plan_mode` from `config.configurable`
2. The config is passed to `_build_middlewares(config)`
3. `_build_middlewares()` reads `is_plan_mode` and calls `_create_todo_list_middleware(is_plan_mode)`
2. The config is passed to `build_middlewares(config)`
3. `build_middlewares()` reads `is_plan_mode` and calls `_create_todo_list_middleware(is_plan_mode)`
4. If `is_plan_mode=True`, a `TodoListMiddleware` instance is created and added to the middleware chain
5. The middleware automatically adds a `write_todos` tool to the agent's toolset
6. The agent can use this tool to manage tasks during execution
@ -141,7 +141,7 @@ make_lead_agent(config)
│
├─> Extracts: is_plan_mode = config.configurable.get("is_plan_mode", False)
│
└─> _build_middlewares(config)
└─> build_middlewares(config)
│
├─> ThreadDataMiddleware
├─> SandboxMiddleware
@ -156,7 +156,7 @@ make_lead_agent(config)
### Agent Module
- **Location**: `packages/harness/deerflow/agents/lead_agent/agent.py`
- **Function**: `_create_todo_list_middleware(is_plan_mode: bool)` - Creates TodoListMiddleware if plan mode is enabled
- **Function**: `_build_middlewares(config: RunnableConfig)` - Builds middleware chain based on runtime config
- **Function**: `build_middlewares(config: RunnableConfig)` - Builds middleware chain based on runtime config
- **Function**: `make_lead_agent(config: RunnableConfig)` - Creates agent with appropriate middlewares
### Runtime Configuration

17
backend/packages/harness/deerflow/agents/lead_agent/agent.py
View File

@ -265,7 +265,7 @@ Being proactive with task management demonstrates thoroughness and ensures all r
# ViewImageMiddleware should be before ClarificationMiddleware to inject image details before LLM
# ToolErrorHandlingMiddleware should be before ClarificationMiddleware to convert tool exceptions to ToolMessages
# ClarificationMiddleware should be last to intercept clarification requests after model calls
def _build_middlewares(
def build_middlewares(
config: RunnableConfig,
model_name: str | None,
agent_name: str | None = None,
@ -274,12 +274,21 @@ def _build_middlewares(
app_config: AppConfig | None = None,
deferred_setup=None,
):
"""Build middleware chain based on runtime configuration.
"""Build the lead-agent middleware chain based on runtime configuration.
Public entry point for the lead agent's full middleware composition. Used by
``make_lead_agent`` and by the embedded ``DeerFlowClient`` (a lead-agent variant
that needs the identical chain). Keep this name stable: it is imported across a
module boundary, so renames/signature changes ripple into ``client.py``.
Args:
config: Runtime configuration containing configurable options like is_plan_mode.
model_name: Resolved runtime model name; gates vision-only middleware.
agent_name: If provided, MemoryMiddleware will use per-agent memory storage.
custom_middlewares: Optional list of custom middlewares to inject into the chain.
app_config: Explicit AppConfig; falls back to ``get_app_config()`` when omitted.
deferred_setup: Optional deferred-MCP-tool setup that attaches
``DeferredToolFilterMiddleware`` when ``tool_search`` is enabled.
Returns:
List of middleware instances.
@ -472,7 +481,7 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
return create_agent(
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=resolved_app_config, attach_tracing=False),
tools=final_tools,
middleware=_build_middlewares(config, model_name=model_name, app_config=resolved_app_config, deferred_setup=setup),
middleware=build_middlewares(config, model_name=model_name, app_config=resolved_app_config, deferred_setup=setup),
system_prompt=apply_prompt_template(
subagent_enabled=subagent_enabled,
max_concurrent_subagents=max_concurrent_subagents,
@ -493,7 +502,7 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
return create_agent(
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, reasoning_effort=reasoning_effort, app_config=resolved_app_config, attach_tracing=False),
tools=final_tools,
middleware=_build_middlewares(config, model_name=model_name, agent_name=agent_name, app_config=resolved_app_config, deferred_setup=setup),
middleware=build_middlewares(config, model_name=model_name, agent_name=agent_name, app_config=resolved_app_config, deferred_setup=setup),
system_prompt=apply_prompt_template(
subagent_enabled=subagent_enabled,
max_concurrent_subagents=max_concurrent_subagents,

4
backend/packages/harness/deerflow/client.py
View File

@ -33,7 +33,7 @@ from langchain.agents.middleware import AgentMiddleware
from langchain_core.messages import AIMessage, HumanMessage, SystemMessage, ToolMessage
from langchain_core.runnables import RunnableConfig
from deerflow.agents.lead_agent.agent import _build_middlewares
from deerflow.agents.lead_agent.agent import build_middlewares
from deerflow.agents.lead_agent.prompt import apply_prompt_template
from deerflow.agents.thread_state import ThreadState
from deerflow.config.agents_config import AGENT_NAME_PATTERN
@ -247,7 +247,7 @@ class DeerFlowClient:
# Attaching them again on the model would emit duplicate spans.
"model": create_chat_model(name=model_name, thinking_enabled=thinking_enabled, attach_tracing=False),
"tools": final_tools,
"middleware": _build_middlewares(config, model_name=model_name, agent_name=self._agent_name, custom_middlewares=self._middlewares, deferred_setup=deferred_setup),
"middleware": build_middlewares(config, model_name=model_name, agent_name=self._agent_name, custom_middlewares=self._middlewares, deferred_setup=deferred_setup),
"system_prompt": apply_prompt_template(
subagent_enabled=subagent_enabled,
max_concurrent_subagents=max_concurrent_subagents,

4
backend/tests/test_checkpointer.py
View File

@ -747,7 +747,7 @@ class TestClientCheckpointerFallback:
patch("deerflow.client.get_app_config", return_value=config_mock),
patch("deerflow.client.create_agent", side_effect=fake_create_agent),
patch("deerflow.client.create_chat_model", return_value=MagicMock()),
patch("deerflow.client._build_middlewares", return_value=[]),
patch("deerflow.client.build_middlewares", return_value=[]),
patch("deerflow.client.apply_prompt_template", return_value=""),
patch("deerflow.client.DeerFlowClient._get_tools", return_value=[]),
):
@ -781,7 +781,7 @@ class TestClientCheckpointerFallback:
patch("deerflow.client.get_app_config", return_value=config_mock),
patch("deerflow.client.create_agent", side_effect=fake_create_agent),
patch("deerflow.client.create_chat_model", return_value=MagicMock()),
patch("deerflow.client._build_middlewares", return_value=[]),
patch("deerflow.client.build_middlewares", return_value=[]),
patch("deerflow.client.apply_prompt_template", return_value=""),
patch("deerflow.client.DeerFlowClient._get_tools", return_value=[]),
):

14
backend/tests/test_client.py
View File

@ -910,7 +910,7 @@ class TestEnsureAgent:
with (
patch("deerflow.client.create_chat_model"),
patch("deerflow.client.create_agent", return_value=mock_agent),
patch("deerflow.client._build_middlewares", return_value=[]) as mock_build_middlewares,
patch("deerflow.client.build_middlewares", return_value=[]) as mock_build_middlewares,
patch("deerflow.client.apply_prompt_template", return_value="prompt") as mock_apply_prompt,
patch.object(client, "_get_tools", return_value=[]),
patch("deerflow.runtime.checkpointer.get_checkpointer", return_value=MagicMock()),
@ -935,7 +935,7 @@ class TestEnsureAgent:
with (
patch("deerflow.client.create_chat_model"),
patch("deerflow.client.create_agent", return_value=mock_agent) as mock_create_agent,
patch("deerflow.client._build_middlewares", return_value=[]),
patch("deerflow.client.build_middlewares", return_value=[]),
patch("deerflow.client.apply_prompt_template", return_value="prompt"),
patch.object(client, "_get_tools", return_value=[]),
patch("deerflow.runtime.checkpointer.get_checkpointer", return_value=mock_checkpointer),
@ -960,7 +960,7 @@ class TestEnsureAgent:
with (
patch("deerflow.client.create_chat_model"),
patch("deerflow.client.create_agent", return_value=mock_agent) as mock_create_agent,
patch("deerflow.client._build_middlewares", side_effect=fake_build_middlewares),
patch("deerflow.client.build_middlewares", side_effect=fake_build_middlewares),
patch("deerflow.client.apply_prompt_template", return_value="prompt"),
patch.object(client, "_get_tools", return_value=[]),
patch("deerflow.runtime.checkpointer.get_checkpointer", return_value=MagicMock()),
@ -979,7 +979,7 @@ class TestEnsureAgent:
with (
patch("deerflow.client.create_chat_model"),
patch("deerflow.client.create_agent", return_value=mock_agent) as mock_create_agent,
patch("deerflow.client._build_middlewares", return_value=[]),
patch("deerflow.client.build_middlewares", return_value=[]),
patch("deerflow.client.apply_prompt_template", return_value="prompt"),
patch.object(client, "_get_tools", return_value=[]),
patch("deerflow.runtime.checkpointer.get_checkpointer", return_value=None),
@ -1957,7 +1957,7 @@ class TestScenarioAgentRecreation:
with (
patch("deerflow.client.create_chat_model"),
patch("deerflow.client.create_agent", side_effect=fake_create_agent),
patch("deerflow.client._build_middlewares", return_value=[]),
patch("deerflow.client.build_middlewares", return_value=[]),
patch("deerflow.client.apply_prompt_template", return_value="prompt"),
patch.object(client, "_get_tools", return_value=[]),
patch("deerflow.runtime.checkpointer.get_checkpointer", return_value=MagicMock()),
@ -1985,7 +1985,7 @@ class TestScenarioAgentRecreation:
with (
patch("deerflow.client.create_chat_model"),
patch("deerflow.client.create_agent", side_effect=fake_create_agent),
patch("deerflow.client._build_middlewares", return_value=[]),
patch("deerflow.client.build_middlewares", return_value=[]),
patch("deerflow.client.apply_prompt_template", return_value="prompt"),
patch.object(client, "_get_tools", return_value=[]),
patch("deerflow.runtime.checkpointer.get_checkpointer", return_value=MagicMock()),
@ -2010,7 +2010,7 @@ class TestScenarioAgentRecreation:
with (
patch("deerflow.client.create_chat_model"),
patch("deerflow.client.create_agent", side_effect=fake_create_agent),
patch("deerflow.client._build_middlewares", return_value=[]),
patch("deerflow.client.build_middlewares", return_value=[]),
patch("deerflow.client.apply_prompt_template", return_value="prompt"),
patch.object(client, "_get_tools", return_value=[]),
patch("deerflow.runtime.checkpointer.get_checkpointer", return_value=MagicMock()),

4
backend/tests/test_client_e2e.py
View File

@ -144,14 +144,14 @@ def e2e_env(tmp_path, monkeypatch):
# non-determinism and cost to E2E tests (title generation is already
# disabled via TitleConfig above, but the middleware still participates
# in the chain and can interfere with event ordering).
from deerflow.agents.lead_agent.agent import _build_middlewares as _original_build_middlewares
from deerflow.agents.lead_agent.agent import build_middlewares as _original_build_middlewares
from deerflow.agents.middlewares.title_middleware import TitleMiddleware
def _sync_safe_build_middlewares(*args, **kwargs):
mws = _original_build_middlewares(*args, **kwargs)
return [m for m in mws if not isinstance(m, TitleMiddleware)]
monkeypatch.setattr("deerflow.client._build_middlewares", _sync_safe_build_middlewares)
monkeypatch.setattr("deerflow.client.build_middlewares", _sync_safe_build_middlewares)
return {"tmp_path": tmp_path}

18
backend/tests/test_lead_agent_model_resolution.py
View File

@ -56,7 +56,7 @@ def test_make_lead_agent_attaches_tracing_callbacks_at_graph_root(monkeypatch):
monkeypatch.setattr(lead_agent_module, "get_app_config", lambda: app_config)
monkeypatch.setattr(tools_module, "get_available_tools", lambda **kwargs: [])
monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
sentinel_handler = object()
monkeypatch.setattr(lead_agent_module, "build_tracing_callbacks", lambda: [sentinel_handler])
@ -94,7 +94,7 @@ def test_internal_make_lead_agent_uses_explicit_app_config(monkeypatch):
monkeypatch.setattr(lead_agent_module, "get_app_config", _raise_get_app_config)
monkeypatch.setattr(tools_module, "get_available_tools", lambda **kwargs: [])
monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
captured: dict[str, object] = {}
@ -128,7 +128,7 @@ def test_make_lead_agent_uses_runtime_app_config_from_context_without_global_rea
monkeypatch.setattr(lead_agent_module, "get_app_config", _raise_get_app_config)
monkeypatch.setattr(tools_module, "get_available_tools", lambda **kwargs: [])
monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
captured: dict[str, object] = {}
@ -207,7 +207,7 @@ def test_make_lead_agent_disables_thinking_when_model_does_not_support_it(monkey
monkeypatch.setattr(lead_agent_module, "get_app_config", lambda: app_config)
monkeypatch.setattr(tools_module, "get_available_tools", lambda **kwargs: [])
monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
captured: dict[str, object] = {}
@ -251,7 +251,7 @@ def test_make_lead_agent_reads_runtime_options_from_context(monkeypatch):
get_available_tools = MagicMock(return_value=[])
monkeypatch.setattr(lead_agent_module, "get_app_config", lambda: app_config)
monkeypatch.setattr(tools_module, "get_available_tools", get_available_tools)
monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "build_middlewares", lambda config, model_name, agent_name=None, **kwargs: [])
captured: dict[str, object] = {}
@ -328,7 +328,7 @@ def test_build_middlewares_uses_resolved_model_name_for_vision(monkeypatch):
monkeypatch.setattr(lead_agent_module, "_create_summarization_middleware", lambda **kwargs: None)
monkeypatch.setattr(lead_agent_module, "_create_todo_list_middleware", lambda is_plan_mode: None)
middlewares = lead_agent_module._build_middlewares(
middlewares = lead_agent_module.build_middlewares(
{"configurable": {"model_name": "stale-model", "is_plan_mode": False, "subagent_enabled": False}},
model_name="vision-model",
custom_middlewares=[MagicMock()],
@ -374,7 +374,7 @@ def test_build_middlewares_passes_explicit_app_config_to_shared_factory(monkeypa
lambda agent_name=None, *, memory_config: captured.setdefault("memory_config", memory_config) or "memory-middleware",
)
middlewares = lead_agent_module._build_middlewares(
middlewares = lead_agent_module.build_middlewares(
{"configurable": {"is_plan_mode": False, "subagent_enabled": False}},
model_name="safe-model",
app_config=app_config,
@ -407,7 +407,7 @@ def test_build_middlewares_uses_loop_detection_config(monkeypatch):
monkeypatch.setattr(lead_agent_module, "_create_summarization_middleware", lambda *, app_config=None: None)
monkeypatch.setattr(lead_agent_module, "_create_todo_list_middleware", lambda is_plan_mode: None)
middlewares = lead_agent_module._build_middlewares(
middlewares = lead_agent_module.build_middlewares(
{"configurable": {"is_plan_mode": False, "subagent_enabled": False}},
model_name="safe-model",
app_config=app_config,
@ -433,7 +433,7 @@ def test_build_middlewares_omits_loop_detection_when_disabled(monkeypatch):
monkeypatch.setattr(lead_agent_module, "_create_summarization_middleware", lambda *, app_config=None: None)
monkeypatch.setattr(lead_agent_module, "_create_todo_list_middleware", lambda is_plan_mode: None)
middlewares = lead_agent_module._build_middlewares(
middlewares = lead_agent_module.build_middlewares(
{"configurable": {"is_plan_mode": False, "subagent_enabled": False}},
model_name="safe-model",
app_config=app_config,

8
backend/tests/test_lead_agent_skills.py
View File

@ -139,7 +139,7 @@ def test_make_lead_agent_empty_skills_passed_correctly(monkeypatch):
monkeypatch.setattr(lead_agent_module, "create_chat_model", lambda **kwargs: "model")
monkeypatch.setattr("deerflow.tools.get_available_tools", lambda **kwargs: [])
monkeypatch.setattr(lead_agent_module, "_load_enabled_skills_for_tool_policy", lambda available_skills, *, app_config: [])
monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda *args, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "build_middlewares", lambda *args, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "create_agent", lambda **kwargs: kwargs)
class MockModelConfig:
@ -180,7 +180,7 @@ def test_make_lead_agent_filters_tools_from_available_skills(monkeypatch):
monkeypatch.setattr(lead_agent_module, "_resolve_model_name", lambda x=None, **kwargs: "default-model")
monkeypatch.setattr(lead_agent_module, "create_chat_model", lambda **kwargs: "model")
monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda *args, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "build_middlewares", lambda *args, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "apply_prompt_template", lambda **kwargs: "mock_prompt")
monkeypatch.setattr(lead_agent_module, "create_agent", lambda **kwargs: kwargs)
monkeypatch.setattr(lead_agent_module, "load_agent_config", lambda x: AgentConfig(name="test", skills=["restricted", "legacy"]))
@ -203,7 +203,7 @@ def test_make_lead_agent_all_legacy_skills_preserve_all_tools(monkeypatch):
monkeypatch.setattr(lead_agent_module, "_resolve_model_name", lambda x=None, **kwargs: "default-model")
monkeypatch.setattr(lead_agent_module, "create_chat_model", lambda **kwargs: "model")
monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda *args, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "build_middlewares", lambda *args, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "apply_prompt_template", lambda **kwargs: "mock_prompt")
monkeypatch.setattr(lead_agent_module, "create_agent", lambda **kwargs: kwargs)
monkeypatch.setattr(lead_agent_module, "load_agent_config", lambda x: AgentConfig(name="test", skills=None))
@ -227,7 +227,7 @@ def test_make_lead_agent_enforces_allowed_tools_when_skill_cache_is_cold(monkeyp
monkeypatch.setattr(lead_agent_module, "_resolve_model_name", lambda x=None, **kwargs: "default-model")
monkeypatch.setattr(lead_agent_module, "create_chat_model", lambda **kwargs: "model")
monkeypatch.setattr(lead_agent_module, "_build_middlewares", lambda *args, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "build_middlewares", lambda *args, **kwargs: [])
monkeypatch.setattr(lead_agent_module, "apply_prompt_template", lambda **kwargs: "mock_prompt")
monkeypatch.setattr(lead_agent_module, "create_agent", lambda **kwargs: kwargs)
monkeypatch.setattr(lead_agent_module, "load_agent_config", lambda x: AgentConfig(name="test", skills=["restricted"]))

2
frontend/src/content/en/harness/middlewares.mdx
View File

@ -218,4 +218,4 @@ class MyMiddleware(AgentMiddleware):
return state, config
```
Custom middlewares are passed to `make_lead_agent` via the `custom_middlewares` parameter in `_build_middlewares`. They are injected immediately before `ClarificationMiddleware` at the end of the chain.
Custom middlewares are passed to `make_lead_agent` via the `custom_middlewares` parameter in `build_middlewares`. They are injected immediately before `ClarificationMiddleware` at the end of the chain.

4
scripts/tool-error-degradation-detection.sh
View File

@ -35,7 +35,7 @@ from requests.exceptions import SSLError
from langchain.agents.middleware import AgentMiddleware
from langchain_core.messages import ToolMessage
from deerflow.agents.lead_agent.agent import _build_middlewares
from deerflow.agents.lead_agent.agent import build_middlewares
from deerflow.config import get_app_config
from deerflow.sandbox.middleware import SandboxMiddleware
@ -188,7 +188,7 @@ if not model_name:
print("[FAIL] No model configured; cannot evaluate lead middleware chain.")
raise SystemExit(8)
lead_middlewares = _build_middlewares({"configurable": {}}, model_name=model_name)
lead_middlewares = build_middlewares({"configurable": {}}, model_name=model_name)
sub_middlewares = _build_sub_middlewares()
print("[STEP 3] Simulate two sequential tool calls and check whether conversation flow aborts.")