mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-06-10 09:25:57 +00:00
fix(tool-search): reliably hide deferred MCP schemas by removing the ContextVar (closures + graph state) (#3342)
* feat(tool-search): add hash-scoped promoted state to ThreadState * feat(tool-search): add immutable DeferredToolCatalog with stable hash * feat(tool-search): add build_deferred_tool_setup + Command-writing tool_search * refactor(tool-search): replace deferred-tool ContextVar with closures + graph state (#3272) Build the deferred catalog + tool_search tool per agent from the policy-filtered tool list (after skill allowed-tools), pass deferred_names + catalog_hash explicitly to DeferredToolFilterMiddleware and the prompt, and record promotions in ThreadState.promoted (scoped by catalog_hash) via a Command-returning tool_search. Removes DeferredToolRegistry and the _registry_var ContextVar so deferral no longer depends on build/execute sharing an async context. MCP tools are tagged with metadata[deerflow_mcp]; client.py assembles deferral the same way. Catalog is built AFTER tool-policy filtering (no policy-excluded tool can leak via tool_search) and assembly is fail-closed. Migrate tests off the deleted registry APIs; delete the obsolete ContextVar-based #2884 regression (re-covered by state-based tests in a follow-up). * test(tool-search): lock tool_search promotion into next model turn via graph state * test(tool-search): cross-context, policy-leak, fail-closed, #2884 isolation regressions * test(tool-search): align real-LLM e2e with closure-based deferred setup * docs: update DeferredToolFilterMiddleware description for closure+state design * style(tests): drop unused import in test_deferred_setup (ruff) * test(tool-search): harden merge_promoted + replace tautological catalog test From independent code review: - merge_promoted: use existing.get("catalog_hash") so a forward-incompatible or externally-injected persisted promoted dict triggers a replace instead of a KeyError crash; add regression test for the malformed-existing case. - test_deferred_catalog: replace the `== [] or True` tautology (a test that could never fail) with a deterministic invalid-regex->literal-fallback check (positive match on calc + negative empty match). - DeferredToolCatalog: comment why frozen-without-slots is required for the cached_property hash/names fields (adding slots=True would break them). * fix(tool-search): read tool_search.enabled from self._app_config in client DeerFlowClient._ensure_agent called get_app_config() directly to read tool_search.enabled, but the client already resolves and stores its config as self._app_config at construction (and uses it everywhere else). The bare call re-resolves config from disk at agent-build time, which raises FileNotFoundError in environments without a config.yaml (CI) — test_client.py's fixture only patches get_app_config during __init__, so the later call hit the real loader. Use self._app_config, matching the rest of the client. * test(tool-search): lock tool_search post-policy append ordering tool_search is appended after skill-allowlist filtering, so the allowlist can no longer deny it by name. Lock the intended contract: it only appears when allowed MCP tools survive the filter, and its catalog (derived from the already policy-filtered list) can never expose a denied tool. Addresses the ordering observation from the Copilot review on #3342.
This commit is contained in:
@@ -270,6 +270,7 @@ def _build_middlewares(
|
||||
custom_middlewares: list[AgentMiddleware] | None = None,
|
||||
*,
|
||||
app_config: AppConfig | None = None,
|
||||
deferred_setup=None,
|
||||
):
|
||||
"""Build middleware chain based on runtime configuration.
|
||||
|
||||
@@ -318,11 +319,13 @@ def _build_middlewares(
|
||||
if model_config is not None and model_config.supports_vision:
|
||||
middlewares.append(ViewImageMiddleware())
|
||||
|
||||
# Add DeferredToolFilterMiddleware to hide deferred tool schemas from model binding
|
||||
if resolved_app_config.tool_search.enabled:
|
||||
# Hide deferred tool schemas from model binding until tool_search promotes them.
|
||||
# The deferred set + catalog hash come from the build-time setup (assembled
|
||||
# after tool-policy filtering); promotion is read from graph state.
|
||||
if deferred_setup is not None and deferred_setup.deferred_names:
|
||||
from deerflow.agents.middlewares.deferred_tool_filter_middleware import DeferredToolFilterMiddleware
|
||||
|
||||
middlewares.append(DeferredToolFilterMiddleware())
|
||||
middlewares.append(DeferredToolFilterMiddleware(deferred_setup.deferred_names, deferred_setup.catalog_hash))
|
||||
|
||||
# Add SubagentLimitMiddleware to truncate excess parallel task calls
|
||||
subagent_enabled = cfg.get("subagent_enabled", False)
|
||||
@@ -353,6 +356,23 @@ def _build_middlewares(
|
||||
return middlewares
|
||||
|
||||
|
||||
def _assemble_deferred(filtered_tools, *, enabled: bool):
|
||||
"""Build the final tool list + deferred setup from a policy-filtered list.
|
||||
|
||||
Call AFTER tool-policy filtering so the deferred catalog never exposes a
|
||||
tool the agent is not allowed to use. Fail-closed: if tool_search is enabled
|
||||
and MCP tools survived filtering but no deferred set was recovered, raise
|
||||
rather than silently binding their full schemas to the model.
|
||||
"""
|
||||
from deerflow.tools.builtins.tool_search import _is_mcp_tool, build_deferred_tool_setup
|
||||
|
||||
setup = build_deferred_tool_setup(filtered_tools, enabled=enabled)
|
||||
if enabled and not setup.deferred_names and any(_is_mcp_tool(t) for t in filtered_tools):
|
||||
raise RuntimeError("tool_search enabled and MCP tools survived policy filtering, but no deferred set was recovered — refusing to bind MCP schemas (fail-closed).")
|
||||
final_tools = list(filtered_tools) + ([setup.tool_search_tool] if setup.tool_search_tool else [])
|
||||
return final_tools, setup
|
||||
|
||||
|
||||
def _available_skill_names(agent_config, is_bootstrap: bool) -> set[str] | None:
|
||||
if is_bootstrap:
|
||||
return {"bootstrap"}
|
||||
@@ -460,16 +480,19 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
|
||||
|
||||
if is_bootstrap:
|
||||
# Special bootstrap agent with minimal prompt for initial custom agent creation flow
|
||||
tools = get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled, app_config=resolved_app_config) + [setup_agent]
|
||||
raw_tools = get_available_tools(model_name=model_name, subagent_enabled=subagent_enabled, app_config=resolved_app_config) + [setup_agent]
|
||||
filtered = filter_tools_by_skill_allowed_tools(raw_tools, skills_for_tool_policy)
|
||||
final_tools, setup = _assemble_deferred(filtered, enabled=resolved_app_config.tool_search.enabled)
|
||||
return create_agent(
|
||||
model=create_chat_model(name=model_name, thinking_enabled=thinking_enabled, app_config=resolved_app_config, attach_tracing=False),
|
||||
tools=filter_tools_by_skill_allowed_tools(tools, skills_for_tool_policy),
|
||||
middleware=_build_middlewares(config, model_name=model_name, app_config=resolved_app_config),
|
||||
tools=final_tools,
|
||||
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,
|
||||
available_skills=set(["bootstrap"]),
|
||||
app_config=resolved_app_config,
|
||||
deferred_names=setup.deferred_names,
|
||||
),
|
||||
state_schema=ThreadState,
|
||||
)
|
||||
@@ -478,17 +501,20 @@ def _make_lead_agent(config: RunnableConfig, *, app_config: AppConfig):
|
||||
# The default agent (no agent_name) does not see this tool.
|
||||
extra_tools = [update_agent] if agent_name else []
|
||||
# Default lead agent (unchanged behavior)
|
||||
tools = get_available_tools(model_name=model_name, groups=agent_config.tool_groups if agent_config else None, subagent_enabled=subagent_enabled, app_config=resolved_app_config)
|
||||
raw_tools = get_available_tools(model_name=model_name, groups=agent_config.tool_groups if agent_config else None, subagent_enabled=subagent_enabled, app_config=resolved_app_config)
|
||||
filtered = filter_tools_by_skill_allowed_tools(raw_tools + extra_tools, skills_for_tool_policy)
|
||||
final_tools, setup = _assemble_deferred(filtered, enabled=resolved_app_config.tool_search.enabled)
|
||||
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=filter_tools_by_skill_allowed_tools(tools + extra_tools, skills_for_tool_policy),
|
||||
middleware=_build_middlewares(config, model_name=model_name, agent_name=agent_name, app_config=resolved_app_config),
|
||||
tools=final_tools,
|
||||
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,
|
||||
agent_name=agent_name,
|
||||
available_skills=set(agent_config.skills) if agent_config and agent_config.skills is not None else None,
|
||||
app_config=resolved_app_config,
|
||||
deferred_names=setup.deferred_names,
|
||||
),
|
||||
state_schema=ThreadState,
|
||||
)
|
||||
|
||||
@@ -684,33 +684,16 @@ Rules:
|
||||
"""
|
||||
|
||||
|
||||
def get_deferred_tools_prompt_section(*, app_config: AppConfig | None = None) -> str:
|
||||
"""Generate <available-deferred-tools> block for the system prompt.
|
||||
def get_deferred_tools_prompt_section(*, deferred_names: frozenset[str] = frozenset()) -> str:
|
||||
"""Generate <available-deferred-tools> from an explicit deferred-name set.
|
||||
|
||||
Lists only deferred tool names so the agent knows what exists
|
||||
and can use tool_search to load them.
|
||||
Returns empty string when tool_search is disabled or no tools are deferred.
|
||||
Lists only names so the agent knows what exists and can use tool_search to
|
||||
load them. Returns empty string when there are no deferred tools. The set is
|
||||
computed at agent build time (after tool-policy filtering) and passed in.
|
||||
"""
|
||||
from deerflow.tools.builtins.tool_search import get_deferred_registry
|
||||
|
||||
if app_config is None:
|
||||
try:
|
||||
from deerflow.config import get_app_config
|
||||
|
||||
config = get_app_config()
|
||||
except Exception:
|
||||
return ""
|
||||
else:
|
||||
config = app_config
|
||||
|
||||
if not config.tool_search.enabled:
|
||||
if not deferred_names:
|
||||
return ""
|
||||
|
||||
registry = get_deferred_registry()
|
||||
if not registry:
|
||||
return ""
|
||||
|
||||
names = "\n".join(e.name for e in registry.entries)
|
||||
names = "\n".join(sorted(deferred_names))
|
||||
return f"<available-deferred-tools>\n{names}\n</available-deferred-tools>"
|
||||
|
||||
|
||||
@@ -772,6 +755,7 @@ def apply_prompt_template(
|
||||
agent_name: str | None = None,
|
||||
available_skills: set[str] | None = None,
|
||||
app_config: AppConfig | None = None,
|
||||
deferred_names: frozenset[str] = frozenset(),
|
||||
) -> str:
|
||||
# Include subagent section only if enabled (from runtime parameter)
|
||||
n = max_concurrent_subagents
|
||||
@@ -799,7 +783,7 @@ def apply_prompt_template(
|
||||
skills_section = get_skills_prompt_section(available_skills, app_config=app_config)
|
||||
|
||||
# Get deferred tools section (tool_search)
|
||||
deferred_tools_section = get_deferred_tools_prompt_section(app_config=app_config)
|
||||
deferred_tools_section = get_deferred_tools_prompt_section(deferred_names=deferred_names)
|
||||
|
||||
# Build ACP agent section only if ACP agents are configured
|
||||
acp_section = _build_acp_section(app_config=app_config)
|
||||
|
||||
+39
-34
@@ -1,12 +1,15 @@
|
||||
"""Middleware to filter deferred tool schemas from model binding.
|
||||
|
||||
When tool_search is enabled, MCP tools are registered in the DeferredToolRegistry
|
||||
and passed to ToolNode for execution, but their schemas should NOT be sent to the
|
||||
LLM via bind_tools (that's the whole point of deferral — saving context tokens).
|
||||
When tool_search is enabled, MCP tools are still passed to ToolNode for
|
||||
execution, but their schemas must NOT be sent to the LLM via bind_tools until
|
||||
the model has discovered them via tool_search. This middleware removes the
|
||||
still-deferred tools from request.tools before model binding, and blocks tool
|
||||
calls to tools that have not been promoted yet.
|
||||
|
||||
This middleware intercepts wrap_model_call and removes deferred tools from
|
||||
request.tools so that model.bind_tools only receives active tool schemas.
|
||||
The agent discovers deferred tools at runtime via the tool_search tool.
|
||||
The deferred name set and the catalog hash are injected at construction time
|
||||
(no ContextVar). Promotion state is read from graph state (``state["promoted"]``),
|
||||
scoped by catalog hash so a stale persisted promotion cannot expose a renamed
|
||||
or drifted tool.
|
||||
"""
|
||||
|
||||
import logging
|
||||
@@ -24,47 +27,49 @@ logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class DeferredToolFilterMiddleware(AgentMiddleware[AgentState]):
|
||||
"""Remove deferred tools from request.tools before model binding.
|
||||
"""Hide deferred tool schemas from the bound model until promoted.
|
||||
|
||||
ToolNode still holds all tools (including deferred) for execution routing,
|
||||
but the LLM only sees active tool schemas — deferred tools are discoverable
|
||||
via tool_search at runtime.
|
||||
but the LLM only sees active tool schemas plus tools that have already been
|
||||
promoted (recorded in ``state["promoted"]`` under the current catalog hash).
|
||||
"""
|
||||
|
||||
def __init__(self, deferred_names: frozenset[str], catalog_hash: str | None):
|
||||
super().__init__()
|
||||
self._deferred = deferred_names
|
||||
self._catalog_hash = catalog_hash
|
||||
|
||||
def _promoted(self, state) -> set[str]:
|
||||
promoted = (state or {}).get("promoted")
|
||||
if promoted and promoted.get("catalog_hash") == self._catalog_hash:
|
||||
return set(promoted.get("names") or [])
|
||||
return set()
|
||||
|
||||
def _hidden(self, state) -> set[str]:
|
||||
return set(self._deferred) - self._promoted(state)
|
||||
|
||||
def _filter_tools(self, request: ModelRequest) -> ModelRequest:
|
||||
from deerflow.tools.builtins.tool_search import get_deferred_registry
|
||||
|
||||
registry = get_deferred_registry()
|
||||
if not registry:
|
||||
if not self._deferred:
|
||||
return request
|
||||
|
||||
deferred_names = registry.deferred_names
|
||||
active_tools = [t for t in request.tools if getattr(t, "name", None) not in deferred_names]
|
||||
|
||||
if len(active_tools) < len(request.tools):
|
||||
logger.debug(f"Filtered {len(request.tools) - len(active_tools)} deferred tool schema(s) from model binding")
|
||||
|
||||
return request.override(tools=active_tools)
|
||||
hide = self._hidden(request.state)
|
||||
if not hide:
|
||||
return request
|
||||
active = [t for t in request.tools if getattr(t, "name", None) not in hide]
|
||||
if len(active) < len(request.tools):
|
||||
logger.debug("Filtered %d deferred tool schema(s) from model binding", len(request.tools) - len(active))
|
||||
return request.override(tools=active)
|
||||
|
||||
def _blocked_tool_message(self, request: ToolCallRequest) -> ToolMessage | None:
|
||||
from deerflow.tools.builtins.tool_search import get_deferred_registry
|
||||
|
||||
registry = get_deferred_registry()
|
||||
if not registry:
|
||||
if not self._deferred:
|
||||
return None
|
||||
|
||||
tool_name = str(request.tool_call.get("name") or "")
|
||||
if not tool_name:
|
||||
name = str(request.tool_call.get("name") or "")
|
||||
if not name or name not in self._hidden(request.state):
|
||||
return None
|
||||
|
||||
if not registry.contains(tool_name):
|
||||
return None
|
||||
|
||||
tool_call_id = str(request.tool_call.get("id") or "missing_tool_call_id")
|
||||
return ToolMessage(
|
||||
content=(f"Error: Tool '{tool_name}' is deferred and has not been promoted yet. Call tool_search first to expose and promote this tool's schema, then retry."),
|
||||
content=(f"Error: Tool '{name}' is deferred and has not been promoted yet. Call tool_search first to expose and promote this tool's schema, then retry."),
|
||||
tool_call_id=tool_call_id,
|
||||
name=tool_name,
|
||||
name=name,
|
||||
status="error",
|
||||
)
|
||||
|
||||
|
||||
@@ -58,6 +58,32 @@ def merge_todos(existing: list | None, new: list | None) -> list | None:
|
||||
return new
|
||||
|
||||
|
||||
class PromotedTools(TypedDict):
|
||||
catalog_hash: str
|
||||
names: list[str]
|
||||
|
||||
|
||||
def merge_promoted(existing: PromotedTools | None, new: PromotedTools | None) -> PromotedTools | None:
|
||||
"""Reducer for deferred-tool promotions, scoped by catalog hash.
|
||||
|
||||
- new None/empty -> preserve existing (node didn't touch promotions).
|
||||
- catalog_hash changed -> replace wholesale, dropping stale names (prevents a
|
||||
persisted bare name from exposing a different tool after catalog drift).
|
||||
- same catalog_hash -> union names, dedupe, preserve order.
|
||||
"""
|
||||
if not new:
|
||||
return existing
|
||||
if existing is None or existing.get("catalog_hash") != new["catalog_hash"]:
|
||||
return {
|
||||
"catalog_hash": new["catalog_hash"],
|
||||
"names": list(dict.fromkeys(new["names"])),
|
||||
}
|
||||
return {
|
||||
"catalog_hash": existing["catalog_hash"],
|
||||
"names": list(dict.fromkeys(existing["names"] + new["names"])),
|
||||
}
|
||||
|
||||
|
||||
class ThreadState(AgentState):
|
||||
sandbox: NotRequired[SandboxState | None]
|
||||
thread_data: NotRequired[ThreadDataState | None]
|
||||
@@ -66,3 +92,4 @@ class ThreadState(AgentState):
|
||||
todos: Annotated[list | None, merge_todos]
|
||||
uploaded_files: NotRequired[list[dict] | None]
|
||||
viewed_images: Annotated[dict[str, ViewedImageData], merge_viewed_images] # image_path -> {base64, mime_type}
|
||||
promoted: Annotated[PromotedTools | None, merge_promoted]
|
||||
|
||||
Reference in New Issue
Block a user