mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-08-08 05:48:53 +00:00
* feat(extensions): add middleware plugin foundation * fix(extensions): stop config resolution from masking extension loading `create_app()` resolved the configured plugin list inside the fail-open guard around `load_extensions()`. CI has no `config.yaml` (gitignored and never generated by the workflow), so `get_app_config()` raised `FileNotFoundError` there and was swallowed as an extension failure -- `load_extensions()` never ran at all, and the four `create_app()` tests in `test_extension_app_loading.py` passed locally but failed on every runner. Resolve the plugin list before the guard. Only an absent `config.yaml` is tolerated, mirroring `_resolve_trace_enabled_for_app_construction()`: `create_app()` runs at import time, and lifespan still performs strict config loading before serving. A `config.yaml` that exists but fails to parse or validate now propagates instead of being reported as an extension failure -- reporting it as the latter silently dropped a `required: true` extension rather than failing the boot. Make the tests config-independent with an autouse `stub_app_config` fixture, following the existing pattern in `test_gateway_lifespan_shutdown.py`, and cover both new branches of the config-resolution boundary. * fix(extensions): bind the run's extension snapshot through subagent delegation The lead-agent path resolves one immutable loaded-extension snapshot per run and binds it through task-store allocation and graph construction, but the subagent path re-read the process-wide singleton at execution time. In production both are the same object, yet a `set_loaded_extensions()` between the lead run's start and a subagent's execution (test teardown, a future hot-reload path) would let one run mix two extension generations — exactly what the documented invariant exists to prevent. The graph-build binding is a ContextVar scoped to synchronous construction, so it has already exited by the time a tool delegates; the snapshot has to travel through runtime context instead. The run worker publishes it under the host-internal `EXTENSION_SNAPSHOT_CONTEXT_KEY` (written after the caller merge, popped when the run has none, so a caller-supplied value is never authoritative), `task_tool` reads it back through the type-checking `resolve_run_extensions()`, and `SubagentExecutor` binds it at construction. Callers outside the Gateway run path — embedded `DeerFlowClient`, standalone LangGraph Server — install no snapshot and keep the existing `get_loaded_extensions()` fallback. * refactor(extensions): defer the ordering table by call, not by a lying tuple `CORE_ORDERING_CONSTRAINTS` was a `tuple` subclass that overrode only `__iter__` and resolved into a class-level `_resolved` side channel. A tuple cannot populate its own storage after construction, so the instance stayed the empty tuple it was built as: `len()` was 0, `bool()` was False, `in` was always False, indexing raised, slicing and `reversed()` came back empty, and it compared unequal to the plain tuples tests substitute for it — all while iteration yielded the real constraints. Only `assert_ordering` consumed it, and only by iterating, so the split went unnoticed. The sibling `_AnchorTable(dict)` uses the same idea soundly because dict is mutable: `self.update()` fills the real storage, making every inherited operation correct. That trick does not survive the port to an immutable type. Replace it with `core_ordering_constraints()`, matching how `stack.py` defers the same kind of table via `_anchors()`. The deferral is kept — it is about dependency direction, not just cycles: `extensions/` is the layer the middleware layer calls into, so a module-scope `agents.middlewares` import here points the dependency backwards and closes a cycle as soon as any middleware imports something under `extensions/` at module level. Resolution stays at `assert_ordering` time, which already runs inside the middleware builder. Tests pin both halves: the returned value is a plain tuple whose len/bool/ membership/indexing/reversal/equality agree with iteration, and a subprocess probe asserts importing `extensions.ordering` does not load the middleware layer while calling the function does.
215 lines
7.5 KiB
Python
215 lines
7.5 KiB
Python
"""Tests for the extension contract surface.
|
|
|
|
The contracts carry two compatibility promises that are easy to break by
|
|
accident and impossible to catch at runtime later: every Protocol method has a
|
|
default implementation, and every optional dataclass field has a default. Both
|
|
are asserted here.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import dataclasses
|
|
import importlib.resources
|
|
import inspect
|
|
|
|
import pytest
|
|
from deerflow_extension_api import (
|
|
API_VERSION,
|
|
AgentBuildContext,
|
|
AgentScope,
|
|
ExtensionData,
|
|
ExtensionInstall,
|
|
ExtensionRegistry,
|
|
HostPolicySnapshot,
|
|
MiddlewareContributor,
|
|
MiddlewarePlacement,
|
|
Placement,
|
|
extension,
|
|
)
|
|
from deerflow_extension_api.runtime_bridge import (
|
|
EXTENSION_TASK_STORE_KEY,
|
|
task_store_from_runtime,
|
|
)
|
|
|
|
|
|
def test_placement_members_cover_both_axes():
|
|
assert Placement.MODEL_LOGICAL.value == "model_logical"
|
|
assert Placement.MODEL_PHYSICAL.value == "model_physical"
|
|
assert Placement.TOOL_VISIBLE.value == "tool_visible"
|
|
assert Placement.TOOL_RAW.value == "tool_raw"
|
|
assert Placement.STANDARD.value == "standard"
|
|
|
|
|
|
def test_agent_scope_both_is_union():
|
|
assert AgentScope.BOTH == AgentScope.LEAD | AgentScope.SUBAGENT
|
|
assert AgentScope.LEAD in AgentScope.BOTH
|
|
|
|
|
|
def test_middleware_placement_defaults():
|
|
p = MiddlewarePlacement(middleware=object(), placement=Placement.STANDARD)
|
|
assert p.scope is AgentScope.BOTH
|
|
assert p.order == 0
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"cls",
|
|
[
|
|
HostPolicySnapshot,
|
|
AgentBuildContext,
|
|
MiddlewarePlacement,
|
|
],
|
|
)
|
|
def test_every_dataclass_is_frozen(cls):
|
|
assert dataclasses.is_dataclass(cls)
|
|
assert cls.__dataclass_params__.frozen, f"{cls.__name__} must be frozen"
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"cls",
|
|
[HostPolicySnapshot],
|
|
)
|
|
def test_additive_dataclasses_are_constructible_with_required_fields_only(cls):
|
|
"""Fields added later must carry defaults, or old extensions break on upgrade.
|
|
|
|
HostPolicySnapshot is host-constructed and fully optional.
|
|
AgentBuildContext gets its own dedicated test below because its scope is
|
|
legitimately required.
|
|
"""
|
|
assert cls() is not None
|
|
|
|
|
|
def test_agent_build_context_optional_fields_keep_their_defaults():
|
|
"""AgentBuildContext has one required field (scope); the rest must default.
|
|
|
|
Unlike the fully-optional dataclasses above, scope is legitimately
|
|
required, so this is not folded into the parametrized test above — it
|
|
would misrepresent the required/optional split this suite is meant to
|
|
document.
|
|
"""
|
|
ctx = AgentBuildContext(scope=AgentScope.LEAD)
|
|
assert ctx.agent_name is None
|
|
assert ctx.model_name is None
|
|
assert isinstance(ctx.policy, HostPolicySnapshot)
|
|
|
|
|
|
@pytest.mark.parametrize(
|
|
"protocol",
|
|
[
|
|
ExtensionRegistry,
|
|
MiddlewareContributor,
|
|
],
|
|
)
|
|
def test_every_protocol_method_has_a_default_implementation(protocol):
|
|
"""Adding a method to a Protocol is only additive when it has a default.
|
|
|
|
Without this, shipping a new contract method breaks every already-released
|
|
extension that does not implement it.
|
|
"""
|
|
checked = 0
|
|
for name, member in vars(protocol).items():
|
|
if name.startswith("_") or not inspect.isfunction(member):
|
|
continue
|
|
checked += 1
|
|
body = inspect.getsource(member).split("\n", 1)[1]
|
|
assert "return" in body, f"{protocol.__name__}.{name} has no default implementation. Adding a contract method is only additive when it returns a default; otherwise every already-released extension breaks on upgrade."
|
|
assert checked > 0, f"{protocol.__name__} declared no methods to check"
|
|
|
|
|
|
def test_contributor_defaults_return_empty():
|
|
class _Bare:
|
|
pass
|
|
|
|
bare = _Bare()
|
|
assert MiddlewareContributor.contribute_middlewares(bare, ExtensionData("app"), AgentBuildContext(scope=AgentScope.LEAD)) == ()
|
|
|
|
|
|
def test_future_contribution_points_are_not_advertised_before_the_host_supports_them():
|
|
"""A merged slice must not silently accept registrations it cannot run."""
|
|
import deerflow_extension_api
|
|
|
|
for name in (
|
|
"ExtensionRuntimeDeps",
|
|
"ExtensionService",
|
|
"SystemModelCallObserver",
|
|
"TaskLifecycleContributor",
|
|
):
|
|
assert name not in deerflow_extension_api.__all__
|
|
assert not hasattr(deerflow_extension_api, name)
|
|
|
|
|
|
def test_task_store_from_runtime_reads_the_host_key():
|
|
class _Runtime:
|
|
def __init__(self, context):
|
|
self.context = context
|
|
|
|
store = ExtensionData("task-1")
|
|
assert task_store_from_runtime(_Runtime({EXTENSION_TASK_STORE_KEY: store})) is store
|
|
|
|
|
|
def test_task_store_from_runtime_returns_none_on_missing_or_wrong_shape():
|
|
class _Runtime:
|
|
def __init__(self, context):
|
|
self.context = context
|
|
|
|
assert task_store_from_runtime(None) is None
|
|
assert task_store_from_runtime(_Runtime({})) is None
|
|
assert task_store_from_runtime(_Runtime("not-a-mapping")) is None
|
|
assert task_store_from_runtime(_Runtime({EXTENSION_TASK_STORE_KEY: "wrong type"})) is None
|
|
|
|
|
|
def test_extension_decorator_stamps_api_requirement():
|
|
@extension(api="0.1", name="demo")
|
|
def install(registry, config):
|
|
return None
|
|
|
|
assert install.__deerflow_api__ == "0.1"
|
|
assert install.__deerflow_name__ == "demo"
|
|
|
|
|
|
def test_registry_and_install_alias_are_part_of_the_public_surface():
|
|
"""Independent extensions annotate install(registry, config) against the
|
|
contract package alone — importing the host's concrete registry would pin
|
|
them to the harness release cadence and advertise host-only machinery."""
|
|
import typing
|
|
|
|
import deerflow_extension_api
|
|
|
|
assert "ExtensionRegistry" in deerflow_extension_api.__all__
|
|
assert "ExtensionInstall" in deerflow_extension_api.__all__
|
|
parameters, return_type = typing.get_args(ExtensionInstall)
|
|
assert parameters[0] is ExtensionRegistry, "install()'s first argument must be the public registry contract"
|
|
|
|
|
|
def test_distribution_marks_the_contract_package_as_typed():
|
|
marker = importlib.resources.files("deerflow_extension_api").joinpath("py.typed")
|
|
assert marker.is_file()
|
|
|
|
|
|
def test_harness_pins_the_contract_package_exactly():
|
|
"""The version contract (extension-system design): the host pins the
|
|
contract package exactly, extensions use ranges. A range here would let an
|
|
older harness resolve a newer 1.x contract package — API_VERSION would
|
|
then come from the upgraded package and newer extensions would look
|
|
supported against a host whose registry/placements/hook pipeline still
|
|
implements the older contract. The pin makes pip reject that skew at
|
|
install time."""
|
|
import tomllib
|
|
from importlib.metadata import version
|
|
from pathlib import Path
|
|
|
|
from packaging.requirements import Requirement
|
|
|
|
pyproject = Path(__file__).parent.parent / "packages" / "harness" / "pyproject.toml"
|
|
dependencies = tomllib.loads(pyproject.read_text())["project"]["dependencies"]
|
|
requirement = next(Requirement(dep) for dep in dependencies if Requirement(dep).name == "deerflow-extension-api")
|
|
|
|
expected = f"=={version('deerflow-extension-api')}"
|
|
assert str(requirement.specifier) == expected, f"the host must pin deerflow-extension-api exactly ({expected}); a range lets pip resolve a contract newer than the host implements"
|
|
|
|
|
|
def test_runtime_api_version_matches_the_installed_contract_package():
|
|
"""Every additive contract slice bumps both gates together."""
|
|
from importlib.metadata import version
|
|
|
|
assert API_VERSION == version("deerflow-extension-api")
|