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.
203 lines
6.7 KiB
Python
203 lines
6.7 KiB
Python
"""Gateway app-construction wiring for configured Python extensions."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from deerflow.extensions import reset_loaded_extensions, reset_runtime_diagnostics
|
|
from deerflow.extensions.loader import ExtensionLoadError, ExtensionSpec
|
|
from deerflow.extensions.registry import ExtensionRegistry
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def _reset_extension_process_state():
|
|
reset_loaded_extensions()
|
|
reset_runtime_diagnostics()
|
|
yield
|
|
reset_runtime_diagnostics()
|
|
reset_loaded_extensions()
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def stub_app_config(monkeypatch):
|
|
"""Keep ``create_app()`` independent of a real ``config.yaml``.
|
|
|
|
The repo-root ``config.yaml`` is gitignored and absent on CI runners, so
|
|
reading it here would make these tests pass locally and fail on every run
|
|
in CI. Tests that need a specific plugin list copy this config instead of
|
|
loading one from disk.
|
|
"""
|
|
import app.gateway.app as app_module
|
|
from deerflow.config.app_config import AppConfig
|
|
from deerflow.config.sandbox_config import SandboxConfig
|
|
|
|
config = AppConfig(sandbox=SandboxConfig(use="test"))
|
|
monkeypatch.setattr(app_module, "get_app_config", lambda: config)
|
|
return config
|
|
|
|
|
|
def test_create_app_exposes_loaded_extensions_on_app_state_and_process_singleton(monkeypatch):
|
|
import deerflow.extensions as extensions_module
|
|
|
|
loaded = ExtensionRegistry().build()
|
|
monkeypatch.setattr(
|
|
extensions_module,
|
|
"load_extensions",
|
|
lambda plugins: (loaded, []),
|
|
)
|
|
|
|
from app.gateway.app import create_app
|
|
|
|
app = create_app()
|
|
|
|
assert app.state.extensions is loaded
|
|
assert extensions_module.get_loaded_extensions() is loaded
|
|
|
|
|
|
def test_create_app_exposes_one_canonical_live_diagnostics_list(monkeypatch):
|
|
import deerflow.extensions as extensions_module
|
|
|
|
loaded = ExtensionRegistry().build()
|
|
load_diagnostic = extensions_module.Diagnostic.warning(
|
|
"demo:install",
|
|
"optional extension was skipped",
|
|
)
|
|
monkeypatch.setattr(
|
|
extensions_module,
|
|
"load_extensions",
|
|
lambda plugins: (loaded, [load_diagnostic]),
|
|
)
|
|
|
|
from app.gateway.app import create_app
|
|
|
|
first_app = create_app()
|
|
second_app = create_app()
|
|
runtime_diagnostic = extensions_module.Diagnostic.error(
|
|
"demo:install",
|
|
"middleware observation failed",
|
|
)
|
|
extensions_module.record_runtime_diagnostic(runtime_diagnostic)
|
|
|
|
assert first_app.state.extension_diagnostics is second_app.state.extension_diagnostics
|
|
assert first_app.state.extension_diagnostics == [
|
|
load_diagnostic,
|
|
runtime_diagnostic,
|
|
]
|
|
|
|
|
|
def test_create_app_fails_open_when_extension_loading_raises_unexpectedly(monkeypatch):
|
|
import deerflow.extensions as extensions_module
|
|
|
|
def _raise_unexpectedly(plugins):
|
|
raise RuntimeError("malformed plugins configuration")
|
|
|
|
monkeypatch.setattr(extensions_module, "load_extensions", _raise_unexpectedly)
|
|
|
|
from app.gateway.app import create_app
|
|
|
|
app = create_app()
|
|
|
|
assert app.state.extensions is extensions_module.EMPTY_EXTENSIONS
|
|
assert extensions_module.get_loaded_extensions() is extensions_module.EMPTY_EXTENSIONS
|
|
assert app.state.extension_diagnostics == []
|
|
|
|
|
|
def test_create_app_fails_closed_when_a_required_extension_cannot_load(monkeypatch):
|
|
import deerflow.extensions as extensions_module
|
|
from app.gateway.app import create_app
|
|
|
|
def _raise_required(plugins):
|
|
raise extensions_module.ExtensionLoadError("required extension acme_policy:install failed to install")
|
|
|
|
monkeypatch.setattr(extensions_module, "load_extensions", _raise_required)
|
|
|
|
with pytest.raises(extensions_module.ExtensionLoadError):
|
|
create_app()
|
|
|
|
|
|
def test_create_app_tolerates_a_missing_config_file_and_loads_no_extensions(monkeypatch):
|
|
"""``create_app()`` runs at import time, so an absent config.yaml must not break it.
|
|
|
|
Mirrors ``_resolve_trace_enabled_for_app_construction()``: lifespan still
|
|
performs strict config loading before the Gateway serves traffic.
|
|
"""
|
|
import app.gateway.app as app_module
|
|
import deerflow.extensions as extensions_module
|
|
|
|
def _missing_config():
|
|
raise FileNotFoundError("`config.yaml` file not found in the project root or legacy backend/repository root locations")
|
|
|
|
monkeypatch.setattr(app_module, "get_app_config", _missing_config)
|
|
|
|
observed_plugins = []
|
|
loaded = ExtensionRegistry().build()
|
|
|
|
def _record(plugins):
|
|
observed_plugins.append(plugins)
|
|
return loaded, []
|
|
|
|
monkeypatch.setattr(extensions_module, "load_extensions", _record)
|
|
|
|
app = app_module.create_app()
|
|
|
|
assert observed_plugins == [[]]
|
|
assert app.state.extensions is loaded
|
|
|
|
|
|
def test_create_app_propagates_config_failures_instead_of_blaming_extension_loading(monkeypatch):
|
|
"""A parseable-but-broken config.yaml must not be swallowed by the fail-open guard.
|
|
|
|
Extension loading is fail-open for unexpected errors, but resolving the
|
|
plugin list is not part of it: degrading to zero extensions there would
|
|
drop a ``required: true`` extension without failing the boot.
|
|
"""
|
|
import app.gateway.app as app_module
|
|
import deerflow.extensions as extensions_module
|
|
|
|
def _broken_config():
|
|
raise ValueError("config.yaml failed validation")
|
|
|
|
monkeypatch.setattr(app_module, "get_app_config", _broken_config)
|
|
|
|
def _must_not_run(plugins):
|
|
raise AssertionError("load_extensions must not run when the plugin list cannot be resolved")
|
|
|
|
monkeypatch.setattr(extensions_module, "load_extensions", _must_not_run)
|
|
|
|
with pytest.raises(ValueError, match="config.yaml failed validation"):
|
|
app_module.create_app()
|
|
|
|
|
|
def test_create_app_fails_closed_for_required_extension_with_malformed_api_marker(monkeypatch, stub_app_config):
|
|
import app.gateway.app as app_module
|
|
from extension_test_fixtures import demo_extensions
|
|
|
|
class _ExplodingAPIMarker:
|
|
def split(self, separator: str) -> list[str]:
|
|
raise RuntimeError("API marker split exploded")
|
|
|
|
def __str__(self) -> str:
|
|
return "exploding non-string marker"
|
|
|
|
monkeypatch.setattr(
|
|
demo_extensions.install_ok,
|
|
"__deerflow_api__",
|
|
_ExplodingAPIMarker(),
|
|
raising=False,
|
|
)
|
|
|
|
config = stub_app_config.model_copy(
|
|
update={
|
|
"plugins": [
|
|
ExtensionSpec(
|
|
use="extension_test_fixtures.demo_extensions:install_ok",
|
|
required=True,
|
|
)
|
|
]
|
|
}
|
|
)
|
|
monkeypatch.setattr(app_module, "get_app_config", lambda: config)
|
|
|
|
with pytest.raises(ExtensionLoadError, match="declares invalid api marker"):
|
|
app_module.create_app()
|