mirror of
https://github.com/bytedance/deer-flow.git
synced 2026-08-14 16:58:38 +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.
159 lines
5.1 KiB
Python
159 lines
5.1 KiB
Python
"""DeerFlow's extension mechanism (host side).
|
|
|
|
The public contracts live in the separate `deerflow-extension-api` package;
|
|
this module implements loading, registration, middleware injection and the
|
|
hook-site plumbing.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import threading
|
|
from collections.abc import Iterator, Mapping
|
|
from contextlib import contextmanager
|
|
from contextvars import ContextVar
|
|
from typing import Any
|
|
|
|
from deerflow.extensions.loader import (
|
|
Diagnostic,
|
|
ExtensionLoadError,
|
|
ExtensionSpec,
|
|
load_extensions,
|
|
)
|
|
from deerflow.extensions.registry import EMPTY_EXTENSIONS, ExtensionRegistry, LoadedExtensions
|
|
|
|
#: Runtime-context key carrying the run's immutable extension snapshot.
|
|
#:
|
|
#: The graph-build binding below is a ContextVar scoped to synchronous agent
|
|
#: construction, so it is long gone by the time a tool delegates work. Runtime
|
|
#: context is how the run reaches that later code. The double-underscore prefix
|
|
#: marks it as host-internal: the Gateway strips caller-supplied ``__`` keys,
|
|
#: and this snapshot is never part of the public extension contract.
|
|
EXTENSION_SNAPSHOT_CONTEXT_KEY = "__deerflow_extension_snapshot"
|
|
|
|
_loaded: LoadedExtensions = EMPTY_EXTENSIONS
|
|
_agent_build_extensions: ContextVar[LoadedExtensions | None] = ContextVar(
|
|
"deerflow_agent_build_extensions",
|
|
default=None,
|
|
)
|
|
|
|
|
|
def get_loaded_extensions() -> LoadedExtensions:
|
|
"""Return the process-wide loaded extensions.
|
|
|
|
Mirrors the existing `get_app_config()` convention so call sites can take
|
|
an explicit override parameter and fall back to this.
|
|
"""
|
|
return _loaded
|
|
|
|
|
|
def get_agent_build_extensions() -> LoadedExtensions:
|
|
"""Return the run-bound snapshot while an agent graph is being built."""
|
|
return _agent_build_extensions.get() or get_loaded_extensions()
|
|
|
|
|
|
@contextmanager
|
|
def bind_agent_build_extensions(loaded: LoadedExtensions) -> Iterator[None]:
|
|
"""Bind one immutable extension snapshot to synchronous graph assembly."""
|
|
token = _agent_build_extensions.set(loaded)
|
|
try:
|
|
yield
|
|
finally:
|
|
_agent_build_extensions.reset(token)
|
|
|
|
|
|
def resolve_run_extensions(context: Any | None) -> LoadedExtensions | None:
|
|
"""Return the run's extension snapshot from *context*, or ``None``.
|
|
|
|
Runtime context is caller-mergeable, so the value is type-checked rather
|
|
than trusted. ``None`` means "this caller installed no snapshot" (embedded
|
|
client, standalone LangGraph Server) and leaves consumers on their existing
|
|
``get_loaded_extensions()`` fallback.
|
|
"""
|
|
if not isinstance(context, Mapping):
|
|
return None
|
|
snapshot = context.get(EXTENSION_SNAPSHOT_CONTEXT_KEY)
|
|
return snapshot if isinstance(snapshot, LoadedExtensions) else None
|
|
|
|
|
|
def set_loaded_extensions(loaded: LoadedExtensions) -> None:
|
|
global _loaded
|
|
_loaded = loaded
|
|
|
|
|
|
def reset_loaded_extensions() -> None:
|
|
"""Reset to a FRESH empty set. Used by tests to prevent singleton leaks.
|
|
|
|
Builds a new instance rather than reusing EMPTY_EXTENSIONS: that singleton
|
|
owns a mutable ExtensionData app_store, so resetting to it would carry any
|
|
write made while "empty" across every later reset and across the process.
|
|
"""
|
|
global _loaded
|
|
_loaded = ExtensionRegistry().build()
|
|
|
|
|
|
_runtime_diagnostics: list[Diagnostic] = []
|
|
_runtime_diagnostics_lock = threading.RLock()
|
|
_MAX_RUNTIME_DIAGNOSTICS = 1000
|
|
|
|
|
|
def _trim_runtime_diagnostics() -> None:
|
|
overflow = len(_runtime_diagnostics) - _MAX_RUNTIME_DIAGNOSTICS
|
|
if overflow > 0:
|
|
del _runtime_diagnostics[:overflow]
|
|
|
|
|
|
def initialize_runtime_diagnostics(diagnostics: list[Diagnostic]) -> list[Diagnostic]:
|
|
"""Install and return the live diagnostic list for the current host."""
|
|
with _runtime_diagnostics_lock:
|
|
_runtime_diagnostics.clear()
|
|
_runtime_diagnostics.extend(diagnostics)
|
|
_trim_runtime_diagnostics()
|
|
return _runtime_diagnostics
|
|
|
|
|
|
def record_runtime_diagnostic(diagnostic: Diagnostic) -> None:
|
|
"""Collect one diagnostic in the canonical process sink."""
|
|
with _runtime_diagnostics_lock:
|
|
_runtime_diagnostics.append(diagnostic)
|
|
_trim_runtime_diagnostics()
|
|
|
|
|
|
def record_runtime_diagnostics(diagnostics: list[Diagnostic]) -> None:
|
|
"""Collect a diagnostic batch in the canonical process sink."""
|
|
with _runtime_diagnostics_lock:
|
|
_runtime_diagnostics.extend(diagnostics)
|
|
_trim_runtime_diagnostics()
|
|
|
|
|
|
def get_runtime_diagnostics() -> list[Diagnostic]:
|
|
with _runtime_diagnostics_lock:
|
|
return list(_runtime_diagnostics)
|
|
|
|
|
|
def reset_runtime_diagnostics() -> None:
|
|
with _runtime_diagnostics_lock:
|
|
_runtime_diagnostics.clear()
|
|
|
|
|
|
__all__ = [
|
|
"EMPTY_EXTENSIONS",
|
|
"EXTENSION_SNAPSHOT_CONTEXT_KEY",
|
|
"Diagnostic",
|
|
"ExtensionLoadError",
|
|
"ExtensionRegistry",
|
|
"ExtensionSpec",
|
|
"LoadedExtensions",
|
|
"bind_agent_build_extensions",
|
|
"get_agent_build_extensions",
|
|
"get_loaded_extensions",
|
|
"get_runtime_diagnostics",
|
|
"initialize_runtime_diagnostics",
|
|
"load_extensions",
|
|
"record_runtime_diagnostic",
|
|
"record_runtime_diagnostics",
|
|
"reset_loaded_extensions",
|
|
"reset_runtime_diagnostics",
|
|
"resolve_run_extensions",
|
|
"set_loaded_extensions",
|
|
]
|