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.
140 lines
7.1 KiB
Python
140 lines
7.1 KiB
Python
"""Merging extension-contributed middlewares into the host stack."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from collections.abc import Callable, Mapping, Sequence
|
|
|
|
from deerflow_extension_api import AgentBuildContext, AgentScope, MiddlewarePlacement, Placement
|
|
from langchain.agents.middleware import AgentMiddleware
|
|
|
|
from deerflow.extensions.anchors import PlacementAnchor
|
|
from deerflow.extensions.isolation import IsolatedMiddleware, graph_safe_middleware_name
|
|
from deerflow.extensions.loader import Diagnostic
|
|
from deerflow.extensions.registry import LoadedExtensions
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
def inject_middlewares(
|
|
middlewares: Sequence[object],
|
|
anchors: Mapping[Placement, PlacementAnchor],
|
|
scope: AgentScope,
|
|
ctx: AgentBuildContext,
|
|
extensions: LoadedExtensions,
|
|
*,
|
|
isolation_diagnostic_sink: Callable[[Diagnostic], None] | None = None,
|
|
) -> tuple[list[object], dict[int, str], list[Diagnostic]]:
|
|
"""Insert contributed middlewares at their semantic positions.
|
|
|
|
Returns the merged stack, a provenance map from final index to extension
|
|
source (core middlewares are absent from it), and construction diagnostics.
|
|
Later isolation failures go to ``isolation_diagnostic_sink``; when omitted,
|
|
they append to the returned diagnostic list for standalone callers.
|
|
"""
|
|
result = list(middlewares)
|
|
diagnostics: list[Diagnostic] = []
|
|
|
|
if not extensions.has_middleware_contributors:
|
|
return result, {}, diagnostics
|
|
|
|
collected: list[tuple[str, MiddlewarePlacement]] = []
|
|
for source, contributor in extensions.middleware_contributors:
|
|
try:
|
|
contributions = tuple(contributor.contribute_middlewares(extensions.app_store, ctx) or ())
|
|
except Exception as exc:
|
|
message = f"contribute_middlewares() failed: {exc}"
|
|
diagnostics.append(Diagnostic.error(source, message))
|
|
logger.exception("Extension %s: contribute_middlewares() failed", source)
|
|
continue
|
|
for index, placement in enumerate(contributions):
|
|
if not isinstance(placement, MiddlewarePlacement):
|
|
message = f"contribution {index} must be a MiddlewarePlacement, got {type(placement).__name__}"
|
|
diagnostics.append(Diagnostic.error(source, message))
|
|
logger.error("Extension %s: %s", source, message)
|
|
continue
|
|
if not isinstance(placement.scope, AgentScope):
|
|
message = f"contribution {index} has invalid scope {placement.scope!r}"
|
|
diagnostics.append(Diagnostic.error(source, message))
|
|
logger.error("Extension %s: %s", source, message)
|
|
continue
|
|
if not isinstance(placement.placement, Placement):
|
|
message = f"contribution {index} has invalid placement {placement.placement!r}"
|
|
diagnostics.append(Diagnostic.error(source, message))
|
|
logger.error("Extension %s: %s", source, message)
|
|
continue
|
|
if not isinstance(placement.order, int) or isinstance(placement.order, bool):
|
|
message = f"contribution {index} has invalid order {placement.order!r}; expected int"
|
|
diagnostics.append(Diagnostic.error(source, message))
|
|
logger.error("Extension %s: %s", source, message)
|
|
continue
|
|
if not isinstance(placement.middleware, AgentMiddleware):
|
|
message = f"contribution {index} middleware must be an AgentMiddleware, got {type(placement.middleware).__name__}"
|
|
diagnostics.append(Diagnostic.error(source, message))
|
|
logger.error("Extension %s: %s", source, message)
|
|
continue
|
|
if not (placement.scope & scope):
|
|
continue
|
|
collected.append((source, placement))
|
|
|
|
if not collected:
|
|
return result, {}, diagnostics
|
|
|
|
# Sort by declared order, then by registration order, so the outcome is
|
|
# reproducible regardless of dict iteration details.
|
|
ordered = sorted(enumerate(collected), key=lambda item: (item[1][1].order, item[0]))
|
|
|
|
# Insert inner-most positions first: each insertion shifts the indices of
|
|
# everything after it, so working from the back keeps earlier anchors valid.
|
|
#
|
|
# `priority` records each contribution's position in `ordered` (already
|
|
# sorted by declared order, then registration order). It breaks ties when
|
|
# two contributions resolve to the *same* target index: inserting always
|
|
# pushes the previous occupant of that index outward, so to make the
|
|
# higher-priority (earlier in `ordered`) contribution end up outermost, it
|
|
# must be the *last* one inserted at that index. Sorting by (index,
|
|
# priority) descending achieves that: lower-priority items are processed
|
|
# — and therefore inserted, and therefore displaced outward — first.
|
|
resolved: list[tuple[int, int, str, object]] = []
|
|
for priority, (_, (source, placement)) in enumerate(ordered):
|
|
anchor = anchors.get(placement.placement)
|
|
if anchor is None:
|
|
diagnostics.append(Diagnostic.error(source, f"no anchor configured for placement {placement.placement.name}"))
|
|
continue
|
|
index, used_primary = anchor.resolve(result)
|
|
if not used_primary:
|
|
message = f"placement {placement.placement.name} fell back to a secondary anchor (primary anchor middleware is absent from this stack); the observation semantics of this placement may differ from its documented guarantee"
|
|
diagnostics.append(Diagnostic.warning(source, message))
|
|
logger.warning("Extension %s: %s", source, message)
|
|
resolved.append((index, priority, source, placement.middleware))
|
|
|
|
# LangChain requires names to be unique across the complete stack and uses
|
|
# them as trace identities and, for before/after hooks, LangGraph node IDs.
|
|
used_names = {getattr(middleware, "name", type(middleware).__name__) for middleware in result}
|
|
runtime_diagnostic_sink = isolation_diagnostic_sink if isolation_diagnostic_sink is not None else diagnostics.append
|
|
for index, priority, source, middleware in sorted(resolved, key=lambda item: (item[0], item[1]), reverse=True):
|
|
try:
|
|
inner_name = getattr(middleware, "name", type(middleware).__name__)
|
|
base_name = graph_safe_middleware_name(f"extension:{source}:{inner_name}:{priority}")
|
|
name = base_name
|
|
suffix = 2
|
|
while name in used_names:
|
|
name = f"{base_name}_{suffix}"
|
|
suffix += 1
|
|
wrapped = IsolatedMiddleware(
|
|
middleware,
|
|
source,
|
|
runtime_diagnostic_sink,
|
|
name=name,
|
|
)
|
|
except Exception as exc:
|
|
message = f"middleware construction failed: {exc}"
|
|
diagnostics.append(Diagnostic.error(source, message))
|
|
logger.exception("Extension %s: %s", source, message)
|
|
continue
|
|
used_names.add(name)
|
|
result.insert(index, wrapped)
|
|
|
|
provenance = {index: middleware.source for index, middleware in enumerate(result) if isinstance(middleware, IsolatedMiddleware)}
|
|
return result, provenance, diagnostics
|