01845f4311
* chore: add pytest-asyncio in auto mode * test: migrate channel and stream tests to native async Convert run_async() wrapper tests to plain 'async def test_*' under pytest-asyncio auto mode. collect_events() in stream_v3_fakes becomes a coroutine awaited at every call site. * test: migrate command and model/middleware tests to native async Convert run_async() wrappers (import, alias, and fixture forms) to plain 'async def test_*'. Multi-call tests merge onto one loop as sequential awaits; none asserted on loop identity. * test: migrate TUI, notifier, gateway, and session tests to native async TUI/notifier/gateway files convert run_async wrappers to plain async tests. test_sessions.py's unittest.TestCase classes move to unittest.IsolatedAsyncioTestCase (pytest-asyncio does not await async methods on plain TestCase; converting blindly would have made ~70 tests silently vacuous). Its setUpClass keeps a one-shot asyncio.run() since IsolatedAsyncioTestCase has no async class-level hook. TestLoadingWidget in test_tui_widgets.py drops its TestCase base for the same reason. * test: replace direct asyncio.run() calls with native async tests Convert tests that called asyncio.run() (directly or via a local _run helper) to plain 'async def test_*'; delete the local helpers. * test: drop undeclared anyio markers and delete run_async helper The @pytest.mark.anyio tests relied on anyio being a transitive dep of httpx; auto-mode pytest-asyncio collects them natively. run_async() and its fixture are unreferenced after the migration, so remove them — pytest-asyncio's per-test loop teardown covers the pending-task cancellation the helper existed for (verified: full suite runs with no 'Event loop is closed' errors or destroyed-task warnings). * test: add autouse fixture for watcher cleanup * refactor: remove redundant hasattr calls * refactor: add typed middleware event sink and thread through assembly Add MiddlewareEventSink protocol + NoOpSink in middleware/events.py with a documented any-thread non-blocking contract (contract test uses a deliberately-slow fake sink). Thread an optional `events` parameter through create_cli_agent -> _get_default_middleware -> tool selector / model fallback constructors; subagent stacks are always forced to NoOpSink. * refactor: inject a notifier port into async-watcher and background middleware Add public pre_cancel_watcher() and enqueue_task_notification() to cli/async_notifier.py and a small NotifierPort protocol (middleware/notifier.py) that the module satisfies structurally. AsyncWatcherMiddleware and BackgroundExecutionMiddleware now receive the port by constructor injection at the composition root, deleting the lazy 'from ..cli import async_notifier' imports and the private _watcher_by_thread / _enqueue pokes. * refactor: invert tool-selection ownership onto a frontend event sink The adaptive tool selector now reports on_tool_selection_started / on_tool_selection / on_tool_selection_ended to the injected sink instead of writing four process-global module variables. The frontend sink (stream/sink.py FrontendEventSink) owns the selected/total/active state with consume-once + dedup-vs-last-emitted semantics; stream/tool_selection.py reads that sink object (a ToolSelectionView) rather than reaching into tool_selector's globals. Deleted: the 4 module globals, the cross-module mutations in tool_selection.py, the track_stream_selection flag, the now-vestigial _ToolSelectionTrackerMiddleware, reset_tool_selection_state_for_tests, and the autouse conftest fixture. The sink is threaded from the two interactive frontends through create_runtime_gateways -> LocalGraphGateway (read side) and _load_agent -> create_cli_agent (write side); subagent / headless stacks get NoOpSink. * refactor: route model-fallback narration through the injected event sink Delete the _ui_emit_fn / set_ui_emit module global and the ..stream.console import from model_fallback.py. The fallback middleware now reports through its injected sink: the fallback transition via the structured on_model_fallback (the frontend formats the '-> Falling back to ...' line), and the surrounding narration (primary-failure header, per-attempt outcome, exhaustion, non-fallbackable rejection) via emit_fallback_notice, preserving the exact user-facing text. The TUI binds its _append_system as the sink's fallback display where it used to call set_ui_emit (cleared on exit); the Rich CLI's sink prints to the console. _try_fallbacks / _guard_and_fallback take the sink. * refactor: declare events on the GraphGateway protocol Both gateway implementations now carry an explicit events attribute (LangGraphServerGateway holds None — no frontend renders middleware events across the HTTP boundary), so the four call sites use plain attribute access instead of getattr probing an implicit contract. * refactor: bind fallback display via the closure-scoped concrete sink The App methods used gateway.events (typed as the read-side view) and hasattr-probed for the concrete FrontendEventSink API. The enclosing factory creates that sink two hundred lines up — close over it directly: no probing, fully typed, and it becomes a constructor parameter naturally when the App class is hoisted out of the factory. * fix: end tool selection before fallback handler * fix: keep fallback display errors non-fatal * fix: preserve selector suppression for default streams * fix: restore fallback notice console display * refactor: consolidate fallback narration events * refactor: clean middleware event sink plumbing * fix: type gateway session events * refactor: make all event protocols runtime-checkable MiddlewareEventSink already carried @runtime_checkable (the stream binding guard isinstance-checks it); ToolSelectionView and SessionEvents now match, so mirroring that pattern against any of the three protocols works instead of raising TypeError. * fix(cli): close QuickJS workers after one-shot failures * fix(cli): honor no-thinking in final output * fix(channels): report failed startup accurately * fix(channels): make Telegram cleanup idempotent * fix(tui): skip command sync during exit * fix(channels): preserve startup state during retries * refactor(channels): share pending startup status * refactor(cli): expose channel startup snapshot * fix(tui): move channel startup off event loop * test(channels): release retry gate on assertion failure --------- Co-authored-by: Xi Zhang <106144707+X-iZhang@users.noreply.github.com>
106 lines
4.2 KiB
Python
106 lines
4.2 KiB
Python
"""Spawn async-task watchers when the agent invokes start/update_async_task.
|
|
|
|
Hooks via ``awrap_tool_call`` so it only fires on the two launch tools — every
|
|
other tool call is a no-op pass-through. The middleware does not register tools
|
|
of its own; deepagents' built-in async-subagents middleware already publishes
|
|
``start_async_task`` / ``update_async_task`` to the agent.
|
|
|
|
Stable contract this depends on:
|
|
|
|
* The two public tool names ``start_async_task`` and ``update_async_task``.
|
|
* The ``Command(update={"async_tasks": {task_id: AsyncTask}})`` state schema
|
|
returned by both tools.
|
|
* ``runtime.config["configurable"]["thread_id"]`` for capturing the originating
|
|
CLI thread.
|
|
|
|
It also imports ``_ClientCache`` from deepagents — that is a private symbol but
|
|
a stable typed class, used here only as a connection-pool helper keyed by
|
|
``(url, headers)``.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import logging
|
|
from collections.abc import Awaitable, Callable
|
|
from typing import TYPE_CHECKING, Any
|
|
|
|
from langchain.agents.middleware import AgentMiddleware
|
|
from langchain.agents.middleware.types import ToolCallRequest
|
|
from langchain_core.messages import ToolMessage
|
|
from langgraph.types import Command
|
|
|
|
if TYPE_CHECKING:
|
|
from .notifier import NotifierPort
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
_LAUNCH_TOOL_NAMES = ("start_async_task", "update_async_task")
|
|
|
|
|
|
class AsyncWatcherMiddleware(AgentMiddleware):
|
|
"""Spawn an ``async_notifier`` watcher whenever the agent launches or
|
|
updates an async sub-agent task.
|
|
|
|
Args:
|
|
async_agents: Mapping of subagent name → ``AsyncSubAgent`` TypedDict
|
|
(must contain at least ``url`` and ``graph_id``). Used to construct
|
|
a ``_ClientCache`` for resolving the LangGraph client per agent.
|
|
notifier: Injected :class:`~EvoScientist.middleware.notifier.NotifierPort`
|
|
used to pre-cancel stale watchers and spawn new ones. The composition
|
|
root supplies ``EvoScientist.cli.async_notifier``.
|
|
"""
|
|
|
|
def __init__(self, async_agents: dict[str, Any], notifier: NotifierPort) -> None:
|
|
from deepagents.middleware.async_subagents import _ClientCache
|
|
|
|
super().__init__()
|
|
self._clients = _ClientCache(async_agents)
|
|
self._notifier = notifier
|
|
|
|
async def awrap_tool_call(
|
|
self,
|
|
request: ToolCallRequest,
|
|
handler: Callable[[ToolCallRequest], Awaitable[ToolMessage | Command]],
|
|
) -> ToolMessage | Command:
|
|
name = request.tool_call.get("name")
|
|
args = request.tool_call.get("args") or {}
|
|
|
|
# Pre-cancel the existing watcher BEFORE the new run interrupts the old
|
|
# one (see NotifierPort.pre_cancel_watcher for the full rationale).
|
|
if name == "update_async_task" and (tid := args.get("task_id")):
|
|
self._notifier.pre_cancel_watcher(tid)
|
|
|
|
result = await handler(request)
|
|
|
|
if name in _LAUNCH_TOOL_NAMES and isinstance(result, Command):
|
|
cli_thread_id = None
|
|
cfg = getattr(getattr(request, "runtime", None), "config", None)
|
|
if isinstance(cfg, dict):
|
|
cli_thread_id = cfg.get("configurable", {}).get("thread_id")
|
|
|
|
# Tool-name-gated prompt field — `start_async_task` defines
|
|
# `description`, `update_async_task` defines `message`.
|
|
prompt_field = "description" if name == "start_async_task" else "message"
|
|
prompt = args.get(prompt_field, "")
|
|
|
|
tasks_update = (result.update or {}).get("async_tasks") or {}
|
|
for task_id, task in tasks_update.items():
|
|
try:
|
|
client = self._clients.get_async(task["agent_name"])
|
|
self._notifier.spawn_watcher(
|
|
client,
|
|
task_id,
|
|
task["run_id"],
|
|
task["agent_name"],
|
|
prompt=prompt,
|
|
origin_cli_thread_id=cli_thread_id,
|
|
)
|
|
except Exception:
|
|
logger.warning(
|
|
"Failed to spawn watcher for task %s",
|
|
task_id,
|
|
exc_info=True,
|
|
)
|
|
|
|
return result
|