Files
EvoScientist-Multi/tests/stream_v3_fakes.py
T
dinos 01845f4311 refactor: route middleware display events through an injected event sink (#343)
* 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>
2026-07-14 22:34:17 +00:00

280 lines
6.8 KiB
Python

"""Shared DeepAgents v3 protocol fakes for stream tests."""
from __future__ import annotations
import asyncio
from collections.abc import AsyncIterator, Iterable
from dataclasses import dataclass, field
from typing import Any
from unittest.mock import MagicMock
from EvoScientist.stream.events import stream_agent_events
async def async_iter(items: Iterable[Any]) -> AsyncIterator[Any]:
for item in items:
yield item
async def collect_events(
agent,
message: str = "hi",
thread_id: str = "t1",
*,
events=None,
):
"""Collect stream_agent_events output for tests.
``events`` is the frontend tool-selection sink to drive suppression /
selection rendering (defaults to the silent NoOpSink inside the stream).
"""
collected = []
async for ev in stream_agent_events(
agent,
message,
thread_id,
events=events,
):
collected.append(ev)
return collected
def protocol_event(
method: str,
data,
namespace: Iterable[Any] = (),
**params,
) -> dict[str, Any]:
"""Build a minimal DeepAgents v3 protocol event."""
return {
"type": "event",
"method": method,
"params": {
"namespace": list(namespace),
"timestamp": 0,
"data": data,
**params,
},
}
def message_delta(
text: str,
metadata: dict[str, Any] | None = None,
namespace: Iterable[Any] = (),
) -> dict[str, Any]:
return protocol_event(
"messages",
(
{
"event": "content-block-delta",
"index": 0,
"delta": {"type": "text-delta", "text": text},
},
metadata or {},
),
namespace,
)
def message_finish(
usage: dict[str, int] | None = None,
metadata: dict[str, Any] | None = None,
namespace: Iterable[Any] = (),
) -> dict[str, Any]:
payload: dict[str, Any] = {"event": "message-finish"}
if usage is not None:
payload["usage"] = usage
return protocol_event("messages", (payload, metadata or {}), namespace)
def message_tool_call_block(
name: str,
args: dict[str, Any] | None = None,
*,
tool_call_id: str = "tc1",
namespace: Iterable[Any] = (),
) -> dict[str, Any]:
return protocol_event(
"messages",
(
{
"event": "content-block-finish",
"content": {
"type": "tool_call",
"id": tool_call_id,
"name": name,
"args": args or {},
},
},
{},
),
namespace,
)
def tool_started(
name: str,
args: dict[str, Any] | None = None,
*,
tool_call_id: str = "tc1",
namespace: Iterable[Any] = (),
) -> dict[str, Any]:
return protocol_event(
"tools",
{
"event": "tool-started",
"tool_name": name,
"input": args or {},
"tool_call_id": tool_call_id,
},
namespace,
)
def tool_finished(
output,
*,
tool_call_id: str = "tc1",
namespace: Iterable[Any] = (),
) -> dict[str, Any]:
return protocol_event(
"tools",
{
"event": "tool-finished",
"output": output,
"tool_call_id": tool_call_id,
},
namespace,
)
@dataclass
class FakeStateSnapshot:
values: dict[str, Any] = field(default_factory=dict)
class FakeV3Run:
def __init__(self, events: Iterable[Any], subagents: Iterable[Any] | None = None):
self._events = list(events)
self.subagents = async_iter(list(subagents or []))
self.aborted = False
def __aiter__(self):
return async_iter(self._events)
async def abort(self) -> None:
self.aborted = True
class FakeV3Agent:
def __init__(
self,
events: Iterable[Any],
*,
state_values: dict[str, Any] | None = None,
subagents: Iterable[Any] | None = None,
):
self._run = FakeV3Run(events, subagents=subagents)
self.astream_events = MagicMock(return_value=self._run)
self._state_values = state_values if state_values is not None else {}
async def aget_state(self, _config):
return FakeStateSnapshot(values=self._state_values)
class ErroringV3Agent:
def __init__(self, exc: Exception):
self.exc = exc
def astream_events(self, *_args, **_kwargs):
raise self.exc
async def aget_state(self, _config):
return FakeStateSnapshot()
class HangingV3Run:
def __init__(self, events: Iterable[Any]):
self._events = list(events)
self.subagents = async_iter([])
self.aborted = False
async def abort(self) -> None:
self.aborted = True
def __aiter__(self):
return self._iter_events()
async def _iter_events(self):
for event in self._events:
yield event
await asyncio.Event().wait()
class HangingV3Agent:
def __init__(self, events: Iterable[Any]):
self._run = HangingV3Run(events)
self.astream_events = MagicMock(return_value=self._run)
@property
def aborted(self) -> bool:
return self._run.aborted
async def aget_state(self, _config):
return FakeStateSnapshot()
class LazySubagentChannel:
"""Projection fake that only queues handles after subscription."""
def __init__(self, subagents: Iterable[Any]):
self._subagents = list(subagents)
self.subscribed = False
def __aiter__(self):
self.subscribed = True
return async_iter(self._subagents)
def drop_if_unsubscribed(self) -> None:
if not self.subscribed:
self._subagents = []
class SubscriptionSensitiveV3Run:
def __init__(self, events: Iterable[Any], subagents: Iterable[Any]):
self._events = list(events)
self.subagents = LazySubagentChannel(subagents)
def __aiter__(self):
self.subagents.drop_if_unsubscribed()
return async_iter(self._events)
class SubscriptionSensitiveV3Agent:
def __init__(self, events: Iterable[Any], subagents: Iterable[Any]):
self._run = SubscriptionSensitiveV3Run(events, subagents)
self.astream_events = MagicMock(return_value=self._run)
async def aget_state(self, _config):
return FakeStateSnapshot()
@dataclass
class FakeSubagent:
path: Iterable[Any]
name: str = "research-agent"
tool_call_id: str = ""
def __post_init__(self):
self.path = tuple(self.path)
if not self.tool_call_id:
self.tool_call_id = "call_" + "_".join(str(p) for p in self.path)
@property
def cause(self) -> dict[str, str]:
return {"type": "toolCall", "tool_call_id": self.tool_call_id}
async def output(self):
return {"messages": []}