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>
137 lines
4.7 KiB
Python
137 lines
4.7 KiB
Python
"""Tool-selection stream suppression helpers."""
|
|
|
|
from typing import TYPE_CHECKING, Any
|
|
|
|
from .emitter import StreamEventEmitter
|
|
|
|
if TYPE_CHECKING:
|
|
from ..middleware.events import ToolSelectionView
|
|
|
|
|
|
class _ToolSelectionSuppressor:
|
|
"""Suppress selector model JSON while preserving the UI selection event.
|
|
|
|
Reads its selection state from the injected frontend sink (a
|
|
:class:`~EvoScientist.middleware.events.ToolSelectionView`) rather than
|
|
process globals: ``tool_selection_active`` gates chatter suppression and
|
|
``consume_tool_selection`` yields the deduped list to surface. The sink
|
|
owns the state; this class only observes the stream and asks the sink.
|
|
"""
|
|
|
|
def __init__(self, emitter: StreamEventEmitter, sink: "ToolSelectionView") -> None:
|
|
self._emitter = emitter
|
|
self._sink = sink
|
|
self._buffering = False
|
|
self._buffer = ""
|
|
self._was_active = False
|
|
|
|
def observe_tool_block(self, name: str) -> bool:
|
|
if name == "ToolSelectionResponse":
|
|
self._was_active = True
|
|
return True
|
|
return False
|
|
|
|
def process_text(self, text: str) -> tuple[bool, list[dict[str, Any]], str]:
|
|
events = self._emit_selection_if_ready(text)
|
|
if not text:
|
|
return False, events, ""
|
|
|
|
if self._buffering:
|
|
self._buffer += text
|
|
json_kind = self._json_buffer_kind(self._buffer)
|
|
if json_kind == "selector" and self._selector_context_active():
|
|
self._was_active = True
|
|
self._buffering = False
|
|
self._buffer = ""
|
|
return True, events, ""
|
|
if json_kind == "complete":
|
|
replay = self._buffer
|
|
self._buffering = False
|
|
self._buffer = ""
|
|
return False, events, replay
|
|
if len(self._buffer) <= 10000:
|
|
return True, events, ""
|
|
replay = self._buffer
|
|
self._buffering = False
|
|
self._buffer = ""
|
|
return False, events, replay
|
|
|
|
stripped = text.strip()
|
|
if (
|
|
self._selector_context_active()
|
|
and stripped.startswith("{")
|
|
and ('"tools"' in stripped or len(stripped) <= 10)
|
|
):
|
|
json_kind = self._json_buffer_kind(stripped)
|
|
if json_kind == "selector":
|
|
self._was_active = True
|
|
return True, events, ""
|
|
if json_kind == "complete":
|
|
return False, events, text
|
|
self._buffering = True
|
|
self._buffer = text
|
|
return True, events, ""
|
|
|
|
return False, events, text
|
|
|
|
def process_thinking(self, text: str) -> tuple[bool, list[dict[str, Any]]]:
|
|
"""Suppress selector-model reasoning while preserving pending UI events."""
|
|
events = self._emit_selection_if_ready(text)
|
|
if not text:
|
|
return False, events
|
|
if self._selector_call_active():
|
|
self._was_active = True
|
|
return True, events
|
|
return False, events
|
|
|
|
@staticmethod
|
|
def _json_buffer_kind(text: str) -> str:
|
|
try:
|
|
import json
|
|
|
|
parsed = json.loads(text.strip())
|
|
except (TypeError, ValueError):
|
|
stripped = text.strip()
|
|
if '"tools"' in stripped and stripped.endswith("}"):
|
|
return "selector"
|
|
return "incomplete"
|
|
if isinstance(parsed, dict) and "tools" in parsed:
|
|
return "selector"
|
|
return "complete"
|
|
|
|
def _selector_context_active(self) -> bool:
|
|
if self._was_active:
|
|
return True
|
|
return self._selector_call_active() or self._selection_pending()
|
|
|
|
def _selector_call_active(self) -> bool:
|
|
return bool(self._sink.tool_selection_active)
|
|
|
|
def _selection_pending(self) -> bool:
|
|
return bool(self._sink.tool_selection_pending())
|
|
|
|
def flush_selection(self) -> list[dict[str, Any]]:
|
|
return self._emit_selection_if_ready("")
|
|
|
|
def flush_pending_text(self) -> str:
|
|
if not self._buffering:
|
|
return ""
|
|
replay = self._buffer
|
|
self._buffering = False
|
|
self._buffer = ""
|
|
return replay
|
|
|
|
def _emit_selection_if_ready(self, text: str) -> list[dict[str, Any]]:
|
|
if not self._was_active:
|
|
return []
|
|
had_pending, render = self._sink.consume_tool_selection()
|
|
if had_pending:
|
|
# Pending consumed (once) — clear our observation flag regardless of
|
|
# whether the sink chose to render it (dedup / kept-all cases).
|
|
self._was_active = False
|
|
if render is not None:
|
|
return [self._emitter.tool_selection(render).data]
|
|
elif text:
|
|
self._was_active = False
|
|
return []
|