Add `numpy` for testing optional integrated shm API layer

Demonstrates fixed size frame-oriented reads by the child where the
parent only transmits a "read" stream msg on "frame fill events" such
that the child incrementally reads the shm list data (much like in
a real-time-buffered streaming system).

requirements-test.txt

@@ -6,3 +6,4 @@ mypy
 trio_typing
 pexpect
 towncrier
+numpy

tests/test_clustering.py

@@ -49,7 +49,7 @@ async def worker(
     await ctx.started()
 
     async with ctx.open_stream(
-        backpressure=True,
+        allow_overruns=True,
     ) as stream:
 
         # TODO: this with the below assert causes a hang bug?

tests/test_context_stream_semantics.py

@@ -13,7 +13,10 @@ from typing import Optional
 import pytest
 import trio
 import tractor
-from tractor._exceptions import StreamOverrun
+from tractor._exceptions import (
+    StreamOverrun,
+    ContextCancelled,
+)
 
 from conftest import tractor_test
 
@@ -91,7 +94,10 @@ async def not_started_but_stream_opened(
 
 @pytest.mark.parametrize(
     'target',
-    [too_many_starteds, not_started_but_stream_opened],
+    [
+        too_many_starteds,
+        not_started_but_stream_opened,
+    ],
     ids='misuse_type={}'.format,
 )
 def test_started_misuse(target):
@@ -228,6 +234,88 @@ def test_simple_context(
         trio.run(main)
 
 
+@pytest.mark.parametrize(
+    'callee_returns_early',
+    [True, False],
+    ids=lambda item: f'callee_returns_early={item}'
+)
+@pytest.mark.parametrize(
+    'cancel_method',
+    ['ctx', 'portal'],
+    ids=lambda item: f'cancel_method={item}'
+)
+@pytest.mark.parametrize(
+    'chk_ctx_result_before_exit',
+    [True, False],
+    ids=lambda item: f'chk_ctx_result_before_exit={item}'
+)
+def test_caller_cancels(
+    cancel_method: str,
+    chk_ctx_result_before_exit: bool,
+    callee_returns_early: bool,
+):
+    '''
+    Verify that when the opening side of a context (aka the caller)
+    cancels that context, the ctx does not raise a cancelled when
+    either calling `.result()` or on context exit.
+
+    '''
+    async def check_canceller(
+        ctx: tractor.Context,
+    ) -> None:
+        # should not raise yet return the remote
+        # context cancelled error.
+        res = await ctx.result()
+
+        if callee_returns_early:
+            assert res == 'yo'
+
+        else:
+            err = res
+            assert isinstance(err, ContextCancelled)
+            assert (
+                tuple(err.canceller)
+                ==
+                tractor.current_actor().uid
+            )
+
+    async def main():
+        async with tractor.open_nursery() as nursery:
+            portal = await nursery.start_actor(
+                'simple_context',
+                enable_modules=[__name__],
+            )
+            timeout = 0.5 if not callee_returns_early else 2
+            with trio.fail_after(timeout):
+                async with portal.open_context(
+                    simple_setup_teardown,
+                    data=10,
+                    block_forever=not callee_returns_early,
+                ) as (ctx, sent):
+
+                    if callee_returns_early:
+                        # ensure we block long enough before sending
+                        # a cancel such that the callee has already
+                        # returned it's result.
+                        await trio.sleep(0.5)
+
+                    if cancel_method == 'ctx':
+                        await ctx.cancel()
+                    else:
+                        await portal.cancel_actor()
+
+                    if chk_ctx_result_before_exit:
+                        await check_canceller(ctx)
+
+            if not chk_ctx_result_before_exit:
+                await check_canceller(ctx)
+
+            if cancel_method != 'portal':
+                await portal.cancel_actor()
+
+    trio.run(main)
+
+
 # basic stream terminations:
 # - callee context closes without using stream
 # - caller context closes without using stream
@@ -506,7 +594,6 @@ async def test_callee_cancels_before_started():
                 cancel_self,
             ) as (ctx, sent):
                 async with ctx.open_stream():
-
                     await trio.sleep_forever()
 
         # raises a special cancel signal
@@ -559,7 +646,6 @@ async def keep_sending_from_callee(
     'overrun_by',
     [
         ('caller', 1, never_open_stream),
-        ('cancel_caller_during_overrun', 1, never_open_stream),
         ('callee', 0, keep_sending_from_callee),
     ],
     ids='overrun_condition={}'.format,
@@ -589,14 +675,13 @@ def test_one_end_stream_not_opened(overrun_by):
                 if 'caller' in overrunner:
 
                     async with ctx.open_stream() as stream:
+
+                        # itersend +1 msg more then the buffer size
+                        # to cause the most basic overrun.
                         for i in range(buf_size):
                             print(f'sending {i}')
                             await stream.send(i)
 
-                        if 'cancel' in overrunner:
-                            # without this we block waiting on the child side
-                            await ctx.cancel()
-
                         else:
                             # expect overrun error to be relayed back
                             # and this sleep interrupted
@@ -610,7 +695,9 @@ def test_one_end_stream_not_opened(overrun_by):
 
     # 2 overrun cases and the no overrun case (which pushes right up to
     # the msg limit)
-    if overrunner == 'caller' or 'cance' in overrunner:
+    if (
+        overrunner == 'caller'
+    ):
         with pytest.raises(tractor.RemoteActorError) as excinfo:
             trio.run(main)
 
@@ -634,40 +721,102 @@ async def echo_back_sequence(
 
     ctx:  tractor.Context,
     seq: list[int],
-    msg_buffer_size: Optional[int] = None,
+    wait_for_cancel: bool,
+    allow_overruns_side: str,
+    be_slow: bool = False,
+    msg_buffer_size: int = 1,
 
 ) -> None:
     '''
-    Send endlessly on the calleee stream.
+    Send endlessly on the calleee stream using a small buffer size
+    setting on the contex to simulate backlogging that would normally
+    cause overruns.
 
     '''
+    # NOTE: ensure that if the caller is expecting to cancel this task
+    # that we stay echoing much longer then they are so we don't
+    # return early instead of receive the cancel msg.
+    total_batches: int = 1000 if wait_for_cancel else 6
+
     await ctx.started()
+    # await tractor.breakpoint()
     async with ctx.open_stream(
         msg_buffer_size=msg_buffer_size,
+
+        # literally the point of this test XD
+        allow_overruns=(allow_overruns_side in {'child', 'both'}),
     ) as stream:
 
-        seq = list(seq)  # bleh, `msgpack`...
-        count = 0
-        while count < 3:
+        # ensure mem chan settings are correct
+        assert (
+            ctx._send_chan._state.max_buffer_size
+            ==
+            msg_buffer_size
+        )
+
+        seq = list(seq)  # bleh, msgpack sometimes ain't decoded right
+        for _ in range(total_batches):
             batch = []
             async for msg in stream:
                 batch.append(msg)
                 if batch == seq:
                     break
 
+                if be_slow:
+                    await trio.sleep(0.05)
+
+                print('callee waiting on next')
+
             for msg in batch:
                 print(f'callee sending {msg}')
                 await stream.send(msg)
 
-            count += 1
-
-        return 'yo'
+    print(
+        'EXITING CALLEEE:\n'
+        f'{ctx.cancel_called_remote}'
+    )
+    return 'yo'
 
 
-def test_stream_backpressure():
+@pytest.mark.parametrize(
+    # aka the side that will / should raise
+    # and overrun under normal conditions.
+    'allow_overruns_side',
+    ['parent', 'child', 'none', 'both'],
+    ids=lambda item: f'allow_overruns_side={item}'
+)
+@pytest.mark.parametrize(
+    # aka the side that will / should raise
+    # and overrun under normal conditions.
+    'slow_side',
+    ['parent', 'child'],
+    ids=lambda item: f'slow_side={item}'
+)
+@pytest.mark.parametrize(
+    'cancel_ctx',
+    [True, False],
+    ids=lambda item: f'cancel_ctx={item}'
+)
+def test_maybe_allow_overruns_stream(
+    cancel_ctx: bool,
+    slow_side: str,
+    allow_overruns_side: str,
+    loglevel: str,
+):
     '''
     Demonstrate small overruns of each task back and forth
-    on a stream not raising any errors by default.
+    on a stream not raising any errors by default by setting
+    the ``allow_overruns=True``.
+
+    The original idea here was to show that if you set the feeder mem
+    chan to a size smaller then the # of msgs sent you could could not
+    get a `StreamOverrun` crash plus maybe get all the msgs that were
+    sent. The problem with the "real backpressure" case is that due to
+    the current arch it can result in the msg loop being blocked and thus
+    blocking cancellation - which is like super bad. So instead this test
+    had to be adjusted to more or less just "not send overrun errors" so
+    as to handle the case where the sender just moreso cares about not getting
+    errored out when it send to fast..
 
     '''
     async def main():
@@ -675,38 +824,104 @@ def test_stream_backpressure():
             portal = await n.start_actor(
                 'callee_sends_forever',
                 enable_modules=[__name__],
+                loglevel=loglevel,
+
+                # debug_mode=True,
             )
-            seq = list(range(3))
+            seq = list(range(10))
             async with portal.open_context(
                 echo_back_sequence,
                 seq=seq,
-                msg_buffer_size=1,
+                wait_for_cancel=cancel_ctx,
+                be_slow=(slow_side == 'child'),
+                allow_overruns_side=allow_overruns_side,
             ) as (ctx, sent):
+
                 assert sent is None
 
-                async with ctx.open_stream(msg_buffer_size=1) as stream:
-                    count = 0
-                    while count < 3:
+                async with ctx.open_stream(
+                    msg_buffer_size=1 if slow_side == 'parent' else None,
+                    allow_overruns=(allow_overruns_side in {'parent', 'both'}),
+                ) as stream:
+
+                    total_batches: int = 2
+                    for _ in range(total_batches):
                         for msg in seq:
-                            print(f'caller sending {msg}')
+                            # print(f'root tx {msg}')
                             await stream.send(msg)
-                            await trio.sleep(0.1)
+                            if slow_side == 'parent':
+                                # NOTE: we make the parent slightly
+                                # slower, when it is slow, to make sure
+                                # that in the overruns everywhere case
+                                await trio.sleep(0.16)
 
                         batch = []
                         async for msg in stream:
+                            print(f'root rx {msg}')
                             batch.append(msg)
                             if batch == seq:
                                 break
 
-                        count += 1
+                if cancel_ctx:
+                    # cancel the remote task
+                    print('sending root side cancel')
+                    await ctx.cancel()
 
-            # here the context should return
-            assert await ctx.result() == 'yo'
+            res = await ctx.result()
+
+            if cancel_ctx:
+                assert isinstance(res, ContextCancelled)
+                assert tuple(res.canceller) == tractor.current_actor().uid
+
+            else:
+                print(f'RX ROOT SIDE RESULT {res}')
+                assert res == 'yo'
 
             # cancel the daemon
             await portal.cancel_actor()
 
-    trio.run(main)
+    if (
+        allow_overruns_side == 'both'
+        or slow_side == allow_overruns_side
+    ):
+        trio.run(main)
+
+    elif (
+        slow_side != allow_overruns_side
+    ):
+
+        with pytest.raises(tractor.RemoteActorError) as excinfo:
+            trio.run(main)
+
+        err = excinfo.value
+
+        if (
+            allow_overruns_side == 'none'
+        ):
+            # depends on timing is is racy which side will
+            # overrun first :sadkitty:
+
+            # NOTE: i tried to isolate to a deterministic case here
+            # based on timeing, but i was kinda wasted, and i don't
+            # think it's sane to catch them..
+            assert err.type in (
+                tractor.RemoteActorError,
+                StreamOverrun,
+            )
+
+        elif (
+            slow_side == 'child'
+        ):
+            assert err.type == StreamOverrun
+
+        elif slow_side == 'parent':
+            assert err.type == tractor.RemoteActorError
+            assert 'StreamOverrun' in err.msgdata['tb_str']
+
+    else:
+        # if this hits the logic blocks from above are not
+        # exhaustive..
+        pytest.fail('PARAMETRIZED CASE GEN PROBLEM YO')
 
 
 @tractor.context
@@ -737,18 +952,18 @@ async def attach_to_sleep_forever():
             finally:
                 # XXX: previously this would trigger local
                 # ``ContextCancelled`` to be received and raised in the
-                # local context overriding any local error due to
-                # logic inside ``_invoke()`` which checked for
-                # an error set on ``Context._error`` and raised it in
-                # under a cancellation scenario.
-
-                # The problem is you can have a remote cancellation
-                # that is part of a local error and we shouldn't raise
-                # ``ContextCancelled`` **iff** we weren't the side of
-                # the context to initiate it, i.e.
+                # local context overriding any local error due to logic
+                # inside ``_invoke()`` which checked for an error set on
+                # ``Context._error`` and raised it in a cancellation
+                # scenario.
+                # ------
+                # The problem is you can have a remote cancellation that
+                # is part of a local error and we shouldn't raise
+                # ``ContextCancelled`` **iff** we **were not** the side
+                # of the context to initiate it, i.e.
                 # ``Context._cancel_called`` should **NOT** have been
                 # set. The special logic to handle this case is now
-                # inside ``Context._may_raise_from_remote_msg()`` XD
+                # inside ``Context._maybe_raise_from_remote_msg()`` XD
                 await peer_ctx.cancel()
 
 
@@ -769,9 +984,10 @@ async def error_before_started(
 
 def test_do_not_swallow_error_before_started_by_remote_contextcancelled():
     '''
-    Verify that an error raised in a remote context which itself opens another
-    remote context, which it cancels, does not ovverride the original error that
-    caused the cancellation of the secondardy context.
+    Verify that an error raised in a remote context which itself opens
+    another remote context, which it cancels, does not ovverride the
+    original error that caused the cancellation of the secondardy
+    context.
 
     '''
     async def main():

tests/test_infected_asyncio.py

@@ -15,6 +15,7 @@ import tractor
 from tractor import (
     to_asyncio,
     RemoteActorError,
+    ContextCancelled,
 )
 from tractor.trionics import BroadcastReceiver
 
@@ -224,14 +225,23 @@ def test_context_spawns_aio_task_that_errors(
 
                     await trio.sleep_forever()
 
-    with pytest.raises(RemoteActorError) as excinfo:
-        trio.run(main)
+        return await ctx.result()
 
-    err = excinfo.value
-    assert isinstance(err, RemoteActorError)
     if parent_cancels:
-        assert err.type == trio.Cancelled
+        # bc the parent made the cancel request,
+        # the error is not raised locally but instead
+        # the context is exited silently
+        res = trio.run(main)
+        assert isinstance(res, ContextCancelled)
+        assert 'root' in res.canceller[0]
+
     else:
+        expect = RemoteActorError
+        with pytest.raises(expect) as excinfo:
+            trio.run(main)
+
+        err = excinfo.value
+        assert isinstance(err, expect)
         assert err.type == AssertionError
 
 

tests/test_shm.py

@@ -0,0 +1,167 @@
+"""
+Shared mem primitives and APIs.
+
+"""
+import uuid
+
+# import numpy
+import pytest
+import trio
+import tractor
+from tractor._shm import (
+    open_shm_list,
+    attach_shm_list,
+)
+
+
+@tractor.context
+async def child_attach_shml_alot(
+    ctx: tractor.Context,
+    shm_key: str,
+) -> None:
+
+    await ctx.started(shm_key)
+
+    # now try to attach a boatload of times in a loop..
+    for _ in range(1000):
+        shml = attach_shm_list(
+            key=shm_key,
+            readonly=False,
+        )
+        assert shml.shm.name == shm_key
+        await trio.sleep(0.001)
+
+
+def test_child_attaches_alot():
+    async def main():
+        async with tractor.open_nursery() as an:
+
+            # allocate writeable list in parent
+            key = f'shml_{uuid.uuid4()}'
+            shml = open_shm_list(
+                key=key,
+            )
+
+            portal = await an.start_actor(
+                'shm_attacher',
+                enable_modules=[__name__],
+            )
+
+            async with (
+                portal.open_context(
+                    child_attach_shml_alot,
+                    shm_key=shml.key,
+                ) as (ctx, start_val),
+            ):
+                assert start_val == key
+                await ctx.result()
+
+            await portal.cancel_actor()
+
+    trio.run(main)
+
+
+@tractor.context
+async def child_read_shm_list(
+    ctx: tractor.Context,
+    shm_key: str,
+    use_str: bool,
+    frame_size: int,
+) -> None:
+
+    # attach in child
+    shml = attach_shm_list(
+        key=shm_key,
+        # dtype=str if use_str else float,
+    )
+    await ctx.started(shml.key)
+
+    async with ctx.open_stream() as stream:
+        async for i in stream:
+            print(f'(child): reading shm list index: {i}')
+
+            if use_str:
+                expect = str(float(i))
+            else:
+                expect = float(i)
+
+            if frame_size == 1:
+                val = shml[i]
+                assert expect == val
+                print(f'(child): reading value: {val}')
+            else:
+                frame = shml[i - frame_size:i]
+                print(f'(child): reading frame: {frame}')
+
+
+@pytest.mark.parametrize(
+    'use_str',
+    [False, True],
+    ids=lambda i: f'use_str_values={i}',
+)
+@pytest.mark.parametrize(
+    'frame_size',
+    [1, 2**6, 2**10],
+    ids=lambda i: f'frame_size={i}',
+)
+def test_parent_writer_child_reader(
+    use_str: bool,
+    frame_size: int,
+):
+
+    async def main():
+        async with tractor.open_nursery(
+            # debug_mode=True,
+        ) as an:
+
+            portal = await an.start_actor(
+                'shm_reader',
+                enable_modules=[__name__],
+                debug_mode=True,
+            )
+
+            # allocate writeable list in parent
+            key = 'shm_list'
+            seq_size = int(2 * 2 ** 10)
+            shml = open_shm_list(
+                key=key,
+                size=seq_size,
+                dtype=str if use_str else float,
+                readonly=False,
+            )
+
+            async with (
+                portal.open_context(
+                    child_read_shm_list,
+                    shm_key=key,
+                    use_str=use_str,
+                    frame_size=frame_size,
+                ) as (ctx, sent),
+
+                ctx.open_stream() as stream,
+            ):
+
+                assert sent == key
+
+                for i in range(seq_size):
+
+                    val = float(i)
+                    if use_str:
+                        val = str(val)
+
+                    # print(f'(parent): writing {val}')
+                    shml[i] = val
+
+                    # only on frame fills do we
+                    # signal to the child that a frame's
+                    # worth is ready.
+                    if (i % frame_size) == 0:
+                        print(f'(parent): signalling frame full on {val}')
+                        await stream.send(i)
+                else:
+                    print(f'(parent): signalling final frame on {val}')
+                    await stream.send(i)
+
+            await portal.cancel_actor()
+
+    trio.run(main)

tests/test_task_broadcasting.py

@@ -86,7 +86,7 @@ async def open_sequence_streamer(
         ) as (ctx, first):
 
             assert first is None
-            async with ctx.open_stream(backpressure=True) as stream:
+            async with ctx.open_stream(allow_overruns=True) as stream:
                 yield stream
 
         await portal.cancel_actor()
@@ -413,8 +413,8 @@ def test_ensure_slow_consumers_lag_out(
                     seq = brx._state.subs[brx.key]
                     assert seq == len(brx._state.queue) - 1
 
-                # all backpressured entries in the underlying
-                # channel should have been copied into the caster
+                # all no_overruns entries in the underlying
+                # channel should have been copied into the bcaster
                 # queue trailing-window
                 async for i in rx:
                     print(f'bped: {i}')

tractor/__init__.py

@@ -15,18 +15,20 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 """
-tractor: structured concurrent "actors".
+tractor: structured concurrent ``trio``-"actors".
 
 """
 from exceptiongroup import BaseExceptionGroup
 
 from ._clustering import open_actor_cluster
 from ._ipc import Channel
-from ._streaming import (
+from ._context import (
     Context,
+    context,
+)
+from ._streaming import (
     MsgStream,
     stream,
-    context,
 )
 from ._discovery import (
     get_arbiter,

tractor/_context.py

@@ -0,0 +1,778 @@
+# tractor: structured concurrent "actors".
+# Copyright 2018-eternity Tyler Goodlet.
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+'''
+The fundamental cross process SC abstraction: an inter-actor,
+cancel-scope linked task "context".
+
+A ``Context`` is very similar to the ``trio.Nursery.cancel_scope`` built
+into each ``trio.Nursery`` except it links the lifetimes of memory space
+disjoint, parallel executing tasks in separate actors.
+
+'''
+from __future__ import annotations
+from collections import deque
+from contextlib import asynccontextmanager as acm
+from dataclasses import (
+    dataclass,
+    field,
+)
+from functools import partial
+import inspect
+from pprint import pformat
+from typing import (
+    Any,
+    Callable,
+    AsyncGenerator,
+    TYPE_CHECKING,
+)
+import warnings
+
+import trio
+
+from ._exceptions import (
+    unpack_error,
+    pack_error,
+    ContextCancelled,
+    StreamOverrun,
+)
+from .log import get_logger
+from ._ipc import Channel
+from ._streaming import MsgStream
+from ._state import current_actor
+
+if TYPE_CHECKING:
+    from ._portal import Portal
+
+
+log = get_logger(__name__)
+
+
+@dataclass
+class Context:
+    '''
+    An inter-actor, ``trio``-task communication context.
+
+    NB: This class should never be instatiated directly, it is delivered
+    by either,
+     - runtime machinery to a remotely started task or,
+     - by entering ``Portal.open_context()``.
+
+     and is always constructed using ``mkt_context()``.
+
+    Allows maintaining task or protocol specific state between
+    2 communicating, parallel executing actor tasks. A unique context is
+    allocated on each side of any task RPC-linked msg dialog, for
+    every request to a remote actor from a portal. On the "callee"
+    side a context is always allocated inside ``._runtime._invoke()``.
+
+    A context can be cancelled and (possibly eventually restarted) from
+    either side of the underlying IPC channel, it can also open task
+    oriented message streams,  and acts more or less as an IPC aware
+    inter-actor-task ``trio.CancelScope``.
+
+    '''
+    chan: Channel
+    cid: str
+
+    # these are the "feeder" channels for delivering
+    # message values to the local task from the runtime
+    # msg processing loop.
+    _recv_chan: trio.MemoryReceiveChannel
+    _send_chan: trio.MemorySendChannel
+
+    _remote_func_type: str | None = None
+
+    # only set on the caller side
+    _portal: Portal | None = None    # type: ignore # noqa
+    _result: Any | int = None
+    _remote_error: BaseException | None = None
+
+    # cancellation state
+    _cancel_called: bool = False
+    _cancelled_remote: tuple | None = None
+    _cancel_msg: str | None = None
+    _scope: trio.CancelScope | None = None
+    _enter_debugger_on_cancel: bool = True
+
+    @property
+    def cancel_called(self) -> bool:
+        '''
+        Records whether cancellation has been requested for this context
+        by either an explicit call to  ``.cancel()`` or an implicit call
+        due to an error caught inside the ``Portal.open_context()``
+        block.
+
+        '''
+        return self._cancel_called
+
+    @property
+    def cancel_called_remote(self) -> tuple[str, str] | None:
+        '''
+        ``Actor.uid`` of the remote actor who's task was cancelled
+        causing this side of the context to also be cancelled.
+
+        '''
+        remote_uid = self._cancelled_remote
+        if remote_uid:
+            return tuple(remote_uid)
+
+    @property
+    def cancelled_caught(self) -> bool:
+        return self._scope.cancelled_caught
+
+    # init and streaming state
+    _started_called: bool = False
+    _started_received: bool = False
+    _stream_opened: bool = False
+
+    # overrun handling machinery
+    # NOTE: none of this provides "backpressure" to the remote
+    # task, only an ability to not lose messages when the local
+    # task is configured to NOT transmit ``StreamOverrun``s back
+    # to the other side.
+    _overflow_q: deque[dict] = field(
+        default_factory=partial(
+            deque,
+            maxlen=616,
+        )
+    )
+    _scope_nursery: trio.Nursery | None = None
+    _in_overrun: bool = False
+    _allow_overruns: bool = False
+
+    async def send_yield(
+        self,
+        data: Any,
+
+    ) -> None:
+
+        warnings.warn(
+            "`Context.send_yield()` is now deprecated. "
+            "Use ``MessageStream.send()``. ",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        await self.chan.send({'yield': data, 'cid': self.cid})
+
+    async def send_stop(self) -> None:
+        await self.chan.send({'stop': True, 'cid': self.cid})
+
+    async def _maybe_cancel_and_set_remote_error(
+        self,
+        error_msg: dict[str, Any],
+
+    ) -> None:
+        '''
+        (Maybe) unpack and raise a msg error into the local scope
+        nursery for this context.
+
+        Acts as a form of "relay" for a remote error raised
+        in the corresponding remote callee task.
+
+        '''
+        # If this is an error message from a context opened by
+        # ``Portal.open_context()`` we want to interrupt any ongoing
+        # (child) tasks within that context to be notified of the remote
+        # error relayed here.
+        #
+        # The reason we may want to raise the remote error immediately
+        # is that there is no guarantee the associated local task(s)
+        # will attempt to read from any locally opened stream any time
+        # soon.
+        #
+        # NOTE: this only applies when
+        # ``Portal.open_context()`` has been called since it is assumed
+        # (currently) that other portal APIs (``Portal.run()``,
+        # ``.run_in_actor()``) do their own error checking at the point
+        # of the call and result processing.
+        error = unpack_error(
+            error_msg,
+            self.chan,
+        )
+
+        # XXX: set the remote side's error so that after we cancel
+        # whatever task is the opener of this context it can raise
+        # that error as the reason.
+        self._remote_error = error
+
+        # always record the remote actor's uid since its cancellation
+        # state is directly linked to ours (the local one).
+        self._cancelled_remote = self.chan.uid
+
+        if (
+            isinstance(error, ContextCancelled)
+        ):
+            log.cancel(
+                'Remote task-context sucessfully cancelled for '
+                f'{self.chan.uid}:{self.cid}'
+            )
+
+            if self._cancel_called:
+                # from ._debug import breakpoint
+                # await breakpoint()
+
+                # this is an expected cancel request response message
+                # and we **don't need to raise it** in local cancel
+                # scope since it will potentially override a real error.
+                return
+        else:
+            log.error(
+                f'Remote context error for {self.chan.uid}:{self.cid}:\n'
+                f'{error_msg["error"]["tb_str"]}'
+            )
+        # TODO: tempted to **not** do this by-reraising in a
+        # nursery and instead cancel a surrounding scope, detect
+        # the cancellation, then lookup the error that was set?
+        # YES! this is way better and simpler!
+        if (
+            self._scope
+        ):
+            # from trio.testing import wait_all_tasks_blocked
+            # await wait_all_tasks_blocked()
+            # self._cancelled_remote = self.chan.uid
+            self._scope.cancel()
+
+            # NOTE: this usage actually works here B)
+            # from ._debug import breakpoint
+            # await breakpoint()
+
+        # XXX: this will break early callee results sending
+        # since when `.result()` is finally called, this
+        # chan will be closed..
+        # if self._recv_chan:
+        #     await self._recv_chan.aclose()
+
+    async def cancel(
+        self,
+        msg: str | None = None,
+        timeout: float = 0.616,
+        # timeout: float = 1000,
+
+    ) -> None:
+        '''
+        Cancel this inter-actor-task context.
+
+        Request that the far side cancel it's current linked context,
+        Timeout quickly in an attempt to sidestep 2-generals...
+
+        '''
+        side = 'caller' if self._portal else 'callee'
+        if msg:
+            assert side == 'callee', 'Only callee side can provide cancel msg'
+
+        log.cancel(f'Cancelling {side} side of context to {self.chan.uid}')
+
+        self._cancel_called = True
+        # await _debug.breakpoint()
+        # breakpoint()
+
+        if side == 'caller':
+            if not self._portal:
+                raise RuntimeError(
+                    "No portal found, this is likely a callee side context"
+                )
+
+            cid = self.cid
+            with trio.move_on_after(timeout) as cs:
+                cs.shield = True
+                log.cancel(
+                    f"Cancelling stream {cid} to "
+                    f"{self._portal.channel.uid}")
+
+                # NOTE: we're telling the far end actor to cancel a task
+                # corresponding to *this actor*. The far end local channel
+                # instance is passed to `Actor._cancel_task()` implicitly.
+                await self._portal.run_from_ns(
+                    'self',
+                    '_cancel_task',
+                    cid=cid,
+                )
+                # print("EXITING CANCEL CALL")
+
+            if cs.cancelled_caught:
+                # XXX: there's no way to know if the remote task was indeed
+                # cancelled in the case where the connection is broken or
+                # some other network error occurred.
+                # if not self._portal.channel.connected():
+                if not self.chan.connected():
+                    log.cancel(
+                        "May have failed to cancel remote task "
+                        f"{cid} for {self._portal.channel.uid}")
+                else:
+                    log.cancel(
+                        "Timed out on cancelling remote task "
+                        f"{cid} for {self._portal.channel.uid}")
+
+        # callee side remote task
+        else:
+            self._cancel_msg = msg
+
+            # TODO: should we have an explicit cancel message
+            # or is relaying the local `trio.Cancelled` as an
+            # {'error': trio.Cancelled, cid: "blah"} enough?
+            # This probably gets into the discussion in
+            # https://github.com/goodboy/tractor/issues/36
+            assert self._scope
+            self._scope.cancel()
+
+    @acm
+    async def open_stream(
+
+        self,
+        allow_overruns: bool | None = False,
+        msg_buffer_size: int | None = None,
+
+    ) -> AsyncGenerator[MsgStream, None]:
+        '''
+        Open a ``MsgStream``, a bi-directional stream connected to the
+        cross-actor (far end) task for this ``Context``.
+
+        This context manager must be entered on both the caller and
+        callee for the stream to logically be considered "connected".
+
+        A ``MsgStream`` is currently "one-shot" use, meaning if you
+        close it you can not "re-open" it for streaming and instead you
+        must re-establish a new surrounding ``Context`` using
+        ``Portal.open_context()``.  In the future this may change but
+        currently there seems to be no obvious reason to support
+        "re-opening":
+            - pausing a stream can be done with a message.
+            - task errors will normally require a restart of the entire
+              scope of the inter-actor task context due to the nature of
+              ``trio``'s cancellation system.
+
+        '''
+        actor = current_actor()
+
+        # here we create a mem chan that corresponds to the
+        # far end caller / callee.
+
+        # Likewise if the surrounding context has been cancelled we error here
+        # since it likely means the surrounding block was exited or
+        # killed
+
+        if self._cancel_called:
+            task = trio.lowlevel.current_task().name
+            raise ContextCancelled(
+                f'Context around {actor.uid[0]}:{task} was already cancelled!'
+            )
+
+        if not self._portal and not self._started_called:
+            raise RuntimeError(
+                'Context.started()` must be called before opening a stream'
+            )
+
+        # NOTE: in one way streaming this only happens on the
+        # caller side inside `Actor.start_remote_task()` so if you try
+        # to send a stop from the caller to the callee in the
+        # single-direction-stream case you'll get a lookup error
+        # currently.
+        ctx = actor.get_context(
+            self.chan,
+            self.cid,
+            msg_buffer_size=msg_buffer_size,
+            allow_overruns=allow_overruns,
+        )
+        ctx._allow_overruns = allow_overruns
+        assert ctx is self
+
+        # XXX: If the underlying channel feeder receive mem chan has
+        # been closed then likely client code has already exited
+        # a ``.open_stream()`` block prior or there was some other
+        # unanticipated error or cancellation from ``trio``.
+
+        if ctx._recv_chan._closed:
+            raise trio.ClosedResourceError(
+                'The underlying channel for this stream was already closed!?')
+
+        async with MsgStream(
+            ctx=self,
+            rx_chan=ctx._recv_chan,
+        ) as stream:
+
+            if self._portal:
+                self._portal._streams.add(stream)
+
+            try:
+                self._stream_opened = True
+
+                # XXX: do we need this?
+                # ensure we aren't cancelled before yielding the stream
+                # await trio.lowlevel.checkpoint()
+                yield stream
+
+                # NOTE: Make the stream "one-shot use".  On exit, signal
+                # ``trio.EndOfChannel``/``StopAsyncIteration`` to the
+                # far end.
+                await stream.aclose()
+
+            finally:
+                if self._portal:
+                    try:
+                        self._portal._streams.remove(stream)
+                    except KeyError:
+                        log.warning(
+                            f'Stream was already destroyed?\n'
+                            f'actor: {self.chan.uid}\n'
+                            f'ctx id: {self.cid}'
+                        )
+
+    def _maybe_raise_remote_err(
+        self,
+        err: Exception,
+    ) -> None:
+        # NOTE: whenever the context's "opener" side (task) **is**
+        # the side which requested the cancellation (likekly via
+        # ``Context.cancel()``), we don't want to re-raise that
+        # cancellation signal locally (would be akin to
+        # a ``trio.Nursery`` nursery raising ``trio.Cancelled``
+        # whenever  ``CancelScope.cancel()`` was called) and instead
+        # silently reap the expected cancellation "error"-msg.
+        # if 'pikerd' in err.msgdata['tb_str']:
+        #     # from . import _debug
+        #     # await _debug.breakpoint()
+        #     breakpoint()
+
+        if (
+            isinstance(err, ContextCancelled)
+            and (
+                self._cancel_called
+                or self.chan._cancel_called
+                or tuple(err.canceller) == current_actor().uid
+            )
+        ):
+            return err
+
+        raise err  # from None
+
+    async def result(self) -> Any | Exception:
+        '''
+        From some (caller) side task, wait for and return the final
+        result from the remote (callee) side's task.
+
+        This provides a mechanism for one task running in some actor to wait
+        on another task at the other side, in some other actor, to terminate.
+
+        If the remote task is still in a streaming state (it is delivering
+        values from inside a ``Context.open_stream():`` block, then those
+        msgs are drained but discarded since it is presumed this side of
+        the context has already finished with its own streaming logic.
+
+        If the remote context (or its containing actor runtime) was
+        canceled, either by a local task calling one of
+        ``Context.cancel()`` or `Portal.cancel_actor()``, we ignore the
+        received ``ContextCancelled`` exception if the context or
+        underlying IPC channel is marked as having been "cancel called".
+        This is similar behavior to using ``trio.Nursery.cancel()``
+        wherein tasks which raise ``trio.Cancel`` are silently reaped;
+        the main different in this API is in the "cancel called" case,
+        instead of just not raising, we also return the exception *as
+        the result* since client code may be interested in the details
+        of the remote cancellation.
+
+        '''
+        assert self._portal, "Context.result() can not be called from callee!"
+        assert self._recv_chan
+
+        # from . import _debug
+        # await _debug.breakpoint()
+
+        re = self._remote_error
+        if re:
+            self._maybe_raise_remote_err(re)
+            return re
+
+        if (
+            self._result == id(self)
+            and not self._remote_error
+            and not self._recv_chan._closed  # type: ignore
+        ):
+            # wait for a final context result consuming
+            # and discarding any bi dir stream msgs still
+            # in transit from the far end.
+            while True:
+                msg = await self._recv_chan.receive()
+                try:
+                    self._result = msg['return']
+
+                    # NOTE: we don't need to do this right?
+                    # XXX: only close the rx mem chan AFTER
+                    # a final result is retreived.
+                    # if self._recv_chan:
+                    #     await self._recv_chan.aclose()
+
+                    break
+                except KeyError:  # as msgerr:
+
+                    if 'yield' in msg:
+                        # far end task is still streaming to us so discard
+                        log.warning(f'Discarding stream delivered {msg}')
+                        continue
+
+                    elif 'stop' in msg:
+                        log.debug('Remote stream terminated')
+                        continue
+
+                    # internal error should never get here
+                    assert msg.get('cid'), (
+                        "Received internal error at portal?")
+
+                    err = unpack_error(
+                        msg,
+                        self._portal.channel
+                    )  # from msgerr
+
+                    err = self._maybe_raise_remote_err(err)
+                    self._remote_err = err
+
+        return self._remote_error or self._result
+
+    async def started(
+        self,
+        value: Any | None = None
+
+    ) -> None:
+        '''
+        Indicate to calling actor's task that this linked context
+        has started and send ``value`` to the other side.
+
+        On the calling side ``value`` is the second item delivered
+        in the tuple returned by ``Portal.open_context()``.
+
+        '''
+        if self._portal:
+            raise RuntimeError(
+                f"Caller side context {self} can not call started!")
+
+        elif self._started_called:
+            raise RuntimeError(
+                f"called 'started' twice on context with {self.chan.uid}")
+
+        await self.chan.send({'started': value, 'cid': self.cid})
+        self._started_called = True
+
+    # TODO: do we need a restart api?
+    # async def restart(self) -> None:
+    #     pass
+
+    async def _drain_overflows(
+        self,
+    ) -> None:
+        '''
+        Private task spawned to push newly received msgs to the local
+        task which getting overrun by the remote side.
+
+        In order to not block the rpc msg loop, but also not discard
+        msgs received in this context, we need to async push msgs in
+        a new task which only runs for as long as the local task is in
+        an overrun state.
+
+        '''
+        self._in_overrun = True
+        try:
+            while self._overflow_q:
+                # NOTE: these msgs should never be errors since we always do
+                # the check prior to checking if we're in an overrun state
+                # inside ``.deliver_msg()``.
+                msg = self._overflow_q.popleft()
+                try:
+                    await self._send_chan.send(msg)
+                except trio.BrokenResourceError:
+                    log.warning(
+                        f"{self._send_chan} consumer is already closed"
+                    )
+                    return
+                except trio.Cancelled:
+                    # we are obviously still in overrun
+                    # but the context is being closed anyway
+                    # so we just warn that there are un received
+                    # msgs still..
+                    self._overflow_q.appendleft(msg)
+                    fmt_msgs = ''
+                    for msg in self._overflow_q:
+                        fmt_msgs += f'{pformat(msg)}\n'
+
+                    log.warning(
+                        f'Context for {self.cid} is being closed while '
+                        'in an overrun state!\n'
+                        'Discarding the following msgs:\n'
+                        f'{fmt_msgs}\n'
+                    )
+                    raise
+
+        finally:
+            # task is now finished with the backlog so mark us as
+            # no longer in backlog.
+            self._in_overrun = False
+
+    async def _deliver_msg(
+        self,
+        msg: dict,
+
+        draining: bool = False,
+
+    ) -> bool:
+
+        cid = self.cid
+        chan = self.chan
+        uid = chan.uid
+        send_chan: trio.MemorySendChannel = self._send_chan
+
+        log.runtime(
+            f"Delivering {msg} from {uid} to caller {cid}"
+        )
+
+        error = msg.get('error')
+        if error:
+            await self._maybe_cancel_and_set_remote_error(msg)
+
+        if (
+            self._in_overrun
+        ):
+            self._overflow_q.append(msg)
+            return False
+
+        try:
+            send_chan.send_nowait(msg)
+            return True
+            # if an error is deteced we should always
+            # expect it to be raised by any context (stream)
+            # consumer task
+
+        except trio.BrokenResourceError:
+            # TODO: what is the right way to handle the case where the
+            # local task has already sent a 'stop' / StopAsyncInteration
+            # to the other side but and possibly has closed the local
+            # feeder mem chan? Do we wait for some kind of ack or just
+            # let this fail silently and bubble up (currently)?
+
+            # XXX: local consumer has closed their side
+            # so cancel the far end streaming task
+            log.warning(f"{send_chan} consumer is already closed")
+            return False
+
+        # NOTE XXX: by default we do **not** maintain context-stream
+        # backpressure and instead opt to relay stream overrun errors to
+        # the sender; the main motivation is that using bp can block the
+        # msg handling loop which calls into this method!
+        except trio.WouldBlock:
+            # XXX: always push an error even if the local
+            # receiver is in overrun state.
+            # await self._maybe_cancel_and_set_remote_error(msg)
+
+            local_uid = current_actor().uid
+            lines = [
+                f'OVERRUN on actor-task context {cid}@{local_uid}!\n'
+                # TODO: put remote task name here if possible?
+                f'remote sender actor: {uid}',
+                # TODO: put task func name here and maybe an arrow
+                # from sender to overrunner?
+                # f'local task {self.func_name}'
+            ]
+            if not self._stream_opened:
+                lines.insert(
+                    1,
+                    f'\n*** No stream open on `{local_uid[0]}` side! ***\n'
+                )
+
+            text = '\n'.join(lines)
+
+            # XXX: lul, this really can't be backpressure since any
+            # blocking here will block the entire msg loop rpc sched for
+            # a whole channel.. maybe we should rename it?
+            if self._allow_overruns:
+                text += f'\nStarting overflow queuing task on msg: {msg}'
+                log.warning(text)
+                if (
+                    not self._in_overrun
+                ):
+                    self._overflow_q.append(msg)
+                    n = self._scope_nursery
+                    assert not n.child_tasks
+                    try:
+                        n.start_soon(
+                            self._drain_overflows,
+                        )
+                    except RuntimeError:
+                        # if the nursery is already cancelled due to
+                        # this context exiting or in error, we ignore
+                        # the nursery error since we never expected
+                        # anything different.
+                        return False
+            else:
+                try:
+                    raise StreamOverrun(text)
+                except StreamOverrun as err:
+                    err_msg = pack_error(err)
+                    err_msg['cid'] = cid
+                    try:
+                        await chan.send(err_msg)
+                    except trio.BrokenResourceError:
+                        # XXX: local consumer has closed their side
+                        # so cancel the far end streaming task
+                        log.warning(f"{chan} is already closed")
+
+            return False
+
+
+def mk_context(
+    chan: Channel,
+    cid: str,
+    msg_buffer_size: int = 2**6,
+
+    **kwargs,
+
+) -> Context:
+    '''
+    Internal factory to create an inter-actor task ``Context``.
+
+    This is called by internals and should generally never be called
+    by user code.
+
+    '''
+    send_chan: trio.MemorySendChannel
+    recv_chan: trio.MemoryReceiveChannel
+    send_chan, recv_chan = trio.open_memory_channel(msg_buffer_size)
+
+    ctx = Context(
+        chan,
+        cid,
+        _send_chan=send_chan,
+        _recv_chan=recv_chan,
+        **kwargs,
+    )
+    ctx._result: int | Any = id(ctx)
+    return ctx
+
+
+def context(func: Callable) -> Callable:
+    '''
+    Mark an async function as a streaming routine with ``@context``.
+
+    '''
+    # TODO: apply whatever solution ``mypy`` ends up picking for this:
+    # https://github.com/python/mypy/issues/2087#issuecomment-769266912
+    func._tractor_context_function = True  # type: ignore
+
+    sig = inspect.signature(func)
+    params = sig.parameters
+    if 'ctx' not in params:
+        raise TypeError(
+            "The first argument to the context function "
+            f"{func.__name__} must be `ctx: tractor.Context`"
+        )
+    return func

tractor/_discovery.py

@@ -41,8 +41,10 @@ async def get_arbiter(
     port: int,
 
 ) -> AsyncGenerator[Union[Portal, LocalPortal], None]:
-    '''Return a portal instance connected to a local or remote
+    '''
+    Return a portal instance connected to a local or remote
     arbiter.
+
     '''
     actor = current_actor()
 
@@ -134,12 +136,16 @@ async def find_actor(
 @acm
 async def wait_for_actor(
     name: str,
-    arbiter_sockaddr: tuple[str, int] | None = None
+    arbiter_sockaddr: tuple[str, int] | None = None,
+    # registry_addr: tuple[str, int] | None = None,
+
 ) -> AsyncGenerator[Portal, None]:
-    """Wait on an actor to register with the arbiter.
+    '''
+    Wait on an actor to register with the arbiter.
 
     A portal to the first registered actor is returned.
-    """
+
+    '''
     actor = current_actor()
 
     async with get_arbiter(

tractor/_entry.py

@@ -132,7 +132,7 @@ def _trio_main(
         else:
             trio.run(trio_main)
     except KeyboardInterrupt:
-        log.warning(f"Actor {actor.uid} received KBI")
+        log.cancel(f"Actor {actor.uid} received KBI")
 
     finally:
         log.info(f"Actor {actor.uid} terminated")

tractor/_exceptions.py

@@ -18,18 +18,18 @@
 Our classy exception set.
 
 """
+import builtins
+import importlib
 from typing import (
     Any,
-    Optional,
     Type,
 )
-import importlib
-import builtins
 import traceback
 
 import exceptiongroup as eg
 import trio
 
+from ._state import current_actor
 
 _this_mod = importlib.import_module(__name__)
 
@@ -44,7 +44,7 @@ class RemoteActorError(Exception):
     def __init__(
         self,
         message: str,
-        suberror_type: Optional[Type[BaseException]] = None,
+        suberror_type: Type[BaseException] | None = None,
         **msgdata
 
     ) -> None:
@@ -53,21 +53,36 @@ class RemoteActorError(Exception):
         self.type = suberror_type
         self.msgdata = msgdata
 
+    @property
+    def src_actor_uid(self) -> tuple[str, str] | None:
+        return self.msgdata.get('src_actor_uid')
+
 
 class InternalActorError(RemoteActorError):
-    """Remote internal ``tractor`` error indicating
+    '''
+    Remote internal ``tractor`` error indicating
     failure of some primitive or machinery.
-    """
+
+    '''
+
+
+class ContextCancelled(RemoteActorError):
+    '''
+    Inter-actor task context was cancelled by either a call to
+    ``Portal.cancel_actor()`` or ``Context.cancel()``.
+
+    '''
+    @property
+    def canceller(self) -> tuple[str, str] | None:
+        value = self.msgdata.get('canceller')
+        if value:
+            return tuple(value)
 
 
 class TransportClosed(trio.ClosedResourceError):
     "Underlying channel transport was closed prior to use"
 
 
-class ContextCancelled(RemoteActorError):
-    "Inter-actor task context cancelled itself on the callee side."
-
-
 class NoResult(RuntimeError):
     "No final result is expected for this actor"
 
@@ -106,13 +121,17 @@ def pack_error(
     else:
         tb_str = traceback.format_exc()
 
-    return {
-        'error': {
-            'tb_str': tb_str,
-            'type_str': type(exc).__name__,
-        }
+    error_msg = {
+        'tb_str': tb_str,
+        'type_str': type(exc).__name__,
+        'src_actor_uid': current_actor().uid,
     }
 
+    if isinstance(exc, ContextCancelled):
+        error_msg.update(exc.msgdata)
+
+    return {'error': error_msg}
+
 
 def unpack_error(
 
@@ -136,7 +155,7 @@ def unpack_error(
 
     if type_name == 'ContextCancelled':
         err_type = ContextCancelled
-        suberror_type = trio.Cancelled
+        suberror_type = RemoteActorError
 
     else:  # try to lookup a suitable local error type
         for ns in [

tractor/_portal.py

@@ -45,10 +45,8 @@ from ._exceptions import (
     NoResult,
     ContextCancelled,
 )
-from ._streaming import (
-    Context,
-    MsgStream,
-)
+from ._context import Context
+from ._streaming import MsgStream
 
 
 log = get_logger(__name__)
@@ -103,7 +101,7 @@ class Portal:
         # When set to a ``Context`` (when _submit_for_result is called)
         # it is expected that ``result()`` will be awaited at some
         # point.
-        self._expect_result: Optional[Context] = None
+        self._expect_result: Context | None = None
         self._streams: set[MsgStream] = set()
         self.actor = current_actor()
 
@@ -209,7 +207,10 @@ class Portal:
         try:
             # send cancel cmd - might not get response
             # XXX: sure would be nice to make this work with a proper shield
-            with trio.move_on_after(timeout or self.cancel_timeout) as cs:
+            with trio.move_on_after(
+                timeout
+                or self.cancel_timeout
+            ) as cs:
                 cs.shield = True
 
                 await self.run_from_ns('self', 'cancel')
@@ -330,7 +331,9 @@ class Portal:
                     f'{async_gen_func} must be an async generator function!')
 
         fn_mod_path, fn_name = NamespacePath.from_ref(
-            async_gen_func).to_tuple()
+            async_gen_func
+        ).to_tuple()
+
         ctx = await self.actor.start_remote_task(
             self.channel,
             fn_mod_path,
@@ -377,6 +380,7 @@ class Portal:
 
         self,
         func: Callable,
+        allow_overruns: bool = False,
         **kwargs,
 
     ) -> AsyncGenerator[tuple[Context, Any], None]:
@@ -396,13 +400,26 @@ class Portal:
             raise TypeError(
                 f'{func} must be an async generator function!')
 
+        # TODO: i think from here onward should probably
+        # just be factored into an `@acm` inside a new
+        # a new `_context.py` mod.
         fn_mod_path, fn_name = NamespacePath.from_ref(func).to_tuple()
 
         ctx = await self.actor.start_remote_task(
             self.channel,
             fn_mod_path,
             fn_name,
-            kwargs
+            kwargs,
+
+            # NOTE: it's imporant to expose this since you might
+            # get the case where the parent who opened the context does
+            # not open a stream until after some slow startup/init
+            # period, in which case when the first msg is read from
+            # the feeder mem chan, say when first calling
+            # `Context.open_stream(allow_overruns=True)`, the overrun condition will be
+            # raised before any ignoring of overflow msgs can take
+            # place..
+            allow_overruns=allow_overruns,
         )
 
         assert ctx._remote_func_type == 'context'
@@ -426,29 +443,47 @@ class Portal:
                     f' but received a non-error msg:\n{pformat(msg)}'
                 )
 
-        _err: Optional[BaseException] = None
-        ctx._portal = self
+        _err: BaseException | None = None
+        ctx._portal: Portal = self
 
-        uid = self.channel.uid
-        cid = ctx.cid
-        etype: Optional[Type[BaseException]] = None
+        uid: tuple = self.channel.uid
+        cid: str = ctx.cid
+        etype: Type[BaseException] | None = None
 
-        # deliver context instance and .started() msg value in open tuple.
+        # deliver context instance and .started() msg value in enter
+        # tuple.
         try:
-            async with trio.open_nursery() as scope_nursery:
-                ctx._scope_nursery = scope_nursery
-
-                # do we need this?
-                # await trio.lowlevel.checkpoint()
+            async with trio.open_nursery() as nurse:
+                ctx._scope_nursery = nurse
+                ctx._scope = nurse.cancel_scope
 
                 yield ctx, first
 
+                # when in allow_ovveruns mode there may be lingering
+                # overflow sender tasks remaining?
+                if nurse.child_tasks:
+                    # ensure we are in overrun state with
+                    # ``._allow_overruns=True`` bc otherwise
+                    # there should be no tasks in this nursery!
+                    if (
+                        not ctx._allow_overruns
+                        or len(nurse.child_tasks) > 1
+                    ):
+                        raise RuntimeError(
+                            'Context has sub-tasks but is '
+                            'not in `allow_overruns=True` Mode!?'
+                        )
+                    ctx._scope.cancel()
+
         except ContextCancelled as err:
             _err = err
+
+            # swallow and mask cross-actor task context cancels that
+            # were initiated by *this* side's task.
             if not ctx._cancel_called:
-                # context was cancelled at the far end but was
-                # not part of this end requesting that cancel
-                # so raise for the local task to respond and handle.
+                # XXX: this should NEVER happen!
+                # from ._debug import breakpoint
+                # await breakpoint()
                 raise
 
             # if the context was cancelled by client code
@@ -468,17 +503,17 @@ class Portal:
 
         ) as err:
             etype = type(err)
-            # the context cancels itself on any cancel
-            # causing error.
 
-            if ctx.chan.connected():
-                log.cancel(
-                    'Context cancelled for task, sending cancel request..\n'
-                    f'task:{cid}\n'
-                    f'actor:{uid}'
-                )
+            # cancel ourselves on any error.
+            log.cancel(
+                'Context cancelled for task, sending cancel request..\n'
+                f'task:{cid}\n'
+                f'actor:{uid}'
+            )
+            try:
+
                 await ctx.cancel()
-            else:
+            except trio.BrokenResourceError:
                 log.warning(
                     'IPC connection for context is broken?\n'
                     f'task:{cid}\n'
@@ -487,12 +522,7 @@ class Portal:
 
             raise
 
-        finally:
-            # in the case where a runtime nursery (due to internal bug)
-            # or a remote actor transmits an error we want to be
-            # sure we get the error the underlying feeder mem chan.
-            # if it's not raised here it *should* be raised from the
-            # msg loop nursery right?
+        else:
             if ctx.chan.connected():
                 log.info(
                     'Waiting on final context-task result for\n'
@@ -505,6 +535,7 @@ class Portal:
                     f'value from callee `{result}`'
                 )
 
+        finally:
             # though it should be impossible for any tasks
             # operating *in* this scope to have survived
             # we tear down the runtime feeder chan last

tractor/_root.py

@@ -254,7 +254,9 @@ async def open_root_actor(
                 #         tempn.start_soon(an.exited.wait)
 
                 logger.cancel("Shutting down root actor")
-                await actor.cancel()
+                await actor.cancel(
+                    requesting_uid=actor.uid,
+                )
     finally:
         _state._current_actor = None
 

tractor/_runtime.py

@@ -28,9 +28,10 @@ import inspect
 import signal
 import sys
 from typing import (
-    Any, Optional,
-    Union, TYPE_CHECKING,
+    Any,
     Callable,
+    Union,
+    TYPE_CHECKING,
 )
 import uuid
 from types import ModuleType
@@ -44,7 +45,10 @@ import trio  # type: ignore
 from trio_typing import TaskStatus
 
 from ._ipc import Channel
-from ._streaming import Context
+from ._context import (
+    mk_context,
+    Context,
+)
 from .log import get_logger
 from ._exceptions import (
     pack_error,
@@ -53,7 +57,6 @@ from ._exceptions import (
     is_multi_cancelled,
     ContextCancelled,
     TransportClosed,
-    StreamOverrun,
 )
 from . import _debug
 from ._discovery import get_arbiter
@@ -79,7 +82,7 @@ async def _invoke(
 
     is_rpc: bool = True,
     task_status: TaskStatus[
-        Union[trio.CancelScope, BaseException]
+        Union[Context, BaseException]
     ] = trio.TASK_STATUS_IGNORED,
 ):
     '''
@@ -97,9 +100,16 @@ async def _invoke(
 
     cancel_scope = trio.CancelScope()
     # activated cancel scope ref
-    cs: Optional[trio.CancelScope] = None
+    cs: trio.CancelScope | None = None
 
-    ctx = actor.get_context(chan, cid)
+    ctx = actor.get_context(
+        chan,
+        cid,
+        # We shouldn't ever need to pass this through right?
+        # it's up to the soon-to-be called rpc task to
+        # open the stream with this option.
+        # allow_overruns=True,
+    )
     context: bool = False
 
     if getattr(func, '_tractor_stream_function', False):
@@ -138,7 +148,10 @@ async def _invoke(
         ):
             raise TypeError(f'{func} must be an async function!')
 
-        coro = func(**kwargs)
+        try:
+            coro = func(**kwargs)
+        except TypeError:
+            raise
 
         if inspect.isasyncgen(coro):
             await chan.send({'functype': 'asyncgen', 'cid': cid})
@@ -150,7 +163,8 @@ async def _invoke(
             # of the async gen in order to be sure the cancel
             # is propagated!
             with cancel_scope as cs:
-                task_status.started(cs)
+                ctx._scope = cs
+                task_status.started(ctx)
                 async with aclosing(coro) as agen:
                     async for item in agen:
                         # TODO: can we send values back in here?
@@ -176,7 +190,8 @@ async def _invoke(
             # manualy construct the response dict-packet-responses as
             # above
             with cancel_scope as cs:
-                task_status.started(cs)
+                ctx._scope = cs
+                task_status.started(ctx)
                 await coro
 
             if not cs.cancelled_caught:
@@ -189,19 +204,26 @@ async def _invoke(
             await chan.send({'functype': 'context', 'cid': cid})
 
             try:
-                async with trio.open_nursery() as scope_nursery:
-                    ctx._scope_nursery = scope_nursery
-                    cs = scope_nursery.cancel_scope
-                    task_status.started(cs)
+                async with trio.open_nursery() as nurse:
+                    ctx._scope_nursery = nurse
+                    ctx._scope = nurse.cancel_scope
+                    task_status.started(ctx)
                     res = await coro
                     await chan.send({'return': res, 'cid': cid})
 
-            except BaseExceptionGroup:
+            # XXX: do we ever trigger this block any more?
+            except (
+                BaseExceptionGroup,
+                trio.Cancelled,
+            ):
                 # if a context error was set then likely
                 # thei multierror was raised due to that
-                if ctx._error is not None:
-                    raise ctx._error from None
+                if ctx._remote_error is not None:
+                    raise ctx._remote_error
 
+                # maybe TODO: pack in ``trio.Cancelled.__traceback__`` here
+                # so they can be unwrapped and displayed on the caller
+                # side?
                 raise
 
             finally:
@@ -213,38 +235,67 @@ async def _invoke(
                 # associated child isn't in debug any more
                 await _debug.maybe_wait_for_debugger()
                 ctx = actor._contexts.pop((chan.uid, cid))
-
                 if ctx:
                     log.runtime(
                         f'Context entrypoint {func} was terminated:\n{ctx}'
                     )
 
-            assert cs
-            if cs.cancelled_caught:
+            if ctx.cancelled_caught:
 
-                # TODO: pack in ``trio.Cancelled.__traceback__`` here
-                # so they can be unwrapped and displayed on the caller
-                # side!
+                # first check for and raise any remote error
+                # before raising any context cancelled case
+                # so that real remote errors don't get masked as
+                # ``ContextCancelled``s.
+                re = ctx._remote_error
+                if re:
+                    ctx._maybe_raise_remote_err(re)
 
                 fname = func.__name__
-                if ctx._cancel_called:
-                    msg = f'`{fname}()` cancelled itself'
+                cs: trio.CancelScope = ctx._scope
+                if cs.cancel_called:
+                    canceller = ctx._cancelled_remote
+                    # await _debug.breakpoint()
 
-                elif cs.cancel_called:
-                    msg = (
-                        f'`{fname}()` was remotely cancelled by its caller '
-                        f'{ctx.chan.uid}'
+                    # NOTE / TODO: if we end up having
+                    # ``Actor._cancel_task()`` call
+                    # ``Context.cancel()`` directly, we're going to
+                    # need to change this logic branch since it will
+                    # always enter..
+                    if ctx._cancel_called:
+                        msg = f'`{fname}()`@{actor.uid} cancelled itself'
+
+                    else:
+                        msg = (
+                            f'`{fname}()`@{actor.uid} '
+                            'was remotely cancelled by '
+                        )
+
+                    # if the channel which spawned the ctx is the
+                    # one that cancelled it then we report that, vs.
+                    # it being some other random actor that for ex.
+                    # some actor who calls `Portal.cancel_actor()`
+                    # and by side-effect cancels this ctx.
+                    if canceller == ctx.chan.uid:
+                        msg += f'its caller {canceller}'
+                    else:
+                        msg += f'remote actor {canceller}'
+
+                    # TODO: does this ever get set any more or can
+                    # we remove it?
+                    if ctx._cancel_msg:
+                        msg += f' with msg:\n{ctx._cancel_msg}'
+
+                    # task-contex was either cancelled by request using
+                    # ``Portal.cancel_actor()`` or ``Context.cancel()``
+                    # on the far end, or it was cancelled by the local
+                    # (callee) task, so relay this cancel signal to the
+                    # other side.
+                    raise ContextCancelled(
+                        msg,
+                        suberror_type=trio.Cancelled,
+                        canceller=canceller,
                     )
 
-                if ctx._cancel_msg:
-                    msg += f' with msg:\n{ctx._cancel_msg}'
-
-                # task-contex was cancelled so relay to the cancel to caller
-                raise ContextCancelled(
-                    msg,
-                    suberror_type=trio.Cancelled,
-                )
-
         else:
             # regular async function
             try:
@@ -259,12 +310,17 @@ async def _invoke(
                     )
 
             with cancel_scope as cs:
-                task_status.started(cs)
+                ctx._scope = cs
+                task_status.started(ctx)
                 result = await coro
-                log.cancel(f'result: {result}')
+                fname = func.__name__
+                log.runtime(f'{fname}() result: {result}')
                 if not failed_resp:
                     # only send result if we know IPC isn't down
-                    await chan.send({'return': result, 'cid': cid})
+                    await chan.send(
+                        {'return': result,
+                         'cid': cid}
+                    )
 
     except (
         Exception,
@@ -307,6 +363,7 @@ async def _invoke(
         # always ship errors back to caller
         err_msg = pack_error(err, tb=tb)
         err_msg['cid'] = cid
+
         try:
             await chan.send(err_msg)
 
@@ -323,14 +380,21 @@ async def _invoke(
                 f"Failed to ship error to caller @ {chan.uid} !?"
             )
 
-        if cs is None:
-            # error is from above code not from rpc invocation
+        # error is probably from above coro running code *not from the
+        # underlyingn rpc invocation* since a scope was never allocated
+        # around actual coroutine await.
+        if ctx._scope is None:
+            # we don't ever raise directly here to allow the
+            # msg-loop-scheduler to continue running for this
+            # channel.
             task_status.started(err)
 
     finally:
         # RPC task bookeeping
         try:
-            scope, func, is_complete = actor._rpc_tasks.pop((chan, cid))
+            ctx, func, is_complete = actor._rpc_tasks.pop(
+                (chan, cid)
+            )
             is_complete.set()
 
         except KeyError:
@@ -339,6 +403,9 @@ async def _invoke(
                 # cancel scope will not have been inserted yet
                 log.warning(
                     f"Task {func} likely errored or cancelled before start")
+            else:
+                log.cancel(f'{func.__name__}({kwargs}) failed?')
+
         finally:
             if not actor._rpc_tasks:
                 log.runtime("All RPC tasks have completed")
@@ -400,16 +467,20 @@ class Actor:
     msg_buffer_size: int = 2**6
 
     # nursery placeholders filled in by `async_main()` after fork
-    _root_n: Optional[trio.Nursery] = None
-    _service_n: Optional[trio.Nursery] = None
-    _server_n: Optional[trio.Nursery] = None
+    _root_n: trio.Nursery | None = None
+    _service_n: trio.Nursery | None = None
+    _server_n: trio.Nursery | None = None
 
     # Information about `__main__` from parent
     _parent_main_data: dict[str, str]
-    _parent_chan_cs: Optional[trio.CancelScope] = None
+    _parent_chan_cs: trio.CancelScope | None = None
 
     # syncs for setup/teardown sequences
-    _server_down: Optional[trio.Event] = None
+    _server_down: trio.Event | None = None
+
+    # user toggled crash handling (including monkey-patched in
+    # `trio.open_nursery()` via `.trionics._supervisor` B)
+    _debug_mode: bool = False
 
     # if started on ``asycio`` running ``trio`` in guest mode
     _infected_aio: bool = False
@@ -425,8 +496,8 @@ class Actor:
         enable_modules: list[str] = [],
         uid: str | None = None,
         loglevel: str | None = None,
-        arbiter_addr: Optional[tuple[str, int]] = None,
-        spawn_method: Optional[str] = None
+        arbiter_addr: tuple[str, int] | None = None,
+        spawn_method: str | None = None
     ) -> None:
         '''
         This constructor is called in the parent actor **before** the spawning
@@ -437,6 +508,7 @@ class Actor:
         self.uid = (name, uid or str(uuid.uuid4()))
 
         self._cancel_complete = trio.Event()
+        self._cancel_called_by_remote: tuple[str, tuple] | None = None
         self._cancel_called: bool = False
 
         # retreive and store parent `__main__` data which
@@ -475,7 +547,7 @@ class Actor:
         # (chan, cid) -> (cancel_scope, func)
         self._rpc_tasks: dict[
             tuple[Channel, str],
-            tuple[trio.CancelScope, Callable, trio.Event]
+            tuple[Context, Callable, trio.Event]
         ] = {}
 
         # map {actor uids -> Context}
@@ -485,9 +557,8 @@ class Actor:
         ] = {}
 
         self._listeners: list[trio.abc.Listener] = []
-        self._parent_chan: Optional[Channel] = None
-        self._forkserver_info: Optional[
-            tuple[Any, Any, Any, Any, Any]] = None
+        self._parent_chan: Channel | None = None
+        self._forkserver_info: tuple | None = None
         self._actoruid2nursery: dict[
             tuple[str, str],
             ActorNursery | None,
@@ -578,7 +649,7 @@ class Actor:
         self._no_more_peers = trio.Event()  # unset
 
         chan = Channel.from_stream(stream)
-        uid: Optional[tuple[str, str]] = chan.uid
+        uid: tuple[str, str] | None = chan.uid
         log.runtime(f"New connection to us {chan}")
 
         # send/receive initial handshake response
@@ -626,7 +697,7 @@ class Actor:
         # append new channel
         self._peers[uid].append(chan)
 
-        local_nursery: Optional[ActorNursery] = None  # noqa
+        local_nursery: ActorNursery | None = None  # noqa
         disconnected: bool = False
 
         # Begin channel management - respond to remote requests and
@@ -650,8 +721,8 @@ class Actor:
             if (
                 local_nursery
             ):
-
-                log.cancel(f"Waiting on cancel request to peer {chan.uid}")
+                if chan._cancel_called:
+                    log.cancel(f"Waiting on cancel request to peer {chan.uid}")
                 # XXX: this is a soft wait on the channel (and its
                 # underlying transport protocol) to close from the
                 # remote peer side since we presume that any channel
@@ -784,75 +855,15 @@ class Actor:
                 f'\n{msg}')
             return
 
-        send_chan = ctx._send_chan
-
-        log.runtime(f"Delivering {msg} from {chan.uid} to caller {cid}")
-
-        # XXX: we do **not** maintain backpressure and instead
-        # opt to relay stream overrun errors to the sender.
-        try:
-            send_chan.send_nowait(msg)
-            # if an error is deteced we should always
-            # expect it to be raised by any context (stream)
-            # consumer task
-            await ctx._maybe_raise_from_remote_msg(msg)
-
-        except trio.BrokenResourceError:
-            # TODO: what is the right way to handle the case where the
-            # local task has already sent a 'stop' / StopAsyncInteration
-            # to the other side but and possibly has closed the local
-            # feeder mem chan? Do we wait for some kind of ack or just
-            # let this fail silently and bubble up (currently)?
-
-            # XXX: local consumer has closed their side
-            # so cancel the far end streaming task
-            log.warning(f"{send_chan} consumer is already closed")
-            return
-
-        except trio.WouldBlock:
-            # XXX: always push an error even if the local
-            # receiver is in overrun state.
-            await ctx._maybe_raise_from_remote_msg(msg)
-
-            uid = chan.uid
-            lines = [
-                'Task context stream was overrun',
-                f'local task: {cid} @ {self.uid}',
-                f'remote sender: {uid}',
-            ]
-            if not ctx._stream_opened:
-                lines.insert(
-                    1,
-                    f'\n*** No stream open on `{self.uid[0]}` side! ***\n'
-                )
-            text = '\n'.join(lines)
-
-            if ctx._backpressure:
-                log.warning(text)
-                try:
-                    await send_chan.send(msg)
-                except trio.BrokenResourceError:
-                    # XXX: local consumer has closed their side
-                    # so cancel the far end streaming task
-                    log.warning(f"{chan} is already closed")
-            else:
-                try:
-                    raise StreamOverrun(text) from None
-                except StreamOverrun as err:
-                    err_msg = pack_error(err)
-                    err_msg['cid'] = cid
-                    try:
-                        await chan.send(err_msg)
-                    except trio.BrokenResourceError:
-                        # XXX: local consumer has closed their side
-                        # so cancel the far end streaming task
-                        log.warning(f"{chan} is already closed")
+        return await ctx._deliver_msg(msg)
 
     def get_context(
         self,
         chan: Channel,
         cid: str,
-        msg_buffer_size: Optional[int] = None,
+
+        msg_buffer_size: int | None = None,
+        allow_overruns: bool = False,
 
     ) -> Context:
         '''
@@ -868,6 +879,7 @@ class Actor:
         assert actor_uid
         try:
             ctx = self._contexts[(actor_uid, cid)]
+            ctx._allow_overruns = allow_overruns
 
             # adjust buffer size if specified
             state = ctx._send_chan._state  # type: ignore
@@ -875,15 +887,11 @@ class Actor:
                 state.max_buffer_size = msg_buffer_size
 
         except KeyError:
-            send_chan: trio.MemorySendChannel
-            recv_chan: trio.MemoryReceiveChannel
-            send_chan, recv_chan = trio.open_memory_channel(
-                msg_buffer_size or self.msg_buffer_size)
-            ctx = Context(
+            ctx = mk_context(
                 chan,
                 cid,
-                _send_chan=send_chan,
-                _recv_chan=recv_chan,
+                msg_buffer_size=msg_buffer_size or self.msg_buffer_size,
+                _allow_overruns=allow_overruns,
             )
             self._contexts[(actor_uid, cid)] = ctx
 
@@ -895,7 +903,8 @@ class Actor:
         ns: str,
         func: str,
         kwargs: dict,
-        msg_buffer_size: Optional[int] = None,
+        msg_buffer_size: int | None = None,
+        allow_overruns: bool = False,
 
     ) -> Context:
         '''
@@ -909,9 +918,16 @@ class Actor:
         '''
         cid = str(uuid.uuid4())
         assert chan.uid
-        ctx = self.get_context(chan, cid, msg_buffer_size=msg_buffer_size)
+        ctx = self.get_context(
+            chan,
+            cid,
+            msg_buffer_size=msg_buffer_size,
+            allow_overruns=allow_overruns,
+        )
         log.runtime(f"Sending cmd to {chan.uid}: {ns}.{func}({kwargs})")
-        await chan.send({'cmd': (ns, func, kwargs, self.uid, cid)})
+        await chan.send(
+            {'cmd': (ns, func, kwargs, self.uid, cid)}
+        )
 
         # Wait on first response msg and validate; this should be
         # immediate.
@@ -921,7 +937,11 @@ class Actor:
         if 'error' in first_msg:
             raise unpack_error(first_msg, chan)
 
-        elif functype not in ('asyncfunc', 'asyncgen', 'context'):
+        elif functype not in (
+            'asyncfunc',
+            'asyncgen',
+            'context',
+        ):
             raise ValueError(f"{first_msg} is an invalid response packet?")
 
         ctx._remote_func_type = functype
@@ -929,8 +949,8 @@ class Actor:
 
     async def _from_parent(
         self,
-        parent_addr: Optional[tuple[str, int]],
-    ) -> tuple[Channel, Optional[tuple[str, int]]]:
+        parent_addr: tuple[str, int] | None,
+    ) -> tuple[Channel, tuple[str, int] | None]:
         try:
             # Connect back to the parent actor and conduct initial
             # handshake. From this point on if we error, we
@@ -943,7 +963,7 @@ class Actor:
             # Initial handshake: swap names.
             await self._do_handshake(chan)
 
-            accept_addr: Optional[tuple[str, int]] = None
+            accept_addr: tuple[str, int] | None = None
 
             if self._spawn_method == "trio":
                 # Receive runtime state from our parent
@@ -980,7 +1000,7 @@ class Actor:
             log.warning(
                 f"Failed to connect to parent @ {parent_addr},"
                 " closing server")
-            await self.cancel()
+            await self.cancel(requesting_uid=self.uid)
             raise
 
     async def _serve_forever(
@@ -1002,7 +1022,7 @@ class Actor:
         self._server_down = trio.Event()
         try:
             async with trio.open_nursery() as server_n:
-                l: list[trio.abc.Listener] = await server_n.start(
+                listeners: list[trio.abc.Listener] = await server_n.start(
                     partial(
                         trio.serve_tcp,
                         self._stream_handler,
@@ -1013,10 +1033,13 @@ class Actor:
                         host=accept_host,
                     )
                 )
+                sockets: list[trio.socket] = [
+                    getattr(listener, 'socket', 'unknown socket')
+                    for listener in listeners
+                ]
                 log.runtime(
-                    "Started tcp server(s) on"
-                    f" {[getattr(l, 'socket', 'unknown socket') for l in l]}")
-                self._listeners.extend(l)
+                    f'Started tcp server(s) on {sockets}')
+                self._listeners.extend(listeners)
                 task_status.started(server_n)
         finally:
             # signal the server is down since nursery above terminated
@@ -1033,7 +1056,11 @@ class Actor:
         assert self._service_n
         self._service_n.start_soon(self.cancel)
 
-    async def cancel(self) -> bool:
+    async def cancel(
+        self,
+        requesting_uid: tuple[str, str],
+
+    ) -> bool:
         '''
         Cancel this actor's runtime.
 
@@ -1047,6 +1074,7 @@ class Actor:
 
         '''
         log.cancel(f"{self.uid} is trying to cancel")
+        self._cancel_called_by_remote: tuple = requesting_uid
         self._cancel_called = True
 
         # cancel all ongoing rpc tasks
@@ -1060,7 +1088,7 @@ class Actor:
                 dbcs.cancel()
 
             # kill all ongoing tasks
-            await self.cancel_rpc_tasks()
+            await self.cancel_rpc_tasks(requesting_uid=requesting_uid)
 
             # stop channel server
             self.cancel_server()
@@ -1086,7 +1114,13 @@ class Actor:
     #         for n in root.child_nurseries:
     #             n.cancel_scope.cancel()
 
-    async def _cancel_task(self, cid, chan):
+    async def _cancel_task(
+        self,
+        cid: str,
+        chan: Channel,
+
+        requesting_uid: tuple[str, str] | None = None,
+    ) -> bool:
         '''
         Cancel a local task by call-id / channel.
 
@@ -1101,35 +1135,51 @@ class Actor:
         try:
             # this ctx based lookup ensures the requested task to
             # be cancelled was indeed spawned by a request from this channel
-            scope, func, is_complete = self._rpc_tasks[(chan, cid)]
+            ctx, func, is_complete = self._rpc_tasks[(chan, cid)]
+            scope = ctx._scope
         except KeyError:
             log.cancel(f"{cid} has already completed/terminated?")
-            return
+            return True
 
         log.cancel(
             f"Cancelling task:\ncid: {cid}\nfunc: {func}\n"
             f"peer: {chan.uid}\n")
 
+        if (
+            ctx._cancelled_remote is None
+            and requesting_uid
+        ):
+            ctx._cancelled_remote: tuple = requesting_uid
+
         # don't allow cancelling this function mid-execution
         # (is this necessary?)
         if func is self._cancel_task:
-            return
+            return True
 
+        # TODO: shouldn't we eventually be calling ``Context.cancel()``
+        # directly here instead (since that method can handle both
+        # side's calls into it?
         scope.cancel()
 
         # wait for _invoke to mark the task complete
         log.runtime(
-            f"Waiting on task to cancel:\ncid: {cid}\nfunc: {func}\n"
-            f"peer: {chan.uid}\n")
+            'Waiting on task to cancel:\n'
+            f'cid: {cid}\nfunc: {func}\n'
+            f'peer: {chan.uid}\n'
+        )
         await is_complete.wait()
 
         log.runtime(
             f"Sucessfully cancelled task:\ncid: {cid}\nfunc: {func}\n"
             f"peer: {chan.uid}\n")
 
+        return True
+
     async def cancel_rpc_tasks(
         self,
-        only_chan: Optional[Channel] = None,
+        only_chan: Channel | None = None,
+        requesting_uid: tuple[str, str] | None = None,
+
     ) -> None:
         '''
         Cancel all existing RPC responder tasks using the cancel scope
@@ -1141,7 +1191,7 @@ class Actor:
             log.cancel(f"Cancelling all {len(tasks)} rpc tasks:\n{tasks} ")
             for (
                 (chan, cid),
-                (scope, func, is_complete),
+                (ctx, func, is_complete),
             ) in tasks.copy().items():
                 if only_chan is not None:
                     if only_chan != chan:
@@ -1149,7 +1199,11 @@ class Actor:
 
                 # TODO: this should really done in a nursery batch
                 if func != self._cancel_task:
-                    await self._cancel_task(cid, chan)
+                    await self._cancel_task(
+                        cid,
+                        chan,
+                        requesting_uid=requesting_uid,
+                    )
 
             log.cancel(
                 f"Waiting for remaining rpc tasks to complete {tasks}")
@@ -1166,7 +1220,7 @@ class Actor:
             self._server_n.cancel_scope.cancel()
 
     @property
-    def accept_addr(self) -> Optional[tuple[str, int]]:
+    def accept_addr(self) -> tuple[str, int] | None:
         '''
         Primary address to which the channel server is bound.
 
@@ -1218,7 +1272,7 @@ class Actor:
 
 async def async_main(
     actor: Actor,
-    accept_addr: Optional[tuple[str, int]] = None,
+    accept_addr: tuple[str, int] | None = None,
 
     # XXX: currently ``parent_addr`` is only needed for the
     # ``multiprocessing`` backend (which pickles state sent to
@@ -1227,7 +1281,7 @@ async def async_main(
     # change this to a simple ``is_subactor: bool`` which will
     # be False when running as root actor and True when as
     # a subactor.
-    parent_addr: Optional[tuple[str, int]] = None,
+    parent_addr: tuple[str, int] | None = None,
     task_status: TaskStatus[None] = trio.TASK_STATUS_IGNORED,
 
 ) -> None:
@@ -1235,8 +1289,8 @@ async def async_main(
     Actor runtime entrypoint; start the IPC channel server, maybe connect
     back to the parent, and startup all core machinery tasks.
 
-    A "root-most" (or "top-level") nursery for this actor is opened here
-    and when cancelled effectively cancels the actor.
+    A "root" (or "top-level") nursery for this actor is opened here and
+    when cancelled/terminated effectively closes the actor's "runtime".
 
     '''
     # attempt to retreive ``trio``'s sigint handler and stash it
@@ -1330,13 +1384,15 @@ async def async_main(
                         )
                     )
                 log.runtime("Waiting on service nursery to complete")
-            log.runtime("Service nursery complete")
-            log.runtime("Waiting on root nursery to complete")
+            log.runtime(
+                "Service nursery complete\n"
+                "Waiting on root nursery to complete"
+            )
 
         # Blocks here as expected until the root nursery is
         # killed (i.e. this actor is cancelled or signalled by the parent)
     except Exception as err:
-        log.info("Closing all actor lifetime contexts")
+        log.runtime("Closing all actor lifetime contexts")
         actor.lifetime_stack.close()
 
         if not registered_with_arbiter:
@@ -1357,7 +1413,14 @@ async def async_main(
             await try_ship_error_to_parent(actor._parent_chan, err)
 
         # always!
-        log.exception("Actor errored:")
+        match err:
+            case ContextCancelled():
+                log.cancel(
+                    f'Actor: {actor.uid} was task-context-cancelled with,\n'
+                    f'str(err)'
+                )
+            case _:
+                log.exception("Actor errored:")
         raise
 
     finally:
@@ -1424,15 +1487,16 @@ async def process_messages(
 
 ) -> bool:
     '''
-    Process messages for the IPC transport channel async-RPC style.
+    This is the per-channel, low level RPC task scheduler loop.
 
-    Receive multiplexed RPC requests, spawn handler tasks and deliver
-    responses over or boxed errors back to the "caller" task.
+    Receive multiplexed RPC request messages from some remote process,
+    spawn handler tasks depending on request type and deliver responses
+    or boxed errors back to the remote caller (task).
 
     '''
     # TODO: once https://github.com/python-trio/trio/issues/467 gets
     # worked out we'll likely want to use that!
-    msg = None
+    msg: dict | None = None
     nursery_cancelled_before_task: bool = False
 
     log.runtime(f"Entering msg loop for {chan} from {chan.uid}")
@@ -1454,7 +1518,10 @@ async def process_messages(
 
                     for (channel, cid) in actor._rpc_tasks.copy():
                         if channel is chan:
-                            await actor._cancel_task(cid, channel)
+                            await actor._cancel_task(
+                                cid,
+                                channel,
+                            )
 
                     log.runtime(
                             f"Msg loop signalled to terminate for"
@@ -1468,12 +1535,14 @@ async def process_messages(
                 cid = msg.get('cid')
                 if cid:
                     # deliver response to local caller/waiter
+                    # via its per-remote-context memory channel.
                     await actor._push_result(chan, cid, msg)
 
                     log.runtime(
                         f"Waiting on next msg for {chan} from {chan.uid}")
                     continue
 
+                # TODO: implement with ``match:`` syntax?
                 # process command request
                 try:
                     ns, funcname, kwargs, actorid, cid = msg['cmd']
@@ -1493,13 +1562,12 @@ async def process_messages(
                     f"{ns}.{funcname}({kwargs})")
 
                 if ns == 'self':
-                    func = getattr(actor, funcname)
-
                     if funcname == 'cancel':
+                        func = actor.cancel
+                        kwargs['requesting_uid'] = chan.uid
 
-                        # don't start entire actor runtime
-                        # cancellation if this actor is in debug
-                        # mode
+                        # don't start entire actor runtime cancellation
+                        # if this actor is currently in debug mode!
                         pdb_complete = _debug.Lock.local_pdb_complete
                         if pdb_complete:
                             await pdb_complete.wait()
@@ -1511,43 +1579,56 @@ async def process_messages(
                             # msg loop and break out into
                             # ``async_main()``
                             log.cancel(
-                                f"Actor {actor.uid} was remotely cancelled "
+                                "Actor runtime for was remotely cancelled "
                                 f"by {chan.uid}"
                             )
                             await _invoke(
-                                actor, cid, chan, func, kwargs, is_rpc=False
+                                actor,
+                                cid,
+                                chan,
+                                func,
+                                kwargs,
+                                is_rpc=False,
                             )
 
+                        log.cancel(
+                            f'Cancelling msg loop for {chan.uid}'
+                        )
                         loop_cs.cancel()
                         break
 
                     if funcname == '_cancel_task':
+                        func = actor._cancel_task
 
                         # we immediately start the runtime machinery
                         # shutdown
-                        with trio.CancelScope(shield=True):
-                            # actor.cancel() was called so kill this
-                            # msg loop and break out into
-                            # ``async_main()``
-                            kwargs['chan'] = chan
-                            log.cancel(
-                                f'Remote request to cancel task\n'
-                                f'remote actor: {chan.uid}\n'
-                                f'task: {cid}'
+                        # with trio.CancelScope(shield=True):
+                        kwargs['chan'] = chan
+                        target_cid = kwargs['cid']
+                        kwargs['requesting_uid'] = chan.uid
+                        log.cancel(
+                            f'Remote request to cancel task\n'
+                            f'remote actor: {chan.uid}\n'
+                            f'task: {target_cid}'
+                        )
+                        try:
+                            await _invoke(
+                                actor,
+                                cid,
+                                chan,
+                                func,
+                                kwargs,
+                                is_rpc=False,
                             )
-                            try:
-                                await _invoke(
-                                    actor,
-                                    cid,
-                                    chan,
-                                    func,
-                                    kwargs,
-                                    is_rpc=False,
-                                )
-                            except BaseException:
-                                log.exception("failed to cancel task?")
+                        except BaseException:
+                            log.exception("failed to cancel task?")
+
+                        continue
+                    else:
+                        # normally registry methods, eg.
+                        # ``.register_actor()`` etc.
+                        func = getattr(actor, funcname)
 
-                            continue
                 else:
                     # complain to client about restricted modules
                     try:
@@ -1562,34 +1643,49 @@ async def process_messages(
                 log.runtime(f"Spawning task for {func}")
                 assert actor._service_n
                 try:
-                    cs = await actor._service_n.start(
-                        partial(_invoke, actor, cid, chan, func, kwargs),
+                    ctx: Context = await actor._service_n.start(
+                        partial(
+                            _invoke,
+                            actor,
+                            cid,
+                            chan,
+                            func,
+                            kwargs,
+                        ),
                         name=funcname,
                     )
+
                 except (
                     RuntimeError,
                     BaseExceptionGroup,
                 ):
                     # avoid reporting a benign race condition
                     # during actor runtime teardown.
-                    nursery_cancelled_before_task = True
+                    nursery_cancelled_before_task: bool = True
                     break
 
-                # never allow cancelling cancel requests (results in
-                # deadlock and other weird behaviour)
-                # if func != actor.cancel:
-                if isinstance(cs, Exception):
+                # in the lone case where a ``Context`` is not
+                # delivered, it's likely going to be a locally
+                # scoped exception from ``_invoke()`` itself.
+                if isinstance(ctx, Exception):
                     log.warning(
                         f"Task for RPC func {func} failed with"
-                        f"{cs}")
+                        f"{ctx}"
+                    )
+                    continue
+
                 else:
                     # mark that we have ongoing rpc tasks
                     actor._ongoing_rpc_tasks = trio.Event()
                     log.runtime(f"RPC func is {func}")
+
                     # store cancel scope such that the rpc task can be
                     # cancelled gracefully if requested
                     actor._rpc_tasks[(chan, cid)] = (
-                        cs, func, trio.Event())
+                        ctx,
+                        func,
+                        trio.Event(),
+                    )
 
                 log.runtime(
                     f"Waiting on next msg for {chan} from {chan.uid}")
@@ -1630,7 +1726,15 @@ async def process_messages(
         else:
             # ship any "internal" exception (i.e. one from internal
             # machinery not from an rpc task) to parent
-            log.exception("Actor errored:")
+            match err:
+                case ContextCancelled():
+                    log.cancel(
+                        f'Actor: {actor.uid} was context-cancelled with,\n'
+                        f'str(err)'
+                    )
+                case _:
+                    log.exception("Actor errored:")
+
             if actor._parent_chan:
                 await try_ship_error_to_parent(actor._parent_chan, err)
 
@@ -1642,7 +1746,8 @@ async def process_messages(
         # msg debugging for when he machinery is brokey
         log.runtime(
             f"Exiting msg loop for {chan} from {chan.uid} "
-            f"with last msg:\n{msg}")
+            f"with last msg:\n{msg}"
+        )
 
     # transport **was not** disconnected
     return False

tractor/_shm.py

@@ -0,0 +1,828 @@
+# tractor: structured concurrent "actors".
+# Copyright 2018-eternity Tyler Goodlet.
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+"""
+SC friendly shared memory management geared at real-time
+processing.
+
+Support for ``numpy`` compatible array-buffers is provided but is
+considered optional within the context of this runtime-library.
+
+"""
+from __future__ import annotations
+from sys import byteorder
+import time
+from typing import Optional
+from multiprocessing import shared_memory as shm
+from multiprocessing.shared_memory import (
+    SharedMemory,
+    ShareableList,
+)
+
+from msgspec import Struct
+import tractor
+
+from .log import get_logger
+
+
+_USE_POSIX = getattr(shm, '_USE_POSIX', False)
+if _USE_POSIX:
+    from _posixshmem import shm_unlink
+
+
+try:
+    import numpy as np
+    from numpy.lib import recfunctions as rfn
+    import nptyping
+except ImportError:
+    pass
+
+
+log = get_logger(__name__)
+
+
+def disable_mantracker():
+    '''
+    Disable all ``multiprocessing``` "resource tracking" machinery since
+    it's an absolute multi-threaded mess of non-SC madness.
+
+    '''
+    from multiprocessing import resource_tracker as mantracker
+
+    # Tell the "resource tracker" thing to fuck off.
+    class ManTracker(mantracker.ResourceTracker):
+        def register(self, name, rtype):
+            pass
+
+        def unregister(self, name, rtype):
+            pass
+
+        def ensure_running(self):
+            pass
+
+    # "know your land and know your prey"
+    # https://www.dailymotion.com/video/x6ozzco
+    mantracker._resource_tracker = ManTracker()
+    mantracker.register = mantracker._resource_tracker.register
+    mantracker.ensure_running = mantracker._resource_tracker.ensure_running
+    mantracker.unregister = mantracker._resource_tracker.unregister
+    mantracker.getfd = mantracker._resource_tracker.getfd
+
+
+disable_mantracker()
+
+
+class SharedInt:
+    '''
+    Wrapper around a single entry shared memory array which
+    holds an ``int`` value used as an index counter.
+
+    '''
+    def __init__(
+        self,
+        shm: SharedMemory,
+    ) -> None:
+        self._shm = shm
+
+    @property
+    def value(self) -> int:
+        return int.from_bytes(self._shm.buf, byteorder)
+
+    @value.setter
+    def value(self, value) -> None:
+        self._shm.buf[:] = value.to_bytes(self._shm.size, byteorder)
+
+    def destroy(self) -> None:
+        if _USE_POSIX:
+            # We manually unlink to bypass all the "resource tracker"
+            # nonsense meant for non-SC systems.
+            name = self._shm.name
+            try:
+                shm_unlink(name)
+            except FileNotFoundError:
+                # might be a teardown race here?
+                log.warning(f'Shm for {name} already unlinked?')
+
+
+class NDToken(Struct, frozen=True):
+    '''
+    Internal represenation of a shared memory ``numpy`` array "token"
+    which can be used to key and load a system (OS) wide shm entry
+    and correctly read the array by type signature.
+
+    This type is msg safe.
+
+    '''
+    shm_name: str  # this servers as a "key" value
+    shm_first_index_name: str
+    shm_last_index_name: str
+    dtype_descr: tuple
+    size: int  # in struct-array index / row terms
+
+    # TODO: use nptyping here on dtypes
+    @property
+    def dtype(self) -> list[tuple[str, str, tuple[int, ...]]]:
+        return np.dtype(
+            list(
+                map(tuple, self.dtype_descr)
+            )
+        ).descr
+
+    def as_msg(self):
+        return self.to_dict()
+
+    @classmethod
+    def from_msg(cls, msg: dict) -> NDToken:
+        if isinstance(msg, NDToken):
+            return msg
+
+        # TODO: native struct decoding
+        # return _token_dec.decode(msg)
+
+        msg['dtype_descr'] = tuple(map(tuple, msg['dtype_descr']))
+        return NDToken(**msg)
+
+
+# _token_dec = msgspec.msgpack.Decoder(NDToken)
+
+# TODO: this api?
+# _known_tokens = tractor.ActorVar('_shm_tokens', {})
+# _known_tokens = tractor.ContextStack('_known_tokens', )
+# _known_tokens = trio.RunVar('shms', {})
+
+# TODO: this should maybe be provided via
+# a `.trionics.maybe_open_context()` wrapper factory?
+# process-local store of keys to tokens
+_known_tokens: dict[str, NDToken] = {}
+
+
+def get_shm_token(key: str) -> NDToken | None:
+    '''
+    Convenience func to check if a token
+    for the provided key is known by this process.
+
+    Returns either the ``numpy`` token or a string for a shared list.
+
+    '''
+    return _known_tokens.get(key)
+
+
+def _make_token(
+    key: str,
+    size: int,
+    dtype: np.dtype,
+
+) -> NDToken:
+    '''
+    Create a serializable token that can be used
+    to access a shared array.
+
+    '''
+    return NDToken(
+        shm_name=key,
+        shm_first_index_name=key + "_first",
+        shm_last_index_name=key + "_last",
+        dtype_descr=tuple(np.dtype(dtype).descr),
+        size=size,
+    )
+
+
+class ShmArray:
+    '''
+    A shared memory ``numpy.ndarray`` API.
+
+    An underlying shared memory buffer is allocated based on
+    a user specified ``numpy.ndarray``. This fixed size array
+    can be read and written to by pushing data both onto the "front"
+    or "back" of a set index range. The indexes for the "first" and
+    "last" index are themselves stored in shared memory (accessed via
+    ``SharedInt`` interfaces) values such that multiple processes can
+    interact with the same array using a synchronized-index.
+
+    '''
+    def __init__(
+        self,
+        shmarr: np.ndarray,
+        first: SharedInt,
+        last: SharedInt,
+        shm: SharedMemory,
+        # readonly: bool = True,
+    ) -> None:
+        self._array = shmarr
+
+        # indexes for first and last indices corresponding
+        # to fille data
+        self._first = first
+        self._last = last
+
+        self._len = len(shmarr)
+        self._shm = shm
+        self._post_init: bool = False
+
+        # pushing data does not write the index (aka primary key)
+        self._write_fields: list[str] | None = None
+        dtype = shmarr.dtype
+        if dtype.fields:
+            self._write_fields = list(shmarr.dtype.fields.keys())[1:]
+
+    # TODO: ringbuf api?
+
+    @property
+    def _token(self) -> NDToken:
+        return NDToken(
+            shm_name=self._shm.name,
+            shm_first_index_name=self._first._shm.name,
+            shm_last_index_name=self._last._shm.name,
+            dtype_descr=tuple(self._array.dtype.descr),
+            size=self._len,
+        )
+
+    @property
+    def token(self) -> dict:
+        """Shared memory token that can be serialized and used by
+        another process to attach to this array.
+        """
+        return self._token.as_msg()
+
+    @property
+    def index(self) -> int:
+        return self._last.value % self._len
+
+    @property
+    def array(self) -> np.ndarray:
+        '''
+        Return an up-to-date ``np.ndarray`` view of the
+        so-far-written data to the underlying shm buffer.
+
+        '''
+        a = self._array[self._first.value:self._last.value]
+
+        # first, last = self._first.value, self._last.value
+        # a = self._array[first:last]
+
+        # TODO: eventually comment this once we've not seen it in the
+        # wild in a long time..
+        # XXX: race where first/last indexes cause a reader
+        # to load an empty array..
+        if len(a) == 0 and self._post_init:
+            raise RuntimeError('Empty array race condition hit!?')
+            # breakpoint()
+
+        return a
+
+    def ustruct(
+        self,
+        fields: Optional[list[str]] = None,
+
+        # type that all field values will be cast to in the returned
+        # view.
+        common_dtype: np.dtype = np.float64,  # type: ignore
+
+    ) -> np.ndarray:
+
+        array = self._array
+
+        if fields:
+            selection = array[fields]
+            # fcount = len(fields)
+        else:
+            selection = array
+            # fcount = len(array.dtype.fields)
+
+        # XXX: manual ``.view()`` attempt that also doesn't work.
+        # uview = selection.view(
+        #     dtype='<f16',
+        # ).reshape(-1, 4, order='A')
+
+        # assert len(selection) == len(uview)
+
+        u = rfn.structured_to_unstructured(
+            selection,
+            # dtype=float,
+            copy=True,
+        )
+
+        # unstruct = np.ndarray(u.shape, dtype=a.dtype, buffer=shm.buf)
+        # array[:] = a[:]
+        return u
+        # return ShmArray(
+        #     shmarr=u,
+        #     first=self._first,
+        #     last=self._last,
+        #     shm=self._shm
+        # )
+
+    def last(
+        self,
+        length: int = 1,
+
+    ) -> np.ndarray:
+        '''
+        Return the last ``length``'s worth of ("row") entries from the
+        array.
+
+        '''
+        return self.array[-length:]
+
+    def push(
+        self,
+        data: np.ndarray,
+
+        field_map: Optional[dict[str, str]] = None,
+        prepend: bool = False,
+        update_first: bool = True,
+        start: Optional[int] = None,
+
+    ) -> int:
+        '''
+        Ring buffer like "push" to append data
+        into the buffer and return updated "last" index.
+
+        NB: no actual ring logic yet to give a "loop around" on overflow
+        condition, lel.
+
+        '''
+        length = len(data)
+
+        if prepend:
+            index = (start or self._first.value) - length
+
+            if index < 0:
+                raise ValueError(
+                    f'Array size of {self._len} was overrun during prepend.\n'
+                    f'You have passed {abs(index)} too many datums.'
+                )
+
+        else:
+            index = start if start is not None else self._last.value
+
+        end = index + length
+
+        if field_map:
+            src_names, dst_names = zip(*field_map.items())
+        else:
+            dst_names = src_names = self._write_fields
+
+        try:
+            self._array[
+                list(dst_names)
+            ][index:end] = data[list(src_names)][:]
+
+            # NOTE: there was a race here between updating
+            # the first and last indices and when the next reader
+            # tries to access ``.array`` (which due to the index
+            # overlap will be empty). Pretty sure we've fixed it now
+            # but leaving this here as a reminder.
+            if prepend and update_first and length:
+                assert index < self._first.value
+
+            if (
+                index < self._first.value
+                and update_first
+            ):
+                assert prepend, 'prepend=True not passed but index decreased?'
+                self._first.value = index
+
+            elif not prepend:
+                self._last.value = end
+
+            self._post_init = True
+            return end
+
+        except ValueError as err:
+            if field_map:
+                raise
+
+            # should raise if diff detected
+            self.diff_err_fields(data)
+            raise err
+
+    def diff_err_fields(
+        self,
+        data: np.ndarray,
+    ) -> None:
+        # reraise with any field discrepancy
+        our_fields, their_fields = (
+            set(self._array.dtype.fields),
+            set(data.dtype.fields),
+        )
+
+        only_in_ours = our_fields - their_fields
+        only_in_theirs = their_fields - our_fields
+
+        if only_in_ours:
+            raise TypeError(
+                f"Input array is missing field(s): {only_in_ours}"
+            )
+        elif only_in_theirs:
+            raise TypeError(
+                f"Input array has unknown field(s): {only_in_theirs}"
+            )
+
+    # TODO: support "silent" prepends that don't update ._first.value?
+    def prepend(
+        self,
+        data: np.ndarray,
+    ) -> int:
+        end = self.push(data, prepend=True)
+        assert end
+
+    def close(self) -> None:
+        self._first._shm.close()
+        self._last._shm.close()
+        self._shm.close()
+
+    def destroy(self) -> None:
+        if _USE_POSIX:
+            # We manually unlink to bypass all the "resource tracker"
+            # nonsense meant for non-SC systems.
+            shm_unlink(self._shm.name)
+
+        self._first.destroy()
+        self._last.destroy()
+
+    def flush(self) -> None:
+        # TODO: flush to storage backend like markestore?
+        ...
+
+
+def open_shm_ndarray(
+    key: Optional[str] = None,
+    size: int = int(2 ** 10),
+    dtype: np.dtype | None = None,
+    append_start_index: int = 0,
+    readonly: bool = False,
+
+) -> ShmArray:
+    '''
+    Open a memory shared ``numpy`` using the standard library.
+
+    This call unlinks (aka permanently destroys) the buffer on teardown
+    and thus should be used from the parent-most accessor (process).
+
+    '''
+    # create new shared mem segment for which we
+    # have write permission
+    a = np.zeros(size, dtype=dtype)
+    a['index'] = np.arange(len(a))
+
+    shm = SharedMemory(
+        name=key,
+        create=True,
+        size=a.nbytes
+    )
+    array = np.ndarray(
+        a.shape,
+        dtype=a.dtype,
+        buffer=shm.buf
+    )
+    array[:] = a[:]
+    array.setflags(write=int(not readonly))
+
+    token = _make_token(
+        key=key,
+        size=size,
+        dtype=dtype,
+    )
+
+    # create single entry arrays for storing an first and last indices
+    first = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_first_index_name,
+            create=True,
+            size=4,  # std int
+        )
+    )
+
+    last = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_last_index_name,
+            create=True,
+            size=4,  # std int
+        )
+    )
+
+    # Start the "real-time" append-updated (or "pushed-to") section
+    # after some start index: ``append_start_index``. This allows appending
+    # from a start point in the array which isn't the 0 index and looks
+    # something like,
+    # -------------------------
+    # |              |        i
+    # _________________________
+    # <-------------> <------->
+    #  history         real-time
+    #
+    # Once fully "prepended", the history section will leave the
+    # ``ShmArray._start.value: int = 0`` and the yet-to-be written
+    # real-time section will start at ``ShmArray.index: int``.
+
+    # this sets the index to 3/4 of the length of the buffer
+    # leaving a "days worth of second samples" for the real-time
+    # section.
+    last.value = first.value = append_start_index
+
+    shmarr = ShmArray(
+        array,
+        first,
+        last,
+        shm,
+    )
+
+    assert shmarr._token == token
+    _known_tokens[key] = shmarr.token
+
+    # "unlink" created shm on process teardown by
+    # pushing teardown calls onto actor context stack
+    stack = tractor.current_actor().lifetime_stack
+    stack.callback(shmarr.close)
+    stack.callback(shmarr.destroy)
+
+    return shmarr
+
+
+def attach_shm_ndarray(
+    token: tuple[str, str, tuple[str, str]],
+    readonly: bool = True,
+
+) -> ShmArray:
+    '''
+    Attach to an existing shared memory array previously
+    created by another process using ``open_shared_array``.
+
+    No new shared mem is allocated but wrapper types for read/write
+    access are constructed.
+
+    '''
+    token = NDToken.from_msg(token)
+    key = token.shm_name
+
+    if key in _known_tokens:
+        assert NDToken.from_msg(_known_tokens[key]) == token, "WTF"
+
+    # XXX: ugh, looks like due to the ``shm_open()`` C api we can't
+    # actually place files in a subdir, see discussion here:
+    # https://stackoverflow.com/a/11103289
+
+    # attach to array buffer and view as per dtype
+    _err: Optional[Exception] = None
+    for _ in range(3):
+        try:
+            shm = SharedMemory(
+                name=key,
+                create=False,
+            )
+            break
+        except OSError as oserr:
+            _err = oserr
+            time.sleep(0.1)
+    else:
+        if _err:
+            raise _err
+
+    shmarr = np.ndarray(
+        (token.size,),
+        dtype=token.dtype,
+        buffer=shm.buf
+    )
+    shmarr.setflags(write=int(not readonly))
+
+    first = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_first_index_name,
+            create=False,
+            size=4,  # std int
+        ),
+    )
+    last = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_last_index_name,
+            create=False,
+            size=4,  # std int
+        ),
+    )
+
+    # make sure we can read
+    first.value
+
+    sha = ShmArray(
+        shmarr,
+        first,
+        last,
+        shm,
+    )
+    # read test
+    sha.array
+
+    # Stash key -> token knowledge for future queries
+    # via `maybe_opepn_shm_array()` but only after we know
+    # we can attach.
+    if key not in _known_tokens:
+        _known_tokens[key] = token
+
+    # "close" attached shm on actor teardown
+    tractor.current_actor().lifetime_stack.callback(sha.close)
+
+    return sha
+
+
+def maybe_open_shm_ndarray(
+    key: str,  # unique identifier for segment
+
+    # from ``open_shm_array()``
+    size: int = int(2 ** 10),  # array length in index terms
+    dtype: np.dtype | None = None,
+    append_start_index: int = 0,
+    readonly: bool = True,
+
+) -> tuple[ShmArray, bool]:
+    '''
+    Attempt to attach to a shared memory block using a "key" lookup
+    to registered blocks in the users overall "system" registry
+    (presumes you don't have the block's explicit token).
+
+    This function is meant to solve the problem of discovering whether
+    a shared array token has been allocated or discovered by the actor
+    running in **this** process. Systems where multiple actors may seek
+    to access a common block can use this function to attempt to acquire
+    a token as discovered by the actors who have previously stored
+    a "key" -> ``NDToken`` map in an actor local (aka python global)
+    variable.
+
+    If you know the explicit ``NDToken`` for your memory segment instead
+    use ``attach_shm_array``.
+
+    '''
+    try:
+        # see if we already know this key
+        token = _known_tokens[key]
+        return (
+            attach_shm_ndarray(
+                token=token,
+                readonly=readonly,
+            ),
+            False,  # not newly opened
+        )
+    except KeyError:
+        log.warning(f"Could not find {key} in shms cache")
+        if dtype:
+            token = _make_token(
+                key,
+                size=size,
+                dtype=dtype,
+            )
+        else:
+
+            try:
+                return (
+                    attach_shm_ndarray(
+                        token=token,
+                        readonly=readonly,
+                    ),
+                    False,
+                )
+            except FileNotFoundError:
+                log.warning(f"Could not attach to shm with token {token}")
+
+        # This actor does not know about memory
+        # associated with the provided "key".
+        # Attempt to open a block and expect
+        # to fail if a block has been allocated
+        # on the OS by someone else.
+        return (
+            open_shm_ndarray(
+                key=key,
+                size=size,
+                dtype=dtype,
+                append_start_index=append_start_index,
+                readonly=readonly,
+            ),
+            True,
+        )
+
+
+class ShmList(ShareableList):
+    '''
+    Carbon copy of ``.shared_memory.ShareableList`` with a few
+    enhancements:
+
+    - readonly mode via instance var flag  `._readonly: bool`
+    - ``.__getitem__()`` accepts ``slice`` inputs
+    - exposes the underlying buffer "name" as a ``.key: str``
+
+    '''
+    def __init__(
+        self,
+        sequence: list | None = None,
+        *,
+        name: str | None = None,
+        readonly: bool = True
+
+    ) -> None:
+        self._readonly = readonly
+        self._key = name
+        return super().__init__(
+            sequence=sequence,
+            name=name,
+        )
+
+    @property
+    def key(self) -> str:
+        return self._key
+
+    @property
+    def readonly(self) -> bool:
+        return self._readonly
+
+    def __setitem__(
+        self,
+        position,
+        value,
+
+    ) -> None:
+
+        # mimick ``numpy`` error
+        if self._readonly:
+            raise ValueError('assignment destination is read-only')
+
+        return super().__setitem__(position, value)
+
+    def __getitem__(
+        self,
+        indexish,
+    ) -> list:
+
+        # NOTE: this is a non-writeable view (copy?) of the buffer
+        # in a new list instance.
+        if isinstance(indexish, slice):
+            return list(self)[indexish]
+
+        return super().__getitem__(indexish)
+
+    # TODO: should we offer a `.array` and `.push()` equivalent
+    # to the `ShmArray`?
+    # currently we have the following limitations:
+    # - can't write slices of input using traditional slice-assign
+    #   syntax due to the ``ShareableList.__setitem__()`` implementation.
+    # - ``list(shmlist)`` returns a non-mutable copy instead of
+    #   a writeable view which would be handier numpy-style ops.
+
+
+def open_shm_list(
+    key: str,
+    sequence: list | None = None,
+    size: int = int(2 ** 10),
+    dtype: float | int | bool | str | bytes | None = float,
+    readonly: bool = True,
+
+) -> ShmList:
+
+    if sequence is None:
+        default = {
+            float: 0.,
+            int: 0,
+            bool: True,
+            str: 'doggy',
+            None: None,
+        }[dtype]
+        sequence = [default] * size
+
+    shml = ShmList(
+        sequence=sequence,
+        name=key,
+        readonly=readonly,
+    )
+
+    # "close" attached shm on actor teardown
+    try:
+        actor = tractor.current_actor()
+        actor.lifetime_stack.callback(shml.shm.close)
+        actor.lifetime_stack.callback(shml.shm.unlink)
+    except RuntimeError:
+        log.warning('tractor runtime not active, skipping teardown steps')
+
+    return shml
+
+
+def attach_shm_list(
+    key: str,
+    readonly: bool = False,
+
+) -> ShmList:
+
+    return ShmList(
+        name=key,
+        readonly=readonly,
+    )

tractor/_spawn.py

@@ -19,6 +19,7 @@ Machinery for actor process spawning using multiple backends.
 
 """
 from __future__ import annotations
+import multiprocessing as mp
 import sys
 import platform
 from typing import (
@@ -53,7 +54,6 @@ from ._exceptions import ActorFailure
 
 if TYPE_CHECKING:
     from ._supervise import ActorNursery
-    import multiprocessing as mp
     ProcessType = TypeVar('ProcessType', mp.Process, trio.Process)
 
 log = get_logger('tractor')
@@ -70,7 +70,6 @@ _spawn_method: SpawnMethodKey = 'trio'
 
 if platform.system() == 'Windows':
 
-    import multiprocessing as mp
     _ctx = mp.get_context("spawn")
 
     async def proc_waiter(proc: mp.Process) -> None:
@@ -457,7 +456,7 @@ async def trio_proc(
 
             # cancel result waiter that may have been spawned in
             # tandem if not done already
-            log.warning(
+            log.cancel(
                 "Cancelling existing result waiter task for "
                 f"{subactor.uid}")
             nursery.cancel_scope.cancel()

tractor/_state.py

@@ -23,11 +23,6 @@ from typing import (
     Any,
 )
 
-import trio
-
-from ._exceptions import NoRuntime
-
-
 _current_actor: Optional['Actor'] = None  # type: ignore # noqa
 _runtime_vars: dict[str, Any] = {
     '_debug_mode': False,
@@ -37,8 +32,11 @@ _runtime_vars: dict[str, Any] = {
 
 
 def current_actor(err_on_no_runtime: bool = True) -> 'Actor':  # type: ignore # noqa
-    """Get the process-local actor instance.
-    """
+    '''
+    Get the process-local actor instance.
+
+    '''
+    from ._exceptions import NoRuntime
     if _current_actor is None and err_on_no_runtime:
         raise NoRuntime("No local actor has been initialized yet")
 
@@ -46,16 +44,20 @@ def current_actor(err_on_no_runtime: bool = True) -> 'Actor':  # type: ignore #
 
 
 def is_main_process() -> bool:
-    """Bool determining if this actor is running in the top-most process.
-    """
+    '''
+    Bool determining if this actor is running in the top-most process.
+
+    '''
     import multiprocessing as mp
     return mp.current_process().name == 'MainProcess'
 
 
 def debug_mode() -> bool:
-    """Bool determining if "debug mode" is on which enables
+    '''
+    Bool determining if "debug mode" is on which enables
     remote subactor pdb entry on crashes.
-    """
+
+    '''
     return bool(_runtime_vars['_debug_mode'])
 
 

tractor/_streaming.py

@@ -14,31 +14,36 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
-"""
+'''
 Message stream types and APIs.
 
-"""
+The machinery and types behind ``Context.open_stream()``
+
+'''
 from __future__ import annotations
 import inspect
-from contextlib import asynccontextmanager
-from dataclasses import dataclass
+from contextlib import asynccontextmanager as acm
 from typing import (
     Any,
-    Optional,
     Callable,
-    AsyncGenerator,
-    AsyncIterator
+    AsyncIterator,
+    TYPE_CHECKING,
 )
-
 import warnings
 
 import trio
 
-from ._ipc import Channel
-from ._exceptions import unpack_error, ContextCancelled
-from ._state import current_actor
+from ._exceptions import (
+    unpack_error,
+)
 from .log import get_logger
-from .trionics import broadcast_receiver, BroadcastReceiver
+from .trionics import (
+    broadcast_receiver,
+    BroadcastReceiver,
+)
+
+if TYPE_CHECKING:
+    from ._context import Context
 
 
 log = get_logger(__name__)
@@ -70,9 +75,9 @@ class MsgStream(trio.abc.Channel):
     '''
     def __init__(
         self,
-        ctx: 'Context',  # typing: ignore # noqa
+        ctx: Context,  # typing: ignore # noqa
         rx_chan: trio.MemoryReceiveChannel,
-        _broadcaster: Optional[BroadcastReceiver] = None,
+        _broadcaster: BroadcastReceiver | None = None,
 
     ) -> None:
         self._ctx = ctx
@@ -275,7 +280,7 @@ class MsgStream(trio.abc.Channel):
         # still need to consume msgs that are "in transit" from the far
         # end (eg. for ``Context.result()``).
 
-    @asynccontextmanager
+    @acm
     async def subscribe(
         self,
 
@@ -335,8 +340,8 @@ class MsgStream(trio.abc.Channel):
         Send a message over this stream to the far end.
 
         '''
-        if self._ctx._error:
-            raise self._ctx._error  # from None
+        if self._ctx._remote_error:
+            raise self._ctx._remote_error  # from None
 
         if self._closed:
             raise trio.ClosedResourceError('This stream was already closed')
@@ -344,371 +349,11 @@ class MsgStream(trio.abc.Channel):
         await self._ctx.chan.send({'yield': data, 'cid': self._ctx.cid})
 
 
-@dataclass
-class Context:
-    '''
-    An inter-actor, ``trio`` task communication context.
-
-    NB: This class should never be instatiated directly, it is delivered
-    by either runtime machinery to a remotely started task or by entering
-    ``Portal.open_context()``.
-
-    Allows maintaining task or protocol specific state between
-    2 communicating actor tasks. A unique context is created on the
-    callee side/end for every request to a remote actor from a portal.
-
-    A context can be cancelled and (possibly eventually restarted) from
-    either side of the underlying IPC channel, open task oriented
-    message streams and acts as an IPC aware inter-actor-task cancel
-    scope.
-
-    '''
-    chan: Channel
-    cid: str
-
-    # these are the "feeder" channels for delivering
-    # message values to the local task from the runtime
-    # msg processing loop.
-    _recv_chan: trio.MemoryReceiveChannel
-    _send_chan: trio.MemorySendChannel
-
-    _remote_func_type: Optional[str] = None
-
-    # only set on the caller side
-    _portal: Optional['Portal'] = None    # type: ignore # noqa
-    _result: Optional[Any] = False
-    _error: Optional[BaseException] = None
-
-    # status flags
-    _cancel_called: bool = False
-    _cancel_msg: Optional[str] = None
-    _enter_debugger_on_cancel: bool = True
-    _started_called: bool = False
-    _started_received: bool = False
-    _stream_opened: bool = False
-
-    # only set on the callee side
-    _scope_nursery: Optional[trio.Nursery] = None
-
-    _backpressure: bool = False
-
-    async def send_yield(self, data: Any) -> None:
-
-        warnings.warn(
-            "`Context.send_yield()` is now deprecated. "
-            "Use ``MessageStream.send()``. ",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        await self.chan.send({'yield': data, 'cid': self.cid})
-
-    async def send_stop(self) -> None:
-        await self.chan.send({'stop': True, 'cid': self.cid})
-
-    async def _maybe_raise_from_remote_msg(
-        self,
-        msg: dict[str, Any],
-
-    ) -> None:
-        '''
-        (Maybe) unpack and raise a msg error into the local scope
-        nursery for this context.
-
-        Acts as a form of "relay" for a remote error raised
-        in the corresponding remote callee task.
-
-        '''
-        error = msg.get('error')
-        if error:
-            # If this is an error message from a context opened by
-            # ``Portal.open_context()`` we want to interrupt any ongoing
-            # (child) tasks within that context to be notified of the remote
-            # error relayed here.
-            #
-            # The reason we may want to raise the remote error immediately
-            # is that there is no guarantee the associated local task(s)
-            # will attempt to read from any locally opened stream any time
-            # soon.
-            #
-            # NOTE: this only applies when
-            # ``Portal.open_context()`` has been called since it is assumed
-            # (currently) that other portal APIs (``Portal.run()``,
-            # ``.run_in_actor()``) do their own error checking at the point
-            # of the call and result processing.
-            log.error(
-                f'Remote context error for {self.chan.uid}:{self.cid}:\n'
-                f'{msg["error"]["tb_str"]}'
-            )
-            error = unpack_error(msg, self.chan)
-            if (
-                isinstance(error, ContextCancelled) and
-                self._cancel_called
-            ):
-                # this is an expected cancel request response message
-                # and we don't need to raise it in scope since it will
-                # potentially override a real error
-                return
-
-            self._error = error
-
-            # TODO: tempted to **not** do this by-reraising in a
-            # nursery and instead cancel a surrounding scope, detect
-            # the cancellation, then lookup the error that was set?
-            if self._scope_nursery:
-
-                async def raiser():
-                    raise self._error from None
-
-                # from trio.testing import wait_all_tasks_blocked
-                # await wait_all_tasks_blocked()
-                if not self._scope_nursery._closed:  # type: ignore
-                    self._scope_nursery.start_soon(raiser)
-
-    async def cancel(
-        self,
-        msg: Optional[str] = None,
-
-    ) -> None:
-        '''
-        Cancel this inter-actor-task context.
-
-        Request that the far side cancel it's current linked context,
-        Timeout quickly in an attempt to sidestep 2-generals...
-
-        '''
-        side = 'caller' if self._portal else 'callee'
-        if msg:
-            assert side == 'callee', 'Only callee side can provide cancel msg'
-
-        log.cancel(f'Cancelling {side} side of context to {self.chan.uid}')
-
-        self._cancel_called = True
-
-        if side == 'caller':
-            if not self._portal:
-                raise RuntimeError(
-                    "No portal found, this is likely a callee side context"
-                )
-
-            cid = self.cid
-            with trio.move_on_after(0.5) as cs:
-                cs.shield = True
-                log.cancel(
-                    f"Cancelling stream {cid} to "
-                    f"{self._portal.channel.uid}")
-
-                # NOTE: we're telling the far end actor to cancel a task
-                # corresponding to *this actor*. The far end local channel
-                # instance is passed to `Actor._cancel_task()` implicitly.
-                await self._portal.run_from_ns('self', '_cancel_task', cid=cid)
-
-            if cs.cancelled_caught:
-                # XXX: there's no way to know if the remote task was indeed
-                # cancelled in the case where the connection is broken or
-                # some other network error occurred.
-                # if not self._portal.channel.connected():
-                if not self.chan.connected():
-                    log.cancel(
-                        "May have failed to cancel remote task "
-                        f"{cid} for {self._portal.channel.uid}")
-                else:
-                    log.cancel(
-                        "Timed out on cancelling remote task "
-                        f"{cid} for {self._portal.channel.uid}")
-
-        # callee side remote task
-        else:
-            self._cancel_msg = msg
-
-            # TODO: should we have an explicit cancel message
-            # or is relaying the local `trio.Cancelled` as an
-            # {'error': trio.Cancelled, cid: "blah"} enough?
-            # This probably gets into the discussion in
-            # https://github.com/goodboy/tractor/issues/36
-            assert self._scope_nursery
-            self._scope_nursery.cancel_scope.cancel()
-
-        if self._recv_chan:
-            await self._recv_chan.aclose()
-
-    @asynccontextmanager
-    async def open_stream(
-
-        self,
-        backpressure: Optional[bool] = True,
-        msg_buffer_size: Optional[int] = None,
-
-    ) -> AsyncGenerator[MsgStream, None]:
-        '''
-        Open a ``MsgStream``, a bi-directional stream connected to the
-        cross-actor (far end) task for this ``Context``.
-
-        This context manager must be entered on both the caller and
-        callee for the stream to logically be considered "connected".
-
-        A ``MsgStream`` is currently "one-shot" use, meaning if you
-        close it you can not "re-open" it for streaming and instead you
-        must re-establish a new surrounding ``Context`` using
-        ``Portal.open_context()``.  In the future this may change but
-        currently there seems to be no obvious reason to support
-        "re-opening":
-            - pausing a stream can be done with a message.
-            - task errors will normally require a restart of the entire
-              scope of the inter-actor task context due to the nature of
-              ``trio``'s cancellation system.
-
-        '''
-        actor = current_actor()
-
-        # here we create a mem chan that corresponds to the
-        # far end caller / callee.
-
-        # Likewise if the surrounding context has been cancelled we error here
-        # since it likely means the surrounding block was exited or
-        # killed
-
-        if self._cancel_called:
-            task = trio.lowlevel.current_task().name
-            raise ContextCancelled(
-                f'Context around {actor.uid[0]}:{task} was already cancelled!'
-            )
-
-        if not self._portal and not self._started_called:
-            raise RuntimeError(
-                'Context.started()` must be called before opening a stream'
-            )
-
-        # NOTE: in one way streaming this only happens on the
-        # caller side inside `Actor.start_remote_task()` so if you try
-        # to send a stop from the caller to the callee in the
-        # single-direction-stream case you'll get a lookup error
-        # currently.
-        ctx = actor.get_context(
-            self.chan,
-            self.cid,
-            msg_buffer_size=msg_buffer_size,
-        )
-        ctx._backpressure = backpressure
-        assert ctx is self
-
-        # XXX: If the underlying channel feeder receive mem chan has
-        # been closed then likely client code has already exited
-        # a ``.open_stream()`` block prior or there was some other
-        # unanticipated error or cancellation from ``trio``.
-
-        if ctx._recv_chan._closed:
-            raise trio.ClosedResourceError(
-                'The underlying channel for this stream was already closed!?')
-
-        async with MsgStream(
-            ctx=self,
-            rx_chan=ctx._recv_chan,
-        ) as stream:
-
-            if self._portal:
-                self._portal._streams.add(stream)
-
-            try:
-                self._stream_opened = True
-
-                # XXX: do we need this?
-                # ensure we aren't cancelled before yielding the stream
-                # await trio.lowlevel.checkpoint()
-                yield stream
-
-                # NOTE: Make the stream "one-shot use".  On exit, signal
-                # ``trio.EndOfChannel``/``StopAsyncIteration`` to the
-                # far end.
-                await stream.aclose()
-
-            finally:
-                if self._portal:
-                    try:
-                        self._portal._streams.remove(stream)
-                    except KeyError:
-                        log.warning(
-                            f'Stream was already destroyed?\n'
-                            f'actor: {self.chan.uid}\n'
-                            f'ctx id: {self.cid}'
-                        )
-
-    async def result(self) -> Any:
-        '''
-        From a caller side, wait for and return the final result from
-        the callee side task.
-
-        '''
-        assert self._portal, "Context.result() can not be called from callee!"
-        assert self._recv_chan
-
-        if self._result is False:
-
-            if not self._recv_chan._closed:  # type: ignore
-
-                # wait for a final context result consuming
-                # and discarding any bi dir stream msgs still
-                # in transit from the far end.
-                while True:
-
-                    msg = await self._recv_chan.receive()
-                    try:
-                        self._result = msg['return']
-                        break
-                    except KeyError as msgerr:
-
-                        if 'yield' in msg:
-                            # far end task is still streaming to us so discard
-                            log.warning(f'Discarding stream delivered {msg}')
-                            continue
-
-                        elif 'stop' in msg:
-                            log.debug('Remote stream terminated')
-                            continue
-
-                        # internal error should never get here
-                        assert msg.get('cid'), (
-                            "Received internal error at portal?")
-
-                        raise unpack_error(
-                            msg, self._portal.channel
-                        ) from msgerr
-
-        return self._result
-
-    async def started(
-        self,
-        value: Optional[Any] = None
-
-    ) -> None:
-        '''
-        Indicate to calling actor's task that this linked context
-        has started and send ``value`` to the other side.
-
-        On the calling side ``value`` is the second item delivered
-        in the tuple returned by ``Portal.open_context()``.
-
-        '''
-        if self._portal:
-            raise RuntimeError(
-                f"Caller side context {self} can not call started!")
-
-        elif self._started_called:
-            raise RuntimeError(
-                f"called 'started' twice on context with {self.chan.uid}")
-
-        await self.chan.send({'started': value, 'cid': self.cid})
-        self._started_called = True
-
-    # TODO: do we need a restart api?
-    # async def restart(self) -> None:
-    #     pass
-
-
 def stream(func: Callable) -> Callable:
-    """Mark an async function as a streaming routine with ``@stream``.
+    '''
+    Mark an async function as a streaming routine with ``@stream``.
 
-    """
-    # annotate
+    '''
     # TODO: apply whatever solution ``mypy`` ends up picking for this:
     # https://github.com/python/mypy/issues/2087#issuecomment-769266912
     func._tractor_stream_function = True  # type: ignore
@@ -734,22 +379,3 @@ def stream(func: Callable) -> Callable:
             "(Or ``to_trio`` if using ``asyncio`` in guest mode)."
         )
     return func
-
-
-def context(func: Callable) -> Callable:
-    """Mark an async function as a streaming routine with ``@context``.
-
-    """
-    # annotate
-    # TODO: apply whatever solution ``mypy`` ends up picking for this:
-    # https://github.com/python/mypy/issues/2087#issuecomment-769266912
-    func._tractor_context_function = True  # type: ignore
-
-    sig = inspect.signature(func)
-    params = sig.parameters
-    if 'ctx' not in params:
-        raise TypeError(
-            "The first argument to the context function "
-            f"{func.__name__} must be `ctx: tractor.Context`"
-        )
-    return func

tractor/experimental/_pubsub.py

@@ -37,7 +37,7 @@ import trio
 import wrapt
 
 from ..log import get_logger
-from .._streaming import Context
+from .._context import Context
 
 
 __all__ = ['pub']
@@ -148,7 +148,8 @@ def pub(
     *,
     tasks: set[str] = set(),
 ):
-    """Publisher async generator decorator.
+    '''
+    Publisher async generator decorator.
 
     A publisher can be called multiple times from different actors but
     will only spawn a finite set of internal tasks to stream values to
@@ -227,7 +228,8 @@ def pub(
     running in a single actor to stream data to an arbitrary number of
     subscribers. If you are ok to have a new task running for every call
     to ``pub_service()`` then probably don't need this.
-    """
+
+    '''
     global _pubtask2lock
 
     # handle the decorator not called with () case

tractor/log.py

@@ -82,6 +82,10 @@ class StackLevelAdapter(logging.LoggerAdapter):
         msg: str,
 
     ) -> None:
+        '''
+        IPC level msg-ing.
+
+        '''
         return self.log(5, msg)
 
     def runtime(
@@ -94,12 +98,20 @@ class StackLevelAdapter(logging.LoggerAdapter):
         self,
         msg: str,
     ) -> None:
+        '''
+        Cancellation logging, mostly for runtime reporting.
+
+        '''
         return self.log(16, msg)
 
     def pdb(
         self,
         msg: str,
     ) -> None:
+        '''
+        Debugger logging.
+
+        '''
         return self.log(500, msg)
 
     def log(self, level, msg, *args, **kwargs):

tractor/trionics/_broadcast.py

@@ -25,8 +25,16 @@ from collections import deque
 from contextlib import asynccontextmanager
 from functools import partial
 from operator import ne
-from typing import Optional, Callable, Awaitable, Any, AsyncIterator, Protocol
-from typing import Generic, TypeVar
+from typing import (
+    Optional,
+    Callable,
+    Awaitable,
+    Any,
+    AsyncIterator,
+    Protocol,
+    Generic,
+    TypeVar,
+)
 
 import trio
 from trio._core._run import Task

tractor/trionics/_mngrs.py

@@ -237,7 +237,7 @@ async def maybe_open_context(
         yielded = _Cache.values[ctx_key]
 
     except KeyError:
-        log.info(f'Allocating new {acm_func} for {ctx_key}')
+        log.debug(f'Allocating new {acm_func} for {ctx_key}')
         mngr = acm_func(**kwargs)
         resources = _Cache.resources
         assert not resources.get(ctx_key), f'Resource exists? {ctx_key}'
@@ -265,7 +265,7 @@ async def maybe_open_context(
         if yielded is not None:
             # if no more consumers, teardown the client
             if _Cache.users <= 0:
-                log.info(f'De-allocating resource for {ctx_key}')
+                log.debug(f'De-allocating resource for {ctx_key}')
 
                 # XXX: if we're cancelled we the entry may have never
                 # been entered since the nursery task was killed.