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).

examples/advanced_faults/ipc_failure_during_stream.py

@@ -6,47 +6,115 @@ been an outage) and we want to ensure that despite being in debug mode
 actor tree will eventually be cancelled without leaving any zombies.
 
 '''
-import trio
+from contextlib import asynccontextmanager as acm
+from functools import partial
+
 from tractor import (
     open_nursery,
     context,
     Context,
+    ContextCancelled,
     MsgStream,
+    _testing,
 )
+import trio
+import pytest
 
 
-async def break_channel_silently_then_error(
+async def break_ipc(
     stream: MsgStream,
-):
+    method: str|None = None,
-    async for msg in stream:
+    pre_close: bool = False,
-        await stream.send(msg)
 
-        # XXX: close the channel right after an error is raised
+    def_method: str = 'eof',
-        # purposely breaking the IPC transport to make sure the parent
-        # doesn't get stuck in debug or hang on the connection join.
-        # this more or less simulates an infinite msg-receive hang on
-        # the other end.
-        await stream._ctx.chan.send(None)
-        assert 0
 
+) -> None:
+    '''
+    XXX: close the channel right after an error is raised
+    purposely breaking the IPC transport to make sure the parent
+    doesn't get stuck in debug or hang on the connection join.
+    this more or less simulates an infinite msg-receive hang on
+    the other end.
 
-async def close_stream_and_error(
+    '''
-    stream: MsgStream,
+    # close channel via IPC prot msging before
-):
+    # any transport breakage
-    async for msg in stream:
+    if pre_close:
-        await stream.send(msg)
-
-        # wipe out channel right before raising
-        await stream._ctx.chan.send(None)
         await stream.aclose()
-        assert 0
+
+    method: str = method or def_method
+    print(
+        '#################################\n'
+        'Simulating CHILD-side IPC BREAK!\n'
+        f'method: {method}\n'
+        f'pre `.aclose()`: {pre_close}\n'
+        '#################################\n'
+    )
+
+    match method:
+        case 'trans_aclose':
+            await stream._ctx.chan.transport.stream.aclose()
+
+        case 'eof':
+            await stream._ctx.chan.transport.stream.send_eof()
+
+        case 'msg':
+            await stream._ctx.chan.send(None)
+
+        # TODO: the actual real-world simulated cases like
+        # transport layer hangs and/or lower layer 2-gens type
+        # scenarios..
+        #
+        # -[ ] already have some issues for this general testing
+        # area:
+        #  - https://github.com/goodboy/tractor/issues/97
+        #  - https://github.com/goodboy/tractor/issues/124
+        #   - PR from @guille:
+        #     https://github.com/goodboy/tractor/pull/149
+        # case 'hang':
+        # TODO: framework research:
+        #
+        # - https://github.com/GuoTengda1993/pynetem
+        # - https://github.com/shopify/toxiproxy
+        # - https://manpages.ubuntu.com/manpages/trusty/man1/wirefilter.1.html
+
+        case _:
+            raise RuntimeError(
+                f'IPC break method unsupported: {method}'
+            )
+
+
+async def break_ipc_then_error(
+    stream: MsgStream,
+    break_ipc_with: str|None = None,
+    pre_close: bool = False,
+):
+    await break_ipc(
+        stream=stream,
+        method=break_ipc_with,
+        pre_close=pre_close,
+    )
+    async for msg in stream:
+        await stream.send(msg)
+
+    assert 0
+
+
+async def iter_ipc_stream(
+    stream: MsgStream,
+    break_ipc_with: str|None = None,
+    pre_close: bool = False,
+):
+    async for msg in stream:
+        await stream.send(msg)
 
 
 @context
 async def recv_and_spawn_net_killers(
 
     ctx: Context,
-    break_ipc_after: bool | int = False,
+    break_ipc_after: bool|int = False,
+    pre_close: bool = False,
 
 ) -> None:
     '''
@@ -61,26 +129,53 @@ async def recv_and_spawn_net_killers(
         async for i in stream:
             print(f'child echoing {i}')
             await stream.send(i)
+
             if (
                 break_ipc_after
-                and i > break_ipc_after
+                and
+                i >= break_ipc_after
             ):
-                '#################################\n'
+                n.start_soon(
-                'Simulating child-side IPC BREAK!\n'
+                    iter_ipc_stream,
-                '#################################'
+                    stream,
-                n.start_soon(break_channel_silently_then_error, stream)
+                )
-                n.start_soon(close_stream_and_error, stream)
+                n.start_soon(
+                    partial(
+                        break_ipc_then_error,
+                        stream=stream,
+                        pre_close=pre_close,
+                    )
+                )
+
+
+@acm
+async def stuff_hangin_ctlc(timeout: float = 1) -> None:
+
+    with trio.move_on_after(timeout) as cs:
+        yield timeout
+
+    if cs.cancelled_caught:
+        # pretend to be a user seeing no streaming action
+        # thinking it's a hang, and then hitting ctl-c..
+        print(
+            f"i'm a user on the PARENT side and thingz hangin "
+            f'after timeout={timeout} ???\n\n'
+            'MASHING CTlR-C..!?\n'
+        )
+        raise KeyboardInterrupt
 
 
 async def main(
     debug_mode: bool = False,
     start_method: str = 'trio',
+    loglevel: str = 'cancel',
 
     # by default we break the parent IPC first (if configured to break
     # at all), but this can be changed so the child does first (even if
     # both are set to break).
-    break_parent_ipc_after: int | bool = False,
+    break_parent_ipc_after: int|bool = False,
-    break_child_ipc_after: int | bool = False,
+    break_child_ipc_after: int|bool = False,
+    pre_close: bool = False,
 
 ) -> None:
 
@@ -91,60 +186,123 @@ async def main(
             # NOTE: even debugger is used we shouldn't get
             # a hang since it never engages due to broken IPC
             debug_mode=debug_mode,
-            loglevel='warning',
+            loglevel=loglevel,
 
         ) as an,
     ):
+        sub_name: str = 'chitty_hijo'
         portal = await an.start_actor(
-            'chitty_hijo',
+            sub_name,
             enable_modules=[__name__],
         )
 
-        async with portal.open_context(
+        async with (
-            recv_and_spawn_net_killers,
+            stuff_hangin_ctlc(timeout=2) as timeout,
-            break_ipc_after=break_child_ipc_after,
+            _testing.expect_ctxc(
+                yay=(
+                    break_parent_ipc_after
+                    or break_child_ipc_after
+                ),
+                # TODO: we CAN'T remove this right?
+                # since we need the ctxc to bubble up from either
+                # the stream API after the `None` msg is sent
+                # (which actually implicitly cancels all remote
+                # tasks in the hijo) or from simluated
+                # KBI-mash-from-user
+                # or should we expect that a KBI triggers the ctxc
+                # and KBI in an eg?
+                reraise=True,
+            ),
 
-        ) as (ctx, sent):
+            portal.open_context(
+                recv_and_spawn_net_killers,
+                break_ipc_after=break_child_ipc_after,
+                pre_close=pre_close,
+            ) as (ctx, sent),
+        ):
+            rx_eoc: bool = False
+            ipc_break_sent: bool = False
             async with ctx.open_stream() as stream:
                 for i in range(1000):
 
                     if (
                         break_parent_ipc_after
-                        and i > break_parent_ipc_after
+                        and
+                        i > break_parent_ipc_after
+                        and
+                        not ipc_break_sent
                     ):
                         print(
                             '#################################\n'
-                            'Simulating parent-side IPC BREAK!\n'
+                            'Simulating PARENT-side IPC BREAK!\n'
-                            '#################################'
+                            '#################################\n'
                         )
-                        await stream._ctx.chan.send(None)
+
+                        # TODO: other methods? see break func above.
+                        # await stream._ctx.chan.send(None)
+                        # await stream._ctx.chan.transport.stream.send_eof()
+                        await stream._ctx.chan.transport.stream.aclose()
+
+                        ipc_break_sent = True
 
                     # it actually breaks right here in the
                     # mp_spawn/forkserver backends and thus the zombie
                     # reaper never even kicks in?
                     print(f'parent sending {i}')
-                    await stream.send(i)
+                    try:
+                        await stream.send(i)
+                    except ContextCancelled as ctxc:
+                        print(
+                            'parent received ctxc on `stream.send()`\n'
+                            f'{ctxc}\n'
+                        )
+                        assert 'root' in ctxc.canceller
+                        assert sub_name in ctx.canceller
 
-                    with trio.move_on_after(2) as cs:
+                        # TODO: is this needed or no?
+                        raise
 
+                    # timeout: int = 1
+                    # with trio.move_on_after(timeout) as cs:
+                    async with stuff_hangin_ctlc() as timeout:
+                        print(
+                            f'PARENT `stream.receive()` with timeout={timeout}\n'
+                        )
                         # NOTE: in the parent side IPC failure case this
                         # will raise an ``EndOfChannel`` after the child
                         # is killed and sends a stop msg back to it's
                         # caller/this-parent.
-                        rx = await stream.receive()
+                        try:
+                            rx = await stream.receive()
+                            print(
+                                "I'm a happy PARENT user and echoed to me is\n"
+                                f'{rx}\n'
+                            )
+                        except trio.EndOfChannel:
+                            rx_eoc: bool = True
+                            print('MsgStream got EoC for PARENT')
+                            raise
 
-                        print(f"I'm a happy user and echoed to me is {rx}")
+            print(
+                'Streaming finished and we got Eoc.\n'
+                'Canceling `.open_context()` in root with\n'
+                'CTlR-C..'
+            )
+            if rx_eoc:
+                assert stream.closed
+                try:
+                    await stream.send(i)
+                    pytest.fail('stream not closed?')
+                except (
+                    trio.ClosedResourceError,
+                    trio.EndOfChannel,
+                ) as send_err:
+                    if rx_eoc:
+                        assert send_err is stream._eoc
+                    else:
+                        assert send_err is stream._closed
 
-                    if cs.cancelled_caught:
+            raise KeyboardInterrupt
-                        # pretend to be a user seeing no streaming action
-                        # thinking it's a hang, and then hitting ctl-c..
-                        print("YOO i'm a user anddd thingz hangin..")
-
-                print(
-                    "YOO i'm mad send side dun but thingz hangin..\n"
-                    'MASHING CTlR-C Ctl-c..'
-                )
-                raise KeyboardInterrupt
 
 
 if __name__ == '__main__':

examples/debugging/debug_mode_hang.py

@@ -0,0 +1,9 @@
+'''
+Reproduce a bug where enabling debug mode for a sub-actor actually causes
+a hang on teardown...
+
+'''
+import asyncio
+
+import trio
+import tractor

examples/full_fledged_streaming_service.py

@@ -65,21 +65,28 @@ async def aggregate(seed):
     print("AGGREGATOR COMPLETE!")
 
 
-# this is the main actor and *arbiter*
+async def main() -> list[int]:
-async def main():
+    '''
-    # a nursery which spawns "actors"
+    This is the "root" actor's main task's entrypoint.
-    async with tractor.open_nursery(
+
-        arbiter_addr=('127.0.0.1', 1616)
+    By default (and if not otherwise specified) that root process
-    ) as nursery:
+    also acts as a "registry actor" / "registrar" on the localhost
+    for the purposes of multi-actor "service discovery".
+
+    '''
+    # yes, a nursery which spawns `trio`-"actors" B)
+    nursery: tractor.ActorNursery
+    async with tractor.open_nursery() as nursery:
 
         seed = int(1e3)
         pre_start = time.time()
 
-        portal = await nursery.start_actor(
+        portal: tractor.Portal = await nursery.start_actor(
             name='aggregator',
             enable_modules=[__name__],
         )
 
+        stream: tractor.MsgStream
         async with portal.open_stream_from(
             aggregate,
             seed=seed,

examples/parallelism/concurrent_actors_primes.py

@@ -8,7 +8,10 @@ This uses no extra threads, fancy semaphores or futures; all we need
 is ``tractor``'s channels.
 
 """
-from contextlib import asynccontextmanager
+from contextlib import (
+    asynccontextmanager as acm,
+    aclosing,
+)
 from typing import Callable
 import itertools
 import math
@@ -16,7 +19,6 @@ import time
 
 import tractor
 import trio
-from async_generator import aclosing
 
 
 PRIMES = [
@@ -44,7 +46,7 @@ async def is_prime(n):
     return True
 
 
-@asynccontextmanager
+@acm
 async def worker_pool(workers=4):
     """Though it's a trivial special case for ``tractor``, the well
     known "worker pool" seems to be the defacto "but, I want this

examples/rpc_bidir_streaming.py

@@ -13,7 +13,7 @@ async def simple_rpc(
 
     '''
     # signal to parent that we're up much like
-    # ``trio_typing.TaskStatus.started()``
+    # ``trio.TaskStatus.started()``
     await ctx.started(data + 1)
 
     async with ctx.open_stream() as stream:

pyproject.toml

@@ -26,3 +26,23 @@ all_bullets = true
   directory = "trivial"
   name = "Trivial/Internal Changes"
   showcontent = true
+
+
+[tool.pytest.ini_options]
+minversion = '6.0'
+testpaths = [
+  'tests'
+]
+addopts = [
+  # TODO: figure out why this isn't working..
+  '--rootdir=./tests',
+
+  '--import-mode=importlib',
+  # don't show frickin captured logs AGAIN in the report..
+  '--show-capture=no',
+]
+log_cli = false
+
+# TODO: maybe some of these layout choices?
+# https://docs.pytest.org/en/8.0.x/explanation/goodpractices.html#choosing-a-test-layout-import-rules
+# pythonpath = "src"

requirements-test.txt

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

setup.py

@@ -36,18 +36,20 @@ setup(
     platforms=['linux', 'windows'],
     packages=[
         'tractor',
-        'tractor.experimental',
+        'tractor.experimental',  # wacky ideas
-        'tractor.trionics',
+        'tractor.trionics',  # trio extensions
+        'tractor.msg',  # lowlevel data types
     ],
     install_requires=[
 
         # trio related
         # proper range spec:
         # https://packaging.python.org/en/latest/discussions/install-requires-vs-requirements/#id5
-        'trio >= 0.22',
+        'trio >= 0.24',
-        'async_generator',
+
-        'trio_typing',
+        # 'async_generator',  # in stdlib mostly!
-        'exceptiongroup',
+        # 'trio_typing',  # trio==0.23.0 has type hints!
+        # 'exceptiongroup',  # in stdlib as of 3.11!
 
         # tooling
         'tricycle',

tests/conftest.py

@@ -7,94 +7,19 @@ import os
 import random
 import signal
 import platform
-import pathlib
 import time
-import inspect
-from functools import partial, wraps
 
 import pytest
-import trio
 import tractor
+from tractor._testing import (
+    examples_dir as examples_dir,
+    tractor_test as tractor_test,
+    expect_ctxc as expect_ctxc,
+)
 
+# TODO: include wtv plugin(s) we build in `._testing.pytest`?
 pytest_plugins = ['pytester']
 
-
-def tractor_test(fn):
-    """
-    Use:
-
-    @tractor_test
-    async def test_whatever():
-        await ...
-
-    If fixtures:
-
-        - ``arb_addr`` (a socket addr tuple where arbiter is listening)
-        - ``loglevel`` (logging level passed to tractor internals)
-        - ``start_method`` (subprocess spawning backend)
-
-    are defined in the `pytest` fixture space they will be automatically
-    injected to tests declaring these funcargs.
-    """
-    @wraps(fn)
-    def wrapper(
-        *args,
-        loglevel=None,
-        arb_addr=None,
-        start_method=None,
-        **kwargs
-    ):
-        # __tracebackhide__ = True
-
-        if 'arb_addr' in inspect.signature(fn).parameters:
-            # injects test suite fixture value to test as well
-            # as `run()`
-            kwargs['arb_addr'] = arb_addr
-
-        if 'loglevel' in inspect.signature(fn).parameters:
-            # allows test suites to define a 'loglevel' fixture
-            # that activates the internal logging
-            kwargs['loglevel'] = loglevel
-
-        if start_method is None:
-            if platform.system() == "Windows":
-                start_method = 'trio'
-
-        if 'start_method' in inspect.signature(fn).parameters:
-            # set of subprocess spawning backends
-            kwargs['start_method'] = start_method
-
-        if kwargs:
-
-            # use explicit root actor start
-
-            async def _main():
-                async with tractor.open_root_actor(
-                    # **kwargs,
-                    arbiter_addr=arb_addr,
-                    loglevel=loglevel,
-                    start_method=start_method,
-
-                    # TODO: only enable when pytest is passed --pdb
-                    # debug_mode=True,
-
-                ):
-                    await fn(*args, **kwargs)
-
-            main = _main
-
-        else:
-            # use implicit root actor start
-            main = partial(fn, *args, **kwargs)
-
-        return trio.run(main)
-
-    return wrapper
-
-
-_arb_addr = '127.0.0.1', random.randint(1000, 9999)
-
-
 # Sending signal.SIGINT on subprocess fails on windows. Use CTRL_* alternatives
 if platform.system() == 'Windows':
     _KILL_SIGNAL = signal.CTRL_BREAK_EVENT
@@ -114,23 +39,6 @@ no_windows = pytest.mark.skipif(
 )
 
 
-def repodir() -> pathlib.Path:
-    '''
-    Return the abspath to the repo directory.
-
-    '''
-    # 2 parents up to step up through tests/<repo_dir>
-    return pathlib.Path(__file__).parent.parent.absolute()
-
-
-def examples_dir() -> pathlib.Path:
-    '''
-    Return the abspath to the examples directory as `pathlib.Path`.
-
-    '''
-    return repodir() / 'examples'
-
-
 def pytest_addoption(parser):
     parser.addoption(
         "--ll", action="store", dest='loglevel',
@@ -168,11 +76,26 @@ _ci_env: bool = os.environ.get('CI', False)
 
 @pytest.fixture(scope='session')
 def ci_env() -> bool:
-    """Detect CI envoirment.
+    '''
-    """
+    Detect CI envoirment.
+
+    '''
     return _ci_env
 
 
+# TODO: also move this to `._testing` for now?
+# -[ ] possibly generalize and re-use for multi-tree spawning
+#    along with the new stuff for multi-addrs in distribute_dis
+#    branch?
+#
+# choose randomly at import time
+_reg_addr: tuple[str, int] = (
+    '127.0.0.1',
+    random.randint(1000, 9999),
+)
+_arb_addr = _reg_addr
+
+
 @pytest.fixture(scope='session')
 def arb_addr():
     return _arb_addr
@@ -212,6 +135,7 @@ def sig_prog(proc, sig):
     assert ret
 
 
+# TODO: factor into @cm and move to `._testing`?
 @pytest.fixture
 def daemon(
     loglevel: str,

tests/test_advanced_faults.py

@@ -3,22 +3,29 @@ Sketchy network blackoutz, ugly byzantine gens, puedes eschuchar la
 cancelacion?..
 
 '''
+import itertools
 from functools import partial
+from types import ModuleType
 
 import pytest
 from _pytest.pathlib import import_path
 import trio
 import tractor
-
+from tractor._testing import (
-from conftest import (
     examples_dir,
 )
 
 
 @pytest.mark.parametrize(
-    'debug_mode',
+    'pre_aclose_msgstream',
-    [False, True],
+    [
-    ids=['no_debug_mode', 'debug_mode'],
+        False,
+        True,
+    ],
+    ids=[
+        'no_msgstream_aclose',
+        'pre_aclose_msgstream',
+    ],
 )
 @pytest.mark.parametrize(
     'ipc_break',
@@ -63,8 +70,10 @@ from conftest import (
 )
 def test_ipc_channel_break_during_stream(
     debug_mode: bool,
+    loglevel: str,
     spawn_backend: str,
-    ipc_break: dict | None,
+    ipc_break: dict|None,
+    pre_aclose_msgstream: bool,
 ):
     '''
     Ensure we can have an IPC channel break its connection during
@@ -83,70 +92,130 @@ def test_ipc_channel_break_during_stream(
         # requires the user to do ctl-c to cancel the actor tree.
         expect_final_exc = trio.ClosedResourceError
 
-    mod = import_path(
+    mod: ModuleType = import_path(
         examples_dir() / 'advanced_faults' / 'ipc_failure_during_stream.py',
         root=examples_dir(),
     )
 
-    expect_final_exc = KeyboardInterrupt
+    # by def we expect KBI from user after a simulated "hang
-
+    # period" wherein the user eventually hits ctl-c to kill the
-    # when ONLY the child breaks we expect the parent to get a closed
+    # root-actor tree.
-    # resource error on the next `MsgStream.receive()` and then fail out
+    expect_final_exc: BaseException = KeyboardInterrupt
-    # and cancel the child from there.
     if (
+        # only expect EoC if trans is broken on the child side,
+        ipc_break['break_child_ipc_after'] is not False
+        # AND we tell the child to call `MsgStream.aclose()`.
+        and pre_aclose_msgstream
+    ):
+        # expect_final_exc = trio.EndOfChannel
+        # ^XXX NOPE! XXX^ since now `.open_stream()` absorbs this
+        # gracefully!
+        expect_final_exc = KeyboardInterrupt
 
-        # only child breaks
+    # NOTE when ONLY the child breaks or it breaks BEFORE the
-        (
+    # parent we expect the parent to get a closed resource error
-            ipc_break['break_child_ipc_after']
+    # on the next `MsgStream.receive()` and then fail out and
-            and ipc_break['break_parent_ipc_after'] is False
+    # cancel the child from there.
-        )
+    #
-
+    # ONLY CHILD breaks
-        # both break but, parent breaks first
+    if (
-        or (
+        ipc_break['break_child_ipc_after']
-            ipc_break['break_child_ipc_after'] is not False
+        and
-            and (
+        ipc_break['break_parent_ipc_after'] is False
-                ipc_break['break_parent_ipc_after']
+    ):
-                > ipc_break['break_child_ipc_after']
+        # NOTE: we DO NOT expect this any more since
-            )
+        # the child side's channel will be broken silently
+        # and nothing on the parent side will indicate this!
+        # expect_final_exc = trio.ClosedResourceError
+
+        # NOTE: child will send a 'stop' msg before it breaks
+        # the transport channel BUT, that will be absorbed by the
+        # `ctx.open_stream()` block and thus the `.open_context()`
+        # should hang, after which the test script simulates
+        # a user sending ctl-c by raising a KBI.
+        if pre_aclose_msgstream:
+            expect_final_exc = KeyboardInterrupt
+
+            # XXX OLD XXX
+            # if child calls `MsgStream.aclose()` then expect EoC.
+            # ^ XXX not any more ^ since eoc is always absorbed
+            # gracefully and NOT bubbled to the `.open_context()`
+            # block!
+            # expect_final_exc = trio.EndOfChannel
+
+    # BOTH but, CHILD breaks FIRST
+    elif (
+        ipc_break['break_child_ipc_after'] is not False
+        and (
+            ipc_break['break_parent_ipc_after']
+            > ipc_break['break_child_ipc_after']
         )
+    ):
+        if pre_aclose_msgstream:
+            expect_final_exc = KeyboardInterrupt
 
+    # NOTE when the parent IPC side dies (even if the child's does as well
+    # but the child fails BEFORE the parent) we always expect the
+    # IPC layer to raise a closed-resource, NEVER do we expect
+    # a stop msg since the parent-side ctx apis will error out
+    # IMMEDIATELY before the child ever sends any 'stop' msg.
+    #
+    # ONLY PARENT breaks
+    elif (
+        ipc_break['break_parent_ipc_after']
+        and
+        ipc_break['break_child_ipc_after'] is False
     ):
         expect_final_exc = trio.ClosedResourceError
 
-    # when the parent IPC side dies (even if the child's does as well
+    # BOTH but, PARENT breaks FIRST
-    # but the child fails BEFORE the parent) we expect the channel to be
-    # sent a stop msg from the child at some point which will signal the
-    # parent that the stream has been terminated.
-    # NOTE: when the parent breaks "after" the child you get this same
-    # case as well, the child breaks the IPC channel with a stop msg
-    # before any closure takes place.
     elif (
-        # only parent breaks
+        ipc_break['break_parent_ipc_after'] is not False
-        (
+        and (
+            ipc_break['break_child_ipc_after']
+            >
             ipc_break['break_parent_ipc_after']
-            and ipc_break['break_child_ipc_after'] is False
-        )
-
-        # both break but, child breaks first
-        or (
-            ipc_break['break_parent_ipc_after'] is not False
-            and (
-                ipc_break['break_child_ipc_after']
-                > ipc_break['break_parent_ipc_after']
-            )
         )
     ):
-        expect_final_exc = trio.EndOfChannel
+        expect_final_exc = trio.ClosedResourceError
 
-    with pytest.raises(expect_final_exc):
+    with pytest.raises(
-        trio.run(
+        expected_exception=(
-            partial(
+            expect_final_exc,
-                mod.main,
+            ExceptionGroup,
-                debug_mode=debug_mode,
+        ),
-                start_method=spawn_backend,
+    ) as excinfo:
-                **ipc_break,
+        try:
+            trio.run(
+                partial(
+                    mod.main,
+                    debug_mode=debug_mode,
+                    start_method=spawn_backend,
+                    loglevel=loglevel,
+                    pre_close=pre_aclose_msgstream,
+                    **ipc_break,
+                )
+            )
+        except KeyboardInterrupt as kbi:
+            _err = kbi
+            if expect_final_exc is not KeyboardInterrupt:
+                pytest.fail(
+                    'Rxed unexpected KBI !?\n'
+                    f'{repr(kbi)}'
+                )
+
+            raise
+
+    # get raw instance from pytest wrapper
+    value = excinfo.value
+    if isinstance(value, ExceptionGroup):
+        value = next(
+            itertools.dropwhile(
+                lambda exc: not isinstance(exc, expect_final_exc),
+                value.exceptions,
             )
         )
+        assert value
 
 
 @tractor.context
@@ -169,25 +238,29 @@ def test_stream_closed_right_after_ipc_break_and_zombie_lord_engages():
 
     '''
     async def main():
-        async with tractor.open_nursery() as n:
+        with trio.fail_after(3):
-            portal = await n.start_actor(
+            async with tractor.open_nursery() as n:
-                'ipc_breaker',
+                portal = await n.start_actor(
-                enable_modules=[__name__],
+                    'ipc_breaker',
-            )
+                    enable_modules=[__name__],
+                )
 
-            with trio.move_on_after(1):
+                with trio.move_on_after(1):
-                async with (
+                    async with (
-                    portal.open_context(
+                        portal.open_context(
-                        break_ipc_after_started
+                            break_ipc_after_started
-                    ) as (ctx, sent),
+                        ) as (ctx, sent),
-                ):
+                    ):
-                    async with ctx.open_stream():
+                        async with ctx.open_stream():
-                        await trio.sleep(0.5)
+                            await trio.sleep(0.5)
 
-                    print('parent waiting on context')
+                        print('parent waiting on context')
 
-            print('parent exited context')
+                print(
-            raise KeyboardInterrupt
+                    'parent exited context\n'
+                    'parent raising KBI..\n'
+                )
+                raise KeyboardInterrupt
 
     with pytest.raises(KeyboardInterrupt):
         trio.run(main)

tests/test_advanced_streaming.py

@@ -6,6 +6,7 @@ from collections import Counter
 import itertools
 import platform
 
+import pytest
 import trio
 import tractor
 
@@ -143,8 +144,16 @@ def test_dynamic_pub_sub():
 
     try:
         trio.run(main)
-    except trio.TooSlowError:
+    except (
-        pass
+        trio.TooSlowError,
+        ExceptionGroup,
+    ) as err:
+        if isinstance(err, ExceptionGroup):
+            for suberr in err.exceptions:
+                if isinstance(suberr, trio.TooSlowError):
+                    break
+            else:
+                pytest.fail('Never got a `TooSlowError` ?')
 
 
 @tractor.context
@@ -298,44 +307,69 @@ async def inf_streamer(
 
     async with (
         ctx.open_stream() as stream,
-        trio.open_nursery() as n,
+        trio.open_nursery() as tn,
     ):
-        async def bail_on_sentinel():
+        async def close_stream_on_sentinel():
             async for msg in stream:
                 if msg == 'done':
+                    print(
+                        'streamer RXed "done" sentinel msg!\n'
+                        'CLOSING `MsgStream`!'
+                    )
                     await stream.aclose()
                 else:
                     print(f'streamer received {msg}')
+            else:
+                print('streamer exited recv loop')
 
         # start termination detector
-        n.start_soon(bail_on_sentinel)
+        tn.start_soon(close_stream_on_sentinel)
 
-        for val in itertools.count():
+        cap: int = 10000  # so that we don't spin forever when bug..
+        for val in range(cap):
             try:
+                print(f'streamer sending {val}')
                 await stream.send(val)
+                if val > cap:
+                    raise RuntimeError(
+                        'Streamer never cancelled by setinel?'
+                    )
+                await trio.sleep(0.001)
+
+            # close out the stream gracefully
             except trio.ClosedResourceError:
-                # close out the stream gracefully
+                print('transport closed on streamer side!')
+                assert stream.closed
                 break
+        else:
+            raise RuntimeError(
+                'Streamer not cancelled before finished sending?'
+            )
 
-    print('terminating streamer')
+    print('streamer exited .open_streamer() block')
 
 
-def test_local_task_fanout_from_stream():
+def test_local_task_fanout_from_stream(
+    debug_mode: bool,
+):
     '''
     Single stream with multiple local consumer tasks using the
     ``MsgStream.subscribe()` api.
 
-    Ensure all tasks receive all values after stream completes sending.
+    Ensure all tasks receive all values after stream completes
+    sending.
 
     '''
-    consumers = 22
+    consumers: int = 22
 
     async def main():
 
         counts = Counter()
 
-        async with tractor.open_nursery() as tn:
+        async with tractor.open_nursery(
-            p = await tn.start_actor(
+            debug_mode=debug_mode,
+        ) as tn:
+            p: tractor.Portal = await tn.start_actor(
                 'inf_streamer',
                 enable_modules=[__name__],
             )
@@ -343,7 +377,6 @@ def test_local_task_fanout_from_stream():
                 p.open_context(inf_streamer) as (ctx, _),
                 ctx.open_stream() as stream,
             ):
-
                 async def pull_and_count(name: str):
                     # name = trio.lowlevel.current_task().name
                     async with stream.subscribe() as recver:
@@ -352,7 +385,7 @@ def test_local_task_fanout_from_stream():
                             tractor.trionics.BroadcastReceiver
                         )
                         async for val in recver:
-                            # print(f'{name}: {val}')
+                            print(f'bx {name} rx: {val}')
                             counts[name] += 1
 
                         print(f'{name} bcaster ended')
@@ -362,10 +395,14 @@ def test_local_task_fanout_from_stream():
                 with trio.fail_after(3):
                     async with trio.open_nursery() as nurse:
                         for i in range(consumers):
-                            nurse.start_soon(pull_and_count, i)
+                            nurse.start_soon(
+                                pull_and_count,
+                                i,
+                            )
 
+                        # delay to let bcast consumers pull msgs
                         await trio.sleep(0.5)
-                        print('\nterminating')
+                        print('terminating nursery of bcast rxer consumers!')
                         await stream.send('done')
 
             print('closed stream connection')

tests/test_cancellation.py

@@ -8,15 +8,13 @@ import platform
 import time
 from itertools import repeat
 
-from exceptiongroup import (
-    BaseExceptionGroup,
-    ExceptionGroup,
-)
 import pytest
 import trio
 import tractor
-
+from tractor._testing import (
-from conftest import tractor_test, no_windows
+    tractor_test,
+)
+from conftest import no_windows
 
 
 def is_win():
@@ -47,17 +45,19 @@ async def do_nuthin():
     ],
     ids=['no_args', 'unexpected_args'],
 )
-def test_remote_error(arb_addr, args_err):
+def test_remote_error(reg_addr, args_err):
-    """Verify an error raised in a subactor that is propagated
+    '''
+    Verify an error raised in a subactor that is propagated
     to the parent nursery, contains the underlying boxed builtin
     error type info and causes cancellation and reraising all the
     way up the stack.
-    """
+
+    '''
     args, errtype = args_err
 
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as nursery:
 
             # on a remote type error caused by bad input args
@@ -65,7 +65,9 @@ def test_remote_error(arb_addr, args_err):
             # an exception group outside the nursery since the error
             # here and the far end task error are one in the same?
             portal = await nursery.run_in_actor(
-                assert_err, name='errorer', **args
+                assert_err,
+                name='errorer',
+                **args
             )
 
             # get result(s) from main task
@@ -97,7 +99,7 @@ def test_remote_error(arb_addr, args_err):
             assert exc.type == errtype
 
 
-def test_multierror(arb_addr):
+def test_multierror(reg_addr):
     '''
     Verify we raise a ``BaseExceptionGroup`` out of a nursery where
     more then one actor errors.
@@ -105,7 +107,7 @@ def test_multierror(arb_addr):
     '''
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as nursery:
 
             await nursery.run_in_actor(assert_err, name='errorer1')
@@ -130,14 +132,14 @@ def test_multierror(arb_addr):
 @pytest.mark.parametrize(
     'num_subactors', range(25, 26),
 )
-def test_multierror_fast_nursery(arb_addr, start_method, num_subactors, delay):
+def test_multierror_fast_nursery(reg_addr, start_method, num_subactors, delay):
     """Verify we raise a ``BaseExceptionGroup`` out of a nursery where
     more then one actor errors and also with a delay before failure
     to test failure during an ongoing spawning.
     """
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as nursery:
 
             for i in range(num_subactors):
@@ -175,15 +177,20 @@ async def do_nothing():
 
 
 @pytest.mark.parametrize('mechanism', ['nursery_cancel', KeyboardInterrupt])
-def test_cancel_single_subactor(arb_addr, mechanism):
+def test_cancel_single_subactor(reg_addr, mechanism):
-    """Ensure a ``ActorNursery.start_actor()`` spawned subactor
+    '''
+    Ensure a ``ActorNursery.start_actor()`` spawned subactor
     cancels when the nursery is cancelled.
-    """
+
+    '''
     async def spawn_actor():
-        """Spawn an actor that blocks indefinitely.
+        '''
-        """
+        Spawn an actor that blocks indefinitely then cancel via
+        either `ActorNursery.cancel()` or an exception raise.
+
+        '''
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as nursery:
 
             portal = await nursery.start_actor(

tests/test_child_manages_service_nursery.py

@@ -6,14 +6,15 @@ sub-sub-actor daemons.
 '''
 from typing import Optional
 import asyncio
-from contextlib import asynccontextmanager as acm
+from contextlib import (
+    asynccontextmanager as acm,
+    aclosing,
+)
 
 import pytest
 import trio
-from trio_typing import TaskStatus
 import tractor
 from tractor import RemoteActorError
-from async_generator import aclosing
 
 
 async def aio_streamer(
@@ -141,7 +142,7 @@ async def open_actor_local_nursery(
 )
 def test_actor_managed_trio_nursery_task_error_cancels_aio(
     asyncio_mode: bool,
-    arb_addr
+    reg_addr: tuple,
 ):
     '''
     Verify that a ``trio`` nursery created managed in a child actor

tests/test_clustering.py

@@ -5,9 +5,7 @@ import trio
 import tractor
 from tractor import open_actor_cluster
 from tractor.trionics import gather_contexts
-
+from tractor._testing import tractor_test
-from conftest import tractor_test
-
 
 MESSAGE = 'tractoring at full speed'
 

tests/test_context_stream_semantics.py

@@ -1,24 +1,34 @@
 '''
 ``async with ():`` inlined context-stream cancellation testing.
 
-Verify the we raise errors when streams are opened prior to sync-opening
+Verify the we raise errors when streams are opened prior to
-a ``tractor.Context`` beforehand.
+sync-opening a ``tractor.Context`` beforehand.
 
 '''
-from contextlib import asynccontextmanager as acm
 from itertools import count
 import platform
-from typing import Optional
+from pprint import pformat
+from typing import (
+    Callable,
+)
 
 import pytest
 import trio
 import tractor
+from tractor import (
+    Actor,
+    Context,
+    current_actor,
+)
 from tractor._exceptions import (
     StreamOverrun,
     ContextCancelled,
 )
 
-from conftest import tractor_test
+from tractor._testing import (
+    tractor_test,
+    expect_ctxc,
+)
 
 # ``Context`` semantics are as follows,
 #  ------------------------------------
@@ -64,7 +74,7 @@ _state: bool = False
 
 @tractor.context
 async def too_many_starteds(
-    ctx: tractor.Context,
+    ctx: Context,
 ) -> None:
     '''
     Call ``Context.started()`` more then once (an error).
@@ -79,7 +89,7 @@ async def too_many_starteds(
 
 @tractor.context
 async def not_started_but_stream_opened(
-    ctx: tractor.Context,
+    ctx: Context,
 ) -> None:
     '''
     Enter ``Context.open_stream()`` without calling ``.started()``.
@@ -100,11 +110,15 @@ async def not_started_but_stream_opened(
     ],
     ids='misuse_type={}'.format,
 )
-def test_started_misuse(target):
+def test_started_misuse(
-
+    target: Callable,
+    debug_mode: bool,
+):
     async def main():
-        async with tractor.open_nursery() as n:
+        async with tractor.open_nursery(
-            portal = await n.start_actor(
+            debug_mode=debug_mode,
+        ) as an:
+            portal = await an.start_actor(
                 target.__name__,
                 enable_modules=[__name__],
             )
@@ -119,7 +133,7 @@ def test_started_misuse(target):
 @tractor.context
 async def simple_setup_teardown(
 
-    ctx: tractor.Context,
+    ctx: Context,
     data: int,
     block_forever: bool = False,
 
@@ -165,6 +179,7 @@ def test_simple_context(
     error_parent,
     callee_blocks_forever,
     pointlessly_open_stream,
+    debug_mode: bool,
 ):
 
     timeout = 1.5 if not platform.system() == 'Windows' else 4
@@ -172,20 +187,22 @@ def test_simple_context(
     async def main():
 
         with trio.fail_after(timeout):
-            async with tractor.open_nursery() as nursery:
+            async with tractor.open_nursery(
-
+                debug_mode=debug_mode,
-                portal = await nursery.start_actor(
+            ) as an:
+                portal = await an.start_actor(
                     'simple_context',
                     enable_modules=[__name__],
                 )
 
                 try:
-                    async with portal.open_context(
+                    async with (
-                        simple_setup_teardown,
+                        portal.open_context(
-                        data=10,
+                            simple_setup_teardown,
-                        block_forever=callee_blocks_forever,
+                            data=10,
-                    ) as (ctx, sent):
+                            block_forever=callee_blocks_forever,
-
+                        ) as (ctx, sent),
+                    ):
                         assert sent == 11
 
                         if callee_blocks_forever:
@@ -193,9 +210,6 @@ def test_simple_context(
                         else:
                             assert await ctx.result() == 'yo'
 
-                        if not error_parent:
-                            await ctx.cancel()
-
                         if pointlessly_open_stream:
                             async with ctx.open_stream():
                                 if error_parent:
@@ -208,10 +222,15 @@ def test_simple_context(
                                     # 'stop' msg to the far end which needs
                                     # to be ignored
                                     pass
+
                         else:
                             if error_parent:
                                 raise error_parent
 
+                            # cancel AFTER we open a stream
+                            # to avoid a cancel raised inside
+                            # `.open_stream()`
+                            await ctx.cancel()
                 finally:
 
                     # after cancellation
@@ -253,6 +272,7 @@ def test_caller_cancels(
     cancel_method: str,
     chk_ctx_result_before_exit: bool,
     callee_returns_early: bool,
+    debug_mode: bool,
 ):
     '''
     Verify that when the opening side of a context (aka the caller)
@@ -261,37 +281,100 @@ def test_caller_cancels(
 
     '''
     async def check_canceller(
-        ctx: tractor.Context,
+        ctx: Context,
     ) -> None:
-        # should not raise yet return the remote
+        actor: Actor = current_actor()
-        # context cancelled error.
+        uid: tuple = actor.uid
-        res = await ctx.result()
+        _ctxc: ContextCancelled|None = None
 
+        if (
+            cancel_method == 'portal'
+            and not callee_returns_early
+        ):
+            try:
+                res = await ctx.result()
+                assert 0, 'Portal cancel should raise!'
+
+            except ContextCancelled as ctxc:
+                # with trio.CancelScope(shield=True):
+                #     await tractor.pause()
+                _ctxc = ctxc
+                assert ctx.chan._cancel_called
+                assert ctxc.canceller == uid
+                assert ctxc is ctx.maybe_error
+
+        # NOTE: should not ever raise even in the `ctx`
+        # case since self-cancellation should swallow the ctxc
+        # silently!
+        else:
+            try:
+                res = await ctx.result()
+            except ContextCancelled as ctxc:
+                pytest.fail(f'should not have raised ctxc\n{ctxc}')
+
+        # we actually get a result
         if callee_returns_early:
             assert res == 'yo'
+            assert ctx.outcome is res
+            assert ctx.maybe_error is None
 
         else:
-            err = res
+            err: Exception = ctx.outcome
             assert isinstance(err, ContextCancelled)
             assert (
                 tuple(err.canceller)
                 ==
-                tractor.current_actor().uid
+                uid
             )
+            assert (
+                err
+                is ctx.maybe_error
+                is ctx._remote_error
+            )
+            if le := ctx._local_error:
+                assert err is le
+
+            # else:
+                # TODO: what should this be then?
+                # not defined until block closes right?
+                #
+                # await tractor.pause()
+                # assert ctx._local_error is None
+
+        # TODO: don't need this right?
+        # if _ctxc:
+        #     raise _ctxc
+
 
     async def main():
-        async with tractor.open_nursery() as nursery:
+
-            portal = await nursery.start_actor(
+        async with tractor.open_nursery(
+            debug_mode=debug_mode,
+        ) as an:
+            portal = await an.start_actor(
                 'simple_context',
                 enable_modules=[__name__],
             )
-            timeout = 0.5 if not callee_returns_early else 2
+            timeout: float = (
+                0.5
+                if not callee_returns_early
+                else 2
+            )
             with trio.fail_after(timeout):
-                async with portal.open_context(
+                async with (
-                    simple_setup_teardown,
+                    expect_ctxc(
-                    data=10,
+                        yay=(
-                    block_forever=not callee_returns_early,
+                            not callee_returns_early
-                ) as (ctx, sent):
+                            and cancel_method == 'portal'
+                        )
+                    ),
+
+                    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
@@ -300,10 +383,18 @@ def test_caller_cancels(
                         await trio.sleep(0.5)
 
                     if cancel_method == 'ctx':
+                        print('cancelling with `Context.cancel()`')
                         await ctx.cancel()
-                    else:
+
+                    elif cancel_method == 'portal':
+                        print('cancelling with `Portal.cancel_actor()`')
                         await portal.cancel_actor()
 
+                    else:
+                        pytest.fail(
+                            f'Unknown `cancel_method={cancel_method} ?'
+                        )
+
                     if chk_ctx_result_before_exit:
                         await check_canceller(ctx)
 
@@ -313,6 +404,23 @@ def test_caller_cancels(
             if cancel_method != 'portal':
                 await portal.cancel_actor()
 
+            # XXX NOTE XXX: non-normal yet purposeful
+            # test-specific ctxc suppression is implemented!
+            #
+            # WHY: the `.cancel_actor()` case (cancel_method='portal')
+            # will cause both:
+            #  * the `ctx.result()` inside `.open_context().__aexit__()`
+            #  * AND the `ctx.result()` inside `check_canceller()`
+            # to raise ctxc.
+            #
+            #   which should in turn cause `ctx._scope` to
+            # catch any cancellation?
+            if (
+                not callee_returns_early
+                and cancel_method != 'portal'
+            ):
+                assert not ctx._scope.cancelled_caught
+
     trio.run(main)
 
 
@@ -331,7 +439,7 @@ def test_caller_cancels(
 @tractor.context
 async def close_ctx_immediately(
 
-    ctx: tractor.Context,
+    ctx: Context,
 
 ) -> None:
 
@@ -343,17 +451,33 @@ async def close_ctx_immediately(
 
 
 @tractor_test
-async def test_callee_closes_ctx_after_stream_open():
+async def test_callee_closes_ctx_after_stream_open(
-    'callee context closes without using stream'
+    debug_mode: bool,
+):
+    '''
+    callee context closes without using stream.
 
-    async with tractor.open_nursery() as n:
+    This should result in a msg sequence
+    |_<root>_
+             |_<fast_stream_closer>
 
-        portal = await n.start_actor(
+             <= {'started': <Any>, 'cid': <str>}
+             <= {'stop': True, 'cid': <str>}
+             <= {'result': Any, ..}
+
+     (ignored by child)
+    => {'stop': True, 'cid': <str>}
+
+    '''
+    async with tractor.open_nursery(
+        debug_mode=debug_mode,
+    ) as an:
+        portal = await an.start_actor(
             'fast_stream_closer',
             enable_modules=[__name__],
         )
 
-        with trio.fail_after(2):
+        with trio.fail_after(0.5):
             async with portal.open_context(
                 close_ctx_immediately,
 
@@ -361,10 +485,9 @@ async def test_callee_closes_ctx_after_stream_open():
                 # cancel_on_exit=True,
 
             ) as (ctx, sent):
-
                 assert sent is None
 
-                with trio.fail_after(0.5):
+                with trio.fail_after(0.4):
                     async with ctx.open_stream() as stream:
 
                         # should fall through since ``StopAsyncIteration``
@@ -372,12 +495,15 @@ async def test_callee_closes_ctx_after_stream_open():
                         # a ``trio.EndOfChannel`` by
                         # ``trio.abc.ReceiveChannel.__anext__()``
                         async for _ in stream:
+                            # trigger failure if we DO NOT
+                            # get an EOC!
                             assert 0
                         else:
 
                             # verify stream is now closed
                             try:
-                                await stream.receive()
+                                with trio.fail_after(0.3):
+                                    await stream.receive()
                             except trio.EndOfChannel:
                                 pass
 
@@ -397,8 +523,7 @@ async def test_callee_closes_ctx_after_stream_open():
 
 @tractor.context
 async def expect_cancelled(
-
+    ctx: Context,
-    ctx: tractor.Context,
 
 ) -> None:
     global _state
@@ -412,12 +537,29 @@ async def expect_cancelled(
                 await stream.send(msg)  # echo server
 
     except trio.Cancelled:
+
+        # on ctx.cancel() the internal RPC scope is cancelled but
+        # never caught until the func exits.
+        assert ctx._scope.cancel_called
+        assert not ctx._scope.cancelled_caught
+
+        # should be the RPC cmd request for `._cancel_task()`
+        assert ctx._cancel_msg
+        # which, has not yet resolved to an error outcome
+        # since this rpc func has not yet exited.
+        assert not ctx.maybe_error
+        assert not ctx._final_result_is_set()
+
+        # debug REPL if needed
+        # with trio.CancelScope(shield=True):
+        #     await tractor.pause()
+
         # expected case
         _state = False
         raise
 
     else:
-        assert 0, "Wasn't cancelled!?"
+        assert 0, "callee wasn't cancelled !?"
 
 
 @pytest.mark.parametrize(
@@ -427,12 +569,18 @@ async def expect_cancelled(
 @tractor_test
 async def test_caller_closes_ctx_after_callee_opens_stream(
     use_ctx_cancel_method: bool,
+    debug_mode: bool,
 ):
-    'caller context closes without using stream'
+    '''
+    caller context closes without using/opening stream
 
-    async with tractor.open_nursery() as n:
+    '''
+    async with tractor.open_nursery(
+        debug_mode=debug_mode,
+    ) as an:
 
-        portal = await n.start_actor(
+        root: Actor = current_actor()
+        portal = await an.start_actor(
             'ctx_cancelled',
             enable_modules=[__name__],
         )
@@ -440,22 +588,37 @@ async def test_caller_closes_ctx_after_callee_opens_stream(
         async with portal.open_context(
             expect_cancelled,
         ) as (ctx, sent):
-            await portal.run(assert_state, value=True)
-
             assert sent is None
 
-            # call cancel explicitly
+            await portal.run(assert_state, value=True)
-            if use_ctx_cancel_method:
 
+            # call `ctx.cancel()` explicitly
+            if use_ctx_cancel_method:
                 await ctx.cancel()
 
+                # NOTE: means the local side `ctx._scope` will
+                # have been cancelled by an ctxc ack and thus
+                # `._scope.cancelled_caught` should be set.
                 try:
                     async with ctx.open_stream() as stream:
                         async for msg in stream:
                             pass
 
-                except tractor.ContextCancelled:
+                except tractor.ContextCancelled as ctxc:
-                    raise  # XXX: must be propagated to __aexit__
+                    # XXX: the cause is US since we call
+                    # `Context.cancel()` just above!
+                    assert (
+                        ctxc.canceller
+                        ==
+                        current_actor().uid
+                        ==
+                        root.uid
+                    )
+
+                    # XXX: must be propagated to __aexit__
+                    # and should be silently absorbed there
+                    # since we called `.cancel()` just above ;)
+                    raise
 
                 else:
                     assert 0, "Should have context cancelled?"
@@ -464,7 +627,10 @@ async def test_caller_closes_ctx_after_callee_opens_stream(
                 assert portal.channel.connected()
 
                 # ctx is closed here
-                await portal.run(assert_state, value=False)
+                await portal.run(
+                    assert_state,
+                    value=False,
+                )
 
             else:
                 try:
@@ -472,7 +638,25 @@ async def test_caller_closes_ctx_after_callee_opens_stream(
                         await ctx.result()
                         assert 0, "Callee should have blocked!?"
                 except trio.TooSlowError:
+                    # NO-OP -> since already called above
                     await ctx.cancel()
+
+        # NOTE: local scope should have absorbed the cancellation since
+        # in this case we call `ctx.cancel()` and the local
+        # `._scope` does not get `.cancel_called` and thus
+        # `.cancelled_caught` neither will ever bet set.
+        if use_ctx_cancel_method:
+            assert not ctx._scope.cancelled_caught
+
+        # rxed ctxc response from far end
+        assert ctx.cancel_acked
+        assert (
+            ctx._remote_error
+            is ctx._local_error
+            is ctx.maybe_error
+            is ctx.outcome
+        )
+
         try:
             async with ctx.open_stream() as stream:
                 async for msg in stream:
@@ -494,11 +678,13 @@ async def test_caller_closes_ctx_after_callee_opens_stream(
 
 
 @tractor_test
-async def test_multitask_caller_cancels_from_nonroot_task():
+async def test_multitask_caller_cancels_from_nonroot_task(
-
+    debug_mode: bool,
-    async with tractor.open_nursery() as n:
+):
-
+    async with tractor.open_nursery(
-        portal = await n.start_actor(
+        debug_mode=debug_mode,
+    ) as an:
+        portal = await an.start_actor(
             'ctx_cancelled',
             enable_modules=[__name__],
         )
@@ -545,25 +731,31 @@ async def test_multitask_caller_cancels_from_nonroot_task():
 @tractor.context
 async def cancel_self(
 
-    ctx: tractor.Context,
+    ctx: Context,
 
 ) -> None:
     global _state
     _state = True
 
+    # since we call this the below `.open_stream()` should always
+    # error!
     await ctx.cancel()
 
     # should inline raise immediately
     try:
         async with ctx.open_stream():
             pass
-    except tractor.ContextCancelled:
+    # except tractor.ContextCancelled:
+    except RuntimeError:
         # suppress for now so we can do checkpoint tests below
-        pass
+        print('Got expected runtime error for stream-after-cancel')
+
     else:
         raise RuntimeError('Context didnt cancel itself?!')
 
-    # check a real ``trio.Cancelled`` is raised on a checkpoint
+    # check that``trio.Cancelled`` is now raised on any further
+    # checkpoints since the self cancel above will have cancelled
+    # the `Context._scope.cancel_scope: trio.CancelScope`
     try:
         with trio.fail_after(0.1):
             await trio.sleep_forever()
@@ -574,17 +766,22 @@ async def cancel_self(
         # should never get here
         assert 0
 
+    raise RuntimeError('Context didnt cancel itself?!')
+
 
 @tractor_test
-async def test_callee_cancels_before_started():
+async def test_callee_cancels_before_started(
+    debug_mode: bool,
+):
     '''
     Callee calls `Context.cancel()` while streaming and caller
     sees stream terminated in `ContextCancelled`.
 
     '''
-    async with tractor.open_nursery() as n:
+    async with tractor.open_nursery(
-
+        debug_mode=debug_mode,
-        portal = await n.start_actor(
+    ) as an:
+        portal = await an.start_actor(
             'cancels_self',
             enable_modules=[__name__],
         )
@@ -601,7 +798,7 @@ async def test_callee_cancels_before_started():
             ce.type == trio.Cancelled
 
             # the traceback should be informative
-            assert 'cancelled itself' in ce.msgdata['tb_str']
+            assert 'itself' in ce.msgdata['tb_str']
 
         # teardown the actor
         await portal.cancel_actor()
@@ -610,7 +807,7 @@ async def test_callee_cancels_before_started():
 @tractor.context
 async def never_open_stream(
 
-    ctx:  tractor.Context,
+    ctx:  Context,
 
 ) -> None:
     '''
@@ -624,8 +821,8 @@ async def never_open_stream(
 @tractor.context
 async def keep_sending_from_callee(
 
-    ctx:  tractor.Context,
+    ctx:  Context,
-    msg_buffer_size: Optional[int] = None,
+    msg_buffer_size: int|None = None,
 
 ) -> None:
     '''
@@ -650,7 +847,10 @@ async def keep_sending_from_callee(
     ],
     ids='overrun_condition={}'.format,
 )
-def test_one_end_stream_not_opened(overrun_by):
+def test_one_end_stream_not_opened(
+    overrun_by: tuple[str, int, Callable],
+    debug_mode: bool,
+):
     '''
     This should exemplify the bug from:
     https://github.com/goodboy/tractor/issues/265
@@ -661,8 +861,10 @@ def test_one_end_stream_not_opened(overrun_by):
     buf_size = buf_size_increase + Actor.msg_buffer_size
 
     async def main():
-        async with tractor.open_nursery() as n:
+        async with tractor.open_nursery(
-            portal = await n.start_actor(
+            debug_mode=debug_mode,
+        ) as an:
+            portal = await an.start_actor(
                 entrypoint.__name__,
                 enable_modules=[__name__],
             )
@@ -719,7 +921,7 @@ def test_one_end_stream_not_opened(overrun_by):
 @tractor.context
 async def echo_back_sequence(
 
-    ctx:  tractor.Context,
+    ctx:  Context,
     seq: list[int],
     wait_for_cancel: bool,
     allow_overruns_side: str,
@@ -736,7 +938,10 @@ async def echo_back_sequence(
     # 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
+    total_batches: int = (
+        1000 if wait_for_cancel
+        else 6
+    )
 
     await ctx.started()
     # await tractor.breakpoint()
@@ -755,8 +960,23 @@ async def echo_back_sequence(
         )
 
         seq = list(seq)  # bleh, msgpack sometimes ain't decoded right
-        for _ in range(total_batches):
+        for i in range(total_batches):
+            print(f'starting new stream batch {i} iter in child')
             batch = []
+
+            # EoC case, delay a little instead of hot
+            # iter-stopping (since apparently py3.11+ can do that
+            # faster then a ctxc can be sent) on the async for
+            # loop when child was requested to ctxc.
+            if (
+                stream.closed
+                or
+                ctx.cancel_called
+            ):
+                print('child stream already closed!?!')
+                await trio.sleep(0.05)
+                continue
+
             async for msg in stream:
                 batch.append(msg)
                 if batch == seq:
@@ -767,15 +987,18 @@ async def echo_back_sequence(
 
                 print('callee waiting on next')
 
+            print(f'callee echoing back latest batch\n{batch}')
             for msg in batch:
-                print(f'callee sending {msg}')
+                print(f'callee sending msg\n{msg}')
                 await stream.send(msg)
 
-    print(
+    try:
-        'EXITING CALLEEE:\n'
+        return 'yo'
-        f'{ctx.cancel_called_remote}'
+    finally:
-    )
+        print(
-    return 'yo'
+            'exiting callee with context:\n'
+            f'{pformat(ctx)}\n'
+        )
 
 
 @pytest.mark.parametrize(
@@ -801,7 +1024,10 @@ def test_maybe_allow_overruns_stream(
     cancel_ctx: bool,
     slow_side: str,
     allow_overruns_side: str,
+
+    # conftest wide
     loglevel: str,
+    debug_mode: bool,
 ):
     '''
     Demonstrate small overruns of each task back and forth
@@ -820,13 +1046,14 @@ def test_maybe_allow_overruns_stream(
 
     '''
     async def main():
-        async with tractor.open_nursery() as n:
+        async with tractor.open_nursery(
-            portal = await n.start_actor(
+            debug_mode=debug_mode,
+        ) as an:
+            portal = await an.start_actor(
                 'callee_sends_forever',
                 enable_modules=[__name__],
                 loglevel=loglevel,
-
+                debug_mode=debug_mode,
-                # debug_mode=True,
             )
             seq = list(range(10))
             async with portal.open_context(
@@ -835,8 +1062,8 @@ def test_maybe_allow_overruns_stream(
                 wait_for_cancel=cancel_ctx,
                 be_slow=(slow_side == 'child'),
                 allow_overruns_side=allow_overruns_side,
-            ) as (ctx, sent):
 
+            ) as (ctx, sent):
                 assert sent is None
 
                 async with ctx.open_stream(
@@ -864,14 +1091,14 @@ def test_maybe_allow_overruns_stream(
 
                 if cancel_ctx:
                     # cancel the remote task
-                    print('sending root side cancel')
+                    print('Requesting `ctx.cancel()` in parent!')
                     await ctx.cancel()
 
-            res = await ctx.result()
+            res: str|ContextCancelled = await ctx.result()
 
             if cancel_ctx:
                 assert isinstance(res, ContextCancelled)
-                assert tuple(res.canceller) == tractor.current_actor().uid
+                assert tuple(res.canceller) == current_actor().uid
 
             else:
                 print(f'RX ROOT SIDE RESULT {res}')
@@ -924,91 +1151,50 @@ def test_maybe_allow_overruns_stream(
         pytest.fail('PARAMETRIZED CASE GEN PROBLEM YO')
 
 
-@tractor.context
+def test_ctx_with_self_actor(
-async def sleep_forever(
+    loglevel: str,
-    ctx: tractor.Context,
+    debug_mode: bool,
-) -> None:
+):
-    await ctx.started()
-    async with ctx.open_stream():
-        await trio.sleep_forever()
-
-
-@acm
-async def attach_to_sleep_forever():
     '''
-    Cancel a context **before** any underlying error is raised in order
+    NOTE: for now this is an INVALID OP!
-    to trigger a local reception of a ``ContextCancelled`` which **should not**
-    be re-raised in the local surrounding ``Context`` *iff* the cancel was
-    requested by **this** side of the context.
 
-    '''
+    BUT, eventually presuming we add a "side" key to `Actor.get_context()`,
-    async with tractor.wait_for_actor('sleeper') as p2:
+    we might be able to get this working symmetrically, but should we??
-        async with (
-            p2.open_context(sleep_forever) as (peer_ctx, first),
-            peer_ctx.open_stream(),
-        ):
-            try:
-                yield
-            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 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._maybe_raise_from_remote_msg()`` XD
-                await peer_ctx.cancel()
 
-
+    Open a context back to the same actor and ensure all cancellation
-@tractor.context
+    and error semantics hold the same.
-async def error_before_started(
-    ctx: tractor.Context,
-) -> None:
-    '''
-    This simulates exactly an original bug discovered in:
-    https://github.com/pikers/piker/issues/244
-
-    '''
-    async with attach_to_sleep_forever():
-        # send an unserializable type which should raise a type error
-        # here and **NOT BE SWALLOWED** by the surrounding acm!!?!
-        await ctx.started(object())
-
-
-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.
 
     '''
     async def main():
-        async with tractor.open_nursery() as n:
+        async with tractor.open_nursery(
-            portal = await n.start_actor(
+            debug_mode=debug_mode,
-                'errorer',
+            enable_modules=[__name__],
-                enable_modules=[__name__],
+        ) as an:
-            )
+            assert an
-            await n.start_actor(
-                'sleeper',
-                enable_modules=[__name__],
-            )
-
             async with (
+                tractor.find_actor('root') as portal,
                 portal.open_context(
-                    error_before_started
+                    expect_cancelled,
-                ) as (ctx, sent),
+                    # echo_back_sequence,
-            ):
+                    # seq=seq,
-                await trio.sleep_forever()
+                    # wait_for_cancel=cancel_ctx,
+                    # be_slow=(slow_side == 'child'),
+                    # allow_overruns_side=allow_overruns_side,
 
-    with pytest.raises(tractor.RemoteActorError) as excinfo:
+                ) as (ctx, sent),
+                ctx.open_stream() as ipc,
+            ):
+                assert sent is None
+
+                seq = list(range(10))
+                for i in seq:
+                    await ipc.send(i)
+                    rx: int = await ipc.receive()
+                    assert rx == i
+
+                await ctx.cancel()
+
+    with pytest.raises(RuntimeError) as excinfo:
         trio.run(main)
 
-    assert excinfo.value.type == TypeError
+    assert 'Invalid Operation' in repr(excinfo.value)

tests/test_debugger.py

@@ -11,11 +11,9 @@ TODO:
 
 """
 import itertools
-from os import path
 from typing import Optional
 import platform
 import pathlib
-import sys
 import time
 
 import pytest
@@ -25,8 +23,10 @@ from pexpect.exceptions import (
     EOF,
 )
 
-from conftest import (
+from tractor._testing import (
     examples_dir,
+)
+from conftest import (
     _ci_env,
 )
 
@@ -78,7 +78,7 @@ has_nested_actors = pytest.mark.has_nested_actors
 def spawn(
     start_method,
     testdir,
-    arb_addr,
+    reg_addr,
 ) -> 'pexpect.spawn':
 
     if start_method != 'trio':

tests/test_discovery.py

@@ -9,25 +9,24 @@ import itertools
 
 import pytest
 import tractor
+from tractor._testing import tractor_test
 import trio
 
-from conftest import tractor_test
-
 
 @tractor_test
-async def test_reg_then_unreg(arb_addr):
+async def test_reg_then_unreg(reg_addr):
     actor = tractor.current_actor()
     assert actor.is_arbiter
     assert len(actor._registry) == 1  # only self is registered
 
     async with tractor.open_nursery(
-        arbiter_addr=arb_addr,
+        registry_addrs=[reg_addr],
     ) as n:
 
         portal = await n.start_actor('actor', enable_modules=[__name__])
         uid = portal.channel.uid
 
-        async with tractor.get_arbiter(*arb_addr) as aportal:
+        async with tractor.get_arbiter(*reg_addr) as aportal:
             # this local actor should be the arbiter
             assert actor is aportal.actor
 
@@ -53,15 +52,27 @@ async def hi():
     return the_line.format(tractor.current_actor().name)
 
 
-async def say_hello(other_actor):
+async def say_hello(
+    other_actor: str,
+    reg_addr: tuple[str, int],
+):
     await trio.sleep(1)  # wait for other actor to spawn
-    async with tractor.find_actor(other_actor) as portal:
+    async with tractor.find_actor(
+        other_actor,
+        registry_addrs=[reg_addr],
+    ) as portal:
         assert portal is not None
         return await portal.run(__name__, 'hi')
 
 
-async def say_hello_use_wait(other_actor):
+async def say_hello_use_wait(
-    async with tractor.wait_for_actor(other_actor) as portal:
+    other_actor: str,
+    reg_addr: tuple[str, int],
+):
+    async with tractor.wait_for_actor(
+        other_actor,
+        registry_addr=reg_addr,
+    ) as portal:
         assert portal is not None
         result = await portal.run(__name__, 'hi')
         return result
@@ -69,21 +80,29 @@ async def say_hello_use_wait(other_actor):
 
 @tractor_test
 @pytest.mark.parametrize('func', [say_hello, say_hello_use_wait])
-async def test_trynamic_trio(func, start_method, arb_addr):
+async def test_trynamic_trio(
-    """Main tractor entry point, the "master" process (for now
+    func,
-    acts as the "director").
+    start_method,
-    """
+    reg_addr,
+):
+    '''
+    Root actor acting as the "director" and running one-shot-task-actors
+    for the directed subs.
+
+    '''
     async with tractor.open_nursery() as n:
         print("Alright... Action!")
 
         donny = await n.run_in_actor(
             func,
             other_actor='gretchen',
+            reg_addr=reg_addr,
             name='donny',
         )
         gretchen = await n.run_in_actor(
             func,
             other_actor='donny',
+            reg_addr=reg_addr,
             name='gretchen',
         )
         print(await gretchen.result())
@@ -131,7 +150,7 @@ async def unpack_reg(actor_or_portal):
 
 
 async def spawn_and_check_registry(
-    arb_addr: tuple,
+    reg_addr: tuple,
     use_signal: bool,
     remote_arbiter: bool = False,
     with_streaming: bool = False,
@@ -139,9 +158,9 @@ async def spawn_and_check_registry(
 ) -> None:
 
     async with tractor.open_root_actor(
-        arbiter_addr=arb_addr,
+        registry_addrs=[reg_addr],
     ):
-        async with tractor.get_arbiter(*arb_addr) as portal:
+        async with tractor.get_arbiter(*reg_addr) as portal:
             # runtime needs to be up to call this
             actor = tractor.current_actor()
 
@@ -213,17 +232,19 @@ async def spawn_and_check_registry(
 def test_subactors_unregister_on_cancel(
     start_method,
     use_signal,
-    arb_addr,
+    reg_addr,
     with_streaming,
 ):
-    """Verify that cancelling a nursery results in all subactors
+    '''
+    Verify that cancelling a nursery results in all subactors
     deregistering themselves with the arbiter.
-    """
+
+    '''
     with pytest.raises(KeyboardInterrupt):
         trio.run(
             partial(
                 spawn_and_check_registry,
-                arb_addr,
+                reg_addr,
                 use_signal,
                 remote_arbiter=False,
                 with_streaming=with_streaming,
@@ -237,7 +258,7 @@ def test_subactors_unregister_on_cancel_remote_daemon(
     daemon,
     start_method,
     use_signal,
-    arb_addr,
+    reg_addr,
     with_streaming,
 ):
     """Verify that cancelling a nursery results in all subactors
@@ -248,7 +269,7 @@ def test_subactors_unregister_on_cancel_remote_daemon(
         trio.run(
             partial(
                 spawn_and_check_registry,
-                arb_addr,
+                reg_addr,
                 use_signal,
                 remote_arbiter=True,
                 with_streaming=with_streaming,
@@ -262,7 +283,7 @@ async def streamer(agen):
 
 
 async def close_chans_before_nursery(
-    arb_addr: tuple,
+    reg_addr: tuple,
     use_signal: bool,
     remote_arbiter: bool = False,
 ) -> None:
@@ -275,9 +296,9 @@ async def close_chans_before_nursery(
         entries_at_end = 1
 
     async with tractor.open_root_actor(
-        arbiter_addr=arb_addr,
+        registry_addrs=[reg_addr],
     ):
-        async with tractor.get_arbiter(*arb_addr) as aportal:
+        async with tractor.get_arbiter(*reg_addr) as aportal:
             try:
                 get_reg = partial(unpack_reg, aportal)
 
@@ -329,7 +350,7 @@ async def close_chans_before_nursery(
 def test_close_channel_explicit(
     start_method,
     use_signal,
-    arb_addr,
+    reg_addr,
 ):
     """Verify that closing a stream explicitly and killing the actor's
     "root nursery" **before** the containing nursery tears down also
@@ -339,7 +360,7 @@ def test_close_channel_explicit(
         trio.run(
             partial(
                 close_chans_before_nursery,
-                arb_addr,
+                reg_addr,
                 use_signal,
                 remote_arbiter=False,
             ),
@@ -351,7 +372,7 @@ def test_close_channel_explicit_remote_arbiter(
     daemon,
     start_method,
     use_signal,
-    arb_addr,
+    reg_addr,
 ):
     """Verify that closing a stream explicitly and killing the actor's
     "root nursery" **before** the containing nursery tears down also
@@ -361,7 +382,7 @@ def test_close_channel_explicit_remote_arbiter(
         trio.run(
             partial(
                 close_chans_before_nursery,
-                arb_addr,
+                reg_addr,
                 use_signal,
                 remote_arbiter=True,
             ),

tests/test_docs_examples.py

@@ -11,8 +11,7 @@ import platform
 import shutil
 
 import pytest
-
+from tractor._testing import (
-from conftest import (
     examples_dir,
 )
 

tests/test_infected_asyncio.py

@@ -8,7 +8,6 @@ import builtins
 import itertools
 import importlib
 
-from exceptiongroup import BaseExceptionGroup
 import pytest
 import trio
 import tractor
@@ -18,6 +17,7 @@ from tractor import (
     ContextCancelled,
 )
 from tractor.trionics import BroadcastReceiver
+from tractor._testing import expect_ctxc
 
 
 async def sleep_and_err(
@@ -47,7 +47,7 @@ async def trio_cancels_single_aio_task():
         await tractor.to_asyncio.run_task(sleep_forever)
 
 
-def test_trio_cancels_aio_on_actor_side(arb_addr):
+def test_trio_cancels_aio_on_actor_side(reg_addr):
     '''
     Spawn an infected actor that is cancelled by the ``trio`` side
     task using std cancel scope apis.
@@ -55,7 +55,7 @@ def test_trio_cancels_aio_on_actor_side(arb_addr):
     '''
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr
+            registry_addrs=[reg_addr]
         ) as n:
             await n.run_in_actor(
                 trio_cancels_single_aio_task,
@@ -68,7 +68,7 @@ def test_trio_cancels_aio_on_actor_side(arb_addr):
 async def asyncio_actor(
 
     target: str,
-    expect_err: Optional[Exception] = None
+    expect_err: Exception|None = None
 
 ) -> None:
 
@@ -94,7 +94,7 @@ async def asyncio_actor(
         raise
 
 
-def test_aio_simple_error(arb_addr):
+def test_aio_simple_error(reg_addr):
     '''
     Verify a simple remote asyncio error propagates back through trio
     to the parent actor.
@@ -103,7 +103,7 @@ def test_aio_simple_error(arb_addr):
     '''
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr
+            registry_addrs=[reg_addr]
         ) as n:
             await n.run_in_actor(
                 asyncio_actor,
@@ -112,15 +112,26 @@ def test_aio_simple_error(arb_addr):
                 infect_asyncio=True,
             )
 
-    with pytest.raises(RemoteActorError) as excinfo:
+    with pytest.raises(
+        expected_exception=(RemoteActorError, ExceptionGroup),
+    ) as excinfo:
         trio.run(main)
 
     err = excinfo.value
+
+    # might get multiple `trio.Cancelled`s as well inside an inception
+    if isinstance(err, ExceptionGroup):
+        err = next(itertools.dropwhile(
+            lambda exc: not isinstance(exc, tractor.RemoteActorError),
+            err.exceptions
+        ))
+        assert err
+
     assert isinstance(err, RemoteActorError)
     assert err.type == AssertionError
 
 
-def test_tractor_cancels_aio(arb_addr):
+def test_tractor_cancels_aio(reg_addr):
     '''
     Verify we can cancel a spawned asyncio task gracefully.
 
@@ -139,7 +150,7 @@ def test_tractor_cancels_aio(arb_addr):
     trio.run(main)
 
 
-def test_trio_cancels_aio(arb_addr):
+def test_trio_cancels_aio(reg_addr):
     '''
     Much like the above test with ``tractor.Portal.cancel_actor()``
     except we just use a standard ``trio`` cancellation api.
@@ -190,11 +201,12 @@ async def trio_ctx(
 
 
 @pytest.mark.parametrize(
-    'parent_cancels', [False, True],
+    'parent_cancels',
+    ['context', 'actor', False],
     ids='parent_actor_cancels_child={}'.format
 )
 def test_context_spawns_aio_task_that_errors(
-    arb_addr,
+    reg_addr,
     parent_cancels: bool,
 ):
     '''
@@ -214,18 +226,36 @@ def test_context_spawns_aio_task_that_errors(
                     # debug_mode=True,
                     loglevel='cancel',
                 )
-                async with p.open_context(
+                async with (
-                    trio_ctx,
+                    expect_ctxc(
-                ) as (ctx, first):
+                        yay=parent_cancels == 'actor',
+                    ),
+                    p.open_context(
+                        trio_ctx,
+                    ) as (ctx, first),
+                ):
 
                     assert first == 'start'
 
-                    if parent_cancels:
+                    if parent_cancels == 'actor':
                         await p.cancel_actor()
 
-                    await trio.sleep_forever()
+                    elif parent_cancels == 'context':
+                        await ctx.cancel()
 
-        return await ctx.result()
+                    else:
+                        await trio.sleep_forever()
+
+                async with expect_ctxc(
+                    yay=parent_cancels == 'actor',
+                ):
+                    await ctx.result()
+
+                if parent_cancels == 'context':
+                    # to tear down sub-acor
+                    await p.cancel_actor()
+
+        return ctx.outcome
 
     if parent_cancels:
         # bc the parent made the cancel request,
@@ -258,7 +288,7 @@ async def aio_cancel():
     await sleep_forever()
 
 
-def test_aio_cancelled_from_aio_causes_trio_cancelled(arb_addr):
+def test_aio_cancelled_from_aio_causes_trio_cancelled(reg_addr):
 
     async def main():
         async with tractor.open_nursery() as n:
@@ -269,11 +299,22 @@ def test_aio_cancelled_from_aio_causes_trio_cancelled(arb_addr):
                 infect_asyncio=True,
             )
 
-    with pytest.raises(RemoteActorError) as excinfo:
+    with pytest.raises(
+        expected_exception=(RemoteActorError, ExceptionGroup),
+    ) as excinfo:
         trio.run(main)
 
+    # might get multiple `trio.Cancelled`s as well inside an inception
+    err = excinfo.value
+    if isinstance(err, ExceptionGroup):
+        err = next(itertools.dropwhile(
+            lambda exc: not isinstance(exc, tractor.RemoteActorError),
+            err.exceptions
+        ))
+        assert err
+
     # ensure boxed error is correct
-    assert excinfo.value.type == to_asyncio.AsyncioCancelled
+    assert err.type == to_asyncio.AsyncioCancelled
 
 
 # TODO: verify open_channel_from will fail on this..
@@ -395,7 +436,7 @@ async def stream_from_aio(
     'fan_out', [False, True],
     ids='fan_out_w_chan_subscribe={}'.format
 )
-def test_basic_interloop_channel_stream(arb_addr, fan_out):
+def test_basic_interloop_channel_stream(reg_addr, fan_out):
     async def main():
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
@@ -409,7 +450,7 @@ def test_basic_interloop_channel_stream(arb_addr, fan_out):
 
 
 # TODO: parametrize the above test and avoid the duplication here?
-def test_trio_error_cancels_intertask_chan(arb_addr):
+def test_trio_error_cancels_intertask_chan(reg_addr):
     async def main():
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
@@ -428,7 +469,7 @@ def test_trio_error_cancels_intertask_chan(arb_addr):
         assert exc.type == Exception
 
 
-def test_trio_closes_early_and_channel_exits(arb_addr):
+def test_trio_closes_early_and_channel_exits(reg_addr):
     async def main():
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
@@ -443,7 +484,7 @@ def test_trio_closes_early_and_channel_exits(arb_addr):
     trio.run(main)
 
 
-def test_aio_errors_and_channel_propagates_and_closes(arb_addr):
+def test_aio_errors_and_channel_propagates_and_closes(reg_addr):
     async def main():
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
@@ -520,7 +561,7 @@ async def trio_to_aio_echo_server(
     ids='raise_error={}'.format,
 )
 def test_echoserver_detailed_mechanics(
-    arb_addr,
+    reg_addr,
     raise_error_mid_stream,
 ):
 

tests/test_legacy_one_way_streaming.py

@@ -9,7 +9,7 @@ import trio
 import tractor
 import pytest
 
-from conftest import tractor_test
+from tractor._testing import tractor_test
 
 
 def test_must_define_ctx():
@@ -55,7 +55,7 @@ async def context_stream(
 
 
 async def stream_from_single_subactor(
-    arb_addr,
+    reg_addr,
     start_method,
     stream_func,
 ):
@@ -64,7 +64,7 @@ async def stream_from_single_subactor(
     # only one per host address, spawns an actor if None
 
     async with tractor.open_nursery(
-        arbiter_addr=arb_addr,
+        registry_addrs=[reg_addr],
         start_method=start_method,
     ) as nursery:
 
@@ -115,13 +115,13 @@ async def stream_from_single_subactor(
 @pytest.mark.parametrize(
     'stream_func', [async_gen_stream, context_stream]
 )
-def test_stream_from_single_subactor(arb_addr, start_method, stream_func):
+def test_stream_from_single_subactor(reg_addr, start_method, stream_func):
     """Verify streaming from a spawned async generator.
     """
     trio.run(
         partial(
             stream_from_single_subactor,
-            arb_addr,
+            reg_addr,
             start_method,
             stream_func=stream_func,
         ),
@@ -225,14 +225,14 @@ async def a_quadruple_example():
         return result_stream
 
 
-async def cancel_after(wait, arb_addr):
+async def cancel_after(wait, reg_addr):
-    async with tractor.open_root_actor(arbiter_addr=arb_addr):
+    async with tractor.open_root_actor(registry_addrs=[reg_addr]):
         with trio.move_on_after(wait):
             return await a_quadruple_example()
 
 
 @pytest.fixture(scope='module')
-def time_quad_ex(arb_addr, ci_env, spawn_backend):
+def time_quad_ex(reg_addr, ci_env, spawn_backend):
     if spawn_backend == 'mp':
         """no idea but the  mp *nix runs are flaking out here often...
         """
@@ -240,7 +240,7 @@ def time_quad_ex(arb_addr, ci_env, spawn_backend):
 
     timeout = 7 if platform.system() in ('Windows', 'Darwin') else 4
     start = time.time()
-    results = trio.run(cancel_after, timeout, arb_addr)
+    results = trio.run(cancel_after, timeout, reg_addr)
     diff = time.time() - start
     assert results
     return results, diff
@@ -260,14 +260,14 @@ def test_a_quadruple_example(time_quad_ex, ci_env, spawn_backend):
     list(map(lambda i: i/10, range(3, 9)))
 )
 def test_not_fast_enough_quad(
-    arb_addr, time_quad_ex, cancel_delay, ci_env, spawn_backend
+    reg_addr, time_quad_ex, cancel_delay, ci_env, spawn_backend
 ):
     """Verify we can cancel midway through the quad example and all actors
     cancel gracefully.
     """
     results, diff = time_quad_ex
     delay = max(diff - cancel_delay, 0)
-    results = trio.run(cancel_after, delay, arb_addr)
+    results = trio.run(cancel_after, delay, reg_addr)
     system = platform.system()
     if system in ('Windows', 'Darwin') and results is not None:
         # In CI envoirments it seems later runs are quicker then the first
@@ -280,7 +280,7 @@ def test_not_fast_enough_quad(
 
 @tractor_test
 async def test_respawn_consumer_task(
-    arb_addr,
+    reg_addr,
     spawn_backend,
     loglevel,
 ):

tests/test_local.py

@@ -7,7 +7,7 @@ import pytest
 import trio
 import tractor
 
-from conftest import tractor_test
+from tractor._testing import tractor_test
 
 
 @pytest.mark.trio
@@ -24,7 +24,7 @@ async def test_no_runtime():
 
 
 @tractor_test
-async def test_self_is_registered(arb_addr):
+async def test_self_is_registered(reg_addr):
     "Verify waiting on the arbiter to register itself using the standard api."
     actor = tractor.current_actor()
     assert actor.is_arbiter
@@ -34,20 +34,20 @@ async def test_self_is_registered(arb_addr):
 
 
 @tractor_test
-async def test_self_is_registered_localportal(arb_addr):
+async def test_self_is_registered_localportal(reg_addr):
     "Verify waiting on the arbiter to register itself using a local portal."
     actor = tractor.current_actor()
     assert actor.is_arbiter
-    async with tractor.get_arbiter(*arb_addr) as portal:
+    async with tractor.get_arbiter(*reg_addr) as portal:
         assert isinstance(portal, tractor._portal.LocalPortal)
 
         with trio.fail_after(0.2):
             sockaddr = await portal.run_from_ns(
                     'self', 'wait_for_actor', name='root')
-            assert sockaddr[0] == arb_addr
+            assert sockaddr[0] == reg_addr
 
 
-def test_local_actor_async_func(arb_addr):
+def test_local_actor_async_func(reg_addr):
     """Verify a simple async function in-process.
     """
     nums = []
@@ -55,7 +55,7 @@ def test_local_actor_async_func(arb_addr):
     async def print_loop():
 
         async with tractor.open_root_actor(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ):
             # arbiter is started in-proc if dne
             assert tractor.current_actor().is_arbiter

tests/test_multi_program.py

@@ -7,8 +7,10 @@ import time
 import pytest
 import trio
 import tractor
-from conftest import (
+from tractor._testing import (
     tractor_test,
+)
+from conftest import (
     sig_prog,
     _INT_SIGNAL,
     _INT_RETURN_CODE,
@@ -28,9 +30,9 @@ def test_abort_on_sigint(daemon):
 
 
 @tractor_test
-async def test_cancel_remote_arbiter(daemon, arb_addr):
+async def test_cancel_remote_arbiter(daemon, reg_addr):
     assert not tractor.current_actor().is_arbiter
-    async with tractor.get_arbiter(*arb_addr) as portal:
+    async with tractor.get_arbiter(*reg_addr) as portal:
         await portal.cancel_actor()
 
     time.sleep(0.1)
@@ -39,16 +41,16 @@ async def test_cancel_remote_arbiter(daemon, arb_addr):
 
     # no arbiter socket should exist
     with pytest.raises(OSError):
-        async with tractor.get_arbiter(*arb_addr) as portal:
+        async with tractor.get_arbiter(*reg_addr) as portal:
             pass
 
 
-def test_register_duplicate_name(daemon, arb_addr):
+def test_register_duplicate_name(daemon, reg_addr):
 
     async def main():
 
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as n:
 
             assert not tractor.current_actor().is_arbiter

tests/test_pubsub.py

@@ -5,8 +5,7 @@ import pytest
 import trio
 import tractor
 from tractor.experimental import msgpub
-
+from tractor._testing import tractor_test
-from conftest import tractor_test
 
 
 def test_type_checks():
@@ -160,7 +159,7 @@ async def test_required_args(callwith_expecterror):
 )
 def test_multi_actor_subs_arbiter_pub(
     loglevel,
-    arb_addr,
+    reg_addr,
     pub_actor,
 ):
     """Try out the neato @pub decorator system.
@@ -170,7 +169,7 @@ def test_multi_actor_subs_arbiter_pub(
     async def main():
 
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
             enable_modules=[__name__],
         ) as n:
 
@@ -255,12 +254,12 @@ def test_multi_actor_subs_arbiter_pub(
 
 def test_single_subactor_pub_multitask_subs(
     loglevel,
-    arb_addr,
+    reg_addr,
 ):
     async def main():
 
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
             enable_modules=[__name__],
         ) as n:
 

tests/test_resource_cache.py

@@ -34,7 +34,6 @@ def test_resource_only_entered_once(key_on):
     global _resource
     _resource = 0
 
-    kwargs = {}
     key = None
     if key_on == 'key_value':
         key = 'some_common_key'
@@ -139,7 +138,7 @@ def test_open_local_sub_to_stream():
     N local tasks using ``trionics.maybe_open_context():``.
 
     '''
-    timeout = 3 if platform.system() != "Windows" else 10
+    timeout: float = 3.6 if platform.system() != "Windows" else 10
 
     async def main():
 

tests/test_rpc.py

@@ -1,6 +1,8 @@
-"""
+'''
-RPC related
+RPC (or maybe better labelled as "RTS: remote task scheduling"?)
-"""
+related API and error checks.
+
+'''
 import itertools
 
 import pytest
@@ -42,10 +44,15 @@ async def short_sleep():
         (['tmp_mod'], 'import doggy', ModuleNotFoundError),
         (['tmp_mod'], '4doggy', SyntaxError),
     ],
-    ids=['no_mods', 'this_mod', 'this_mod_bad_func', 'fail_to_import',
+    ids=[
-         'fail_on_syntax'],
+        'no_mods',
+        'this_mod',
+        'this_mod_bad_func',
+        'fail_to_import',
+        'fail_on_syntax',
+    ],
 )
-def test_rpc_errors(arb_addr, to_call, testdir):
+def test_rpc_errors(reg_addr, to_call, testdir):
     """Test errors when making various RPC requests to an actor
     that either doesn't have the requested module exposed or doesn't define
     the named function.
@@ -77,7 +84,7 @@ def test_rpc_errors(arb_addr, to_call, testdir):
 
         # spawn a subactor which calls us back
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            arbiter_addr=reg_addr,
             enable_modules=exposed_mods.copy(),
         ) as n:
 
@@ -105,14 +112,16 @@ def test_rpc_errors(arb_addr, to_call, testdir):
         run()
     else:
         # underlying errors aren't propagated upwards (yet)
-        with pytest.raises(remote_err) as err:
+        with pytest.raises(
+            expected_exception=(remote_err, ExceptionGroup),
+        ) as err:
             run()
 
         # get raw instance from pytest wrapper
         value = err.value
 
         # might get multiple `trio.Cancelled`s as well inside an inception
-        if isinstance(value, trio.MultiError):
+        if isinstance(value, ExceptionGroup):
             value = next(itertools.dropwhile(
                 lambda exc: not isinstance(exc, tractor.RemoteActorError),
                 value.exceptions

tests/test_runtime.py

@@ -8,7 +8,7 @@ import pytest
 import trio
 import tractor
 
-from conftest import tractor_test
+from tractor._testing import tractor_test
 
 
 _file_path: str = ''
@@ -64,7 +64,8 @@ async def test_lifetime_stack_wipes_tmpfile(
 
     except (
         tractor.RemoteActorError,
-        tractor.BaseExceptionGroup,
+        # tractor.BaseExceptionGroup,
+        BaseExceptionGroup,
     ):
         pass
 

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_spawning.py

@@ -8,7 +8,7 @@ import pytest
 import trio
 import tractor
 
-from conftest import tractor_test
+from tractor._testing import tractor_test
 
 data_to_pass_down = {'doggy': 10, 'kitty': 4}
 
@@ -16,14 +16,14 @@ data_to_pass_down = {'doggy': 10, 'kitty': 4}
 async def spawn(
     is_arbiter: bool,
     data: dict,
-    arb_addr: tuple[str, int],
+    reg_addr: tuple[str, int],
 ):
     namespaces = [__name__]
 
     await trio.sleep(0.1)
 
     async with tractor.open_root_actor(
-        arbiter_addr=arb_addr,
+        arbiter_addr=reg_addr,
     ):
 
         actor = tractor.current_actor()
@@ -41,7 +41,7 @@ async def spawn(
                     is_arbiter=False,
                     name='sub-actor',
                     data=data,
-                    arb_addr=arb_addr,
+                    reg_addr=reg_addr,
                     enable_modules=namespaces,
                 )
 
@@ -55,12 +55,12 @@ async def spawn(
             return 10
 
 
-def test_local_arbiter_subactor_global_state(arb_addr):
+def test_local_arbiter_subactor_global_state(reg_addr):
     result = trio.run(
         spawn,
         True,
         data_to_pass_down,
-        arb_addr,
+        reg_addr,
     )
     assert result == 10
 
@@ -140,7 +140,7 @@ async def check_loglevel(level):
 def test_loglevel_propagated_to_subactor(
     start_method,
     capfd,
-    arb_addr,
+    reg_addr,
 ):
     if start_method == 'mp_forkserver':
         pytest.skip(
@@ -152,7 +152,7 @@ def test_loglevel_propagated_to_subactor(
         async with tractor.open_nursery(
             name='arbiter',
             start_method=start_method,
-            arbiter_addr=arb_addr,
+            arbiter_addr=reg_addr,
 
         ) as tn:
             await tn.run_in_actor(

tests/test_task_broadcasting.py

@@ -66,13 +66,13 @@ async def ensure_sequence(
 async def open_sequence_streamer(
 
     sequence: list[int],
-    arb_addr: tuple[str, int],
+    reg_addr: tuple[str, int],
     start_method: str,
 
 ) -> tractor.MsgStream:
 
     async with tractor.open_nursery(
-        arbiter_addr=arb_addr,
+        arbiter_addr=reg_addr,
         start_method=start_method,
     ) as tn:
 
@@ -93,7 +93,7 @@ async def open_sequence_streamer(
 
 
 def test_stream_fan_out_to_local_subscriptions(
-    arb_addr,
+    reg_addr,
     start_method,
 ):
 
@@ -103,7 +103,7 @@ def test_stream_fan_out_to_local_subscriptions(
 
         async with open_sequence_streamer(
             sequence,
-            arb_addr,
+            reg_addr,
             start_method,
         ) as stream:
 
@@ -138,7 +138,7 @@ def test_stream_fan_out_to_local_subscriptions(
     ]
 )
 def test_consumer_and_parent_maybe_lag(
-    arb_addr,
+    reg_addr,
     start_method,
     task_delays,
 ):
@@ -150,7 +150,7 @@ def test_consumer_and_parent_maybe_lag(
 
         async with open_sequence_streamer(
             sequence,
-            arb_addr,
+            reg_addr,
             start_method,
         ) as stream:
 
@@ -211,7 +211,7 @@ def test_consumer_and_parent_maybe_lag(
 
 
 def test_faster_task_to_recv_is_cancelled_by_slower(
-    arb_addr,
+    reg_addr,
     start_method,
 ):
     '''
@@ -225,7 +225,7 @@ def test_faster_task_to_recv_is_cancelled_by_slower(
 
         async with open_sequence_streamer(
             sequence,
-            arb_addr,
+            reg_addr,
             start_method,
 
         ) as stream:
@@ -302,7 +302,7 @@ def test_subscribe_errors_after_close():
 
 
 def test_ensure_slow_consumers_lag_out(
-    arb_addr,
+    reg_addr,
     start_method,
 ):
     '''This is a pure local task test; no tractor

tests/test_trioisms.py

@@ -5,7 +5,7 @@ want to see changed.
 '''
 import pytest
 import trio
-from trio_typing import TaskStatus
+from trio import TaskStatus
 
 
 @pytest.mark.parametrize(

tractor/__init__.py

@@ -23,8 +23,8 @@ from exceptiongroup import BaseExceptionGroup
 from ._clustering import open_actor_cluster
 from ._ipc import Channel
 from ._context import (
-    Context,
+    Context,  # the type
-    context,
+    context,  # a func-decorator
 )
 from ._streaming import (
     MsgStream,

tractor/_child.py

@@ -18,8 +18,6 @@
 This is the "bootloader" for actors started using the native trio backend.
 
 """
-import sys
-import trio
 import argparse
 
 from ast import literal_eval
@@ -37,8 +35,6 @@ def parse_ipaddr(arg):
     return (str(host), int(port))
 
 
-from ._entry import _trio_main
-
 if __name__ == "__main__":
 
     parser = argparse.ArgumentParser()

tractor/_entry.py

@@ -106,25 +106,29 @@ def _trio_main(
     Entry point for a `trio_run_in_process` subactor.
 
     '''
-    log.info(f"Started new trio process for {actor.uid}")
-
-    if actor.loglevel is not None:
-        log.info(
-            f"Setting loglevel for {actor.uid} to {actor.loglevel}")
-        get_console_log(actor.loglevel)
-
-    log.info(
-        f"Started {actor.uid}")
-
     _state._current_actor = actor
-
-    log.debug(f"parent_addr is {parent_addr}")
     trio_main = partial(
         async_main,
         actor,
         parent_addr=parent_addr
     )
 
+    if actor.loglevel is not None:
+        get_console_log(actor.loglevel)
+        import os
+        actor_info: str = (
+            f'|_{actor}\n'
+            f'  uid: {actor.uid}\n'
+            f'  pid: {os.getpid()}\n'
+            f'  parent_addr: {parent_addr}\n'
+            f'  loglevel: {actor.loglevel}\n'
+        )
+        log.info(
+            'Started new trio process:\n'
+            +
+            actor_info
+        )
+
     try:
         if infect_asyncio:
             actor._infected_aio = True
@@ -132,7 +136,15 @@ def _trio_main(
         else:
             trio.run(trio_main)
     except KeyboardInterrupt:
-        log.cancel(f"Actor {actor.uid} received KBI")
+        log.cancel(
+            'Actor received KBI\n'
+            +
+            actor_info
+        )
 
     finally:
-        log.info(f"Actor {actor.uid} terminated")
+        log.info(
+            'Actor terminated\n'
+            +
+            actor_info
+        )

tractor/_exceptions.py

@@ -14,22 +14,34 @@
 # 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/>.
 
-"""
+'''
 Our classy exception set.
 
-"""
+'''
+from __future__ import annotations
 import builtins
 import importlib
+from pprint import pformat
 from typing import (
     Any,
     Type,
+    TYPE_CHECKING,
 )
+import textwrap
 import traceback
 
-import exceptiongroup as eg
 import trio
 
-from ._state import current_actor
+from tractor._state import current_actor
+from tractor.log import get_logger
+
+if TYPE_CHECKING:
+    from ._context import Context
+    from .log import StackLevelAdapter
+    from ._stream import MsgStream
+    from ._ipc import Channel
+
+log = get_logger('tractor')
 
 _this_mod = importlib.import_module(__name__)
 
@@ -38,9 +50,40 @@ class ActorFailure(Exception):
     "General actor failure"
 
 
+class InternalError(RuntimeError):
+    '''
+    Entirely unexpected internal machinery error indicating
+    a completely invalid state or interface.
+
+    '''
+
+_body_fields: list[str] = [
+    'src_actor_uid',
+    'canceller',
+    'sender',
+]
+
+_msgdata_keys: list[str] = [
+    'type_str',
+] + _body_fields
+
+
+
+# TODO: rename to just `RemoteError`?
 class RemoteActorError(Exception):
-    # TODO: local recontruction of remote exception deats
+    '''
-    "Remote actor exception bundled locally"
+    A box(ing) type which bundles a remote actor `BaseException` for
+    (near identical, and only if possible,) local object/instance
+    re-construction in the local process memory domain.
+
+    Normally each instance is expected to be constructed from
+    a special "error" IPC msg sent by some remote actor-runtime.
+
+    '''
+    reprol_fields: list[str] = [
+        'src_actor_uid',
+    ]
+
     def __init__(
         self,
         message: str,
@@ -50,18 +93,101 @@ class RemoteActorError(Exception):
     ) -> None:
         super().__init__(message)
 
-        self.type = suberror_type
+        # TODO: maybe a better name?
-        self.msgdata = msgdata
+        # - .errtype
+        # - .retype
+        # - .boxed_errtype
+        # - .boxed_type
+        # - .remote_type
+        # also pertains to our long long oustanding issue XD
+        # https://github.com/goodboy/tractor/issues/5
+        self.boxed_type: str = suberror_type
+        self.msgdata: dict[str, Any] = msgdata
 
     @property
-    def src_actor_uid(self) -> tuple[str, str] | None:
+    def type(self) -> str:
+        return self.boxed_type
+
+    @property
+    def type_str(self) -> str:
+        return str(type(self.boxed_type).__name__)
+
+    @property
+    def src_actor_uid(self) -> tuple[str, str]|None:
         return self.msgdata.get('src_actor_uid')
 
+    @property
+    def tb_str(
+        self,
+        indent: str = ' '*3,
+    ) -> str:
+        if remote_tb := self.msgdata.get('tb_str'):
+            return textwrap.indent(
+                remote_tb,
+                prefix=indent,
+            )
+
+        return ''
+
+    def reprol(self) -> str:
+        '''
+        Represent this error for "one line" display, like in
+        a field of our `Context.__repr__()` output.
+
+        '''
+        _repr: str = f'{type(self).__name__}('
+        for key in self.reprol_fields:
+            val: Any|None = self.msgdata.get(key)
+            if val:
+                _repr += f'{key}={repr(val)} '
+
+        return _repr
+
+    def __repr__(self) -> str:
+
+        fields: str = ''
+        for key in _body_fields:
+            val: str|None = self.msgdata.get(key)
+            if val:
+                fields += f'{key}={val}\n'
+
+        fields: str = textwrap.indent(
+            fields,
+            # prefix=' '*2,
+            prefix=' |_',
+        )
+        indent: str = ''*1
+        body: str = (
+            f'{fields}'
+            f'  |\n'
+            f'   ------ - ------\n\n'
+            f'{self.tb_str}\n'
+            f'   ------ - ------\n'
+            f' _|\n'
+        )
+            # f'|\n'
+            # f'         |\n'
+        if indent:
+            body: str = textwrap.indent(
+                body,
+                prefix=indent,
+            )
+        return (
+            f'<{type(self).__name__}(\n'
+            f'{body}'
+            ')>'
+        )
+
+    # TODO: local recontruction of remote exception deats
+    # def unbox(self) -> BaseException:
+    #     ...
+
 
 class InternalActorError(RemoteActorError):
     '''
-    Remote internal ``tractor`` error indicating
+    (Remote) internal `tractor` error indicating failure of some
-    failure of some primitive or machinery.
+    primitive, machinery state or lowlevel task that should never
+    occur.
 
     '''
 
@@ -72,12 +198,43 @@ class ContextCancelled(RemoteActorError):
     ``Portal.cancel_actor()`` or ``Context.cancel()``.
 
     '''
+    reprol_fields: list[str] = [
+        'canceller',
+    ]
     @property
-    def canceller(self) -> tuple[str, str] | None:
+    def canceller(self) -> tuple[str, str]|None:
+        '''
+        Return the (maybe) `Actor.uid` for the requesting-author
+        of this ctxc.
+
+        Emit a warning msg when `.canceller` has not been set,
+        which usually idicates that a `None` msg-loop setinel was
+        sent before expected in the runtime. This can happen in
+        a few situations:
+
+        - (simulating) an IPC transport network outage
+        - a (malicious) pkt sent specifically to cancel an actor's
+          runtime non-gracefully without ensuring ongoing RPC tasks are 
+          incrementally cancelled as is done with:
+          `Actor`
+          |_`.cancel()`
+          |_`.cancel_soon()`
+          |_`._cancel_task()`
+
+        '''
         value = self.msgdata.get('canceller')
         if value:
             return tuple(value)
 
+        log.warning(
+            'IPC Context cancelled without a requesting actor?\n'
+            'Maybe the IPC transport ended abruptly?\n\n'
+            f'{self}'
+        )
+
+    # to make `.__repr__()` work uniformly
+    # src_actor_uid = canceller
+
 
 class TransportClosed(trio.ClosedResourceError):
     "Underlying channel transport was closed prior to use"
@@ -95,8 +252,22 @@ class NoRuntime(RuntimeError):
     "The root actor has not been initialized yet"
 
 
-class StreamOverrun(trio.TooSlowError):
+class StreamOverrun(
-    "This stream was overrun by sender"
+    RemoteActorError,
+    trio.TooSlowError,
+):
+    reprol_fields: list[str] = [
+        'sender',
+    ]
+    '''
+    This stream was overrun by sender
+
+    '''
+    @property
+    def sender(self) -> tuple[str, str] | None:
+        value = self.msgdata.get('sender')
+        if value:
+            return tuple(value)
 
 
 class AsyncioCancelled(Exception):
@@ -107,75 +278,115 @@ class AsyncioCancelled(Exception):
 
     '''
 
+class MessagingError(Exception):
+    'Some kind of unexpected SC messaging dialog issue'
+
 
 def pack_error(
     exc: BaseException,
-    tb=None,
+    tb: str|None = None,
+    cid: str|None = None,
 
-) -> dict[str, Any]:
+) -> dict[str, dict]:
-    """Create an "error message" for tranmission over
+    '''
-    a channel (aka the wire).
+    Create an "error message" which boxes a locally caught
-    """
+    exception's meta-data and encodes it for wire transport via an
+    IPC `Channel`; expected to be unpacked (and thus unboxed) on
+    the receiver side using `unpack_error()` below.
+
+    '''
     if tb:
         tb_str = ''.join(traceback.format_tb(tb))
     else:
         tb_str = traceback.format_exc()
 
-    error_msg = {
+    error_msg: dict[
+        str,
+        str | tuple[str, str]
+    ] = {
         'tb_str': tb_str,
         'type_str': type(exc).__name__,
+        'boxed_type': type(exc).__name__,
         'src_actor_uid': current_actor().uid,
     }
 
-    if isinstance(exc, ContextCancelled):
+    # TODO: ?just wholesale proxy `.msgdata: dict`?
+    # XXX WARNING, when i swapped these ctx-semantics
+    # tests started hanging..???!!!???
+    # if msgdata := exc.getattr('msgdata', {}):
+    #     error_msg.update(msgdata)
+    if (
+        isinstance(exc, ContextCancelled)
+        or isinstance(exc, StreamOverrun)
+    ):
         error_msg.update(exc.msgdata)
 
-    return {'error': error_msg}
+    pkt: dict = {'error': error_msg}
+    if cid:
+        pkt['cid'] = cid
+
+    return pkt
 
 
 def unpack_error(
 
     msg: dict[str, Any],
-    chan=None,
-    err_type=RemoteActorError
 
-) -> Exception:
+    chan: Channel|None = None,
+    box_type: RemoteActorError = RemoteActorError,
+
+    hide_tb: bool = True,
+
+) -> None|Exception:
     '''
     Unpack an 'error' message from the wire
-    into a local ``RemoteActorError``.
+    into a local `RemoteActorError` (subtype).
+
+    NOTE: this routine DOES not RAISE the embedded remote error,
+    which is the responsibilitiy of the caller.
 
     '''
-    __tracebackhide__ = True
+    __tracebackhide__: bool = hide_tb
-    error = msg['error']
 
-    tb_str = error.get('tb_str', '')
+    error_dict: dict[str, dict] | None
-    message = f"{chan.uid}\n" + tb_str
+    if (
-    type_name = error['type_str']
+        error_dict := msg.get('error')
+    ) is None:
+        # no error field, nothing to unpack.
+        return None
+
+    # retrieve the remote error's msg encoded details
+    tb_str: str = error_dict.get('tb_str', '')
+    message: str = f'{chan.uid}\n' + tb_str
+    type_name: str = (
+        error_dict.get('type_str')
+        or error_dict['boxed_type']
+    )
     suberror_type: Type[BaseException] = Exception
 
     if type_name == 'ContextCancelled':
-        err_type = ContextCancelled
+        box_type = ContextCancelled
-        suberror_type = RemoteActorError
+        suberror_type = box_type
 
     else:  # try to lookup a suitable local error type
         for ns in [
             builtins,
             _this_mod,
-            eg,
             trio,
         ]:
-            try:
+            if suberror_type := getattr(
-                suberror_type = getattr(ns, type_name)
+                ns,
+                type_name,
+                False,
+            ):
                 break
-            except AttributeError:
-                continue
 
-    exc = err_type(
+    exc = box_type(
         message,
         suberror_type=suberror_type,
 
         # unpack other fields into error type init
-        **msg['error'],
+        **error_dict,
     )
 
     return exc
@@ -183,14 +394,127 @@ def unpack_error(
 
 def is_multi_cancelled(exc: BaseException) -> bool:
     '''
-    Predicate to determine if a possible ``eg.BaseExceptionGroup`` contains
+    Predicate to determine if a possible ``BaseExceptionGroup`` contains
     only ``trio.Cancelled`` sub-exceptions (and is likely the result of
     cancelling a collection of subtasks.
 
     '''
-    if isinstance(exc, eg.BaseExceptionGroup):
+    # if isinstance(exc, eg.BaseExceptionGroup):
+    if isinstance(exc, BaseExceptionGroup):
         return exc.subgroup(
             lambda exc: isinstance(exc, trio.Cancelled)
         ) is not None
 
     return False
+
+
+def _raise_from_no_key_in_msg(
+    ctx: Context,
+    msg: dict,
+    src_err: KeyError,
+    log: StackLevelAdapter,  # caller specific `log` obj
+
+    expect_key: str = 'yield',
+    stream: MsgStream | None = None,
+
+    # allow "deeper" tbs when debugging B^o
+    hide_tb: bool = True,
+
+) -> bool:
+    '''
+    Raise an appopriate local error when a
+    `MsgStream` msg arrives which does not
+    contain the expected (at least under normal
+    operation) `'yield'` field.
+
+    `Context` and any embedded `MsgStream` termination,
+    as well as remote task errors are handled in order
+    of priority as:
+
+    - any 'error' msg is re-boxed and raised locally as
+      -> `RemoteActorError`|`ContextCancelled`
+
+    - a `MsgStream` 'stop' msg is constructed, assigned
+      and raised locally as -> `trio.EndOfChannel`
+
+    - All other mis-keyed msgss (like say a "final result"
+      'return' msg, normally delivered from `Context.result()`)
+      are re-boxed inside a `MessagingError` with an explicit
+      exc content describing the missing IPC-msg-key.
+
+    '''
+    __tracebackhide__: bool = hide_tb
+
+    # an internal error should never get here
+    try:
+        cid: str = msg['cid']
+    except KeyError as src_err:
+        raise MessagingError(
+            f'IPC `Context` rx-ed msg without a ctx-id (cid)!?\n'
+            f'cid: {cid}\n\n'
+
+            f'{pformat(msg)}\n'
+        ) from src_err
+
+    # TODO: test that shows stream raising an expected error!!!
+
+    # raise the error message in a boxed exception type!
+    if msg.get('error'):
+        raise unpack_error(
+            msg,
+            ctx.chan,
+            hide_tb=hide_tb,
+
+        ) from None
+
+    # `MsgStream` termination msg.
+    # TODO: does it make more sense to pack 
+    # the stream._eoc outside this in the calleer always?
+    elif (
+        msg.get('stop')
+        or (
+            stream
+            and stream._eoc
+        )
+    ):
+        log.debug(
+            f'Context[{cid}] stream was stopped by remote side\n'
+            f'cid: {cid}\n'
+        )
+
+        # TODO: if the a local task is already blocking on
+        # a `Context.result()` and thus a `.receive()` on the
+        # rx-chan, we close the chan and set state ensuring that
+        # an eoc is raised!
+
+        # XXX: this causes ``ReceiveChannel.__anext__()`` to
+        # raise a ``StopAsyncIteration`` **and** in our catch
+        # block below it will trigger ``.aclose()``.
+        eoc = trio.EndOfChannel(
+            f'Context stream ended due to msg:\n\n'
+            f'{pformat(msg)}\n'
+        )
+        # XXX: important to set so that a new `.receive()`
+        # call (likely by another task using a broadcast receiver)
+        # doesn't accidentally pull the `return` message
+        # value out of the underlying feed mem chan which is
+        # destined for the `Context.result()` call during ctx-exit!
+        stream._eoc: Exception = eoc
+
+        raise eoc from src_err
+
+    if (
+        stream
+        and stream._closed
+    ):
+        raise trio.ClosedResourceError('This stream was closed')
+
+
+    # always re-raise the source error if no translation error case
+    # is activated above.
+    _type: str = 'Stream' if stream else 'Context'
+    raise MessagingError(
+        f"{_type} was expecting a '{expect_key}' message"
+        " BUT received a non-error msg:\n"
+        f'{pformat(msg)}'
+    ) from src_err

tractor/_ipc.py

@@ -19,34 +19,33 @@ Inter-process comms abstractions
 
 """
 from __future__ import annotations
-import platform
-import struct
-import typing
 from collections.abc import (
     AsyncGenerator,
     AsyncIterator,
 )
+from contextlib import asynccontextmanager as acm
+import platform
+from pprint import pformat
+import struct
+import typing
 from typing import (
     Any,
     runtime_checkable,
-    Optional,
     Protocol,
     Type,
     TypeVar,
 )
 
-from tricycle import BufferedReceiveStream
 import msgspec
+from tricycle import BufferedReceiveStream
 import trio
-from async_generator import asynccontextmanager
 
-from .log import get_logger
+from tractor.log import get_logger
-from ._exceptions import TransportClosed
+from tractor._exceptions import TransportClosed
+
 log = get_logger(__name__)
 
-
 _is_windows = platform.system() == 'Windows'
-log = get_logger(__name__)
 
 
 def get_stream_addrs(stream: trio.SocketStream) -> tuple:
@@ -112,6 +111,13 @@ class MsgpackTCPStream(MsgTransport):
     using the ``msgspec`` codec lib.
 
     '''
+    layer_key: int = 4
+    name_key: str = 'tcp'
+
+    # TODO: better naming for this?
+    # -[ ] check how libp2p does naming for such things?
+    codec_key: str = 'msgpack'
+
     def __init__(
         self,
         stream: trio.SocketStream,
@@ -199,7 +205,17 @@ class MsgpackTCPStream(MsgTransport):
                 else:
                     raise
 
-    async def send(self, msg: Any) -> None:
+    async def send(
+        self,
+        msg: Any,
+
+        # hide_tb: bool = False,
+    ) -> None:
+        '''
+        Send a msgpack coded blob-as-msg over TCP.
+
+        '''
+        # __tracebackhide__: bool = hide_tb
         async with self._send_lock:
 
             bytes_data: bytes = self.encode(msg)
@@ -267,7 +283,7 @@ class Channel:
     def __init__(
 
         self,
-        destaddr: Optional[tuple[str, int]],
+        destaddr: tuple[str, int]|None,
 
         msg_transport_type_key: tuple[str, str] = ('msgpack', 'tcp'),
 
@@ -285,18 +301,29 @@ class Channel:
 
         # Either created in ``.connect()`` or passed in by
         # user in ``.from_stream()``.
-        self._stream: Optional[trio.SocketStream] = None
+        self._stream: trio.SocketStream|None = None
-        self.msgstream: Optional[MsgTransport] = None
+        self._transport: MsgTransport|None = None
 
         # set after handshake - always uid of far end
-        self.uid: Optional[tuple[str, str]] = None
+        self.uid: tuple[str, str]|None = None
 
         self._agen = self._aiter_recv()
-        self._exc: Optional[Exception] = None  # set if far end actor errors
+        self._exc: Exception|None = None  # set if far end actor errors
         self._closed: bool = False
-        # flag set on ``Portal.cancel_actor()`` indicating
+
-        # remote (peer) cancellation of the far end actor runtime.
+        # flag set by ``Portal.cancel_actor()`` indicating remote
-        self._cancel_called: bool = False  # set on ``Portal.cancel_actor()``
+        # (possibly peer) cancellation of the far end actor
+        # runtime.
+        self._cancel_called: bool = False
+
+    @property
+    def msgstream(self) -> MsgTransport:
+        log.info('`Channel.msgstream` is an old name, use `._transport`')
+        return self._transport
+
+    @property
+    def transport(self) -> MsgTransport:
+        return self._transport
 
     @classmethod
     def from_stream(
@@ -307,37 +334,44 @@ class Channel:
     ) -> Channel:
 
         src, dst = get_stream_addrs(stream)
-        chan = Channel(destaddr=dst, **kwargs)
+        chan = Channel(
+            destaddr=dst,
+            **kwargs,
+        )
 
         # set immediately here from provided instance
-        chan._stream = stream
+        chan._stream: trio.SocketStream = stream
         chan.set_msg_transport(stream)
         return chan
 
     def set_msg_transport(
         self,
         stream: trio.SocketStream,
-        type_key: Optional[tuple[str, str]] = None,
+        type_key: tuple[str, str]|None = None,
 
     ) -> MsgTransport:
         type_key = type_key or self._transport_key
-        self.msgstream = get_msg_transport(type_key)(stream)
+        self._transport = get_msg_transport(type_key)(stream)
-        return self.msgstream
+        return self._transport
 
     def __repr__(self) -> str:
-        if self.msgstream:
+        if not self._transport:
-            return repr(
+            return '<Channel with inactive transport?>'
-                self.msgstream.stream.socket._sock).replace(  # type: ignore
+
-                        "socket.socket", "Channel")
+        return repr(
-        return object.__repr__(self)
+            self._transport.stream.socket._sock
+        ).replace(  # type: ignore
+            "socket.socket",
+            "Channel",
+        )
 
     @property
-    def laddr(self) -> Optional[tuple[str, int]]:
+    def laddr(self) -> tuple[str, int]|None:
-        return self.msgstream.laddr if self.msgstream else None
+        return self._transport.laddr if self._transport else None
 
     @property
-    def raddr(self) -> Optional[tuple[str, int]]:
+    def raddr(self) -> tuple[str, int]|None:
-        return self.msgstream.raddr if self.msgstream else None
+        return self._transport.raddr if self._transport else None
 
     async def connect(
         self,
@@ -356,26 +390,42 @@ class Channel:
             *destaddr,
             **kwargs
         )
-        msgstream = self.set_msg_transport(stream)
+        transport = self.set_msg_transport(stream)
 
         log.transport(
-            f'Opened channel[{type(msgstream)}]: {self.laddr} -> {self.raddr}'
+            f'Opened channel[{type(transport)}]: {self.laddr} -> {self.raddr}'
         )
-        return msgstream
+        return transport
 
-    async def send(self, item: Any) -> None:
+    async def send(
+        self,
+        payload: Any,
 
-        log.transport(f"send `{item}`")  # type: ignore
+        # hide_tb: bool = False,
-        assert self.msgstream
 
-        await self.msgstream.send(item)
+    ) -> None:
+        '''
+        Send a coded msg-blob over the transport.
+
+        '''
+        # __tracebackhide__: bool = hide_tb
+        log.transport(
+            '=> send IPC msg:\n\n'
+            f'{pformat(payload)}\n'
+        )  # type: ignore
+        assert self._transport
+
+        await self._transport.send(
+            payload,
+            # hide_tb=hide_tb,
+        )
 
     async def recv(self) -> Any:
-        assert self.msgstream
+        assert self._transport
-        return await self.msgstream.recv()
+        return await self._transport.recv()
 
         # try:
-        #     return await self.msgstream.recv()
+        #     return await self._transport.recv()
         # except trio.BrokenResourceError:
         #     if self._autorecon:
         #         await self._reconnect()
@@ -388,8 +438,8 @@ class Channel:
             f'Closing channel to {self.uid} '
             f'{self.laddr} -> {self.raddr}'
         )
-        assert self.msgstream
+        assert self._transport
-        await self.msgstream.stream.aclose()
+        await self._transport.stream.aclose()
         self._closed = True
 
     async def __aenter__(self):
@@ -440,16 +490,16 @@ class Channel:
         Async iterate items from underlying stream.
 
         '''
-        assert self.msgstream
+        assert self._transport
         while True:
             try:
-                async for item in self.msgstream:
+                async for item in self._transport:
                     yield item
                     # sent = yield item
                     # if sent is not None:
                     #     # optimization, passing None through all the
                     #     # time is pointless
-                    #     await self.msgstream.send(sent)
+                    #     await self._transport.send(sent)
             except trio.BrokenResourceError:
 
                 # if not self._autorecon:
@@ -462,10 +512,10 @@ class Channel:
             #     continue
 
     def connected(self) -> bool:
-        return self.msgstream.connected() if self.msgstream else False
+        return self._transport.connected() if self._transport else False
 
 
-@asynccontextmanager
+@acm
 async def _connect_chan(
     host: str, port: int
 ) -> typing.AsyncGenerator[Channel, None]:

tractor/_portal.py

@@ -15,71 +15,94 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 '''
-Memory boundary "Portals": an API for structured
+Memory "portal" contruct.
-concurrency linked tasks running in disparate memory domains.
+
+"Memory portals" are both an API and set of IPC wrapping primitives
+for managing structured concurrency "cancel-scope linked" tasks
+running in disparate virtual memory domains - at least in different
+OS processes, possibly on different (hardware) hosts.
 
 '''
 from __future__ import annotations
+from contextlib import asynccontextmanager as acm
 import importlib
 import inspect
 from typing import (
-    Any, Optional,
+    Any,
-    Callable, AsyncGenerator,
+    Callable,
-    Type,
+    AsyncGenerator,
+    # Type,
 )
 from functools import partial
 from dataclasses import dataclass
-from pprint import pformat
 import warnings
 
 import trio
-from async_generator import asynccontextmanager
 
 from .trionics import maybe_open_nursery
-from ._state import current_actor
+from ._state import (
+    current_actor,
+)
 from ._ipc import Channel
 from .log import get_logger
 from .msg import NamespacePath
 from ._exceptions import (
     unpack_error,
     NoResult,
-    ContextCancelled,
 )
-from ._context import Context
+from ._context import (
-from ._streaming import MsgStream
+    Context,
+    open_context_from_portal,
+)
+from ._streaming import (
+    MsgStream,
+)
 
 
 log = get_logger(__name__)
 
 
+# TODO: rename to `unwrap_result()` and use
+# `._raise_from_no_key_in_msg()` (after tweak to
+# accept a `chan: Channel` arg) in key block!
 def _unwrap_msg(
     msg: dict[str, Any],
-    channel: Channel
+    channel: Channel,
+
+    hide_tb: bool = True,
 
 ) -> Any:
-    __tracebackhide__ = True
+    '''
+    Unwrap a final result from a `{return: <Any>}` IPC msg.
+
+    '''
+    __tracebackhide__: bool = hide_tb
+
     try:
         return msg['return']
-    except KeyError:
+    except KeyError as ke:
+
         # internal error should never get here
-        assert msg.get('cid'), "Received internal error at portal?"
+        assert msg.get('cid'), (
-        raise unpack_error(msg, channel) from None
+            "Received internal error at portal?"
+        )
 
-
+        raise unpack_error(
-class MessagingError(Exception):
+            msg,
-    'Some kind of unexpected SC messaging dialog issue'
+            channel
+        ) from ke
 
 
 class Portal:
     '''
-    A 'portal' to a(n) (remote) ``Actor``.
+    A 'portal' to a memory-domain-separated `Actor`.
 
     A portal is "opened" (and eventually closed) by one side of an
     inter-actor communication context. The side which opens the portal
     is equivalent to a "caller" in function parlance and usually is
     either the called actor's parent (in process tree hierarchy terms)
     or a client interested in scheduling work to be done remotely in a
-    far process.
+    process which has a separate (virtual) memory domain.
 
     The portal api allows the "caller" actor to invoke remote routines
     and receive results through an underlying ``tractor.Channel`` as
@@ -89,14 +112,14 @@ class Portal:
     like having a "portal" between the seperate actor memory spaces.
 
     '''
-    # the timeout for a remote cancel request sent to
+    # global timeout for remote cancel requests sent to
-    # a(n) (peer) actor.
+    # connected (peer) actors.
-    cancel_timeout = 0.5
+    cancel_timeout: float = 0.5
 
     def __init__(self, channel: Channel) -> None:
-        self.channel = channel
+        self.chan = channel
         # during the portal's lifetime
-        self._result_msg: Optional[dict] = None
+        self._result_msg: dict|None = None
 
         # When set to a ``Context`` (when _submit_for_result is called)
         # it is expected that ``result()`` will be awaited at some
@@ -105,6 +128,18 @@ class Portal:
         self._streams: set[MsgStream] = set()
         self.actor = current_actor()
 
+    @property
+    def channel(self) -> Channel:
+        '''
+        Proxy to legacy attr name..
+
+        Consider the shorter `Portal.chan` instead of `.channel` ;)
+        '''
+        log.debug(
+            'Consider the shorter `Portal.chan` instead of `.channel` ;)'
+        )
+        return self.chan
+
     async def _submit_for_result(
         self,
         ns: str,
@@ -112,14 +147,14 @@ class Portal:
         **kwargs
     ) -> None:
 
-        assert self._expect_result is None, \
+        assert self._expect_result is None, (
-                "A pending main result has already been submitted"
+            "A pending main result has already been submitted"
+        )
 
         self._expect_result = await self.actor.start_remote_task(
             self.channel,
-            ns,
+            nsf=NamespacePath(f'{ns}:{func}'),
-            func,
+            kwargs=kwargs
-            kwargs
         )
 
     async def _return_once(
@@ -129,7 +164,7 @@ class Portal:
     ) -> dict[str, Any]:
 
         assert ctx._remote_func_type == 'asyncfunc'  # single response
-        msg = await ctx._recv_chan.receive()
+        msg: dict = await ctx._recv_chan.receive()
         return msg
 
     async def result(self) -> Any:
@@ -160,7 +195,10 @@ class Portal:
                 self._expect_result
             )
 
-        return _unwrap_msg(self._result_msg, self.channel)
+        return _unwrap_msg(
+            self._result_msg,
+            self.channel,
+        )
 
     async def _cancel_streams(self):
         # terminate all locally running async generator
@@ -191,33 +229,57 @@ class Portal:
 
     ) -> bool:
         '''
-        Cancel the actor on the other end of this portal.
+        Cancel the actor runtime (and thus process) on the far
+        end of this portal.
+
+        **NOTE** THIS CANCELS THE ENTIRE RUNTIME AND THE
+        SUBPROCESS, it DOES NOT just cancel the remote task. If you
+        want to have a handle to cancel a remote ``tri.Task`` look
+        at `.open_context()` and the definition of
+        `._context.Context.cancel()` which CAN be used for this
+        purpose.
 
         '''
-        if not self.channel.connected():
+        chan: Channel = self.channel
-            log.cancel("This channel is already closed can't cancel")
+        if not chan.connected():
+            log.runtime(
+                'This channel is already closed, skipping cancel request..'
+            )
             return False
 
+        reminfo: str = (
+            f'`Portal.cancel_actor()` => {self.channel.uid}\n'
+            f' |_{chan}\n'
+        )
         log.cancel(
-            f"Sending actor cancel request to {self.channel.uid} on "
+            f'Sending runtime `.cancel()` request to peer\n\n'
-            f"{self.channel}")
+            f'{reminfo}'
-
+        )
-        self.channel._cancel_called = True
 
+        self.channel._cancel_called: bool = True
         try:
             # send cancel cmd - might not get response
-            # XXX: sure would be nice to make this work with a proper shield
+            # XXX: sure would be nice to make this work with
+            # a proper shield
             with trio.move_on_after(
                 timeout
-                or self.cancel_timeout
+                or
+                self.cancel_timeout
             ) as cs:
-                cs.shield = True
+                cs.shield: bool = True
-
+                await self.run_from_ns(
-                await self.run_from_ns('self', 'cancel')
+                    'self',
+                    'cancel',
+                )
                 return True
 
             if cs.cancelled_caught:
-                log.cancel(f"May have failed to cancel {self.channel.uid}")
+                # may timeout and we never get an ack (obvi racy)
+                # but that doesn't mean it wasn't cancelled.
+                log.debug(
+                    'May have failed to cancel peer?\n'
+                    f'{reminfo}'
+                )
 
             # if we get here some weird cancellation case happened
             return False
@@ -226,9 +288,11 @@ class Portal:
             trio.ClosedResourceError,
             trio.BrokenResourceError,
         ):
-            log.cancel(
+            log.debug(
-                f"{self.channel} for {self.channel.uid} was already "
+                'IPC chan for actor already closed or broken?\n\n'
-                "closed or broken?")
+                f'{self.channel.uid}\n'
+                f' |_{self.channel}\n'
+            )
             return False
 
     async def run_from_ns(
@@ -247,27 +311,33 @@ class Portal:
 
         Note::
 
-            A special namespace `self` can be used to invoke `Actor`
+          A special namespace `self` can be used to invoke `Actor`
-            instance methods in the remote runtime. Currently this
+          instance methods in the remote runtime. Currently this
-            should only be used solely for ``tractor`` runtime
+          should only ever be used for `Actor` (method) runtime
-            internals.
+          internals!
 
         '''
+        nsf = NamespacePath(
+            f'{namespace_path}:{function_name}'
+        )
         ctx = await self.actor.start_remote_task(
-            self.channel,
+            chan=self.channel,
-            namespace_path,
+            nsf=nsf,
-            function_name,
+            kwargs=kwargs,
-            kwargs,
         )
         ctx._portal = self
         msg = await self._return_once(ctx)
-        return _unwrap_msg(msg, self.channel)
+        return _unwrap_msg(
+            msg,
+            self.channel,
+        )
 
     async def run(
         self,
         func: str,
-        fn_name: Optional[str] = None,
+        fn_name: str|None = None,
         **kwargs
+
     ) -> Any:
         '''
         Submit a remote function to be scheduled and run by actor, in
@@ -286,8 +356,9 @@ class Portal:
                 DeprecationWarning,
                 stacklevel=2,
             )
-            fn_mod_path = func
+            fn_mod_path: str = func
             assert isinstance(fn_name, str)
+            nsf = NamespacePath(f'{fn_mod_path}:{fn_name}')
 
         else:  # function reference was passed directly
             if (
@@ -300,13 +371,12 @@ class Portal:
                 raise TypeError(
                     f'{func} must be a non-streaming async function!')
 
-            fn_mod_path, fn_name = NamespacePath.from_ref(func).to_tuple()
+            nsf = NamespacePath.from_ref(func)
 
         ctx = await self.actor.start_remote_task(
             self.channel,
-            fn_mod_path,
+            nsf=nsf,
-            fn_name,
+            kwargs=kwargs,
-            kwargs,
         )
         ctx._portal = self
         return _unwrap_msg(
@@ -314,7 +384,7 @@ class Portal:
             self.channel,
         )
 
-    @asynccontextmanager
+    @acm
     async def open_stream_from(
         self,
         async_gen_func: Callable,  # typing: ignore
@@ -330,15 +400,10 @@ class Portal:
                 raise TypeError(
                     f'{async_gen_func} must be an async generator function!')
 
-        fn_mod_path, fn_name = NamespacePath.from_ref(
+        ctx: Context = await self.actor.start_remote_task(
-            async_gen_func
-        ).to_tuple()
-
-        ctx = await self.actor.start_remote_task(
             self.channel,
-            fn_mod_path,
+            nsf=NamespacePath.from_ref(async_gen_func),
-            fn_name,
+            kwargs=kwargs,
-            kwargs
         )
         ctx._portal = self
 
@@ -348,7 +413,8 @@ class Portal:
         try:
             # deliver receive only stream
             async with MsgStream(
-                ctx, ctx._recv_chan,
+                ctx=ctx,
+                rx_chan=ctx._recv_chan,
             ) as rchan:
                 self._streams.add(rchan)
                 yield rchan
@@ -375,203 +441,12 @@ class Portal:
             # await recv_chan.aclose()
             self._streams.remove(rchan)
 
-    @asynccontextmanager
+    # NOTE: impl is found in `._context`` mod to make
-    async def open_context(
+    # reading/groking the details simpler code-org-wise. This
-
+    # method does not have to be used over that `@acm` module func
-        self,
+    # directly, it is for conventience and from the original API
-        func: Callable,
+    # design.
-        allow_overruns: bool = False,
+    open_context = open_context_from_portal
-        **kwargs,
-
-    ) -> AsyncGenerator[tuple[Context, Any], None]:
-        '''
-        Open an inter-actor task context.
-
-        This is a synchronous API which allows for deterministic
-        setup/teardown of a remote task. The yielded ``Context`` further
-        allows for opening bidirectional streams, explicit cancellation
-        and synchronized final result collection. See ``tractor.Context``.
-
-        '''
-        # conduct target func method structural checks
-        if not inspect.iscoroutinefunction(func) and (
-            getattr(func, '_tractor_contex_function', False)
-        ):
-            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,
-
-            # 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'
-        msg = await ctx._recv_chan.receive()
-
-        try:
-            # the "first" value here is delivered by the callee's
-            # ``Context.started()`` call.
-            first = msg['started']
-            ctx._started_called = True
-
-        except KeyError:
-            assert msg.get('cid'), ("Received internal error at context?")
-
-            if msg.get('error'):
-                # raise kerr from unpack_error(msg, self.channel)
-                raise unpack_error(msg, self.channel) from None
-            else:
-                raise MessagingError(
-                    f'Context for {ctx.cid} was expecting a `started` message'
-                    f' but received a non-error msg:\n{pformat(msg)}'
-                )
-
-        _err: BaseException | None = None
-        ctx._portal: Portal = self
-
-        uid: tuple = self.channel.uid
-        cid: str = ctx.cid
-        etype: Type[BaseException] | None = None
-
-        # deliver context instance and .started() msg value in enter
-        # tuple.
-        try:
-            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:
-                # XXX: this should NEVER happen!
-                # from ._debug import breakpoint
-                # await breakpoint()
-                raise
-
-            # if the context was cancelled by client code
-            # then we don't need to raise since user code
-            # is expecting this and the block should exit.
-            else:
-                log.debug(f'Context {ctx} cancelled gracefully')
-
-        except (
-            BaseException,
-
-            # more specifically, we need to handle these but not
-            # sure it's worth being pedantic:
-            # Exception,
-            # trio.Cancelled,
-            # KeyboardInterrupt,
-
-        ) as err:
-            etype = type(err)
-
-            # 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()
-            except trio.BrokenResourceError:
-                log.warning(
-                    'IPC connection for context is broken?\n'
-                    f'task:{cid}\n'
-                    f'actor:{uid}'
-                )
-
-            raise
-
-        else:
-            if ctx.chan.connected():
-                log.info(
-                    'Waiting on final context-task result for\n'
-                    f'task: {cid}\n'
-                    f'actor: {uid}'
-                )
-                result = await ctx.result()
-                log.runtime(
-                    f'Context {fn_name} returned '
-                    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
-            # to avoid premature stream clobbers.
-            if ctx._recv_chan is not None:
-                # should we encapsulate this in the context api?
-                await ctx._recv_chan.aclose()
-
-            if etype:
-                if ctx._cancel_called:
-                    log.cancel(
-                        f'Context {fn_name} cancelled by caller with\n{etype}'
-                    )
-                elif _err is not None:
-                    log.cancel(
-                        f'Context for task cancelled by callee with {etype}\n'
-                        f'target: `{fn_name}`\n'
-                        f'task:{cid}\n'
-                        f'actor:{uid}'
-                    )
-            # XXX: (MEGA IMPORTANT) if this is a root opened process we
-            # wait for any immediate child in debug before popping the
-            # context from the runtime msg loop otherwise inside
-            # ``Actor._push_result()`` the msg will be discarded and in
-            # the case where that msg is global debugger unlock (via
-            # a "stop" msg for a stream), this can result in a deadlock
-            # where the root is waiting on the lock to clear but the
-            # child has already cleared it and clobbered IPC.
-            from ._debug import maybe_wait_for_debugger
-            await maybe_wait_for_debugger()
-
-            # remove the context from runtime tracking
-            self.actor._contexts.pop(
-                (self.channel.uid, ctx.cid),
-                None,
-            )
 
 
 @dataclass
@@ -597,11 +472,11 @@ class LocalPortal:
         return await func(**kwargs)
 
 
-@asynccontextmanager
+@acm
 async def open_portal(
 
     channel: Channel,
-    nursery: Optional[trio.Nursery] = None,
+    nursery: trio.Nursery|None = None,
     start_msg_loop: bool = True,
     shield: bool = False,
 
@@ -626,7 +501,7 @@ async def open_portal(
         if channel.uid is None:
             await actor._do_handshake(channel)
 
-        msg_loop_cs: Optional[trio.CancelScope] = None
+        msg_loop_cs: trio.CancelScope|None = None
         if start_msg_loop:
             from ._runtime import process_messages
             msg_loop_cs = await nursery.start(

tractor/_root.py

@@ -29,12 +29,13 @@ import typing
 import warnings
 
 
-from exceptiongroup import BaseExceptionGroup
 import trio
 
 from ._runtime import (
     Actor,
     Arbiter,
+    # TODO: rename and make a non-actor subtype?
+    # Arbiter as Registry,
     async_main,
 )
 from . import _debug
@@ -237,8 +238,11 @@ async def open_root_actor(
 
                 entered = await _debug._maybe_enter_pm(err)
 
-                if not entered and not is_multi_cancelled(err):
+                if (
-                    logger.exception("Root actor crashed:")
+                    not entered
+                    and not is_multi_cancelled(err)
+                ):
+                    logger.exception('Root actor crashed:\n')
 
                 # always re-raise
                 raise
@@ -253,12 +257,13 @@ async def open_root_actor(
                 #     for an in nurseries:
                 #         tempn.start_soon(an.exited.wait)
 
-                logger.cancel("Shutting down root actor")
+                logger.info(
-                await actor.cancel(
+                    'Closing down root actor'
-                    requesting_uid=actor.uid,
                 )
+                await actor.cancel(None)  # self cancel
     finally:
         _state._current_actor = None
+        _state._last_actor_terminated = actor
 
         # restore breakpoint hook state
         sys.breakpointhook = builtin_bp_handler

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

@@ -31,25 +31,24 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from exceptiongroup import BaseExceptionGroup
 import trio
-from trio_typing import TaskStatus
+from trio import TaskStatus
 
 from ._debug import (
     maybe_wait_for_debugger,
     acquire_debug_lock,
 )
-from ._state import (
+from tractor._state import (
     current_actor,
     is_main_process,
     is_root_process,
     debug_mode,
 )
-from .log import get_logger
+from tractor.log import get_logger
-from ._portal import Portal
+from tractor._portal import Portal
-from ._runtime import Actor
+from tractor._runtime import Actor
-from ._entry import _mp_main
+from tractor._entry import _mp_main
-from ._exceptions import ActorFailure
+from tractor._exceptions import ActorFailure
 
 
 if TYPE_CHECKING:
@@ -144,7 +143,7 @@ async def exhaust_portal(
 
         # XXX: streams should never be reaped here since they should
         # always be established and shutdown using a context manager api
-        final = await portal.result()
+        final: Any = await portal.result()
 
     except (
         Exception,
@@ -152,13 +151,23 @@ async def exhaust_portal(
     ) as err:
         # we reraise in the parent task via a ``BaseExceptionGroup``
         return err
+
     except trio.Cancelled as err:
         # lol, of course we need this too ;P
         # TODO: merge with above?
-        log.warning(f"Cancelled result waiter for {portal.actor.uid}")
+        log.warning(
+            'Cancelled portal result waiter task:\n'
+            f'uid: {portal.channel.uid}\n'
+            f'error: {err}\n'
+        )
         return err
+
     else:
-        log.debug(f"Returning final result: {final}")
+        log.debug(
+            f'Returning final result from portal:\n'
+            f'uid: {portal.channel.uid}\n'
+            f'result: {final}\n'
+        )
         return final
 
 
@@ -170,41 +179,71 @@ async def cancel_on_completion(
 
 ) -> None:
     '''
-    Cancel actor gracefully once it's "main" portal's
+    Cancel actor gracefully once its "main" portal's
     result arrives.
 
-    Should only be called for actors spawned with `run_in_actor()`.
+    Should only be called for actors spawned via the
+    `Portal.run_in_actor()` API.
+
+    => and really this API will be deprecated and should be
+    re-implemented as a `.hilevel.one_shot_task_nursery()`..)
 
     '''
     # if this call errors we store the exception for later
     # in ``errors`` which will be reraised inside
     # an exception group and we still send out a cancel request
-    result = await exhaust_portal(portal, actor)
+    result: Any|Exception = await exhaust_portal(portal, actor)
     if isinstance(result, Exception):
-        errors[actor.uid] = result
+        errors[actor.uid]: Exception = result
-        log.warning(
+        log.cancel(
-            f"Cancelling {portal.channel.uid} after error {result}"
+            'Cancelling subactor runtime due to error:\n\n'
+            f'Portal.cancel_actor() => {portal.channel.uid}\n\n'
+            f'error: {result}\n'
         )
 
     else:
         log.runtime(
-            f"Cancelling {portal.channel.uid} gracefully "
+            'Cancelling subactor gracefully:\n\n'
-            f"after result {result}")
+            f'Portal.cancel_actor() => {portal.channel.uid}\n\n'
+            f'result: {result}\n'
+        )
 
     # cancel the process now that we have a final result
     await portal.cancel_actor()
 
 
-async def do_hard_kill(
+async def hard_kill(
     proc: trio.Process,
-    terminate_after: int = 3,
+    terminate_after: int = 1.6,
+
+    # NOTE: for mucking with `.pause()`-ing inside the runtime
+    # whilst also hacking on it XD
+    # terminate_after: int = 99999,
 
 ) -> None:
+    '''
+    Un-gracefully terminate an OS level `trio.Process` after timeout.
+
+    Used in 2 main cases:
+
+    - "unknown remote runtime state": a hanging/stalled actor that
+      isn't responding after sending a (graceful) runtime cancel
+      request via an IPC msg.
+    - "cancelled during spawn": a process who's actor runtime was
+      cancelled before full startup completed (such that
+      cancel-request-handling machinery was never fully
+      initialized) and thus a "cancel request msg" is never going
+      to be handled.
+
+    '''
+    log.cancel(
+        'Terminating sub-proc:\n'
+        f'|_{proc}\n'
+    )
     # NOTE: this timeout used to do nothing since we were shielding
     # the ``.wait()`` inside ``new_proc()`` which will pretty much
     # never release until the process exits, now it acts as
     # a hard-kill time ultimatum.
-    log.debug(f"Terminating {proc}")
     with trio.move_on_after(terminate_after) as cs:
 
         # NOTE: code below was copied verbatim from the now deprecated
@@ -215,6 +254,9 @@ async def do_hard_kill(
         # and wait for it to exit. If cancelled, kills the process and
         # waits for it to finish exiting before propagating the
         # cancellation.
+        #
+        # This code was originally triggred by ``proc.__aexit__()``
+        # but now must be called manually.
         with trio.CancelScope(shield=True):
             if proc.stdin is not None:
                 await proc.stdin.aclose()
@@ -230,15 +272,25 @@ async def do_hard_kill(
                 with trio.CancelScope(shield=True):
                     await proc.wait()
 
+    # XXX NOTE XXX: zombie squad dispatch:
+    # (should ideally never, but) If we do get here it means
+    # graceful termination of a process failed and we need to
+    # resort to OS level signalling to interrupt and cancel the
+    # (presumably stalled or hung) actor. Since we never allow
+    # zombies (as a feature) we ask the OS to do send in the
+    # removal swad as the last resort.
     if cs.cancelled_caught:
-        # XXX: should pretty much never get here unless we have
+        # TODO: toss in the skynet-logo face as ascii art?
-        # to move the bits from ``proc.__aexit__()`` out and
+        log.critical(
-        # into here.
+            # 'Well, the #ZOMBIE_LORD_IS_HERE# to collect\n'
-        log.critical(f"#ZOMBIE_LORD_IS_HERE: {proc}")
+            '#T-800 deployed to collect zombie B0\n'
+            f'|\n'
+            f'|_{proc}\n'
+        )
         proc.kill()
 
 
-async def soft_wait(
+async def soft_kill(
 
     proc: ProcessType,
     wait_func: Callable[
@@ -248,14 +300,26 @@ async def soft_wait(
     portal: Portal,
 
 ) -> None:
-    # Wait for proc termination but **dont' yet** call
+    '''
-    # ``trio.Process.__aexit__()`` (it tears down stdio
+    Wait for proc termination but **don't yet** teardown
-    # which will kill any waiting remote pdb trace).
+    std-streams since it will clobber any ongoing pdb REPL
-    # This is a "soft" (cancellable) join/reap.
+    session.
-    uid = portal.channel.uid
+
+    This is our "soft"/graceful, and thus itself also cancellable,
+    join/reap on an actor-runtime-in-process shutdown; it is
+    **not** the same as a "hard kill" via an OS signal (for that
+    see `.hard_kill()`).
+
+    '''
+    uid: tuple[str, str] = portal.channel.uid
     try:
-        log.cancel(f'Soft waiting on actor:\n{uid}')
+        log.cancel(
+            'Soft killing sub-actor via `Portal.cancel_actor()`\n'
+            f'|_{proc}\n'
+        )
+        # wait on sub-proc to signal termination
         await wait_func(proc)
+
     except trio.Cancelled:
         # if cancelled during a soft wait, cancel the child
         # actor before entering the hard reap sequence
@@ -267,22 +331,29 @@ async def soft_wait(
 
             async def cancel_on_proc_deth():
                 '''
-                Cancel the actor cancel request if we detect that
+                "Cancel-the-cancel" request: if we detect that the
-                that the process terminated.
+                underlying sub-process exited prior to
+                a `Portal.cancel_actor()` call completing .
 
                 '''
                 await wait_func(proc)
                 n.cancel_scope.cancel()
 
+            # start a task to wait on the termination of the
+            # process by itself waiting on a (caller provided) wait
+            # function which should unblock when the target process
+            # has terminated.
             n.start_soon(cancel_on_proc_deth)
+
+            # send the actor-runtime a cancel request.
             await portal.cancel_actor()
 
             if proc.poll() is None:  # type: ignore
                 log.warning(
-                    'Actor still alive after cancel request:\n'
+                    'Subactor still alive after cancel request?\n\n'
-                    f'{uid}'
+                    f'uid: {uid}\n'
+                    f'|_{proc}\n'
                 )
-
                 n.cancel_scope.cancel()
         raise
 
@@ -306,7 +377,7 @@ async def new_proc(
 ) -> None:
 
     # lookup backend spawning target
-    target = _methods[_spawn_method]
+    target: Callable = _methods[_spawn_method]
 
     # mark the new actor with the global spawn method
     subactor._spawn_method = _spawn_method
@@ -374,19 +445,22 @@ async def trio_proc(
         spawn_cmd.append("--asyncio")
 
     cancelled_during_spawn: bool = False
-    proc: trio.Process | None = None
+    proc: trio.Process|None = None
     try:
         try:
             # TODO: needs ``trio_typing`` patch?
             proc = await trio.lowlevel.open_process(spawn_cmd)
-
+            log.runtime(
-            log.runtime(f"Started {proc}")
+                'Started new sub-proc\n'
+                f'|_{proc}\n'
+            )
 
             # wait for actor to spawn and connect back to us
             # channel should have handshake completed by the
             # local actor by the time we get a ref to it
             event, chan = await actor_nursery._actor.wait_for_peer(
-                subactor.uid)
+                subactor.uid
+            )
 
         except trio.Cancelled:
             cancelled_during_spawn = True
@@ -448,7 +522,7 @@ async def trio_proc(
             # This is a "soft" (cancellable) join/reap which
             # will remote cancel the actor on a ``trio.Cancelled``
             # condition.
-            await soft_wait(
+            await soft_kill(
                 proc,
                 trio.Process.wait,
                 portal
@@ -457,8 +531,9 @@ async def trio_proc(
             # cancel result waiter that may have been spawned in
             # tandem if not done already
             log.cancel(
-                "Cancelling existing result waiter task for "
+                'Cancelling existing result waiter task for '
-                f"{subactor.uid}")
+                f'{subactor.uid}'
+            )
             nursery.cancel_scope.cancel()
 
     finally:
@@ -476,22 +551,39 @@ async def trio_proc(
                         with trio.move_on_after(0.5):
                             await proc.wait()
 
-                if is_root_process():
+                log.pdb(
-                    # TODO: solve the following issue where we need
+                    'Delaying subproc reaper while debugger locked..'
-                    # to do a similar wait like this but in an
+                )
-                    # "intermediary" parent actor that itself isn't
+                await maybe_wait_for_debugger(
-                    # in debug but has a child that is, and we need
+                    child_in_debug=_runtime_vars.get(
-                    # to hold off on relaying SIGINT until that child
+                        '_debug_mode', False
-                    # is complete.
+                    ),
-                    # https://github.com/goodboy/tractor/issues/320
+                    # TODO: need a diff value then default?
-                    await maybe_wait_for_debugger(
+                    # poll_steps=9999999,
-                        child_in_debug=_runtime_vars.get(
+                )
-                            '_debug_mode', False),
+                # TODO: solve the following issue where we need
-                    )
+                # to do a similar wait like this but in an
+                # "intermediary" parent actor that itself isn't
+                # in debug but has a child that is, and we need
+                # to hold off on relaying SIGINT until that child
+                # is complete.
+                # https://github.com/goodboy/tractor/issues/320
+                # -[ ] we need to handle non-root parent-actors specially
+                # by somehow determining if a child is in debug and then
+                # avoiding cancel/kill of said child by this
+                # (intermediary) parent until such a time as the root says
+                # the pdb lock is released and we are good to tear down
+                # (our children)..
+                #
+                # -[ ] so maybe something like this where we try to
+                #     acquire the lock and get notified of who has it,
+                #     check that uid against our known children?
+                # this_uid: tuple[str, str] = current_actor().uid
+                # await acquire_debug_lock(this_uid)
 
                 if proc.poll() is None:
                     log.cancel(f"Attempting to hard kill {proc}")
-                    await do_hard_kill(proc)
+                    await hard_kill(proc)
 
                 log.debug(f"Joined {proc}")
         else:
@@ -635,7 +727,7 @@ async def mp_proc(
             # This is a "soft" (cancellable) join/reap which
             # will remote cancel the actor on a ``trio.Cancelled``
             # condition.
-            await soft_wait(
+            await soft_kill(
                 proc,
                 proc_waiter,
                 portal

tractor/_state.py

@@ -18,12 +18,18 @@
 Per process state
 
 """
+from __future__ import annotations
 from typing import (
-    Optional,
     Any,
+    TYPE_CHECKING,
 )
 
-_current_actor: Optional['Actor'] = None  # type: ignore # noqa
+if TYPE_CHECKING:
+    from ._runtime import Actor
+
+
+_current_actor: Actor|None = None  # type: ignore # noqa
+_last_actor_terminated: Actor|None = None
 _runtime_vars: dict[str, Any] = {
     '_debug_mode': False,
     '_is_root': False,
@@ -31,14 +37,49 @@ _runtime_vars: dict[str, Any] = {
 }
 
 
-def current_actor(err_on_no_runtime: bool = True) -> 'Actor':  # type: ignore # noqa
+def last_actor() -> Actor|None:
+    '''
+    Try to return last active `Actor` singleton
+    for this process.
+
+    For case where runtime already exited but someone is asking
+    about the "last" actor probably to get its `.uid: tuple`.
+
+    '''
+    return _last_actor_terminated
+
+
+def current_actor(
+    err_on_no_runtime: bool = True,
+) -> Actor:
     '''
     Get the process-local actor instance.
 
     '''
-    from ._exceptions import NoRuntime
+    if (
-    if _current_actor is None and err_on_no_runtime:
+        err_on_no_runtime
-        raise NoRuntime("No local actor has been initialized yet")
+        and _current_actor is None
+    ):
+        msg: str = 'No local actor has been initialized yet'
+        from ._exceptions import NoRuntime
+
+        if last := last_actor():
+            msg += (
+                f'Apparently the lact active actor was\n'
+                f'|_{last}\n'
+                f'|_{last.uid}\n'
+            )
+        # no actor runtime has (as of yet) ever been started for
+        # this process.
+        else:
+            msg += (
+                'No last actor found?\n'
+                'Did you forget to open one of:\n\n'
+                '- `tractor.open_root_actor()`\n'
+                '- `tractor.open_nursery()`\n'
+            )
+
+        raise NoRuntime(msg)
 
     return _current_actor
 

tractor/_streaming.py

@@ -21,8 +21,9 @@ The machinery and types behind ``Context.open_stream()``
 
 '''
 from __future__ import annotations
-import inspect
 from contextlib import asynccontextmanager as acm
+import inspect
+from pprint import pformat
 from typing import (
     Any,
     Callable,
@@ -34,7 +35,8 @@ import warnings
 import trio
 
 from ._exceptions import (
-    unpack_error,
+    _raise_from_no_key_in_msg,
+    ContextCancelled,
 )
 from .log import get_logger
 from .trionics import (
@@ -54,7 +56,6 @@ log = get_logger(__name__)
 #   messages? class ReceiveChannel(AsyncResource, Generic[ReceiveType]):
 # - use __slots__ on ``Context``?
 
-
 class MsgStream(trio.abc.Channel):
     '''
     A bidirectional message stream for receiving logically sequenced
@@ -85,122 +86,248 @@ class MsgStream(trio.abc.Channel):
         self._broadcaster = _broadcaster
 
         # flag to denote end of stream
-        self._eoc: bool = False
+        self._eoc: bool|trio.EndOfChannel = False
-        self._closed: bool = False
+        self._closed: bool|trio.ClosedResourceError = False
 
     # delegate directly to underlying mem channel
-    def receive_nowait(self):
+    def receive_nowait(
-        msg = self._rx_chan.receive_nowait()
+        self,
-        return msg['yield']
+        allow_msg_keys: list[str] = ['yield'],
+    ):
+        msg: dict = self._rx_chan.receive_nowait()
+        for (
+            i,
+            key,
+        ) in enumerate(allow_msg_keys):
+            try:
+                return msg[key]
+            except KeyError as kerr:
+                if i < (len(allow_msg_keys) - 1):
+                    continue
 
-    async def receive(self):
+                _raise_from_no_key_in_msg(
-        '''Async receive a single msg from the IPC transport, the next
+                    ctx=self._ctx,
-        in sequence for this stream.
+                    msg=msg,
+                    src_err=kerr,
+                    log=log,
+                    expect_key=key,
+                    stream=self,
+                )
+
+    async def receive(
+        self,
+
+        hide_tb: bool = True,
+    ):
+        '''
+        Receive a single msg from the IPC transport, the next in
+        sequence sent by the far end task (possibly in order as
+        determined by the underlying protocol).
 
         '''
+        __tracebackhide__: bool = hide_tb
+
+        # NOTE: `trio.ReceiveChannel` implements
+        # EOC handling as follows (aka uses it
+        # to gracefully exit async for loops):
+        #
+        # async def __anext__(self) -> ReceiveType:
+        #     try:
+        #         return await self.receive()
+        #     except trio.EndOfChannel:
+        #         raise StopAsyncIteration
+        #
         # see ``.aclose()`` for notes on the old behaviour prior to
         # introducing this
         if self._eoc:
-            raise trio.EndOfChannel
+            raise self._eoc
 
         if self._closed:
-            raise trio.ClosedResourceError('This stream was closed')
+            raise self._closed
 
+        src_err: Exception|None = None  # orig tb
         try:
-            msg = await self._rx_chan.receive()
+            try:
-            return msg['yield']
+                msg = await self._rx_chan.receive()
+                return msg['yield']
 
-        except KeyError as err:
+            except KeyError as kerr:
-            # internal error should never get here
+                src_err = kerr
-            assert msg.get('cid'), ("Received internal error at portal?")
 
-            # TODO: handle 2 cases with 3.10 match syntax
+                # NOTE: may raise any of the below error types
-            # - 'stop'
+                # includg EoC when a 'stop' msg is found.
-            # - 'error'
+                _raise_from_no_key_in_msg(
-            # possibly just handle msg['stop'] here!
+                    ctx=self._ctx,
-
+                    msg=msg,
-            if self._closed:
+                    src_err=kerr,
-                raise trio.ClosedResourceError('This stream was closed')
+                    log=log,
-
+                    expect_key='yield',
-            if msg.get('stop') or self._eoc:
+                    stream=self,
-                log.debug(f"{self} was stopped at remote end")
+                )
-
-                # XXX: important to set so that a new ``.receive()``
-                # call (likely by another task using a broadcast receiver)
-                # doesn't accidentally pull the ``return`` message
-                # value out of the underlying feed mem chan!
-                self._eoc = True
-
-                # # when the send is closed we assume the stream has
-                # # terminated and signal this local iterator to stop
-                # await self.aclose()
-
-                # XXX: this causes ``ReceiveChannel.__anext__()`` to
-                # raise a ``StopAsyncIteration`` **and** in our catch
-                # block below it will trigger ``.aclose()``.
-                raise trio.EndOfChannel from err
-
-            # TODO: test that shows stream raising an expected error!!!
-            elif msg.get('error'):
-                # raise the error message
-                raise unpack_error(msg, self._ctx.chan)
-
-            else:
-                raise
 
+        # XXX: the stream terminates on either of:
+        # - via `self._rx_chan.receive()` raising  after manual closure
+        #   by the rpc-runtime OR,
+        # - via a received `{'stop': ...}` msg from remote side.
+        #   |_ NOTE: previously this was triggered by calling
+        #   ``._rx_chan.aclose()`` on the send side of the channel inside
+        #   `Actor._push_result()`, but now the 'stop' message handling
+        #   has been put just above inside `_raise_from_no_key_in_msg()`.
         except (
-            trio.ClosedResourceError,  # by self._rx_chan
+            trio.EndOfChannel,
-            trio.EndOfChannel,  # by self._rx_chan or `stop` msg from far end
+        ) as eoc:
-        ):
+            src_err = eoc
-            # XXX: we close the stream on any of these error conditions:
+            self._eoc = eoc
-
-            # a ``ClosedResourceError`` indicates that the internal
-            # feeder memory receive channel was closed likely by the
-            # runtime after the associated transport-channel
-            # disconnected or broke.
-
-            # an ``EndOfChannel`` indicates either the internal recv
-            # memchan exhausted **or** we raisesd it just above after
-            # receiving a `stop` message from the far end of the stream.
-
-            # Previously this was triggered by calling ``.aclose()`` on
-            # the send side of the channel inside
-            # ``Actor._push_result()`` (should still be commented code
-            # there - which should eventually get removed), but now the
-            # 'stop' message handling has been put just above.
 
             # TODO: Locally, we want to close this stream gracefully, by
             # terminating any local consumers tasks deterministically.
-            # One we have broadcast support, we **don't** want to be
+            # Once we have broadcast support, we **don't** want to be
             # closing this stream and not flushing a final value to
             # remaining (clone) consumers who may not have been
             # scheduled to receive it yet.
+            # try:
+            #     maybe_err_msg_or_res: dict = self._rx_chan.receive_nowait()
+            #     if maybe_err_msg_or_res:
+            #         log.warning(
+            #             'Discarding un-processed msg:\n'
+            #             f'{maybe_err_msg_or_res}'
+            #         )
+            # except trio.WouldBlock:
+            #     # no queued msgs that might be another remote
+            #     # error, so just raise the original EoC
+            #     pass
 
-            # when the send is closed we assume the stream has
+            # raise eoc
-            # terminated and signal this local iterator to stop
-            await self.aclose()
 
-            raise  # propagate
+        # a ``ClosedResourceError`` indicates that the internal
+        # feeder memory receive channel was closed likely by the
+        # runtime after the associated transport-channel
+        # disconnected or broke.
+        except trio.ClosedResourceError as cre:  # by self._rx_chan.receive()
+            src_err = cre
+            log.warning(
+                '`Context._rx_chan` was already closed?'
+            )
+            self._closed = cre
 
-    async def aclose(self):
+        # when the send is closed we assume the stream has
+        # terminated and signal this local iterator to stop
+        drained: list[Exception|dict] = await self.aclose()
+        if drained:
+            # from .devx import pause
+            # await pause()
+            log.warning(
+                'Drained context msgs during closure:\n'
+                f'{drained}'
+            )
+        # TODO: pass these to the `._ctx._drained_msgs: deque`
+        # and then iterate them as part of any `.result()` call?
+
+        # NOTE XXX: if the context was cancelled or remote-errored
+        # but we received the stream close msg first, we
+        # probably want to instead raise the remote error
+        # over the end-of-stream connection error since likely
+        # the remote error was the source cause?
+        ctx: Context = self._ctx
+        ctx.maybe_raise(
+            raise_ctxc_from_self_call=True,
+        )
+
+        # propagate any error but hide low-level frame details
+        # from the caller by default for debug noise reduction.
+        if (
+            hide_tb
+
+            # XXX NOTE XXX don't reraise on certain
+            # stream-specific internal error types like,
+            #
+            # - `trio.EoC` since we want to use the exact instance
+            #   to ensure that it is the error that bubbles upward
+            #   for silent absorption by `Context.open_stream()`.
+            and not self._eoc
+
+            # - `RemoteActorError` (or `ContextCancelled`) if it gets
+            #   raised from `_raise_from_no_key_in_msg()` since we
+            #   want the same (as the above bullet) for any
+            #   `.open_context()` block bubbled error raised by
+            #   any nearby ctx API remote-failures.
+            # and not isinstance(src_err, RemoteActorError)
+        ):
+            raise type(src_err)(*src_err.args) from src_err
+        else:
+            raise src_err
+
+    async def aclose(self) -> list[Exception|dict]:
         '''
         Cancel associated remote actor task and local memory channel on
         close.
 
+        Notes: 
+         - REMEMBER that this is also called by `.__aexit__()` so
+           careful consideration must be made to handle whatever
+           internal stsate is mutated, particuarly in terms of
+           draining IPC msgs!
+
+         - more or less we try to maintain adherance to trio's `.aclose()` semantics:
+           https://trio.readthedocs.io/en/stable/reference-io.html#trio.abc.AsyncResource.aclose
         '''
-        # XXX: keep proper adherance to trio's `.aclose()` semantics:
-        # https://trio.readthedocs.io/en/stable/reference-io.html#trio.abc.AsyncResource.aclose
-        rx_chan = self._rx_chan
 
-        if rx_chan._closed:
+        # rx_chan = self._rx_chan
-            log.cancel(f"{self} is already closed")
 
+        # XXX NOTE XXX
+        # it's SUPER IMPORTANT that we ensure we don't DOUBLE
+        # DRAIN msgs on closure so avoid getting stuck handing on
+        # the `._rx_chan` since we call this method on
+        # `.__aexit__()` as well!!!
+        # => SO ENSURE WE CATCH ALL TERMINATION STATES in this
+        # block including the EoC..
+        if self.closed:
             # this stream has already been closed so silently succeed as
             # per ``trio.AsyncResource`` semantics.
             # https://trio.readthedocs.io/en/stable/reference-io.html#trio.abc.AsyncResource.aclose
-            return
+            return []
 
-        self._eoc = True
+        ctx: Context = self._ctx
+        drained: list[Exception|dict] = []
+        while not drained:
+            try:
+                maybe_final_msg = self.receive_nowait(
+                    allow_msg_keys=['yield', 'return'],
+                )
+                if maybe_final_msg:
+                    log.debug(
+                        'Drained un-processed stream msg:\n'
+                        f'{pformat(maybe_final_msg)}'
+                    )
+                    # TODO: inject into parent `Context` buf?
+                    drained.append(maybe_final_msg)
+
+            # NOTE: we only need these handlers due to the
+            # `.receive_nowait()` call above which may re-raise
+            # one of these errors on a msg key error!
+
+            except trio.WouldBlock as be:
+                drained.append(be)
+                break
+
+            except trio.EndOfChannel as eoc:
+                self._eoc: Exception = eoc
+                drained.append(eoc)
+                break
+
+            except trio.ClosedResourceError as cre:
+                self._closed = cre
+                drained.append(cre)
+                break
+
+            except ContextCancelled as ctxc:
+                # log.exception('GOT CTXC')
+                log.cancel(
+                    'Context was cancelled during stream closure:\n'
+                    f'canceller: {ctxc.canceller}\n'
+                    f'{pformat(ctxc.msgdata)}'
+                )
+                break
 
         # NOTE: this is super subtle IPC messaging stuff:
         # Relay stop iteration to far end **iff** we're
@@ -231,26 +358,40 @@ class MsgStream(trio.abc.Channel):
         except (
             trio.BrokenResourceError,
             trio.ClosedResourceError
-        ):
+        ) as re:
             # the underlying channel may already have been pulled
             # in which case our stop message is meaningless since
             # it can't traverse the transport.
-            ctx = self._ctx
             log.warning(
                 f'Stream was already destroyed?\n'
                 f'actor: {ctx.chan.uid}\n'
                 f'ctx id: {ctx.cid}'
             )
+            drained.append(re)
+            self._closed = re
 
-        self._closed = True
+        # if caught_eoc:
+        #     # from .devx import _debug
+        #     # await _debug.pause()
+        #     with trio.CancelScope(shield=True):
+        #         await rx_chan.aclose()
 
-        # Do we close the local mem chan ``self._rx_chan`` ??!?
+        if not self._eoc:
-
+            log.cancel(
-        # NO, DEFINITELY NOT if we're a bi-dir ``MsgStream``!
+                'Stream closed before it received an EoC?\n'
-        # BECAUSE this same core-msg-loop mem recv-chan is used to deliver
+                'Setting eoc manually..\n..'
-        # the potential final result from the surrounding inter-actor
+            )
-        # `Context` so we don't want to close it until that context has
+            self._eoc: bool = trio.EndOfChannel(
-        # run to completion.
+                f'Context stream closed by {self._ctx.side}\n'
+                f'|_{self}\n'
+            )
+        # ?XXX WAIT, why do we not close the local mem chan `._rx_chan` XXX?
+        # => NO, DEFINITELY NOT! <=
+        # if we're a bi-dir ``MsgStream`` BECAUSE this same
+        # core-msg-loop mem recv-chan is used to deliver the
+        # potential final result from the surrounding inter-actor
+        # `Context` so we don't want to close it until that
+        # context has run to completion.
 
         # XXX: Notes on old behaviour:
         # await rx_chan.aclose()
@@ -279,6 +420,26 @@ class MsgStream(trio.abc.Channel):
         # runtime's closure of ``rx_chan`` in the case where we may
         # still need to consume msgs that are "in transit" from the far
         # end (eg. for ``Context.result()``).
+        # self._closed = True
+        return drained
+
+    @property
+    def closed(self) -> bool:
+
+        rxc: bool = self._rx_chan._closed
+        _closed: bool|Exception = self._closed
+        _eoc: bool|trio.EndOfChannel = self._eoc
+        if rxc or _closed or _eoc:
+            log.runtime(
+                f'`MsgStream` is already closed\n'
+                f'{self}\n'
+                f' |_cid: {self._ctx.cid}\n'
+                f' |_rx_chan._closed: {type(rxc)} = {rxc}\n'
+                f' |_closed: {type(_closed)} = {_closed}\n'
+                f' |_eoc: {type(_eoc)} = {_eoc}'
+            )
+            return True
+        return False
 
     @acm
     async def subscribe(
@@ -334,19 +495,43 @@ class MsgStream(trio.abc.Channel):
 
     async def send(
         self,
-        data: Any
+        data: Any,
+
+        hide_tb: bool = True,
     ) -> None:
         '''
         Send a message over this stream to the far end.
 
         '''
-        if self._ctx._remote_error:
+        __tracebackhide__: bool = hide_tb
-            raise self._ctx._remote_error  # from None
+
+        # raise any alreay known error immediately
+        self._ctx.maybe_raise()
+        if self._eoc:
+            raise self._eoc
 
         if self._closed:
-            raise trio.ClosedResourceError('This stream was already closed')
+            raise self._closed
 
-        await self._ctx.chan.send({'yield': data, 'cid': self._ctx.cid})
+        try:
+            await self._ctx.chan.send(
+                payload={
+                    'yield': data,
+                    'cid': self._ctx.cid,
+                },
+                # hide_tb=hide_tb,
+            )
+        except (
+            trio.ClosedResourceError,
+            trio.BrokenResourceError,
+            BrokenPipeError,
+        ) as trans_err:
+            if hide_tb:
+                raise type(trans_err)(
+                    *trans_err.args
+                ) from trans_err
+            else:
+                raise
 
 
 def stream(func: Callable) -> Callable:

tractor/_supervise.py

@@ -21,6 +21,7 @@
 from contextlib import asynccontextmanager as acm
 from functools import partial
 import inspect
+from pprint import pformat
 from typing import (
     Optional,
     TYPE_CHECKING,
@@ -28,7 +29,6 @@ from typing import (
 import typing
 import warnings
 
-from exceptiongroup import BaseExceptionGroup
 import trio
 
 from ._debug import maybe_wait_for_debugger
@@ -36,7 +36,10 @@ from ._state import current_actor, is_main_process
 from .log import get_logger, get_loglevel
 from ._runtime import Actor
 from ._portal import Portal
-from ._exceptions import is_multi_cancelled
+from ._exceptions import (
+    is_multi_cancelled,
+    ContextCancelled,
+)
 from ._root import open_root_actor
 from . import _state
 from . import _spawn
@@ -106,6 +109,14 @@ class ActorNursery:
         self.errors = errors
         self.exited = trio.Event()
 
+        # NOTE: when no explicit call is made to
+        # `.open_root_actor()` by application code,
+        # `.open_nursery()` will implicitly call it to start the
+        # actor-tree runtime. In this case we mark ourselves as
+        # such so that runtime components can be aware for logging
+        # and syncing purposes to any actor opened nurseries.
+        self._implicit_runtime_started: bool = False
+
     async def start_actor(
         self,
         name: str,
@@ -157,7 +168,7 @@ class ActorNursery:
 
         # start a task to spawn a process
         # blocks until process has been started and a portal setup
-        nursery = nursery or self._da_nursery
+        nursery: trio.Nursery = nursery or self._da_nursery
 
         # XXX: the type ignore is actually due to a `mypy` bug
         return await nursery.start(  # type: ignore
@@ -190,14 +201,16 @@ class ActorNursery:
         **kwargs,  # explicit args to ``fn``
 
     ) -> Portal:
-        """Spawn a new actor, run a lone task, then terminate the actor and
+        '''
+        Spawn a new actor, run a lone task, then terminate the actor and
         return its result.
 
         Actors spawned using this method are kept alive at nursery teardown
         until the task spawned by executing ``fn`` completes at which point
         the actor is terminated.
-        """
+
-        mod_path = fn.__module__
+        '''
+        mod_path: str = fn.__module__
 
         if name is None:
             # use the explicit function name if not provided
@@ -232,21 +245,37 @@ class ActorNursery:
         )
         return portal
 
-    async def cancel(self, hard_kill: bool = False) -> None:
+    async def cancel(
-        """Cancel this nursery by instructing each subactor to cancel
+        self,
+        hard_kill: bool = False,
+
+    ) -> None:
+        '''
+        Cancel this nursery by instructing each subactor to cancel
         itself and wait for all subactors to terminate.
 
         If ``hard_killl`` is set to ``True`` then kill the processes
         directly without any far end graceful ``trio`` cancellation.
-        """
+
+        '''
         self.cancelled = True
 
-        log.cancel(f"Cancelling nursery in {self._actor.uid}")
+        # TODO: impl a repr for spawn more compact
+        # then `._children`..
+        children: dict = self._children
+        child_count: int = len(children)
+        msg: str = f'Cancelling actor nursery with {child_count} children\n'
         with trio.move_on_after(3) as cs:
+            async with trio.open_nursery() as tn:
 
-            async with trio.open_nursery() as nursery:
+                subactor: Actor
-
+                proc: trio.Process
-                for subactor, proc, portal in self._children.values():
+                portal: Portal
+                for (
+                    subactor,
+                    proc,
+                    portal,
+                ) in children.values():
 
                     # TODO: are we ever even going to use this or
                     # is the spawning backend responsible for such
@@ -258,12 +287,13 @@ class ActorNursery:
                         if portal is None:  # actor hasn't fully spawned yet
                             event = self._actor._peer_connected[subactor.uid]
                             log.warning(
-                                f"{subactor.uid} wasn't finished spawning?")
+                                f"{subactor.uid} never 't finished spawning?"
+                            )
 
                             await event.wait()
 
                             # channel/portal should now be up
-                            _, _, portal = self._children[subactor.uid]
+                            _, _, portal = children[subactor.uid]
 
                             # XXX should be impossible to get here
                             # unless method was called from within
@@ -280,14 +310,24 @@ class ActorNursery:
                         # spawn cancel tasks for each sub-actor
                         assert portal
                         if portal.channel.connected():
-                            nursery.start_soon(portal.cancel_actor)
+                            tn.start_soon(portal.cancel_actor)
 
+                log.cancel(msg)
         # if we cancelled the cancel (we hung cancelling remote actors)
         # then hard kill all sub-processes
         if cs.cancelled_caught:
             log.error(
-                f"Failed to cancel {self}\nHard killing process tree!")
+                f'Failed to cancel {self}?\n'
-            for subactor, proc, portal in self._children.values():
+                'Hard killing underlying subprocess tree!\n'
+            )
+            subactor: Actor
+            proc: trio.Process
+            portal: Portal
+            for (
+                subactor,
+                proc,
+                portal,
+            ) in children.values():
                 log.warning(f"Hard killing process {proc}")
                 proc.terminate()
 
@@ -327,7 +367,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
             # the above "daemon actor" nursery will be notified.
             async with trio.open_nursery() as ria_nursery:
 
-                anursery = ActorNursery(
+                an = ActorNursery(
                     actor,
                     ria_nursery,
                     da_nursery,
@@ -336,16 +376,16 @@ async def _open_and_supervise_one_cancels_all_nursery(
                 try:
                     # spawning of actors happens in the caller's scope
                     # after we yield upwards
-                    yield anursery
+                    yield an
 
                     # When we didn't error in the caller's scope,
                     # signal all process-monitor-tasks to conduct
                     # the "hard join phase".
                     log.runtime(
-                        f"Waiting on subactors {anursery._children} "
+                        'Waiting on subactors to complete:\n'
-                        "to complete"
+                        f'{pformat(an._children)}\n'
                     )
-                    anursery._join_procs.set()
+                    an._join_procs.set()
 
                 except BaseException as inner_err:
                     errors[actor.uid] = inner_err
@@ -357,37 +397,60 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # Instead try to wait for pdb to be released before
                     # tearing down.
                     await maybe_wait_for_debugger(
-                        child_in_debug=anursery._at_least_one_child_in_debug
+                        child_in_debug=an._at_least_one_child_in_debug
                     )
 
                     # if the caller's scope errored then we activate our
                     # one-cancels-all supervisor strategy (don't
                     # worry more are coming).
-                    anursery._join_procs.set()
+                    an._join_procs.set()
 
-                    # XXX: hypothetically an error could be
+                    # XXX NOTE XXX: hypothetically an error could
-                    # raised and then a cancel signal shows up
+                    # be raised and then a cancel signal shows up
                     # slightly after in which case the `else:`
                     # block here might not complete?  For now,
                     # shield both.
                     with trio.CancelScope(shield=True):
-                        etype = type(inner_err)
+                        etype: type = type(inner_err)
                         if etype in (
                             trio.Cancelled,
-                            KeyboardInterrupt
+                            KeyboardInterrupt,
                         ) or (
                             is_multi_cancelled(inner_err)
                         ):
                             log.cancel(
-                                f"Nursery for {current_actor().uid} "
+                                f'Actor-nursery cancelled by {etype}\n\n'
-                                f"was cancelled with {etype}")
+
+                                f'{current_actor().uid}\n'
+                                f' |_{an}\n\n'
+
+                                # TODO: show tb str?
+                                # f'{tb_str}'
+                            )
+                        elif etype in {
+                            ContextCancelled,
+                        }:
+                            log.cancel(
+                                'Actor-nursery caught remote cancellation\n\n'
+
+                                f'{inner_err.tb_str}'
+                            )
                         else:
                             log.exception(
-                                f"Nursery for {current_actor().uid} "
+                                'Nursery errored with:\n'
-                                f"errored with")
+
+                                # TODO: same thing as in
+                                # `._invoke()` to compute how to
+                                # place this div-line in the
+                                # middle of the above msg
+                                # content..
+                                # -[ ] prolly helper-func it too
+                                #   in our `.log` module..
+                                # '------ - ------'
+                            )
 
                         # cancel all subactors
-                        await anursery.cancel()
+                        await an.cancel()
 
             # ria_nursery scope end
 
@@ -408,18 +471,22 @@ async def _open_and_supervise_one_cancels_all_nursery(
             # XXX: yet another guard before allowing the cancel
             # sequence in case a (single) child is in debug.
             await maybe_wait_for_debugger(
-                child_in_debug=anursery._at_least_one_child_in_debug
+                child_in_debug=an._at_least_one_child_in_debug
             )
 
             # If actor-local error was raised while waiting on
             # ".run_in_actor()" actors then we also want to cancel all
             # remaining sub-actors (due to our lone strategy:
             # one-cancels-all).
-            log.cancel(f"Nursery cancelling due to {err}")
+            if an._children:
-            if anursery._children:
+                log.cancel(
+                    'Actor-nursery cancelling due error type:\n'
+                    f'{err}\n'
+                )
                 with trio.CancelScope(shield=True):
-                    await anursery.cancel()
+                    await an.cancel()
             raise
+
         finally:
             # No errors were raised while awaiting ".run_in_actor()"
             # actors but those actors may have returned remote errors as
@@ -428,9 +495,9 @@ async def _open_and_supervise_one_cancels_all_nursery(
             # collected in ``errors`` so cancel all actors, summarize
             # all errors and re-raise.
             if errors:
-                if anursery._children:
+                if an._children:
                     with trio.CancelScope(shield=True):
-                        await anursery.cancel()
+                        await an.cancel()
 
                 # use `BaseExceptionGroup` as needed
                 if len(errors) > 1:
@@ -465,19 +532,20 @@ async def open_nursery(
     which cancellation scopes correspond to each spawned subactor set.
 
     '''
-    implicit_runtime = False
+    implicit_runtime: bool = False
-
+    actor: Actor = current_actor(err_on_no_runtime=False)
-    actor = current_actor(err_on_no_runtime=False)
+    an: ActorNursery|None = None
-
     try:
-        if actor is None and is_main_process():
+        if (
-
+            actor is None
+            and is_main_process()
+        ):
             # if we are the parent process start the
             # actor runtime implicitly
             log.info("Starting actor runtime!")
 
             # mark us for teardown on exit
-            implicit_runtime = True
+            implicit_runtime: bool = True
 
             async with open_root_actor(**kwargs) as actor:
                 assert actor is current_actor()
@@ -485,24 +553,42 @@ async def open_nursery(
                 try:
                     async with _open_and_supervise_one_cancels_all_nursery(
                         actor
-                    ) as anursery:
+                    ) as an:
-                        yield anursery
+
+                        # NOTE: mark this nursery as having
+                        # implicitly started the root actor so
+                        # that `._runtime` machinery can avoid
+                        # certain teardown synchronization
+                        # blocking/waits and any associated (warn)
+                        # logging when it's known that this
+                        # nursery shouldn't be exited before the
+                        # root actor is.
+                        an._implicit_runtime_started = True
+                        yield an
                 finally:
-                    anursery.exited.set()
+                    # XXX: this event will be set after the root actor
+                    # runtime is already torn down, so we want to
+                    # avoid any blocking on it.
+                    an.exited.set()
 
         else:  # sub-nursery case
 
             try:
                 async with _open_and_supervise_one_cancels_all_nursery(
                     actor
-                ) as anursery:
+                ) as an:
-                    yield anursery
+                    yield an
             finally:
-                anursery.exited.set()
+                an.exited.set()
 
     finally:
-        log.debug("Nursery teardown complete")
+        msg: str = (
+            'Actor-nursery exited\n'
+            f'|_{an}\n\n'
+        )
 
         # shutdown runtime if it was started
         if implicit_runtime:
-            log.info("Shutting down actor tree")
+            msg += '=> Shutting down actor runtime <=\n'
+
+        log.info(msg)

tractor/_testing/__init__.py

@@ -0,0 +1,74 @@
+# 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/>.
+
+'''
+Various helpers/utils for auditing your `tractor` app and/or the
+core runtime.
+
+'''
+from contextlib import asynccontextmanager as acm
+import pathlib
+
+import tractor
+from .pytest import (
+    tractor_test as tractor_test
+)
+
+
+def repodir() -> pathlib.Path:
+    '''
+    Return the abspath to the repo directory.
+
+    '''
+    # 2 parents up to step up through tests/<repo_dir>
+    return pathlib.Path(
+        __file__
+
+    # 3 .parents bc:
+    # <._testing-pkg>.<tractor-pkg>.<git-repo-dir>
+    # /$HOME/../<tractor-repo-dir>/tractor/_testing/__init__.py
+    ).parent.parent.parent.absolute()
+
+
+def examples_dir() -> pathlib.Path:
+    '''
+    Return the abspath to the examples directory as `pathlib.Path`.
+
+    '''
+    return repodir() / 'examples'
+
+
+@acm
+async def expect_ctxc(
+    yay: bool,
+    reraise: bool = False,
+) -> None:
+    '''
+    Small acm to catch `ContextCancelled` errors when expected
+    below it in a `async with ()` block.
+
+    '''
+    if yay:
+        try:
+            yield
+            raise RuntimeError('Never raised ctxc?')
+        except tractor.ContextCancelled:
+            if reraise:
+                raise
+            else:
+                return
+    else:
+        yield

tractor/_testing/pytest.py

@@ -0,0 +1,113 @@
+# 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/>.
+
+'''
+`pytest` utils helpers and plugins for testing `tractor`'s runtime
+and applications.
+
+'''
+from functools import (
+    partial,
+    wraps,
+)
+import inspect
+import platform
+
+import tractor
+import trio
+
+
+def tractor_test(fn):
+    '''
+    Decorator for async test funcs to present them as "native"
+    looking sync funcs runnable by `pytest` using `trio.run()`.
+
+    Use:
+
+    @tractor_test
+    async def test_whatever():
+        await ...
+
+    If fixtures:
+
+        - ``reg_addr`` (a socket addr tuple where arbiter is listening)
+        - ``loglevel`` (logging level passed to tractor internals)
+        - ``start_method`` (subprocess spawning backend)
+
+    are defined in the `pytest` fixture space they will be automatically
+    injected to tests declaring these funcargs.
+    '''
+    @wraps(fn)
+    def wrapper(
+        *args,
+        loglevel=None,
+        reg_addr=None,
+        start_method: str|None = None,
+        debug_mode: bool = False,
+        **kwargs
+    ):
+        # __tracebackhide__ = True
+
+        # NOTE: inject ant test func declared fixture
+        # names by manually checking!
+        if 'reg_addr' in inspect.signature(fn).parameters:
+            # injects test suite fixture value to test as well
+            # as `run()`
+            kwargs['reg_addr'] = reg_addr
+
+        if 'loglevel' in inspect.signature(fn).parameters:
+            # allows test suites to define a 'loglevel' fixture
+            # that activates the internal logging
+            kwargs['loglevel'] = loglevel
+
+        if start_method is None:
+            if platform.system() == "Windows":
+                start_method = 'trio'
+
+        if 'start_method' in inspect.signature(fn).parameters:
+            # set of subprocess spawning backends
+            kwargs['start_method'] = start_method
+
+        if 'debug_mode' in inspect.signature(fn).parameters:
+            # set of subprocess spawning backends
+            kwargs['debug_mode'] = debug_mode
+
+
+        if kwargs:
+
+            # use explicit root actor start
+            async def _main():
+                async with tractor.open_root_actor(
+                    # **kwargs,
+                    registry_addrs=[reg_addr] if reg_addr else None,
+                    loglevel=loglevel,
+                    start_method=start_method,
+
+                    # TODO: only enable when pytest is passed --pdb
+                    debug_mode=debug_mode,
+
+                ):
+                    await fn(*args, **kwargs)
+
+            main = _main
+
+        else:
+            # use implicit root actor start
+            main = partial(fn, *args, **kwargs)
+
+        return trio.run(main)
+
+    return wrapper

tractor/experimental/_pubsub.py

@@ -31,7 +31,7 @@ from typing import (
     Callable,
 )
 from functools import partial
-from async_generator import aclosing
+from contextlib import aclosing
 
 import trio
 import wrapt

tractor/log.py

@@ -48,12 +48,15 @@ LOG_FORMAT = (
 
 DATE_FORMAT = '%b %d %H:%M:%S'
 
-LEVELS = {
+LEVELS: dict[str, int] = {
     'TRANSPORT': 5,
     'RUNTIME': 15,
     'CANCEL': 16,
     'PDB': 500,
 }
+# _custom_levels: set[str] = {
+#     lvlname.lower for lvlname in LEVELS.keys()
+# }
 
 STD_PALETTE = {
     'CRITICAL': 'red',
@@ -102,7 +105,11 @@ class StackLevelAdapter(logging.LoggerAdapter):
         Cancellation logging, mostly for runtime reporting.
 
         '''
-        return self.log(16, msg)
+        return self.log(
+            level=16,
+            msg=msg,
+            # stacklevel=4,
+        )
 
     def pdb(
         self,
@@ -114,14 +121,37 @@ class StackLevelAdapter(logging.LoggerAdapter):
         '''
         return self.log(500, msg)
 
-    def log(self, level, msg, *args, **kwargs):
+    def log(
-        """
+        self,
+        level,
+        msg,
+        *args,
+        **kwargs,
+    ):
+        '''
         Delegate a log call to the underlying logger, after adding
         contextual information from this adapter instance.
-        """
+
+        '''
         if self.isEnabledFor(level):
+            stacklevel: int = 3
+            if (
+                level in LEVELS.values()
+                # or level in _custom_levels
+            ):
+                stacklevel: int = 4
+
             # msg, kwargs = self.process(msg, kwargs)
-            self._log(level, msg, args, **kwargs)
+            self._log(
+                level=level,
+                msg=msg,
+                args=args,
+                # NOTE: not sure how this worked before but, it
+                # seems with our custom level methods defined above
+                # we do indeed (now) require another stack level??
+                stacklevel=stacklevel,
+                **kwargs,
+            )
 
     # LOL, the stdlib doesn't allow passing through ``stacklevel``..
     def _log(
@@ -134,12 +164,15 @@ class StackLevelAdapter(logging.LoggerAdapter):
         stack_info=False,
 
         # XXX: bit we added to show fileinfo from actual caller.
-        # this level then ``.log()`` then finally the caller's level..
+        # - this level
-        stacklevel=3,
+        # - then ``.log()``
+        # - then finally the caller's level..
+        stacklevel=4,
     ):
-        """
+        '''
         Low-level log implementation, proxied to allow nested logger adapters.
-        """
+
+        '''
         return self.logger._log(
             level,
             msg,
@@ -193,15 +226,39 @@ def get_logger(
     '''
     log = rlog = logging.getLogger(_root_name)
 
-    if name and name != _proj_name:
+    if (
+        name
+        and name != _proj_name
+    ):
 
-        # handling for modules that use ``get_logger(__name__)`` to
+        # NOTE: for handling for modules that use ``get_logger(__name__)``
-        # avoid duplicate project-package token in msg output
+        # we make the following stylistic choice:
-        rname, _, tail = name.partition('.')
+        # - always avoid duplicate project-package token
-        if rname == _root_name:
+        #   in msg output: i.e. tractor.tractor _ipc.py in header
-            name = tail
+        #   looks ridiculous XD
+        # - never show the leaf module name in the {name} part
+        #   since in python the {filename} is always this same
+        #   module-file.
+
+        sub_name: None | str = None
+        rname, _, sub_name = name.partition('.')
+        pkgpath, _, modfilename = sub_name.rpartition('.')
+
+        # NOTE: for tractor itself never include the last level
+        # module key in the name such that something like: eg.
+        # 'tractor.trionics._broadcast` only includes the first
+        # 2 tokens in the (coloured) name part.
+        if rname == 'tractor':
+            sub_name = pkgpath
+
+        if _root_name in sub_name:
+            duplicate, _, sub_name = sub_name.partition('.')
+
+        if not sub_name:
+            log = rlog
+        else:
+            log = rlog.getChild(sub_name)
 
-        log = rlog.getChild(name)
         log.level = rlog.level
 
     # add our actor-task aware adapter which will dynamically look up
@@ -232,11 +289,19 @@ def get_console_log(
     if not level:
         return log
 
-    log.setLevel(level.upper() if not isinstance(level, int) else level)
+    log.setLevel(
+        level.upper()
+        if not isinstance(level, int)
+        else level
+    )
 
     if not any(
         handler.stream == sys.stderr  # type: ignore
-        for handler in logger.handlers if getattr(handler, 'stream', None)
+        for handler in logger.handlers if getattr(
+            handler,
+            'stream',
+            None,
+        )
     ):
         handler = logging.StreamHandler()
         formatter = colorlog.ColoredFormatter(
@@ -254,3 +319,7 @@ def get_console_log(
 
 def get_loglevel() -> str:
     return _default_loglevel
+
+
+# global module logger for tractor itself
+log = get_logger('tractor')

tractor/msg/__init__.py

@@ -0,0 +1,26 @@
+# 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/>.
+
+'''
+Built-in messaging patterns, types, APIs and helpers.
+
+'''
+from .ptr import (
+    NamespacePath as NamespacePath,
+)
+from .types import (
+    Struct as Struct,
+)

tractor/msg/ptr.py

@@ -15,7 +15,7 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 '''
-Built-in messaging patterns, types, APIs and helpers.
+IPC-compat cross-mem-boundary object pointer.
 
 '''
 
@@ -43,38 +43,92 @@ Built-in messaging patterns, types, APIs and helpers.
 # - https://github.com/msgpack/msgpack-python#packingunpacking-of-custom-data-type
 
 from __future__ import annotations
+from inspect import (
+    isfunction,
+    ismethod,
+)
 from pkgutil import resolve_name
 
 
 class NamespacePath(str):
     '''
-    A serializeable description of a (function) Python object location
+    A serializeable `str`-subtype implementing a "namespace
-    described by the target's module path and namespace key meant as
+    pointer" to any Python object reference (like a function)
-    a message-native "packet" to allows actors to point-and-load objects
+    using the same format as the built-in `pkgutil.resolve_name()`
-    by absolute reference.
+    system.
+
+    A value describes a target's module-path and namespace-key
+    separated by a ':' and thus can be easily used as
+    a IPC-message-native reference-type allowing memory isolated
+    actors to point-and-load objects via a minimal `str` value.
 
     '''
-    _ref: object = None
+    _ref: object | type | None = None
 
-    def load_ref(self) -> object:
+    # TODO: support providing the ns instance in
+    # order to support 'self.<meth>` style to make
+    # `Portal.run_from_ns()` work!
+    # _ns: ModuleType|type|None = None
+
+    def load_ref(self) -> object | type:
         if self._ref is None:
             self._ref = resolve_name(self)
         return self._ref
 
-    def to_tuple(
+    @staticmethod
-        self,
+    def _mk_fqnp(ref: type | object) -> tuple[str, str]:
+        '''
+        Generate a minial ``str`` pair which describes a python
+        object's namespace path and object/type name.
 
-    ) -> tuple[str, str]:
+        In more precise terms something like:
-        ref = self.load_ref()
+          - 'py.namespace.path:object_name',
-        return ref.__module__, getattr(ref, '__name__', '')
+          - eg.'tractor.msg:NamespacePath' will be the ``str`` form
+            of THIS type XD
+
+        '''
+        if (
+            isfunction(ref)
+        ):
+            name: str = getattr(ref, '__name__')
+
+        elif ismethod(ref):
+            # build out the path manually i guess..?
+            # TODO: better way?
+            name: str = '.'.join([
+                type(ref.__self__).__name__,
+                ref.__func__.__name__,
+            ])
+
+        else:  # object or other?
+            # isinstance(ref, object)
+            # and not isfunction(ref)
+            name: str = type(ref).__name__
+
+        # fully qualified namespace path, tuple.
+        fqnp: tuple[str, str] = (
+            ref.__module__,
+            name,
+        )
+        return fqnp
 
     @classmethod
     def from_ref(
         cls,
-        ref,
+        ref: type | object,
 
     ) -> NamespacePath:
-        return cls(':'.join(
+
-            (ref.__module__,
+        fqnp: tuple[str, str] = cls._mk_fqnp(ref)
-             getattr(ref, '__name__', ''))
+        return cls(':'.join(fqnp))
-        ))
+
+    def to_tuple(
+        self,
+
+        # TODO: could this work re `self:<meth>` case from above?
+        # load_ref: bool = True,
+
+    ) -> tuple[str, str]:
+        return self._mk_fqnp(
+            self.load_ref()
+        )

tractor/msg/types.py

@@ -0,0 +1,270 @@
+# 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/>.
+
+'''
+Extensions to built-in or (heavily used but 3rd party) friend-lib
+types.
+
+'''
+from __future__ import annotations
+from collections import UserList
+from pprint import (
+    saferepr,
+)
+from typing import (
+    Any,
+    Iterator,
+)
+
+from msgspec import (
+    msgpack,
+    Struct as _Struct,
+    structs,
+)
+
+# TODO: auto-gen type sig for input func both for
+# type-msgs and logging of RPC tasks?
+# taken and modified from:
+# https://stackoverflow.com/a/57110117
+# import inspect
+# from typing import List
+
+# def my_function(input_1: str, input_2: int) -> list[int]:
+#     pass
+
+# def types_of(func):
+#     specs = inspect.getfullargspec(func)
+#     return_type = specs.annotations['return']
+#     input_types = [t.__name__ for s, t in specs.annotations.items() if s != 'return']
+#     return f'{func.__name__}({": ".join(input_types)}) -> {return_type}'
+
+# types_of(my_function)
+
+
+class DiffDump(UserList):
+    '''
+    Very simple list delegator that repr() dumps (presumed) tuple
+    elements of the form `tuple[str, Any, Any]` in a nice
+    multi-line readable form for analyzing `Struct` diffs.
+
+    '''
+    def __repr__(self) -> str:
+        if not len(self):
+            return super().__repr__()
+
+        # format by displaying item pair's ``repr()`` on multiple,
+        # indented lines such that they are more easily visually
+        # comparable when printed to console when printed to
+        # console.
+        repstr: str = '[\n'
+        for k, left, right in self:
+            repstr += (
+                f'({k},\n'
+                f'\t{repr(left)},\n'
+                f'\t{repr(right)},\n'
+                ')\n'
+            )
+        repstr += ']\n'
+        return repstr
+
+
+class Struct(
+    _Struct,
+
+    # https://jcristharif.com/msgspec/structs.html#tagged-unions
+    # tag='pikerstruct',
+    # tag=True,
+):
+    '''
+    A "human friendlier" (aka repl buddy) struct subtype.
+
+    '''
+    def _sin_props(self) -> Iterator[
+        tuple[
+            structs.FieldIinfo,
+            str,
+            Any,
+        ]
+    ]:
+        '''
+        Iterate over all non-@property fields of this struct.
+
+        '''
+        fi: structs.FieldInfo
+        for fi in structs.fields(self):
+            key: str = fi.name
+            val: Any = getattr(self, key)
+            yield fi, key, val
+
+    def to_dict(
+        self,
+        include_non_members: bool = True,
+
+    ) -> dict:
+        '''
+        Like it sounds.. direct delegation to:
+        https://jcristharif.com/msgspec/api.html#msgspec.structs.asdict
+
+        BUT, by default we pop all non-member (aka not defined as
+        struct fields) fields by default.
+
+        '''
+        asdict: dict = structs.asdict(self)
+        if include_non_members:
+            return asdict
+
+        # only return a dict of the struct members
+        # which were provided as input, NOT anything
+        # added as type-defined `@property` methods!
+        sin_props: dict = {}
+        fi: structs.FieldInfo
+        for fi, k, v in self._sin_props():
+            sin_props[k] = asdict[k]
+
+        return sin_props
+
+    def pformat(
+        self,
+        field_indent: int = 2,
+        indent: int = 0,
+
+    ) -> str:
+        '''
+        Recursion-safe `pprint.pformat()` style formatting of
+        a `msgspec.Struct` for sane reading by a human using a REPL.
+
+        '''
+        # global whitespace indent
+        ws: str = ' '*indent
+
+        # field whitespace indent
+        field_ws: str = ' '*(field_indent + indent)
+
+        # qtn: str = ws + self.__class__.__qualname__
+        qtn: str = self.__class__.__qualname__
+
+        obj_str: str = ''  # accumulator
+        fi: structs.FieldInfo
+        k: str
+        v: Any
+        for fi, k, v in self._sin_props():
+
+            # TODO: how can we prefer `Literal['option1',  'option2,
+            # ..]` over .__name__ == `Literal` but still get only the
+            # latter for simple types like `str | int | None` etc..?
+            ft: type = fi.type
+            typ_name: str = getattr(ft, '__name__', str(ft))
+
+            # recurse to get sub-struct's `.pformat()` output Bo
+            if isinstance(v, Struct):
+                val_str: str =  v.pformat(
+                    indent=field_indent + indent,
+                    field_indent=indent + field_indent,
+                )
+
+            else:  # the `pprint` recursion-safe format:
+                # https://docs.python.org/3.11/library/pprint.html#pprint.saferepr
+                val_str: str = saferepr(v)
+
+            # TODO: LOLOL use `textwrap.indent()` instead dawwwwwg!
+            obj_str += (field_ws + f'{k}: {typ_name} = {val_str},\n')
+
+        return (
+            f'{qtn}(\n'
+            f'{obj_str}'
+            f'{ws})'
+        )
+
+    # TODO: use a pprint.PrettyPrinter instance around ONLY rendering
+    # inside a known tty?
+    # def __repr__(self) -> str:
+    #     ...
+
+    # __str__ = __repr__ = pformat
+    __repr__ = pformat
+
+    def copy(
+        self,
+        update: dict | None = None,
+
+    ) -> Struct:
+        '''
+        Validate-typecast all self defined fields, return a copy of
+        us with all such fields.
+
+        NOTE: This is kinda like the default behaviour in
+        `pydantic.BaseModel` except a copy of the object is
+        returned making it compat with `frozen=True`.
+
+        '''
+        if update:
+            for k, v in update.items():
+                setattr(self, k, v)
+
+        # NOTE: roundtrip serialize to validate
+        # - enode to msgpack binary format,
+        # - decode that back to a struct.
+        return msgpack.Decoder(type=type(self)).decode(
+            msgpack.Encoder().encode(self)
+        )
+
+    def typecast(
+        self,
+
+        # TODO: allow only casting a named subset?
+        # fields: set[str] | None = None,
+
+    ) -> None:
+        '''
+        Cast all fields using their declared type annotations
+        (kinda like what `pydantic` does by default).
+
+        NOTE: this of course won't work on frozen types, use
+        ``.copy()`` above in such cases.
+
+        '''
+        # https://jcristharif.com/msgspec/api.html#msgspec.structs.fields
+        fi: structs.FieldInfo
+        for fi in structs.fields(self):
+            setattr(
+                self,
+                fi.name,
+                fi.type(getattr(self, fi.name)),
+            )
+
+    def __sub__(
+        self,
+        other: Struct,
+
+    ) -> DiffDump[tuple[str, Any, Any]]:
+        '''
+        Compare fields/items key-wise and return a ``DiffDump``
+        for easy visual REPL comparison B)
+
+        '''
+        diffs: DiffDump[tuple[str, Any, Any]] = DiffDump()
+        for fi in structs.fields(self):
+            attr_name: str = fi.name
+            ours: Any = getattr(self, attr_name)
+            theirs: Any = getattr(other, attr_name)
+            if ours != theirs:
+                diffs.append((
+                    attr_name,
+                    ours,
+                    theirs,
+                ))
+
+        return diffs

tractor/to_asyncio.py

@@ -217,7 +217,14 @@ def _run_asyncio_task(
         try:
             result = await coro
         except BaseException as aio_err:
-            log.exception('asyncio task errored')
+            if isinstance(aio_err, CancelledError):
+                log.runtime(
+                    '`asyncio` task was cancelled..\n'
+                )
+            else:
+                log.exception(
+                    '`asyncio` task errored\n'
+                )
             chan._aio_err = aio_err
             raise
 
@@ -272,12 +279,22 @@ def _run_asyncio_task(
         except BaseException as terr:
             task_err = terr
 
+            msg: str = (
+                'Infected `asyncio` task {etype_str}\n'
+                f'|_{task}\n'
+            )
             if isinstance(terr, CancelledError):
-                log.cancel(f'`asyncio` task cancelled: {task.get_name()}')
+                log.cancel(
+                    msg.format(etype_str='cancelled')
+                )
             else:
-                log.exception(f'`asyncio` task: {task.get_name()} errored')
+                log.exception(
+                    msg.format(etype_str='cancelled')
+                )
 
-            assert type(terr) is type(aio_err), 'Asyncio task error mismatch?'
+            assert type(terr) is type(aio_err), (
+                '`asyncio` task error mismatch?!?'
+            )
 
         if aio_err is not None:
             # XXX: uhh is this true?
@@ -290,18 +307,22 @@ def _run_asyncio_task(
             # We might want to change this in the future though.
             from_aio.close()
 
-            if type(aio_err) is CancelledError:
+            if task_err is None:
-                log.cancel("infected task was cancelled")
-
-                # TODO: show that the cancellation originated
-                # from the ``trio`` side? right?
-                # if cancel_scope.cancelled:
-                #     raise aio_err from err
-
-            elif task_err is None:
                 assert aio_err
                 aio_err.with_traceback(aio_err.__traceback__)
-                log.error('infected task errorred')
+                # log.error(
+                #     'infected task errorred'
+                # )
+
+            # TODO: show that the cancellation originated
+            # from the ``trio`` side? right?
+            # elif type(aio_err) is CancelledError:
+            #     log.cancel(
+            #         'infected task was cancelled'
+            #     )
+
+                # if cancel_scope.cancelled:
+                #     raise aio_err from err
 
             # XXX: alway cancel the scope on error
             # in case the trio task is blocking

tractor/trionics/__init__.py

@@ -19,22 +19,13 @@ Sugary patterns for trio + tractor designs.
 
 '''
 from ._mngrs import (
-    gather_contexts,
+    gather_contexts as gather_contexts,
-    maybe_open_context,
+    maybe_open_context as maybe_open_context,
-    maybe_open_nursery,
+    maybe_open_nursery as maybe_open_nursery,
 )
 from ._broadcast import (
-    broadcast_receiver,
+    AsyncReceiver as AsyncReceiver,
-    BroadcastReceiver,
+    broadcast_receiver as broadcast_receiver,
-    Lagged,
+    BroadcastReceiver as BroadcastReceiver,
+    Lagged as Lagged,
 )
-
-
-__all__ = [
-    'gather_contexts',
-    'broadcast_receiver',
-    'BroadcastReceiver',
-    'Lagged',
-    'maybe_open_context',
-    'maybe_open_nursery',
-]

tractor/trionics/_broadcast.py

@@ -26,7 +26,6 @@ from contextlib import asynccontextmanager
 from functools import partial
 from operator import ne
 from typing import (
-    Optional,
     Callable,
     Awaitable,
     Any,
@@ -45,6 +44,11 @@ from tractor.log import get_logger
 
 log = get_logger(__name__)
 
+# TODO: use new type-vars syntax from 3.12
+# https://realpython.com/python312-new-features/#dedicated-type-variable-syntax
+# https://docs.python.org/3/whatsnew/3.12.html#whatsnew312-pep695
+# https://docs.python.org/3/reference/simple_stmts.html#type
+#
 # A regular invariant generic type
 T = TypeVar("T")
 
@@ -110,7 +114,7 @@ class BroadcastState(Struct):
 
     # broadcast event to wake up all sleeping consumer tasks
     # on a newly produced value from the sender.
-    recv_ready: Optional[tuple[int, trio.Event]] = None
+    recv_ready: tuple[int, trio.Event]|None = None
 
     # if a ``trio.EndOfChannel`` is received on any
     # consumer all consumers should be placed in this state
@@ -164,7 +168,7 @@ class BroadcastReceiver(ReceiveChannel):
 
         rx_chan: AsyncReceiver,
         state: BroadcastState,
-        receive_afunc: Optional[Callable[[], Awaitable[Any]]] = None,
+        receive_afunc: Callable[[], Awaitable[Any]]|None = None,
         raise_on_lag: bool = True,
 
     ) -> None:
@@ -452,7 +456,7 @@ def broadcast_receiver(
 
     recv_chan: AsyncReceiver,
     max_buffer_size: int,
-    receive_afunc: Optional[Callable[[], Awaitable[Any]]] = None,
+    receive_afunc: Callable[[], Awaitable[Any]]|None = None,
     raise_on_lag: bool = True,
 
 ) -> BroadcastReceiver:

tractor/trionics/_mngrs.py

@@ -33,10 +33,9 @@ from typing import (
 )
 
 import trio
-from trio_typing import TaskStatus
 
-from .._state import current_actor
+from tractor._state import current_actor
-from ..log import get_logger
+from tractor.log import get_logger
 
 
 log = get_logger(__name__)
@@ -70,6 +69,7 @@ async def _enter_and_wait(
     unwrapped: dict[int, T],
     all_entered: trio.Event,
     parent_exit: trio.Event,
+    seed: int,
 
 ) -> None:
     '''
@@ -80,7 +80,10 @@ async def _enter_and_wait(
     async with mngr as value:
         unwrapped[id(mngr)] = value
 
-        if all(unwrapped.values()):
+        if all(
+            val != seed
+            for val in unwrapped.values()
+        ):
             all_entered.set()
 
         await parent_exit.wait()
@@ -91,7 +94,13 @@ async def gather_contexts(
 
     mngrs: Sequence[AsyncContextManager[T]],
 
-) -> AsyncGenerator[tuple[Optional[T], ...], None]:
+) -> AsyncGenerator[
+    tuple[
+        T | None,
+        ...
+    ],
+    None,
+]:
     '''
     Concurrently enter a sequence of async context managers, each in
     a separate ``trio`` task and deliver the unwrapped values in the
@@ -104,7 +113,11 @@ async def gather_contexts(
     entered and exited, and cancellation just works.
 
     '''
-    unwrapped: dict[int, Optional[T]] = {}.fromkeys(id(mngr) for mngr in mngrs)
+    seed: int = id(mngrs)
+    unwrapped: dict[int, T | None] = {}.fromkeys(
+        (id(mngr) for mngr in mngrs),
+        seed,
+    )
 
     all_entered = trio.Event()
     parent_exit = trio.Event()
@@ -116,8 +129,9 @@ async def gather_contexts(
 
     if not mngrs:
         raise ValueError(
-            'input mngrs is empty?\n'
+            '`.trionics.gather_contexts()` input mngrs is empty?\n'
-            'Did try to use inline generator syntax?'
+            'Did try to use inline generator syntax?\n'
+            'Use a non-lazy iterator or sequence type intead!'
         )
 
     async with trio.open_nursery() as n:
@@ -128,6 +142,7 @@ async def gather_contexts(
                 unwrapped,
                 all_entered,
                 parent_exit,
+                seed,
             )
 
         # deliver control once all managers have started up
@@ -168,7 +183,7 @@ class _Cache:
         cls,
         mng,
         ctx_key: tuple,
-        task_status: TaskStatus[T] = trio.TASK_STATUS_IGNORED,
+        task_status: trio.TaskStatus[T] = trio.TASK_STATUS_IGNORED,
 
     ) -> None:
         async with mng as value:
@@ -209,6 +224,7 @@ async def maybe_open_context(
 
     # yielded output
     yielded: Any = None
+    lock_registered: bool = False
 
     # Lock resource acquisition around task racing  / ``trio``'s
     # scheduler protocol.
@@ -216,6 +232,7 @@ async def maybe_open_context(
     # to allow re-entrant use cases where one `maybe_open_context()`
     # wrapped factor may want to call into another.
     lock = _Cache.locks.setdefault(fid, trio.Lock())
+    lock_registered: bool = True
     await lock.acquire()
 
     # XXX: one singleton nursery per actor and we want to
@@ -275,4 +292,9 @@ async def maybe_open_context(
                     _, no_more_users = entry
                     no_more_users.set()
 
-                _Cache.locks.pop(fid)
+                if lock_registered:
+                    maybe_lock = _Cache.locks.pop(fid, None)
+                    if maybe_lock is None:
+                        log.error(
+                            f'Resource lock for {fid} ALREADY POPPED?'
+                        )