Add back in async gen loop

Theoretically we can actually concurrently soft wait the process and the
nursery exit event, the only problem at the moment is some pubsub tests
puking. You're right in guessing this isn't really changing anything but
it is meant to be a reminder. If we can add this the spawn task can
report when a process dies earlier then expected and in the longer term
once we remove the `ActorNursery.run_in_actor()` API, we can probably do
away with both the nursery exit event and the portal result fetching.

.github/workflows/ci.yml

@@ -1,11 +1,6 @@
 name: CI
 
-on:
+on: push
-  # any time someone pushes a new branch to origin
-  push:
-
-  # Allows you to run this workflow manually from the Actions tab
-  workflow_dispatch:
 
 jobs:
 
@@ -20,35 +15,13 @@ jobs:
       - name: Setup python
         uses: actions/setup-python@v2
         with:
-          python-version: '3.10'
+          python-version: '3.9'
 
       - name: Install dependencies
         run: pip install -U . --upgrade-strategy eager -r requirements-test.txt
 
       - name: Run MyPy check
-        run: mypy tractor/ --ignore-missing-imports --show-traceback
+        run: mypy tractor/ --ignore-missing-imports
-
-  # test that we can generate a software distribution and install it
-  # thus avoid missing file issues after packaging.
-  sdist-linux:
-    name: 'sdist'
-    runs-on: ubuntu-latest
-
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v2
-
-      - name: Setup python
-        uses: actions/setup-python@v2
-        with:
-          python-version: '3.10'
-
-      - name: Build sdist
-        run: python setup.py sdist --formats=zip
-
-      - name: Install sdist from .zips
-        run: python -m pip install dist/*.zip
-
 
   testing-linux:
     name: '${{ matrix.os }} Python ${{ matrix.python }} - ${{ matrix.spawn_backend }}'
@@ -59,12 +32,8 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python: ['3.10']
+        python: ['3.9', '3.10']
-        spawn_backend: [
+        spawn_backend: ['trio', 'mp']
-          'trio',
-          'mp_spawn',
-          'mp_forkserver',
-        ]
 
     steps:
 
@@ -79,53 +48,71 @@ jobs:
       - name: Install dependencies
         run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
 
-      - name: List dependencies
+      - name: Run tests
-        run: pip list
+        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rs
+
+  testing-linux-msgspec:
+    # runs jobs on all OS's but with optional `msgspec` dep installed
+    name: '${{ matrix.os }} Python ${{ matrix.python }} - ${{ matrix.spawn_backend }} - msgspec'
+    timeout-minutes: 10
+    runs-on: ${{ matrix.os }}
+
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ubuntu-latest]
+        python: ['3.9', '3.10']
+        spawn_backend: ['trio', 'mp']
+
+    steps:
+
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '${{ matrix.python }}'
+
+      - name: Install dependencies
+        run: pip install -U .[msgspec] -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
 
       - name: Run tests
-        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rsx
+        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rs
 
-  # We skip 3.10 on windows for now due to not having any collabs to
+  # We skip 3.10 on windows for now due to
-  # debug the CI failures. Anyone wanting to hack and solve them is very
+  # https://github.com/pytest-dev/pytest/issues/8733
-  # welcome, but our primary user base is not using that OS.
+  # some kinda weird `pyreadline` issue..
 
   # TODO: use job filtering to accomplish instead of repeated
   # boilerplate as is above XD:
   # - https://docs.github.com/en/actions/learn-github-actions/managing-complex-workflows
   # - https://docs.github.com/en/actions/learn-github-actions/managing-complex-workflows#using-a-build-matrix
   # - https://docs.github.com/en/actions/learn-github-actions/workflow-syntax-for-github-actions#jobsjob_idif
-  # testing-windows:
+  testing-windows:
-  #   name: '${{ matrix.os }} Python ${{ matrix.python }} - ${{ matrix.spawn_backend }}'
+    name: '${{ matrix.os }} Python ${{ matrix.python }} - ${{ matrix.spawn_backend }}'
-  #   timeout-minutes: 12
+    timeout-minutes: 12
-  #   runs-on: ${{ matrix.os }}
+    runs-on: ${{ matrix.os }}
 
-  #   strategy:
+    strategy:
-  #     fail-fast: false
+      fail-fast: false
-  #     matrix:
+      matrix:
-  #       os: [windows-latest]
+        os: [windows-latest]
-  #       python: ['3.10']
+        python: ['3.9']
-  #       spawn_backend: ['trio', 'mp']
+        spawn_backend: ['trio', 'mp']
 
-  #   steps:
+    steps:
 
-  #     - name: Checkout
+      - name: Checkout
-  #       uses: actions/checkout@v2
+        uses: actions/checkout@v2
 
-  #     - name: Setup python
+      - name: Setup python
-  #       uses: actions/setup-python@v2
+        uses: actions/setup-python@v2
-  #       with:
+        with:
-  #         python-version: '${{ matrix.python }}'
+          python-version: '${{ matrix.python }}'
 
-  #     - name: Install dependencies
+      - name: Install dependencies
-  #       run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
+        run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
 
-  #     # TODO: pretty sure this solves debugger deps-issues on windows, but it needs to
+      - name: Run tests
-  #     # be verified by someone with a native setup.
+        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rs
-  #     # - name: Force pyreadline3
-  #     #   run: pip uninstall pyreadline; pip install -U pyreadline3
-
-  #     - name: List dependencies
-  #       run: pip list
-
-  #     - name: Run tests
-  #       run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rsx

MANIFEST.in

@@ -1,2 +0,0 @@
-# https://packaging.python.org/en/latest/guides/using-manifest-in/#using-manifest-in
-include docs/README.rst

NEWS.rst

@@ -4,148 +4,6 @@ Changelog
 
 .. towncrier release notes start
 
-tractor 0.1.0a5 (2022-08-03)
-============================
-
-This is our final release supporting Python 3.9 since we will be moving
-internals to the new `match:` syntax from 3.10 going forward and
-further, we have officially dropped usage of the `msgpack` library and
-happily adopted `msgspec`.
-
-Features
---------
-
-- `#165 <https://github.com/goodboy/tractor/issues/165>`_: Add SIGINT
-  protection to our `pdbpp` based debugger subystem such that for
-  (single-depth) actor trees in debug mode we ignore interrupts in any
-  actor currently holding the TTY lock thus avoiding clobbering IPC
-  connections and/or task and process state when working in the REPL.
-
-  As a big note currently so called "nested" actor trees (trees with
-  actors having more then one parent/ancestor) are not fully supported
-  since we don't yet have a mechanism to relay the debug mode knowledge
-  "up" the actor tree (for eg. when handling a crash in a leaf actor).
-  As such currently there is a set of tests and known scenarios which will
-  result in process cloberring by the zombie repaing machinery and these
-  have been documented in https://github.com/goodboy/tractor/issues/320.
-
-  The implementation details include:
-
-  - utilizing a custom SIGINT handler which we apply whenever an actor's
-    runtime enters the debug machinery, which we also make sure the
-    stdlib's `pdb` configuration doesn't override (which it does by
-    default without special instance config).
-  - litter the runtime with `maybe_wait_for_debugger()` mostly in spots
-    where the root actor should block before doing embedded nursery
-    teardown ops which both cancel potential-children-in-deubg as well
-    as eventually trigger zombie reaping machinery.
-  - hardening of the TTY locking semantics/API both in terms of IPC
-    terminations and cancellation and lock release determinism from
-    sync debugger instance methods.
-  - factoring of locking infrastructure into a new `._debug.Lock` global
-    which encapsulates all details of the ``trio`` sync primitives and
-    task/actor uid management and tracking.
-
-  We also add `ctrl-c` cases throughout the test suite though these are
-  disabled for py3.9 (`pdbpp` UX differences that don't seem worth
-  compensating for, especially since this will be our last 3.9 supported
-  release) and there are a slew of marked cases that aren't expected to
-  work in CI more generally (as mentioned in the "nested" tree note
-  above) despite seemingly working  when run manually on linux.
-
-- `#304 <https://github.com/goodboy/tractor/issues/304>`_: Add a new
-  ``to_asyncio.LinkedTaskChannel.subscribe()`` which gives task-oriented
-  broadcast functionality semantically equivalent to
-  ``tractor.MsgStream.subscribe()`` this makes it possible for multiple
-  ``trio``-side tasks to consume ``asyncio``-side task msgs in tandem.
-
-  Further Improvements to the test suite were added in this patch set
-  including a new scenario test for a sub-actor managed "service nursery"
-  (implementing the basics of a "service manager") including use of
-  *infected asyncio* mode. Further we added a lower level
-  ``test_trioisms.py`` to start to track issues we need to work around in
-  ``trio`` itself which in this case included a bug we were trying to
-  solve related to https://github.com/python-trio/trio/issues/2258.
-
-
-Bug Fixes
----------
-
-- `#318 <https://github.com/goodboy/tractor/issues/318>`_: Fix
-  a previously undetected ``trio``-``asyncio`` task lifetime linking
-  issue with the ``to_asyncio.open_channel_from()`` api where both sides
-  where not properly waiting/signalling termination and it was possible
-  for ``asyncio``-side errors to not propagate due to a race condition.
-
-  The implementation fix summary is:
-  - add state to signal the end of the ``trio`` side task to be
-    read by the ``asyncio`` side and always cancel any ongoing
-    task in such cases.
-  - always wait on the ``asyncio`` task termination from the ``trio``
-    side on error before maybe raising said error.
-  - always close the ``trio`` mem chan on exit to ensure the other
-    side can detect it and follow.
-
-
-Trivial/Internal Changes
-------------------------
-
-- `#248 <https://github.com/goodboy/tractor/issues/248>`_: Adjust the
-  `tractor._spawn.soft_wait()` strategy to avoid sending an actor cancel
-  request (via `Portal.cancel_actor()`) if either the child process is
-  detected as having terminated or the IPC channel is detected to be
-  closed.
-
-  This ensures (even) more deterministic inter-actor cancellation by
-  avoiding the timeout condition where possible when a whild never
-  sucessfully spawned, crashed, or became un-contactable over IPC.
-
-- `#295 <https://github.com/goodboy/tractor/issues/295>`_: Add an
-  experimental ``tractor.msg.NamespacePath`` type for passing Python
-  objects by "reference" through a ``str``-subtype message and using the
-  new ``pkgutil.resolve_name()`` for reference loading.
-
-- `#298 <https://github.com/goodboy/tractor/issues/298>`_: Add a new
-  `tractor.experimental` subpackage for staging new high level APIs and
-  subystems that we might eventually make built-ins.
-
-- `#300 <https://github.com/goodboy/tractor/issues/300>`_: Update to and
-  pin latest ``msgpack`` (1.0.3) and ``msgspec`` (0.4.0) both of which
-  required adjustments for backwards imcompatible API tweaks.
-
-- `#303 <https://github.com/goodboy/tractor/issues/303>`_: Fence off
-  ``multiprocessing`` imports until absolutely necessary in an effort to
-  avoid "resource tracker" spawning side effects that seem to have
-  varying degrees of unreliability per Python release. Port to new
-  ``msgspec.DecodeError``.
-
-- `#305 <https://github.com/goodboy/tractor/issues/305>`_: Add
-  ``tractor.query_actor()`` an addr looker-upper which doesn't deliver
-  a ``Portal`` instance and instead just a socket address ``tuple``.
-
-  Sometimes it's handy to just have a simple way to figure out if
-  a "service" actor is up, so add this discovery helper for that. We'll
-  prolly just leave it undocumented for now until we figure out
-  a longer-term/better discovery system.
-
-- `#316 <https://github.com/goodboy/tractor/issues/316>`_: Run windows
-  CI jobs on python 3.10 after some hacks for ``pdbpp`` dependency
-  issues.
-
-  Issue was to do with the now deprecated `pyreadline` project which
-  should be changed over to `pyreadline3`.
-
-- `#317 <https://github.com/goodboy/tractor/issues/317>`_: Drop use of
-  the ``msgpack`` package and instead move fully to the ``msgspec``
-  codec library.
-
-  We've now used ``msgspec`` extensively in production and there's no
-  reason to not use it as default. Further this change preps us for the up
-  and coming typed messaging semantics (#196), dialog-unprotocol system
-  (#297), and caps-based messaging-protocols (#299) planned before our
-  first beta.
-
-
 tractor 0.1.0a4 (2021-12-18)
 ============================
 

docs/README.rst

@@ -3,20 +3,13 @@
 |gh_actions|
 |docs|
 
-``tractor`` is a `structured concurrent`_, multi-processing_ runtime
+``tractor`` is a `structured concurrent`_, multi-processing_ runtime built on trio_.
-built on trio_.
 
-Fundamentally, ``tractor`` gives you parallelism via
+Fundamentally ``tractor`` gives you parallelism via ``trio``-"*actors*":
-``trio``-"*actors*": independent Python processes (aka
+our nurseries_ let you spawn new Python processes which each run a ``trio``
-non-shared-memory threads) which maintain structured
-concurrency (SC) *end-to-end* inside a *supervision tree*.
-
-Cross-process (and thus cross-host) SC is accomplished through the
-combined use of our "actor nurseries_" and an "SC-transitive IPC
-protocol" constructed on top of multiple Pythons each running a ``trio``
 scheduled runtime - a call to ``trio.run()``.
 
-We believe the system adheres to the `3 axioms`_ of an "`actor model`_"
+We believe the system adhere's to the `3 axioms`_ of an "`actor model`_"
 but likely *does not* look like what *you* probably think an "actor
 model" looks like, and that's *intentional*.
 
@@ -29,10 +22,9 @@ Features
 - **It's just** a ``trio`` API
 - *Infinitely nesteable* process trees
 - Builtin IPC streaming APIs with task fan-out broadcasting
-- A "native" multi-core debugger REPL using `pdbp`_ (a fork & fix of
+- A (first ever?) "native" multi-core debugger UX for Python using `pdb++`_
-  `pdb++`_ thanks to @mdmintz!)
 - Support for a swappable, OS specific, process spawning layer
-- A modular transport stack, allowing for custom serialization (eg. with
+- A modular transport stack, allowing for custom serialization (eg.
   `msgspec`_), communications protocols, and environment specific IPC
   primitives
 - Support for spawning process-level-SC, inter-loop one-to-one-task oriented
@@ -125,7 +117,7 @@ Zombie safe: self-destruct a process tree
             f"running in pid {os.getpid()}"
         )
 
-        await trio.sleep_forever()
+       await trio.sleep_forever()
 
 
     async def main():
@@ -156,7 +148,7 @@ it **is a bug**.
 
 "Native" multi-process debugging
 --------------------------------
-Using the magic of `pdbp`_ and our internal IPC, we've
+Using the magic of `pdb++`_ and our internal IPC, we've
 been able to create a native feeling debugging experience for
 any (sub-)process in your ``tractor`` tree.
 
@@ -497,6 +489,12 @@ From PyPi::
     pip install tractor
 
 
+To try out the (optionally) faster `msgspec`_ codec instead of the
+default ``msgpack`` lib::
+
+    pip install tractor[msgspec]
+
+
 From git::
 
     pip install git+git://github.com/goodboy/tractor.git
@@ -565,22 +563,11 @@ properties of the system.
 
 What's on the TODO:
 -------------------
-Help us push toward the future of distributed `Python`.
+Help us push toward the future.
 
-- Erlang-style supervisors via composed context managers (see `#22
+- Typed messaging protocols (ex. via ``msgspec``, see `#36
-  <https://github.com/goodboy/tractor/issues/22>`_)
-- Typed messaging protocols (ex. via ``msgspec.Struct``, see `#36
   <https://github.com/goodboy/tractor/issues/36>`_)
-- Typed capability-based (dialog) protocols ( see `#196
+- Erlang-style supervisors via composed context managers
-  <https://github.com/goodboy/tractor/issues/196>`_ with draft work
-  started in `#311 <https://github.com/goodboy/tractor/pull/311>`_)
-- We **recently disabled CI-testing on windows** and need help getting
-  it running again! (see `#327
-  <https://github.com/goodboy/tractor/pull/327>`_). **We do have windows
-  support** (and have for quite a while) but since no active hacker
-  exists in the user-base to help test on that OS, for now we're not
-  actively maintaining testing due to the added hassle and general
-  latency..
 
 
 Feel like saying hi?
@@ -592,19 +579,18 @@ say hi, please feel free to reach us in our `matrix channel`_.  If
 matrix seems too hip, we're also mostly all in the the `trio gitter
 channel`_!
 
-.. _structured concurrent: https://trio.discourse.group/t/concise-definition-of-structured-concurrency/228
-.. _multi-processing: https://en.wikipedia.org/wiki/Multiprocessing
-.. _trio: https://github.com/python-trio/trio
 .. _nurseries: https://vorpus.org/blog/notes-on-structured-concurrency-or-go-statement-considered-harmful/#nurseries-a-structured-replacement-for-go-statements
 .. _actor model: https://en.wikipedia.org/wiki/Actor_model
+.. _trio: https://github.com/python-trio/trio
+.. _multi-processing: https://en.wikipedia.org/wiki/Multiprocessing
 .. _trionic: https://trio.readthedocs.io/en/latest/design.html#high-level-design-principles
 .. _async sandwich: https://trio.readthedocs.io/en/latest/tutorial.html#async-sandwich
+.. _structured concurrent: https://trio.discourse.group/t/concise-definition-of-structured-concurrency/228
 .. _3 axioms: https://www.youtube.com/watch?v=7erJ1DV_Tlo&t=162s
 .. .. _3 axioms: https://en.wikipedia.org/wiki/Actor_model#Fundamental_concepts
 .. _adherance to: https://www.youtube.com/watch?v=7erJ1DV_Tlo&t=1821s
 .. _trio gitter channel: https://gitter.im/python-trio/general
 .. _matrix channel: https://matrix.to/#/!tractor:matrix.org
-.. _pdbp: https://github.com/mdmintz/pdbp
 .. _pdb++: https://github.com/pdbpp/pdbpp
 .. _guest mode: https://trio.readthedocs.io/en/stable/reference-lowlevel.html?highlight=guest%20mode#using-guest-mode-to-run-trio-on-top-of-other-event-loops
 .. _messages: https://en.wikipedia.org/wiki/Message_passing

docs/index.rst

@@ -396,7 +396,7 @@ tasks spawned via multiple RPC calls to an actor can modify
 
 
         # a per process cache
-        _actor_cache: dict[str, bool] = {}
+        _actor_cache: Dict[str, bool] = {}
 
 
         def ping_endpoints(endpoints: List[str]):

examples/advanced_faults/ipc_failure_during_stream.py

@@ -1,151 +0,0 @@
-'''
-Complex edge case where during real-time streaming the IPC tranport
-channels are wiped out (purposely in this example though it could have
-been an outage) and we want to ensure that despite being in debug mode
-(or not) the user can sent SIGINT once they notice the hang and the
-actor tree will eventually be cancelled without leaving any zombies.
-
-'''
-import trio
-from tractor import (
-    open_nursery,
-    context,
-    Context,
-    MsgStream,
-)
-
-
-async def break_channel_silently_then_error(
-    stream: MsgStream,
-):
-    async for msg in stream:
-        await stream.send(msg)
-
-        # 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.
-        await stream._ctx.chan.send(None)
-        assert 0
-
-
-async def close_stream_and_error(
-    stream: MsgStream,
-):
-    async for msg in stream:
-        await stream.send(msg)
-
-        # wipe out channel right before raising
-        await stream._ctx.chan.send(None)
-        await stream.aclose()
-        assert 0
-
-
-@context
-async def recv_and_spawn_net_killers(
-
-    ctx: Context,
-    break_ipc_after: bool | int = False,
-
-) -> None:
-    '''
-    Receive stream msgs and spawn some IPC killers mid-stream.
-
-    '''
-    await ctx.started()
-    async with (
-        ctx.open_stream() as stream,
-        trio.open_nursery() as n,
-    ):
-        async for i in stream:
-            print(f'child echoing {i}')
-            await stream.send(i)
-            if (
-                break_ipc_after
-                and i > break_ipc_after
-            ):
-                '#################################\n'
-                'Simulating child-side IPC BREAK!\n'
-                '#################################'
-                n.start_soon(break_channel_silently_then_error, stream)
-                n.start_soon(close_stream_and_error, stream)
-
-
-async def main(
-    debug_mode: bool = False,
-    start_method: str = 'trio',
-
-    # 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_child_ipc_after: int | bool = False,
-
-) -> None:
-
-    async with (
-        open_nursery(
-            start_method=start_method,
-
-            # 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',
-
-        ) as an,
-    ):
-        portal = await an.start_actor(
-            'chitty_hijo',
-            enable_modules=[__name__],
-        )
-
-        async with portal.open_context(
-            recv_and_spawn_net_killers,
-            break_ipc_after=break_child_ipc_after,
-
-        ) as (ctx, sent):
-            async with ctx.open_stream() as stream:
-                for i in range(1000):
-
-                    if (
-                        break_parent_ipc_after
-                        and i > break_parent_ipc_after
-                    ):
-                        print(
-                            '#################################\n'
-                            'Simulating parent-side IPC BREAK!\n'
-                            '#################################'
-                        )
-                        await stream._ctx.chan.send(None)
-
-                    # 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)
-
-                    with trio.move_on_after(2) as cs:
-
-                        # 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()
-
-                        print(f"I'm a happy user and echoed to me is {rx}")
-
-                    if cs.cancelled_caught:
-                        # 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__':
-    trio.run(main)

examples/debugging/multi_daemon_subactors.py

@@ -27,18 +27,7 @@ async def main():
 
         # retreive results
         async with p0.open_stream_from(breakpoint_forever) as stream:
-
+            await p1.run(name_error)
-            # triggers the first name error
-            try:
-                await p1.run(name_error)
-            except tractor.RemoteActorError as rae:
-                assert rae.type is NameError
-
-            async for i in stream:
-
-                # a second time try the failing subactor and this tie
-                # let error propagate up to the parent/nursery.
-                await p1.run(name_error)
 
 
 if __name__ == '__main__':

examples/debugging/multi_nested_subactors_error_up_through_nurseries.py

@@ -12,31 +12,18 @@ async def breakpoint_forever():
     while True:
         await tractor.breakpoint()
 
-        # NOTE: if the test never sent 'q'/'quit' commands
-        # on the pdb repl, without this checkpoint line the
-        # repl would spin in this actor forever.
-        # await trio.sleep(0)
-
 
 async def spawn_until(depth=0):
     """"A nested nursery that triggers another ``NameError``.
     """
     async with tractor.open_nursery() as n:
         if depth < 1:
-
+            # await n.run_in_actor('breakpoint_forever', breakpoint_forever)
-            await n.run_in_actor(breakpoint_forever)
+            await n.run_in_actor(
-
-            p = await n.run_in_actor(
                 name_error,
                 name='name_error'
             )
-            await trio.sleep(0.5)
-            # rx and propagate error from child
-            await p.result()
-
         else:
-            # recusrive call to spawn another process branching layer of
-            # the tree
             depth -= 1
             await n.run_in_actor(
                 spawn_until,
@@ -66,7 +53,6 @@ async def main():
     """
     async with tractor.open_nursery(
         debug_mode=True,
-        # loglevel='cancel',
     ) as n:
 
         # spawn both actors
@@ -81,16 +67,8 @@ async def main():
             name='spawner1',
         )
 
-        # TODO: test this case as well where the parent don't see
-        # the sub-actor errors by default and instead expect a user
-        # ctrl-c to kill the root.
-        with trio.move_on_after(3):
-            await trio.sleep_forever()
-
         # gah still an issue here.
         await portal.result()
-
-        # should never get here
         await portal1.result()
 
 

examples/debugging/open_ctx_modnofound.py

@@ -1,40 +0,0 @@
-import trio
-import tractor
-
-
-@tractor.context
-async def just_sleep(
-
-    ctx: tractor.Context,
-    **kwargs,
-
-) -> None:
-    '''
-    Start and sleep.
-
-    '''
-    await ctx.started()
-    await trio.sleep_forever()
-
-
-async def main() -> None:
-
-    async with tractor.open_nursery(
-        debug_mode=True,
-    ) as n:
-        portal = await n.start_actor(
-            'ctx_child',
-
-            # XXX: we don't enable the current module in order
-            # to trigger `ModuleNotFound`.
-            enable_modules=[],
-        )
-
-        async with portal.open_context(
-            just_sleep,  # taken from pytest parameterization
-        ) as (ctx, sent):
-            raise KeyboardInterrupt
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/debugging/restore_builtin_breakpoint.py

@@ -1,24 +0,0 @@
-import os
-import sys
-
-import trio
-import tractor
-
-
-async def main() -> None:
-    async with tractor.open_nursery(debug_mode=True) as an:
-
-        assert os.environ['PYTHONBREAKPOINT'] == 'tractor._debug._set_trace'
-
-        # TODO: an assert that verifies the hook has indeed been, hooked
-        # XD
-        assert sys.breakpointhook is not tractor._debug._set_trace
-
-        breakpoint()
-
-    # TODO: an assert that verifies the hook is unhooked..
-    assert sys.breakpointhook
-    breakpoint()
-
-if __name__ == '__main__':
-    trio.run(main)

examples/infected_asyncio_echo_server.py

@@ -13,7 +13,6 @@ import tractor
 async def aio_echo_server(
     to_trio: trio.MemorySendChannel,
     from_trio: asyncio.Queue,
-
 ) -> None:
 
     # a first message must be sent **from** this ``asyncio``

examples/integration/open_context_and_sleep.py

@@ -1,49 +0,0 @@
-import trio
-import click
-import tractor
-import pydantic
-# from multiprocessing import shared_memory
-
-
-@tractor.context
-async def just_sleep(
-
-    ctx: tractor.Context,
-    **kwargs,
-
-) -> None:
-    '''
-    Test a small ping-pong 2-way streaming server.
-
-    '''
-    await ctx.started()
-    await trio.sleep_forever()
-
-
-async def main() -> None:
-
-    proc = await trio.open_process( (
-        'python',
-        '-c',
-        'import trio; trio.run(trio.sleep_forever)',
-    ))
-    await proc.wait()
-    # await trio.sleep_forever()
-    # async with tractor.open_nursery() as n:
-
-    #     portal = await n.start_actor(
-    #         'rpc_server',
-    #         enable_modules=[__name__],
-    #     )
-
-    #     async with portal.open_context(
-    #         just_sleep,  # taken from pytest parameterization
-    #     ) as (ctx, sent):
-    #         await trio.sleep_forever()
-
-
-
-if __name__ == '__main__':
-    import time
-    # time.sleep(999)
-    trio.run(main)

examples/parallelism/concurrent_actors_primes.py

@@ -9,7 +9,7 @@ is ``tractor``'s channels.
 
 """
 from contextlib import asynccontextmanager
-from typing import Callable
+from typing import List, Callable
 import itertools
 import math
 import time
@@ -71,8 +71,8 @@ async def worker_pool(workers=4):
 
         async def _map(
             worker_func: Callable[[int], bool],
-            sequence: list[int]
+            sequence: List[int]
-        ) -> list[bool]:
+        ) -> List[bool]:
 
             # define an async (local) task to collect results from workers
             async def send_result(func, value, portal):

nooz/248.misc.rst

@@ -0,0 +1,8 @@
+Adjust the `tractor._spawn.soft_wait()` strategy to avoid sending an
+actor cancel request (via `Portal.cancel_actor()`) if either the child
+process is detected as having terminated or the IPC channel is detected
+to be closed.
+
+This ensures (even) more deterministic inter-actor cancellation by
+avoiding the timeout condition where possible when a whild never
+sucessfully spawned, crashed, or became un-contactable over IPC.

nooz/295.misc.rst

@@ -0,0 +1,3 @@
+Add an experimental `tractor.msg.NamespacePath` type for passing Python
+objects by "reference" through a ``str``-subtype message and using the
+new ``pkgutil.resolve_name()`` for reference loading.

nooz/298.misc.rst

@@ -0,0 +1,2 @@
+Add a new `tractor.experimental` subpackage for staging new high level
+APIs and subystems that we might eventually make built-ins.

nooz/300.misc.rst

@@ -0,0 +1,3 @@
+Update to and pin latest `msgpack` (1.0.3) and `msgspec` (0.4.0)
+both of which required adjustments for backwards imcompatible API
+tweaks.

nooz/322.trivial.rst

@@ -1,16 +0,0 @@
-Strictly support Python 3.10+, start runtime machinery reorg
-
-Since we want to push forward using the new `match:` syntax for our
-internal RPC-msg loops, we officially drop 3.9 support for the next
-release which should coincide well with the first release of 3.11.
-
-This patch set also officially removes the ``tractor.run()`` API (which
-has been deprecated for some time) as well as starts an initial re-org
-of the internal runtime core by:
-- renaming ``tractor._actor`` -> ``._runtime``
-- moving the ``._runtime.ActorActor._process_messages()`` and
-  ``._async_main()`` to be module level singleton-task-functions since
-  they are only started once for each connection and actor spawn
-  respectively; this internal API thus looks more similar to (at the
-  time of writing) the ``trio``-internals in ``trio._core._run``.
-- officially remove ``tractor.run()``, now deprecated for some time.

nooz/324.bugfix.rst

@@ -1,4 +0,0 @@
-Only set `._debug.Lock.local_pdb_complete` if has been created.
-
-This can be triggered by a very rare race condition (and thus we have no
-working test yet) but it is known to exist in (a) consumer project(s).

nooz/333.feature.rst

@@ -1,25 +0,0 @@
-Add support for ``trio >= 0.22`` and support for the new Python 3.11
-``[Base]ExceptionGroup`` from `pep 654`_ via the backported
-`exceptiongroup`_ package and some final fixes to the debug mode
-subsystem.
-
-This port ended up driving some (hopefully) final fixes to our debugger
-subsystem including the solution to all lingering stdstreams locking
-race-conditions and deadlock scenarios. This includes extending the
-debugger tests suite as well as cancellation and ``asyncio`` mode cases.
-Some of the notable details:
-
-- always reverting to the ``trio`` SIGINT handler when leaving debug
-  mode.
-- bypassing child attempts to acquire the debug lock when detected
-  to be amdist actor-runtime-cancellation.
-- allowing the root actor to cancel local but IPC-stale subactor
-  requests-tasks for the debug lock when in a "no IPC peers" state.
-
-Further we refined our ``ActorNursery`` semantics to be more similar to
-``trio`` in the sense that parent task errors are always packed into the
-actor-nursery emitted exception group and adjusted all tests and
-examples accordingly.
-
-.. _pep 654: https://peps.python.org/pep-0654/#handling-exception-groups
-.. _exceptiongroup: https://github.com/python-trio/exceptiongroup

nooz/335.trivial.rst

@@ -1,5 +0,0 @@
-Establish an explicit "backend spawning" method table; use it from CI
-
-More clearly lays out the current set of (3) backends: ``['trio',
-'mp_spawn', 'mp_forkserver']`` and adjusts the ``._spawn.py`` internals
-as well as the test suite to accommodate.

nooz/336.trivial.rst

@@ -1,4 +0,0 @@
-Add ``key: Callable[..., Hashable]`` support to ``.trionics.maybe_open_context()``
-
-Gives users finer grained control over cache hit behaviour using
-a callable which receives the input ``kwargs: dict``.

nooz/337.feature.rst

@@ -1,41 +0,0 @@
-Add support for debug-lock blocking using a ``._debug.Lock._blocked:
-set[tuple]`` and add ids when no-more IPC connections with the
-root actor are detected.
-
-This is an enhancement which (mostly) solves a lingering debugger
-locking race case we needed to handle:
-
-- child crashes acquires TTY lock in root and attaches to ``pdb``
-- child IPC goes down such that all channels to the root are broken
-  / non-functional.
-- root is stuck thinking the child is still in debug even though it
-  can't be contacted and the child actor machinery hasn't been
-  cancelled by its parent.
-- root get's stuck in deadlock with child since it won't send a cancel
-  request until the child is finished debugging (to avoid clobbering
-  a child that is actually using the debugger), but the child can't
-  unlock the debugger bc IPC is down and it can't contact the root.
-
-To avoid this scenario add debug lock blocking list via
-`._debug.Lock._blocked: set[tuple]` which holds actor uids for any actor
-that is detected by the root as having no transport channel connections
-(of which at least one should exist if this sub-actor at some point
-acquired the debug lock). The root consequently checks this list for any
-actor that tries to (re)acquire the lock and blocks with
-a ``ContextCancelled``. Further, when a debug condition is tested in
-``._runtime._invoke``, the context's ``._enter_debugger_on_cancel`` is
-set to `False` if the actor was put on the block list then all
-post-mortem / crash handling will be bypassed for that task.
-
-In theory this approach to block list management may cause problems
-where some nested child actor acquires and releases the lock multiple
-times and it gets stuck on the block list after the first use? If this
-turns out to be an issue we can try changing the strat so blocks are
-only added when the root has zero IPC peers left?
-
-Further, this adds a root-locking-task side cancel scope,
-``Lock._root_local_task_cs_in_debug``, which can be ``.cancel()``-ed by the root
-runtime when a stale lock is detected during the IPC channel testing.
-However, right now we're NOT using this since it seems to cause test
-failures likely due to causing pre-mature cancellation and maybe needs
-a bit more experimenting?

nooz/343.trivial.rst

@@ -1,19 +0,0 @@
-Rework our ``.trionics.BroadcastReceiver`` internals to avoid method
-recursion and approach a design and interface closer to ``trio``'s
-``MemoryReceiveChannel``.
-
-The details of the internal changes include:
-
-- implementing a ``BroadcastReceiver.receive_nowait()`` and using it
-  within the async ``.receive()`` thus avoiding recursion from
-  ``.receive()``.
-- failing over to an internal ``._receive_from_underlying()`` when the
-  ``_nowait()`` call raises ``trio.WouldBlock``
-- adding ``BroadcastState.statistics()`` for debugging and testing both
-  internals and by users.
-- add an internal ``BroadcastReceiver._raise_on_lag: bool`` which can be
-  set to avoid ``Lagged`` raising for possible use cases where a user
-  wants to choose between a [cheap or nasty
-  pattern](https://zguide.zeromq.org/docs/chapter7/#The-Cheap-or-Nasty-Pattern)
-  the the particular stream (we use this in ``piker``'s dark clearing
-  engine to avoid fast feeds breaking during HFT periods).

nooz/344.bugfix.rst

@@ -1,11 +0,0 @@
-Always ``list``-cast the ``mngrs`` input to
-``.trionics.gather_contexts()`` and ensure its size otherwise raise
-a ``ValueError``.
-
-Turns out that trying to pass an inline-style generator comprehension
-doesn't seem to work inside the ``async with`` expression? Further, in
-such a case we can get a hang waiting on the all-entered event
-completion when the internal mngrs iteration is a noop. Instead we
-always greedily check a size and error on empty input; the lazy
-iteration of a generator input is not beneficial anyway since we're
-entering all manager instances in concurrent tasks.

nooz/346.bugfix.rst

@@ -1,15 +0,0 @@
-Fixes to ensure IPC (channel) breakage doesn't result in hung actor
-trees; the zombie reaping and general supervision machinery will always
-clean up and terminate.
-
-This includes not only the (mostly minor) fixes to solve these cases but
-also a new extensive test suite in `test_advanced_faults.py` with an
-accompanying highly configurable example module-script in
-`examples/advanced_faults/ipc_failure_during_stream.py`. Tests ensure we
-never get hang or zombies despite operating in debug mode and attempt to
-simulate all possible IPC transport failure cases for a local-host actor
-tree.
-
-Further we simplify `Context.open_stream.__aexit__()` to just call
-`MsgStream.aclose()` directly more or less avoiding a pure duplicate
-code path.

nooz/349.trivial.rst

@@ -1,10 +0,0 @@
-Always redraw the `pdbpp` prompt on `SIGINT` during REPL use.
-
-There was recent changes todo with Python 3.10 that required us to pin
-to a specific commit in `pdbpp` which have recently been fixed minus
-this last issue with `SIGINT` shielding: not clobbering or not
-showing the `(Pdb++)` prompt on ctlr-c by the user. This repairs all
-that by firstly removing the standard KBI intercepting of the std lib's
-`pdb.Pdb._cmdloop()` as well as ensuring that only the actor with REPL
-control ever reports `SIGINT` handler log msgs and prompt redraws. With
-this we move back to using pypi `pdbpp` release.

nooz/356.trivial.rst

@@ -1,7 +0,0 @@
-Drop `trio.Process.aclose()` usage, copy into our spawning code.
-
-The details are laid out in https://github.com/goodboy/tractor/issues/330.
-`trio` changed is process running quite some time ago, this just copies
-out the small bit we needed (from the old `.aclose()`) for hard kills
-where a soft runtime cancel request fails and our "zombie killer"
-implementation kicks in.

nooz/358.feature.rst

@@ -1,15 +0,0 @@
-Switch to using the fork & fix of `pdb++`, `pdbp`:
-https://github.com/mdmintz/pdbp
-
-Allows us to sidestep a variety of issues that aren't being maintained
-in the upstream project thanks to the hard work of @mdmintz!
-
-We also include some default settings adjustments as per recent
-development on the fork:
-
-- sticky mode is still turned on by default but now activates when
-  a using the `ll` repl command.
-- turn off line truncation by default to avoid inter-line gaps when
-  resizing the terimnal during use.
-- when using the backtrace cmd either by `w` or `bt`, the config
-  automatically switches to non-sticky mode.

pyproject.toml

@@ -1,28 +0,0 @@
-[tool.towncrier]
-package = "tractor"
-filename = "NEWS.rst"
-directory = "nooz/"
-version = "0.1.0a6"
-title_format = "tractor {version} ({project_date})"
-template = "nooz/_template.rst"
-all_bullets = true
-
-  [[tool.towncrier.type]]
-  directory = "feature"
-  name = "Features"
-  showcontent = true
-
-  [[tool.towncrier.type]]
-  directory = "bugfix"
-  name = "Bug Fixes"
-  showcontent = true
-
-  [[tool.towncrier.type]]
-  directory = "doc"
-  name = "Improved Documentation"
-  showcontent = true
-
-  [[tool.towncrier.type]]
-  directory = "trivial"
-  name = "Trivial/Internal Changes"
-  showcontent = true

requirements-test.txt

@@ -1,8 +1,7 @@
 pytest
 pytest-trio
-pytest-timeout
+pdbpp
-pdbp
+mypy<0.920
-mypy
+trio_typing<0.7.0
-trio_typing
 pexpect
 towncrier

setup.py

@@ -1,22 +1,21 @@
 #!/usr/bin/env python
 #
-# tractor: structured concurrent "actors".
+# tractor: a trionic actor model built on `multiprocessing` and `trio`
 #
-# Copyright 2018-eternity Tyler Goodlet.
+# Copyright (C) 2018-2020  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
+# it under the terms of the GNU 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.
+# GNU 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/>.
 
+# You should have received a copy of the GNU General Public License
+# along with this program.  If not, see <http://www.gnu.org/licenses/>.
 from setuptools import setup
 
 with open('docs/README.rst', encoding='utf-8') as f:
@@ -25,62 +24,55 @@ with open('docs/README.rst', encoding='utf-8') as f:
 
 setup(
     name="tractor",
-    version='0.1.0a6dev0',  # alpha zone
+    version='0.1.0a5.dev',  # alpha zone
-    description='structured concurrrent `trio`-"actors"',
+    description='structured concurrrent "actors"',
     long_description=readme,
-    license='AGPLv3',
+    license='GPLv3',
     author='Tyler Goodlet',
     maintainer='Tyler Goodlet',
-    maintainer_email='goodboy_foss@protonmail.com',
+    maintainer_email='jgbt@protonmail.com',
     url='https://github.com/goodboy/tractor',
     platforms=['linux', 'windows'],
     packages=[
         'tractor',
         'tractor.experimental',
         'tractor.trionics',
+        'tractor.testing',
     ],
     install_requires=[
 
         # trio related
-        # proper range spec:
+        'trio>0.8',
-        # https://packaging.python.org/en/latest/discussions/install-requires-vs-requirements/#id5
-        'trio >= 0.22',
         'async_generator',
         'trio_typing',
-        'exceptiongroup',
 
         # tooling
         'tricycle',
         'trio_typing',
+
+        # tooling
         'colorlog',
         'wrapt',
+        'pdbpp',
 
-        # IPC serialization
+        # serialization
-        'msgspec',
+        'msgpack>=1.0.3',
-
-        # debug mode REPL
-        'pdbp',
-
-        # pip ref docs on these specs:
-        # https://pip.pypa.io/en/stable/reference/requirement-specifiers/#examples
-        # and pep:
-        # https://peps.python.org/pep-0440/#version-specifiers
-
-        # windows deps workaround for ``pdbpp``
-        # https://github.com/pdbpp/pdbpp/issues/498
-        # https://github.com/pdbpp/fancycompleter/issues/37
-        'pyreadline3 ; platform_system == "Windows"',
 
     ],
+    extras_require={
+
+        # serialization
+        'msgspec': ['msgspec >= "0.4.0"'],
+
+    },
     tests_require=['pytest'],
-    python_requires=">=3.10",
+    python_requires=">=3.9",
     keywords=[
         'trio',
-        'async',
+        "async",
-        'concurrency',
+        "concurrency",
-        'structured concurrency',
+        "actor model",
-        'actor model',
+        "distributed",
-        'distributed',
         'multiprocessing'
     ],
     classifiers=[
@@ -88,10 +80,11 @@ setup(
         "Operating System :: POSIX :: Linux",
         "Operating System :: Microsoft :: Windows",
         "Framework :: Trio",
-        "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
+        "License :: OSI Approved :: GNU General Public License v3 or later (GPLv3+)",
         "Programming Language :: Python :: Implementation :: CPython",
         "Programming Language :: Python :: 3 :: Only",
-        "Programming Language :: Python :: 3.10",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
         "Intended Audience :: Science/Research",
         "Intended Audience :: Developers",
         "Topic :: System :: Distributed Computing",

tests/conftest.py

@@ -7,91 +7,16 @@ 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
 
+# export for tests
+from tractor.testing import tractor_test  # noqa
+
+
 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)
 
 
@@ -114,21 +39,14 @@ no_windows = pytest.mark.skipif(
 )
 
 
-def repodir() -> pathlib.Path:
+def repodir():
-    '''
+    """Return the abspath to the repo directory.
-    Return the abspath to the repo directory.
+    """
-
+    dirname = os.path.dirname
-    '''
+    dirpath = os.path.abspath(
-    # 2 parents up to step up through tests/<repo_dir>
+        dirname(dirname(os.path.realpath(__file__)))
-    return pathlib.Path(__file__).parent.parent.absolute()
+        )
-
+    return dirpath
-
-def examples_dir() -> pathlib.Path:
-    '''
-    Return the abspath to the examples directory as `pathlib.Path`.
-
-    '''
-    return repodir() / 'examples'
 
 
 def pytest_addoption(parser):
@@ -146,7 +64,11 @@ def pytest_addoption(parser):
 
 def pytest_configure(config):
     backend = config.option.spawn_backend
-    tractor._spawn.try_set_start_method(backend)
+
+    if backend == 'mp':
+        tractor._spawn.try_set_start_method('spawn')
+    elif backend == 'trio':
+        tractor._spawn.try_set_start_method(backend)
 
 
 @pytest.fixture(scope='session', autouse=True)
@@ -159,18 +81,15 @@ def loglevel(request):
 
 
 @pytest.fixture(scope='session')
-def spawn_backend(request) -> str:
+def spawn_backend(request):
     return request.config.option.spawn_backend
 
 
-_ci_env: bool = os.environ.get('CI', False)
-
-
 @pytest.fixture(scope='session')
 def ci_env() -> bool:
     """Detect CI envoirment.
     """
-    return _ci_env
+    return os.environ.get('TRAVIS', False) or os.environ.get('CI', False)
 
 
 @pytest.fixture(scope='session')
@@ -180,24 +99,24 @@ def arb_addr():
 
 def pytest_generate_tests(metafunc):
     spawn_backend = metafunc.config.option.spawn_backend
-
     if not spawn_backend:
         # XXX some weird windows bug with `pytest`?
-        spawn_backend = 'trio'
+        spawn_backend = 'mp'
+    assert spawn_backend in ('mp', 'trio')
 
-    # TODO: maybe just use the literal `._spawn.SpawnMethodKey`?
-    assert spawn_backend in (
-        'mp_spawn',
-        'mp_forkserver',
-        'trio',
-    )
-
-    # NOTE: used to be used to dyanmically parametrize tests for when
-    # you just passed --spawn-backend=`mp` on the cli, but now we expect
-    # that cli input to be manually specified, BUT, maybe we'll do
-    # something like this again in the future?
     if 'start_method' in metafunc.fixturenames:
-        metafunc.parametrize("start_method", [spawn_backend], scope='module')
+        if spawn_backend == 'mp':
+            from multiprocessing import get_all_start_methods
+            methods = get_all_start_methods()
+            if 'fork' in methods:
+                # fork not available on windows, so check before
+                # removing XXX: the fork method is in general
+                # incompatible with trio's global scheduler state
+                methods.remove('fork')
+        elif spawn_backend == 'trio':
+            methods = ['trio']
+
+        metafunc.parametrize("start_method", methods, scope='module')
 
 
 def sig_prog(proc, sig):
@@ -213,22 +132,16 @@ def sig_prog(proc, sig):
 
 
 @pytest.fixture
-def daemon(
+def daemon(loglevel, testdir, arb_addr):
-    loglevel: str,
+    """Run a daemon actor as a "remote arbiter".
-    testdir,
+    """
-    arb_addr: tuple[str, int],
-):
-    '''
-    Run a daemon actor as a "remote arbiter".
-
-    '''
     if loglevel in ('trace', 'debug'):
         # too much logging will lock up the subproc (smh)
         loglevel = 'info'
 
     cmdargs = [
         sys.executable, '-c',
-        "import tractor; tractor.run_daemon([], registry_addr={}, loglevel={})"
+        "import tractor; tractor.run_daemon([], arbiter_addr={}, loglevel={})"
         .format(
             arb_addr,
             "'{}'".format(loglevel) if loglevel else None)

tests/test_advanced_faults.py

@@ -1,193 +0,0 @@
-'''
-Sketchy network blackoutz, ugly byzantine gens, puedes eschuchar la
-cancelacion?..
-
-'''
-from functools import partial
-
-import pytest
-from _pytest.pathlib import import_path
-import trio
-import tractor
-
-from conftest import (
-    examples_dir,
-)
-
-
-@pytest.mark.parametrize(
-    'debug_mode',
-    [False, True],
-    ids=['no_debug_mode', 'debug_mode'],
-)
-@pytest.mark.parametrize(
-    'ipc_break',
-    [
-        # no breaks
-        {
-            'break_parent_ipc_after': False,
-            'break_child_ipc_after': False,
-        },
-
-        # only parent breaks
-        {
-            'break_parent_ipc_after': 500,
-            'break_child_ipc_after': False,
-        },
-
-        # only child breaks
-        {
-            'break_parent_ipc_after': False,
-            'break_child_ipc_after': 500,
-        },
-
-        # both: break parent first
-        {
-            'break_parent_ipc_after': 500,
-            'break_child_ipc_after': 800,
-        },
-        # both: break child first
-        {
-            'break_parent_ipc_after': 800,
-            'break_child_ipc_after': 500,
-        },
-
-    ],
-    ids=[
-        'no_break',
-        'break_parent',
-        'break_child',
-        'break_both_parent_first',
-        'break_both_child_first',
-    ],
-)
-def test_ipc_channel_break_during_stream(
-    debug_mode: bool,
-    spawn_backend: str,
-    ipc_break: dict | None,
-):
-    '''
-    Ensure we can have an IPC channel break its connection during
-    streaming and it's still possible for the (simulated) user to kill
-    the actor tree using SIGINT.
-
-    We also verify the type of connection error expected in the parent
-    depending on which side if the IPC breaks first.
-
-    '''
-    if spawn_backend != 'trio':
-        if debug_mode:
-            pytest.skip('`debug_mode` only supported on `trio` spawner')
-
-        # non-`trio` spawners should never hit the hang condition that
-        # requires the user to do ctl-c to cancel the actor tree.
-        expect_final_exc = trio.ClosedResourceError
-
-    mod = import_path(
-        examples_dir() / 'advanced_faults' / 'ipc_failure_during_stream.py',
-        root=examples_dir(),
-    )
-
-    expect_final_exc = KeyboardInterrupt
-
-    # when ONLY the child breaks we expect the parent to get a closed
-    # resource error on the next `MsgStream.receive()` and then fail out
-    # and cancel the child from there.
-    if (
-
-        # only child breaks
-        (
-            ipc_break['break_child_ipc_after']
-            and ipc_break['break_parent_ipc_after'] is False
-        )
-
-        # both break but, parent breaks first
-        or (
-            ipc_break['break_child_ipc_after'] is not False
-            and (
-                ipc_break['break_parent_ipc_after']
-                > ipc_break['break_child_ipc_after']
-            )
-        )
-
-    ):
-        expect_final_exc = trio.ClosedResourceError
-
-    # when the parent IPC side dies (even if the child's does as well
-    # 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']
-            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
-
-    with pytest.raises(expect_final_exc):
-        trio.run(
-            partial(
-                mod.main,
-                debug_mode=debug_mode,
-                start_method=spawn_backend,
-                **ipc_break,
-            )
-        )
-
-
-@tractor.context
-async def break_ipc_after_started(
-    ctx: tractor.Context,
-) -> None:
-    await ctx.started()
-    async with ctx.open_stream() as stream:
-        await stream.aclose()
-        await trio.sleep(0.2)
-        await ctx.chan.send(None)
-        print('child broke IPC and terminating')
-
-
-def test_stream_closed_right_after_ipc_break_and_zombie_lord_engages():
-    '''
-    Verify that is a subactor's IPC goes down just after bringing up a stream
-    the parent can trigger a SIGINT and the child will be reaped out-of-IPC by
-    the localhost process supervision machinery: aka "zombie lord".
-
-    '''
-    async def main():
-        async with tractor.open_nursery() as n:
-            portal = await n.start_actor(
-                'ipc_breaker',
-                enable_modules=[__name__],
-            )
-
-            with trio.move_on_after(1):
-                async with (
-                    portal.open_context(
-                        break_ipc_after_started
-                    ) as (ctx, sent),
-                ):
-                    async with ctx.open_stream():
-                        await trio.sleep(0.5)
-
-                    print('parent waiting on context')
-
-            print('parent exited context')
-            raise KeyboardInterrupt
-
-    with pytest.raises(KeyboardInterrupt):
-        trio.run(main)

tests/test_advanced_streaming.py

@@ -5,6 +5,7 @@ Advanced streaming patterns using bidirectional streams and contexts.
 from collections import Counter
 import itertools
 import platform
+from typing import Set, Dict, List
 
 import trio
 import tractor
@@ -14,7 +15,7 @@ def is_win():
     return platform.system() == 'Windows'
 
 
-_registry: dict[str, set[tractor.MsgStream]] = {
+_registry: Dict[str, Set[tractor.ReceiveMsgStream]] = {
     'even': set(),
     'odd': set(),
 }
@@ -76,7 +77,7 @@ async def subscribe(
 
 async def consumer(
 
-    subs: list[str],
+    subs: List[str],
 
 ) -> None:
 

tests/test_cancellation.py

@@ -8,10 +8,6 @@ import platform
 import time
 from itertools import repeat
 
-from exceptiongroup import (
-    BaseExceptionGroup,
-    ExceptionGroup,
-)
 import pytest
 import trio
 import tractor
@@ -60,49 +56,29 @@ def test_remote_error(arb_addr, args_err):
             arbiter_addr=arb_addr,
         ) as nursery:
 
-            # on a remote type error caused by bad input args
-            # this should raise directly which means we **don't** get
-            # 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
             )
 
             # get result(s) from main task
             try:
-                # this means the root actor will also raise a local
-                # parent task error and thus an eg will propagate out
-                # of this actor nursery.
                 await portal.result()
             except tractor.RemoteActorError as err:
                 assert err.type == errtype
                 print("Look Maa that actor failed hard, hehh")
                 raise
 
-    # ensure boxed errors
+    with pytest.raises(tractor.RemoteActorError) as excinfo:
-    if args:
+        trio.run(main)
-        with pytest.raises(tractor.RemoteActorError) as excinfo:
-            trio.run(main)
 
-        assert excinfo.value.type == errtype
+    # ensure boxed error is correct
-
+    assert excinfo.value.type == errtype
-    else:
-        # the root task will also error on the `.result()` call
-        # so we expect an error from there AND the child.
-        with pytest.raises(BaseExceptionGroup) as excinfo:
-            trio.run(main)
-
-        # ensure boxed errors
-        for exc in excinfo.value.exceptions:
-            assert exc.type == errtype
 
 
 def test_multierror(arb_addr):
-    '''
+    """Verify we raise a ``trio.MultiError`` out of a nursery where
-    Verify we raise a ``BaseExceptionGroup`` out of a nursery where
     more then one actor errors.
-
+    """
-    '''
     async def main():
         async with tractor.open_nursery(
             arbiter_addr=arb_addr,
@@ -119,10 +95,10 @@ def test_multierror(arb_addr):
                 print("Look Maa that first actor failed hard, hehh")
                 raise
 
-        # here we should get a ``BaseExceptionGroup`` containing exceptions
+        # here we should get a `trio.MultiError` containing exceptions
         # from both subactors
 
-    with pytest.raises(BaseExceptionGroup):
+    with pytest.raises(trio.MultiError):
         trio.run(main)
 
 
@@ -131,7 +107,7 @@ def test_multierror(arb_addr):
     'num_subactors', range(25, 26),
 )
 def test_multierror_fast_nursery(arb_addr, start_method, num_subactors, delay):
-    """Verify we raise a ``BaseExceptionGroup`` out of a nursery where
+    """Verify we raise a ``trio.MultiError`` out of a nursery where
     more then one actor errors and also with a delay before failure
     to test failure during an ongoing spawning.
     """
@@ -147,11 +123,10 @@ def test_multierror_fast_nursery(arb_addr, start_method, num_subactors, delay):
                     delay=delay
                 )
 
-    # with pytest.raises(trio.MultiError) as exc_info:
+    with pytest.raises(trio.MultiError) as exc_info:
-    with pytest.raises(BaseExceptionGroup) as exc_info:
         trio.run(main)
 
-    assert exc_info.type == ExceptionGroup
+    assert exc_info.type == tractor.MultiError
     err = exc_info.value
     exceptions = err.exceptions
 
@@ -239,8 +214,8 @@ async def test_cancel_infinite_streamer(start_method):
     [
         # daemon actors sit idle while single task actors error out
         (1, tractor.RemoteActorError, AssertionError, (assert_err, {}), None),
-        (2, BaseExceptionGroup, AssertionError, (assert_err, {}), None),
+        (2, tractor.MultiError, AssertionError, (assert_err, {}), None),
-        (3, BaseExceptionGroup, AssertionError, (assert_err, {}), None),
+        (3, tractor.MultiError, AssertionError, (assert_err, {}), None),
 
         # 1 daemon actor errors out while single task actors sleep forever
         (3, tractor.RemoteActorError, AssertionError, (sleep_forever, {}),
@@ -251,7 +226,7 @@ async def test_cancel_infinite_streamer(start_method):
          (do_nuthin, {}), (assert_err, {'delay': 1}, True)),
         # daemon complete quickly delay while single task
         # actors error after brief delay
-        (3, BaseExceptionGroup, AssertionError,
+        (3, tractor.MultiError, AssertionError,
          (assert_err, {'delay': 1}), (do_nuthin, {}, False)),
     ],
     ids=[
@@ -318,7 +293,7 @@ async def test_some_cancels_all(num_actors_and_errs, start_method, loglevel):
         # should error here with a ``RemoteActorError`` or ``MultiError``
 
     except first_err as err:
-        if isinstance(err, BaseExceptionGroup):
+        if isinstance(err, tractor.MultiError):
             assert len(err.exceptions) == num_actors
             for exc in err.exceptions:
                 if isinstance(exc, tractor.RemoteActorError):
@@ -362,7 +337,7 @@ async def spawn_and_error(breadth, depth) -> None:
 @tractor_test
 async def test_nested_multierrors(loglevel, start_method):
     '''
-    Test that failed actor sets are wrapped in `BaseExceptionGroup`s. This
+    Test that failed actor sets are wrapped in `trio.MultiError`s. This
     test goes only 2 nurseries deep but we should eventually have tests
     for arbitrary n-depth actor trees.
 
@@ -390,7 +365,7 @@ async def test_nested_multierrors(loglevel, start_method):
                         breadth=subactor_breadth,
                         depth=depth,
                     )
-        except BaseExceptionGroup as err:
+        except trio.MultiError as err:
             assert len(err.exceptions) == subactor_breadth
             for subexc in err.exceptions:
 
@@ -408,10 +383,10 @@ async def test_nested_multierrors(loglevel, start_method):
                         assert subexc.type in (
                             tractor.RemoteActorError,
                             trio.Cancelled,
-                            BaseExceptionGroup,
+                            trio.MultiError
                         )
 
-                    elif isinstance(subexc, BaseExceptionGroup):
+                    elif isinstance(subexc, trio.MultiError):
                         for subsub in subexc.exceptions:
 
                             if subsub in (tractor.RemoteActorError,):
@@ -419,7 +394,7 @@ async def test_nested_multierrors(loglevel, start_method):
 
                             assert type(subsub) in (
                                 trio.Cancelled,
-                                BaseExceptionGroup,
+                                trio.MultiError,
                             )
                 else:
                     assert isinstance(subexc, tractor.RemoteActorError)
@@ -431,13 +406,13 @@ async def test_nested_multierrors(loglevel, start_method):
                     if is_win():
                         if isinstance(subexc, tractor.RemoteActorError):
                             assert subexc.type in (
-                                BaseExceptionGroup,
+                                trio.MultiError,
                                 tractor.RemoteActorError
                             )
                         else:
-                            assert isinstance(subexc, BaseExceptionGroup)
+                            assert isinstance(subexc, trio.MultiError)
                     else:
-                        assert subexc.type is ExceptionGroup
+                        assert subexc.type is trio.MultiError
                 else:
                     assert subexc.type in (
                         tractor.RemoteActorError,
@@ -460,7 +435,7 @@ def test_cancel_via_SIGINT(
         with trio.fail_after(2):
             async with tractor.open_nursery() as tn:
                 await tn.start_actor('sucka')
-                if 'mp' in spawn_backend:
+                if spawn_backend == 'mp':
                     time.sleep(0.1)
                 os.kill(pid, signal.SIGINT)
                 await trio.sleep_forever()
@@ -499,7 +474,7 @@ def test_cancel_via_SIGINT_other_task(
         with trio.fail_after(timeout):
             async with trio.open_nursery() as n:
                 await n.start(spawn_and_sleep_forever)
-                if 'mp' in spawn_backend:
+                if spawn_backend == 'mp':
                     time.sleep(0.1)
                 os.kill(pid, signal.SIGINT)
 

tests/test_child_manages_service_nursery.py

@@ -1,173 +0,0 @@
-'''
-Test a service style daemon that maintains a nursery for spawning
-"remote async tasks" including both spawning other long living
-sub-sub-actor daemons.
-
-'''
-from typing import Optional
-import asyncio
-from contextlib import asynccontextmanager as acm
-
-import pytest
-import trio
-from trio_typing import TaskStatus
-import tractor
-from tractor import RemoteActorError
-from async_generator import aclosing
-
-
-async def aio_streamer(
-    from_trio: asyncio.Queue,
-    to_trio: trio.abc.SendChannel,
-) -> trio.abc.ReceiveChannel:
-
-    # required first msg to sync caller
-    to_trio.send_nowait(None)
-
-    from itertools import cycle
-    for i in cycle(range(10)):
-        to_trio.send_nowait(i)
-        await asyncio.sleep(0.01)
-
-
-async def trio_streamer():
-    from itertools import cycle
-    for i in cycle(range(10)):
-        yield i
-        await trio.sleep(0.01)
-
-
-async def trio_sleep_and_err(delay: float = 0.5):
-    await trio.sleep(delay)
-    # name error
-    doggy()  # noqa
-
-
-_cached_stream: Optional[
-    trio.abc.ReceiveChannel
-] = None
-
-
-@acm
-async def wrapper_mngr(
-):
-    from tractor.trionics import broadcast_receiver
-    global _cached_stream
-    in_aio = tractor.current_actor().is_infected_aio()
-
-    if in_aio:
-        if _cached_stream:
-
-            from_aio = _cached_stream
-
-            # if we already have a cached feed deliver a rx side clone
-            # to consumer
-            async with broadcast_receiver(from_aio, 6) as from_aio:
-                yield from_aio
-                return
-        else:
-            async with tractor.to_asyncio.open_channel_from(
-                aio_streamer,
-            ) as (first, from_aio):
-                assert not first
-
-                # cache it so next task uses broadcast receiver
-                _cached_stream = from_aio
-
-                yield from_aio
-    else:
-        async with aclosing(trio_streamer()) as stream:
-            # cache it so next task uses broadcast receiver
-            _cached_stream = stream
-            yield stream
-
-
-_nursery: trio.Nursery = None
-
-
-@tractor.context
-async def trio_main(
-    ctx: tractor.Context,
-):
-    # sync
-    await ctx.started()
-
-    # stash a "service nursery" as "actor local" (aka a Python global)
-    global _nursery
-    n = _nursery
-    assert n
-
-    async def consume_stream():
-        async with wrapper_mngr() as stream:
-            async for msg in stream:
-                print(msg)
-
-    # run 2 tasks to ensure broadcaster chan use
-    n.start_soon(consume_stream)
-    n.start_soon(consume_stream)
-
-    n.start_soon(trio_sleep_and_err)
-
-    await trio.sleep_forever()
-
-
-@tractor.context
-async def open_actor_local_nursery(
-    ctx: tractor.Context,
-):
-    global _nursery
-    async with trio.open_nursery() as n:
-        _nursery = n
-        await ctx.started()
-        await trio.sleep(10)
-        # await trio.sleep(1)
-
-        # XXX: this causes the hang since
-        # the caller does not unblock from its own
-        # ``trio.sleep_forever()``.
-
-        # TODO: we need to test a simple ctx task starting remote tasks
-        # that error and then blocking on a ``Nursery.start()`` which
-        # never yields back.. aka a scenario where the
-        # ``tractor.context`` task IS NOT in the service n's cancel
-        # scope.
-        n.cancel_scope.cancel()
-
-
-@pytest.mark.parametrize(
-    'asyncio_mode',
-    [True, False],
-    ids='asyncio_mode={}'.format,
-)
-def test_actor_managed_trio_nursery_task_error_cancels_aio(
-    asyncio_mode: bool,
-    arb_addr
-):
-    '''
-    Verify that a ``trio`` nursery created managed in a child actor
-    correctly relays errors to the parent actor when one of its spawned
-    tasks errors even when running in infected asyncio mode and using
-    broadcast receivers for multi-task-per-actor subscription.
-
-    '''
-    async def main():
-
-        # cancel the nursery shortly after boot
-        async with tractor.open_nursery() as n:
-            p = await n.start_actor(
-                'nursery_mngr',
-                infect_asyncio=asyncio_mode,
-                enable_modules=[__name__],
-            )
-            async with (
-                p.open_context(open_actor_local_nursery) as (ctx, first),
-                p.open_context(trio_main) as (ctx, first),
-            ):
-                await trio.sleep_forever()
-
-    with pytest.raises(RemoteActorError) as excinfo:
-        trio.run(main)
-
-    # verify boxed error
-    err = excinfo.value
-    assert isinstance(err.type(), NameError)

tests/test_clustering.py

@@ -1,6 +1,5 @@
 import itertools
 
-import pytest
 import trio
 import tractor
 from tractor import open_actor_cluster
@@ -12,72 +11,26 @@ from conftest import tractor_test
 MESSAGE = 'tractoring at full speed'
 
 
-def test_empty_mngrs_input_raises() -> None:
-
-    async def main():
-        with trio.fail_after(1):
-            async with (
-                open_actor_cluster(
-                    modules=[__name__],
-
-                    # NOTE: ensure we can passthrough runtime opts
-                    loglevel='info',
-                    # debug_mode=True,
-
-                ) as portals,
-
-                gather_contexts(
-                    # NOTE: it's the use of inline-generator syntax
-                    # here that causes the empty input.
-                    mngrs=(
-                        p.open_context(worker) for p in portals.values()
-                    ),
-                ),
-            ):
-                assert 0
-
-    with pytest.raises(ValueError):
-        trio.run(main)
-
-
 @tractor.context
-async def worker(
+async def worker(ctx: tractor.Context) -> None:
-    ctx: tractor.Context,
-
-) -> None:
-
     await ctx.started()
-
+    async with ctx.open_stream(backpressure=True) as stream:
-    async with ctx.open_stream(
-        backpressure=True,
-    ) as stream:
-
-        # TODO: this with the below assert causes a hang bug?
-        # with trio.move_on_after(1):
-
         async for msg in stream:
             # do something with msg
             print(msg)
             assert msg == MESSAGE
 
-        # TODO: does this ever cause a hang
-        # assert 0
-
 
 @tractor_test
 async def test_streaming_to_actor_cluster() -> None:
-
     async with (
         open_actor_cluster(modules=[__name__]) as portals,
-
         gather_contexts(
             mngrs=[p.open_context(worker) for p in portals.values()],
         ) as contexts,
-
         gather_contexts(
             mngrs=[ctx[0].open_stream() for ctx in contexts],
         ) as streams,
-
     ):
         with trio.move_on_after(1):
             for stream in itertools.cycle(streams):

tests/test_context_stream_semantics.py

@@ -265,44 +265,42 @@ async def test_callee_closes_ctx_after_stream_open():
             enable_modules=[__name__],
         )
 
-        with trio.fail_after(2):
+        async with portal.open_context(
-            async with portal.open_context(
+            close_ctx_immediately,
-                close_ctx_immediately,
 
-                # flag to avoid waiting the final result
+            # flag to avoid waiting the final result
-                # cancel_on_exit=True,
+            # cancel_on_exit=True,
 
-            ) as (ctx, sent):
+        ) as (ctx, sent):
 
-                assert sent is None
+            assert sent is None
 
-                with trio.fail_after(0.5):
+            with trio.fail_after(0.5):
-                    async with ctx.open_stream() as stream:
+                async with ctx.open_stream() as stream:
 
-                        # should fall through since ``StopAsyncIteration``
+                    # should fall through since ``StopAsyncIteration``
-                        # should be raised through translation of
+                    # should be raised through translation of
-                        # a ``trio.EndOfChannel`` by
+                    # a ``trio.EndOfChannel`` by
-                        # ``trio.abc.ReceiveChannel.__anext__()``
+                    # ``trio.abc.ReceiveChannel.__anext__()``
-                        async for _ in stream:
+                    async for _ in stream:
-                            assert 0
+                        assert 0
-                        else:
+                    else:
 
-                            # verify stream is now closed
+                        # verify stream is now closed
-                            try:
+                        try:
-                                await stream.receive()
+                            await stream.receive()
-                            except trio.EndOfChannel:
+                        except trio.EndOfChannel:
-                                pass
-
-                # TODO: should be just raise the closed resource err
-                # directly here to enforce not allowing a re-open
-                # of a stream to the context (at least until a time of
-                # if/when we decide that's a good idea?)
-                try:
-                    with trio.fail_after(0.5):
-                        async with ctx.open_stream() as stream:
                             pass
-                except trio.ClosedResourceError:
+
+            # TODO: should be just raise the closed resource err
+            # directly here to enforce not allowing a re-open
+            # of a stream to the context (at least until a time of
+            # if/when we decide that's a good idea?)
+            try:
+                async with ctx.open_stream() as stream:
                     pass
+            except trio.ClosedResourceError:
+                pass
 
         await portal.cancel_actor()
 
@@ -571,7 +569,7 @@ def test_one_end_stream_not_opened(overrun_by):
 
     '''
     overrunner, buf_size_increase, entrypoint = overrun_by
-    from tractor._runtime import Actor
+    from tractor._actor import Actor
     buf_size = buf_size_increase + Actor.msg_buffer_size
 
     async def main():

tests/test_debugger.py

@@ -1,5 +1,5 @@
 """
-That "native" debug mode better work!
+That native debug better work!
 
 All these tests can be understood (somewhat) by running the equivalent
 `examples/debugging/` scripts manually.
@@ -10,25 +10,15 @@ TODO:
     - wonder if any of it'll work on OS X?
 
 """
-import itertools
-from os import path
-from typing import Optional
-import platform
-import pathlib
-import sys
 import time
+from os import path
+import platform
 
 import pytest
 import pexpect
-from pexpect.exceptions import (
-    TIMEOUT,
-    EOF,
-)
 
-from conftest import (
+from conftest import repodir
-    examples_dir,
+
-    _ci_env,
-)
 
 # TODO: The next great debugger audit could be done by you!
 # - recurrent entry to breakpoint() from single actor *after* and an
@@ -47,31 +37,19 @@ if platform.system() == 'Windows':
     )
 
 
+def examples_dir():
+    """Return the abspath to the examples directory.
+    """
+    return path.join(repodir(), 'examples', 'debugging/')
+
+
 def mk_cmd(ex_name: str) -> str:
-    '''
+    """Generate a command suitable to pass to ``pexpect.spawn()``.
-    Generate a command suitable to pass to ``pexpect.spawn()``.
+    """
-
+    return ' '.join(
-    '''
+        ['python',
-    script_path: pathlib.Path = examples_dir() / 'debugging' / f'{ex_name}.py'
+         path.join(examples_dir(), f'{ex_name}.py')]
-    return ' '.join(['python', str(script_path)])
+    )
-
-
-# TODO: was trying to this xfail style but some weird bug i see in CI
-# that's happening at collect time.. pretty soon gonna dump actions i'm
-# thinkin...
-# in CI we skip tests which >= depth 1 actor trees due to there
-# still being an oustanding issue with relaying the debug-mode-state
-# through intermediary parents.
-has_nested_actors = pytest.mark.has_nested_actors
-# .xfail(
-#     os.environ.get('CI', False),
-#     reason=(
-#         'This test uses nested actors and fails in CI\n'
-#         'The test seems to run fine locally but until we solve the '
-#         'following issue this CI test will be xfail:\n'
-#         'https://github.com/goodboy/tractor/issues/320'
-#     )
-# )
 
 
 @pytest.fixture
@@ -95,83 +73,6 @@ def spawn(
     return _spawn
 
 
-PROMPT = r"\(Pdb\+\)"
-
-
-def expect(
-    child,
-
-    # prompt by default
-    patt: str = PROMPT,
-
-    **kwargs,
-
-) -> None:
-    '''
-    Expect wrapper that prints last seen console
-    data before failing.
-
-    '''
-    try:
-        child.expect(
-            patt,
-            **kwargs,
-        )
-    except TIMEOUT:
-        before = str(child.before.decode())
-        print(before)
-        raise
-
-
-def assert_before(
-    child,
-    patts: list[str],
-
-) -> None:
-
-    before = str(child.before.decode())
-
-    for patt in patts:
-        try:
-            assert patt in before
-        except AssertionError:
-            print(before)
-            raise
-
-
-@pytest.fixture(
-    params=[False, True],
-    ids='ctl-c={}'.format,
-)
-def ctlc(
-    request,
-    ci_env: bool,
-
-) -> bool:
-
-    use_ctlc = request.param
-
-    node = request.node
-    markers = node.own_markers
-    for mark in markers:
-        if mark.name == 'has_nested_actors':
-            pytest.skip(
-                f'Test {node} has nested actors and fails with Ctrl-C.\n'
-                f'The test can sometimes run fine locally but until'
-                ' we solve' 'this issue this CI test will be xfail:\n'
-                'https://github.com/goodboy/tractor/issues/320'
-            )
-
-    if use_ctlc:
-        # XXX: disable pygments highlighting for auto-tests
-        # since some envs (like actions CI) will struggle
-        # the the added color-char encoding..
-        from tractor._debug import TractorConfig
-        TractorConfig.use_pygements = False
-
-    yield use_ctlc
-
-
 @pytest.mark.parametrize(
     'user_in_out',
     [
@@ -181,16 +82,14 @@ def ctlc(
     ids=lambda item: f'{item[0]} -> {item[1]}',
 )
 def test_root_actor_error(spawn, user_in_out):
-    '''
+    """Demonstrate crash handler entering pdbpp from basic error in root actor.
-    Demonstrate crash handler entering pdb from basic error in root actor.
+    """
-
-    '''
     user_input, expect_err_str = user_in_out
 
     child = spawn('root_actor_error')
 
-    # scan for the prompt
+    # scan for the pdbpp prompt
-    expect(child, PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     before = str(child.before.decode())
 
@@ -202,7 +101,7 @@ def test_root_actor_error(spawn, user_in_out):
     child.sendline(user_input)
 
     # process should exit
-    expect(child, EOF)
+    child.expect(pexpect.EOF)
     assert expect_err_str in str(child.before)
 
 
@@ -220,8 +119,8 @@ def test_root_actor_bp(spawn, user_in_out):
     user_input, expect_err_str = user_in_out
     child = spawn('root_actor_breakpoint')
 
-    # scan for the prompt
+    # scan for the pdbpp prompt
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     assert 'Error' not in str(child.before)
 
@@ -238,129 +137,56 @@ def test_root_actor_bp(spawn, user_in_out):
         assert expect_err_str in str(child.before)
 
 
-def do_ctlc(
+def test_root_actor_bp_forever(spawn):
-    child,
-    count: int = 3,
-    delay: float = 0.1,
-    patt: Optional[str] = None,
-
-    # expect repl UX to reprint the prompt after every
-    # ctrl-c send.
-    # XXX: no idea but, in CI this never seems to work even on 3.10 so
-    # needs some further investigation potentially...
-    expect_prompt: bool = not _ci_env,
-
-) -> None:
-
-    # make sure ctl-c sends don't do anything but repeat output
-    for _ in range(count):
-        time.sleep(delay)
-        child.sendcontrol('c')
-
-        # TODO: figure out why this makes CI fail..
-        # if you run this test manually it works just fine..
-        if expect_prompt:
-            before = str(child.before.decode())
-            time.sleep(delay)
-            child.expect(PROMPT)
-            time.sleep(delay)
-
-            if patt:
-                # should see the last line on console
-                assert patt in before
-
-
-def test_root_actor_bp_forever(
-    spawn,
-    ctlc: bool,
-):
     "Re-enter a breakpoint from the root actor-task."
     child = spawn('root_actor_breakpoint_forever')
 
     # do some "next" commands to demonstrate recurrent breakpoint
     # entries
     for _ in range(10):
-
-        child.expect(PROMPT)
-
-        if ctlc:
-            do_ctlc(child)
-
         child.sendline('next')
+        child.expect(r"\(Pdb\+\+\)")
 
-    # do one continue which should trigger a
+    # do one continue which should trigger a new task to lock the tty
-    # new task to lock the tty
     child.sendline('continue')
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
-
-    # seems that if we hit ctrl-c too fast the
-    # sigint guard machinery might not kick in..
-    time.sleep(0.001)
-
-    if ctlc:
-        do_ctlc(child)
 
     # XXX: this previously caused a bug!
     child.sendline('n')
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     child.sendline('n')
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
-
-    # quit out of the loop
-    child.sendline('q')
-    child.expect(pexpect.EOF)
 
 
-@pytest.mark.parametrize(
+def test_subactor_error(spawn):
-    'do_next',
+    "Single subactor raising an error"
-    (True, False),
-    ids='do_next={}'.format,
-)
-def test_subactor_error(
-    spawn,
-    ctlc: bool,
-    do_next: bool,
-):
-    '''
-    Single subactor raising an error
 
-    '''
     child = spawn('subactor_error')
 
-    # scan for the prompt
+    # scan for the pdbpp prompt
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     before = str(child.before.decode())
     assert "Attaching to pdb in crashed actor: ('name_error'" in before
 
-    if do_next:
+    # send user command
-        child.sendline('n')
+    # (in this case it's the same for 'continue' vs. 'quit')
+    child.sendline('continue')
 
-    else:
+    # the debugger should enter a second time in the nursery
-        # make sure ctl-c sends don't do anything but repeat output
+    # creating actor
-        if ctlc:
-            do_ctlc(
-                child,
-            )
 
-        # send user command and (in this case it's the same for 'continue'
+    child.expect(r"\(Pdb\+\+\)")
-        # vs. 'quit') the debugger should enter a second time in the nursery
-        # creating actor
-        child.sendline('continue')
 
-    child.expect(PROMPT)
     before = str(child.before.decode())
 
     # root actor gets debugger engaged
     assert "Attaching to pdb in crashed actor: ('root'" in before
+
     # error is a remote error propagated from the subactor
     assert "RemoteActorError: ('name_error'" in before
 
-    # another round
-    if ctlc:
-        do_ctlc(child)
-
     child.sendline('c')
     child.expect('\r\n')
 
@@ -368,16 +194,13 @@ def test_subactor_error(
     child.expect(pexpect.EOF)
 
 
-def test_subactor_breakpoint(
+def test_subactor_breakpoint(spawn):
-    spawn,
-    ctlc: bool,
-):
     "Single subactor with an infinite breakpoint loop"
 
     child = spawn('subactor_breakpoint')
 
-    # scan for the prompt
+    # scan for the pdbpp prompt
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     before = str(child.before.decode())
     assert "Attaching pdb to actor: ('breakpoint_forever'" in before
@@ -386,34 +209,25 @@ def test_subactor_breakpoint(
     # entries
     for _ in range(10):
         child.sendline('next')
-        child.expect(PROMPT)
+        child.expect(r"\(Pdb\+\+\)")
-
-        if ctlc:
-            do_ctlc(child)
 
     # now run some "continues" to show re-entries
     for _ in range(5):
         child.sendline('continue')
-        child.expect(PROMPT)
+        child.expect(r"\(Pdb\+\+\)")
         before = str(child.before.decode())
         assert "Attaching pdb to actor: ('breakpoint_forever'" in before
 
-        if ctlc:
-            do_ctlc(child)
-
     # finally quit the loop
     child.sendline('q')
 
     # child process should exit but parent will capture pdb.BdbQuit
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     before = str(child.before.decode())
     assert "RemoteActorError: ('breakpoint_forever'" in before
     assert 'bdb.BdbQuit' in before
 
-    if ctlc:
-        do_ctlc(child)
-
     # quit the parent
     child.sendline('c')
 
@@ -425,159 +239,110 @@ def test_subactor_breakpoint(
     assert 'bdb.BdbQuit' in before
 
 
-@has_nested_actors
+def test_multi_subactors(spawn):
-def test_multi_subactors(
+    """
-    spawn,
+    Multiple subactors, both erroring and breakpointing as well as
-    ctlc: bool,
+    a nested subactor erroring.
-):
+    """
-    '''
-    Multiple subactors, both erroring and
-    breakpointing as well as a nested subactor erroring.
-
-    '''
     child = spawn(r'multi_subactors')
 
-    # scan for the prompt
+    # scan for the pdbpp prompt
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     before = str(child.before.decode())
     assert "Attaching pdb to actor: ('breakpoint_forever'" in before
 
-    if ctlc:
-        do_ctlc(child)
-
     # do some "next" commands to demonstrate recurrent breakpoint
     # entries
     for _ in range(10):
         child.sendline('next')
-        child.expect(PROMPT)
+        child.expect(r"\(Pdb\+\+\)")
-
-        if ctlc:
-            do_ctlc(child)
 
     # continue to next error
     child.sendline('c')
 
     # first name_error failure
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
     before = str(child.before.decode())
     assert "Attaching to pdb in crashed actor: ('name_error'" in before
     assert "NameError" in before
 
-    if ctlc:
-        do_ctlc(child)
-
     # continue again
     child.sendline('c')
 
     # 2nd name_error failure
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
-
+    before = str(child.before.decode())
-    # TODO: will we ever get the race where this crash will show up?
+    assert "Attaching to pdb in crashed actor: ('name_error_1'" in before
-    # blocklist strat now prevents this crash
+    assert "NameError" in before
-    # assert_before(child, [
-    #     "Attaching to pdb in crashed actor: ('name_error_1'",
-    #     "NameError",
-    # ])
-
-    if ctlc:
-        do_ctlc(child)
 
     # breakpoint loop should re-engage
     child.sendline('c')
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
     before = str(child.before.decode())
     assert "Attaching pdb to actor: ('breakpoint_forever'" in before
 
-    if ctlc:
-        do_ctlc(child)
-
     # wait for spawn error to show up
     spawn_err = "Attaching to pdb in crashed actor: ('spawn_error'"
-    start = time.time()
+    while spawn_err not in before:
-    while (
-        spawn_err not in before
-        and (time.time() - start) < 3  # timeout eventually
-    ):
         child.sendline('c')
         time.sleep(0.1)
-        child.expect(PROMPT)
+        child.expect(r"\(Pdb\+\+\)")
         before = str(child.before.decode())
 
-        if ctlc:
-            do_ctlc(child)
-
     # 2nd depth nursery should trigger
-    # (XXX: this below if guard is technically a hack that makes the
+    # child.sendline('c')
-    # nested case seem to work locally on linux but ideally in the long
+    # child.expect(r"\(Pdb\+\+\)")
-    # run this can be dropped.)
+    # before = str(child.before.decode())
-    if not ctlc:
+    assert spawn_err in before
-        assert_before(child, [
+    assert "RemoteActorError: ('name_error_1'" in before
-            spawn_err,
-            "RemoteActorError: ('name_error_1'",
-        ])
 
     # now run some "continues" to show re-entries
     for _ in range(5):
         child.sendline('c')
-        child.expect(PROMPT)
+        child.expect(r"\(Pdb\+\+\)")
 
     # quit the loop and expect parent to attach
     child.sendline('q')
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
     before = str(child.before.decode())
-
+    # debugger attaches to root
-    assert_before(child, [
+    assert "Attaching to pdb in crashed actor: ('root'" in before
-        # debugger attaches to root
+    # expect a multierror with exceptions for each sub-actor
-        "Attaching to pdb in crashed actor: ('root'",
+    assert "RemoteActorError: ('breakpoint_forever'" in before
-
+    assert "RemoteActorError: ('name_error'" in before
-        # expect a multierror with exceptions for each sub-actor
+    assert "RemoteActorError: ('spawn_error'" in before
-        "RemoteActorError: ('breakpoint_forever'",
+    assert "RemoteActorError: ('name_error_1'" in before
-        "RemoteActorError: ('name_error'",
+    assert 'bdb.BdbQuit' in before
-        "RemoteActorError: ('spawn_error'",
-        "RemoteActorError: ('name_error_1'",
-        'bdb.BdbQuit',
-    ])
-
-    if ctlc:
-        do_ctlc(child)
 
     # process should exit
     child.sendline('c')
     child.expect(pexpect.EOF)
-
     # repeat of previous multierror for final output
-    assert_before(child, [
+    before = str(child.before.decode())
-        "RemoteActorError: ('breakpoint_forever'",
+    assert "RemoteActorError: ('breakpoint_forever'" in before
-        "RemoteActorError: ('name_error'",
+    assert "RemoteActorError: ('name_error'" in before
-        "RemoteActorError: ('spawn_error'",
+    assert "RemoteActorError: ('spawn_error'" in before
-        "RemoteActorError: ('name_error_1'",
+    assert "RemoteActorError: ('name_error_1'" in before
-        'bdb.BdbQuit',
+    assert 'bdb.BdbQuit' in before
-    ])
 
 
-def test_multi_daemon_subactors(
+def test_multi_daemon_subactors(spawn, loglevel):
-    spawn,
+    """Multiple daemon subactors, both erroring and breakpointing within a
-    loglevel: str,
-    ctlc: bool
-):
-    '''
-    Multiple daemon subactors, both erroring and breakpointing within a
     stream.
-
+    """
-    '''
     child = spawn('multi_daemon_subactors')
 
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
-    # there can be a race for which subactor will acquire
+    # there is a race for which subactor will acquire
-    # the root's tty lock first so anticipate either crash
+    # the root's tty lock first
-    # message on the first entry.
-
-    bp_forever_msg = "Attaching pdb to actor: ('bp_forever'"
-    name_error_msg = "NameError: name 'doggypants' is not defined"
 
     before = str(child.before.decode())
+
+    bp_forever_msg = "Attaching pdb to actor: ('bp_forever'"
+    name_error_msg = "NameError"
+
     if bp_forever_msg in before:
         next_msg = name_error_msg
 
@@ -587,9 +352,6 @@ def test_multi_daemon_subactors(
     else:
         raise ValueError("Neither log msg was found !?")
 
-    if ctlc:
-        do_ctlc(child)
-
     # NOTE: previously since we did not have clobber prevention
     # in the root actor this final resume could result in the debugger
     # tearing down since both child actors would be cancelled and it was
@@ -598,8 +360,10 @@ def test_multi_daemon_subactors(
     # second entry by `bp_forever`.
 
     child.sendline('c')
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
-    assert_before(child, [next_msg])
+    before = str(child.before.decode())
+
+    assert next_msg in before
 
     # XXX: hooray the root clobbering the child here was fixed!
     # IMO, this demonstrates the true power of SC system design.
@@ -607,7 +371,7 @@ def test_multi_daemon_subactors(
     # now the root actor won't clobber the bp_forever child
     # during it's first access to the debug lock, but will instead
     # wait for the lock to release, by the edge triggered
-    # ``_debug.Lock.no_remote_has_tty`` event before sending cancel messages
+    # ``_debug._no_remote_has_tty`` event before sending cancel messages
     # (via portals) to its underlings B)
 
     # at some point here there should have been some warning msg from
@@ -615,61 +379,32 @@ def test_multi_daemon_subactors(
     # it seems unreliable in testing here to gnab it:
     # assert "in use by child ('bp_forever'," in before
 
-    if ctlc:
+    # wait for final error in root
-        do_ctlc(child)
+    while True:
-
-    # expect another breakpoint actor entry
-    child.sendline('c')
-    child.expect(PROMPT)
-
-    try:
-        assert_before(child, [bp_forever_msg])
-    except AssertionError:
-        assert_before(child, [name_error_msg])
-
-    else:
-        if ctlc:
-            do_ctlc(child)
-
-        # should crash with the 2nd name error (simulates
-        # a retry) and then the root eventually (boxed) errors
-        # after 1 or more further bp actor entries.
 
         child.sendline('c')
-        child.expect(PROMPT)
+        child.expect(r"\(Pdb\+\+\)")
-        assert_before(child, [name_error_msg])
+        before = str(child.before.decode())
-
-    # wait for final error in root
-    # where it crashs with boxed error
-    while True:
         try:
-            child.sendline('c')
+
-            child.expect(PROMPT)
+            # root error should be packed as remote error
-            assert_before(
+            assert "_exceptions.RemoteActorError: ('name_error'" in before
-                child,
-                [bp_forever_msg]
-            )
-        except AssertionError:
             break
 
-    assert_before(
+        except AssertionError:
-        child,
+            assert bp_forever_msg in before
-        [
-            # boxed error raised in root task
-            "Attaching to pdb in crashed actor: ('root'",
-            "_exceptions.RemoteActorError: ('name_error'",
-        ]
-    )
 
-    child.sendline('c')
+    try:
-    child.expect(pexpect.EOF)
+        child.sendline('c')
+        child.expect(pexpect.EOF)
+
+    except pexpect.exceptions.TIMEOUT:
+        # Failed to exit using continue..?
+        child.sendline('q')
+        child.expect(pexpect.EOF)
 
 
-@has_nested_actors
+def test_multi_subactors_root_errors(spawn):
-def test_multi_subactors_root_errors(
-    spawn,
-    ctlc: bool
-):
     '''
     Multiple subactors, both erroring and breakpointing as well as
     a nested subactor erroring.
@@ -677,87 +412,50 @@ def test_multi_subactors_root_errors(
     '''
     child = spawn('multi_subactor_root_errors')
 
-    # scan for the prompt
+    # scan for the pdbpp prompt
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     # at most one subactor should attach before the root is cancelled
     before = str(child.before.decode())
     assert "NameError: name 'doggypants' is not defined" in before
 
-    if ctlc:
-        do_ctlc(child)
-
     # continue again to catch 2nd name error from
     # actor 'name_error_1' (which is 2nd depth).
     child.sendline('c')
-
+    child.expect(r"\(Pdb\+\+\)")
-    # due to block list strat from #337, this will no longer
-    # propagate before the root errors and cancels the spawner sub-tree.
-    child.expect(PROMPT)
-
-    # only if the blocking condition doesn't kick in fast enough
     before = str(child.before.decode())
-    if "Debug lock blocked for ['name_error_1'" not in before:
+    assert "Attaching to pdb in crashed actor: ('name_error_1'" in before
+    assert "NameError" in before
 
-        assert_before(child, [
+    child.sendline('c')
-            "Attaching to pdb in crashed actor: ('name_error_1'",
+    child.expect(r"\(Pdb\+\+\)")
-            "NameError",
-        ])
-
-        if ctlc:
-            do_ctlc(child)
-
-        child.sendline('c')
-        child.expect(PROMPT)
-
-    # check if the spawner crashed or was blocked from debug
-    # and if this intermediary attached check the boxed error
     before = str(child.before.decode())
-    if "Attaching to pdb in crashed actor: ('spawn_error'" in before:
+    assert "Attaching to pdb in crashed actor: ('spawn_error'" in before
+    # boxed error from previous step
+    assert "RemoteActorError: ('name_error_1'" in before
+    assert "NameError" in before
 
-        assert_before(child, [
+    child.sendline('c')
-            # boxed error from spawner's child
+    child.expect(r"\(Pdb\+\+\)")
-            "RemoteActorError: ('name_error_1'",
+    before = str(child.before.decode())
-            "NameError",
+    assert "Attaching to pdb in crashed actor: ('root'" in before
-        ])
+    # boxed error from first level failure
+    assert "RemoteActorError: ('name_error'" in before
+    assert "NameError" in before
 
-        if ctlc:
+    # warnings assert we probably don't need
-            do_ctlc(child)
+    # assert "Cancelling nursery in ('spawn_error'," in before
-
-        child.sendline('c')
-        child.expect(PROMPT)
-
-    # expect a root actor crash
-    assert_before(child, [
-        "RemoteActorError: ('name_error'",
-        "NameError",
-
-        # error from root actor and root task that created top level nursery
-        "Attaching to pdb in crashed actor: ('root'",
-        "AssertionError",
-    ])
 
+    # continue again
     child.sendline('c')
     child.expect(pexpect.EOF)
 
-    assert_before(child, [
+    before = str(child.before.decode())
-        # "Attaching to pdb in crashed actor: ('root'",
+    # error from root actor and root task that created top level nursery
-        # boxed error from previous step
+    assert "AssertionError" in before
-        "RemoteActorError: ('name_error'",
-        "NameError",
-        "AssertionError",
-        'assert 0',
-    ])
 
 
-@has_nested_actors
+def test_multi_nested_subactors_error_through_nurseries(spawn):
-def test_multi_nested_subactors_error_through_nurseries(
-    spawn,
-
-    # TODO: address debugger issue for nested tree:
-    # https://github.com/goodboy/tractor/issues/320
-    # ctlc: bool,
-):
     """Verify deeply nested actors that error trigger debugger entries
     at each actor nurserly (level) all the way up the tree.
 
@@ -772,70 +470,55 @@ def test_multi_nested_subactors_error_through_nurseries(
 
     timed_out_early: bool = False
 
-    for send_char in itertools.cycle(['c', 'q']):
+    for i in range(12):
         try:
-            child.expect(PROMPT)
+            child.expect(r"\(Pdb\+\+\)")
-            child.sendline(send_char)
+            child.sendline('c')
-            time.sleep(0.01)
+            time.sleep(0.1)
 
-        except EOF:
+        except pexpect.exceptions.EOF:
+
+            # race conditions on how fast the continue is sent?
+            print(f"Failed early on {i}?")
+            timed_out_early = True
             break
+    else:
+        child.expect(pexpect.EOF)
 
-    assert_before(child, [
+    if not timed_out_early:
-
+        before = str(child.before.decode())
-        # boxed source errors
+        assert "NameError" in before
-        "NameError: name 'doggypants' is not defined",
-        "tractor._exceptions.RemoteActorError: ('name_error'",
-        "bdb.BdbQuit",
-
-        # first level subtrees
-        "tractor._exceptions.RemoteActorError: ('spawner0'",
-        # "tractor._exceptions.RemoteActorError: ('spawner1'",
-
-        # propagation of errors up through nested subtrees
-        "tractor._exceptions.RemoteActorError: ('spawn_until_0'",
-        "tractor._exceptions.RemoteActorError: ('spawn_until_1'",
-        "tractor._exceptions.RemoteActorError: ('spawn_until_2'",
-    ])
 
 
-@pytest.mark.timeout(15)
-@has_nested_actors
 def test_root_nursery_cancels_before_child_releases_tty_lock(
     spawn,
-    start_method,
+    start_method
-    ctlc: bool,
 ):
-    '''
+    """Test that when the root sends a cancel message before a nested
-    Test that when the root sends a cancel message before a nested child
+    child has unblocked (which can happen when it has the tty lock and
-    has unblocked (which can happen when it has the tty lock and is
+    is engaged in pdb) it is indeed cancelled after exiting the debugger.
-    engaged in pdb) it is indeed cancelled after exiting the debugger.
+    """
-
-    '''
     timed_out_early = False
 
     child = spawn('root_cancelled_but_child_is_in_tty_lock')
 
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     before = str(child.before.decode())
     assert "NameError: name 'doggypants' is not defined" in before
     assert "tractor._exceptions.RemoteActorError: ('name_error'" not in before
     time.sleep(0.5)
 
-    if ctlc:
-        do_ctlc(child)
-
     child.sendline('c')
 
     for i in range(4):
         time.sleep(0.5)
         try:
-            child.expect(PROMPT)
+            child.expect(r"\(Pdb\+\+\)")
 
         except (
-            EOF,
+            pexpect.exceptions.EOF,
-            TIMEOUT,
+            pexpect.exceptions.TIMEOUT,
         ):
             # races all over..
 
@@ -850,37 +533,26 @@ def test_root_nursery_cancels_before_child_releases_tty_lock(
         before = str(child.before.decode())
         assert "NameError: name 'doggypants' is not defined" in before
 
-        if ctlc:
-            do_ctlc(child)
-
         child.sendline('c')
-        time.sleep(0.1)
 
-    for i in range(3):
+    while True:
         try:
-            child.expect(pexpect.EOF, timeout=0.5)
+            child.expect(pexpect.EOF)
             break
-        except TIMEOUT:
+        except pexpect.exceptions.TIMEOUT:
             child.sendline('c')
-            time.sleep(0.1)
             print('child was able to grab tty lock again?')
-    else:
-        print('giving up on child releasing, sending `quit` cmd')
-        child.sendline('q')
-        expect(child, EOF)
 
     if not timed_out_early:
+
         before = str(child.before.decode())
-        assert_before(child, [
+        assert "tractor._exceptions.RemoteActorError: ('spawner0'" in before
-            "tractor._exceptions.RemoteActorError: ('spawner0'",
+        assert "tractor._exceptions.RemoteActorError: ('name_error'" in before
-            "tractor._exceptions.RemoteActorError: ('name_error'",
+        assert "NameError: name 'doggypants' is not defined" in before
-            "NameError: name 'doggypants' is not defined",
-        ])
 
 
 def test_root_cancels_child_context_during_startup(
     spawn,
-    ctlc: bool,
 ):
     '''Verify a fast fail in the root doesn't lock up the child reaping
     and all while using the new context api.
@@ -888,33 +560,26 @@ def test_root_cancels_child_context_during_startup(
     '''
     child = spawn('fast_error_in_root_after_spawn')
 
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     before = str(child.before.decode())
     assert "AssertionError" in before
 
-    if ctlc:
-        do_ctlc(child)
-
     child.sendline('c')
     child.expect(pexpect.EOF)
 
 
 def test_different_debug_mode_per_actor(
     spawn,
-    ctlc: bool,
 ):
     child = spawn('per_actor_debug')
-    child.expect(PROMPT)
+    child.expect(r"\(Pdb\+\+\)")
 
     # only one actor should enter the debugger
     before = str(child.before.decode())
     assert "Attaching to pdb in crashed actor: ('debugged_boi'" in before
     assert "RuntimeError" in before
 
-    if ctlc:
-        do_ctlc(child)
-
     child.sendline('c')
     child.expect(pexpect.EOF)
 

tests/test_docs_examples.py

@@ -12,17 +12,17 @@ import shutil
 
 import pytest
 
-from conftest import (
+from conftest import repodir
-    examples_dir,
+
-)
+
+def examples_dir():
+    """Return the abspath to the examples directory.
+    """
+    return os.path.join(repodir(), 'examples')
 
 
 @pytest.fixture
-def run_example_in_subproc(
+def run_example_in_subproc(loglevel, testdir, arb_addr):
-    loglevel: str,
-    testdir,
-    arb_addr: tuple[str, int],
-):
 
     @contextmanager
     def run(script_code):
@@ -32,8 +32,8 @@ def run_example_in_subproc(
             # on windows we need to create a special __main__.py which will
             # be executed with ``python -m <modulename>`` on windows..
             shutil.copyfile(
-                examples_dir() / '__main__.py',
+                os.path.join(examples_dir(), '__main__.py'),
-                str(testdir / '__main__.py'),
+                os.path.join(str(testdir), '__main__.py')
             )
 
             # drop the ``if __name__ == '__main__'`` guard onwards from
@@ -81,15 +81,11 @@ def run_example_in_subproc(
     'example_script',
 
     # walk yields: (dirpath, dirnames, filenames)
-    [
+    [(p[0], f) for p in os.walk(examples_dir()) for f in p[2]
-        (p[0], f) for p in os.walk(examples_dir()) for f in p[2]
 
         if '__' not in f
         and f[0] != '_'
-        and 'debugging' not in p[0]
+        and 'debugging' not in p[0]],
-        and 'integration' not in p[0]
-        and 'advanced_faults' not in p[0]
-    ],
 
     ids=lambda t: t[1],
 )
@@ -117,19 +113,9 @@ def test_example(run_example_in_subproc, example_script):
             # print(f'STDOUT: {out}')
 
             # if we get some gnarly output let's aggregate and raise
-            if err:
+            errmsg = err.decode()
-                errmsg = err.decode()
+            errlines = errmsg.splitlines()
-                errlines = errmsg.splitlines()
+            if err and 'Error' in errlines[-1]:
-                last_error = errlines[-1]
+                raise Exception(errmsg)
-                if (
-                    'Error' in last_error
-
-                    # XXX: currently we print this to console, but maybe
-                    # shouldn't eventually once we figure out what's
-                    # a better way to be explicit about aio side
-                    # cancels?
-                    and 'asyncio.exceptions.CancelledError' not in last_error
-                ):
-                    raise Exception(errmsg)
 
             assert proc.returncode == 0

tests/test_infected_asyncio.py

@@ -2,36 +2,20 @@
 The hipster way to force SC onto the stdlib's "async": 'infection mode'.
 
 '''
-from typing import Optional, Iterable, Union
+from typing import Optional, Iterable
 import asyncio
 import builtins
-import itertools
 import importlib
 
-from exceptiongroup import BaseExceptionGroup
 import pytest
 import trio
 import tractor
-from tractor import (
+from tractor import to_asyncio
-    to_asyncio,
+from tractor import RemoteActorError
-    RemoteActorError,
-)
-from tractor.trionics import BroadcastReceiver
 
 
-async def sleep_and_err(
+async def sleep_and_err():
-    sleep_for: float = 0.1,
+    await asyncio.sleep(0.1)
-
-    # just signature placeholders for compat with
-    # ``to_asyncio.open_channel_from()``
-    to_trio: Optional[trio.MemorySendChannel] = None,
-    from_trio: Optional[asyncio.Queue] = None,
-
-):
-    if to_trio:
-        to_trio.send_nowait('start')
-
-    await asyncio.sleep(sleep_for)
     assert 0
 
 
@@ -160,81 +144,6 @@ def test_trio_cancels_aio(arb_addr):
     trio.run(main)
 
 
-@tractor.context
-async def trio_ctx(
-    ctx: tractor.Context,
-):
-
-    await ctx.started('start')
-
-    # this will block until the ``asyncio`` task sends a "first"
-    # message.
-    with trio.fail_after(2):
-        async with (
-            trio.open_nursery() as n,
-
-            tractor.to_asyncio.open_channel_from(
-                sleep_and_err,
-            ) as (first, chan),
-        ):
-
-            assert first == 'start'
-
-            # spawn another asyncio task for the cuck of it.
-            n.start_soon(
-                tractor.to_asyncio.run_task,
-                sleep_forever,
-            )
-            await trio.sleep_forever()
-
-
-@pytest.mark.parametrize(
-    'parent_cancels', [False, True],
-    ids='parent_actor_cancels_child={}'.format
-)
-def test_context_spawns_aio_task_that_errors(
-    arb_addr,
-    parent_cancels: bool,
-):
-    '''
-    Verify that spawning a task via an intertask channel ctx mngr that
-    errors correctly propagates the error back from the `asyncio`-side
-    task.
-
-    '''
-    async def main():
-
-        with trio.fail_after(2):
-            async with tractor.open_nursery() as n:
-                p = await n.start_actor(
-                    'aio_daemon',
-                    enable_modules=[__name__],
-                    infect_asyncio=True,
-                    # debug_mode=True,
-                    loglevel='cancel',
-                )
-                async with p.open_context(
-                    trio_ctx,
-                ) as (ctx, first):
-
-                    assert first == 'start'
-
-                    if parent_cancels:
-                        await p.cancel_actor()
-
-                    await trio.sleep_forever()
-
-    with pytest.raises(RemoteActorError) as excinfo:
-        trio.run(main)
-
-    err = excinfo.value
-    assert isinstance(err, RemoteActorError)
-    if parent_cancels:
-        assert err.type == trio.Cancelled
-    else:
-        assert err.type == AssertionError
-
-
 async def aio_cancel():
     ''''
     Cancel urself boi.
@@ -308,7 +217,6 @@ async def stream_from_aio(
     exit_early: bool = False,
     raise_err: bool = False,
     aio_raise_err: bool = False,
-    fan_out: bool = False,
 
 ) -> None:
     seq = range(100)
@@ -326,38 +234,15 @@ async def stream_from_aio(
 
             assert first is True
 
-            async def consume(
+            async for value in chan:
-                chan: Union[
+                print(f'trio received {value}')
-                    to_asyncio.LinkedTaskChannel,
+                pulled.append(value)
-                    BroadcastReceiver,
-                ],
-            ):
-                async for value in chan:
-                    print(f'trio received {value}')
-                    pulled.append(value)
 
-                    if value == 50:
+                if value == 50:
-                        if raise_err:
+                    if raise_err:
-                            raise Exception
+                        raise Exception
-                        elif exit_early:
+                    elif exit_early:
-                            break
+                        break
-
-            if fan_out:
-                # start second task that get's the same stream value set.
-                async with (
-
-                    # NOTE: this has to come first to avoid
-                    # the channel being closed before the nursery
-                    # tasks are joined..
-                    chan.subscribe() as br,
-
-                    trio.open_nursery() as n,
-                ):
-                    n.start_soon(consume, br)
-                    await consume(chan)
-
-            else:
-                await consume(chan)
     finally:
 
         if (
@@ -365,33 +250,19 @@ async def stream_from_aio(
             not exit_early and
             not aio_raise_err
         ):
-            if fan_out:
+            assert pulled == expect
-                # we get double the pulled values in the
-                # ``.subscribe()`` fan out case.
-                doubled = list(itertools.chain(*zip(expect, expect)))
-                expect = doubled[:len(pulled)]
-                assert list(sorted(pulled)) == expect
-
-            else:
-                assert pulled == expect
         else:
-            assert not fan_out
             assert pulled == expect[:51]
 
         print('trio guest mode task completed!')
 
 
-@pytest.mark.parametrize(
+def test_basic_interloop_channel_stream(arb_addr):
-    'fan_out', [False, True],
-    ids='fan_out_w_chan_subscribe={}'.format
-)
-def test_basic_interloop_channel_stream(arb_addr, fan_out):
     async def main():
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
                 stream_from_aio,
                 infect_asyncio=True,
-                fan_out=fan_out,
             )
             await portal.result()
 
@@ -410,12 +281,11 @@ def test_trio_error_cancels_intertask_chan(arb_addr):
             # should trigger remote actor error
             await portal.result()
 
-    with pytest.raises(BaseExceptionGroup) as excinfo:
+    with pytest.raises(RemoteActorError) as excinfo:
         trio.run(main)
 
-    # ensure boxed errors
+    # ensure boxed error is correct
-    for exc in excinfo.value.exceptions:
+    assert excinfo.value.type == Exception
-        assert exc.type == Exception
 
 
 def test_trio_closes_early_and_channel_exits(arb_addr):
@@ -444,12 +314,11 @@ def test_aio_errors_and_channel_propagates_and_closes(arb_addr):
             # should trigger remote actor error
             await portal.result()
 
-    with pytest.raises(BaseExceptionGroup) as excinfo:
+    with pytest.raises(RemoteActorError) as excinfo:
         trio.run(main)
 
-    # ensure boxed errors
+    # ensure boxed error is correct
-    for exc in excinfo.value.exceptions:
+    assert excinfo.value.type == Exception
-        assert exc.type == Exception
 
 
 @tractor.context
@@ -476,8 +345,6 @@ async def trio_to_aio_echo_server(
                 print('breaking aio echo loop')
                 break
 
-        print('exiting asyncio task')
-
     async with to_asyncio.open_channel_from(
         aio_echo_server,
     ) as (first, chan):

tests/test_local.py

@@ -11,18 +11,25 @@ from conftest import tractor_test
 
 
 @pytest.mark.trio
-async def test_no_runtime():
+async def test_no_arbitter():
     """An arbitter must be established before any nurseries
     can be created.
 
     (In other words ``tractor.open_root_actor()`` must be engaged at
     some point?)
     """
-    with pytest.raises(RuntimeError) :
+    with pytest.raises(RuntimeError):
-        async with tractor.find_actor('doggy'):
+        with tractor.open_nursery():
             pass
 
 
+def test_no_main():
+    """An async function **must** be passed to ``tractor.run()``.
+    """
+    with pytest.raises(TypeError):
+        tractor.run(None)
+
+
 @tractor_test
 async def test_self_is_registered(arb_addr):
     "Verify waiting on the arbiter to register itself using the standard api."

tests/test_pubsub.py

@@ -4,10 +4,9 @@ from itertools import cycle
 import pytest
 import trio
 import tractor
+from tractor.testing import tractor_test
 from tractor.experimental import msgpub
 
-from conftest import tractor_test
-
 
 def test_type_checks():
 

tests/test_runtime.py

@@ -1,73 +0,0 @@
-"""
-Verifying internal runtime state and undocumented extras.
-
-"""
-import os
-
-import pytest
-import trio
-import tractor
-
-from conftest import tractor_test
-
-
-_file_path: str = ''
-
-
-def unlink_file():
-    print('Removing tmp file!')
-    os.remove(_file_path)
-
-
-async def crash_and_clean_tmpdir(
-    tmp_file_path: str,
-    error: bool = True,
-):
-    global _file_path
-    _file_path = tmp_file_path
-
-    actor = tractor.current_actor()
-    actor.lifetime_stack.callback(unlink_file)
-
-    assert os.path.isfile(tmp_file_path)
-    await trio.sleep(0.1)
-    if error:
-        assert 0
-    else:
-        actor.cancel_soon()
-
-
-@pytest.mark.parametrize(
-    'error_in_child',
-    [True, False],
-)
-@tractor_test
-async def test_lifetime_stack_wipes_tmpfile(
-    tmp_path,
-    error_in_child: bool,
-):
-    child_tmp_file = tmp_path / "child.txt"
-    child_tmp_file.touch()
-    assert child_tmp_file.exists()
-    path = str(child_tmp_file)
-
-    try:
-        with trio.move_on_after(0.5):
-            async with tractor.open_nursery() as n:
-                    await (  # inlined portal
-                        await n.run_in_actor(
-                            crash_and_clean_tmpdir,
-                            tmp_file_path=path,
-                            error=error_in_child,
-                        )
-                    ).result()
-
-    except (
-        tractor.RemoteActorError,
-        tractor.BaseExceptionGroup,
-    ):
-        pass
-
-    # tmp file should have been wiped by
-    # teardown stack.
-    assert not child_tmp_file.exists()

tests/test_spawning.py

@@ -1,8 +1,7 @@
 """
 Spawning basics
-
 """
-from typing import Optional
+from typing import Dict, Tuple, Optional
 
 import pytest
 import trio
@@ -15,8 +14,8 @@ data_to_pass_down = {'doggy': 10, 'kitty': 4}
 
 async def spawn(
     is_arbiter: bool,
-    data: dict,
+    data: Dict,
-    arb_addr: tuple[str, int],
+    arb_addr: Tuple[str, int],
 ):
     namespaces = [__name__]
 
@@ -142,7 +141,7 @@ def test_loglevel_propagated_to_subactor(
     capfd,
     arb_addr,
 ):
-    if start_method == 'mp_forkserver':
+    if start_method == 'forkserver':
         pytest.skip(
             "a bug with `capfd` seems to make forkserver capture not work?")
 
@@ -151,13 +150,13 @@ def test_loglevel_propagated_to_subactor(
     async def main():
         async with tractor.open_nursery(
             name='arbiter',
+            loglevel=level,
             start_method=start_method,
             arbiter_addr=arb_addr,
 
         ) as tn:
             await tn.run_in_actor(
                 check_loglevel,
-                loglevel=level,
                 level=level,
             )
 

tests/test_streaming.py

@@ -7,10 +7,9 @@ import platform
 
 import trio
 import tractor
+from tractor.testing import tractor_test
 import pytest
 
-from conftest import tractor_test
-
 
 def test_must_define_ctx():
 
@@ -251,7 +250,7 @@ def test_a_quadruple_example(time_quad_ex, ci_env, spawn_backend):
 
     results, diff = time_quad_ex
     assert results
-    this_fast = 6 if platform.system() in ('Windows', 'Darwin') else 3
+    this_fast = 6 if platform.system() in ('Windows', 'Darwin') else 2.666
     assert diff < this_fast
 
 

tests/test_task_broadcasting.py

@@ -6,16 +6,13 @@ from contextlib import asynccontextmanager
 from functools import partial
 from itertools import cycle
 import time
-from typing import Optional
+from typing import Optional, List, Tuple
 
 import pytest
 import trio
 from trio.lowlevel import current_task
 import tractor
-from tractor.trionics import (
+from tractor.trionics import broadcast_receiver, Lagged
-    broadcast_receiver,
-    Lagged,
-)
 
 
 @tractor.context
@@ -40,7 +37,7 @@ async def echo_sequences(
 
 async def ensure_sequence(
 
-    stream: tractor.MsgStream,
+    stream: tractor.ReceiveMsgStream,
     sequence: list,
     delay: Optional[float] = None,
 
@@ -65,8 +62,8 @@ async def ensure_sequence(
 @asynccontextmanager
 async def open_sequence_streamer(
 
-    sequence: list[int],
+    sequence: List[int],
-    arb_addr: tuple[str, int],
+    arb_addr: Tuple[str, int],
     start_method: str,
 
 ) -> tractor.MsgStream:
@@ -214,8 +211,7 @@ def test_faster_task_to_recv_is_cancelled_by_slower(
     arb_addr,
     start_method,
 ):
-    '''
+    '''Ensure that if a faster task consuming from a stream is cancelled
-    Ensure that if a faster task consuming from a stream is cancelled
     the slower task can continue to receive all expected values.
 
     '''
@@ -464,51 +460,3 @@ def test_first_recver_is_cancelled():
                     assert value == 1
 
     trio.run(main)
-
-
-def test_no_raise_on_lag():
-    '''
-    Run a simple 2-task broadcast where one task is slow but configured
-    so that it does not raise `Lagged` on overruns using
-    `raise_on_lasg=False` and verify that the task does not raise.
-
-    '''
-    size = 100
-    tx, rx = trio.open_memory_channel(size)
-    brx = broadcast_receiver(rx, size)
-
-    async def slow():
-        async with brx.subscribe(
-            raise_on_lag=False,
-        ) as br:
-            async for msg in br:
-                print(f'slow task got: {msg}')
-                await trio.sleep(0.1)
-
-    async def fast():
-        async with brx.subscribe() as br:
-            async for msg in br:
-                print(f'fast task got: {msg}')
-
-    async def main():
-        async with (
-            tractor.open_root_actor(
-                # NOTE: so we see the warning msg emitted by the bcaster
-                # internals when the no raise flag is set.
-                loglevel='warning',
-            ),
-            trio.open_nursery() as n,
-        ):
-            n.start_soon(slow)
-            n.start_soon(fast)
-
-            for i in range(1000):
-                await tx.send(i)
-
-            # simulate user nailing ctl-c after realizing
-            # there's a lag in the slow task.
-            await trio.sleep(1)
-            raise KeyboardInterrupt
-
-    with pytest.raises(KeyboardInterrupt):
-        trio.run(main)

tests/test_trioisms.py

@@ -1,82 +0,0 @@
-'''
-Reminders for oddities in `trio` that we need to stay aware of and/or
-want to see changed.
-
-'''
-import pytest
-import trio
-from trio_typing import TaskStatus
-
-
-@pytest.mark.parametrize(
-    'use_start_soon', [
-        pytest.param(
-            True,
-            marks=pytest.mark.xfail(reason="see python-trio/trio#2258")
-        ),
-        False,
-    ]
-)
-def test_stashed_child_nursery(use_start_soon):
-
-    _child_nursery = None
-
-    async def waits_on_signal(
-        ev: trio.Event(),
-        task_status: TaskStatus[trio.Nursery] = trio.TASK_STATUS_IGNORED,
-    ):
-        '''
-        Do some stuf, then signal other tasks, then yield back to "starter".
-
-        '''
-        await ev.wait()
-        task_status.started()
-
-    async def mk_child_nursery(
-        task_status: TaskStatus = trio.TASK_STATUS_IGNORED,
-    ):
-        '''
-        Allocate a child sub-nursery and stash it as a global.
-
-        '''
-        nonlocal _child_nursery
-
-        async with trio.open_nursery() as cn:
-            _child_nursery = cn
-            task_status.started(cn)
-
-            # block until cancelled by parent.
-            await trio.sleep_forever()
-
-    async def sleep_and_err(
-        ev: trio.Event,
-        task_status: TaskStatus = trio.TASK_STATUS_IGNORED,
-    ):
-        await trio.sleep(0.5)
-        doggy()  # noqa
-        ev.set()
-        task_status.started()
-
-    async def main():
-
-        async with (
-            trio.open_nursery() as pn,
-        ):
-            cn = await pn.start(mk_child_nursery)
-            assert cn
-
-            ev = trio.Event()
-
-            if use_start_soon:
-                # this causes inf hang
-                cn.start_soon(sleep_and_err, ev)
-
-            else:
-                # this does not.
-                await cn.start(sleep_and_err, ev)
-
-            with trio.fail_after(1):
-                await cn.start(waits_on_signal, ev)
-
-    with pytest.raises(NameError):
-        trio.run(main)

towncrier.toml

@@ -0,0 +1,7 @@
+[tool.towncrier]
+package = "tractor"
+filename = "NEWS.rst"
+directory = "nooz/"
+title_format = "tractor {version} ({project_date})"
+version = "0.1.0a4"
+template = "nooz/_template.rst"

tractor/__init__.py

@@ -18,57 +18,39 @@
 tractor: structured concurrent "actors".
 
 """
-from exceptiongroup import BaseExceptionGroup
+from trio import MultiError
 
 from ._clustering import open_actor_cluster
 from ._ipc import Channel
 from ._streaming import (
     Context,
+    ReceiveMsgStream,
     MsgStream,
     stream,
     context,
 )
-from ._discovery import (
+from ._discovery import get_arbiter, find_actor, wait_for_actor
-    get_arbiter,
-    find_actor,
-    wait_for_actor,
-    query_actor,
-)
 from ._supervise import open_nursery
-from ._state import (
+from ._state import current_actor, is_root_process
-    current_actor,
-    is_root_process,
-)
 from ._exceptions import (
     RemoteActorError,
     ModuleNotExposed,
     ContextCancelled,
 )
-from ._debug import (
+from ._debug import breakpoint, post_mortem
-    breakpoint,
-    post_mortem,
-)
 from . import msg
-from ._root import (
+from ._root import run, run_daemon, open_root_actor
-    run_daemon,
-    open_root_actor,
-)
 from ._portal import Portal
-from ._runtime import Actor
 
 
 __all__ = [
-    'Actor',
     'Channel',
     'Context',
-    'ContextCancelled',
     'ModuleNotExposed',
-    'MsgStream',
+    'MultiError',
-    'BaseExceptionGroup',
-    'Portal',
     'RemoteActorError',
+    'ContextCancelled',
     'breakpoint',
-    'context',
     'current_actor',
     'find_actor',
     'get_arbiter',
@@ -77,10 +59,14 @@ __all__ = [
     'open_actor_cluster',
     'open_nursery',
     'open_root_actor',
+    'Portal',
     'post_mortem',
-    'query_actor',
+    'run',
     'run_daemon',
     'stream',
+    'context',
+    'ReceiveMsgStream',
+    'MsgStream',
     'to_asyncio',
     'wait_for_actor',
 ]

tractor/_child.py

@@ -24,7 +24,7 @@ import argparse
 
 from ast import literal_eval
 
-from ._runtime import Actor
+from ._actor import Actor
 from ._entry import _trio_main
 
 

tractor/_clustering.py

@@ -32,12 +32,9 @@ import tractor
 async def open_actor_cluster(
     modules: list[str],
     count: int = cpu_count(),
-    names: list[str] | None = None,
+    names: Optional[list[str]] = None,
+    start_method: Optional[str] = None,
     hard_kill: bool = False,
-
-    # passed through verbatim to ``open_root_actor()``
-    **runtime_kwargs,
-
 ) -> AsyncGenerator[
     dict[str, tractor.Portal],
     None,
@@ -52,9 +49,7 @@ async def open_actor_cluster(
         raise ValueError(
             'Number of names is {len(names)} but count it {count}')
 
-    async with tractor.open_nursery(
+    async with tractor.open_nursery(start_method=start_method) as an:
-        **runtime_kwargs,
-    ) as an:
         async with trio.open_nursery() as n:
             uid = tractor.current_actor().uid
 

tractor/_discovery.py

@@ -18,12 +18,9 @@
 Actor discovery API.
 
 """
-from typing import (
+import typing
-    Optional,
+from typing import Tuple, Optional, Union
-    Union,
+from async_generator import asynccontextmanager
-    AsyncGenerator,
-)
-from contextlib import asynccontextmanager as acm
 
 from ._ipc import _connect_chan, Channel
 from ._portal import (
@@ -34,13 +31,13 @@ from ._portal import (
 from ._state import current_actor, _runtime_vars
 
 
-@acm
+@asynccontextmanager
 async def get_arbiter(
 
     host: str,
     port: int,
 
-) -> AsyncGenerator[Union[Portal, LocalPortal], None]:
+) -> typing.AsyncGenerator[Union[Portal, LocalPortal], None]:
     '''Return a portal instance connected to a local or remote
     arbiter.
     '''
@@ -61,10 +58,10 @@ async def get_arbiter(
                 yield arb_portal
 
 
-@acm
+@asynccontextmanager
 async def get_root(
     **kwargs,
-) -> AsyncGenerator[Portal, None]:
+) -> typing.AsyncGenerator[Portal, None]:
 
     host, port = _runtime_vars['_root_mailbox']
     assert host is not None
@@ -74,56 +71,28 @@ async def get_root(
             yield portal
 
 
-@acm
+@asynccontextmanager
-async def query_actor(
+async def find_actor(
     name: str,
-    arbiter_sockaddr: Optional[tuple[str, int]] = None,
+    arbiter_sockaddr: Tuple[str, int] = None
+) -> typing.AsyncGenerator[Optional[Portal], None]:
+    """Ask the arbiter to find actor(s) by name.
 
-) -> AsyncGenerator[tuple[str, int], None]:
+    Returns a connected portal to the last registered matching actor
-    '''
+    known to the arbiter.
-    Simple address lookup for a given actor name.
+    """
-
-    Returns the (socket) address or ``None``.
-
-    '''
     actor = current_actor()
-    async with get_arbiter(
+    async with get_arbiter(*arbiter_sockaddr or actor._arb_addr) as arb_portal:
-        *arbiter_sockaddr or actor._arb_addr
-    ) as arb_portal:
 
-        sockaddr = await arb_portal.run_from_ns(
+        sockaddr = await arb_portal.run_from_ns('self', 'find_actor', name=name)
-            'self',
-            'find_actor',
-            name=name,
-        )
 
         # TODO: return portals to all available actors - for now just
         # the last one that registered
         if name == 'arbiter' and actor.is_arbiter:
             raise RuntimeError("The current actor is the arbiter")
 
-        yield sockaddr if sockaddr else None
+        elif sockaddr:
 
-
-@acm
-async def find_actor(
-    name: str,
-    arbiter_sockaddr: tuple[str, int] | None = None
-
-) -> AsyncGenerator[Optional[Portal], None]:
-    '''
-    Ask the arbiter to find actor(s) by name.
-
-    Returns a connected portal to the last registered matching actor
-    known to the arbiter.
-
-    '''
-    async with query_actor(
-        name=name,
-        arbiter_sockaddr=arbiter_sockaddr,
-    ) as sockaddr:
-
-        if sockaddr:
             async with _connect_chan(*sockaddr) as chan:
                 async with open_portal(chan) as portal:
                     yield portal
@@ -131,25 +100,20 @@ async def find_actor(
             yield None
 
 
-@acm
+@asynccontextmanager
 async def wait_for_actor(
     name: str,
-    arbiter_sockaddr: tuple[str, int] | None = None
+    arbiter_sockaddr: Tuple[str, int] = None
-) -> AsyncGenerator[Portal, None]:
+) -> typing.AsyncGenerator[Portal, None]:
     """Wait on an actor to register with the arbiter.
 
     A portal to the first registered actor is returned.
     """
     actor = current_actor()
 
-    async with get_arbiter(
+    async with get_arbiter(*arbiter_sockaddr or actor._arb_addr) as arb_portal:
-        *arbiter_sockaddr or actor._arb_addr,
+
-    ) as arb_portal:
+        sockaddrs = await arb_portal.run_from_ns('self', 'wait_for_actor', name=name)
-        sockaddrs = await arb_portal.run_from_ns(
-            'self',
-            'wait_for_actor',
-            name=name,
-        )
         sockaddr = sockaddrs[-1]
 
         async with _connect_chan(*sockaddr) as chan:

tractor/_entry.py

@@ -18,28 +18,15 @@
 Sub-process entry points.
 
 """
-from __future__ import annotations
 from functools import partial
-from typing import (
+from typing import Tuple, Any
-    Any,
+import signal
-    TYPE_CHECKING,
-)
 
 import trio  # type: ignore
 
-from .log import (
+from .log import get_console_log, get_logger
-    get_console_log,
-    get_logger,
-)
 from . import _state
 from .to_asyncio import run_as_asyncio_guest
-from ._runtime import (
-    async_main,
-    Actor,
-)
-
-if TYPE_CHECKING:
-    from ._spawn import SpawnMethodKey
 
 
 log = get_logger(__name__)
@@ -47,11 +34,11 @@ log = get_logger(__name__)
 
 def _mp_main(
 
-    actor: Actor,  # type: ignore
+    actor: 'Actor',  # type: ignore
-    accept_addr: tuple[str, int],
+    accept_addr: Tuple[str, int],
-    forkserver_info: tuple[Any, Any, Any, Any, Any],
+    forkserver_info: Tuple[Any, Any, Any, Any, Any],
-    start_method: SpawnMethodKey,
+    start_method: str,
-    parent_addr: tuple[str, int] | None = None,
+    parent_addr: Tuple[str, int] = None,
     infect_asyncio: bool = False,
 
 ) -> None:
@@ -76,8 +63,7 @@ def _mp_main(
 
     log.debug(f"parent_addr is {parent_addr}")
     trio_main = partial(
-        async_main,
+        actor._async_main,
-        actor,
         accept_addr,
         parent_addr=parent_addr
     )
@@ -96,9 +82,9 @@ def _mp_main(
 
 def _trio_main(
 
-    actor: Actor,  # type: ignore
+    actor: 'Actor',  # type: ignore
     *,
-    parent_addr: tuple[str, int] | None = None,
+    parent_addr: Tuple[str, int] = None,
     infect_asyncio: bool = False,
 
 ) -> None:
@@ -120,8 +106,7 @@ def _trio_main(
 
     log.debug(f"parent_addr is {parent_addr}")
     trio_main = partial(
-        async_main,
+        actor._async_main,
-        actor,
         parent_addr=parent_addr
     )
 

tractor/_exceptions.py

@@ -18,16 +18,11 @@
 Our classy exception set.
 
 """
-from typing import (
+from typing import Dict, Any, Optional, Type
-    Any,
-    Optional,
-    Type,
-)
 import importlib
 import builtins
 import traceback
 
-import exceptiongroup as eg
 import trio
 
 
@@ -53,6 +48,9 @@ class RemoteActorError(Exception):
         self.type = suberror_type
         self.msgdata = msgdata
 
+    # TODO: a trio.MultiError.catch like context manager
+    # for catching underlying remote errors of a particular type
+
 
 class InternalActorError(RemoteActorError):
     """Remote internal ``tractor`` error indicating
@@ -97,7 +95,7 @@ def pack_error(
     exc: BaseException,
     tb=None,
 
-) -> dict[str, Any]:
+) -> Dict[str, Any]:
     """Create an "error message" for tranmission over
     a channel (aka the wire).
     """
@@ -116,17 +114,15 @@ def pack_error(
 
 def unpack_error(
 
-    msg: dict[str, Any],
+    msg: Dict[str, Any],
     chan=None,
     err_type=RemoteActorError
 
 ) -> Exception:
-    '''
+    """Unpack an 'error' message from the wire
-    Unpack an 'error' message from the wire
     into a local ``RemoteActorError``.
 
-    '''
+    """
-    __tracebackhide__ = True
     error = msg['error']
 
     tb_str = error.get('tb_str', '')
@@ -139,12 +135,7 @@ def unpack_error(
         suberror_type = trio.Cancelled
 
     else:  # try to lookup a suitable local error type
-        for ns in [
+        for ns in [builtins, _this_mod, trio]:
-            builtins,
-            _this_mod,
-            eg,
-            trio,
-        ]:
             try:
                 suberror_type = getattr(ns, type_name)
                 break
@@ -163,15 +154,12 @@ def unpack_error(
 
 
 def is_multi_cancelled(exc: BaseException) -> bool:
-    '''
+    """Predicate to determine if a ``trio.MultiError`` contains only
-    Predicate to determine if a possible ``eg.BaseExceptionGroup`` contains
+    ``trio.Cancelled`` sub-exceptions (and is likely the result of
-    only ``trio.Cancelled`` sub-exceptions (and is likely the result of
     cancelling a collection of subtasks.
 
-    '''
+    """
-    if isinstance(exc, eg.BaseExceptionGroup):
+    return not trio.MultiError.filter(
-        return exc.subgroup(
+        lambda exc: exc if not isinstance(exc, trio.Cancelled) else None,
-            lambda exc: isinstance(exc, trio.Cancelled)
+        exc,
-        ) is not None
+    )
-
-    return False

tractor/_ipc.py

@@ -22,21 +22,14 @@ from __future__ import annotations
 import platform
 import struct
 import typing
-from collections.abc import (
+from collections.abc import AsyncGenerator, AsyncIterator
-    AsyncGenerator,
-    AsyncIterator,
-)
 from typing import (
-    Any,
+    Any, Tuple, Optional,
-    runtime_checkable,
+    Type, Protocol, TypeVar,
-    Optional,
-    Protocol,
-    Type,
-    TypeVar,
 )
 
 from tricycle import BufferedReceiveStream
-import msgspec
+import msgpack
 import trio
 from async_generator import asynccontextmanager
 
@@ -49,7 +42,7 @@ _is_windows = platform.system() == 'Windows'
 log = get_logger(__name__)
 
 
-def get_stream_addrs(stream: trio.SocketStream) -> tuple:
+def get_stream_addrs(stream: trio.SocketStream) -> Tuple:
     # should both be IP sockets
     lsockname = stream.socket.getsockname()
     rsockname = stream.socket.getpeername()
@@ -67,7 +60,6 @@ MsgType = TypeVar("MsgType")
 # - https://jcristharif.com/msgspec/usage.html#structs
 
 
-@runtime_checkable
 class MsgTransport(Protocol[MsgType]):
 
     stream: trio.SocketStream
@@ -95,27 +87,23 @@ class MsgTransport(Protocol[MsgType]):
         ...
 
     @property
-    def laddr(self) -> tuple[str, int]:
+    def laddr(self) -> Tuple[str, int]:
         ...
 
     @property
-    def raddr(self) -> tuple[str, int]:
+    def raddr(self) -> Tuple[str, int]:
         ...
 
 
-# TODO: not sure why we have to inherit here, but it seems to be an
+class MsgpackTCPStream:
-# issue with ``get_msg_transport()`` returning a ``Type[Protocol]``;
-# probably should make a `mypy` issue?
-class MsgpackTCPStream(MsgTransport):
     '''
     A ``trio.SocketStream`` delivering ``msgpack`` formatted data
-    using the ``msgspec`` codec lib.
+    using ``msgpack-python``.
 
     '''
     def __init__(
         self,
         stream: trio.SocketStream,
-        prefix_size: int = 4,
 
     ) -> None:
 
@@ -132,92 +120,66 @@ class MsgpackTCPStream(MsgTransport):
         # public i guess?
         self.drained: list[dict] = []
 
-        self.recv_stream = BufferedReceiveStream(transport_stream=stream)
-        self.prefix_size = prefix_size
-
-        # TODO: struct aware messaging coders
-        self.encode = msgspec.msgpack.Encoder().encode
-        self.decode = msgspec.msgpack.Decoder().decode  # dict[str, Any])
-
     async def _iter_packets(self) -> AsyncGenerator[dict, None]:
-        '''Yield packets from the underlying stream.
+        '''
+        Yield packets from the underlying stream.
 
         '''
-        import msgspec  # noqa
+        unpacker = msgpack.Unpacker(
-        decodes_failed: int = 0
+            raw=False,
-
+        )
         while True:
             try:
-                header = await self.recv_stream.receive_exactly(4)
+                data = await self.stream.receive_some(2**10)
 
-            except (
+            except trio.BrokenResourceError as err:
-                ValueError,
+                msg = err.args[0]
-                ConnectionResetError,
 
-                # not sure entirely why we need this but without it we
+                # XXX: handle connection-reset-by-peer the same as a EOF.
-                # seem to be getting racy failures here on
+                # we're currently remapping this since we allow
-                # arbiter/registry name subs..
+                # a quick connect then drop for root actors when
-                trio.BrokenResourceError,
+                # checking to see if there exists an "arbiter"
-            ):
+                # on the chosen sockaddr (``_root.py:108`` or thereabouts)
-                raise TransportClosed(
+                if (
-                    f'transport {self} was already closed prior ro read'
+                    # nix
-                )
+                    '[Errno 104]' in msg or
 
-            if header == b'':
+                    # on windows it seems there are a variety of errors
-                raise TransportClosed(
+                    # to handle..
-                    f'transport {self} was already closed prior ro read'
+                    _is_windows
-                )
+                ):
-
+                    raise TransportClosed(
-            size, = struct.unpack("<I", header)
+                        f'{self} was broken with {msg}'
-
-            log.transport(f'received header {size}')  # type: ignore
-
-            msg_bytes = await self.recv_stream.receive_exactly(size)
-
-            log.transport(f"received {msg_bytes}")  # type: ignore
-            try:
-                yield self.decode(msg_bytes)
-            except (
-                msgspec.DecodeError,
-                UnicodeDecodeError,
-            ):
-                if decodes_failed < 4:
-                    # ignore decoding errors for now and assume they have to
-                    # do with a channel drop - hope that receiving from the
-                    # channel will raise an expected error and bubble up.
-                    try:
-                        msg_str: str | bytes = msg_bytes.decode()
-                    except UnicodeDecodeError:
-                        msg_str = msg_bytes
-
-                    log.error(
-                        '`msgspec` failed to decode!?\n'
-                        'dumping bytes:\n'
-                        f'{msg_str!r}'
                     )
-                    decodes_failed += 1
+
                 else:
                     raise
 
-    async def send(self, msg: Any) -> None:
+            log.transport(f"received {data}")  # type: ignore
-        async with self._send_lock:
 
-            bytes_data: bytes = self.encode(msg)
+            if data == b'':
+                raise TransportClosed(
+                    f'transport {self} was already closed prior to read'
+                )
 
-            # supposedly the fastest says,
+            unpacker.feed(data)
-            # https://stackoverflow.com/a/54027962
+            for packet in unpacker:
-            size: bytes = struct.pack("<I", len(bytes_data))
+                yield packet
-
-            return await self.stream.send_all(size + bytes_data)
 
     @property
-    def laddr(self) -> tuple[str, int]:
+    def laddr(self) -> Tuple[Any, ...]:
         return self._laddr
 
     @property
-    def raddr(self) -> tuple[str, int]:
+    def raddr(self) -> Tuple[Any, ...]:
         return self._raddr
 
+    async def send(self, msg: Any) -> None:
+        async with self._send_lock:
+            return await self.stream.send_all(
+                msgpack.dumps(msg, use_bin_type=True)
+            )
+
     async def recv(self) -> Any:
         return await self._agen.asend(None)
 
@@ -242,14 +204,99 @@ class MsgpackTCPStream(MsgTransport):
         return self.stream.socket.fileno() != -1
 
 
+class MsgspecTCPStream(MsgpackTCPStream):
+    '''
+    A ``trio.SocketStream`` delivering ``msgpack`` formatted data
+    using ``msgspec``.
+
+    '''
+    def __init__(
+        self,
+        stream: trio.SocketStream,
+        prefix_size: int = 4,
+
+    ) -> None:
+        import msgspec
+
+        super().__init__(stream)
+        self.recv_stream = BufferedReceiveStream(transport_stream=stream)
+        self.prefix_size = prefix_size
+
+        # TODO: struct aware messaging coders
+        self.encode = msgspec.msgpack.Encoder().encode
+        self.decode = msgspec.msgpack.Decoder().decode  # dict[str, Any])
+
+    async def _iter_packets(self) -> AsyncGenerator[dict, None]:
+        '''Yield packets from the underlying stream.
+
+        '''
+        import msgspec  # noqa
+        last_decode_failed: bool = False
+
+        while True:
+            try:
+                header = await self.recv_stream.receive_exactly(4)
+
+            except (
+                ValueError,
+
+                # not sure entirely why we need this but without it we
+                # seem to be getting racy failures here on
+                # arbiter/registry name subs..
+                trio.BrokenResourceError,
+            ):
+                raise TransportClosed(
+                    f'transport {self} was already closed prior ro read'
+                )
+
+            if header == b'':
+                raise TransportClosed(
+                    f'transport {self} was already closed prior ro read'
+                )
+
+            size, = struct.unpack("<I", header)
+
+            log.transport(f'received header {size}')  # type: ignore
+
+            msg_bytes = await self.recv_stream.receive_exactly(size)
+
+            log.transport(f"received {msg_bytes}")  # type: ignore
+            try:
+                yield self.decode(msg_bytes)
+            except (
+                msgspec.DecodingError,
+                UnicodeDecodeError,
+            ):
+                if not last_decode_failed:
+                    # ignore decoding errors for now and assume they have to
+                    # do with a channel drop - hope that receiving from the
+                    # channel will raise an expected error and bubble up.
+                    log.error('`msgspec` failed to decode!?')
+                    last_decode_failed = True
+                else:
+                    raise
+
+    async def send(self, msg: Any) -> None:
+        async with self._send_lock:
+
+            bytes_data: bytes = self.encode(msg)
+
+            # supposedly the fastest says,
+            # https://stackoverflow.com/a/54027962
+            size: bytes = struct.pack("<I", len(bytes_data))
+
+            return await self.stream.send_all(size + bytes_data)
+
+
 def get_msg_transport(
 
-    key: tuple[str, str],
+    key: Tuple[str, str],
 
 ) -> Type[MsgTransport]:
 
     return {
         ('msgpack', 'tcp'): MsgpackTCPStream,
+        ('msgspec', 'tcp'): MsgspecTCPStream,
     }[key]
 
 
@@ -258,18 +305,16 @@ class Channel:
     An inter-process channel for communication between (remote) actors.
 
     Wraps a ``MsgStream``: transport + encoding IPC connection.
-
     Currently we only support ``trio.SocketStream`` for transport
-    (aka TCP) and the ``msgpack`` interchange format via the ``msgspec``
+    (aka TCP).
-    codec libary.
 
     '''
     def __init__(
 
         self,
-        destaddr: Optional[tuple[str, int]],
+        destaddr: Optional[Tuple[str, int]],
 
-        msg_transport_type_key: tuple[str, str] = ('msgpack', 'tcp'),
+        msg_transport_type_key: Tuple[str, str] = ('msgpack', 'tcp'),
 
         # TODO: optional reconnection support?
         # auto_reconnect: bool = False,
@@ -280,6 +325,14 @@ class Channel:
         # self._recon_seq = on_reconnect
         # self._autorecon = auto_reconnect
 
+        # TODO: maybe expose this through the nursery api?
+        try:
+            # if installed load the msgspec transport since it's faster
+            import msgspec  # noqa
+            msg_transport_type_key = ('msgspec', 'tcp')
+        except ImportError:
+            pass
+
         self._destaddr = destaddr
         self._transport_key = msg_transport_type_key
 
@@ -289,7 +342,7 @@ class Channel:
         self.msgstream: Optional[MsgTransport] = None
 
         # set after handshake - always uid of far end
-        self.uid: Optional[tuple[str, str]] = None
+        self.uid: Optional[Tuple[str, str]] = None
 
         self._agen = self._aiter_recv()
         self._exc: Optional[Exception] = None  # set if far end actor errors
@@ -317,7 +370,7 @@ class Channel:
     def set_msg_transport(
         self,
         stream: trio.SocketStream,
-        type_key: Optional[tuple[str, str]] = None,
+        type_key: Optional[Tuple[str, str]] = None,
 
     ) -> MsgTransport:
         type_key = type_key or self._transport_key
@@ -332,16 +385,16 @@ class Channel:
         return object.__repr__(self)
 
     @property
-    def laddr(self) -> Optional[tuple[str, int]]:
+    def laddr(self) -> Optional[Tuple[str, int]]:
         return self.msgstream.laddr if self.msgstream else None
 
     @property
-    def raddr(self) -> Optional[tuple[str, int]]:
+    def raddr(self) -> Optional[Tuple[str, int]]:
         return self.msgstream.raddr if self.msgstream else None
 
     async def connect(
         self,
-        destaddr: tuple[Any, ...] | None = None,
+        destaddr: Tuple[Any, ...] = None,
         **kwargs
 
     ) -> MsgTransport:

tractor/_mp_fixup_main.py

@@ -18,9 +18,9 @@
 Helpers pulled mostly verbatim from ``multiprocessing.spawn``
 to aid with "fixing up" the ``__main__`` module in subprocesses.
 
-These helpers are needed for any spawing backend that doesn't already
+These helpers are needed for any spawing backend that doesn't already handle this.
-handle this. For example when using ``trio_run_in_process`` it is needed
+For example when using ``trio_run_in_process`` it is needed but obviously not when
-but obviously not when we're already using ``multiprocessing``.
+we're already using ``multiprocessing``.
 
 """
 import os
@@ -28,12 +28,13 @@ import sys
 import platform
 import types
 import runpy
+from typing import Dict
 
 
 ORIGINAL_DIR = os.path.abspath(os.getcwd())
 
 
-def _mp_figure_out_main() -> dict[str, str]:
+def _mp_figure_out_main() -> Dict[str, str]:
     """Taken from ``multiprocessing.spawn.get_preparation_data()``.
 
     Retrieve parent actor `__main__` module data.

tractor/_portal.py

@@ -35,7 +35,6 @@ import warnings
 import trio
 from async_generator import asynccontextmanager
 
-from .trionics import maybe_open_nursery
 from ._state import current_actor
 from ._ipc import Channel
 from .log import get_logger
@@ -45,27 +44,43 @@ from ._exceptions import (
     NoResult,
     ContextCancelled,
 )
-from ._streaming import (
+from ._streaming import Context, ReceiveMsgStream
-    Context,
-    MsgStream,
-)
 
 
 log = get_logger(__name__)
 
 
+@asynccontextmanager
+async def maybe_open_nursery(
+    nursery: trio.Nursery = None,
+    shield: bool = False,
+) -> AsyncGenerator[trio.Nursery, Any]:
+    '''
+    Create a new nursery if None provided.
+
+    Blocks on exit as expected if no input nursery is provided.
+
+    '''
+    if nursery is not None:
+        yield nursery
+    else:
+        async with trio.open_nursery() as nursery:
+            nursery.cancel_scope.shield = shield
+            yield nursery
+
+
 def _unwrap_msg(
+
     msg: dict[str, Any],
     channel: Channel
 
 ) -> Any:
-    __tracebackhide__ = True
     try:
         return msg['return']
     except KeyError:
         # internal error should never get here
         assert msg.get('cid'), "Received internal error at portal?"
-        raise unpack_error(msg, channel) from None
+        raise unpack_error(msg, channel)
 
 
 class MessagingError(Exception):
@@ -104,7 +119,7 @@ class Portal:
         # it is expected that ``result()`` will be awaited at some
         # point.
         self._expect_result: Optional[Context] = None
-        self._streams: set[MsgStream] = set()
+        self._streams: set[ReceiveMsgStream] = set()
         self.actor = current_actor()
 
     async def _submit_for_result(
@@ -139,7 +154,6 @@ class Portal:
         Return the result(s) from the remote actor's "main" task.
 
         '''
-        # __tracebackhide__ = True
         # Check for non-rpc errors slapped on the
         # channel for which we always raise
         exc = self.channel._exc
@@ -189,7 +203,7 @@ class Portal:
 
     async def cancel_actor(
         self,
-        timeout: float | None = None,
+        timeout: float = None,
 
     ) -> bool:
         '''
@@ -319,7 +333,7 @@ class Portal:
         async_gen_func: Callable,  # typing: ignore
         **kwargs,
 
-    ) -> AsyncGenerator[MsgStream, None]:
+    ) -> AsyncGenerator[ReceiveMsgStream, None]:
 
         if not inspect.isasyncgenfunction(async_gen_func):
             if not (
@@ -344,7 +358,7 @@ class Portal:
 
         try:
             # deliver receive only stream
-            async with MsgStream(
+            async with ReceiveMsgStream(
                 ctx, ctx._recv_chan,
             ) as rchan:
                 self._streams.add(rchan)
@@ -464,6 +478,7 @@ class Portal:
             # sure it's worth being pedantic:
             # Exception,
             # trio.Cancelled,
+            # trio.MultiError,
             # KeyboardInterrupt,
 
         ) as err:
@@ -496,14 +511,10 @@ class Portal:
             if ctx.chan.connected():
                 log.info(
                     'Waiting on final context-task result for\n'
-                    f'task: {cid}\n'
+                    f'task:{cid}\n'
-                    f'actor: {uid}'
+                    f'actor:{uid}'
                 )
                 result = await ctx.result()
-                log.runtime(
-                    f'Context {fn_name} returned '
-                    f'value from callee `{result}`'
-                )
 
             # though it should be impossible for any tasks
             # operating *in* this scope to have survived
@@ -525,22 +536,14 @@ class Portal:
                         f'task:{cid}\n'
                         f'actor:{uid}'
                     )
-            # XXX: (MEGA IMPORTANT) if this is a root opened process we
+            else:
-            # wait for any immediate child in debug before popping the
+                log.runtime(
-            # context from the runtime msg loop otherwise inside
+                    f'Context {fn_name} returned '
-            # ``Actor._push_result()`` the msg will be discarded and in
+                    f'value from callee `{result}`'
-            # 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.actor._contexts.pop((self.channel.uid, ctx.cid))
-                (self.channel.uid, ctx.cid),
-                None,
-            )
 
 
 @dataclass
@@ -597,11 +600,9 @@ async def open_portal(
 
         msg_loop_cs: Optional[trio.CancelScope] = None
         if start_msg_loop:
-            from ._runtime import process_messages
             msg_loop_cs = await nursery.start(
                 partial(
-                    process_messages,
+                    actor._process_messages,
-                    actor,
                     channel,
                     # if the local task is cancelled we want to keep
                     # the msg loop running until our block ends

tractor/_root.py

@@ -22,21 +22,14 @@ from contextlib import asynccontextmanager
 from functools import partial
 import importlib
 import logging
-import signal
-import sys
 import os
+from typing import Tuple, Optional, List, Any
 import typing
 import warnings
 
-
-from exceptiongroup import BaseExceptionGroup
 import trio
 
-from ._runtime import (
+from ._actor import Actor, Arbiter
-    Actor,
-    Arbiter,
-    async_main,
-)
 from . import _debug
 from . import _spawn
 from . import _state
@@ -56,45 +49,37 @@ logger = log.get_logger('tractor')
 @asynccontextmanager
 async def open_root_actor(
 
-    *,
     # defaults are above
-    arbiter_addr: tuple[str, int] | None = None,
+    arbiter_addr: Optional[Tuple[str, int]] = (
+        _default_arbiter_host,
+        _default_arbiter_port,
+    ),
 
-    # defaults are above
+    name: Optional[str] = 'root',
-    registry_addr: tuple[str, int] | None = None,
-
-    name: str | None = 'root',
 
     # either the `multiprocessing` start method:
     # https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
     # OR `trio` (the new default).
-    start_method: _spawn.SpawnMethodKey | None = None,
+    start_method: Optional[str] = None,
 
     # enables the multi-process debugger support
     debug_mode: bool = False,
 
     # internal logging
-    loglevel: str | None = None,
+    loglevel: Optional[str] = None,
 
-    enable_modules: list | None = None,
+    enable_modules: Optional[List] = None,
-    rpc_module_paths: list | None = None,
+    rpc_module_paths: Optional[List] = None,
 
 ) -> typing.Any:
-    '''
+    """Async entry point for ``tractor``.
-    Runtime init entry point for ``tractor``.
 
-    '''
+    """
     # Override the global debugger hook to make it play nice with
-    # ``trio``, see much discussion in:
+    # ``trio``, see:
     # https://github.com/python-trio/trio/issues/1155#issuecomment-742964018
-    builtin_bp_handler = sys.breakpointhook
-    orig_bp_path: str | None = os.environ.get('PYTHONBREAKPOINT', None)
     os.environ['PYTHONBREAKPOINT'] = 'tractor._debug._set_trace'
 
-    # attempt to retreive ``trio``'s sigint handler and stash it
-    # on our debugger lock state.
-    _debug.Lock._trio_handler = signal.getsignal(signal.SIGINT)
-
     # mark top most level process as root actor
     _state._runtime_vars['_is_root'] = True
 
@@ -113,24 +98,18 @@ async def open_root_actor(
     if start_method is not None:
         _spawn.try_set_start_method(start_method)
 
-    if arbiter_addr is not None:
+    arbiter_addr = (host, port) = arbiter_addr or (
-        warnings.warn(
+        _default_arbiter_host,
-            '`arbiter_addr` is now deprecated and has been renamed to'
+        _default_arbiter_port,
-            '`registry_addr`.\nUse that instead..',
-            DeprecationWarning,
-            stacklevel=2,
-        )
-
-    registry_addr = (host, port) = (
-        registry_addr
-        or arbiter_addr
-        or (
-            _default_arbiter_host,
-            _default_arbiter_port,
-        )
     )
 
-    loglevel = (loglevel or log._default_loglevel).upper()
+    if loglevel is None:
+        loglevel = log.get_loglevel()
+    else:
+        log._default_loglevel = loglevel
+        log.get_console_log(loglevel)
+
+    assert loglevel
 
     if debug_mode and _spawn._spawn_method == 'trio':
         _state._runtime_vars['_debug_mode'] = True
@@ -145,7 +124,7 @@ async def open_root_actor(
             logging.getLevelName(
                 # lul, need the upper case for the -> int map?
                 # sweet "dynamic function behaviour" stdlib...
-                loglevel,
+                loglevel.upper()
             ) > logging.getLevelName('PDB')
         ):
             loglevel = 'PDB'
@@ -155,25 +134,20 @@ async def open_root_actor(
             "Debug mode is only supported for the `trio` backend!"
         )
 
-    log.get_console_log(loglevel)
+    # make a temporary connection to see if an arbiter exists
+    arbiter_found = False
 
     try:
-        # make a temporary connection to see if an arbiter exists,
-        # if one can't be made quickly we assume none exists.
-        arbiter_found = False
-
         # TODO: this connect-and-bail forces us to have to carefully
         # rewrap TCP 104-connection-reset errors as EOF so as to avoid
         # propagating cancel-causing errors to the channel-msg loop
         # machinery.  Likely it would be better to eventually have
         # a "discovery" protocol with basic handshake instead.
-        with trio.move_on_after(1):
+        async with _connect_chan(host, port):
-            async with _connect_chan(host, port):
+            arbiter_found = True
-                arbiter_found = True
 
     except OSError:
-        # TODO: make this a "discovery" log level?
+        logger.warning(f"No actor could be found @ {host}:{port}")
-        logger.warning(f"No actor registry found @ {host}:{port}")
 
     # create a local actor and start up its main routine/task
     if arbiter_found:
@@ -183,7 +157,7 @@ async def open_root_actor(
 
         actor = Actor(
             name or 'anonymous',
-            arbiter_addr=registry_addr,
+            arbiter_addr=arbiter_addr,
             loglevel=loglevel,
             enable_modules=enable_modules,
         )
@@ -199,7 +173,7 @@ async def open_root_actor(
 
         actor = Arbiter(
             name or 'arbiter',
-            arbiter_addr=registry_addr,
+            arbiter_addr=arbiter_addr,
             loglevel=loglevel,
             enable_modules=enable_modules,
         )
@@ -215,14 +189,13 @@ async def open_root_actor(
         # start the actor runtime in a new task
         async with trio.open_nursery() as nursery:
 
-            # ``_runtime.async_main()`` creates an internal nursery and
+            # ``Actor._async_main()`` creates an internal nursery and
             # thus blocks here until the entire underlying actor tree has
             # terminated thereby conducting structured concurrency.
 
             await nursery.start(
                 partial(
-                    async_main,
+                    actor._async_main,
-                    actor,
                     accept_addr=(host, port),
                     parent_addr=None
                 )
@@ -230,10 +203,7 @@ async def open_root_actor(
             try:
                 yield actor
 
-            except (
+            except (Exception, trio.MultiError) as err:
-                Exception,
-                BaseExceptionGroup,
-            ) as err:
 
                 entered = await _debug._maybe_enter_pm(err)
 
@@ -246,8 +216,7 @@ async def open_root_actor(
             finally:
                 # NOTE: not sure if we'll ever need this but it's
                 # possibly better for even more determinism?
-                # logger.cancel(
+                # logger.cancel(f'Waiting on {len(nurseries)} nurseries in root..')
-                #     f'Waiting on {len(nurseries)} nurseries in root..')
                 # nurseries = actor._actoruid2nursery.values()
                 # async with trio.open_nursery() as tempn:
                 #     for an in nurseries:
@@ -257,40 +226,64 @@ async def open_root_actor(
                 await actor.cancel()
     finally:
         _state._current_actor = None
-
-        # restore breakpoint hook state
-        sys.breakpointhook = builtin_bp_handler
-        if orig_bp_path is not None:
-            os.environ['PYTHONBREAKPOINT'] = orig_bp_path
-        else:
-            # clear env back to having no entry
-            os.environ.pop('PYTHONBREAKPOINT')
-
         logger.runtime("Root actor terminated")
 
 
-def run_daemon(
+def run(
-    enable_modules: list[str],
+
+    # target
+    async_fn: typing.Callable[..., typing.Awaitable],
+    *args,
 
     # runtime kwargs
-    name: str | None = 'root',
+    name: Optional[str] = 'root',
-    registry_addr: tuple[str, int] = (
+    arbiter_addr: Tuple[str, int] = (
         _default_arbiter_host,
         _default_arbiter_port,
     ),
 
-    start_method: str | None = None,
+    start_method: Optional[str] = None,
     debug_mode: bool = False,
-    **kwargs
+    **kwargs,
 
+) -> Any:
+    """Run a trio-actor async function in process.
+
+    This is tractor's main entry and the start point for any async actor.
+    """
+    async def _main():
+
+        async with open_root_actor(
+            arbiter_addr=arbiter_addr,
+            name=name,
+            start_method=start_method,
+            debug_mode=debug_mode,
+            **kwargs,
+        ):
+
+            return await async_fn(*args)
+
+    warnings.warn(
+        "`tractor.run()` is now deprecated. `tractor` now"
+        " implicitly starts the root actor on first actor nursery"
+        " use. If you want to start the root actor manually, use"
+        " `tractor.open_root_actor()`.",
+        DeprecationWarning,
+        stacklevel=2,
+    )
+    return trio.run(_main)
+
+
+def run_daemon(
+    enable_modules: list[str],
+    **kwargs
 ) -> None:
     '''
-    Spawn daemon actor which will respond to RPC; the main task simply
+    Spawn daemon actor which will respond to RPC.
-    starts the runtime and then sleeps forever.
 
-    This is a very minimal convenience wrapper around starting
+    This is a convenience wrapper around
-    a "run-until-cancelled" root actor which can be started with a set
+    ``tractor.run(trio.sleep(float('inf')))`` such that the first actor spawned
-    of enabled modules for RPC request handling.
+    is meant to run forever responding to RPC requests.
 
     '''
     kwargs['enable_modules'] = list(enable_modules)
@@ -298,15 +291,4 @@ def run_daemon(
     for path in enable_modules:
         importlib.import_module(path)
 
-    async def _main():
+    return run(partial(trio.sleep, float('inf')), **kwargs)
-
-        async with open_root_actor(
-            registry_addr=registry_addr,
-            name=name,
-            start_method=start_method,
-            debug_mode=debug_mode,
-            **kwargs,
-        ):
-            return await trio.sleep_forever()
-
-    return trio.run(_main)

tractor/_spawn.py

@@ -18,22 +18,30 @@
 Machinery for actor process spawning using multiple backends.
 
 """
-from __future__ import annotations
 import sys
+import multiprocessing as mp
 import platform
 from typing import (
-    Any,
+    Any, Dict, Optional, Callable,
-    Awaitable,
-    Literal,
-    Callable,
     TypeVar,
-    TYPE_CHECKING,
 )
+from collections.abc import Awaitable
 
-from exceptiongroup import BaseExceptionGroup
 import trio
 from trio_typing import TaskStatus
 
+try:
+    from multiprocessing import semaphore_tracker  # type: ignore
+    resource_tracker = semaphore_tracker
+    resource_tracker._resource_tracker = resource_tracker._semaphore_tracker
+except ImportError:
+    # 3.8 introduces a more general version that also tracks shared mems
+    from multiprocessing import resource_tracker  # type: ignore
+
+from multiprocessing import forkserver  # type: ignore
+from typing import Tuple
+
+from . import _forkserver_override
 from ._debug import (
     maybe_wait_for_debugger,
     acquire_debug_lock,
@@ -44,33 +52,24 @@ from ._state import (
     is_root_process,
     debug_mode,
 )
+
 from .log import get_logger
 from ._portal import Portal
-from ._runtime import Actor
+from ._actor import Actor
 from ._entry import _mp_main
 from ._exceptions import ActorFailure
 
 
-if TYPE_CHECKING:
-    from ._supervise import ActorNursery
-    import multiprocessing as mp
-    ProcessType = TypeVar('ProcessType', mp.Process, trio.Process)
-
 log = get_logger('tractor')
+ProcessType = TypeVar('ProcessType', mp.Process, trio.Process)
 
 # placeholder for an mp start context if so using that backend
-_ctx: mp.context.BaseContext | None = None
+_ctx: Optional[mp.context.BaseContext] = None
-SpawnMethodKey = Literal[
+_spawn_method: str = "trio"
-    'trio',  # supported on all platforms
-    'mp_spawn',
-    'mp_forkserver',  # posix only
-]
-_spawn_method: SpawnMethodKey = 'trio'
 
 
 if platform.system() == 'Windows':
 
-    import multiprocessing as mp
     _ctx = mp.get_context("spawn")
 
     async def proc_waiter(proc: mp.Process) -> None:
@@ -82,10 +81,7 @@ else:
         await trio.lowlevel.wait_readable(proc.sentinel)
 
 
-def try_set_start_method(
+def try_set_start_method(name: str) -> Optional[mp.context.BaseContext]:
-    key: SpawnMethodKey
-
-) -> mp.context.BaseContext | None:
     '''
     Attempt to set the method for process starting, aka the "actor
     spawning backend".
@@ -96,34 +92,30 @@ def try_set_start_method(
     ``subprocess.Popen``.
 
     '''
-    import multiprocessing as mp
     global _ctx
     global _spawn_method
 
-    mp_methods = mp.get_all_start_methods()
+    methods = mp.get_all_start_methods()
-    if 'fork' in mp_methods:
+    if 'fork' in methods:
         # forking is incompatible with ``trio``s global task tree
-        mp_methods.remove('fork')
+        methods.remove('fork')
 
-    match key:
+    # supported on all platforms
-        case 'mp_forkserver':
+    methods += ['trio']
-            from . import _forkserver_override
-            _forkserver_override.override_stdlib()
-            _ctx = mp.get_context('forkserver')
 
-        case 'mp_spawn':
+    if name not in methods:
-            _ctx = mp.get_context('spawn')
+        raise ValueError(
+            f"Spawn method `{name}` is invalid please choose one of {methods}"
+        )
+    elif name == 'forkserver':
+        _forkserver_override.override_stdlib()
+        _ctx = mp.get_context(name)
+    elif name == 'trio':
+        _ctx = None
+    else:
+        _ctx = mp.get_context(name)
 
-        case 'trio':
+    _spawn_method = name
-            _ctx = None
-
-        case _:
-            raise ValueError(
-                f'Spawn method `{key}` is invalid!\n'
-                f'Please choose one of {SpawnMethodKey}'
-            )
-
-    _spawn_method = key
     return _ctx
 
 
@@ -139,7 +131,6 @@ async def exhaust_portal(
     If the main task is an async generator do our best to consume
     what's left of it.
     '''
-    __tracebackhide__ = True
     try:
         log.debug(f"Waiting on final result from {actor.uid}")
 
@@ -147,11 +138,8 @@ async def exhaust_portal(
         # always be established and shutdown using a context manager api
         final = await portal.result()
 
-    except (
+    except (Exception, trio.MultiError) as err:
-        Exception,
+        # we reraise in the parent task via a ``trio.MultiError``
-        BaseExceptionGroup,
-    ) 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
@@ -167,7 +155,7 @@ async def cancel_on_completion(
 
     portal: Portal,
     actor: Actor,
-    errors: dict[tuple[str, str], Exception],
+    errors: Dict[Tuple[str, str], Exception],
 
 ) -> None:
     '''
@@ -179,7 +167,7 @@ async def cancel_on_completion(
     '''
     # 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
+    # a MultiError and we still send out a cancel request
     result = await exhaust_portal(portal, actor)
     if isinstance(result, Exception):
         errors[actor.uid] = result
@@ -199,37 +187,16 @@ async def cancel_on_completion(
 async def do_hard_kill(
     proc: trio.Process,
     terminate_after: int = 3,
-
 ) -> None:
     # 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
+        # NOTE: This ``__aexit__()`` shields internally.
-        # (in 0.20.0) ``trio._subrocess.Process.aclose()``, orig doc
+        async with proc:  # calls ``trio.Process.aclose()``
-        # string:
+            log.debug(f"Terminating {proc}")
-        #
-        # Close any pipes we have to the process (both input and output)
-        # and wait for it to exit. If cancelled, kills the process and
-        # waits for it to finish exiting before propagating the
-        # cancellation.
-        with trio.CancelScope(shield=True):
-            if proc.stdin is not None:
-                await proc.stdin.aclose()
-            if proc.stdout is not None:
-                await proc.stdout.aclose()
-            if proc.stderr is not None:
-                await proc.stderr.aclose()
-        try:
-            await proc.wait()
-        finally:
-            if proc.returncode is None:
-                proc.kill()
-                with trio.CancelScope(shield=True):
-                    await proc.wait()
 
     if cs.cancelled_caught:
         # XXX: should pretty much never get here unless we have
@@ -280,65 +247,29 @@ async def soft_wait(
 
             if proc.poll() is None:  # type: ignore
                 log.warning(
-                    'Actor still alive after cancel request:\n'
+                    f'Process still alive after cancel request:\n{uid}')
-                    f'{uid}'
-                )
 
                 n.cancel_scope.cancel()
         raise
 
 
 async def new_proc(
+
     name: str,
-    actor_nursery: ActorNursery,
+    actor_nursery: 'ActorNursery',  # type: ignore  # noqa
     subactor: Actor,
-    errors: dict[tuple[str, str], Exception],
+    errors: Dict[Tuple[str, str], Exception],
 
     # passed through to actor main
-    bind_addr: tuple[str, int],
+    bind_addr: Tuple[str, int],
-    parent_addr: tuple[str, int],
+    parent_addr: Tuple[str, int],
-    _runtime_vars: dict[str, Any],  # serialized and sent to _child
+    _runtime_vars: Dict[str, Any],  # serialized and sent to _child
 
     *,
 
     infect_asyncio: bool = False,
     task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
 
-) -> None:
-
-    # lookup backend spawning target
-    target = _methods[_spawn_method]
-
-    # mark the new actor with the global spawn method
-    subactor._spawn_method = _spawn_method
-
-    await target(
-        name,
-        actor_nursery,
-        subactor,
-        errors,
-        bind_addr,
-        parent_addr,
-        _runtime_vars,  # run time vars
-        infect_asyncio=infect_asyncio,
-        task_status=task_status,
-    )
-
-
-async def trio_proc(
-    name: str,
-    actor_nursery: ActorNursery,
-    subactor: Actor,
-    errors: dict[tuple[str, str], Exception],
-
-    # passed through to actor main
-    bind_addr: tuple[str, int],
-    parent_addr: tuple[str, int],
-    _runtime_vars: dict[str, Any],  # serialized and sent to _child
-    *,
-    infect_asyncio: bool = False,
-    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
-
 ) -> None:
     '''
     Create a new ``Process`` using a "spawn method" as (configured using
@@ -348,191 +279,217 @@ async def trio_proc(
     here is to be considered the core supervision strategy.
 
     '''
-    spawn_cmd = [
+    # mark the new actor with the global spawn method
-        sys.executable,
+    subactor._spawn_method = _spawn_method
-        "-m",
+    uid = subactor.uid
-        # Hardcode this (instead of using ``_child.__name__`` to avoid a
-        # double import warning: https://stackoverflow.com/a/45070583
-        "tractor._child",
-        # We provide the child's unique identifier on this exec/spawn
-        # line for debugging purposes when viewing the process tree from
-        # the OS; it otherwise can be passed via the parent channel if
-        # we prefer in the future (for privacy).
-        "--uid",
-        str(subactor.uid),
-        # Address the child must connect to on startup
-        "--parent_addr",
-        str(parent_addr)
-    ]
 
-    if subactor.loglevel:
+    if _spawn_method == 'trio':
-        spawn_cmd += [
+        spawn_cmd = [
-            "--loglevel",
+            sys.executable,
-            subactor.loglevel
+            "-m",
+            # Hardcode this (instead of using ``_child.__name__`` to avoid a
+            # double import warning: https://stackoverflow.com/a/45070583
+            "tractor._child",
+            # We provide the child's unique identifier on this exec/spawn
+            # line for debugging purposes when viewing the process tree from
+            # the OS; it otherwise can be passed via the parent channel if
+            # we prefer in the future (for privacy).
+            "--uid",
+            str(uid),
+            # Address the child must connect to on startup
+            "--parent_addr",
+            str(parent_addr)
         ]
-    # Tell child to run in guest mode on top of ``asyncio`` loop
-    if infect_asyncio:
-        spawn_cmd.append("--asyncio")
 
-    cancelled_during_spawn: bool = False
+        if subactor.loglevel:
-    proc: trio.Process | None = None
+            spawn_cmd += [
-    try:
+                "--loglevel",
+                subactor.loglevel
+            ]
+        # Tell child to run in guest mode on top of ``asyncio`` loop
+        if infect_asyncio:
+            spawn_cmd.append("--asyncio")
+
+        cancelled_during_spawn: bool = False
+        proc: Optional[trio.Process] = None
         try:
-            # TODO: needs ``trio_typing`` patch?
+            try:
-            proc = await trio.lowlevel.open_process(spawn_cmd)
+                proc = await trio.open_process(spawn_cmd)
 
-            log.runtime(f"Started {proc}")
+                log.runtime(f"Started {proc}")
 
-            # wait for actor to spawn and connect back to us
+                # wait for actor to spawn and connect back to us
-            # channel should have handshake completed by the
+                # channel should have handshake completed by the
-            # local actor by the time we get a ref to it
+                # local actor by the time we get a ref to it
-            event, chan = await actor_nursery._actor.wait_for_peer(
+                event, chan = await actor_nursery._actor.wait_for_peer(uid)
-                subactor.uid)
 
-        except trio.Cancelled:
+            except trio.Cancelled:
-            cancelled_during_spawn = True
+                cancelled_during_spawn = True
-            # we may cancel before the child connects back in which
+                # we may cancel before the child connects back in which
-            # case avoid clobbering the pdb tty.
+                # case avoid clobbering the pdb tty.
-            if debug_mode():
+                if debug_mode():
-                with trio.CancelScope(shield=True):
+                    with trio.CancelScope(shield=True):
-                    # don't clobber an ongoing pdb
+                        # don't clobber an ongoing pdb
-                    if is_root_process():
+                        if is_root_process():
-                        await maybe_wait_for_debugger()
+                            await maybe_wait_for_debugger()
 
-                    elif proc is not None:
+                        elif proc is not None:
-                        async with acquire_debug_lock(subactor.uid):
+                            async with acquire_debug_lock(uid):
-                            # soft wait on the proc to terminate
+                                # soft wait on the proc to terminate
-                            with trio.move_on_after(0.5):
+                                with trio.move_on_after(0.5):
-                                await proc.wait()
+                                    await proc.wait()
-            raise
+                raise
 
-        # a sub-proc ref **must** exist now
+            portal = Portal(chan)
-        assert proc
+            actor_nursery._children[subactor.uid] = (
+                subactor, proc, portal)
 
-        portal = Portal(chan)
+            # send additional init params
-        actor_nursery._children[subactor.uid] = (
+            await chan.send({
-            subactor,
+                "_parent_main_data": subactor._parent_main_data,
-            proc,
+                "enable_modules": subactor.enable_modules,
-            portal,
+                "_arb_addr": subactor._arb_addr,
-        )
+                "bind_host": bind_addr[0],
+                "bind_port": bind_addr[1],
+                "_runtime_vars": _runtime_vars,
+            })
 
-        # send additional init params
+            # track subactor in current nursery
-        await chan.send({
+            curr_actor = current_actor()
-            "_parent_main_data": subactor._parent_main_data,
+            curr_actor._actoruid2nursery[subactor.uid] = actor_nursery
-            "enable_modules": subactor.enable_modules,
-            "_arb_addr": subactor._arb_addr,
-            "bind_host": bind_addr[0],
-            "bind_port": bind_addr[1],
-            "_runtime_vars": _runtime_vars,
-        })
 
-        # track subactor in current nursery
+            # resume caller at next checkpoint now that child is up
-        curr_actor = current_actor()
+            task_status.started(portal)
-        curr_actor._actoruid2nursery[subactor.uid] = actor_nursery
 
-        # resume caller at next checkpoint now that child is up
+            # wait for ActorNursery.wait() to be called
-        task_status.started(portal)
+            n_exited = actor_nursery._join_procs
-
-        # wait for ActorNursery.wait() to be called
-        with trio.CancelScope(shield=True):
-            await actor_nursery._join_procs.wait()
-
-        async with trio.open_nursery() as nursery:
-            if portal in actor_nursery._cancel_after_result_on_exit:
-                nursery.start_soon(
-                    cancel_on_completion,
-                    portal,
-                    subactor,
-                    errors
-                )
-
-            # This is a "soft" (cancellable) join/reap which
-            # will remote cancel the actor on a ``trio.Cancelled``
-            # condition.
-            await soft_wait(
-                proc,
-                trio.Process.wait,
-                portal
-            )
-
-            # cancel result waiter that may have been spawned in
-            # tandem if not done already
-            log.warning(
-                "Cancelling existing result waiter task for "
-                f"{subactor.uid}")
-            nursery.cancel_scope.cancel()
-
-    finally:
-        # XXX NOTE XXX: The "hard" reap since no actor zombies are
-        # allowed! Do this **after** cancellation/teardown to avoid
-        # killing the process too early.
-        if proc:
-            log.cancel(f'Hard reap sequence starting for {subactor.uid}')
             with trio.CancelScope(shield=True):
+                await n_exited.wait()
 
-                # don't clobber an ongoing pdb
+            async with trio.open_nursery() as nursery:
-                if cancelled_during_spawn:
-                    # Try again to avoid TTY clobbering.
-                    async with acquire_debug_lock(subactor.uid):
-                        with trio.move_on_after(0.5):
-                            await proc.wait()
 
-                if is_root_process():
+                async def soft_wait_and_maybe_cancel_ria_task():
-                    # TODO: solve the following issue where we need
+                    # This is a "soft" (cancellable) join/reap which
-                    # to do a similar wait like this but in an
+                    # will remote cancel the actor on a ``trio.Cancelled``
-                    # "intermediary" parent actor that itself isn't
+                    # condition.
-                    # in debug but has a child that is, and we need
+                    await soft_wait(
-                    # to hold off on relaying SIGINT until that child
+                        proc,
-                    # is complete.
+                        trio.Process.wait,
-                    # https://github.com/goodboy/tractor/issues/320
+                        portal
-                    await maybe_wait_for_debugger(
-                        child_in_debug=_runtime_vars.get(
-                            '_debug_mode', False),
                     )
 
-                if proc.poll() is None:
+                    if n_exited.is_set():
-                    log.cancel(f"Attempting to hard kill {proc}")
+                        # cancel result waiter that may have been spawned in
-                    await do_hard_kill(proc)
+                        # tandem if not done already
+                        log.warning(
+                            "Cancelling existing result waiter task for "
+                            f"{subactor.uid}"
+                        )
+                        nursery.cancel_scope.cancel()
 
-                log.debug(f"Joined {proc}")
+                    else:
-        else:
+                        log.warning(
-            log.warning('Nursery cancelled before sub-proc started')
+                            f'Process for actor {uid} terminated before'
+                            'nursery exit. ' 'This may mean an IPC'
+                            'connection failed!'
+                        )
 
-        if not cancelled_during_spawn:
+                nursery.start_soon(soft_wait_and_maybe_cancel_ria_task)
-            # pop child entry to indicate we no longer managing this
+
-            # subactor
+                # TODO: when we finally remove the `.run_in_actor()` api
-            actor_nursery._children.pop(subactor.uid)
+                # we should be able to entirely drop these 2 blocking calls:
+                # - we don't need to wait on nursery exit to capture
+                #   process-spawn-machinery level errors (and propagate them).
+                # - we don't need to wait on final results from ria portals
+                #   since this will be done in some higher level wrapper API.
+
+                # XXX: interestingly we can't put this here bc it causes
+                # the pub-sub tests to fail? wth.. should probably drop
+                # those XD
+                # wait for ActorNursery.wait() to be called
+                # with trio.CancelScope(shield=True):
+                #     await n_exited.wait()
+
+                if portal in actor_nursery._cancel_after_result_on_exit:
+                    nursery.start_soon(
+                        cancel_on_completion,
+                        portal,
+                        subactor,
+                        errors
+                    )
+
+        finally:
+            # The "hard" reap since no actor zombies are allowed!
+            # XXX: do this **after** cancellation/tearfown to avoid
+            # killing the process too early.
+            if proc:
+                log.cancel(f'Hard reap sequence starting for {uid}')
+                with trio.CancelScope(shield=True):
+
+                    # don't clobber an ongoing pdb
+                    if cancelled_during_spawn:
+                        # Try again to avoid TTY clobbering.
+                        async with acquire_debug_lock(uid):
+                            with trio.move_on_after(0.5):
+                                await proc.wait()
+
+                    if is_root_process():
+
+                        await maybe_wait_for_debugger(
+                            child_in_debug=_runtime_vars.get(
+                                '_debug_mode', False)
+                        )
+
+                    if proc.poll() is None:
+                        log.cancel(f"Attempting to hard kill {proc}")
+                        await do_hard_kill(proc)
+
+                    log.debug(f"Joined {proc}")
+            else:
+                log.warning('Nursery cancelled before sub-proc started')
+
+            if not cancelled_during_spawn:
+                # pop child entry to indicate we no longer managing this
+                # subactor
+                actor_nursery._children.pop(subactor.uid)
+
+    else:
+        # `multiprocessing`
+        # async with trio.open_nursery() as nursery:
+        await mp_new_proc(
+            name=name,
+            actor_nursery=actor_nursery,
+            subactor=subactor,
+            errors=errors,
+
+            # passed through to actor main
+            bind_addr=bind_addr,
+            parent_addr=parent_addr,
+            _runtime_vars=_runtime_vars,
+            infect_asyncio=infect_asyncio,
+            task_status=task_status,
+        )
 
 
-async def mp_proc(
+async def mp_new_proc(
+
     name: str,
-    actor_nursery: ActorNursery,  # type: ignore  # noqa
+    actor_nursery: 'ActorNursery',  # type: ignore  # noqa
     subactor: Actor,
-    errors: dict[tuple[str, str], Exception],
+    errors: Dict[Tuple[str, str], Exception],
     # passed through to actor main
-    bind_addr: tuple[str, int],
+    bind_addr: Tuple[str, int],
-    parent_addr: tuple[str, int],
+    parent_addr: Tuple[str, int],
-    _runtime_vars: dict[str, Any],  # serialized and sent to _child
+    _runtime_vars: Dict[str, Any],  # serialized and sent to _child
     *,
     infect_asyncio: bool = False,
     task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
 
 ) -> None:
 
-    # uggh zone
-    try:
-        from multiprocessing import semaphore_tracker  # type: ignore
-        resource_tracker = semaphore_tracker
-        resource_tracker._resource_tracker = resource_tracker._semaphore_tracker  # noqa
-    except ImportError:
-        # 3.8 introduces a more general version that also tracks shared mems
-        from multiprocessing import resource_tracker  # type: ignore
-
     assert _ctx
     start_method = _ctx.get_start_method()
     if start_method == 'forkserver':
-
-        from multiprocessing import forkserver  # type: ignore
         # XXX do our hackery on the stdlib to avoid multiple
         # forkservers (one at each subproc layer).
         fs = forkserver._forkserver
@@ -544,24 +501,23 @@ async def mp_proc(
             # forkserver.set_forkserver_preload(enable_modules)
             forkserver.ensure_running()
             fs_info = (
-                fs._forkserver_address,  # type: ignore  # noqa
+                fs._forkserver_address,
-                fs._forkserver_alive_fd,  # type: ignore  # noqa
+                fs._forkserver_alive_fd,
                 getattr(fs, '_forkserver_pid', None),
                 getattr(
                     resource_tracker._resource_tracker, '_pid', None),
                 resource_tracker._resource_tracker._fd,
             )
-        else:  # request to forkerserver to fork a new child
+        else:
             assert curr_actor._forkserver_info
             fs_info = (
-                fs._forkserver_address,  # type: ignore  # noqa
+                fs._forkserver_address,
-                fs._forkserver_alive_fd,  # type: ignore  # noqa
+                fs._forkserver_alive_fd,
-                fs._forkserver_pid,  # type: ignore  # noqa
+                fs._forkserver_pid,
                 resource_tracker._resource_tracker._pid,
                 resource_tracker._resource_tracker._fd,
              ) = curr_actor._forkserver_info
     else:
-        # spawn method
         fs_info = (None, None, None, None, None)
 
     proc: mp.Process = _ctx.Process(  # type: ignore
@@ -570,7 +526,7 @@ async def mp_proc(
             subactor,
             bind_addr,
             fs_info,
-            _spawn_method,
+            start_method,
             parent_addr,
             infect_asyncio,
         ),
@@ -664,16 +620,4 @@ async def mp_proc(
         log.debug(f"Joined {proc}")
 
         # pop child entry to indicate we are no longer managing subactor
-        actor_nursery._children.pop(subactor.uid)
+        subactor, proc, portal = actor_nursery._children.pop(subactor.uid)
-
-        # TODO: prolly report to ``mypy`` how this causes all sorts of
-        # false errors..
-        # subactor, proc, portal = actor_nursery._children.pop(subactor.uid)
-
-
-# proc spawning backend target map
-_methods: dict[SpawnMethodKey, Callable] = {
-    'trio': trio_proc,
-    'mp_spawn': mp_proc,
-    'mp_forkserver': mp_proc,
-}

tractor/_state.py

@@ -18,10 +18,9 @@
 Per process state
 
 """
-from typing import (
+from typing import Optional, Dict, Any
-    Optional,
+from collections.abc import Mapping
-    Any,
+import multiprocessing as mp
-)
 
 import trio
 
@@ -29,7 +28,7 @@ from ._exceptions import NoRuntime
 
 
 _current_actor: Optional['Actor'] = None  # type: ignore # noqa
-_runtime_vars: dict[str, Any] = {
+_runtime_vars: Dict[str, Any] = {
     '_debug_mode': False,
     '_is_root': False,
     '_root_mailbox': (None, None)
@@ -45,10 +44,33 @@ def current_actor(err_on_no_runtime: bool = True) -> 'Actor':  # type: ignore #
     return _current_actor
 
 
+_conc_name_getters = {
+    'task': trio.lowlevel.current_task,
+    'actor': current_actor
+}
+
+
+class ActorContextInfo(Mapping):
+    "Dyanmic lookup for local actor and task names"
+    _context_keys = ('task', 'actor')
+
+    def __len__(self):
+        return len(self._context_keys)
+
+    def __iter__(self):
+        return iter(self._context_keys)
+
+    def __getitem__(self, key: str) -> str:
+        try:
+            return _conc_name_getters[key]().name  # type: ignore
+        except RuntimeError:
+            # no local actor/task context initialized yet
+            return f'no {key} context'
+
+
 def is_main_process() -> bool:
     """Bool determining if this actor is running in the top-most process.
     """
-    import multiprocessing as mp
     return mp.current_process().name == 'MainProcess'
 
 

tractor/_streaming.py

@@ -23,10 +23,8 @@ import inspect
 from contextlib import asynccontextmanager
 from dataclasses import dataclass
 from typing import (
-    Any,
+    Any, Optional, Callable,
-    Optional,
+    AsyncGenerator, Dict,
-    Callable,
-    AsyncGenerator,
     AsyncIterator
 )
 
@@ -50,13 +48,12 @@ log = get_logger(__name__)
 # - use __slots__ on ``Context``?
 
 
-class MsgStream(trio.abc.Channel):
+class ReceiveMsgStream(trio.abc.ReceiveChannel):
     '''
-    A bidirectional message stream for receiving logically sequenced
+    A IPC message stream for receiving logically sequenced values over
-    values over an inter-actor IPC ``Channel``.
+    an inter-actor ``Channel``. This is the type returned to a local
-
+    task which entered either ``Portal.open_stream_from()`` or
-    This is the type returned to a local task which entered either
+    ``Context.open_stream()``.
-    ``Portal.open_stream_from()`` or ``Context.open_stream()``.
 
     Termination rules:
 
@@ -98,9 +95,6 @@ class MsgStream(trio.abc.Channel):
         if self._eoc:
             raise trio.EndOfChannel
 
-        if self._closed:
-            raise trio.ClosedResourceError('This stream was closed')
-
         try:
             msg = await self._rx_chan.receive()
             return msg['yield']
@@ -114,9 +108,6 @@ class MsgStream(trio.abc.Channel):
             # - 'error'
             # possibly just handle msg['stop'] here!
 
-            if self._closed:
-                raise trio.ClosedResourceError('This stream was closed')
-
             if msg.get('stop') or self._eoc:
                 log.debug(f"{self} was stopped at remote end")
 
@@ -196,6 +187,7 @@ class MsgStream(trio.abc.Channel):
             return
 
         self._eoc = True
+        self._closed = True
 
         # NOTE: this is super subtle IPC messaging stuff:
         # Relay stop iteration to far end **iff** we're
@@ -212,32 +204,29 @@ class MsgStream(trio.abc.Channel):
 
         # In the bidirectional case, `Context.open_stream()` will create
         # the `Actor._cids2qs` entry from a call to
-        # `Actor.get_context()` and will call us here to send the stop
+        # `Actor.get_context()` and will send the stop message in
-        # msg in ``__aexit__()`` on teardown.
+        # ``__aexit__()`` on teardown so it **does not** need to be
-        try:
+        # called here.
-            # NOTE: if this call is cancelled we expect this end to
+        if not self._ctx._portal:
-            # handle as though the stop was never sent (though if it
+            # Only for 2 way streams can we can send stop from the
-            # was it shouldn't matter since it's unlikely a user
+            # caller side.
-            # will try to re-use a stream after attemping to close
+            try:
-            # it).
+                # NOTE: if this call is cancelled we expect this end to
-            with trio.CancelScope(shield=True):
+                # handle as though the stop was never sent (though if it
-                await self._ctx.send_stop()
+                # was it shouldn't matter since it's unlikely a user
+                # will try to re-use a stream after attemping to close
+                # it).
+                with trio.CancelScope(shield=True):
+                    await self._ctx.send_stop()
 
-        except (
+            except (
-            trio.BrokenResourceError,
+                trio.BrokenResourceError,
-            trio.ClosedResourceError
+                trio.ClosedResourceError
-        ):
+            ):
-            # the underlying channel may already have been pulled
+                # the underlying channel may already have been pulled
-            # in which case our stop message is meaningless since
+                # in which case our stop message is meaningless since
-            # it can't traverse the transport.
+                # it can't traverse the transport.
-            ctx = self._ctx
+                log.debug(f'Channel for {self} was already closed')
-            log.warning(
-                f'Stream was already destroyed?\n'
-                f'actor: {ctx.chan.uid}\n'
-                f'ctx id: {ctx.cid}'
-            )
-
-        self._closed = True
 
         # Do we close the local mem chan ``self._rx_chan`` ??!?
 
@@ -280,8 +269,7 @@ class MsgStream(trio.abc.Channel):
         self,
 
     ) -> AsyncIterator[BroadcastReceiver]:
-        '''
+        '''Allocate and return a ``BroadcastReceiver`` which delegates
-        Allocate and return a ``BroadcastReceiver`` which delegates
         to this message stream.
 
         This allows multiple local tasks to receive each their own copy
@@ -318,15 +306,15 @@ class MsgStream(trio.abc.Channel):
         async with self._broadcaster.subscribe() as bstream:
             assert bstream.key != self._broadcaster.key
             assert bstream._recv == self._broadcaster._recv
-
-            # NOTE: we patch on a `.send()` to the bcaster so that the
-            # caller can still conduct 2-way streaming using this
-            # ``bstream`` handle transparently as though it was the msg
-            # stream instance.
-            bstream.send = self.send  # type: ignore
-
             yield bstream
 
+
+class MsgStream(ReceiveMsgStream, trio.abc.Channel):
+    '''
+    Bidirectional message stream for use within an inter-actor actor
+    ``Context```.
+
+    '''
     async def send(
         self,
         data: Any
@@ -381,8 +369,6 @@ class Context:
 
     # status flags
     _cancel_called: bool = False
-    _cancel_msg: Optional[str] = None
-    _enter_debugger_on_cancel: bool = True
     _started_called: bool = False
     _started_received: bool = False
     _stream_opened: bool = False
@@ -407,7 +393,7 @@ class Context:
 
     async def _maybe_raise_from_remote_msg(
         self,
-        msg: dict[str, Any],
+        msg: Dict[str, Any],
 
     ) -> None:
         '''
@@ -464,11 +450,7 @@ class Context:
                 if not self._scope_nursery._closed:  # type: ignore
                     self._scope_nursery.start_soon(raiser)
 
-    async def cancel(
+    async def cancel(self) -> None:
-        self,
-        msg: Optional[str] = None,
-
-    ) -> None:
         '''
         Cancel this inter-actor-task context.
 
@@ -477,8 +459,6 @@ class Context:
 
         '''
         side = 'caller' if self._portal else 'callee'
-        if msg:
-            assert side == 'callee', 'Only callee side can provide cancel msg'
 
         log.cancel(f'Cancelling {side} side of context to {self.chan.uid}')
 
@@ -515,10 +495,8 @@ class Context:
                     log.cancel(
                         "Timed out on cancelling remote task "
                         f"{cid} for {self._portal.channel.uid}")
-
-        # callee side remote task
         else:
-            self._cancel_msg = msg
+            # callee side remote task
 
             # TODO: should we have an explicit cancel message
             # or is relaying the local `trio.Cancelled` as an
@@ -603,34 +581,27 @@ class Context:
         async with MsgStream(
             ctx=self,
             rx_chan=ctx._recv_chan,
-        ) as stream:
+        ) as rchan:
 
             if self._portal:
-                self._portal._streams.add(stream)
+                self._portal._streams.add(rchan)
 
             try:
                 self._stream_opened = True
 
-                # XXX: do we need this?
+                # ensure we aren't cancelled before delivering
-                # ensure we aren't cancelled before yielding the stream
+                # the stream
                 # await trio.lowlevel.checkpoint()
-                yield stream
+                yield rchan
 
-                # NOTE: Make the stream "one-shot use".  On exit, signal
+                # XXX: Make the stream "one-shot use".  On exit, signal
                 # ``trio.EndOfChannel``/``StopAsyncIteration`` to the
                 # far end.
-                await stream.aclose()
+                await self.send_stop()
 
             finally:
                 if self._portal:
-                    try:
+                    self._portal._streams.remove(rchan)
-                        self._portal._streams.remove(stream)
-                    except KeyError:
-                        log.warning(
-                            f'Stream was already destroyed?\n'
-                            f'actor: {self.chan.uid}\n'
-                            f'ctx id: {self.cid}'
-                        )
 
     async def result(self) -> Any:
         '''

tractor/_supervise.py

@@ -18,23 +18,20 @@
 ``trio`` inspired apis and helpers
 
 """
-from contextlib import asynccontextmanager as acm
 from functools import partial
 import inspect
-from typing import (
+import multiprocessing as mp
-    Optional,
+from typing import Tuple, List, Dict, Optional
-    TYPE_CHECKING,
-)
 import typing
 import warnings
 
-from exceptiongroup import BaseExceptionGroup
 import trio
+from async_generator import asynccontextmanager
 
 from ._debug import maybe_wait_for_debugger
 from ._state import current_actor, is_main_process
 from .log import get_logger, get_loglevel
-from ._runtime import Actor
+from ._actor import Actor
 from ._portal import Portal
 from ._exceptions import is_multi_cancelled
 from ._root import open_root_actor
@@ -42,12 +39,9 @@ from . import _state
 from . import _spawn
 
 
-if TYPE_CHECKING:
-    import multiprocessing as mp
-
 log = get_logger(__name__)
 
-_default_bind_addr: tuple[str, int] = ('127.0.0.1', 0)
+_default_bind_addr: Tuple[str, int] = ('127.0.0.1', 0)
 
 
 class ActorNursery:
@@ -83,19 +77,15 @@ class ActorNursery:
         actor: Actor,
         ria_nursery: trio.Nursery,
         da_nursery: trio.Nursery,
-        errors: dict[tuple[str, str], BaseException],
+        errors: Dict[Tuple[str, str], Exception],
     ) -> None:
         # self.supervisor = supervisor  # TODO
         self._actor: Actor = actor
         self._ria_nursery = ria_nursery
         self._da_nursery = da_nursery
-        self._children: dict[
+        self._children: Dict[
-            tuple[str, str],
+            Tuple[str, str],
-            tuple[
+            Tuple[Actor, mp.Process, Optional[Portal]]
-                Actor,
-                trio.Process | mp.Process,
-                Optional[Portal],
-            ]
         ] = {}
         # portals spawned with ``run_in_actor()`` are
         # cancelled when their "main" result arrives
@@ -110,12 +100,12 @@ class ActorNursery:
         self,
         name: str,
         *,
-        bind_addr: tuple[str, int] = _default_bind_addr,
+        bind_addr: Tuple[str, int] = _default_bind_addr,
-        rpc_module_paths: list[str] | None = None,
+        rpc_module_paths: List[str] = None,
-        enable_modules: list[str] | None = None,
+        enable_modules: List[str] = None,
-        loglevel: str | None = None,  # set log level per subactor
+        loglevel: str = None,  # set log level per subactor
-        nursery: trio.Nursery | None = None,
+        nursery: trio.Nursery = None,
-        debug_mode: Optional[bool] | None = None,
+        debug_mode: Optional[bool] = None,
         infect_asyncio: bool = False,
     ) -> Portal:
         '''
@@ -181,10 +171,10 @@ class ActorNursery:
         *,
 
         name: Optional[str] = None,
-        bind_addr: tuple[str, int] = _default_bind_addr,
+        bind_addr: Tuple[str, int] = _default_bind_addr,
-        rpc_module_paths: list[str] | None = None,
+        rpc_module_paths: Optional[List[str]] = None,
-        enable_modules: list[str] | None = None,
+        enable_modules: List[str] = None,
-        loglevel: str | None = None,  # set log level per subactor
+        loglevel: str = None,  # set log level per subactor
         infect_asyncio: bool = False,
 
         **kwargs,  # explicit args to ``fn``
@@ -295,17 +285,13 @@ class ActorNursery:
         self._join_procs.set()
 
 
-@acm
+@asynccontextmanager
 async def _open_and_supervise_one_cancels_all_nursery(
     actor: Actor,
-
 ) -> typing.AsyncGenerator[ActorNursery, None]:
 
-    # TODO: yay or nay?
-    __tracebackhide__ = True
-
     # the collection of errors retreived from spawned sub-actors
-    errors: dict[tuple[str, str], BaseException] = {}
+    errors: Dict[Tuple[str, str], Exception] = {}
 
     # This is the outermost level "deamon actor" nursery. It is awaited
     # **after** the below inner "run in actor nursery". This allows for
@@ -338,17 +324,19 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # after we yield upwards
                     yield anursery
 
-                    # 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} "
                         "to complete"
                     )
+
+                    # Last bit before first nursery block ends in the case
+                    # where we didn't error in the caller's scope
+
+                    # signal all process monitor tasks to conduct
+                    # hard join phase.
                     anursery._join_procs.set()
 
-                except BaseException as inner_err:
+                except BaseException as err:
-                    errors[actor.uid] = inner_err
 
                     # If we error in the root but the debugger is
                     # engaged we don't want to prematurely kill (and
@@ -365,42 +353,49 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # worry more are coming).
                     anursery._join_procs.set()
 
-                    # XXX: hypothetically an error could be
+                    try:
-                    # raised and then a cancel signal shows up
+                        # XXX: hypothetically an error could be
-                    # slightly after in which case the `else:`
+                        # raised and then a cancel signal shows up
-                    # block here might not complete?  For now,
+                        # slightly after in which case the `else:`
-                    # shield both.
+                        # block here might not complete?  For now,
-                    with trio.CancelScope(shield=True):
+                        # shield both.
-                        etype = type(inner_err)
+                        with trio.CancelScope(shield=True):
-                        if etype in (
+                            etype = type(err)
-                            trio.Cancelled,
+                            if etype in (
-                            KeyboardInterrupt
+                                trio.Cancelled,
-                        ) or (
+                                KeyboardInterrupt
-                            is_multi_cancelled(inner_err)
+                            ) or (
-                        ):
+                                is_multi_cancelled(err)
-                            log.cancel(
+                            ):
-                                f"Nursery for {current_actor().uid} "
+                                log.cancel(
-                                f"was cancelled with {etype}")
+                                    f"Nursery for {current_actor().uid} "
-                        else:
+                                    f"was cancelled with {etype}")
-                            log.exception(
+                            else:
-                                f"Nursery for {current_actor().uid} "
+                                log.exception(
-                                f"errored with")
+                                    f"Nursery for {current_actor().uid} "
+                                    f"errored with {err}, ")
 
-                        # cancel all subactors
+                            # cancel all subactors
-                        await anursery.cancel()
+                            await anursery.cancel()
 
-            # ria_nursery scope end
+                    except trio.MultiError as merr:
+                        # If we receive additional errors while waiting on
+                        # remaining subactors that were cancelled,
+                        # aggregate those errors with the original error
+                        # that triggered this teardown.
+                        if err not in merr.exceptions:
+                            raise trio.MultiError(merr.exceptions + [err])
+                    else:
+                        raise
 
-        # TODO: this is the handler around the ``.run_in_actor()``
+                # ria_nursery scope end
-        # nursery. Ideally we can drop this entirely in the future as
+
-        # the whole ``.run_in_actor()`` API should be built "on top of"
+        # XXX: do we need a `trio.Cancelled` catch here as well?
-        # this lower level spawn-request-cancel "daemon actor" API where
+        # this is the catch around the ``.run_in_actor()`` nursery
-        # a local in-actor task nursery is used with one-to-one task
-        # + `await Portal.run()` calls and the results/errors are
-        # handled directly (inline) and errors by the local nursery.
         except (
+
             Exception,
-            BaseExceptionGroup,
+            trio.MultiError,
             trio.Cancelled
 
         ) as err:
@@ -432,20 +427,18 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     with trio.CancelScope(shield=True):
                         await anursery.cancel()
 
-                # use `BaseExceptionGroup` as needed
+                # use `MultiError` as needed
                 if len(errors) > 1:
-                    raise BaseExceptionGroup(
+                    raise trio.MultiError(tuple(errors.values()))
-                        'tractor.ActorNursery errored with',
-                        tuple(errors.values()),
-                    )
                 else:
                     raise list(errors.values())[0]
 
-        # da_nursery scope end - nursery checkpoint
+        # ria_nursery scope end - nursery checkpoint
-    # final exit
+
+    # after nursery exit
 
 
-@acm
+@asynccontextmanager
 async def open_nursery(
     **kwargs,
 

tractor/experimental/_pubsub.py

@@ -26,10 +26,7 @@ support provided by ``tractor.Context.open_stream()`` and friends.
 from __future__ import annotations
 import inspect
 import typing
-from typing import (
+from typing import Dict, Any, Set, Callable, List, Tuple
-    Any,
-    Callable,
-)
 from functools import partial
 from async_generator import aclosing
 
@@ -47,8 +44,8 @@ log = get_logger('messaging')
 
 async def fan_out_to_ctxs(
     pub_async_gen_func: typing.Callable,  # it's an async gen ... gd mypy
-    topics2ctxs: dict[str, list],
+    topics2ctxs: Dict[str, list],
-    packetizer: typing.Callable | None = None,
+    packetizer: typing.Callable = None,
 ) -> None:
     '''
     Request and fan out quotes to each subscribed actor channel.
@@ -64,7 +61,7 @@ async def fan_out_to_ctxs(
 
         async for published in pub_gen:
 
-            ctx_payloads: list[tuple[Context, Any]] = []
+            ctx_payloads: List[Tuple[Context, Any]] = []
 
             for topic, data in published.items():
                 log.debug(f"publishing {topic, data}")
@@ -106,8 +103,8 @@ async def fan_out_to_ctxs(
 
 def modify_subs(
 
-    topics2ctxs: dict[str, list[Context]],
+    topics2ctxs: Dict[str, List[Context]],
-    topics: set[str],
+    topics: Set[str],
     ctx: Context,
 
 ) -> None:
@@ -139,20 +136,20 @@ def modify_subs(
             topics2ctxs.pop(topic)
 
 
-_pub_state: dict[str, dict] = {}
+_pub_state: Dict[str, dict] = {}
-_pubtask2lock: dict[str, trio.StrictFIFOLock] = {}
+_pubtask2lock: Dict[str, trio.StrictFIFOLock] = {}
 
 
 def pub(
-    wrapped: typing.Callable | None = None,
+    wrapped: typing.Callable = None,
     *,
-    tasks: set[str] = set(),
+    tasks: Set[str] = set(),
 ):
     """Publisher async generator decorator.
 
     A publisher can be called multiple times from different actors but
     will only spawn a finite set of internal tasks to stream values to
-    each caller. The ``tasks: set[str]`` argument to the decorator
+    each caller. The ``tasks: Set[str]`` argument to the decorator
     specifies the names of the mutex set of publisher tasks.  When the
     publisher function is called, an argument ``task_name`` must be
     passed to specify which task (of the set named in ``tasks``) should
@@ -161,9 +158,9 @@ def pub(
     necessary.
 
     Values yielded from the decorated async generator must be
-    ``dict[str, dict[str, Any]]`` where the fist level key is the topic
+    ``Dict[str, Dict[str, Any]]`` where the fist level key is the topic
     string and determines which subscription the packet will be
-    delivered to and the value is a packet ``dict[str, Any]`` by default
+    delivered to and the value is a packet ``Dict[str, Any]`` by default
     of the form:
 
     .. ::python
@@ -189,7 +186,7 @@ def pub(
 
 
     The publisher must be called passing in the following arguments:
-    - ``topics: set[str]`` the topic sequence or "subscriptions"
+    - ``topics: Set[str]`` the topic sequence or "subscriptions"
     - ``task_name: str`` the task to use (if ``tasks`` was passed)
     - ``ctx: Context`` the tractor context (only needed if calling the
       pub func without a nursery, otherwise this is provided implicitly)
@@ -234,7 +231,7 @@ def pub(
     if wrapped is None:
         return partial(pub, tasks=tasks)
 
-    task2lock: dict[str, trio.StrictFIFOLock] = {}
+    task2lock: Dict[str, trio.StrictFIFOLock] = {}
 
     for name in tasks:
         task2lock[name] = trio.StrictFIFOLock()
@@ -246,11 +243,11 @@ def pub(
         # `wrapt` docs
         async def _execute(
             ctx: Context,
-            topics: set[str],
+            topics: Set[str],
             *args,
             # *,
-            task_name: str | None = None,  # default: only one task allocated
+            task_name: str = None,  # default: only one task allocated
-            packetizer: Callable | None = None,
+            packetizer: Callable = None,
             **kwargs,
         ):
             if task_name is None:

tractor/log.py

@@ -18,14 +18,12 @@
 Log like a forester!
 
 """
-from collections.abc import Mapping
 import sys
 import logging
 import colorlog  # type: ignore
+from typing import Optional
 
-import trio
+from ._state import ActorContextInfo
-
-from ._state import current_actor
 
 
 _proj_name: str = 'tractor'
@@ -38,8 +36,7 @@ LOG_FORMAT = (
     # "{bold_white}{log_color}{asctime}{reset}"
     "{log_color}{asctime}{reset}"
     " {bold_white}{thin_white}({reset}"
-    "{thin_white}{actor_name}[{actor_uid}], "
+    "{thin_white}{actor}, {process}, {task}){reset}{bold_white}{thin_white})"
-    "{process}, {task}){reset}{bold_white}{thin_white})"
     " {reset}{log_color}[{reset}{bold_log_color}{levelname}{reset}{log_color}]"
     " {log_color}{name}"
     " {thin_white}{filename}{log_color}:{reset}{thin_white}{lineno}{log_color}"
@@ -139,40 +136,9 @@ class StackLevelAdapter(logging.LoggerAdapter):
         )
 
 
-_conc_name_getters = {
-    'task': lambda: trio.lowlevel.current_task().name,
-    'actor': lambda: current_actor(),
-    'actor_name': lambda: current_actor().name,
-    'actor_uid': lambda: current_actor().uid[1][:6],
-}
-
-
-class ActorContextInfo(Mapping):
-    "Dyanmic lookup for local actor and task names"
-    _context_keys = (
-        'task',
-        'actor',
-        'actor_name',
-        'actor_uid',
-    )
-
-    def __len__(self):
-        return len(self._context_keys)
-
-    def __iter__(self):
-        return iter(self._context_keys)
-
-    def __getitem__(self, key: str) -> str:
-        try:
-            return _conc_name_getters[key]()
-        except RuntimeError:
-            # no local actor/task context initialized yet
-            return f'no {key} context'
-
-
 def get_logger(
 
-    name: str | None = None,
+    name: str = None,
     _root_name: str = _proj_name,
 
 ) -> StackLevelAdapter:
@@ -207,7 +173,7 @@ def get_logger(
 
 
 def get_console_log(
-    level: str | None = None,
+    level: str = None,
     **kwargs,
 ) -> logging.LoggerAdapter:
     '''Get the package logger and enable a handler which writes to stderr.

tractor/msg.py

@@ -24,7 +24,7 @@ Built-in messaging patterns, types, APIs and helpers.
 # ``pkgutil.resolve_name()`` internally uses
 # ``importlib.import_module()`` which can be filtered by inserting
 # a ``MetaPathFinder`` into ``sys.meta_path`` (which we could do before
-# entering the ``_runtime.process_messages()`` loop).
+# entering the ``Actor._process_messages()`` loop).
 # - https://github.com/python/cpython/blob/main/Lib/pkgutil.py#L645
 # - https://stackoverflow.com/questions/1350466/preventing-python-code-from-importing-certain-modules
 #   - https://stackoverflow.com/a/63320902

tractor/testing/__init__.py

@@ -0,0 +1,17 @@
+# 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/>.
+
+from ._tractor_test import tractor_test

tractor/testing/_tractor_test.py

@@ -0,0 +1,104 @@
+# 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/>.
+
+import inspect
+import platform
+from functools import partial, wraps
+
+import trio
+import tractor
+
+
+__all__ = ['tractor_test']
+
+
+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 = 'spawn'
+            else:
+                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,
+
+                ) as actor:
+                    await fn(*args, **kwargs)
+
+            main = _main
+
+        else:
+            # use implicit root actor start
+            main = partial(fn, *args, **kwargs)
+
+        return trio.run(main)
+            # arbiter_addr=arb_addr,
+            # loglevel=loglevel,
+            # start_method=start_method,
+        # )
+
+    return wrapper

tractor/to_asyncio.py

@@ -32,15 +32,10 @@ from typing import (
 )
 
 import trio
-from outcome import Error
 
 from .log import get_logger
 from ._state import current_actor
 from ._exceptions import AsyncioCancelled
-from .trionics._broadcast import (
-    broadcast_receiver,
-    BroadcastReceiver,
-)
 
 log = get_logger(__name__)
 
@@ -62,35 +57,19 @@ class LinkedTaskChannel(trio.abc.Channel):
 
     _trio_cs: trio.CancelScope
     _aio_task_complete: trio.Event
-    _trio_exited: bool = False
 
     # set after ``asyncio.create_task()``
     _aio_task: Optional[asyncio.Task] = None
     _aio_err: Optional[BaseException] = None
-    _broadcaster: Optional[BroadcastReceiver] = None
 
     async def aclose(self) -> None:
         await self._from_aio.aclose()
 
     async def receive(self) -> Any:
-        async with translate_aio_errors(
+        async with translate_aio_errors(self):
-            self,
-
-            # XXX: obviously this will deadlock if an on-going stream is
-            # being procesed.
-            # wait_on_aio_task=False,
-        ):
-
-            # TODO: do we need this to guarantee asyncio code get's
-            # cancelled in the case where the trio side somehow creates
-            # a state where the asyncio cycle-task isn't getting the
-            # cancel request sent by (in theory) the last checkpoint
-            # cycle on the trio side?
-            # await trio.lowlevel.checkpoint()
-
             return await self._from_aio.receive()
 
-    async def wait_asyncio_complete(self) -> None:
+    async def wait_ayncio_complete(self) -> None:
         await self._aio_task_complete.wait()
 
     # def cancel_asyncio_task(self) -> None:
@@ -105,43 +84,6 @@ class LinkedTaskChannel(trio.abc.Channel):
         '''
         self._to_aio.put_nowait(item)
 
-    def closed(self) -> bool:
-        return self._from_aio._closed  # type: ignore
-
-    # TODO: shoud we consider some kind of "decorator" system
-    # that checks for structural-typing compatibliity and then
-    # automatically adds this ctx-mngr-as-method machinery?
-    @acm
-    async def subscribe(
-        self,
-
-    ) -> AsyncIterator[BroadcastReceiver]:
-        '''
-        Allocate and return a ``BroadcastReceiver`` which delegates
-        to this inter-task channel.
-
-        This allows multiple local tasks to receive each their own copy
-        of this message stream.
-
-        See ``tractor._streaming.MsgStream.subscribe()`` for further
-        similar details.
-        '''
-        if self._broadcaster is None:
-
-            bcast = self._broadcaster = broadcast_receiver(
-                self,
-                # use memory channel size by default
-                self._from_aio._state.max_buffer_size,  # type: ignore
-                receive_afunc=self.receive,
-            )
-
-            self.receive = bcast.receive  # type: ignore
-
-        async with self._broadcaster.subscribe() as bstream:
-            assert bstream.key != self._broadcaster.key
-            assert bstream._recv == self._broadcaster._recv
-            yield bstream
-
 
 def _run_asyncio_task(
 
@@ -157,7 +99,6 @@ def _run_asyncio_task(
     or stream the result back to ``trio``.
 
     '''
-    __tracebackhide__ = True
     if not current_actor().is_infected_aio():
         raise RuntimeError("`infect_asyncio` mode is not enabled!?")
 
@@ -217,7 +158,6 @@ def _run_asyncio_task(
         try:
             result = await coro
         except BaseException as aio_err:
-            log.exception('asyncio task errored')
             chan._aio_err = aio_err
             raise
 
@@ -241,7 +181,6 @@ def _run_asyncio_task(
                 to_trio.close()
 
             aio_task_complete.set()
-            log.runtime(f'`asyncio` task: {task.get_name()} is complete')
 
     # start the asyncio task we submitted from trio
     if not inspect.isawaitable(coro):
@@ -263,25 +202,20 @@ def _run_asyncio_task(
         '''
         nonlocal chan
         aio_err = chan._aio_err
-        task_err: Optional[BaseException] = None
 
         # only to avoid ``asyncio`` complaining about uncaptured
         # task exceptions
         try:
             task.exception()
         except BaseException as terr:
-            task_err = terr
-
-            if isinstance(terr, CancelledError):
-                log.cancel(f'`asyncio` task cancelled: {task.get_name()}')
-            else:
-                log.exception(f'`asyncio` task: {task.get_name()} errored')
-
             assert type(terr) is type(aio_err), 'Asyncio task error mismatch?'
 
         if aio_err is not None:
-            # XXX: uhh is this true?
+            if type(aio_err) is CancelledError:
-            # assert task_err, f'Asyncio task {task.get_name()} discrepancy!?'
+                log.cancel("infected task was cancelled")
+            else:
+                aio_err.with_traceback(aio_err.__traceback__)
+                log.exception("infected task errorred:")
 
             # NOTE: currently mem chan closure may act as a form
             # of error relay (at least in the ``asyncio.CancelledError``
@@ -290,28 +224,8 @@ def _run_asyncio_task(
             # We might want to change this in the future though.
             from_aio.close()
 
-            if type(aio_err) is CancelledError:
-                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')
-
-            # XXX: alway cancel the scope on error
-            # in case the trio task is blocking
-            # on a checkpoint.
-            cancel_scope.cancel()
-
-            # raise any ``asyncio`` side error.
-            raise aio_err
-
     task.add_done_callback(cancel_trio)
+
     return chan
 
 
@@ -319,7 +233,6 @@ def _run_asyncio_task(
 async def translate_aio_errors(
 
     chan: LinkedTaskChannel,
-    wait_on_aio_task: bool = False,
 
 ) -> AsyncIterator[None]:
     '''
@@ -327,11 +240,8 @@ async def translate_aio_errors(
     appropriately translates errors and cancels into ``trio`` land.
 
     '''
-    trio_task = trio.lowlevel.current_task()
-
     aio_err: Optional[BaseException] = None
 
-    # TODO: make thisi a channel method?
     def maybe_raise_aio_err(
         err: Optional[Exception] = None
     ) -> None:
@@ -350,22 +260,10 @@ async def translate_aio_errors(
     assert task
     try:
         yield
-
-    except (
-        trio.Cancelled,
-    ):
-        # relay cancel through to called ``asyncio`` task
-        assert chan._aio_task
-        chan._aio_task.cancel(
-            msg=f'the `trio` caller task was cancelled: {trio_task.name}'
-        )
-        raise
-
     except (
         # NOTE: see the note in the ``cancel_trio()`` asyncio task
         # termination callback
         trio.ClosedResourceError,
-        # trio.BrokenResourceError,
     ):
         aio_err = chan._aio_err
         if (
@@ -379,32 +277,14 @@ async def translate_aio_errors(
 
         else:
             raise
-
     finally:
-        if (
+        # always cancel the ``asyncio`` task if we've made it this far
-            # NOTE: always cancel the ``asyncio`` task if we've made it
+        # and it's not done.
-            # this far and it's not done.
+        if not task.done() and aio_err:
-            not task.done() and aio_err
-
-            # or the trio side has exited it's surrounding cancel scope
-            # indicating the lifetime of the ``asyncio``-side task
-            # should also be terminated.
-            or chan._trio_exited
-        ):
-            log.runtime(
-                f'Cancelling `asyncio`-task: {task.get_name()}'
-            )
             # assert not aio_err, 'WTF how did asyncio do this?!'
             task.cancel()
 
-        # Required to sync with the far end ``asyncio``-task to ensure
+        # if any ``asyncio`` error was caught, raise it here inline
-        # any error is captured (via monkeypatching the
-        # ``channel._aio_err``) before calling ``maybe_raise_aio_err()``
-        # below!
-        if wait_on_aio_task:
-            await chan._aio_task_complete.wait()
-
-        # NOTE: if any ``asyncio`` error was caught, raise it here inline
         # here in the ``trio`` task
         maybe_raise_aio_err()
 
@@ -429,10 +309,8 @@ async def run_task(
         **kwargs,
     )
     with chan._from_aio:
-        async with translate_aio_errors(
+        # try:
-            chan,
+        async with translate_aio_errors(chan):
-            wait_on_aio_task=True,
-        ):
             # return single value that is the output from the
             # ``asyncio`` function-as-task. Expect the mem chan api to
             # do the job of handling cross-framework cancellations
@@ -460,21 +338,13 @@ async def open_channel_from(
         **kwargs,
     )
     async with chan._from_aio:
-        async with translate_aio_errors(
+        async with translate_aio_errors(chan):
-            chan,
-            wait_on_aio_task=True,
-        ):
             # sync to a "started()"-like first delivered value from the
             # ``asyncio`` task.
-            try:
+            first = await chan.receive()
-                with chan._trio_cs:
-                    first = await chan.receive()
 
-                    # deliver stream handle upward
+            # stream values upward
-                    yield first, chan
+            yield first, chan
-            finally:
-                chan._trio_exited = True
-                chan._to_trio.close()
 
 
 def run_as_asyncio_guest(
@@ -491,18 +361,16 @@ def run_as_asyncio_guest(
     SC semantics.
 
     '''
-    # Uh, oh.
+    # Uh, oh. :o
-    #
-    # :o
 
     # It looks like your event loop has caught a case of the ``trio``s.
 
     # :()
 
-    # Don't worry, we've heard you'll barely notice. You might
+    # Don't worry, we've heard you'll barely notice. You might hallucinate
-    # hallucinate a few more propagating errors and feel like your
+    # a few more propagating errors and feel like your digestion has
-    # digestion has slowed but if anything get's too bad your parents
+    # slowed but if anything get's too bad your parents will know about
-    # will know about it.
+    # it.
 
     # :)
 
@@ -513,20 +381,8 @@ def run_as_asyncio_guest(
 
         def trio_done_callback(main_outcome):
 
-            if isinstance(main_outcome, Error):
+            print(f"trio_main finished: {main_outcome!r}")
-                error = main_outcome.error
+            trio_done_fut.set_result(main_outcome)
-                trio_done_fut.set_exception(error)
-
-                # TODO: explicit asyncio tb?
-                # traceback.print_exception(error)
-
-                # XXX: do we need this?
-                # actor.cancel_soon()
-
-                main_outcome.unwrap()
-            else:
-                trio_done_fut.set_result(main_outcome)
-                log.runtime(f"trio_main finished: {main_outcome!r}")
 
         # start the infection: run trio on the asyncio loop in "guest mode"
         log.info(f"Infecting asyncio process with {trio_main}")
@@ -536,7 +392,6 @@ def run_as_asyncio_guest(
             run_sync_soon_threadsafe=loop.call_soon_threadsafe,
             done_callback=trio_done_callback,
         )
-        # ``.unwrap()`` will raise here on error
         return (await trio_done_fut).unwrap()
 
     # might as well if it's installed.

tractor/trionics/__init__.py

@@ -21,7 +21,6 @@ Sugary patterns for trio + tractor designs.
 from ._mngrs import (
     gather_contexts,
     maybe_open_context,
-    maybe_open_nursery,
 )
 from ._broadcast import (
     broadcast_receiver,
@@ -36,5 +35,4 @@ __all__ = [
     'BroadcastReceiver',
     'Lagged',
     'maybe_open_context',
-    'maybe_open_nursery',
 ]

tractor/trionics/_broadcast.py

@@ -23,6 +23,7 @@ from __future__ import annotations
 from abc import abstractmethod
 from collections import deque
 from contextlib import asynccontextmanager
+from dataclasses import dataclass
 from functools import partial
 from operator import ne
 from typing import Optional, Callable, Awaitable, Any, AsyncIterator, Protocol
@@ -32,10 +33,7 @@ import trio
 from trio._core._run import Task
 from trio.abc import ReceiveChannel
 from trio.lowlevel import current_task
-from msgspec import Struct
-from tractor.log import get_logger
 
-log = get_logger(__name__)
 
 # A regular invariant generic type
 T = TypeVar("T")
@@ -88,7 +86,8 @@ class Lagged(trio.TooSlowError):
     '''
 
 
-class BroadcastState(Struct):
+@dataclass
+class BroadcastState:
     '''
     Common state to all receivers of a broadcast.
 
@@ -111,35 +110,7 @@ class BroadcastState(Struct):
     eoc: bool = False
 
     # If the broadcaster was cancelled, we might as well track it
-    cancelled: dict[int, Task] = {}
+    cancelled: bool = False
-
-    def statistics(self) -> dict[str, Any]:
-        '''
-        Return broadcast receiver group "statistics" like many of
-        ``trio``'s internal task-sync primitives.
-
-        '''
-        key: int | None
-        ev: trio.Event | None
-
-        subs = self.subs
-        if self.recv_ready is not None:
-            key, ev = self.recv_ready
-        else:
-            key = ev = None
-
-        qlens: dict[int, int] = {}
-        for tid, sz in subs.items():
-            qlens[tid] = sz if sz != -1 else 0
-
-        return {
-            'open_consumers': len(subs),
-            'queued_len_by_task': qlens,
-            'max_buffer_size': self.maxlen,
-            'tasks_waiting': ev.statistics().tasks_waiting if ev else 0,
-            'tasks_cancelled': self.cancelled,
-            'next_value_receiver_id': key,
-        }
 
 
 class BroadcastReceiver(ReceiveChannel):
@@ -157,40 +128,23 @@ class BroadcastReceiver(ReceiveChannel):
         rx_chan: AsyncReceiver,
         state: BroadcastState,
         receive_afunc: Optional[Callable[[], Awaitable[Any]]] = None,
-        raise_on_lag: bool = True,
 
     ) -> None:
 
         # register the original underlying (clone)
         self.key = id(self)
         self._state = state
-
-        # each consumer has an int count which indicates
-        # which index contains the next value that the task has not yet
-        # consumed and thus should read. In the "up-to-date" case the
-        # consumer task must wait for a new value from the underlying
-        # receiver and we use ``-1`` as the sentinel for this state.
         state.subs[self.key] = -1
 
         # underlying for this receiver
         self._rx = rx_chan
         self._recv = receive_afunc or rx_chan.receive
         self._closed: bool = False
-        self._raise_on_lag = raise_on_lag
 
-    def receive_nowait(
+    async def receive(self) -> ReceiveType:
-        self,
-        _key: int | None = None,
-        _state: BroadcastState | None = None,
 
-    ) -> Any:
+        key = self.key
-        '''
+        state = self._state
-        Sync version of `.receive()` which does all the low level work
-        of receiving from the underlying/wrapped receive channel.
-
-        '''
-        key = _key or self.key
-        state = _state or self._state
 
         # TODO: ideally we can make some way to "lock out" the
         # underlying receive channel in some way such that if some task
@@ -223,173 +177,128 @@ class BroadcastReceiver(ReceiveChannel):
                 # return this value."
                 # https://docs.rs/tokio/1.11.0/tokio/sync/broadcast/index.html#lagging
 
-                mxln = state.maxlen
-                lost = seq - mxln
-
                 # decrement to the last value and expect
                 # consumer to either handle the ``Lagged`` and come back
                 # or bail out on its own (thus un-subscribing)
-                state.subs[key] = mxln - 1
+                state.subs[key] = state.maxlen - 1
 
                 # this task was overrun by the producer side
                 task: Task = current_task()
-                msg = f'Task `{task.name}` overrun and dropped `{lost}` values'
+                raise Lagged(f'Task {task.name} was overrun')
-
-                if self._raise_on_lag:
-                    raise Lagged(msg)
-                else:
-                    log.warning(msg)
-                    return self.receive_nowait(_key, _state)
 
             state.subs[key] -= 1
             return value
 
-        raise trio.WouldBlock
+        # current task already has the latest value **and** is the
+        # first task to begin waiting for a new one
+        if state.recv_ready is None:
 
-    async def _receive_from_underlying(
+            if self._closed:
-        self,
+                raise trio.ClosedResourceError
-        key: int,
-        state: BroadcastState,
 
-    ) -> ReceiveType:
+            event = trio.Event()
+            state.recv_ready = key, event
 
-        if self._closed:
-            raise trio.ClosedResourceError
-
-        event = trio.Event()
-        assert state.recv_ready is None
-        state.recv_ready = key, event
-
-        try:
             # if we're cancelled here it should be
             # fine to bail without affecting any other consumers
             # right?
-            value = await self._recv()
+            try:
+                value = await self._recv()
 
-            # items with lower indices are "newer"
+                # items with lower indices are "newer"
-            # NOTE: ``collections.deque`` implicitly takes care of
+                # NOTE: ``collections.deque`` implicitly takes care of
-            # trucating values outside our ``state.maxlen``. In the
+                # trucating values outside our ``state.maxlen``. In the
-            # alt-backend-array-case we'll need to make sure this is
+                # alt-backend-array-case we'll need to make sure this is
-            # implemented in similar ringer-buffer-ish style.
+                # implemented in similar ringer-buffer-ish style.
-            state.queue.appendleft(value)
+                state.queue.appendleft(value)
 
-            # broadcast new value to all subscribers by increasing
+                # broadcast new value to all subscribers by increasing
-            # all sequence numbers that will point in the queue to
+                # all sequence numbers that will point in the queue to
-            # their latest available value.
+                # their latest available value.
 
-            # don't decrement the sequence for this task since we
+                # don't decrement the sequence for this task since we
-            # already retreived the last value
+                # already retreived the last value
 
-            # XXX: which of these impls is fastest?
+                # XXX: which of these impls is fastest?
-            # subs = state.subs.copy()
-            # subs.pop(key)
 
-            for sub_key in filter(
+                # subs = state.subs.copy()
-                # lambda k: k != key, state.subs,
+                # subs.pop(key)
-                partial(ne, key), state.subs,
+
+                for sub_key in filter(
+                    # lambda k: k != key, state.subs,
+                    partial(ne, key), state.subs,
+                ):
+                    state.subs[sub_key] += 1
+
+                # NOTE: this should ONLY be set if the above task was *NOT*
+                # cancelled on the `._recv()` call.
+                event.set()
+                return value
+
+            except trio.EndOfChannel:
+                # if any one consumer gets an EOC from the underlying
+                # receiver we need to unblock and send that signal to
+                # all other consumers.
+                self._state.eoc = True
+                if event.statistics().tasks_waiting:
+                    event.set()
+                raise
+
+            except (
+                trio.Cancelled,
             ):
-                state.subs[sub_key] += 1
+                # handle cancelled specially otherwise sibling
+                # consumers will be awoken with a sequence of -1
+                # and will potentially try to rewait the underlying
+                # receiver instead of just cancelling immediately.
+                self._state.cancelled = True
+                if event.statistics().tasks_waiting:
+                    event.set()
+                raise
 
-            # NOTE: this should ONLY be set if the above task was *NOT*
+            finally:
-            # cancelled on the `._recv()` call.
-            event.set()
-            return value
 
-        except trio.EndOfChannel:
+                # Reset receiver waiter task event for next blocking condition.
-            # if any one consumer gets an EOC from the underlying
+                # this MUST be reset even if the above ``.recv()`` call
-            # receiver we need to unblock and send that signal to
+                # was cancelled to avoid the next consumer from blocking on
-            # all other consumers.
+                # an event that won't be set!
-            self._state.eoc = True
+                state.recv_ready = None
-            if event.statistics().tasks_waiting:
-                event.set()
-            raise
-
-        except (
-            trio.Cancelled,
-        ):
-            # handle cancelled specially otherwise sibling
-            # consumers will be awoken with a sequence of -1
-            # and will potentially try to rewait the underlying
-            # receiver instead of just cancelling immediately.
-            self._state.cancelled[key] = current_task()
-            if event.statistics().tasks_waiting:
-                event.set()
-            raise
-
-        finally:
-            # Reset receiver waiter task event for next blocking condition.
-            # this MUST be reset even if the above ``.recv()`` call
-            # was cancelled to avoid the next consumer from blocking on
-            # an event that won't be set!
-            state.recv_ready = None
-
-    async def receive(self) -> ReceiveType:
-        key = self.key
-        state = self._state
-
-        try:
-            return self.receive_nowait(
-                _key=key,
-                _state=state,
-            )
-        except trio.WouldBlock:
-            pass
-
-        # current task already has the latest value **and** is the
-        # first task to begin waiting for a new one so we begin blocking
-        # until rescheduled with the a new value from the underlying.
-        if state.recv_ready is None:
-            return await self._receive_from_underlying(key, state)
 
         # This task is all caught up and ready to receive the latest
-        # value, so queue/schedule it to be woken on the next internal
+        # value, so queue sched it on the internal event.
-        # event.
         else:
-            while state.recv_ready is not None:
+            seq = state.subs[key]
-                # seq = state.subs[key]
+            assert seq == -1  # sanity
-                # assert seq == -1  # sanity
+            _, ev = state.recv_ready
-                _, ev = state.recv_ready
+            await ev.wait()
-                await ev.wait()
-                try:
-                    return self.receive_nowait(
-                        _key=key,
-                        _state=state,
-                    )
-                except trio.WouldBlock:
-                    if self._closed:
-                        raise trio.ClosedResourceError
 
-                    subs = state.subs
+            # NOTE: if we ever would like the behaviour where if the
-                    if (
+            # first task to recv on the underlying is cancelled but it
-                        len(subs) == 1
+            # still DOES trigger the ``.recv_ready``, event we'll likely need
-                        and key in subs
+            # this logic:
-                        # or cancelled
-                    ):
-                        # XXX: we are the last and only user of this BR so
-                        # likely it makes sense to unwind back to the
-                        # underlying?
-                        # import tractor
-                        # await tractor.breakpoint()
-                        log.warning(
-                            f'Only one sub left for {self}?\n'
-                            'We can probably unwind from breceiver?'
-                        )
 
-                    # XXX: In the case where the first task to allocate the
+            if seq > -1:
-                    # ``.recv_ready`` event is cancelled we will be woken
+                # stuff from above..
-                    # with a non-incremented sequence number (the ``-1``
+                seq = state.subs[key]
-                    # sentinel) and thus will read the oldest value if we
-                    # use that. Instead we need to detect if we have not
-                    # been incremented and then receive again.
-                    # return await self.receive()
 
-            return await self._receive_from_underlying(key, state)
+                value = state.queue[seq]
+                state.subs[key] -= 1
+                return value
+
+            elif seq == -1:
+                # XXX: In the case where the first task to allocate the
+                # ``.recv_ready`` event is cancelled we will be woken with
+                # a non-incremented sequence number and thus will read the
+                # oldest value if we use that. Instead we need to detect if
+                # we have not been incremented and then receive again.
+                return await self.receive()
+
+            else:
+                raise ValueError(f'Invalid sequence {seq}!?')
 
     @asynccontextmanager
     async def subscribe(
         self,
-        raise_on_lag: bool = True,
-
     ) -> AsyncIterator[BroadcastReceiver]:
         '''
         Subscribe for values from this broadcast receiver.
@@ -407,7 +316,6 @@ class BroadcastReceiver(ReceiveChannel):
             rx_chan=self._rx,
             state=state,
             receive_afunc=self._recv,
-            raise_on_lag=raise_on_lag,
         )
         # assert clone in state.subs
         assert br.key in state.subs
@@ -444,8 +352,7 @@ def broadcast_receiver(
 
     recv_chan: AsyncReceiver,
     max_buffer_size: int,
-    receive_afunc: Optional[Callable[[], Awaitable[Any]]] = None,
+    **kwargs,
-    raise_on_lag: bool = True,
 
 ) -> BroadcastReceiver:
 
@@ -456,6 +363,5 @@ def broadcast_receiver(
             maxlen=max_buffer_size,
             subs={},
         ),
-        receive_afunc=receive_afunc,
+        **kwargs,
-        raise_on_lag=raise_on_lag,
     )

tractor/trionics/_mngrs.py

@@ -19,7 +19,6 @@ Async context manager primitives with hard ``trio``-aware semantics
 
 '''
 from contextlib import asynccontextmanager as acm
-import inspect
 from typing import (
     Any,
     AsyncContextManager,
@@ -35,8 +34,8 @@ from typing import (
 import trio
 from trio_typing import TaskStatus
 
-from .._state import current_actor
 from ..log import get_logger
+from .._state import current_actor
 
 
 log = get_logger(__name__)
@@ -45,25 +44,6 @@ log = get_logger(__name__)
 T = TypeVar("T")
 
 
-@acm
-async def maybe_open_nursery(
-    nursery: trio.Nursery | None = None,
-    shield: bool = False,
-) -> AsyncGenerator[trio.Nursery, Any]:
-    '''
-    Create a new nursery if None provided.
-
-    Blocks on exit as expected if no input nursery is provided.
-
-    '''
-    if nursery is not None:
-        yield nursery
-    else:
-        async with trio.open_nursery() as nursery:
-            nursery.cancel_scope.shield = shield
-            yield nursery
-
-
 async def _enter_and_wait(
 
     mngr: AsyncContextManager[T],
@@ -101,7 +81,7 @@ async def gather_contexts(
     This function is somewhat similar to common usage of
     ``contextlib.AsyncExitStack.enter_async_context()`` (in a loop) in
     combo with ``asyncio.gather()`` except the managers are concurrently
-    entered and exited, and cancellation just works.
+    entered and exited cancellation just works.
 
     '''
     unwrapped: dict[int, Optional[T]] = {}.fromkeys(id(mngr) for mngr in mngrs)
@@ -109,17 +89,6 @@ async def gather_contexts(
     all_entered = trio.Event()
     parent_exit = trio.Event()
 
-    # XXX: ensure greedy sequence of manager instances
-    # since a lazy inline generator doesn't seem to work
-    # with `async with` syntax.
-    mngrs = list(mngrs)
-
-    if not mngrs:
-        raise ValueError(
-            'input mngrs is empty?\n'
-            'Did try to use inline generator syntax?'
-        )
-
     async with trio.open_nursery() as n:
         for mngr in mngrs:
             n.start_soon(
@@ -133,13 +102,11 @@ async def gather_contexts(
         # deliver control once all managers have started up
         await all_entered.wait()
 
-        try:
+        yield tuple(unwrapped.values())
-            yield tuple(unwrapped.values())
+
-        finally:
+        # we don't need a try/finally since cancellation will be triggered
-            # NOTE: this is ABSOLUTELY REQUIRED to avoid
+        # by the surrounding nursery on error.
-            # the following wacky bug:
+        parent_exit.set()
-            # <tractorbugurlhere>
-            parent_exit.set()
 
 
 # Per actor task caching helpers.
@@ -152,15 +119,13 @@ class _Cache:
     a kept-alive-while-in-use async resource.
 
     '''
-    service_n: Optional[trio.Nursery] = None
+    lock = trio.Lock()
-    locks: dict[Hashable, trio.Lock] = {}
     users: int = 0
     values: dict[Any,  Any] = {}
     resources: dict[
         Hashable,
         tuple[trio.Nursery, trio.Event]
     ] = {}
-    # nurseries: dict[int, trio.Nursery] = {}
     no_more_users: Optional[trio.Event] = None
 
     @classmethod
@@ -191,7 +156,7 @@ async def maybe_open_context(
     # XXX: used as cache key after conversion to tuple
     # and all embedded values must also be hashable
     kwargs: dict = {},
-    key: Hashable | Callable[..., Hashable] = None,
+    key: Hashable = None,
 
 ) -> AsyncIterator[tuple[bool, T]]:
     '''
@@ -200,69 +165,51 @@ async def maybe_open_context(
     _Cached instance on a _Cache hit.
 
     '''
-    fid = id(acm_func)
+    # lock resource acquisition around task racing  / ``trio``'s
+    # scheduler protocol
+    await _Cache.lock.acquire()
 
-    if inspect.isfunction(key):
+    ctx_key = (id(acm_func), key or tuple(kwargs.items()))
-        ctx_key = (fid, key(**kwargs))
+    value = None
-    else:
-        ctx_key = (fid, key or tuple(kwargs.items()))
-
-    # yielded output
-    yielded: Any = None
-
-    # Lock resource acquisition around task racing  / ``trio``'s
-    # scheduler protocol.
-    # NOTE: the lock is target context manager func specific in order
-    # 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())
-    await lock.acquire()
-
-    # XXX: one singleton nursery per actor and we want to
-    # have it not be closed until all consumers have exited (which is
-    # currently difficult to implement any other way besides using our
-    # pre-allocated runtime instance..)
-    service_n: trio.Nursery = current_actor()._service_n
-
-    # TODO: is there any way to allocate
-    # a 'stays-open-till-last-task-finshed nursery?
-    # service_n: trio.Nursery
-    # async with maybe_open_nursery(_Cache.service_n) as service_n:
-    #     _Cache.service_n = service_n
 
     try:
         # **critical section** that should prevent other tasks from
         # checking the _Cache until complete otherwise the scheduler
         # may switch and by accident we create more then one resource.
-        yielded = _Cache.values[ctx_key]
+        value = _Cache.values[ctx_key]
 
     except KeyError:
         log.info(f'Allocating new {acm_func} for {ctx_key}')
+
         mngr = acm_func(**kwargs)
+        # TODO: avoid pulling from ``tractor`` internals and
+        # instead offer a "root nursery" in piker actors?
+        service_n = current_actor()._service_n
+
+        # TODO: does this need to be a tractor "root nursery"?
         resources = _Cache.resources
         assert not resources.get(ctx_key), f'Resource exists? {ctx_key}'
-        resources[ctx_key] = (service_n, trio.Event())
+        ln, _ = resources[ctx_key] = (service_n, trio.Event())
 
-        # sync up to the mngr's yielded value
+        value = await ln.start(
-        yielded = await service_n.start(
             _Cache.run_ctx,
             mngr,
             ctx_key,
         )
         _Cache.users += 1
-        lock.release()
+        _Cache.lock.release()
-        yield False, yielded
+        yield False, value
 
     else:
         log.info(f'Reusing _Cached resource for {ctx_key}')
         _Cache.users += 1
-        lock.release()
+        _Cache.lock.release()
-        yield True, yielded
+        yield True, value
 
     finally:
         _Cache.users -= 1
 
-        if yielded is not None:
+        if value is not None:
             # if no more consumers, teardown the client
             if _Cache.users <= 0:
                 log.info(f'De-allocating resource for {ctx_key}')
@@ -274,5 +221,3 @@ async def maybe_open_context(
                 if entry:
                     _, no_more_users = entry
                     no_more_users.set()
-
-                _Cache.locks.pop(fid)