Include ./docs/README.rst in src dist

.github/workflows/ci.yml

@@ -20,35 +20,13 @@ jobs:
       - name: Setup python
         uses: actions/setup-python@v2
         with:
-          python-version: '3.11'
+          python-version: '3.10'
 
       - 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
-
-  # 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: '3.11'
-
-      - name: Build sdist
-        run: python setup.py sdist --formats=zip
-
-      - name: Install sdist from .zips
-        run: python -m pip install dist/*.zip
-
+        run: mypy tractor/ --ignore-missing-imports
 
   testing-linux:
     name: '${{ matrix.os }} Python ${{ matrix.python }} - ${{ matrix.spawn_backend }}'
@@ -59,12 +37,8 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python: ['3.11']
-        spawn_backend: [
-          'trio',
-          'mp_spawn',
-          'mp_forkserver',
-        ]
+        python: ['3.9', '3.10']
+        spawn_backend: ['trio', 'mp']
 
     steps:
 
@@ -79,53 +53,71 @@ jobs:
       - name: Install dependencies
         run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
 
-      - name: List dependencies
-        run: pip list
+      - name: Run tests
+        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
-  # debug the CI failures. Anyone wanting to hack and solve them is very
-  # welcome, but our primary user base is not using that OS.
+  # We skip 3.10 on windows for now due to
+  # https://github.com/pytest-dev/pytest/issues/8733
+  # 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:
-  #   name: '${{ matrix.os }} Python ${{ matrix.python }} - ${{ matrix.spawn_backend }}'
-  #   timeout-minutes: 12
-  #   runs-on: ${{ matrix.os }}
+  testing-windows:
+    name: '${{ matrix.os }} Python ${{ matrix.python }} - ${{ matrix.spawn_backend }}'
+    timeout-minutes: 12
+    runs-on: ${{ matrix.os }}
 
-  #   strategy:
-  #     fail-fast: false
-  #     matrix:
-  #       os: [windows-latest]
-  #       python: ['3.10']
-  #       spawn_backend: ['trio', 'mp']
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [windows-latest]
+        python: ['3.9']
+        spawn_backend: ['trio', 'mp']
 
-  #   steps:
+    steps:
 
-  #     - name: Checkout
-  #       uses: actions/checkout@v2
+      - name: Checkout
+        uses: actions/checkout@v2
 
-  #     - name: Setup python
-  #       uses: actions/setup-python@v2
-  #       with:
-  #         python-version: '${{ matrix.python }}'
+      - name: Setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '${{ matrix.python }}'
 
-  #     - name: Install dependencies
-  #       run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
+      - name: Install dependencies
+        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
-  #     # be verified by someone with a native setup.
-  #     # - 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=${{ matrix.spawn_backend }} -rsx
+      - name: Run tests
+        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rs

305.misc.rst

@@ -0,0 +1,7 @@
+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.

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

@@ -1,122 +1,39 @@
-|logo| ``tractor``: distributed structurred concurrency
+|logo| ``tractor``: next-gen Python parallelism
 
 |gh_actions|
 |docs|
 
-``tractor`` is a `structured concurrency`_ (SC), multi-processing_ runtime built on trio_.
+``tractor`` is a `structured concurrent`_, multi-processing_ runtime built on trio_.
 
-Fundamentally, ``tractor`` provides parallelism via
-``trio``-"*actors*": independent Python **processes** (i.e.
-*non-shared-memory threads*) which can schedule ``trio`` tasks whilst
-maintaining *end-to-end SC* inside a *distributed supervision tree*.
+Fundamentally ``tractor`` gives you parallelism via ``trio``-"*actors*":
+our nurseries_ let you spawn new Python processes which each run a ``trio``
+scheduled runtime - a call to ``trio.run()``.
 
-Cross-process (and thus cross-host) SC is accomplished through the
-combined use of our,
+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*.
 
-- "actor nurseries_" which provide for spawning multiple, and
-  possibly nested, Python processes each running a ``trio`` scheduled
-  runtime - a call to ``trio.run()``,
-- an "SC-transitive supervision protocol" enforced as an
-  IPC-message-spec encapsulating all RPC-dialogs.
-
-We believe the system adheres 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**.
-
-
-Where do i start!?
-------------------
-The first step to grok ``tractor`` is to get an intermediate
-knowledge of ``trio`` and **structured concurrency** B)
-
-Some great places to start are,
-
-- the seminal `blog post`_
-- obviously the `trio docs`_
-- wikipedia's nascent SC_ page
-- the fancy diagrams @ libdill-docs_
+The first step to grok ``tractor`` is to get the basics of ``trio`` down.
+A great place to start is the `trio docs`_ and this `blog post`_.
 
 
 Features
 --------
-- **It's just** a ``trio`` API!
-- *Infinitely nesteable* process trees running embedded ``trio`` tasks.
-- Swappable, OS-specific, process spawning via multiple backends.
-- Modular IPC stack, allowing for custom interchange formats (eg.
-  as offered from `msgspec`_), varied transport protocols (TCP, RUDP,
-  QUIC, wireguard), and OS-env specific higher-perf primitives (UDS,
-  shm-ring-buffers).
-- Optionally distributed_: all IPC and RPC APIs work over multi-host
-  transports the same as local.
-- Builtin high-level streaming API that enables your app to easily
-  leverage the benefits of a "`cheap or nasty`_" `(un)protocol`_.
-- A "native UX" around a multi-process safe debugger REPL using
-  `pdbp`_ (a fork & fix of `pdb++`_)
-- "Infected ``asyncio``" mode: support for starting an actor's
-  runtime as a `guest`_ on the ``asyncio`` loop allowing us to
-  provide stringent SC-style ``trio.Task``-supervision around any
-  ``asyncio.Task`` spawned via our ``tractor.to_asyncio`` APIs.
-- A **very naive** and still very much work-in-progress inter-actor
-  `discovery`_ sys with plans to support multiple `modern protocol`_
-  approaches.
-- Various ``trio`` extension APIs via ``tractor.trionics`` such as,
-  - task fan-out `broadcasting`_,
-  - multi-task-single-resource-caching and fan-out-to-multi
-    ``__aenter__()`` APIs for ``@acm`` functions,
-  - (WIP) a ``TaskMngr``: one-cancels-one style nursery supervisor.
-
-
-Install
--------
-``tractor`` is still in a *alpha-near-beta-stage* for many
-of its subsystems, however we are very close to having a stable
-lowlevel runtime and API.
-
-As such, it's currently recommended that you clone and install the
-repo from source::
-
-    pip install git+git://github.com/goodboy/tractor.git
-
-
-We use the very hip `uv`_ for project mgmt::
-
-    git clone https://github.com/goodboy/tractor.git
-    cd tractor
-    uv sync --dev
-    uv run python examples/rpc_bidir_streaming.py
-
-Consider activating a virtual/project-env before starting to hack on
-the code base::
-
-    # you could use plain ol' venvs
-    # https://docs.astral.sh/uv/pip/environments/
-    uv venv tractor_py313 --python 3.13
-
-    # but @goodboy prefers the more explicit (and shell agnostic)
-    # https://docs.astral.sh/uv/configuration/environment/#uv_project_environment
-    UV_PROJECT_ENVIRONMENT="tractor_py313
-
-    # hint hint, enter @goodboy's fave shell B)
-    uv run --dev xonsh
-
-Alongside all this we ofc offer "releases" on PyPi::
-
-    pip install tractor
-
-Just note that YMMV since the main git branch is often much further
-ahead then any latest release.
-
-
-Example codez
--------------
-In ``tractor``'s (very lacking) documention we prefer to point to
-example scripts in the repo over duplicating them in docs, but with
-that in mind here are some definitive snippets to try and hook you
-into digging deeper.
+- **It's just** a ``trio`` API
+- *Infinitely nesteable* process trees
+- Builtin IPC streaming APIs with task fan-out broadcasting
+- A (first ever?) "native" multi-core debugger UX for Python using `pdb++`_
+- Support for a swappable, OS specific, process spawning layer
+- 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
+  ``asyncio`` actors via "infected ``asyncio``" mode
+- `structured chadcurrency`_ from the ground up
 
 
 Run a func in a process
-***********************
+-----------------------
 Use ``trio``'s style of focussing on *tasks as functions*:
 
 .. code:: python
@@ -174,7 +91,7 @@ might want to check out `trio-parallel`_.
 
 
 Zombie safe: self-destruct a process tree
-*****************************************
+-----------------------------------------
 ``tractor`` tries to protect you from zombies, no matter what.
 
 .. code:: python
@@ -200,7 +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():
@@ -230,8 +147,8 @@ 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.
 
@@ -285,7 +202,7 @@ We're hoping to add a respawn-from-repl system soon!
 
 
 SC compatible bi-directional streaming
-**************************************
+--------------------------------------
 Yes, you saw it here first; we provide 2-way streams
 with reliable, transitive setup/teardown semantics.
 
@@ -377,7 +294,7 @@ hear your thoughts on!
 
 
 Worker poolz are easy peasy
-***************************
+---------------------------
 The initial ask from most new users is *"how do I make a worker
 pool thing?"*.
 
@@ -399,10 +316,10 @@ This uses no extra threads, fancy semaphores or futures; all we need
 is ``tractor``'s IPC!
 
 "Infected ``asyncio``" mode
-***************************
+---------------------------
 Have a bunch of ``asyncio`` code you want to force to be SC at the process level?
 
-Check out our experimental system for `guest`_-mode controlled
+Check out our experimental system for `guest-mode`_ controlled
 ``asyncio`` actors:
 
 .. code:: python
@@ -508,7 +425,7 @@ We need help refining the `asyncio`-side channel API to be more
 
 
 Higher level "cluster" APIs
-***************************
+---------------------------
 To be extra terse the ``tractor`` devs have started hacking some "higher
 level" APIs for managing actor trees/clusters. These interfaces should
 generally be condsidered provisional for now but we encourage you to try
@@ -565,6 +482,24 @@ spawn a flat cluster:
 .. _full worker pool re-implementation: https://github.com/goodboy/tractor/blob/master/examples/parallelism/concurrent_actors_primes.py
 
 
+Install
+-------
+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
+
+
 Under the hood
 --------------
 ``tractor`` is an attempt to pair trionic_ `structured concurrency`_ with
@@ -628,22 +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
-  <https://github.com/goodboy/tractor/issues/22>`_)
-- Typed messaging protocols (ex. via ``msgspec.Struct``, see `#36
+- Typed messaging protocols (ex. via ``msgspec``, see `#36
   <https://github.com/goodboy/tractor/issues/36>`_)
-- Typed capability-based (dialog) protocols ( see `#196
-  <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..
+- Erlang-style supervisors via composed context managers
 
 
 Feel like saying hi?
@@ -655,39 +579,31 @@ 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
-.. _distributed: https://en.wikipedia.org/wiki/Distributed_computing
-.. _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
-.. _broadcasting: https://github.com/goodboy/tractor/pull/229
-.. _modern procotol: https://en.wikipedia.org/wiki/Rendezvous_protocol
-.. _pdbp: https://github.com/mdmintz/pdbp
 .. _pdb++: https://github.com/pdbpp/pdbpp
-.. _cheap or nasty: https://zguide.zeromq.org/docs/chapter7/#The-Cheap-or-Nasty-Pattern
-.. _(un)protocol: https://zguide.zeromq.org/docs/chapter7/#Unprotocols
-.. _discovery: https://zguide.zeromq.org/docs/chapter8/#Discovery
-.. _modern protocol: https://en.wikipedia.org/wiki/Rendezvous_protocol
+.. _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
 .. _trio docs: https://trio.readthedocs.io/en/latest/
 .. _blog post: https://vorpus.org/blog/notes-on-structured-concurrency-or-go-statement-considered-harmful/
 .. _structured concurrency: https://en.wikipedia.org/wiki/Structured_concurrency
-.. _SC: https://en.wikipedia.org/wiki/Structured_concurrency
-.. _libdill-docs: https://sustrik.github.io/libdill/structured-concurrency.html
+.. _structured chadcurrency: https://en.wikipedia.org/wiki/Structured_concurrency
+.. _structured concurrency: https://en.wikipedia.org/wiki/Structured_concurrency
 .. _unrequirements: https://en.wikipedia.org/wiki/Actor_model#Direct_communication_and_asynchrony
 .. _async generators: https://www.python.org/dev/peps/pep-0525/
 .. _trio-parallel: https://github.com/richardsheridan/trio-parallel
-.. _uv: https://docs.astral.sh/uv/
 .. _msgspec: https://jcristharif.com/msgspec/
-.. _guest: https://trio.readthedocs.io/en/stable/reference-lowlevel.html?highlight=guest%20mode#using-guest-mode-to-run-trio-on-top-of-other-event-loops
+.. _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
 
 
 .. |gh_actions| image:: https://img.shields.io/endpoint.svg?url=https%3A%2F%2Factions-badge.atrox.dev%2Fgoodboy%2Ftractor%2Fbadge&style=popout-square

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

@@ -1,259 +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.
-
-'''
-from contextlib import asynccontextmanager as acm
-from functools import partial
-
-from tractor import (
-    open_nursery,
-    context,
-    Context,
-    ContextCancelled,
-    MsgStream,
-    _testing,
-)
-import trio
-import pytest
-
-
-async def break_ipc_then_error(
-    stream: MsgStream,
-    break_ipc_with: str|None = None,
-    pre_close: bool = False,
-):
-    await _testing.break_ipc(
-        stream=stream,
-        method=break_ipc_with,
-        pre_close=pre_close,
-    )
-    async for msg in stream:
-        await stream.send(msg)
-
-    assert 0
-
-
-async def iter_ipc_stream(
-    stream: MsgStream,
-    break_ipc_with: str|None = None,
-    pre_close: bool = False,
-):
-    async for msg in stream:
-        await stream.send(msg)
-
-
-@context
-async def recv_and_spawn_net_killers(
-
-    ctx: Context,
-    break_ipc_after: bool|int = False,
-    pre_close: bool = False,
-
-) -> None:
-    '''
-    Receive stream msgs and spawn some IPC killers mid-stream.
-
-    '''
-    broke_ipc: bool = False
-    await ctx.started()
-    async with (
-        ctx.open_stream() as stream,
-        trio.open_nursery(
-            strict_exception_groups=False,
-        ) as tn,
-    ):
-        async for i in stream:
-            print(f'child echoing {i}')
-            if not broke_ipc:
-                await stream.send(i)
-            else:
-                await trio.sleep(0.01)
-
-            if (
-                break_ipc_after
-                and
-                i >= break_ipc_after
-            ):
-                broke_ipc = True
-                tn.start_soon(
-                    iter_ipc_stream,
-                    stream,
-                )
-                tn.start_soon(
-                    partial(
-                        break_ipc_then_error,
-                        stream=stream,
-                        pre_close=pre_close,
-                    )
-                )
-
-
-@acm
-async def stuff_hangin_ctlc(timeout: float = 1) -> None:
-
-    with trio.move_on_after(timeout) as cs:
-        yield timeout
-
-    if cs.cancelled_caught:
-        # pretend to be a user seeing no streaming action
-        # thinking it's a hang, and then hitting ctl-c..
-        print(
-            f"i'm a user on the PARENT side and thingz hangin "
-            f'after timeout={timeout} ???\n\n'
-            'MASHING CTlR-C..!?\n'
-        )
-        raise KeyboardInterrupt
-
-
-async def main(
-    debug_mode: bool = False,
-    start_method: str = 'trio',
-    loglevel: str = 'cancel',
-
-    # by default we break the parent IPC first (if configured to break
-    # at all), but this can be changed so the child does first (even if
-    # both are set to break).
-    break_parent_ipc_after: int|bool = False,
-    break_child_ipc_after: int|bool = False,
-    pre_close: 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=loglevel,
-
-        ) as an,
-    ):
-        sub_name: str = 'chitty_hijo'
-        portal = await an.start_actor(
-            sub_name,
-            enable_modules=[__name__],
-        )
-
-        async with (
-            stuff_hangin_ctlc(timeout=2) as timeout,
-            _testing.expect_ctxc(
-                yay=(
-                    break_parent_ipc_after
-                    or break_child_ipc_after
-                ),
-                # TODO: we CAN'T remove this right?
-                # since we need the ctxc to bubble up from either
-                # the stream API after the `None` msg is sent
-                # (which actually implicitly cancels all remote
-                # tasks in the hijo) or from simluated
-                # KBI-mash-from-user
-                # or should we expect that a KBI triggers the ctxc
-                # and KBI in an eg?
-                reraise=True,
-            ),
-
-            portal.open_context(
-                recv_and_spawn_net_killers,
-                break_ipc_after=break_child_ipc_after,
-                pre_close=pre_close,
-            ) as (ctx, sent),
-        ):
-            rx_eoc: bool = False
-            ipc_break_sent: bool = False
-            async with ctx.open_stream() as stream:
-                for i in range(1000):
-
-                    if (
-                        break_parent_ipc_after
-                        and
-                        i > break_parent_ipc_after
-                        and
-                        not ipc_break_sent
-                    ):
-                        print(
-                            '#################################\n'
-                            'Simulating PARENT-side IPC BREAK!\n'
-                            '#################################\n'
-                        )
-
-                        # TODO: other methods? see break func above.
-                        # await stream._ctx.chan.send(None)
-                        # await stream._ctx.chan.transport.stream.send_eof()
-                        await stream._ctx.chan.transport.stream.aclose()
-                        ipc_break_sent = True
-
-                    # it actually breaks right here in the
-                    # mp_spawn/forkserver backends and thus the
-                    # zombie reaper never even kicks in?
-                    try:
-                        print(f'parent sending {i}')
-                        await stream.send(i)
-                    except ContextCancelled as ctxc:
-                        print(
-                            'parent received ctxc on `stream.send()`\n'
-                            f'{ctxc}\n'
-                        )
-                        assert 'root' in ctxc.canceller
-                        assert sub_name in ctx.canceller
-
-                        # TODO: is this needed or no?
-                        raise
-
-                    except trio.ClosedResourceError:
-                        # NOTE: don't send if we already broke the
-                        # connection to avoid raising a closed-error
-                        # such that we drop through to the ctl-c
-                        # mashing by user.
-                        await trio.sleep(0.01)
-
-                    # timeout: int = 1
-                    # with trio.move_on_after(timeout) as cs:
-                    async with stuff_hangin_ctlc() as timeout:
-                        print(
-                            f'PARENT `stream.receive()` with timeout={timeout}\n'
-                        )
-                        # NOTE: in the parent side IPC failure case this
-                        # will raise an ``EndOfChannel`` after the child
-                        # is killed and sends a stop msg back to it's
-                        # caller/this-parent.
-                        try:
-                            rx = await stream.receive()
-                            print(
-                                "I'm a happy PARENT user and echoed to me is\n"
-                                f'{rx}\n'
-                            )
-                        except trio.EndOfChannel:
-                            rx_eoc: bool = True
-                            print('MsgStream got EoC for PARENT')
-                            raise
-
-            print(
-                'Streaming finished and we got Eoc.\n'
-                'Canceling `.open_context()` in root with\n'
-                'CTlR-C..'
-            )
-            if rx_eoc:
-                assert stream.closed
-                try:
-                    await stream.send(i)
-                    pytest.fail('stream not closed?')
-                except (
-                    trio.ClosedResourceError,
-                    trio.EndOfChannel,
-                ) as send_err:
-                    if rx_eoc:
-                        assert send_err is stream._eoc
-                    else:
-                        assert send_err is stream._closed
-
-            raise KeyboardInterrupt
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/debugging/asyncio_bp.py

@@ -1,136 +0,0 @@
-'''
-Examples of using the builtin `breakpoint()` from an `asyncio.Task`
-running in a subactor spawned with `infect_asyncio=True`.
-
-'''
-import asyncio
-
-import trio
-import tractor
-from tractor import (
-    to_asyncio,
-    Portal,
-)
-
-
-async def aio_sleep_forever():
-    await asyncio.sleep(float('inf'))
-
-
-async def bp_then_error(
-    to_trio: trio.MemorySendChannel,
-    from_trio: asyncio.Queue,
-
-    raise_after_bp: bool = True,
-
-) -> None:
-
-    # sync with `trio`-side (caller) task
-    to_trio.send_nowait('start')
-
-    # NOTE: what happens here inside the hook needs some refinement..
-    # => seems like it's still `._debug._set_trace()` but
-    #    we set `Lock.local_task_in_debug = 'sync'`, we probably want
-    #    some further, at least, meta-data about the task/actor in debug
-    #    in terms of making it clear it's `asyncio` mucking about.
-    breakpoint()  # asyncio-side
-
-    # short checkpoint / delay
-    await asyncio.sleep(0.5)  # asyncio-side
-
-    if raise_after_bp:
-        raise ValueError('asyncio side error!')
-
-    # TODO: test case with this so that it gets cancelled?
-    else:
-        # XXX NOTE: this is required in order to get the SIGINT-ignored
-        # hang case documented in the module script section!
-        await aio_sleep_forever()
-
-
-@tractor.context
-async def trio_ctx(
-    ctx: tractor.Context,
-    bp_before_started: bool = False,
-):
-
-    # this will block until the ``asyncio`` task sends a "first"
-    # message, see first line in above func.
-    async with (
-        to_asyncio.open_channel_from(
-            bp_then_error,
-            # raise_after_bp=not bp_before_started,
-        ) as (first, chan),
-
-        trio.open_nursery() as tn,
-    ):
-        assert first == 'start'
-
-        if bp_before_started:
-            await tractor.pause()  # trio-side
-
-        await ctx.started(first)  # trio-side
-
-        tn.start_soon(
-            to_asyncio.run_task,
-            aio_sleep_forever,
-        )
-        await trio.sleep_forever()
-
-
-async def main(
-    bps_all_over: bool = True,
-
-    # TODO, WHICH OF THESE HAZ BUGZ?
-    cancel_from_root: bool = False,
-    err_from_root: bool = False,
-
-) -> None:
-
-    async with tractor.open_nursery(
-        debug_mode=True,
-        maybe_enable_greenback=True,
-        # loglevel='devx',
-    ) as an:
-        ptl: Portal = await an.start_actor(
-            'aio_daemon',
-            enable_modules=[__name__],
-            infect_asyncio=True,
-            debug_mode=True,
-            # loglevel='cancel',
-        )
-
-        async with ptl.open_context(
-            trio_ctx,
-            bp_before_started=bps_all_over,
-        ) as (ctx, first):
-
-            assert first == 'start'
-
-            # pause in parent to ensure no cross-actor
-            # locking problems exist!
-            await tractor.pause()  # trio-root
-
-            if cancel_from_root:
-                await ctx.cancel()
-
-            if err_from_root:
-                assert 0
-            else:
-                await trio.sleep_forever()
-
-
-        # TODO: case where we cancel from trio-side while asyncio task
-        # has debugger lock?
-        # await ptl.cancel_actor()
-
-
-if __name__ == '__main__':
-
-    # works fine B)
-    trio.run(main)
-
-    # will hang and ignores SIGINT !!
-    # NOTE: you'll need to send a SIGQUIT (via ctl-\) to kill it
-    # manually..
-    # trio.run(main, True)

examples/debugging/debug_mode_hang.py

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

examples/debugging/fast_error_in_root_after_spawn.py

@@ -1,5 +1,5 @@
 '''
-Fast fail test with a `Context`.
+Fast fail test with a context.
 
 Ensure the partially initialized sub-actor process
 doesn't cause a hang on error/cancel of the parent

examples/debugging/multi_daemon_subactors.py

@@ -4,15 +4,9 @@ import trio
 
 async def breakpoint_forever():
     "Indefinitely re-enter debugger in child actor."
-    try:
-        while True:
-            yield 'yo'
-            await tractor.pause()
-    except BaseException:
-        tractor.log.get_console_log().exception(
-            'Cancelled while trying to enter pause point!'
-        )
-        raise
+    while True:
+        yield 'yo'
+        await tractor.breakpoint()
 
 
 async def name_error():
@@ -21,14 +15,11 @@ async def name_error():
 
 
 async def main():
-    '''
-    Test breakpoint in a streaming actor.
-
-    '''
+    """Test breakpoint in a streaming actor.
+    """
     async with tractor.open_nursery(
         debug_mode=True,
-        loglevel='cancel',
-        # loglevel='devx',
+        loglevel='error',
     ) as n:
 
         p0 = await n.start_actor('bp_forever', enable_modules=[__name__])
@@ -36,18 +27,7 @@ async def main():
 
         # retreive results
         async with p0.open_stream_from(breakpoint_forever) as stream:
-
-            # triggers the first name error
-            try:
-                await p1.run(name_error)
-            except tractor.RemoteActorError as rae:
-                assert rae.boxed_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)
+            await p1.run(name_error)
 
 
 if __name__ == '__main__':

examples/debugging/multi_nested_subactors_error_up_through_nurseries.py

@@ -10,12 +10,7 @@ async def name_error():
 async def breakpoint_forever():
     "Indefinitely re-enter debugger in child actor."
     while True:
-        await tractor.pause()
-
-        # 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)
+        await tractor.breakpoint()
 
 
 async def spawn_until(depth=0):
@@ -23,20 +18,12 @@ async def spawn_until(depth=0):
     """
     async with tractor.open_nursery() as n:
         if depth < 1:
-
-            await n.run_in_actor(breakpoint_forever)
-
-            p = await n.run_in_actor(
+            # await n.run_in_actor('breakpoint_forever', breakpoint_forever)
+            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,
@@ -45,7 +32,6 @@ async def spawn_until(depth=0):
             )
 
 
-# TODO: notes on the new boxed-relayed errors through proxy actors
 async def main():
     """The main ``tractor`` routine.
 
@@ -67,7 +53,6 @@ async def main():
     """
     async with tractor.open_nursery(
         debug_mode=True,
-        # loglevel='cancel',
     ) as n:
 
         # spawn both actors
@@ -82,16 +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/multi_subactor_root_errors.py

@@ -40,7 +40,7 @@ async def main():
     """
     async with tractor.open_nursery(
         debug_mode=True,
-        loglevel='devx',
+        # loglevel='cancel',
     ) as n:
 
         # spawn both actors

examples/debugging/multi_subactors.py

@@ -6,7 +6,7 @@ async def breakpoint_forever():
     "Indefinitely re-enter debugger in child actor."
     while True:
         await trio.sleep(0.1)
-        await tractor.pause()
+        await tractor.breakpoint()
 
 
 async def name_error():
@@ -38,7 +38,6 @@ async def main():
     """
     async with tractor.open_nursery(
         debug_mode=True,
-        # loglevel='runtime',
     ) as n:
 
         # Spawn both actors, don't bother with collecting results

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/per_actor_debug.py

@@ -23,6 +23,5 @@ async def main():
             n.start_soon(debug_actor.run, die)
             n.start_soon(crash_boi.run, die)
 
-
 if __name__ == '__main__':
     trio.run(main)

examples/debugging/pm_in_subactor.py

@@ -1,56 +0,0 @@
-import trio
-import tractor
-
-
-@tractor.context
-async def name_error(
-    ctx: tractor.Context,
-):
-    '''
-    Raise a `NameError`, catch it and enter `.post_mortem()`, then
-    expect the `._rpc._invoke()` crash handler to also engage.
-
-    '''
-    try:
-        getattr(doggypants)  # noqa (on purpose)
-    except NameError:
-        await tractor.post_mortem()
-        raise
-
-
-async def main():
-    '''
-    Test 3 `PdbREPL` entries:
-      - one in the child due to manual `.post_mortem()`,
-      - another in the child due to runtime RPC crash handling.
-      - final one here in parent from the RAE.
-
-    '''
-    # XXX NOTE: ideally the REPL arrives at this frame in the parent
-    # ONE UP FROM the inner ctx block below!
-    async with tractor.open_nursery(
-        debug_mode=True,
-        # loglevel='cancel',
-    ) as an:
-        p: tractor.Portal = await an.start_actor(
-            'child',
-            enable_modules=[__name__],
-        )
-
-        # XXX should raise `RemoteActorError[NameError]`
-        # AND be the active frame when REPL enters!
-        try:
-            async with p.open_context(name_error) as (ctx, first):
-                assert first
-        except tractor.RemoteActorError as rae:
-            assert rae.boxed_type is NameError
-
-            # manually handle in root's parent task
-            await tractor.post_mortem()
-            raise
-        else:
-            raise RuntimeError('IPC ctx should have remote errored!?')
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/debugging/restore_builtin_breakpoint.py

@@ -1,49 +0,0 @@
-import os
-import sys
-
-import trio
-import tractor
-
-
-async def main() -> None:
-
-    # intially unset, no entry.
-    orig_pybp_var: int = os.environ.get('PYTHONBREAKPOINT')
-    assert orig_pybp_var in {None, "0"}
-
-    async with tractor.open_nursery(
-        debug_mode=True,
-    ) as an:
-        assert an
-        assert (
-            (pybp_var := os.environ['PYTHONBREAKPOINT'])
-            ==
-            'tractor.devx._debug._sync_pause_from_builtin'
-        )
-
-        # TODO: an assert that verifies the hook has indeed been, hooked
-        # XD
-        assert (
-            (pybp_hook := sys.breakpointhook)
-            is not tractor.devx._debug._set_trace
-        )
-
-        print(
-            f'$PYTHONOBREAKPOINT: {pybp_var!r}\n'
-            f'`sys.breakpointhook`: {pybp_hook!r}\n'
-        )
-        breakpoint()  # first bp, tractor hook set.
-
-    # XXX AFTER EXIT (of actor-runtime) verify the hook is unset..
-    #
-    # YES, this is weird but it's how stdlib docs say to do it..
-    # https://docs.python.org/3/library/sys.html#sys.breakpointhook
-    assert os.environ.get('PYTHONBREAKPOINT') is orig_pybp_var
-    assert sys.breakpointhook
-
-    # now ensure a regular builtin pause still works
-    breakpoint()  # last bp, stdlib hook restored
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/debugging/root_actor_breakpoint.py

@@ -10,7 +10,7 @@ async def main():
 
         await trio.sleep(0.1)
 
-        await tractor.pause()
+        await tractor.breakpoint()
 
         await trio.sleep(0.1)
 

examples/debugging/root_actor_breakpoint_forever.py

@@ -2,16 +2,13 @@ import trio
 import tractor
 
 
-async def main(
-    registry_addrs: tuple[str, int]|None = None
-):
+async def main():
 
     async with tractor.open_root_actor(
         debug_mode=True,
-        # loglevel='runtime',
     ):
         while True:
-            await tractor.pause()
+            await tractor.breakpoint()
 
 
 if __name__ == '__main__':

examples/debugging/shield_hang_in_sub.py

@@ -1,83 +0,0 @@
-'''
-Verify we can dump a `stackscope` tree on a hang.
-
-'''
-import os
-import signal
-
-import trio
-import tractor
-
-@tractor.context
-async def start_n_shield_hang(
-    ctx: tractor.Context,
-):
-    # actor: tractor.Actor = tractor.current_actor()
-
-    # sync to parent-side task
-    await ctx.started(os.getpid())
-
-    print('Entering shield sleep..')
-    with trio.CancelScope(shield=True):
-        await trio.sleep_forever()  # in subactor
-
-    # XXX NOTE ^^^ since this shields, we expect
-    # the zombie reaper (aka T800) to engage on
-    # SIGINT from the user and eventually hard-kill
-    # this subprocess!
-
-
-async def main(
-    from_test: bool = False,
-) -> None:
-
-    async with (
-        tractor.open_nursery(
-            debug_mode=True,
-            enable_stack_on_sig=True,
-            # maybe_enable_greenback=False,
-            loglevel='devx',
-        ) as an,
-    ):
-        ptl: tractor.Portal  = await an.start_actor(
-            'hanger',
-            enable_modules=[__name__],
-            debug_mode=True,
-        )
-        async with ptl.open_context(
-            start_n_shield_hang,
-        ) as (ctx, cpid):
-
-            _, proc, _ = an._children[ptl.chan.uid]
-            assert cpid == proc.pid
-
-            print(
-                'Yo my child hanging..?\n'
-                # "i'm a user who wants to see a `stackscope` tree!\n"
-            )
-
-            # XXX simulate the wrapping test's "user actions"
-            # (i.e. if a human didn't run this manually but wants to
-            # know what they should do to reproduce test behaviour)
-            if from_test:
-                print(
-                    f'Sending SIGUSR1 to {cpid!r}!\n'
-                )
-                os.kill(
-                    cpid,
-                    signal.SIGUSR1,
-                )
-
-                # simulate user cancelling program
-                await trio.sleep(0.5)
-                os.kill(
-                    os.getpid(),
-                    signal.SIGINT,
-                )
-            else:
-                # actually let user send the ctl-c
-                await trio.sleep_forever()  # in root
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/debugging/shielded_pause.py

@@ -1,88 +0,0 @@
-import trio
-import tractor
-
-
-async def cancellable_pause_loop(
-    task_status: trio.TaskStatus[trio.CancelScope] = trio.TASK_STATUS_IGNORED
-):
-    with trio.CancelScope() as cs:
-        task_status.started(cs)
-        for _ in range(3):
-            try:
-                # ON first entry, there is no level triggered
-                # cancellation yet, so this cp does a parent task
-                # ctx-switch so that this scope raises for the NEXT
-                # checkpoint we hit.
-                await trio.lowlevel.checkpoint()
-                await tractor.pause()
-
-                cs.cancel()
-
-                # parent should have called `cs.cancel()` by now
-                await trio.lowlevel.checkpoint()
-
-            except trio.Cancelled:
-                print('INSIDE SHIELDED PAUSE')
-                await tractor.pause(shield=True)
-        else:
-            # should raise it again, bubbling up to parent
-            print('BUBBLING trio.Cancelled to parent task-nursery')
-            await trio.lowlevel.checkpoint()
-
-
-async def pm_on_cancelled():
-    async with trio.open_nursery() as tn:
-        tn.cancel_scope.cancel()
-        try:
-            await trio.sleep_forever()
-        except trio.Cancelled:
-            # should also raise `Cancelled` since
-            # we didn't pass `shield=True`.
-            try:
-                await tractor.post_mortem(hide_tb=False)
-            except trio.Cancelled as taskc:
-
-                # should enter just fine, in fact it should
-                # be debugging the internals of the previous
-                # sin-shield call above Bo
-                await tractor.post_mortem(
-                    hide_tb=False,
-                    shield=True,
-                )
-                raise taskc
-
-        else:
-            raise RuntimeError('Dint cancel as expected!?')
-
-
-async def cancelled_before_pause(
-):
-    '''
-    Verify that using a shielded pause works despite surrounding
-    cancellation called state in the calling task.
-
-    '''
-    async with trio.open_nursery() as tn:
-        cs: trio.CancelScope = await tn.start(cancellable_pause_loop)
-        await trio.sleep(0.1)
-
-    assert cs.cancelled_caught
-
-    await pm_on_cancelled()
-
-
-async def main():
-    async with tractor.open_nursery(
-        debug_mode=True,
-    ) as n:
-        portal: tractor.Portal = await n.run_in_actor(
-            cancelled_before_pause,
-        )
-        await portal.result()
-
-        # ensure the same works in the root actor!
-        await pm_on_cancelled()
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/debugging/subactor_bp_in_ctx.py

@@ -1,50 +0,0 @@
-import tractor
-import trio
-
-
-async def gen():
-    yield 'yo'
-    await tractor.pause()
-    yield 'yo'
-    await tractor.pause()
-
-
-@tractor.context
-async def just_bp(
-    ctx: tractor.Context,
-) -> None:
-
-    await ctx.started()
-    await tractor.pause()
-
-    # TODO: bps and errors in this call..
-    async for val in gen():
-        print(val)
-
-    # await trio.sleep(0.5)
-
-    # prematurely destroy the connection
-    await ctx.chan.aclose()
-
-    # THIS CAUSES AN UNRECOVERABLE HANG
-    # without latest ``pdbpp``:
-    assert 0
-
-
-
-async def main():
-    async with tractor.open_nursery(
-        debug_mode=True,
-    ) as n:
-        p = await n.start_actor(
-            'bp_boi',
-            enable_modules=[__name__],
-        )
-        async with p.open_context(
-            just_bp,
-        ) as (ctx, first):
-            await trio.sleep_forever()
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/debugging/subactor_breakpoint.py

@@ -3,20 +3,17 @@ import tractor
 
 
 async def breakpoint_forever():
-    '''
-    Indefinitely re-enter debugger in child actor.
-
-    '''
+    """Indefinitely re-enter debugger in child actor.
+    """
     while True:
         await trio.sleep(0.1)
-        await tractor.pause()
+        await tractor.breakpoint()
 
 
 async def main():
 
     async with tractor.open_nursery(
         debug_mode=True,
-        loglevel='cancel',
     ) as n:
 
         portal = await n.run_in_actor(

examples/debugging/subactor_error.py

@@ -3,26 +3,16 @@ import tractor
 
 
 async def name_error():
-    getattr(doggypants)  # noqa (on purpose)
+    getattr(doggypants)
 
 
 async def main():
     async with tractor.open_nursery(
         debug_mode=True,
-        # loglevel='transport',
-    ) as an:
+    ) as n:
 
-        # TODO: ideally the REPL arrives at this frame in the parent,
-        # ABOVE the @api_frame of `Portal.run_in_actor()` (which
-        # should eventually not even be a portal method ... XD)
-        # await tractor.pause()
-        p: tractor.Portal = await an.run_in_actor(name_error)
-
-        # with this style, should raise on this line
-        await p.result()
-
-        # with this alt style should raise at `open_nusery()`
-        # return await p.result()
+        portal = await n.run_in_actor(name_error)
+        await portal.result()
 
 
 if __name__ == '__main__':

examples/debugging/sync_bp.py

@@ -1,169 +0,0 @@
-from functools import partial
-import time
-
-import trio
-import tractor
-
-# TODO: only import these when not running from test harness?
-# can we detect `pexpect` usage maybe?
-# from tractor.devx._debug import (
-#     get_lock,
-#     get_debug_req,
-# )
-
-
-def sync_pause(
-    use_builtin: bool = False,
-    error: bool = False,
-    hide_tb: bool = True,
-    pre_sleep: float|None = None,
-):
-    if pre_sleep:
-        time.sleep(pre_sleep)
-
-    if use_builtin:
-        breakpoint(hide_tb=hide_tb)
-
-    else:
-        # TODO: maybe for testing some kind of cm style interface
-        # where the `._set_trace()` call doesn't happen until block
-        # exit?
-        # assert get_lock().ctx_in_debug is None
-        # assert get_debug_req().repl is None
-        tractor.pause_from_sync()
-        # assert get_debug_req().repl is None
-
-    if error:
-        raise RuntimeError('yoyo sync code error')
-
-
-@tractor.context
-async def start_n_sync_pause(
-    ctx: tractor.Context,
-):
-    actor: tractor.Actor = tractor.current_actor()
-
-    # sync to parent-side task
-    await ctx.started()
-
-    print(f'Entering `sync_pause()` in subactor: {actor.uid}\n')
-    sync_pause()
-    print(f'Exited `sync_pause()` in subactor: {actor.uid}\n')
-
-
-async def main() -> None:
-    async with (
-        tractor.open_nursery(
-            debug_mode=True,
-            maybe_enable_greenback=True,
-            enable_stack_on_sig=True,
-            # loglevel='warning',
-            # loglevel='devx',
-        ) as an,
-        trio.open_nursery() as tn,
-    ):
-        # just from root task
-        sync_pause()
-
-        p: tractor.Portal  = await an.start_actor(
-            'subactor',
-            enable_modules=[__name__],
-            # infect_asyncio=True,
-            debug_mode=True,
-        )
-
-        # TODO: 3 sub-actor usage cases:
-        # -[x] via a `.open_context()`
-        # -[ ] via a `.run_in_actor()` call
-        # -[ ] via a `.run()`
-        # -[ ] via a `.to_thread.run_sync()` in subactor
-        async with p.open_context(
-            start_n_sync_pause,
-        ) as (ctx, first):
-            assert first is None
-
-            # TODO: handle bg-thread-in-root-actor special cases!
-            #
-            # there are a couple very subtle situations possible here
-            # and they are likely to become more important as cpython
-            # moves to support no-GIL.
-            #
-            # Cases:
-            # 1. root-actor bg-threads that call `.pause_from_sync()`
-            #   whilst an in-tree subactor also is using ` .pause()`.
-            # |_ since the root-actor bg thread can not
-            #   `Lock._debug_lock.acquire_nowait()` without running
-            #   a `trio.Task`, AND because the
-            #   `PdbREPL.set_continue()` is called from that
-            #   bg-thread, we can not `._debug_lock.release()`
-            #   either!
-            #  |_ this results in no actor-tree `Lock` being used
-            #    on behalf of the bg-thread and thus the subactor's
-            #    task and the thread trying to to use stdio
-            #    simultaneously which results in the classic TTY
-            #    clobbering!
-            #
-            # 2. mutiple sync-bg-threads that call
-            #   `.pause_from_sync()` where one is scheduled via
-            #   `Nursery.start_soon(to_thread.run_sync)` in a bg
-            #   task.
-            #
-            #   Due to the GIL, the threads never truly try to step
-            #   through the REPL simultaneously, BUT their `logging`
-            #   and traceback outputs are interleaved since the GIL
-            #   (seemingly) on every REPL-input from the user
-            #   switches threads..
-            #
-            #   Soo, the context switching semantics of the GIL
-            #   result in a very confusing and messy interaction UX
-            #   since eval and (tb) print output is NOT synced to
-            #   each REPL-cycle (like we normally make it via
-            #   a `.set_continue()` callback triggering the
-            #   `Lock.release()`). Ideally we can solve this
-            #   usability issue NOW because this will of course be
-            #   that much more important when eventually there is no
-            #   GIL!
-
-            # XXX should cause double REPL entry and thus TTY
-            # clobbering due to case 1. above!
-            tn.start_soon(
-                partial(
-                    trio.to_thread.run_sync,
-                    partial(
-                        sync_pause,
-                        use_builtin=False,
-                        # pre_sleep=0.5,
-                    ),
-                    abandon_on_cancel=True,
-                    thread_name='start_soon_root_bg_thread',
-                )
-            )
-
-            await tractor.pause()
-
-            # XXX should cause double REPL entry and thus TTY
-            # clobbering due to case 2. above!
-            await trio.to_thread.run_sync(
-                partial(
-                    sync_pause,
-                    # NOTE this already works fine since in the new
-                    # thread the `breakpoint()` built-in is never
-                    # overloaded, thus NO locking is used, HOWEVER
-                    # the case 2. from above still exists!
-                    use_builtin=True,
-                ),
-                # TODO: with this `False` we can hang!??!
-                # abandon_on_cancel=False,
-                abandon_on_cancel=True,
-                thread_name='inline_root_bg_thread',
-            )
-
-        await ctx.cancel()
-
-        # TODO: case where we cancel from trio-side while asyncio task
-        # has debugger lock?
-        await p.cancel_actor()
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/full_fledged_streaming_service.py

@@ -1,11 +1,6 @@
 import time
 import trio
 import tractor
-from tractor import (
-    ActorNursery,
-    MsgStream,
-    Portal,
-)
 
 
 # this is the first 2 actors, streamer_1 and streamer_2
@@ -17,18 +12,14 @@ async def stream_data(seed):
 
 # this is the third actor; the aggregator
 async def aggregate(seed):
-    '''
-    Ensure that the two streams we receive match but only stream
+    """Ensure that the two streams we receive match but only stream
     a single set of values to the parent.
-
-    '''
-    an: ActorNursery
-    async with tractor.open_nursery() as an:
-        portals: list[Portal] = []
+    """
+    async with tractor.open_nursery() as nursery:
+        portals = []
         for i in range(1, 3):
-
-            # fork/spawn call
-            portal = await an.start_actor(
+            # fork point
+            portal = await nursery.start_actor(
                 name=f'streamer_{i}',
                 enable_modules=[__name__],
             )
@@ -52,11 +43,7 @@ async def aggregate(seed):
         async with trio.open_nursery() as n:
 
             for portal in portals:
-                n.start_soon(
-                    push_to_chan,
-                    portal,
-                    send_chan.clone(),
-                )
+                n.start_soon(push_to_chan, portal, send_chan.clone())
 
             # close this local task's reference to send side
             await send_chan.aclose()
@@ -73,36 +60,26 @@ async def aggregate(seed):
 
             print("FINISHED ITERATING in aggregator")
 
-        await an.cancel()
+        await nursery.cancel()
         print("WAITING on `ActorNursery` to finish")
     print("AGGREGATOR COMPLETE!")
 
 
-async def main() -> list[int]:
-    '''
-    This is the "root" actor's main task's entrypoint.
-
-    By default (and if not otherwise specified) that root process
-    also acts as a "registry actor" / "registrar" on the localhost
-    for the purposes of multi-actor "service discovery".
-
-    '''
-    # yes, a nursery which spawns `trio`-"actors" B)
-    an: ActorNursery
+# this is the main actor and *arbiter*
+async def main():
+    # a nursery which spawns "actors"
     async with tractor.open_nursery(
-        loglevel='cancel',
-        # debug_mode=True,
-    ) as an:
+        arbiter_addr=('127.0.0.1', 1616)
+    ) as nursery:
 
         seed = int(1e3)
         pre_start = time.time()
 
-        portal: Portal = await an.start_actor(
+        portal = await nursery.start_actor(
             name='aggregator',
             enable_modules=[__name__],
         )
 
-        stream: MsgStream
         async with portal.open_stream_from(
             aggregate,
             seed=seed,
@@ -111,12 +88,11 @@ async def main() -> list[int]:
             start = time.time()
             # the portal call returns exactly what you'd expect
             # as if the remote "aggregate" function was called locally
-            result_stream: list[int] = []
+            result_stream = []
             async for value in stream:
                 result_stream.append(value)
 
-        cancelled: bool = await portal.cancel_actor()
-        assert cancelled
+        await portal.cancel_actor()
 
         print(f"STREAM TIME = {time.time() - start}")
         print(f"STREAM + SPAWN TIME = {time.time() - pre_start}")

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

@@ -8,17 +8,15 @@ This uses no extra threads, fancy semaphores or futures; all we need
 is ``tractor``'s channels.
 
 """
-from contextlib import (
-    asynccontextmanager as acm,
-    aclosing,
-)
-from typing import Callable
+from contextlib import asynccontextmanager
+from typing import List, Callable
 import itertools
 import math
 import time
 
 import tractor
 import trio
+from async_generator import aclosing
 
 
 PRIMES = [
@@ -46,7 +44,7 @@ async def is_prime(n):
     return True
 
 
-@acm
+@asynccontextmanager
 async def worker_pool(workers=4):
     """Though it's a trivial special case for ``tractor``, the well
     known "worker pool" seems to be the defacto "but, I want this
@@ -73,8 +71,8 @@ async def worker_pool(workers=4):
 
         async def _map(
             worker_func: Callable[[int], bool],
-            sequence: list[int]
-        ) -> list[bool]:
+            sequence: List[int]
+        ) -> List[bool]:
 
             # define an async (local) task to collect results from workers
             async def send_result(func, value, portal):

examples/quick_cluster.py

@@ -3,18 +3,20 @@ import trio
 import tractor
 
 
-async def sleepy_jane() -> None:
-    uid: tuple = tractor.current_actor().uid
+async def sleepy_jane():
+    uid = tractor.current_actor().uid
     print(f'Yo i am actor {uid}')
     await trio.sleep_forever()
 
 
 async def main():
     '''
-    Spawn a flat actor cluster, with one process per detected core.
+    Spawn a flat actor cluster, with one process per
+    detected core.
 
     '''
     portal_map: dict[str, tractor.Portal]
+    results: dict[str, str]
 
     # look at this hip new syntax!
     async with (
@@ -23,16 +25,11 @@ async def main():
             modules=[__name__]
         ) as portal_map,
 
-        trio.open_nursery(
-            strict_exception_groups=False,
-        ) as tn,
+        trio.open_nursery() as n,
     ):
 
         for (name, portal) in portal_map.items():
-            tn.start_soon(
-                portal.run,
-                sleepy_jane,
-            )
+            n.start_soon(portal.run, sleepy_jane)
 
         await trio.sleep(0.5)
 
@@ -44,4 +41,4 @@ if __name__ == '__main__':
     try:
         trio.run(main)
     except KeyboardInterrupt:
-        print('trio cancelled by KBI')
+        pass

examples/rpc_bidir_streaming.py

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

examples/service_discovery.py

@@ -9,7 +9,7 @@ async def main(service_name):
     async with tractor.open_nursery() as an:
         await an.start_actor(service_name)
 
-        async with tractor.get_registry('127.0.0.1', 1616) as portal:
+        async with tractor.get_arbiter('127.0.0.1', 1616) as portal:
             print(f"Arbiter is listening on {portal.channel}")
 
         async with tractor.wait_for_actor(service_name) as sockaddr:

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/303.misc.rst

@@ -0,0 +1,4 @@
+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``.

nooz/304.feature.rst

@@ -0,0 +1,12 @@
+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.

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.

notes_to_self/howtorelease.md

@@ -1,18 +0,0 @@
-First generate a built disti:
-
-```
-python -m pip install --upgrade build
-python -m build --sdist --outdir dist/alpha5/
-```
-
-Then try a test ``pypi`` upload:
-
-```
-python -m twine upload --repository testpypi dist/alpha5/*
-```
-
-The push to `pypi` for realz.
-
-```
-python -m twine upload --repository testpypi dist/alpha5/*
-```

pyproject.toml

@@ -1,158 +0,0 @@
-[build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
-
-# ------ build-system ------
-
-[project]
-name = "tractor"
-version = "0.1.0a6dev0"
-description = 'structured concurrent `trio`-"actors"'
-authors = [{ name = "Tyler Goodlet", email = "goodboy_foss@protonmail.com" }]
-requires-python = ">= 3.11"
-readme = "docs/README.rst"
-license = "AGPL-3.0-or-later"
-keywords = [
-  "trio",
-  "async",
-  "concurrency",
-  "structured concurrency",
-  "actor model",
-  "distributed",
-  "multiprocessing",
-]
-classifiers = [
-  "Development Status :: 3 - Alpha",
-  "Operating System :: POSIX :: Linux",
-  "Framework :: Trio",
-  "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
-  "Programming Language :: Python :: Implementation :: CPython",
-  "Programming Language :: Python :: 3 :: Only",
-  "Programming Language :: Python :: 3.11",
-  "Topic :: System :: Distributed Computing",
-]
-dependencies = [
-  # trio runtime and friends
-  # (poetry) proper range specs,
-  # https://packaging.python.org/en/latest/discussions/install-requires-vs-requirements/#id5
-  # TODO, for 3.13 we must go go `0.27` which means we have to
-  # disable strict egs or port to handling them internally!
-  "trio>0.27",
-  "tricycle>=0.4.1,<0.5",
-  "wrapt>=1.16.0,<2",
-  "colorlog>=6.8.2,<7",
-  # built-in multi-actor `pdb` REPL
-  "pdbp>=1.6,<2", # windows only (from `pdbp`)
-  # typed IPC msging
-  "msgspec>=0.19.0",
-]
-
-# ------ project ------
-
-[dependency-groups]
-dev = [
-  # test suite
-  # TODO: maybe some of these layout choices?
-  # https://docs.pytest.org/en/8.0.x/explanation/goodpractices.html#choosing-a-test-layout-import-rules
-  "pytest>=8.3.5",
-  "pexpect>=4.9.0,<5",
-  # `tractor.devx` tooling
-  "greenback>=1.2.1,<2",
-  "stackscope>=0.2.2,<0.3",
-  "pyperclip>=1.9.0",
-  "prompt-toolkit>=3.0.50",
-  "xonsh>=0.19.2",
-]
-# TODO, add these with sane versions; were originally in
-# `requirements-docs.txt`..
-# docs = [
-#   "sphinx>="
-#   "sphinx_book_theme>="
-# ]
-
-# ------ dependency-groups ------
-
-# ------ dependency-groups ------
-
-[tool.uv.sources]
-# XXX NOTE, only for @goodboy's hacking on `pprint(sort_dicts=False)`
-# for the `pp` alias..
-# pdbp = { path = "../pdbp", editable = true }
-
-# ------ tool.uv.sources ------
-# TODO, distributed (multi-host) extensions
-# linux kernel networking
-# 'pyroute2
-
-# ------ tool.uv.sources ------
-
-[tool.uv]
-# XXX NOTE, prefer the sys python bc apparently the distis from
-# `astral` are built in a way that breaks `pdbp`+`tabcompleter`'s
-# likely due to linking against `libedit` over `readline`..
-# |_https://docs.astral.sh/uv/concepts/python-versions/#managed-python-distributions
-# |_https://gregoryszorc.com/docs/python-build-standalone/main/quirks.html#use-of-libedit-on-linux
-#
-# https://docs.astral.sh/uv/reference/settings/#python-preference
-python-preference = 'system'
-
-# ------ tool.uv ------
-
-[tool.hatch.build.targets.sdist]
-include = ["tractor"]
-
-[tool.hatch.build.targets.wheel]
-include = ["tractor"]
-
-# ------ tool.hatch ------
-
-[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
-
-# ------ tool.towncrier ------
-
-[tool.pytest.ini_options]
-minversion = '6.0'
-testpaths = [
-  'tests'
-]
-addopts = [
-  # TODO: figure out why this isn't working..
-  '--rootdir=./tests',
-
-  '--import-mode=importlib',
-  # don't show frickin captured logs AGAIN in the report..
-  '--show-capture=no',
-]
-log_cli = false
-# TODO: maybe some of these layout choices?
-# https://docs.pytest.org/en/8.0.x/explanation/goodpractices.html#choosing-a-test-layout-import-rules
-# pythonpath = "src"
-
-# ------ tool.pytest ------

pytest.ini

@@ -1,8 +0,0 @@
-# vim: ft=ini
-# pytest.ini for tractor
-
-[pytest]
-# don't show frickin captured logs AGAIN in the report..
-addopts = --show-capture='no'
-log_cli = false
-; minversion = 6.0

requirements-docs.txt

@@ -0,0 +1,2 @@
+sphinx
+sphinx_book_theme

requirements-test.txt

@@ -0,0 +1,7 @@
+pytest
+pytest-trio
+pdbpp
+mypy<0.920
+trio_typing<0.7.0
+pexpect
+towncrier

ruff.toml

@@ -1,82 +0,0 @@
-# from default `ruff.toml` @
-# https://docs.astral.sh/ruff/configuration/
-
-# Exclude a variety of commonly ignored directories.
-exclude = [
-    ".bzr",
-    ".direnv",
-    ".eggs",
-    ".git",
-    ".git-rewrite",
-    ".hg",
-    ".ipynb_checkpoints",
-    ".mypy_cache",
-    ".nox",
-    ".pants.d",
-    ".pyenv",
-    ".pytest_cache",
-    ".pytype",
-    ".ruff_cache",
-    ".svn",
-    ".tox",
-    ".venv",
-    ".vscode",
-    "__pypackages__",
-    "_build",
-    "buck-out",
-    "build",
-    "dist",
-    "node_modules",
-    "site-packages",
-    "venv",
-]
-
-# Same as Black.
-line-length = 88
-indent-width = 4
-
-# Assume Python 3.9
-target-version = "py311"
-
-[lint]
-# Enable Pyflakes (`F`) and a subset of the pycodestyle (`E`)  codes by default.
-# Unlike Flake8, Ruff doesn't enable pycodestyle warnings (`W`) or
-# McCabe complexity (`C901`) by default.
-select = ["E4", "E7", "E9", "F"]
-ignore = [
-  'E402',  # https://docs.astral.sh/ruff/rules/module-import-not-at-top-of-file/
-]
-
-# Allow fix for all enabled rules (when `--fix`) is provided.
-fixable = ["ALL"]
-unfixable = []
-
-# Allow unused variables when underscore-prefixed.
-# dummy-variable-rgx = "^(_+|(_+[a-zA-Z0-9_]*[a-zA-Z0-9]+?))$"
-
-[format]
-# Use single quotes in `ruff format`.
-quote-style = "single"
-
-# Like Black, indent with spaces, rather than tabs.
-indent-style = "space"
-
-# Like Black, respect magic trailing commas.
-skip-magic-trailing-comma = false
-
-# Like Black, automatically detect the appropriate line ending.
-line-ending = "auto"
-
-# Enable auto-formatting of code examples in docstrings. Markdown,
-# reStructuredText code/literal blocks and doctests are all supported.
-#
-# This is currently disabled by default, but it is planned for this
-# to be opt-out in the future.
-docstring-code-format = false
-
-# Set the line length limit used when formatting code snippets in
-# docstrings.
-#
-# This only has an effect when the `docstring-code-format` setting is
-# enabled.
-docstring-code-line-length = "dynamic"

setup.py

@@ -0,0 +1,93 @@
+#!/usr/bin/env python
+#
+# 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 setuptools import setup
+
+with open('docs/README.rst', encoding='utf-8') as f:
+    readme = f.read()
+
+
+setup(
+    name="tractor",
+    version='0.1.0a5.dev',  # alpha zone
+    description='structured concurrrent "actors"',
+    long_description=readme,
+    license='AGPLv3',
+    author='Tyler Goodlet',
+    maintainer='Tyler Goodlet',
+    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
+        'trio>0.8',
+        'async_generator',
+        'trio_typing',
+
+        # tooling
+        'tricycle',
+        'trio_typing',
+
+        # tooling
+        'colorlog',
+        'wrapt',
+        'pdbpp',
+
+        # serialization
+        'msgpack>=1.0.3',
+
+    ],
+    extras_require={
+
+        # serialization
+        'msgspec': ['msgspec >= "0.4.0"'],
+
+    },
+    tests_require=['pytest'],
+    python_requires=">=3.9",
+    keywords=[
+        'trio',
+        "async",
+        "concurrency",
+        "actor model",
+        "distributed",
+        'multiprocessing'
+    ],
+    classifiers=[
+        "Development Status :: 3 - Alpha",
+        "Operating System :: POSIX :: Linux",
+        "Operating System :: Microsoft :: Windows",
+        "Framework :: Trio",
+        "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
+        "Programming Language :: Python :: Implementation :: CPython",
+        "Programming Language :: Python :: 3 :: Only",
+        "Programming Language :: Python :: 3.8",
+        "Programming Language :: Python :: 3.9",
+        "Intended Audience :: Science/Research",
+        "Intended Audience :: Developers",
+        "Topic :: System :: Distributed Computing",
+    ],
+)

tests/conftest.py

@@ -11,14 +11,14 @@ import time
 
 import pytest
 import tractor
-from tractor._testing import (
-    examples_dir as examples_dir,
-    tractor_test as tractor_test,
-    expect_ctxc as expect_ctxc,
-)
 
-# TODO: include wtv plugin(s) we build in `._testing.pytest`?
+# export for tests
+from tractor.testing import tractor_test  # noqa
+
+
 pytest_plugins = ['pytester']
+_arb_addr = '127.0.0.1', random.randint(1000, 9999)
+
 
 # Sending signal.SIGINT on subprocess fails on windows. Use CTRL_* alternatives
 if platform.system() == 'Windows':
@@ -39,46 +39,36 @@ no_windows = pytest.mark.skipif(
 )
 
 
+def repodir():
+    """Return the abspath to the repo directory.
+    """
+    dirname = os.path.dirname
+    dirpath = os.path.abspath(
+        dirname(dirname(os.path.realpath(__file__)))
+        )
+    return dirpath
+
+
 def pytest_addoption(parser):
     parser.addoption(
-        "--ll",
-        action="store",
-        dest='loglevel',
+        "--ll", action="store", dest='loglevel',
         default='ERROR', help="logging level to set when testing"
     )
 
     parser.addoption(
-        "--spawn-backend",
-        action="store",
-        dest='spawn_backend',
+        "--spawn-backend", action="store", dest='spawn_backend',
         default='trio',
         help="Processing spawning backend to use for test run",
     )
 
-    parser.addoption(
-        "--tpdb", "--debug-mode",
-        action="store_true",
-        dest='tractor_debug_mode',
-        # default=False,
-        help=(
-            'Enable a flag that can be used by tests to to set the '
-            '`debug_mode: bool` for engaging the internal '
-            'multi-proc debugger sys.'
-        ),
-    )
-
 
 def pytest_configure(config):
     backend = config.option.spawn_backend
-    tractor._spawn.try_set_start_method(backend)
 
-
-@pytest.fixture(scope='session')
-def debug_mode(request):
-    debug_mode: bool = request.config.option.tractor_debug_mode
-    # if debug_mode:
-    #     breakpoint()
-    return debug_mode
+    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)
@@ -91,84 +81,42 @@ def loglevel(request):
 
 
 @pytest.fixture(scope='session')
-def spawn_backend(request) -> str:
+def spawn_backend(request):
     return request.config.option.spawn_backend
 
 
-# @pytest.fixture(scope='function', autouse=True)
-# def debug_enabled(request) -> str:
-#     from tractor import _state
-#     if _state._runtime_vars['_debug_mode']:
-#         breakpoint()
-
-_ci_env: bool = os.environ.get('CI', False)
-
-
 @pytest.fixture(scope='session')
 def ci_env() -> bool:
-    '''
-    Detect CI envoirment.
-
-    '''
-    return _ci_env
-
-
-# TODO: also move this to `._testing` for now?
-# -[ ] possibly generalize and re-use for multi-tree spawning
-#    along with the new stuff for multi-addrs in distribute_dis
-#    branch?
-#
-# choose randomly at import time
-_reg_addr: tuple[str, int] = (
-    '127.0.0.1',
-    random.randint(1000, 9999),
-)
+    """Detect CI envoirment.
+    """
+    return os.environ.get('TRAVIS', False) or os.environ.get('CI', False)
 
 
 @pytest.fixture(scope='session')
-def reg_addr() -> tuple[str, int]:
-
-    # globally override the runtime to the per-test-session-dynamic
-    # addr so that all tests never conflict with any other actor
-    # tree using the default.
-    from tractor import _root
-    _root._default_lo_addrs = [_reg_addr]
-
-    return _reg_addr
+def arb_addr():
+    return _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']
 
-
-# TODO: a way to let test scripts (like from `examples/`)
-# guarantee they won't registry addr collide!
-# @pytest.fixture
-# def open_test_runtime(
-#     reg_addr: tuple,
-# ) -> AsyncContextManager:
-#     return partial(
-#         tractor.open_nursery,
-#         registry_addrs=[reg_addr],
-#     )
+        metafunc.parametrize("start_method", methods, scope='module')
 
 
 def sig_prog(proc, sig):
@@ -183,40 +131,28 @@ def sig_prog(proc, sig):
     assert ret
 
 
-# TODO: factor into @cm and move to `._testing`?
 @pytest.fixture
-def daemon(
-    loglevel: str,
-    testdir,
-    reg_addr: tuple[str, int],
-):
-    '''
-    Run a daemon root actor as a separate actor-process tree and
-    "remote registrar" for discovery-protocol related tests.
-
-    '''
+def daemon(loglevel, testdir, arb_addr):
+    """Run a daemon actor as a "remote arbiter".
+    """
     if loglevel in ('trace', 'debug'):
-        # XXX: too much logging will lock up the subproc (smh)
-        loglevel: str = 'info'
+        # too much logging will lock up the subproc (smh)
+        loglevel = 'info'
 
-    code: str = (
-            "import tractor; "
-            "tractor.run_daemon([], registry_addrs={reg_addrs}, loglevel={ll})"
-    ).format(
-        reg_addrs=str([reg_addr]),
-        ll="'{}'".format(loglevel) if loglevel else None,
-    )
-    cmd: list[str] = [
-        sys.executable,
-        '-c', code,
+    cmdargs = [
+        sys.executable, '-c',
+        "import tractor; tractor.run_daemon([], arbiter_addr={}, loglevel={})"
+        .format(
+            arb_addr,
+            "'{}'".format(loglevel) if loglevel else None)
     ]
-    kwargs = {}
+    kwargs = dict()
     if platform.system() == 'Windows':
         # without this, tests hang on windows forever
         kwargs['creationflags'] = subprocess.CREATE_NEW_PROCESS_GROUP
 
     proc = testdir.popen(
-        cmd,
+        cmdargs,
         stdout=subprocess.PIPE,
         stderr=subprocess.PIPE,
         **kwargs,

tests/devx/conftest.py

@@ -1,243 +0,0 @@
-'''
-`tractor.devx.*` tooling sub-pkg test space.
-
-'''
-import time
-from typing import (
-    Callable,
-)
-
-import pytest
-from pexpect.exceptions import (
-    TIMEOUT,
-)
-from pexpect.spawnbase import SpawnBase
-
-from tractor._testing import (
-    mk_cmd,
-)
-from tractor.devx._debug import (
-    _pause_msg as _pause_msg,
-    _crash_msg as _crash_msg,
-    _repl_fail_msg as _repl_fail_msg,
-    _ctlc_ignore_header as _ctlc_ignore_header,
-)
-from ..conftest import (
-    _ci_env,
-)
-
-
-@pytest.fixture
-def spawn(
-    start_method,
-    testdir: pytest.Pytester,
-    reg_addr: tuple[str, int],
-
-) -> Callable[[str], None]:
-    '''
-    Use the `pexpect` module shipped via `testdir.spawn()` to
-    run an `./examples/..` script by name.
-
-    '''
-    if start_method != 'trio':
-        pytest.skip(
-            '`pexpect` based tests only supported on `trio` backend'
-        )
-
-    def unset_colors():
-        '''
-        Python 3.13 introduced colored tracebacks that break patt
-        matching,
-
-        https://docs.python.org/3/using/cmdline.html#envvar-PYTHON_COLORS
-        https://docs.python.org/3/using/cmdline.html#using-on-controlling-color
-
-        '''
-        import os
-        os.environ['PYTHON_COLORS'] = '0'
-
-    def _spawn(
-        cmd: str,
-        **mkcmd_kwargs,
-    ):
-        unset_colors()
-        return testdir.spawn(
-            cmd=mk_cmd(
-                cmd,
-                **mkcmd_kwargs,
-            ),
-            expect_timeout=3,
-            # preexec_fn=unset_colors,
-            # ^TODO? get `pytest` core to expose underlying
-            # `pexpect.spawn()` stuff?
-        )
-
-    # such that test-dep can pass input script name.
-    return _spawn
-
-
-@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 mark.name == 'ctlcs_bish':
-            pytest.skip(
-                f'Test {node} prolly uses something from the stdlib (namely `asyncio`..)\n'
-                f'The test and/or underlying example script can *sometimes* run fine '
-                f'locally but more then likely until the cpython peeps get their sh#$ together, '
-                f'this test will definitely not behave like `trio` under SIGINT..\n'
-            )
-
-    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.devx._debug import TractorConfig
-        TractorConfig.use_pygements = False
-
-    yield use_ctlc
-
-
-def expect(
-    child,
-
-    # normally a `pdb` prompt by default
-    patt: str,
-
-    **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
-
-
-PROMPT = r"\(Pdb\+\)"
-
-
-def in_prompt_msg(
-    child: SpawnBase,
-    parts: list[str],
-
-    pause_on_false: bool = False,
-    err_on_false: bool = False,
-    print_prompt_on_false: bool = True,
-
-) -> bool:
-    '''
-    Predicate check if (the prompt's) std-streams output has all
-    `str`-parts in it.
-
-    Can be used in test asserts for bulk matching expected
-    log/REPL output for a given `pdb` interact point.
-
-    '''
-    __tracebackhide__: bool = False
-
-    before: str = str(child.before.decode())
-    for part in parts:
-        if part not in before:
-            if pause_on_false:
-                import pdbp
-                pdbp.set_trace()
-
-            if print_prompt_on_false:
-                print(before)
-
-            if err_on_false:
-                raise ValueError(
-                    f'Could not find pattern in `before` output?\n'
-                    f'part: {part!r}\n'
-                )
-            return False
-
-    return True
-
-
-# TODO: todo support terminal color-chars stripping so we can match
-# against call stack frame output from the the 'll' command the like!
-# -[ ] SO answer for stipping ANSI codes: https://stackoverflow.com/a/14693789
-def assert_before(
-    child: SpawnBase,
-    patts: list[str],
-
-    **kwargs,
-
-) -> None:
-    __tracebackhide__: bool = False
-
-    assert in_prompt_msg(
-        child=child,
-        parts=patts,
-
-        # since this is an "assert" helper ;)
-        err_on_false=True,
-        **kwargs
-    )
-
-
-def do_ctlc(
-    child,
-    count: int = 3,
-    delay: float = 0.1,
-    patt: str|None = 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,
-
-) -> str|None:
-
-    before: str|None = 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:
-            time.sleep(delay)
-            child.expect(PROMPT)
-            before = str(child.before.decode())
-            time.sleep(delay)
-
-            if patt:
-                # should see the last line on console
-                assert patt in before
-
-    # return the console content up to the final prompt
-    return before

tests/devx/test_pause_from_non_trio.py

@@ -1,381 +0,0 @@
-'''
-That "foreign loop/thread" debug REPL support better ALSO WORK!
-
-Same as `test_native_pause.py`.
-All these tests can be understood (somewhat) by running the
-equivalent `examples/debugging/` scripts manually.
-
-'''
-from contextlib import (
-    contextmanager as cm,
-)
-# from functools import partial
-# import itertools
-import time
-# from typing import (
-#     Iterator,
-# )
-
-import pytest
-from pexpect.exceptions import (
-    TIMEOUT,
-    EOF,
-)
-
-from .conftest import (
-    # _ci_env,
-    do_ctlc,
-    PROMPT,
-    # expect,
-    in_prompt_msg,
-    assert_before,
-    _pause_msg,
-    _crash_msg,
-    _ctlc_ignore_header,
-    # _repl_fail_msg,
-)
-
-@cm
-def maybe_expect_timeout(
-    ctlc: bool = False,
-) -> None:
-    try:
-        yield
-    except TIMEOUT:
-        # breakpoint()
-        if ctlc:
-            pytest.xfail(
-                'Some kinda redic threading SIGINT bug i think?\n'
-                'See the notes in `examples/debugging/sync_bp.py`..\n'
-            )
-        raise
-
-
-@pytest.mark.ctlcs_bish
-def test_pause_from_sync(
-    spawn,
-    ctlc: bool,
-):
-    '''
-    Verify we can use the `pdbp` REPL from sync functions AND from
-    any thread spawned with `trio.to_thread.run_sync()`.
-
-    `examples/debugging/sync_bp.py`
-
-    '''
-    child = spawn('sync_bp')
-
-    # first `sync_pause()` after nurseries open
-    child.expect(PROMPT)
-    assert_before(
-        child,
-        [
-            # pre-prompt line
-            _pause_msg,
-            "<Task '__main__.main'",
-            "('root'",
-        ]
-    )
-    if ctlc:
-        do_ctlc(child)
-        # ^NOTE^ subactor not spawned yet; don't need extra delay.
-
-    child.sendline('c')
-
-    # first `await tractor.pause()` inside `p.open_context()` body
-    child.expect(PROMPT)
-
-    # XXX shouldn't see gb loaded message with PDB loglevel!
-    # assert not in_prompt_msg(
-    #     child,
-    #     ['`greenback` portal opened!'],
-    # )
-    # should be same root task
-    assert_before(
-        child,
-        [
-            _pause_msg,
-            "<Task '__main__.main'",
-            "('root'",
-        ]
-    )
-
-    if ctlc:
-        do_ctlc(
-            child,
-            # NOTE: setting this to 0 (or some other sufficient
-            # small val) can cause the test to fail since the
-            # `subactor` suffers a race where the root/parent
-            # sends an actor-cancel prior to it hitting its pause
-            # point; by def the value is 0.1
-            delay=0.4,
-        )
-
-    # XXX, fwiw without a brief sleep here the SIGINT might actually
-    # trigger "subactor" cancellation by its parent  before the
-    # shield-handler is engaged.
-    #
-    # => similar to the `delay` input to `do_ctlc()` below, setting
-    # this too low can cause the test to fail since the `subactor`
-    # suffers a race where the root/parent sends an actor-cancel
-    # prior to the context task hitting its pause point (and thus
-    # engaging the `sigint_shield()` handler in time); this value
-    # seems be good enuf?
-    time.sleep(0.6)
-
-    # one of the bg thread or subactor should have
-    # `Lock.acquire()`-ed
-    # (NOT both, which will result in REPL clobbering!)
-    attach_patts: dict[str, list[str]] = {
-        'subactor': [
-            "'start_n_sync_pause'",
-            "('subactor'",
-        ],
-        'inline_root_bg_thread': [
-            "<Thread(inline_root_bg_thread",
-            "('root'",
-        ],
-        'start_soon_root_bg_thread': [
-            "<Thread(start_soon_root_bg_thread",
-            "('root'",
-        ],
-    }
-    conts: int = 0  # for debugging below matching logic on failure
-    while attach_patts:
-        child.sendline('c')
-        conts += 1
-        child.expect(PROMPT)
-        before = str(child.before.decode())
-        for key in attach_patts:
-            if key in before:
-                attach_key: str = key
-                expected_patts: str = attach_patts.pop(key)
-                assert_before(
-                    child,
-                    [_pause_msg]
-                    +
-                    expected_patts
-                )
-                break
-        else:
-            pytest.fail(
-                f'No keys found?\n\n'
-                f'{attach_patts.keys()}\n\n'
-                f'{before}\n'
-            )
-
-        # ensure no other task/threads engaged a REPL
-        # at the same time as the one that was detected above.
-        for key, other_patts in attach_patts.copy().items():
-            assert not in_prompt_msg(
-                child,
-                other_patts,
-            )
-
-        if ctlc:
-            do_ctlc(
-                child,
-                patt=attach_key,
-                # NOTE same as comment above
-                delay=0.4,
-            )
-
-    child.sendline('c')
-
-    # XXX TODO, weird threading bug it seems despite the
-    # `abandon_on_cancel: bool` setting to
-    # `trio.to_thread.run_sync()`..
-    with maybe_expect_timeout(
-        ctlc=ctlc,
-    ):
-        child.expect(EOF)
-
-
-def expect_any_of(
-    attach_patts: dict[str, list[str]],
-    child,   # what type?
-    ctlc: bool = False,
-    prompt: str = _ctlc_ignore_header,
-    ctlc_delay: float = .4,
-
-) -> list[str]:
-    '''
-    Receive any of a `list[str]` of patterns provided in
-    `attach_patts`.
-
-    Used to test racing prompts from multiple actors and/or
-    tasks using a common root process' `pdbp` REPL.
-
-    '''
-    assert attach_patts
-
-    child.expect(PROMPT)
-    before = str(child.before.decode())
-
-    for attach_key in attach_patts:
-        if attach_key in before:
-            expected_patts: str = attach_patts.pop(attach_key)
-            assert_before(
-                child,
-                expected_patts
-            )
-            break  # from for
-    else:
-        pytest.fail(
-            f'No keys found?\n\n'
-            f'{attach_patts.keys()}\n\n'
-            f'{before}\n'
-        )
-
-    # ensure no other task/threads engaged a REPL
-    # at the same time as the one that was detected above.
-    for key, other_patts in attach_patts.copy().items():
-        assert not in_prompt_msg(
-            child,
-            other_patts,
-        )
-
-    if ctlc:
-        do_ctlc(
-            child,
-            patt=prompt,
-            # NOTE same as comment above
-            delay=ctlc_delay,
-        )
-
-    return expected_patts
-
-
-@pytest.mark.ctlcs_bish
-def test_sync_pause_from_aio_task(
-    spawn,
-
-    ctlc: bool
-    # ^TODO, fix for `asyncio`!!
-):
-    '''
-    Verify we can use the `pdbp` REPL from an `asyncio.Task` spawned using
-    APIs in `.to_asyncio`.
-
-    `examples/debugging/asycio_bp.py`
-
-    '''
-    child = spawn('asyncio_bp')
-
-    # RACE on whether trio/asyncio task bps first
-    attach_patts: dict[str, list[str]] = {
-
-        # first pause in guest-mode (aka "infecting")
-        # `trio.Task`.
-        'trio-side': [
-            _pause_msg,
-            "<Task 'trio_ctx'",
-            "('aio_daemon'",
-        ],
-
-        # `breakpoint()` from `asyncio.Task`.
-        'asyncio-side': [
-            _pause_msg,
-            "<Task pending name='Task-2' coro=<greenback_shim()",
-            "('aio_daemon'",
-        ],
-    }
-
-    while attach_patts:
-        expect_any_of(
-            attach_patts=attach_patts,
-            child=child,
-            ctlc=ctlc,
-        )
-        child.sendline('c')
-
-    # NOW in race order,
-    # - the asyncio-task will error
-    # - the root-actor parent task will pause
-    #
-    attach_patts: dict[str, list[str]] = {
-
-        # error raised in `asyncio.Task`
-        "raise ValueError('asyncio side error!')": [
-            _crash_msg,
-            "<Task 'trio_ctx'",
-            "@ ('aio_daemon'",
-            "ValueError: asyncio side error!",
-
-            # XXX, we no longer show this frame by default!
-            # 'return await chan.receive()',  # `.to_asyncio` impl internals in tb
-        ],
-
-        # parent-side propagation via actor-nursery/portal
-        # "tractor._exceptions.RemoteActorError: remote task raised a 'ValueError'": [
-        "remote task raised a 'ValueError'": [
-            _crash_msg,
-            "src_uid=('aio_daemon'",
-            "('aio_daemon'",
-        ],
-
-        # a final pause in root-actor
-        "<Task '__main__.main'": [
-            _pause_msg,
-            "<Task '__main__.main'",
-            "('root'",
-        ],
-    }
-    while attach_patts:
-        expect_any_of(
-            attach_patts=attach_patts,
-            child=child,
-            ctlc=ctlc,
-        )
-        child.sendline('c')
-
-    assert not attach_patts
-
-    # final boxed error propagates to root
-    assert_before(
-        child,
-        [
-            _crash_msg,
-            "<Task '__main__.main'",
-            "('root'",
-            "remote task raised a 'ValueError'",
-            "ValueError: asyncio side error!",
-        ]
-    )
-
-    if ctlc:
-        do_ctlc(
-            child,
-            # NOTE: setting this to 0 (or some other sufficient
-            # small val) can cause the test to fail since the
-            # `subactor` suffers a race where the root/parent
-            # sends an actor-cancel prior to it hitting its pause
-            # point; by def the value is 0.1
-            delay=0.4,
-        )
-
-    child.sendline('c')
-    # with maybe_expect_timeout():
-    child.expect(EOF)
-
-
-def test_sync_pause_from_non_greenbacked_aio_task():
-    '''
-    Where the `breakpoint()` caller task is NOT spawned by
-    `tractor.to_asyncio` and thus never activates
-    a `greenback.ensure_portal()` beforehand, presumably bc the task
-    was started by some lib/dep as in often seen in the field.
-
-    Ensure sync pausing works when the pause is in,
-
-    - the root actor running in infected-mode?
-      |_ since we don't need any IPC to acquire the debug lock?
-      |_ is there some way to handle this like the non-main-thread case?
-
-    All other cases need to error out appropriately right?
-
-    - for any subactor we can't avoid needing the repl lock..
-      |_ is there a way to hook into `asyncio.ensure_future(obj)`?
-
-    '''
-    pass

tests/devx/test_tooling.py

@@ -1,172 +0,0 @@
-'''
-That "native" runtime-hackin toolset better be dang useful!
-
-Verify the funtion of a variety of "developer-experience" tools we
-offer from the `.devx` sub-pkg:
-
-- use of the lovely `stackscope` for dumping actor `trio`-task trees
-  during operation and hangs.
-
-TODO:
-- demonstration of `CallerInfo` call stack frame filtering such that
-  for logging and REPL purposes a user sees exactly the layers needed
-  when debugging a problem inside the stack vs. in their app.
-
-'''
-import os
-import signal
-import time
-
-from .conftest import (
-    expect,
-    assert_before,
-    in_prompt_msg,
-    PROMPT,
-    _pause_msg,
-)
-from pexpect.exceptions import (
-    # TIMEOUT,
-    EOF,
-)
-
-
-def test_shield_pause(
-    spawn,
-):
-    '''
-    Verify the `tractor.pause()/.post_mortem()` API works inside an
-    already cancelled `trio.CancelScope` and that you can step to the
-    next checkpoint wherein the cancelled will get raised.
-
-    '''
-    child = spawn(
-        'shield_hang_in_sub'
-    )
-    expect(
-        child,
-        'Yo my child hanging..?',
-    )
-    assert_before(
-        child,
-        [
-            'Entering shield sleep..',
-            'Enabling trace-trees on `SIGUSR1` since `stackscope` is installed @',
-        ]
-    )
-
-    script_pid: int = child.pid
-    print(
-        f'Sending SIGUSR1 to {script_pid}\n'
-        f'(kill -s SIGUSR1 {script_pid})\n'
-    )
-    os.kill(
-        script_pid,
-        signal.SIGUSR1,
-    )
-    time.sleep(0.2)
-    expect(
-        child,
-        # end-of-tree delimiter
-        "end-of-\('root'",
-    )
-    assert_before(
-        child,
-        [
-            # 'Srying to dump `stackscope` tree..',
-            # 'Dumping `stackscope` tree for actor',
-            "('root'",  # uid line
-
-            # TODO!? this used to show?
-            # -[ ] mk reproducable for @oremanj?
-            #
-            # parent block point (non-shielded)
-            # 'await trio.sleep_forever()  # in root',
-        ]
-    )
-    expect(
-        child,
-        # end-of-tree delimiter
-        "end-of-\('hanger'",
-    )
-    assert_before(
-        child,
-        [
-            # relay to the sub should be reported
-            'Relaying `SIGUSR1`[10] to sub-actor',
-
-            "('hanger'",  # uid line
-
-            # TODO!? SEE ABOVE
-            # hanger LOC where it's shield-halted
-            # 'await trio.sleep_forever()  # in subactor',
-        ]
-    )
-
-    # simulate the user sending a ctl-c to the hanging program.
-    # this should result in the terminator kicking in since
-    # the sub is shield blocking and can't respond to SIGINT.
-    os.kill(
-        child.pid,
-        signal.SIGINT,
-    )
-    expect(
-        child,
-        'Shutting down actor runtime',
-        timeout=6,
-    )
-    assert_before(
-        child,
-        [
-            'raise KeyboardInterrupt',
-            # 'Shutting down actor runtime',
-            '#T-800 deployed to collect zombie B0',
-            "'--uid', \"('hanger',",
-        ]
-    )
-
-
-def test_breakpoint_hook_restored(
-    spawn,
-):
-    '''
-    Ensures our actor runtime sets a custom `breakpoint()` hook
-    on open then restores the stdlib's default on close.
-
-    The hook state validation is done via `assert`s inside the
-    invoked script with only `breakpoint()` (not `tractor.pause()`)
-    calls used.
-
-    '''
-    child = spawn('restore_builtin_breakpoint')
-
-    child.expect(PROMPT)
-    assert_before(
-        child,
-        [
-            _pause_msg,
-            "<Task '__main__.main'",
-            "('root'",
-            "first bp, tractor hook set",
-        ]
-    )
-    child.sendline('c')
-    child.expect(PROMPT)
-    assert_before(
-        child,
-        [
-            "last bp, stdlib hook restored",
-        ]
-    )
-
-    # since the stdlib hook was already restored there should be NO
-    # `tractor` `log.pdb()` content from console!
-    assert not in_prompt_msg(
-        child,
-        [
-            _pause_msg,
-            "<Task '__main__.main'",
-            "('root'",
-        ],
-    )
-    child.sendline('c')
-    child.expect(EOF)

tests/test_advanced_faults.py

@@ -1,290 +0,0 @@
-'''
-Sketchy network blackoutz, ugly byzantine gens, puedes eschuchar la
-cancelacion?..
-
-'''
-from functools import partial
-from types import ModuleType
-
-import pytest
-from _pytest.pathlib import import_path
-import trio
-import tractor
-from tractor._testing import (
-    examples_dir,
-    break_ipc,
-)
-
-
-@pytest.mark.parametrize(
-    'pre_aclose_msgstream',
-    [
-        False,
-        True,
-    ],
-    ids=[
-        'no_msgstream_aclose',
-        'pre_aclose_msgstream',
-    ],
-)
-@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,
-    loglevel: str,
-    spawn_backend: str,
-    ipc_break: dict|None,
-    pre_aclose_msgstream: bool,
-):
-    '''
-    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
-        expect_final_exc = tractor.TransportClosed
-
-    mod: ModuleType = import_path(
-        examples_dir() / 'advanced_faults'
-        / 'ipc_failure_during_stream.py',
-        root=examples_dir(),
-        consider_namespace_packages=False,
-    )
-
-    # by def we expect KBI from user after a simulated "hang
-    # period" wherein the user eventually hits ctl-c to kill the
-    # root-actor tree.
-    expect_final_exc: BaseException = KeyboardInterrupt
-    if (
-        # only expect EoC if trans is broken on the child side,
-        ipc_break['break_child_ipc_after'] is not False
-        # AND we tell the child to call `MsgStream.aclose()`.
-        and pre_aclose_msgstream
-    ):
-        # expect_final_exc = trio.EndOfChannel
-        # ^XXX NOPE! XXX^ since now `.open_stream()` absorbs this
-        # gracefully!
-        expect_final_exc = KeyboardInterrupt
-
-    # NOTE when ONLY the child breaks or it breaks BEFORE the
-    # parent 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.
-    #
-    # ONLY CHILD breaks
-    if (
-        ipc_break['break_child_ipc_after']
-        and
-        ipc_break['break_parent_ipc_after'] is False
-    ):
-        # NOTE: we DO NOT expect this any more since
-        # the child side's channel will be broken silently
-        # and nothing on the parent side will indicate this!
-        # expect_final_exc = trio.ClosedResourceError
-
-        # NOTE: child will send a 'stop' msg before it breaks
-        # the transport channel BUT, that will be absorbed by the
-        # `ctx.open_stream()` block and thus the `.open_context()`
-        # should hang, after which the test script simulates
-        # a user sending ctl-c by raising a KBI.
-        if pre_aclose_msgstream:
-            expect_final_exc = KeyboardInterrupt
-
-            # XXX OLD XXX
-            # if child calls `MsgStream.aclose()` then expect EoC.
-            # ^ XXX not any more ^ since eoc is always absorbed
-            # gracefully and NOT bubbled to the `.open_context()`
-            # block!
-            # expect_final_exc = trio.EndOfChannel
-
-    # BOTH but, CHILD breaks FIRST
-    elif (
-        ipc_break['break_child_ipc_after'] is not False
-        and (
-            ipc_break['break_parent_ipc_after']
-            > ipc_break['break_child_ipc_after']
-        )
-    ):
-        if pre_aclose_msgstream:
-            expect_final_exc = KeyboardInterrupt
-
-    # NOTE when the parent IPC side dies (even if the child does as well
-    # but the child fails BEFORE the parent) we always expect the
-    # IPC layer to raise a closed-resource, NEVER do we expect
-    # a stop msg since the parent-side ctx apis will error out
-    # IMMEDIATELY before the child ever sends any 'stop' msg.
-    #
-    # ONLY PARENT breaks
-    elif (
-        ipc_break['break_parent_ipc_after']
-        and
-        ipc_break['break_child_ipc_after'] is False
-    ):
-        # expect_final_exc = trio.ClosedResourceError
-        expect_final_exc = tractor.TransportClosed
-
-    # BOTH but, PARENT breaks FIRST
-    elif (
-        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.ClosedResourceError
-        expect_final_exc = tractor.TransportClosed
-
-    with pytest.raises(
-        expected_exception=(
-            expect_final_exc,
-            ExceptionGroup,
-        ),
-    ) as excinfo:
-        try:
-            trio.run(
-                partial(
-                    mod.main,
-                    debug_mode=debug_mode,
-                    start_method=spawn_backend,
-                    loglevel=loglevel,
-                    pre_close=pre_aclose_msgstream,
-                    **ipc_break,
-                )
-            )
-        except KeyboardInterrupt as _kbi:
-            kbi = _kbi
-            if expect_final_exc is not KeyboardInterrupt:
-                pytest.fail(
-                    'Rxed unexpected KBI !?\n'
-                    f'{repr(kbi)}'
-                )
-
-            raise
-
-        except tractor.TransportClosed as _tc:
-            tc = _tc
-            if expect_final_exc is KeyboardInterrupt:
-                pytest.fail(
-                    'Unexpected transport failure !?\n'
-                    f'{repr(tc)}'
-                )
-            cause: Exception = tc.__cause__
-            assert (
-                type(cause) is trio.ClosedResourceError
-                and
-                cause.args[0] == 'another task closed this fd'
-            )
-            raise
-
-    # get raw instance from pytest wrapper
-    value = excinfo.value
-    if isinstance(value, ExceptionGroup):
-        excs = value.exceptions
-        assert len(excs) == 1
-        final_exc = excs[0]
-        assert isinstance(final_exc, expect_final_exc)
-
-
-@tractor.context
-async def break_ipc_after_started(
-    ctx: tractor.Context,
-) -> None:
-    await ctx.started()
-    async with ctx.open_stream() as stream:
-
-        # TODO: make a test which verifies the error
-        # for this, i.e. raises a `MsgTypeError`
-        # await ctx.chan.send(None)
-
-        await break_ipc(
-            stream=stream,
-            pre_close=True,
-        )
-        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():
-        with trio.fail_after(3):
-            async with tractor.open_nursery() as an:
-                portal = await an.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\n'
-                    'parent raising KBI..\n'
-                )
-                raise KeyboardInterrupt
-
-    with pytest.raises(KeyboardInterrupt):
-        trio.run(main)

tests/test_advanced_streaming.py

@@ -5,8 +5,8 @@ Advanced streaming patterns using bidirectional streams and contexts.
 from collections import Counter
 import itertools
 import platform
+from typing import Set, Dict, List
 
-import pytest
 import trio
 import tractor
 
@@ -15,7 +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(),
 }
@@ -77,7 +77,7 @@ async def subscribe(
 
 async def consumer(
 
-    subs: list[str],
+    subs: List[str],
 
 ) -> None:
 
@@ -144,16 +144,8 @@ def test_dynamic_pub_sub():
 
     try:
         trio.run(main)
-    except (
-        trio.TooSlowError,
-        ExceptionGroup,
-    ) as err:
-        if isinstance(err, ExceptionGroup):
-            for suberr in err.exceptions:
-                if isinstance(suberr, trio.TooSlowError):
-                    break
-            else:
-                pytest.fail('Never got a `TooSlowError` ?')
+    except trio.TooSlowError:
+        pass
 
 
 @tractor.context
@@ -307,77 +299,44 @@ async def inf_streamer(
 
     async with (
         ctx.open_stream() as stream,
-
-        # XXX TODO, INTERESTING CASE!!
-        # - if we don't collapse the eg then the embedded
-        # `trio.EndOfChannel` doesn't propagate directly to the above
-        # .open_stream() parent, resulting in it also raising instead
-        # of gracefully absorbing as normal.. so how to handle?
-        trio.open_nursery(
-            strict_exception_groups=False,
-        ) as tn,
+        trio.open_nursery() as n,
     ):
-        async def close_stream_on_sentinel():
+        async def bail_on_sentinel():
             async for msg in stream:
                 if msg == 'done':
-                    print(
-                        'streamer RXed "done" sentinel msg!\n'
-                        'CLOSING `MsgStream`!'
-                    )
                     await stream.aclose()
                 else:
                     print(f'streamer received {msg}')
-            else:
-                print('streamer exited recv loop')
 
         # start termination detector
-        tn.start_soon(close_stream_on_sentinel)
+        n.start_soon(bail_on_sentinel)
 
-        cap: int = 10000  # so that we don't spin forever when bug..
-        for val in range(cap):
+        for val in itertools.count():
             try:
-                print(f'streamer sending {val}')
                 await stream.send(val)
-                if val > cap:
-                    raise RuntimeError(
-                        'Streamer never cancelled by setinel?'
-                    )
-                await trio.sleep(0.001)
-
-            # close out the stream gracefully
             except trio.ClosedResourceError:
-                print('transport closed on streamer side!')
-                assert stream.closed
+                # close out the stream gracefully
                 break
-        else:
-            raise RuntimeError(
-                'Streamer not cancelled before finished sending?'
-            )
 
-    print('streamer exited .open_streamer() block')
+    print('terminating streamer')
 
 
-def test_local_task_fanout_from_stream(
-    debug_mode: bool,
-):
+def test_local_task_fanout_from_stream():
     '''
     Single stream with multiple local consumer tasks using the
     ``MsgStream.subscribe()` api.
 
-    Ensure all tasks receive all values after stream completes
-    sending.
+    Ensure all tasks receive all values after stream completes sending.
 
     '''
-    consumers: int = 22
+    consumers = 22
 
     async def main():
 
         counts = Counter()
 
-        async with tractor.open_nursery(
-            debug_mode=debug_mode,
-        ) as tn:
-            p: tractor.Portal = await tn.start_actor(
+        async with tractor.open_nursery() as tn:
+            p = await tn.start_actor(
                 'inf_streamer',
                 enable_modules=[__name__],
             )
@@ -385,6 +344,7 @@ def test_local_task_fanout_from_stream(
                 p.open_context(inf_streamer) as (ctx, _),
                 ctx.open_stream() as stream,
             ):
+
                 async def pull_and_count(name: str):
                     # name = trio.lowlevel.current_task().name
                     async with stream.subscribe() as recver:
@@ -393,7 +353,7 @@ def test_local_task_fanout_from_stream(
                             tractor.trionics.BroadcastReceiver
                         )
                         async for val in recver:
-                            print(f'bx {name} rx: {val}')
+                            # print(f'{name}: {val}')
                             counts[name] += 1
 
                         print(f'{name} bcaster ended')
@@ -403,14 +363,10 @@ def test_local_task_fanout_from_stream(
                 with trio.fail_after(3):
                     async with trio.open_nursery() as nurse:
                         for i in range(consumers):
-                            nurse.start_soon(
-                                pull_and_count,
-                                i,
-                            )
+                            nurse.start_soon(pull_and_count, i)
 
-                        # delay to let bcast consumers pull msgs
                         await trio.sleep(0.5)
-                        print('terminating nursery of bcast rxer consumers!')
+                        print('\nterminating')
                         await stream.send('done')
 
             print('closed stream connection')

tests/test_cancellation.py

@@ -11,10 +11,8 @@ from itertools import repeat
 import pytest
 import trio
 import tractor
-from tractor._testing import (
-    tractor_test,
-)
-from .conftest import no_windows
+
+from conftest import tractor_test, no_windows
 
 
 def is_win():
@@ -45,82 +43,45 @@ async def do_nuthin():
     ],
     ids=['no_args', 'unexpected_args'],
 )
-def test_remote_error(reg_addr, args_err):
-    '''
-    Verify an error raised in a subactor that is propagated
+def test_remote_error(arb_addr, args_err):
+    """Verify an error raised in a subactor that is propagated
     to the parent nursery, contains the underlying boxed builtin
     error type info and causes cancellation and reraising all the
     way up the stack.
-
-    '''
+    """
     args, errtype = args_err
 
     async def main():
         async with tractor.open_nursery(
-            registry_addrs=[reg_addr],
+            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
+                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.boxed_type == errtype
+                assert err.type == errtype
                 print("Look Maa that actor failed hard, hehh")
                 raise
 
-    # ensure boxed errors
-    if args:
-        with pytest.raises(tractor.RemoteActorError) as excinfo:
-            trio.run(main)
+    with pytest.raises(tractor.RemoteActorError) as excinfo:
+        trio.run(main)
 
-        assert excinfo.value.boxed_type == errtype
-
-    else:
-        # the root task will also error on the `Portal.result()`
-        # call so we expect an error from there AND the child.
-        # |_ tho seems like on new `trio` this doesn't always
-        #    happen?
-        with pytest.raises((
-            BaseExceptionGroup,
-            tractor.RemoteActorError,
-        )) as excinfo:
-            trio.run(main)
-
-        # ensure boxed errors are `errtype`
-        err: BaseException = excinfo.value
-        if isinstance(err, BaseExceptionGroup):
-            suberrs: list[BaseException] = err.exceptions
-        else:
-            suberrs: list[BaseException] = [err]
-
-        for exc in suberrs:
-            assert exc.boxed_type == errtype
+    # ensure boxed error is correct
+    assert excinfo.value.type == errtype
 
 
-def test_multierror(
-    reg_addr: tuple[str, int],
-):
-    '''
-    Verify we raise a ``BaseExceptionGroup`` out of a nursery where
+def test_multierror(arb_addr):
+    """Verify we raise a ``trio.MultiError`` out of a nursery where
     more then one actor errors.
-
-    '''
+    """
     async def main():
         async with tractor.open_nursery(
-            registry_addrs=[reg_addr],
+            arbiter_addr=arb_addr,
         ) as nursery:
 
             await nursery.run_in_actor(assert_err, name='errorer1')
@@ -130,14 +91,14 @@ def test_multierror(
             try:
                 await portal2.result()
             except tractor.RemoteActorError as err:
-                assert err.boxed_type is AssertionError
+                assert err.type == AssertionError
                 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)
 
 
@@ -145,14 +106,14 @@ def test_multierror(
 @pytest.mark.parametrize(
     'num_subactors', range(25, 26),
 )
-def test_multierror_fast_nursery(reg_addr, start_method, num_subactors, delay):
-    """Verify we raise a ``BaseExceptionGroup`` out of a nursery where
+def test_multierror_fast_nursery(arb_addr, start_method, num_subactors, delay):
+    """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.
     """
     async def main():
         async with tractor.open_nursery(
-            registry_addrs=[reg_addr],
+            arbiter_addr=arb_addr,
         ) as nursery:
 
             for i in range(num_subactors):
@@ -162,11 +123,10 @@ def test_multierror_fast_nursery(reg_addr, start_method, num_subactors, delay):
                     delay=delay
                 )
 
-    # with pytest.raises(trio.MultiError) as exc_info:
-    with pytest.raises(BaseExceptionGroup) as exc_info:
+    with pytest.raises(trio.MultiError) as exc_info:
         trio.run(main)
 
-    assert exc_info.type == ExceptionGroup
+    assert exc_info.type == tractor.MultiError
     err = exc_info.value
     exceptions = err.exceptions
 
@@ -182,7 +142,7 @@ def test_multierror_fast_nursery(reg_addr, start_method, num_subactors, delay):
 
     for exc in exceptions:
         assert isinstance(exc, tractor.RemoteActorError)
-        assert exc.boxed_type is AssertionError
+        assert exc.type == AssertionError
 
 
 async def do_nothing():
@@ -190,20 +150,15 @@ async def do_nothing():
 
 
 @pytest.mark.parametrize('mechanism', ['nursery_cancel', KeyboardInterrupt])
-def test_cancel_single_subactor(reg_addr, mechanism):
-    '''
-    Ensure a ``ActorNursery.start_actor()`` spawned subactor
+def test_cancel_single_subactor(arb_addr, mechanism):
+    """Ensure a ``ActorNursery.start_actor()`` spawned subactor
     cancels when the nursery is cancelled.
-
-    '''
+    """
     async def spawn_actor():
-        '''
-        Spawn an actor that blocks indefinitely then cancel via
-        either `ActorNursery.cancel()` or an exception raise.
-
-        '''
+        """Spawn an actor that blocks indefinitely.
+        """
         async with tractor.open_nursery(
-            registry_addrs=[reg_addr],
+            arbiter_addr=arb_addr,
         ) as nursery:
 
             portal = await nursery.start_actor(
@@ -259,8 +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),
-        (3, BaseExceptionGroup, AssertionError, (assert_err, {}), None),
+        (2, tractor.MultiError, 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, {}),
@@ -271,7 +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=[
@@ -323,7 +278,7 @@ async def test_some_cancels_all(num_actors_and_errs, start_method, loglevel):
                         await portal.run(func, **kwargs)
 
                     except tractor.RemoteActorError as err:
-                        assert err.boxed_type == err_type
+                        assert err.type == err_type
                         # we only expect this first error to propogate
                         # (all other daemons are cancelled before they
                         # can be scheduled)
@@ -338,15 +293,15 @@ 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):
-                    assert exc.boxed_type == err_type
+                    assert exc.type == err_type
                 else:
                     assert isinstance(exc, trio.Cancelled)
         elif isinstance(err, tractor.RemoteActorError):
-            assert err.boxed_type == err_type
+            assert err.type == err_type
 
         assert n.cancelled is True
         assert not n._children
@@ -382,7 +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.
 
@@ -410,7 +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:
 
@@ -425,21 +380,21 @@ async def test_nested_multierrors(loglevel, start_method):
                     elif isinstance(subexc, tractor.RemoteActorError):
                         # on windows it seems we can't exactly be sure wtf
                         # will happen..
-                        assert subexc.boxed_type in (
+                        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,):
-                                subsub = subsub.boxed_type
+                                subsub = subsub.type
 
                             assert type(subsub) in (
                                 trio.Cancelled,
-                                BaseExceptionGroup,
+                                trio.MultiError,
                             )
                 else:
                     assert isinstance(subexc, tractor.RemoteActorError)
@@ -450,16 +405,16 @@ async def test_nested_multierrors(loglevel, start_method):
                     # we get back the (sent) cancel signal instead
                     if is_win():
                         if isinstance(subexc, tractor.RemoteActorError):
-                            assert subexc.boxed_type in (
-                                BaseExceptionGroup,
+                            assert subexc.type in (
+                                trio.MultiError,
                                 tractor.RemoteActorError
                             )
                         else:
-                            assert isinstance(subexc, BaseExceptionGroup)
+                            assert isinstance(subexc, trio.MultiError)
                     else:
-                        assert subexc.boxed_type is ExceptionGroup
+                        assert subexc.type is trio.MultiError
                 else:
-                    assert subexc.boxed_type in (
+                    assert subexc.type in (
                         tractor.RemoteActorError,
                         trio.Cancelled
                     )
@@ -480,7 +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()
@@ -504,9 +459,7 @@ def test_cancel_via_SIGINT_other_task(
     if is_win():  # smh
         timeout += 1
 
-    async def spawn_and_sleep_forever(
-        task_status=trio.TASK_STATUS_IGNORED
-    ):
+    async def spawn_and_sleep_forever(task_status=trio.TASK_STATUS_IGNORED):
         async with tractor.open_nursery() as tn:
             for i in range(3):
                 await tn.run_in_actor(
@@ -519,11 +472,9 @@ def test_cancel_via_SIGINT_other_task(
     async def main():
         # should never timeout since SIGINT should cancel the current program
         with trio.fail_after(timeout):
-            async with trio.open_nursery(
-                strict_exception_groups=False,
-            ) as n:
+            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)
 
@@ -614,12 +565,6 @@ def test_fast_graceful_cancel_when_spawn_task_in_soft_proc_wait_for_daemon(
                     nurse.start_soon(delayed_kbi)
 
                     await p.run(do_nuthin)
-
-        # need to explicitly re-raise the lone kbi..now
-        except* KeyboardInterrupt as kbi_eg:
-            assert (len(excs := kbi_eg.exceptions) == 1)
-            raise excs[0]
-
         finally:
             duration = time.time() - start
             if duration > timeout:

tests/test_child_manages_service_nursery.py

@@ -6,15 +6,14 @@ sub-sub-actor daemons.
 '''
 from typing import Optional
 import asyncio
-from contextlib import (
-    asynccontextmanager as acm,
-    aclosing,
-)
+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(
@@ -95,8 +94,8 @@ async def trio_main(
 
     # stash a "service nursery" as "actor local" (aka a Python global)
     global _nursery
-    tn = _nursery
-    assert tn
+    n = _nursery
+    assert n
 
     async def consume_stream():
         async with wrapper_mngr() as stream:
@@ -104,10 +103,10 @@ async def trio_main(
                 print(msg)
 
     # run 2 tasks to ensure broadcaster chan use
-    tn.start_soon(consume_stream)
-    tn.start_soon(consume_stream)
+    n.start_soon(consume_stream)
+    n.start_soon(consume_stream)
 
-    tn.start_soon(trio_sleep_and_err)
+    n.start_soon(trio_sleep_and_err)
 
     await trio.sleep_forever()
 
@@ -117,10 +116,8 @@ async def open_actor_local_nursery(
     ctx: tractor.Context,
 ):
     global _nursery
-    async with trio.open_nursery(
-        strict_exception_groups=False,
-    ) as tn:
-        _nursery = tn
+    async with trio.open_nursery() as n:
+        _nursery = n
         await ctx.started()
         await trio.sleep(10)
         # await trio.sleep(1)
@@ -134,7 +131,7 @@ async def open_actor_local_nursery(
         # never yields back.. aka a scenario where the
         # ``tractor.context`` task IS NOT in the service n's cancel
         # scope.
-        tn.cancel_scope.cancel()
+        n.cancel_scope.cancel()
 
 
 @pytest.mark.parametrize(
@@ -144,7 +141,7 @@ async def open_actor_local_nursery(
 )
 def test_actor_managed_trio_nursery_task_error_cancels_aio(
     asyncio_mode: bool,
-    reg_addr: tuple,
+    arb_addr
 ):
     '''
     Verify that a ``trio`` nursery created managed in a child actor
@@ -159,7 +156,7 @@ def test_actor_managed_trio_nursery_task_error_cancels_aio(
         async with tractor.open_nursery() as n:
             p = await n.start_actor(
                 'nursery_mngr',
-                infect_asyncio=asyncio_mode,  # TODO, is this enabling debug mode?
+                infect_asyncio=asyncio_mode,
                 enable_modules=[__name__],
             )
             async with (
@@ -173,4 +170,4 @@ def test_actor_managed_trio_nursery_task_error_cancels_aio(
 
     # verify boxed error
     err = excinfo.value
-    assert err.boxed_type is NameError
+    assert isinstance(err.type(), NameError)

tests/test_clustering.py

@@ -1,81 +1,36 @@
 import itertools
 
-import pytest
 import trio
 import tractor
 from tractor import open_actor_cluster
 from tractor.trionics import gather_contexts
-from tractor._testing import tractor_test
+
+from conftest import tractor_test
+
 
 MESSAGE = 'tractoring at full speed'
 
 
-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(
-    ctx: tractor.Context,
-
-) -> None:
-
+async def worker(ctx: tractor.Context) -> None:
     await ctx.started()
-
-    async with ctx.open_stream(
-        allow_overruns=True,
-    ) as stream:
-
-        # TODO: this with the below assert causes a hang bug?
-        # with trio.move_on_after(1):
-
+    async with ctx.open_stream(backpressure=True) as stream:
         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_debugger.py

@@ -0,0 +1,598 @@
+"""
+That native debug better work!
+
+All these tests can be understood (somewhat) by running the equivalent
+`examples/debugging/` scripts manually.
+
+TODO:
+    - none of these tests have been run successfully on windows yet but
+      there's been manual testing that verified it works.
+    - wonder if any of it'll work on OS X?
+
+"""
+import time
+from os import path
+import platform
+
+import pytest
+import pexpect
+
+from conftest import repodir
+
+
+# TODO: The next great debugger audit could be done by you!
+# - recurrent entry to breakpoint() from single actor *after* and an
+#   error in another task?
+# - root error before child errors
+# - root error after child errors
+# - root error before child breakpoint
+# - root error after child breakpoint
+# - recurrent root errors
+
+
+if platform.system() == 'Windows':
+    pytest.skip(
+        'Debugger tests have no windows support (yet)',
+        allow_module_level=True,
+    )
+
+
+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()``.
+    """
+    return ' '.join(
+        ['python',
+         path.join(examples_dir(), f'{ex_name}.py')]
+    )
+
+
+@pytest.fixture
+def spawn(
+    start_method,
+    testdir,
+    arb_addr,
+) -> 'pexpect.spawn':
+
+    if start_method != 'trio':
+        pytest.skip(
+            "Debugger tests are only supported on the trio backend"
+        )
+
+    def _spawn(cmd):
+        return testdir.spawn(
+            cmd=mk_cmd(cmd),
+            expect_timeout=3,
+        )
+
+    return _spawn
+
+
+@pytest.mark.parametrize(
+    'user_in_out',
+    [
+        ('c', 'AssertionError'),
+        ('q', 'AssertionError'),
+    ],
+    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.
+    """
+    user_input, expect_err_str = user_in_out
+
+    child = spawn('root_actor_error')
+
+    # scan for the pdbpp prompt
+    child.expect(r"\(Pdb\+\+\)")
+
+    before = str(child.before.decode())
+
+    # make sure expected logging and error arrives
+    assert "Attaching to pdb in crashed actor: ('root'" in before
+    assert 'AssertionError' in before
+
+    # send user command
+    child.sendline(user_input)
+
+    # process should exit
+    child.expect(pexpect.EOF)
+    assert expect_err_str in str(child.before)
+
+
+@pytest.mark.parametrize(
+    'user_in_out',
+    [
+        ('c', None),
+        ('q', 'bdb.BdbQuit'),
+    ],
+    ids=lambda item: f'{item[0]} -> {item[1]}',
+)
+def test_root_actor_bp(spawn, user_in_out):
+    """Demonstrate breakpoint from in root actor.
+    """
+    user_input, expect_err_str = user_in_out
+    child = spawn('root_actor_breakpoint')
+
+    # scan for the pdbpp prompt
+    child.expect(r"\(Pdb\+\+\)")
+
+    assert 'Error' not in str(child.before)
+
+    # send user command
+    child.sendline(user_input)
+    child.expect('\r\n')
+
+    # process should exit
+    child.expect(pexpect.EOF)
+
+    if expect_err_str is None:
+        assert 'Error' not in str(child.before)
+    else:
+        assert expect_err_str in str(child.before)
+
+
+def test_root_actor_bp_forever(spawn):
+    "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.sendline('next')
+        child.expect(r"\(Pdb\+\+\)")
+
+    # do one continue which should trigger a new task to lock the tty
+    child.sendline('continue')
+    child.expect(r"\(Pdb\+\+\)")
+
+    # XXX: this previously caused a bug!
+    child.sendline('n')
+    child.expect(r"\(Pdb\+\+\)")
+
+    child.sendline('n')
+    child.expect(r"\(Pdb\+\+\)")
+
+
+def test_subactor_error(spawn):
+    "Single subactor raising an error"
+
+    child = spawn('subactor_error')
+
+    # scan for the pdbpp prompt
+    child.expect(r"\(Pdb\+\+\)")
+
+    before = str(child.before.decode())
+    assert "Attaching to pdb in crashed actor: ('name_error'" in before
+
+    # send user command
+    # (in this case it's the same for 'continue' vs. 'quit')
+    child.sendline('continue')
+
+    # the debugger should enter a second time in the nursery
+    # creating actor
+
+    child.expect(r"\(Pdb\+\+\)")
+
+    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
+
+    child.sendline('c')
+    child.expect('\r\n')
+
+    # process should exit
+    child.expect(pexpect.EOF)
+
+
+def test_subactor_breakpoint(spawn):
+    "Single subactor with an infinite breakpoint loop"
+
+    child = spawn('subactor_breakpoint')
+
+    # scan for the pdbpp prompt
+    child.expect(r"\(Pdb\+\+\)")
+
+    before = str(child.before.decode())
+    assert "Attaching pdb to actor: ('breakpoint_forever'" in before
+
+    # do some "next" commands to demonstrate recurrent breakpoint
+    # entries
+    for _ in range(10):
+        child.sendline('next')
+        child.expect(r"\(Pdb\+\+\)")
+
+    # now run some "continues" to show re-entries
+    for _ in range(5):
+        child.sendline('continue')
+        child.expect(r"\(Pdb\+\+\)")
+        before = str(child.before.decode())
+        assert "Attaching pdb to actor: ('breakpoint_forever'" in before
+
+    # finally quit the loop
+    child.sendline('q')
+
+    # child process should exit but parent will capture pdb.BdbQuit
+    child.expect(r"\(Pdb\+\+\)")
+
+    before = str(child.before.decode())
+    assert "RemoteActorError: ('breakpoint_forever'" in before
+    assert 'bdb.BdbQuit' in before
+
+    # quit the parent
+    child.sendline('c')
+
+    # process should exit
+    child.expect(pexpect.EOF)
+
+    before = str(child.before.decode())
+    assert "RemoteActorError: ('breakpoint_forever'" in before
+    assert 'bdb.BdbQuit' in before
+
+
+def test_multi_subactors(spawn):
+    """
+    Multiple subactors, both erroring and breakpointing as well as
+    a nested subactor erroring.
+    """
+    child = spawn(r'multi_subactors')
+
+    # scan for the pdbpp prompt
+    child.expect(r"\(Pdb\+\+\)")
+
+    before = str(child.before.decode())
+    assert "Attaching pdb to actor: ('breakpoint_forever'" in before
+
+    # do some "next" commands to demonstrate recurrent breakpoint
+    # entries
+    for _ in range(10):
+        child.sendline('next')
+        child.expect(r"\(Pdb\+\+\)")
+
+    # continue to next error
+    child.sendline('c')
+
+    # first name_error failure
+    child.expect(r"\(Pdb\+\+\)")
+    before = str(child.before.decode())
+    assert "Attaching to pdb in crashed actor: ('name_error'" in before
+    assert "NameError" in before
+
+    # continue again
+    child.sendline('c')
+
+    # 2nd name_error failure
+    child.expect(r"\(Pdb\+\+\)")
+    before = str(child.before.decode())
+    assert "Attaching to pdb in crashed actor: ('name_error_1'" in before
+    assert "NameError" in before
+
+    # breakpoint loop should re-engage
+    child.sendline('c')
+    child.expect(r"\(Pdb\+\+\)")
+    before = str(child.before.decode())
+    assert "Attaching pdb to actor: ('breakpoint_forever'" in before
+
+    # wait for spawn error to show up
+    spawn_err = "Attaching to pdb in crashed actor: ('spawn_error'"
+    while spawn_err not in before:
+        child.sendline('c')
+        time.sleep(0.1)
+        child.expect(r"\(Pdb\+\+\)")
+        before = str(child.before.decode())
+
+    # 2nd depth nursery should trigger
+    # child.sendline('c')
+    # child.expect(r"\(Pdb\+\+\)")
+    # before = str(child.before.decode())
+    assert spawn_err in before
+    assert "RemoteActorError: ('name_error_1'" in before
+
+    # now run some "continues" to show re-entries
+    for _ in range(5):
+        child.sendline('c')
+        child.expect(r"\(Pdb\+\+\)")
+
+    # quit the loop and expect parent to attach
+    child.sendline('q')
+    child.expect(r"\(Pdb\+\+\)")
+    before = str(child.before.decode())
+    # debugger attaches to root
+    assert "Attaching to pdb in crashed actor: ('root'" in before
+    # expect a multierror with exceptions for each sub-actor
+    assert "RemoteActorError: ('breakpoint_forever'" in before
+    assert "RemoteActorError: ('name_error'" in before
+    assert "RemoteActorError: ('spawn_error'" in before
+    assert "RemoteActorError: ('name_error_1'" in before
+    assert 'bdb.BdbQuit' in before
+
+    # process should exit
+    child.sendline('c')
+    child.expect(pexpect.EOF)
+    # repeat of previous multierror for final output
+    before = str(child.before.decode())
+    assert "RemoteActorError: ('breakpoint_forever'" in before
+    assert "RemoteActorError: ('name_error'" in before
+    assert "RemoteActorError: ('spawn_error'" in before
+    assert "RemoteActorError: ('name_error_1'" in before
+    assert 'bdb.BdbQuit' in before
+
+
+def test_multi_daemon_subactors(spawn, loglevel):
+    """Multiple daemon subactors, both erroring and breakpointing within a
+    stream.
+    """
+    child = spawn('multi_daemon_subactors')
+
+    child.expect(r"\(Pdb\+\+\)")
+
+    # there is a race for which subactor will acquire
+    # the root's tty lock first
+
+    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
+
+    elif name_error_msg in before:
+        next_msg = bp_forever_msg
+
+    else:
+        raise ValueError("Neither log msg was found !?")
+
+    # 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
+    # unlikely that `bp_forever` would re-acquire the tty lock again.
+    # Now, we should have a final resumption in the root plus a possible
+    # second entry by `bp_forever`.
+
+    child.sendline('c')
+    child.expect(r"\(Pdb\+\+\)")
+    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.
+
+    # 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._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
+    # the root announcing it avoided a clobber of the child's lock, but
+    # it seems unreliable in testing here to gnab it:
+    # assert "in use by child ('bp_forever'," in before
+
+    # wait for final error in root
+    while True:
+
+        child.sendline('c')
+        child.expect(r"\(Pdb\+\+\)")
+        before = str(child.before.decode())
+        try:
+
+            # root error should be packed as remote error
+            assert "_exceptions.RemoteActorError: ('name_error'" in before
+            break
+
+        except AssertionError:
+            assert bp_forever_msg in before
+
+    try:
+        child.sendline('c')
+        child.expect(pexpect.EOF)
+
+    except pexpect.exceptions.TIMEOUT:
+        # Failed to exit using continue..?
+        child.sendline('q')
+        child.expect(pexpect.EOF)
+
+
+def test_multi_subactors_root_errors(spawn):
+    '''
+    Multiple subactors, both erroring and breakpointing as well as
+    a nested subactor erroring.
+
+    '''
+    child = spawn('multi_subactor_root_errors')
+
+    # scan for the pdbpp 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
+
+    # continue again to catch 2nd name error from
+    # actor 'name_error_1' (which is 2nd depth).
+    child.sendline('c')
+    child.expect(r"\(Pdb\+\+\)")
+    before = str(child.before.decode())
+    assert "Attaching to pdb in crashed actor: ('name_error_1'" in before
+    assert "NameError" in before
+
+    child.sendline('c')
+    child.expect(r"\(Pdb\+\+\)")
+    before = str(child.before.decode())
+    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
+
+    child.sendline('c')
+    child.expect(r"\(Pdb\+\+\)")
+    before = str(child.before.decode())
+    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
+
+    # warnings assert we probably don't need
+    # assert "Cancelling nursery in ('spawn_error'," in before
+
+    # continue again
+    child.sendline('c')
+    child.expect(pexpect.EOF)
+
+    before = str(child.before.decode())
+    # error from root actor and root task that created top level nursery
+    assert "AssertionError" in before
+
+
+def test_multi_nested_subactors_error_through_nurseries(spawn):
+    """Verify deeply nested actors that error trigger debugger entries
+    at each actor nurserly (level) all the way up the tree.
+
+    """
+    # NOTE: previously, inside this script was a bug where if the
+    # parent errors before a 2-levels-lower actor has released the lock,
+    # the parent tries to cancel it but it's stuck in the debugger?
+    # A test (below) has now been added to explicitly verify this is
+    # fixed.
+
+    child = spawn('multi_nested_subactors_error_up_through_nurseries')
+
+    timed_out_early: bool = False
+
+    for i in range(12):
+        try:
+            child.expect(r"\(Pdb\+\+\)")
+            child.sendline('c')
+            time.sleep(0.1)
+
+        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)
+
+    if not timed_out_early:
+        before = str(child.before.decode())
+        assert "NameError" in before
+
+
+def test_root_nursery_cancels_before_child_releases_tty_lock(
+    spawn,
+    start_method
+):
+    """Test that when the root sends a cancel message before a nested
+    child has unblocked (which can happen when it has the tty lock and
+    is 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(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)
+
+    child.sendline('c')
+
+    for i in range(4):
+        time.sleep(0.5)
+        try:
+            child.expect(r"\(Pdb\+\+\)")
+
+        except (
+            pexpect.exceptions.EOF,
+            pexpect.exceptions.TIMEOUT,
+        ):
+            # races all over..
+
+            print(f"Failed early on {i}?")
+            before = str(child.before.decode())
+
+            timed_out_early = True
+
+            # race conditions on how fast the continue is sent?
+            break
+
+        before = str(child.before.decode())
+        assert "NameError: name 'doggypants' is not defined" in before
+
+        child.sendline('c')
+
+    while True:
+        try:
+            child.expect(pexpect.EOF)
+            break
+        except pexpect.exceptions.TIMEOUT:
+            child.sendline('c')
+            print('child was able to grab tty lock again?')
+
+    if not timed_out_early:
+
+        before = str(child.before.decode())
+        assert "tractor._exceptions.RemoteActorError: ('spawner0'" in before
+        assert "tractor._exceptions.RemoteActorError: ('name_error'" in before
+        assert "NameError: name 'doggypants' is not defined" in before
+
+
+def test_root_cancels_child_context_during_startup(
+    spawn,
+):
+    '''Verify a fast fail in the root doesn't lock up the child reaping
+    and all while using the new context api.
+
+    '''
+    child = spawn('fast_error_in_root_after_spawn')
+
+    child.expect(r"\(Pdb\+\+\)")
+
+    before = str(child.before.decode())
+    assert "AssertionError" in before
+
+    child.sendline('c')
+    child.expect(pexpect.EOF)
+
+
+def test_different_debug_mode_per_actor(
+    spawn,
+):
+    child = spawn('per_actor_debug')
+    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
+
+    child.sendline('c')
+    child.expect(pexpect.EOF)
+
+    before = str(child.before.decode())
+
+    # NOTE: this debugged actor error currently WON'T show up since the
+    # root will actually cancel and terminate the nursery before the error
+    # msg reported back from the debug mode actor is processed.
+    # assert "tractor._exceptions.RemoteActorError: ('debugged_boi'" in before
+
+    assert "tractor._exceptions.RemoteActorError: ('crash_boi'" in before
+
+    # the crash boi should not have made a debugger request but
+    # instead crashed completely
+    assert "tractor._exceptions.RemoteActorError: ('crash_boi'" in before
+    assert "RuntimeError" in before

tests/test_discovery.py

@@ -9,24 +9,25 @@ import itertools
 
 import pytest
 import tractor
-from tractor._testing import tractor_test
 import trio
 
+from conftest import tractor_test
+
 
 @tractor_test
-async def test_reg_then_unreg(reg_addr):
+async def test_reg_then_unreg(arb_addr):
     actor = tractor.current_actor()
     assert actor.is_arbiter
     assert len(actor._registry) == 1  # only self is registered
 
     async with tractor.open_nursery(
-        registry_addrs=[reg_addr],
+        arbiter_addr=arb_addr,
     ) as n:
 
         portal = await n.start_actor('actor', enable_modules=[__name__])
         uid = portal.channel.uid
 
-        async with tractor.get_registry(*reg_addr) as aportal:
+        async with tractor.get_arbiter(*arb_addr) as aportal:
             # this local actor should be the arbiter
             assert actor is aportal.actor
 
@@ -52,27 +53,15 @@ async def hi():
     return the_line.format(tractor.current_actor().name)
 
 
-async def say_hello(
-    other_actor: str,
-    reg_addr: tuple[str, int],
-):
+async def say_hello(other_actor):
     await trio.sleep(1)  # wait for other actor to spawn
-    async with tractor.find_actor(
-        other_actor,
-        registry_addrs=[reg_addr],
-    ) as portal:
+    async with tractor.find_actor(other_actor) as portal:
         assert portal is not None
         return await portal.run(__name__, 'hi')
 
 
-async def say_hello_use_wait(
-    other_actor: str,
-    reg_addr: tuple[str, int],
-):
-    async with tractor.wait_for_actor(
-        other_actor,
-        registry_addr=reg_addr,
-    ) as portal:
+async def say_hello_use_wait(other_actor):
+    async with tractor.wait_for_actor(other_actor) as portal:
         assert portal is not None
         result = await portal.run(__name__, 'hi')
         return result
@@ -80,29 +69,21 @@ async def say_hello_use_wait(
 
 @tractor_test
 @pytest.mark.parametrize('func', [say_hello, say_hello_use_wait])
-async def test_trynamic_trio(
-    func,
-    start_method,
-    reg_addr,
-):
-    '''
-    Root actor acting as the "director" and running one-shot-task-actors
-    for the directed subs.
-
-    '''
+async def test_trynamic_trio(func, start_method, arb_addr):
+    """Main tractor entry point, the "master" process (for now
+    acts as the "director").
+    """
     async with tractor.open_nursery() as n:
         print("Alright... Action!")
 
         donny = await n.run_in_actor(
             func,
             other_actor='gretchen',
-            reg_addr=reg_addr,
             name='donny',
         )
         gretchen = await n.run_in_actor(
             func,
             other_actor='donny',
-            reg_addr=reg_addr,
             name='gretchen',
         )
         print(await gretchen.result())
@@ -150,7 +131,7 @@ async def unpack_reg(actor_or_portal):
 
 
 async def spawn_and_check_registry(
-    reg_addr: tuple,
+    arb_addr: tuple,
     use_signal: bool,
     remote_arbiter: bool = False,
     with_streaming: bool = False,
@@ -158,9 +139,9 @@ async def spawn_and_check_registry(
 ) -> None:
 
     async with tractor.open_root_actor(
-        registry_addrs=[reg_addr],
+        arbiter_addr=arb_addr,
     ):
-        async with tractor.get_registry(*reg_addr) as portal:
+        async with tractor.get_arbiter(*arb_addr) as portal:
             # runtime needs to be up to call this
             actor = tractor.current_actor()
 
@@ -181,9 +162,7 @@ async def spawn_and_check_registry(
 
             try:
                 async with tractor.open_nursery() as n:
-                    async with trio.open_nursery(
-                        strict_exception_groups=False,
-                    ) as trion:
+                    async with trio.open_nursery() as trion:
 
                         portals = {}
                         for i in range(3):
@@ -234,19 +213,17 @@ async def spawn_and_check_registry(
 def test_subactors_unregister_on_cancel(
     start_method,
     use_signal,
-    reg_addr,
+    arb_addr,
     with_streaming,
 ):
-    '''
-    Verify that cancelling a nursery results in all subactors
+    """Verify that cancelling a nursery results in all subactors
     deregistering themselves with the arbiter.
-
-    '''
+    """
     with pytest.raises(KeyboardInterrupt):
         trio.run(
             partial(
                 spawn_and_check_registry,
-                reg_addr,
+                arb_addr,
                 use_signal,
                 remote_arbiter=False,
                 with_streaming=with_streaming,
@@ -260,7 +237,7 @@ def test_subactors_unregister_on_cancel_remote_daemon(
     daemon,
     start_method,
     use_signal,
-    reg_addr,
+    arb_addr,
     with_streaming,
 ):
     """Verify that cancelling a nursery results in all subactors
@@ -271,7 +248,7 @@ def test_subactors_unregister_on_cancel_remote_daemon(
         trio.run(
             partial(
                 spawn_and_check_registry,
-                reg_addr,
+                arb_addr,
                 use_signal,
                 remote_arbiter=True,
                 with_streaming=with_streaming,
@@ -285,7 +262,7 @@ async def streamer(agen):
 
 
 async def close_chans_before_nursery(
-    reg_addr: tuple,
+    arb_addr: tuple,
     use_signal: bool,
     remote_arbiter: bool = False,
 ) -> None:
@@ -298,9 +275,9 @@ async def close_chans_before_nursery(
         entries_at_end = 1
 
     async with tractor.open_root_actor(
-        registry_addrs=[reg_addr],
+        arbiter_addr=arb_addr,
     ):
-        async with tractor.get_registry(*reg_addr) as aportal:
+        async with tractor.get_arbiter(*arb_addr) as aportal:
             try:
                 get_reg = partial(unpack_reg, aportal)
 
@@ -318,9 +295,7 @@ async def close_chans_before_nursery(
                         async with portal2.open_stream_from(
                             stream_forever
                         ) as agen2:
-                            async with trio.open_nursery(
-                                strict_exception_groups=False,
-                            ) as n:
+                            async with trio.open_nursery() as n:
                                 n.start_soon(streamer, agen1)
                                 n.start_soon(cancel, use_signal, .5)
                                 try:
@@ -354,7 +329,7 @@ async def close_chans_before_nursery(
 def test_close_channel_explicit(
     start_method,
     use_signal,
-    reg_addr,
+    arb_addr,
 ):
     """Verify that closing a stream explicitly and killing the actor's
     "root nursery" **before** the containing nursery tears down also
@@ -364,7 +339,7 @@ def test_close_channel_explicit(
         trio.run(
             partial(
                 close_chans_before_nursery,
-                reg_addr,
+                arb_addr,
                 use_signal,
                 remote_arbiter=False,
             ),
@@ -376,7 +351,7 @@ def test_close_channel_explicit_remote_arbiter(
     daemon,
     start_method,
     use_signal,
-    reg_addr,
+    arb_addr,
 ):
     """Verify that closing a stream explicitly and killing the actor's
     "root nursery" **before** the containing nursery tears down also
@@ -386,7 +361,7 @@ def test_close_channel_explicit_remote_arbiter(
         trio.run(
             partial(
                 close_chans_before_nursery,
-                reg_addr,
+                arb_addr,
                 use_signal,
                 remote_arbiter=True,
             ),

tests/test_docs_examples.py

@@ -11,17 +11,18 @@ import platform
 import shutil
 
 import pytest
-from tractor._testing import (
-    examples_dir,
-)
+
+from conftest import repodir
+
+
+def examples_dir():
+    """Return the abspath to the examples directory.
+    """
+    return os.path.join(repodir(), 'examples')
 
 
 @pytest.fixture
-def run_example_in_subproc(
-    loglevel: str,
-    testdir: pytest.Pytester,
-    reg_addr: tuple[str, int],
-):
+def run_example_in_subproc(loglevel, testdir, arb_addr):
 
     @contextmanager
     def run(script_code):
@@ -31,8 +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',
-                str(testdir / '__main__.py'),
+                os.path.join(examples_dir(), '__main__.py'),
+                os.path.join(str(testdir), '__main__.py')
             )
 
             # drop the ``if __name__ == '__main__'`` guard onwards from
@@ -80,37 +81,24 @@ 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]],
 
-        if (
-            '__' not in f
-            and f[0] != '_'
-            and 'debugging' not in p[0]
-            and 'integration' not in p[0]
-            and 'advanced_faults' not in p[0]
-            and 'multihost' not in p[0]
-        )
-    ],
     ids=lambda t: t[1],
 )
-def test_example(
-    run_example_in_subproc,
-    example_script,
-):
-    '''
-    Load and run scripts from this repo's ``examples/`` dir as a user
+def test_example(run_example_in_subproc, example_script):
+    """Load and run scripts from this repo's ``examples/`` dir as a user
     would copy and pasing them into their editor.
 
     On windows a little more "finessing" is done to make
     ``multiprocessing`` play nice: we copy the ``__main__.py`` into the
     test directory and invoke the script as a module with ``python -m
     test_example``.
-
-    '''
-    ex_file: str = os.path.join(*example_script)
+    """
+    ex_file = os.path.join(*example_script)
 
     if 'rpc_bidir_streaming' in ex_file and sys.version_info < (3, 9):
         pytest.skip("2-way streaming example requires py3.9 async with syntax")
@@ -125,20 +113,9 @@ def test_example(
             # print(f'STDOUT: {out}')
 
             # if we get some gnarly output let's aggregate and raise
-            if err:
-                errmsg = err.decode()
-                errlines = errmsg.splitlines()
-                last_error = errlines[-1]
-                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)
+            errmsg = err.decode()
+            errlines = errmsg.splitlines()
+            if err and 'Error' in errlines[-1]:
+                raise Exception(errmsg)
 
             assert proc.returncode == 0

tests/test_ext_types_msgspec.py

@@ -1,946 +0,0 @@
-'''
-Low-level functional audits for our
-"capability based messaging"-spec feats.
-
-B~)
-
-'''
-from contextlib import (
-    contextmanager as cm,
-    # nullcontext,
-)
-import importlib
-from typing import (
-    Any,
-    Type,
-    Union,
-)
-
-from msgspec import (
-    # structs,
-    # msgpack,
-    Raw,
-    # Struct,
-    ValidationError,
-)
-import pytest
-import trio
-
-import tractor
-from tractor import (
-    Actor,
-    # _state,
-    MsgTypeError,
-    Context,
-)
-from tractor.msg import (
-    _codec,
-    _ctxvar_MsgCodec,
-    _exts,
-
-    NamespacePath,
-    MsgCodec,
-    MsgDec,
-    mk_codec,
-    mk_dec,
-    apply_codec,
-    current_codec,
-)
-from tractor.msg.types import (
-    log,
-    Started,
-    # _payload_msgs,
-    # PayloadMsg,
-    # mk_msg_spec,
-)
-from tractor.msg._ops import (
-    limit_plds,
-)
-
-def enc_nsp(obj: Any) -> Any:
-    actor: Actor = tractor.current_actor(
-        err_on_no_runtime=False,
-    )
-    uid: tuple[str, str]|None = None if not actor else actor.uid
-    print(f'{uid} ENC HOOK')
-
-    match obj:
-        # case NamespacePath()|str():
-        case NamespacePath():
-            encoded: str = str(obj)
-            print(
-                f'----- ENCODING `NamespacePath` as `str` ------\n'
-                f'|_obj:{type(obj)!r} = {obj!r}\n'
-                f'|_encoded: str = {encoded!r}\n'
-            )
-            # if type(obj) != NamespacePath:
-            #     breakpoint()
-            return encoded
-        case _:
-            logmsg: str = (
-                f'{uid}\n'
-                'FAILED ENCODE\n'
-                f'obj-> `{obj}: {type(obj)}`\n'
-            )
-            raise NotImplementedError(logmsg)
-
-
-def dec_nsp(
-    obj_type: Type,
-    obj: Any,
-
-) -> Any:
-    # breakpoint()
-    actor: Actor = tractor.current_actor(
-        err_on_no_runtime=False,
-    )
-    uid: tuple[str, str]|None = None if not actor else actor.uid
-    print(
-        f'{uid}\n'
-        'CUSTOM DECODE\n'
-        f'type-arg-> {obj_type}\n'
-        f'obj-arg-> `{obj}`: {type(obj)}\n'
-    )
-    nsp = None
-    # XXX, never happens right?
-    if obj_type is Raw:
-        breakpoint()
-
-    if (
-        obj_type is NamespacePath
-        and isinstance(obj, str)
-        and ':' in obj
-    ):
-        nsp = NamespacePath(obj)
-        # TODO: we could built a generic handler using
-        # JUST matching the obj_type part?
-        # nsp = obj_type(obj)
-
-    if nsp:
-        print(f'Returning NSP instance: {nsp}')
-        return nsp
-
-    logmsg: str = (
-        f'{uid}\n'
-        'FAILED DECODE\n'
-        f'type-> {obj_type}\n'
-        f'obj-arg-> `{obj}`: {type(obj)}\n\n'
-        f'current codec:\n'
-        f'{current_codec()}\n'
-    )
-    # TODO: figure out the ignore subsys for this!
-    # -[ ] option whether to defense-relay backc the msg
-    #   inside an `Invalid`/`Ignore`
-    # -[ ] how to make this handling pluggable such that a
-    #   `Channel`/`MsgTransport` can intercept and process
-    #   back msgs either via exception handling or some other
-    #   signal?
-    log.warning(logmsg)
-    # NOTE: this delivers the invalid
-    # value up to `msgspec`'s decoding
-    # machinery for error raising.
-    return obj
-    # raise NotImplementedError(logmsg)
-
-
-def ex_func(*args):
-    '''
-    A mod level func we can ref and load via our `NamespacePath`
-    python-object pointer `str` subtype.
-
-    '''
-    print(f'ex_func({args})')
-
-
-@pytest.mark.parametrize(
-    'add_codec_hooks',
-    [
-        True,
-        False,
-    ],
-    ids=['use_codec_hooks', 'no_codec_hooks'],
-)
-def test_custom_extension_types(
-    debug_mode: bool,
-    add_codec_hooks: bool
-):
-    '''
-    Verify that a `MsgCodec` (used for encoding all outbound IPC msgs
-    and decoding all inbound `PayloadMsg`s) and a paired `MsgDec`
-    (used for decoding the `PayloadMsg.pld: Raw` received within a given
-    task's ipc `Context` scope) can both send and receive "extension types"
-    as supported via custom converter hooks passed to `msgspec`.
-
-    '''
-    nsp_pld_dec: MsgDec = mk_dec(
-        spec=None,  # ONLY support the ext type
-        dec_hook=dec_nsp if add_codec_hooks else None,
-        ext_types=[NamespacePath],
-    )
-    nsp_codec: MsgCodec = mk_codec(
-        # ipc_pld_spec=Raw,  # default!
-
-        # NOTE XXX: the encode hook MUST be used no matter what since
-        # our `NamespacePath` is not any of a `Any` native type nor
-        # a `msgspec.Struct` subtype - so `msgspec` has no way to know
-        # how to encode it unless we provide the custom hook.
-        #
-        # AGAIN that is, regardless of whether we spec an
-        # `Any`-decoded-pld the enc has no knowledge (by default)
-        # how to enc `NamespacePath` (nsp), so we add a custom
-        # hook to do that ALWAYS.
-        enc_hook=enc_nsp if add_codec_hooks else None,
-
-        # XXX NOTE: pretty sure this is mutex with the `type=` to
-        # `Decoder`? so it won't work in tandem with the
-        # `ipc_pld_spec` passed above?
-        ext_types=[NamespacePath],
-
-        # TODO? is it useful to have the `.pld` decoded *prior* to
-        # the `PldRx`?? like perf or mem related?
-        # ext_dec=nsp_pld_dec,
-    )
-    if add_codec_hooks:
-        assert nsp_codec.dec.dec_hook is None
-
-        # TODO? if we pass `ext_dec` above?
-        # assert nsp_codec.dec.dec_hook is dec_nsp
-
-        assert nsp_codec.enc.enc_hook is enc_nsp
-
-    nsp = NamespacePath.from_ref(ex_func)
-
-    try:
-        nsp_bytes: bytes = nsp_codec.encode(nsp)
-        nsp_rt_sin_msg = nsp_pld_dec.decode(nsp_bytes)
-        nsp_rt_sin_msg.load_ref() is ex_func
-    except TypeError:
-        if not add_codec_hooks:
-            pass
-
-    try:
-        msg_bytes: bytes = nsp_codec.encode(
-            Started(
-                cid='cid',
-                pld=nsp,
-            )
-        )
-        # since the ext-type obj should also be set as the msg.pld
-        assert nsp_bytes in msg_bytes
-        started_rt: Started = nsp_codec.decode(msg_bytes)
-        pld: Raw = started_rt.pld
-        assert isinstance(pld, Raw)
-        nsp_rt: NamespacePath = nsp_pld_dec.decode(pld)
-        assert isinstance(nsp_rt, NamespacePath)
-        # in obj comparison terms they should be the same
-        assert nsp_rt == nsp
-        # ensure we've decoded to ext type!
-        assert nsp_rt.load_ref() is ex_func
-
-    except TypeError:
-        if not add_codec_hooks:
-            pass
-
-@tractor.context
-async def sleep_forever_in_sub(
-    ctx: Context,
-) -> None:
-    await trio.sleep_forever()
-
-
-def mk_custom_codec(
-    add_hooks: bool,
-
-) -> tuple[
-    MsgCodec,  # encode to send
-    MsgDec,  # pld receive-n-decode
-]:
-    '''
-    Create custom `msgpack` enc/dec-hooks and set a `Decoder`
-    which only loads `pld_spec` (like `NamespacePath`) types.
-
-    '''
-
-    # XXX NOTE XXX: despite defining `NamespacePath` as a type
-    # field on our `PayloadMsg.pld`, we still need a enc/dec_hook() pair
-    # to cast to/from that type on the wire. See the docs:
-    # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
-
-    # if pld_spec is Any:
-    #     pld_spec = Raw
-
-    nsp_codec: MsgCodec = mk_codec(
-        # ipc_pld_spec=Raw,  # default!
-
-        # NOTE XXX: the encode hook MUST be used no matter what since
-        # our `NamespacePath` is not any of a `Any` native type nor
-        # a `msgspec.Struct` subtype - so `msgspec` has no way to know
-        # how to encode it unless we provide the custom hook.
-        #
-        # AGAIN that is, regardless of whether we spec an
-        # `Any`-decoded-pld the enc has no knowledge (by default)
-        # how to enc `NamespacePath` (nsp), so we add a custom
-        # hook to do that ALWAYS.
-        enc_hook=enc_nsp if add_hooks else None,
-
-        # XXX NOTE: pretty sure this is mutex with the `type=` to
-        # `Decoder`? so it won't work in tandem with the
-        # `ipc_pld_spec` passed above?
-        ext_types=[NamespacePath],
-    )
-    # dec_hook=dec_nsp if add_hooks else None,
-    return nsp_codec
-
-
-@pytest.mark.parametrize(
-    'limit_plds_args',
-    [
-        (
-            {'dec_hook': None, 'ext_types': None},
-            None,
-        ),
-        (
-            {'dec_hook': dec_nsp, 'ext_types': None},
-            TypeError,
-        ),
-        (
-            {'dec_hook': dec_nsp, 'ext_types': [NamespacePath]},
-            None,
-        ),
-        (
-            {'dec_hook': dec_nsp, 'ext_types': [NamespacePath|None]},
-            None,
-        ),
-    ],
-    ids=[
-        'no_hook_no_ext_types',
-        'only_hook',
-        'hook_and_ext_types',
-        'hook_and_ext_types_w_null',
-    ]
-)
-def test_pld_limiting_usage(
-    limit_plds_args: tuple[dict, Exception|None],
-):
-    '''
-    Verify `dec_hook()` and `ext_types` need to either both be
-    provided or we raise a explanator type-error.
-
-    '''
-    kwargs, maybe_err = limit_plds_args
-    async def main():
-        async with tractor.open_nursery() as an:  # just to open runtime
-
-            # XXX SHOULD NEVER WORK outside an ipc ctx scope!
-            try:
-                with limit_plds(**kwargs):
-                    pass
-            except RuntimeError:
-                pass
-
-            p: tractor.Portal = await an.start_actor(
-                'sub',
-                enable_modules=[__name__],
-            )
-            async with (
-                p.open_context(
-                    sleep_forever_in_sub
-                ) as (ctx, first),
-            ):
-                try:
-                    with limit_plds(**kwargs):
-                        pass
-                except maybe_err as exc:
-                    assert type(exc) is maybe_err
-                    pass
-
-
-def chk_codec_applied(
-    expect_codec: MsgCodec|None,
-    enter_value: MsgCodec|None = None,
-
-) -> MsgCodec:
-    '''
-    buncha sanity checks ensuring that the IPC channel's
-    context-vars are set to the expected codec and that are
-    ctx-var wrapper APIs match the same.
-
-    '''
-    # TODO: play with tricyle again, bc this is supposed to work
-    # the way we want?
-    #
-    # TreeVar
-    # task: trio.Task = trio.lowlevel.current_task()
-    # curr_codec = _ctxvar_MsgCodec.get_in(task)
-
-    # ContextVar
-    # task_ctx: Context = task.context
-    # assert _ctxvar_MsgCodec in task_ctx
-    # curr_codec: MsgCodec = task.context[_ctxvar_MsgCodec]
-    if expect_codec is None:
-        assert enter_value is None
-        return
-
-    # NOTE: currently we use this!
-    # RunVar
-    curr_codec: MsgCodec = current_codec()
-    last_read_codec = _ctxvar_MsgCodec.get()
-    # assert curr_codec is last_read_codec
-
-    assert (
-        (same_codec := expect_codec) is
-        # returned from `mk_codec()`
-
-        # yielded value from `apply_codec()`
-
-        # read from current task's `contextvars.Context`
-        curr_codec is
-        last_read_codec
-
-        # the default `msgspec` settings
-        is not _codec._def_msgspec_codec
-        is not _codec._def_tractor_codec
-    )
-
-    if enter_value:
-        assert enter_value is same_codec
-
-
-@tractor.context
-async def send_back_values(
-    ctx: Context,
-    rent_pld_spec_type_strs: list[str],
-    add_hooks: bool,
-
-) -> None:
-    '''
-    Setup up a custom codec to load instances of `NamespacePath`
-    and ensure we can round trip a func ref with our parent.
-
-    '''
-    uid: tuple = tractor.current_actor().uid
-
-    # init state in sub-actor should be default
-    chk_codec_applied(
-        expect_codec=_codec._def_tractor_codec,
-    )
-
-    # load pld spec from input str
-    rent_pld_spec = _exts.dec_type_union(
-        rent_pld_spec_type_strs,
-        mods=[
-            importlib.import_module(__name__),
-        ],
-    )
-    rent_pld_spec_types: set[Type] = _codec.unpack_spec_types(
-        rent_pld_spec,
-    )
-
-    # ONLY add ext-hooks if the rent specified a non-std type!
-    add_hooks: bool = (
-        NamespacePath in rent_pld_spec_types
-        and
-        add_hooks
-    )
-
-    # same as on parent side config.
-    nsp_codec: MsgCodec|None = None
-    if add_hooks:
-        nsp_codec = mk_codec(
-            enc_hook=enc_nsp,
-            ext_types=[NamespacePath],
-        )
-
-    with (
-        maybe_apply_codec(nsp_codec) as codec,
-        limit_plds(
-            rent_pld_spec,
-            dec_hook=dec_nsp if add_hooks else None,
-            ext_types=[NamespacePath]  if add_hooks else None,
-        ) as pld_dec,
-    ):
-        # ?XXX? SHOULD WE NOT be swapping the global codec since it
-        # breaks `Context.started()` roundtripping checks??
-        chk_codec_applied(
-            expect_codec=nsp_codec,
-            enter_value=codec,
-        )
-
-        # ?TODO, mismatch case(s)?
-        #
-        # ensure pld spec matches on both sides
-        ctx_pld_dec: MsgDec = ctx._pld_rx._pld_dec
-        assert pld_dec is ctx_pld_dec
-        child_pld_spec: Type = pld_dec.spec
-        child_pld_spec_types: set[Type] = _codec.unpack_spec_types(
-            child_pld_spec,
-        )
-        assert (
-            child_pld_spec_types.issuperset(
-                rent_pld_spec_types
-            )
-        )
-
-        # ?TODO, try loop for each of the types in pld-superset?
-        #
-        # for send_value in [
-        #     nsp,
-        #     str(nsp),
-        #     None,
-        # ]:
-        nsp = NamespacePath.from_ref(ex_func)
-        try:
-            print(
-                f'{uid}: attempting to `.started({nsp})`\n'
-                f'\n'
-                f'rent_pld_spec: {rent_pld_spec}\n'
-                f'child_pld_spec: {child_pld_spec}\n'
-                f'codec: {codec}\n'
-            )
-            # await tractor.pause()
-            await ctx.started(nsp)
-
-        except tractor.MsgTypeError as _mte:
-            mte = _mte
-
-            # false -ve case
-            if add_hooks:
-                raise RuntimeError(
-                    f'EXPECTED to `.started()` value given spec ??\n\n'
-                    f'child_pld_spec -> {child_pld_spec}\n'
-                    f'value = {nsp}: {type(nsp)}\n'
-                )
-
-            # true -ve case
-            raise mte
-
-        # TODO: maybe we should add our own wrapper error so as to
-        # be interchange-lib agnostic?
-        # -[ ] the error type is wtv is raised from the hook so we
-        #   could also require a type-class of errors for
-        #   indicating whether the hook-failure can be handled by
-        #   a nasty-dialog-unprot sub-sys?
-        except TypeError as typerr:
-            # false -ve
-            if add_hooks:
-                raise RuntimeError('Should have been able to send `nsp`??')
-
-            # true -ve
-            print('Failed to send `nsp` due to no ext hooks set!')
-            raise typerr
-
-        # now try sending a set of valid and invalid plds to ensure
-        # the pld spec is respected.
-        sent: list[Any] = []
-        async with ctx.open_stream() as ipc:
-            print(
-                f'{uid}: streaming all pld types to rent..'
-            )
-
-            # for send_value, expect_send in iter_send_val_items:
-            for send_value in [
-                nsp,
-                str(nsp),
-                None,
-            ]:
-                send_type: Type = type(send_value)
-                print(
-                    f'{uid}: SENDING NEXT pld\n'
-                    f'send_type: {send_type}\n'
-                    f'send_value: {send_value}\n'
-                )
-                try:
-                    await ipc.send(send_value)
-                    sent.append(send_value)
-
-                except ValidationError as valerr:
-                    print(f'{uid} FAILED TO SEND {send_value}!')
-
-                    # false -ve
-                    if add_hooks:
-                        raise RuntimeError(
-                            f'EXPECTED to roundtrip value given spec:\n'
-                            f'rent_pld_spec -> {rent_pld_spec}\n'
-                            f'child_pld_spec -> {child_pld_spec}\n'
-                            f'value = {send_value}: {send_type}\n'
-                        )
-
-                    # true -ve
-                    raise valerr
-                    # continue
-
-            else:
-                print(
-                    f'{uid}: finished sending all values\n'
-                    'Should be exiting stream block!\n'
-                )
-
-        print(f'{uid}: exited streaming block!')
-
-
-
-@cm
-def maybe_apply_codec(codec: MsgCodec|None) -> MsgCodec|None:
-    if codec is None:
-        yield None
-        return
-
-    with apply_codec(codec) as codec:
-        yield codec
-
-
-@pytest.mark.parametrize(
-    'pld_spec',
-    [
-        Any,
-        NamespacePath,
-        NamespacePath|None,  # the "maybe" spec Bo
-    ],
-    ids=[
-        'any_type',
-        'only_nsp_ext',
-        'maybe_nsp_ext',
-    ]
-)
-@pytest.mark.parametrize(
-    'add_hooks',
-    [
-        True,
-        False,
-    ],
-    ids=[
-        'use_codec_hooks',
-        'no_codec_hooks',
-    ],
-)
-def test_ext_types_over_ipc(
-    debug_mode: bool,
-    pld_spec: Union[Type],
-    add_hooks: bool,
-):
-    '''
-    Ensure we can support extension types coverted using
-    `enc/dec_hook()`s passed to the `.msg.limit_plds()` API
-    and that sane errors happen when we try do the same without
-    the codec hooks.
-
-    '''
-    pld_types: set[Type] = _codec.unpack_spec_types(pld_spec)
-
-    async def main():
-
-        # sanity check the default pld-spec beforehand
-        chk_codec_applied(
-            expect_codec=_codec._def_tractor_codec,
-        )
-
-        # extension type we want to send as msg payload
-        nsp = NamespacePath.from_ref(ex_func)
-
-        # ^NOTE, 2 cases:
-        # - codec hooks noto added -> decode nsp as `str`
-        # - codec with hooks -> decode nsp as `NamespacePath`
-        nsp_codec: MsgCodec|None = None
-        if (
-            NamespacePath in pld_types
-            and
-            add_hooks
-        ):
-            nsp_codec = mk_codec(
-                enc_hook=enc_nsp,
-                ext_types=[NamespacePath],
-            )
-
-        async with tractor.open_nursery(
-            debug_mode=debug_mode,
-        ) as an:
-            p: tractor.Portal = await an.start_actor(
-                'sub',
-                enable_modules=[__name__],
-            )
-            with (
-                maybe_apply_codec(nsp_codec) as codec,
-            ):
-                chk_codec_applied(
-                    expect_codec=nsp_codec,
-                    enter_value=codec,
-                )
-                rent_pld_spec_type_strs: list[str] = _exts.enc_type_union(pld_spec)
-
-                # XXX should raise an mte (`MsgTypeError`)
-                # when `add_hooks == False` bc the input
-                # `expect_ipc_send` kwarg has a nsp which can't be
-                # serialized!
-                #
-                # TODO:can we ensure this happens from the
-                # `Return`-side (aka the sub) as well?
-                try:
-                    ctx: tractor.Context
-                    ipc: tractor.MsgStream
-                    async with (
-
-                        # XXX should raise an mte (`MsgTypeError`)
-                        # when `add_hooks == False`..
-                        p.open_context(
-                            send_back_values,
-                            # expect_debug=debug_mode,
-                            rent_pld_spec_type_strs=rent_pld_spec_type_strs,
-                            add_hooks=add_hooks,
-                            # expect_ipc_send=expect_ipc_send,
-                        ) as (ctx, first),
-
-                        ctx.open_stream() as ipc,
-                    ):
-                        with (
-                            limit_plds(
-                                pld_spec,
-                                dec_hook=dec_nsp if add_hooks else None,
-                                ext_types=[NamespacePath]  if add_hooks else None,
-                            ) as pld_dec,
-                        ):
-                            ctx_pld_dec: MsgDec = ctx._pld_rx._pld_dec
-                            assert pld_dec is ctx_pld_dec
-
-                            # if (
-                            #     not add_hooks
-                            #     and
-                            #     NamespacePath in 
-                            # ):
-                            #     pytest.fail('ctx should fail to open without custom enc_hook!?')
-
-                            await ipc.send(nsp)
-                            nsp_rt = await ipc.receive()
-
-                            assert nsp_rt == nsp
-                            assert nsp_rt.load_ref() is ex_func
-
-                # this test passes bc we can go no further!
-                except MsgTypeError as mte:
-                    # if not add_hooks:
-                    #     # teardown nursery
-                    #     await p.cancel_actor()
-                        # return
-
-                    raise mte
-
-            await p.cancel_actor()
-
-    if (
-        NamespacePath in pld_types
-        and
-        add_hooks
-    ):
-        trio.run(main)
-
-    else:
-        with pytest.raises(
-            expected_exception=tractor.RemoteActorError,
-        ) as excinfo:
-            trio.run(main)
-
-        exc = excinfo.value
-        # bc `.started(nsp: NamespacePath)` will raise
-        assert exc.boxed_type is TypeError
-
-
-# def chk_pld_type(
-#     payload_spec: Type[Struct]|Any,
-#     pld: Any,
-
-#     expect_roundtrip: bool|None = None,
-
-# ) -> bool:
-
-#     pld_val_type: Type = type(pld)
-
-#     # TODO: verify that the overridden subtypes
-#     # DO NOT have modified type-annots from original!
-#     # 'Start',  .pld: FuncSpec
-#     # 'StartAck',  .pld: IpcCtxSpec
-#     # 'Stop',  .pld: UNSEt
-#     # 'Error',  .pld: ErrorData
-
-#     codec: MsgCodec = mk_codec(
-#         # NOTE: this ONLY accepts `PayloadMsg.pld` fields of a specified
-#         # type union.
-#         ipc_pld_spec=payload_spec,
-#     )
-
-#     # make a one-off dec to compare with our `MsgCodec` instance
-#     # which does the below `mk_msg_spec()` call internally
-#     ipc_msg_spec: Union[Type[Struct]]
-#     msg_types: list[PayloadMsg[payload_spec]]
-#     (
-#         ipc_msg_spec,
-#         msg_types,
-#     ) = mk_msg_spec(
-#         payload_type_union=payload_spec,
-#     )
-#     _enc = msgpack.Encoder()
-#     _dec = msgpack.Decoder(
-#         type=ipc_msg_spec or Any,  # like `PayloadMsg[Any]`
-#     )
-
-#     assert (
-#         payload_spec
-#         ==
-#         codec.pld_spec
-#     )
-
-#     # assert codec.dec == dec
-#     #
-#     # ^-XXX-^ not sure why these aren't "equal" but when cast
-#     # to `str` they seem to match ?? .. kk
-
-#     assert (
-#         str(ipc_msg_spec)
-#         ==
-#         str(codec.msg_spec)
-#         ==
-#         str(_dec.type)
-#         ==
-#         str(codec.dec.type)
-#     )
-
-#     # verify the boxed-type for all variable payload-type msgs.
-#     if not msg_types:
-#         breakpoint()
-
-#     roundtrip: bool|None = None
-#     pld_spec_msg_names: list[str] = [
-#         td.__name__ for td in _payload_msgs
-#     ]
-#     for typedef in msg_types:
-
-#         skip_runtime_msg: bool = typedef.__name__ not in pld_spec_msg_names
-#         if skip_runtime_msg:
-#             continue
-
-#         pld_field = structs.fields(typedef)[1]
-#         assert pld_field.type is payload_spec # TODO-^ does this need to work to get all subtypes to adhere?
-
-#         kwargs: dict[str, Any] = {
-#             'cid': '666',
-#             'pld': pld,
-#         }
-#         enc_msg: PayloadMsg = typedef(**kwargs)
-
-#         _wire_bytes: bytes = _enc.encode(enc_msg)
-#         wire_bytes: bytes = codec.enc.encode(enc_msg)
-#         assert _wire_bytes == wire_bytes
-
-#         ve: ValidationError|None = None
-#         try:
-#             dec_msg = codec.dec.decode(wire_bytes)
-#             _dec_msg = _dec.decode(wire_bytes)
-
-#             # decoded msg and thus payload should be exactly same!
-#             assert (roundtrip := (
-#                 _dec_msg
-#                 ==
-#                 dec_msg
-#                 ==
-#                 enc_msg
-#             ))
-
-#             if (
-#                 expect_roundtrip is not None
-#                 and expect_roundtrip != roundtrip
-#             ):
-#                 breakpoint()
-
-#             assert (
-#                 pld
-#                 ==
-#                 dec_msg.pld
-#                 ==
-#                 enc_msg.pld
-#             )
-#             # assert (roundtrip := (_dec_msg == enc_msg))
-
-#         except ValidationError as _ve:
-#             ve = _ve
-#             roundtrip: bool = False
-#             if pld_val_type is payload_spec:
-#                 raise ValueError(
-#                    'Got `ValidationError` despite type-var match!?\n'
-#                     f'pld_val_type: {pld_val_type}\n'
-#                     f'payload_type: {payload_spec}\n'
-#                 ) from ve
-
-#             else:
-#                 # ow we good cuz the pld spec mismatched.
-#                 print(
-#                     'Got expected `ValidationError` since,\n'
-#                     f'{pld_val_type} is not {payload_spec}\n'
-#                 )
-#         else:
-#             if (
-#                 payload_spec is not Any
-#                 and
-#                 pld_val_type is not payload_spec
-#             ):
-#                 raise ValueError(
-#                    'DID NOT `ValidationError` despite expected type match!?\n'
-#                     f'pld_val_type: {pld_val_type}\n'
-#                     f'payload_type: {payload_spec}\n'
-#                 )
-
-#     # full code decode should always be attempted!
-#     if roundtrip is None:
-#         breakpoint()
-
-#     return roundtrip
-
-
-# ?TODO? maybe remove since covered in the newer `test_pldrx_limiting`
-# via end-2-end testing of all this?
-# -[ ] IOW do we really NEED this lowlevel unit testing?
-#
-# def test_limit_msgspec(
-#     debug_mode: bool,
-# ):
-#     '''
-#     Internals unit testing to verify that type-limiting an IPC ctx's
-#     msg spec with `Pldrx.limit_plds()` results in various
-#     encapsulated `msgspec` object settings and state.
-
-#     '''
-#     async def main():
-#         async with tractor.open_root_actor(
-#             debug_mode=debug_mode,
-#         ):
-#             # ensure we can round-trip a boxing `PayloadMsg`
-#             assert chk_pld_type(
-#                 payload_spec=Any,
-#                 pld=None,
-#                 expect_roundtrip=True,
-#             )
-
-#             # verify that a mis-typed payload value won't decode
-#             assert not chk_pld_type(
-#                 payload_spec=int,
-#                 pld='doggy',
-#             )
-
-#             # parametrize the boxed `.pld` type as a custom-struct
-#             # and ensure that parametrization propagates
-#             # to all payload-msg-spec-able subtypes!
-#             class CustomPayload(Struct):
-#                 name: str
-#                 value: Any
-
-#             assert not chk_pld_type(
-#                 payload_spec=CustomPayload,
-#                 pld='doggy',
-#             )
-
-#             assert chk_pld_type(
-#                 payload_spec=CustomPayload,
-#                 pld=CustomPayload(name='doggy', value='urmom')
-#             )
-
-#             # yah, we can `.pause_from_sync()` now!
-#             # breakpoint()
-
-#     trio.run(main)

tests/test_local.py

@@ -7,24 +7,31 @@ import pytest
 import trio
 import tractor
 
-from tractor._testing import tractor_test
+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) :
-        async with tractor.find_actor('doggy'):
+    with pytest.raises(RuntimeError):
+        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(reg_addr):
+async def test_self_is_registered(arb_addr):
     "Verify waiting on the arbiter to register itself using the standard api."
     actor = tractor.current_actor()
     assert actor.is_arbiter
@@ -34,20 +41,20 @@ async def test_self_is_registered(reg_addr):
 
 
 @tractor_test
-async def test_self_is_registered_localportal(reg_addr):
+async def test_self_is_registered_localportal(arb_addr):
     "Verify waiting on the arbiter to register itself using a local portal."
     actor = tractor.current_actor()
     assert actor.is_arbiter
-    async with tractor.get_registry(*reg_addr) as portal:
+    async with tractor.get_arbiter(*arb_addr) as portal:
         assert isinstance(portal, tractor._portal.LocalPortal)
 
         with trio.fail_after(0.2):
             sockaddr = await portal.run_from_ns(
                     'self', 'wait_for_actor', name='root')
-            assert sockaddr[0] == reg_addr
+            assert sockaddr[0] == arb_addr
 
 
-def test_local_actor_async_func(reg_addr):
+def test_local_actor_async_func(arb_addr):
     """Verify a simple async function in-process.
     """
     nums = []
@@ -55,7 +62,7 @@ def test_local_actor_async_func(reg_addr):
     async def print_loop():
 
         async with tractor.open_root_actor(
-            registry_addrs=[reg_addr],
+            arbiter_addr=arb_addr,
         ):
             # arbiter is started in-proc if dne
             assert tractor.current_actor().is_arbiter

tests/test_multi_program.py

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

tests/test_pldrx_limiting.py

@@ -1,364 +0,0 @@
-'''
-Audit sub-sys APIs from `.msg._ops`
-mostly for ensuring correct `contextvars`
-related settings around IPC contexts.
-
-'''
-from contextlib import (
-    asynccontextmanager as acm,
-)
-
-from msgspec import (
-    Struct,
-)
-import pytest
-import trio
-
-import tractor
-from tractor import (
-    Context,
-    MsgTypeError,
-    current_ipc_ctx,
-    Portal,
-)
-from tractor.msg import (
-    _ops as msgops,
-    Return,
-)
-from tractor.msg import (
-    _codec,
-)
-from tractor.msg.types import (
-    log,
-)
-
-
-class PldMsg(
-    Struct,
-
-    # TODO: with multiple structs in-spec we need to tag them!
-    # -[ ] offer a built-in `PldMsg` type to inherit from which takes
-    #      case of these details?
-    #
-    # https://jcristharif.com/msgspec/structs.html#tagged-unions
-    # tag=True,
-    # tag_field='msg_type',
-):
-    field: str
-
-
-maybe_msg_spec = PldMsg|None
-
-
-@acm
-async def maybe_expect_raises(
-    raises: BaseException|None = None,
-    ensure_in_message: list[str]|None = None,
-    post_mortem: bool = False,
-    timeout: int = 3,
-) -> None:
-    '''
-    Async wrapper for ensuring errors propagate from the inner scope.
-
-    '''
-    if tractor._state.debug_mode():
-        timeout += 999
-
-    with trio.fail_after(timeout):
-        try:
-            yield
-        except BaseException as _inner_err:
-            inner_err = _inner_err
-            # wasn't-expected to error..
-            if raises is None:
-                raise
-
-            else:
-                assert type(inner_err) is raises
-
-                # maybe check for error txt content
-                if ensure_in_message:
-                    part: str
-                    err_repr: str = repr(inner_err)
-                    for part in ensure_in_message:
-                        for i, arg in enumerate(inner_err.args):
-                            if part in err_repr:
-                                break
-                        # if part never matches an arg, then we're
-                        # missing a match.
-                        else:
-                            raise ValueError(
-                                'Failed to find error message content?\n\n'
-                                f'expected: {ensure_in_message!r}\n'
-                                f'part: {part!r}\n\n'
-                                f'{inner_err.args}'
-                        )
-
-                if post_mortem:
-                    await tractor.post_mortem()
-
-        else:
-            if raises:
-                raise RuntimeError(
-                    f'Expected a {raises.__name__!r} to be raised?'
-                )
-
-
-@tractor.context(
-    pld_spec=maybe_msg_spec,
-)
-async def child(
-    ctx: Context,
-    started_value: int|PldMsg|None,
-    return_value: str|None,
-    validate_pld_spec: bool,
-    raise_on_started_mte: bool = True,
-
-) -> None:
-    '''
-    Call ``Context.started()`` more then once (an error).
-
-    '''
-    expect_started_mte: bool = started_value == 10
-
-    # sanaity check that child RPC context is the current one
-    curr_ctx: Context = current_ipc_ctx()
-    assert ctx is curr_ctx
-
-    rx: msgops.PldRx = ctx._pld_rx
-    curr_pldec: _codec.MsgDec = rx.pld_dec
-
-    ctx_meta: dict = getattr(
-        child,
-        '_tractor_context_meta',
-        None,
-    )
-    if ctx_meta:
-        assert (
-            ctx_meta['pld_spec']
-            is curr_pldec.spec
-            is curr_pldec.pld_spec
-        )
-
-    # 2 cases: hdndle send-side and recv-only validation
-    # - when `raise_on_started_mte == True`, send validate
-    # - else, parent-recv-side only validation
-    mte: MsgTypeError|None = None
-    try:
-        await ctx.started(
-            value=started_value,
-            validate_pld_spec=validate_pld_spec,
-        )
-
-    except MsgTypeError as _mte:
-        mte = _mte
-        log.exception('started()` raised an MTE!\n')
-        if not expect_started_mte:
-            raise RuntimeError(
-                'Child-ctx-task SHOULD NOT HAVE raised an MTE for\n\n'
-                f'{started_value!r}\n'
-            )
-
-        boxed_div: str = '------ - ------'
-        assert boxed_div not in mte._message
-        assert boxed_div not in mte.tb_str
-        assert boxed_div not in repr(mte)
-        assert boxed_div not in str(mte)
-        mte_repr: str = repr(mte)
-        for line in mte.message.splitlines():
-            assert line in mte_repr
-
-        # since this is a *local error* there should be no
-        # boxed traceback content!
-        assert not mte.tb_str
-
-        # propagate to parent?
-        if raise_on_started_mte:
-            raise
-
-    # no-send-side-error fallthrough
-    if (
-        validate_pld_spec
-        and
-        expect_started_mte
-    ):
-        raise RuntimeError(
-            'Child-ctx-task SHOULD HAVE raised an MTE for\n\n'
-            f'{started_value!r}\n'
-        )
-
-    assert (
-        not expect_started_mte
-        or
-        not validate_pld_spec
-    )
-
-    # if wait_for_parent_to_cancel:
-    #     ...
-    #
-    # ^-TODO-^ logic for diff validation policies on each side:
-    #
-    # -[ ] ensure that if we don't validate on the send
-    #   side, that we are eventually error-cancelled by our
-    #   parent due to the bad `Started` payload!
-    # -[ ] the boxed error should be srced from the parent's
-    #   runtime NOT ours!
-    # -[ ] we should still error on bad `return_value`s
-    #   despite the parent not yet error-cancelling us?
-    #   |_ how do we want the parent side to look in that
-    #     case?
-    #     -[ ] maybe the equiv of "during handling of the
-    #       above error another occurred" for the case where
-    #       the parent sends a MTE to this child and while
-    #       waiting for the child to terminate it gets back
-    #       the MTE for this case?
-    #
-
-    # XXX should always fail on recv side since we can't
-    # really do much else beside terminate and relay the
-    # msg-type-error from this RPC task ;)
-    return return_value
-
-
-@pytest.mark.parametrize(
-    'return_value',
-    [
-        'yo',
-        None,
-    ],
-    ids=[
-        'return[invalid-"yo"]',
-        'return[valid-None]',
-    ],
-)
-@pytest.mark.parametrize(
-    'started_value',
-    [
-        10,
-        PldMsg(field='yo'),
-    ],
-    ids=[
-        'Started[invalid-10]',
-        'Started[valid-PldMsg]',
-    ],
-)
-@pytest.mark.parametrize(
-    'pld_check_started_value',
-    [
-        True,
-        False,
-    ],
-    ids=[
-        'check-started-pld',
-        'no-started-pld-validate',
-    ],
-)
-def test_basic_payload_spec(
-    debug_mode: bool,
-    loglevel: str,
-    return_value: str|None,
-    started_value: int|PldMsg,
-    pld_check_started_value: bool,
-):
-    '''
-    Validate the most basic `PldRx` msg-type-spec semantics around
-    a IPC `Context` endpoint start, started-sync, and final return
-    value depending on set payload types and the currently applied
-    pld-spec.
-
-    '''
-    invalid_return: bool = return_value == 'yo'
-    invalid_started: bool = started_value == 10
-
-    async def main():
-        async with tractor.open_nursery(
-            debug_mode=debug_mode,
-            loglevel=loglevel,
-        ) as an:
-            p: Portal = await an.start_actor(
-                'child',
-                enable_modules=[__name__],
-            )
-
-            # since not opened yet.
-            assert current_ipc_ctx() is None
-
-            if invalid_started:
-                msg_type_str: str = 'Started'
-                bad_value: int = 10
-            elif invalid_return:
-                msg_type_str: str = 'Return'
-                bad_value: str = 'yo'
-            else:
-                # XXX but should never be used below then..
-                msg_type_str: str = ''
-                bad_value: str = ''
-
-            maybe_mte: MsgTypeError|None = None
-            should_raise: Exception|None = (
-                MsgTypeError if (
-                    invalid_return
-                    or
-                    invalid_started
-                ) else None
-            )
-            async with (
-                maybe_expect_raises(
-                    raises=should_raise,
-                    ensure_in_message=[
-                        f"invalid `{msg_type_str}` msg payload",
-                        f'{bad_value}',
-                        f'has type {type(bad_value)!r}',
-                        'not match type-spec',
-                        f'`{msg_type_str}.pld: PldMsg|NoneType`',
-                    ],
-                    # only for debug
-                    # post_mortem=True,
-                ),
-                p.open_context(
-                    child,
-                    return_value=return_value,
-                    started_value=started_value,
-                    validate_pld_spec=pld_check_started_value,
-                ) as (ctx, first),
-            ):
-                # now opened with 'child' sub
-                assert current_ipc_ctx() is ctx
-
-                assert type(first) is PldMsg
-                assert first.field == 'yo'
-
-                try:
-                    res: None|PldMsg = await ctx.result(hide_tb=False)
-                    assert res is None
-                except MsgTypeError as mte:
-                    maybe_mte = mte
-                    if not invalid_return:
-                        raise
-
-                    # expected this invalid `Return.pld` so audit
-                    # the error state + meta-data
-                    assert mte.expected_msg_type is Return
-                    assert mte.cid == ctx.cid
-                    mte_repr: str = repr(mte)
-                    for line in mte.message.splitlines():
-                        assert line in mte_repr
-
-                    assert mte.tb_str
-                    # await tractor.pause(shield=True)
-
-                    # verify expected remote mte deats
-                    assert ctx._local_error is None
-                    assert (
-                        mte is
-                        ctx._remote_error is
-                        ctx.maybe_error is
-                        ctx.outcome
-                    )
-
-            if should_raise is None:
-                assert maybe_mte is None
-
-            await p.cancel_actor()
-
-    trio.run(main)

tests/test_pubsub.py

@@ -4,8 +4,8 @@ from itertools import cycle
 import pytest
 import trio
 import tractor
+from tractor.testing import tractor_test
 from tractor.experimental import msgpub
-from tractor._testing import tractor_test
 
 
 def test_type_checks():
@@ -159,7 +159,7 @@ async def test_required_args(callwith_expecterror):
 )
 def test_multi_actor_subs_arbiter_pub(
     loglevel,
-    reg_addr,
+    arb_addr,
     pub_actor,
 ):
     """Try out the neato @pub decorator system.
@@ -169,7 +169,7 @@ def test_multi_actor_subs_arbiter_pub(
     async def main():
 
         async with tractor.open_nursery(
-            registry_addrs=[reg_addr],
+            arbiter_addr=arb_addr,
             enable_modules=[__name__],
         ) as n:
 
@@ -254,12 +254,12 @@ def test_multi_actor_subs_arbiter_pub(
 
 def test_single_subactor_pub_multitask_subs(
     loglevel,
-    reg_addr,
+    arb_addr,
 ):
     async def main():
 
         async with tractor.open_nursery(
-            registry_addrs=[reg_addr],
+            arbiter_addr=arb_addr,
             enable_modules=[__name__],
         ) as n:
 

tests/test_resource_cache.py

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

tests/test_root_infect_asyncio.py

@@ -1,248 +0,0 @@
-'''
-Special attention cases for using "infect `asyncio`" mode from a root
-actor; i.e. not using a std `trio.run()` bootstrap.
-
-'''
-import asyncio
-from functools import partial
-
-import pytest
-import trio
-import tractor
-from tractor import (
-    to_asyncio,
-)
-from tests.test_infected_asyncio import (
-    aio_echo_server,
-)
-
-
-@pytest.mark.parametrize(
-    'raise_error_mid_stream',
-    [
-        False,
-        Exception,
-        KeyboardInterrupt,
-    ],
-    ids='raise_error={}'.format,
-)
-def test_infected_root_actor(
-    raise_error_mid_stream: bool|Exception,
-
-    # conftest wide
-    loglevel: str,
-    debug_mode: bool,
-):
-    '''
-    Verify you can run the `tractor` runtime with `Actor.is_infected_aio() == True`
-    in the root actor.
-
-    '''
-    async def _trio_main():
-        with trio.fail_after(2 if not debug_mode else 999):
-            first: str
-            chan: to_asyncio.LinkedTaskChannel
-            async with (
-                tractor.open_root_actor(
-                    debug_mode=debug_mode,
-                    loglevel=loglevel,
-                ),
-                to_asyncio.open_channel_from(
-                    aio_echo_server,
-                ) as (first, chan),
-            ):
-                assert first == 'start'
-
-                for i in range(1000):
-                    await chan.send(i)
-                    out = await chan.receive()
-                    assert out == i
-                    print(f'asyncio echoing {i}')
-
-                    if (
-                        raise_error_mid_stream
-                        and
-                        i == 500
-                    ):
-                        raise raise_error_mid_stream
-
-                    if out is None:
-                        try:
-                            out = await chan.receive()
-                        except trio.EndOfChannel:
-                            break
-                        else:
-                            raise RuntimeError(
-                                'aio channel never stopped?'
-                            )
-
-    if raise_error_mid_stream:
-        with pytest.raises(raise_error_mid_stream):
-            tractor.to_asyncio.run_as_asyncio_guest(
-                trio_main=_trio_main,
-            )
-    else:
-        tractor.to_asyncio.run_as_asyncio_guest(
-            trio_main=_trio_main,
-        )
-
-
-
-async def sync_and_err(
-    # just signature placeholders for compat with
-    # ``to_asyncio.open_channel_from()``
-    to_trio: trio.MemorySendChannel,
-    from_trio: asyncio.Queue,
-    ev: asyncio.Event,
-
-):
-    if to_trio:
-        to_trio.send_nowait('start')
-
-    await ev.wait()
-    raise RuntimeError('asyncio-side')
-
-
-@pytest.mark.parametrize(
-    'aio_err_trigger',
-    [
-        'before_start_point',
-        'after_trio_task_starts',
-        'after_start_point',
-    ],
-    ids='aio_err_triggered={}'.format
-)
-def test_trio_prestarted_task_bubbles(
-    aio_err_trigger: str,
-
-    # conftest wide
-    loglevel: str,
-    debug_mode: bool,
-):
-    async def pre_started_err(
-        raise_err: bool = False,
-        pre_sleep: float|None = None,
-        aio_trigger: asyncio.Event|None = None,
-        task_status=trio.TASK_STATUS_IGNORED,
-    ):
-        '''
-        Maybe pre-started error then sleep.
-
-        '''
-        if pre_sleep is not None:
-            print(f'Sleeping from trio for {pre_sleep!r}s !')
-            await trio.sleep(pre_sleep)
-
-        # signal aio-task to raise JUST AFTER this task
-        # starts but has not yet `.started()`
-        if aio_trigger:
-            print('Signalling aio-task to raise from `trio`!!')
-            aio_trigger.set()
-
-        if raise_err:
-            print('Raising from trio!')
-            raise TypeError('trio-side')
-
-        task_status.started()
-        await trio.sleep_forever()
-
-    async def _trio_main():
-        # with trio.fail_after(2):
-        with trio.fail_after(999):
-            first: str
-            chan: to_asyncio.LinkedTaskChannel
-            aio_ev = asyncio.Event()
-
-            async with (
-                tractor.open_root_actor(
-                    debug_mode=False,
-                    loglevel=loglevel,
-                ),
-            ):
-                # TODO, tests for this with 3.13 egs?
-                # from tractor.devx import open_crash_handler
-                # with open_crash_handler():
-                async with (
-                    # where we'll start a sub-task that errors BEFORE
-                    # calling `.started()` such that the error should
-                    # bubble before the guest run terminates!
-                    trio.open_nursery() as tn,
-
-                    # THEN start an infect task which should error just
-                    # after the trio-side's task does.
-                    to_asyncio.open_channel_from(
-                        partial(
-                            sync_and_err,
-                            ev=aio_ev,
-                        )
-                    ) as (first, chan),
-                ):
-
-                    for i in range(5):
-                        pre_sleep: float|None = None
-                        last_iter: bool = (i == 4)
-
-                        # TODO, missing cases?
-                        # -[ ] error as well on
-                        #    'after_start_point' case as well for
-                        #    another case?
-                        raise_err: bool = False
-
-                        if last_iter:
-                            raise_err: bool = True
-
-                            # trigger aio task to error on next loop
-                            # tick/checkpoint
-                            if aio_err_trigger == 'before_start_point':
-                                aio_ev.set()
-
-                            pre_sleep: float = 0
-
-                        await tn.start(
-                            pre_started_err,
-                            raise_err,
-                            pre_sleep,
-                            (aio_ev if (
-                                    aio_err_trigger == 'after_trio_task_starts'
-                                    and
-                                    last_iter
-                                ) else None
-                            ),
-                        )
-
-                        if (
-                            aio_err_trigger == 'after_start_point'
-                            and
-                            last_iter
-                        ):
-                            aio_ev.set()
-
-    with pytest.raises(
-        expected_exception=ExceptionGroup,
-    ) as excinfo:
-        tractor.to_asyncio.run_as_asyncio_guest(
-            trio_main=_trio_main,
-        )
-
-    eg = excinfo.value
-    rte_eg, rest_eg = eg.split(RuntimeError)
-
-    # ensure the trio-task's error bubbled despite the aio-side
-    # having (maybe) errored first.
-    if aio_err_trigger in (
-        'after_trio_task_starts',
-        'after_start_point',
-    ):
-        assert len(errs := rest_eg.exceptions) == 1
-        typerr = errs[0]
-        assert (
-            type(typerr) is TypeError
-            and
-            'trio-side' in typerr.args
-        )
-
-    # when aio errors BEFORE (last) trio task is scheduled, we should
-    # never see anythinb but the aio-side.
-    else:
-        assert len(rtes := rte_eg.exceptions) == 1
-        assert 'asyncio-side' in rtes[0].args[0]

tests/test_rpc.py

@@ -1,8 +1,6 @@
-'''
-RPC (or maybe better labelled as "RTS: remote task scheduling"?)
-related API and error checks.
-
-'''
+"""
+RPC related
+"""
 import itertools
 
 import pytest
@@ -15,19 +13,9 @@ async def sleep_back_actor(
     func_name,
     func_defined,
     exposed_mods,
-    *,
-    reg_addr: tuple,
 ):
     if actor_name:
-        async with tractor.find_actor(
-            actor_name,
-            # NOTE: must be set manually since
-            # the subactor doesn't have the reg_addr
-            # fixture code run in it!
-            # TODO: maybe we should just set this once in the
-            # _state mod and derive to all children?
-            registry_addrs=[reg_addr],
-        ) as portal:
+        async with tractor.find_actor(actor_name) as portal:
             try:
                 await portal.run(__name__, func_name)
             except tractor.RemoteActorError as err:
@@ -36,7 +24,7 @@ async def sleep_back_actor(
                 if not exposed_mods:
                     expect = tractor.ModuleNotExposed
 
-                assert err.boxed_type is expect
+                assert err.type is expect
                 raise
     else:
         await trio.sleep(float('inf'))
@@ -54,25 +42,14 @@ async def short_sleep():
         (['tmp_mod'], 'import doggy', ModuleNotFoundError),
         (['tmp_mod'], '4doggy', SyntaxError),
     ],
-    ids=[
-        'no_mods',
-        'this_mod',
-        'this_mod_bad_func',
-        'fail_to_import',
-        'fail_on_syntax',
-    ],
+    ids=['no_mods', 'this_mod', 'this_mod_bad_func', 'fail_to_import',
+         'fail_on_syntax'],
 )
-def test_rpc_errors(
-    reg_addr,
-    to_call,
-    testdir,
-):
-    '''
-    Test errors when making various RPC requests to an actor
+def test_rpc_errors(arb_addr, to_call, testdir):
+    """Test errors when making various RPC requests to an actor
     that either doesn't have the requested module exposed or doesn't define
     the named function.
-
-    '''
+    """
     exposed_mods, funcname, inside_err = to_call
     subactor_exposed_mods = []
     func_defined = globals().get(funcname, False)
@@ -100,13 +77,8 @@ def test_rpc_errors(
 
         # spawn a subactor which calls us back
         async with tractor.open_nursery(
-            registry_addrs=[reg_addr],
+            arbiter_addr=arb_addr,
             enable_modules=exposed_mods.copy(),
-
-            # NOTE: will halt test in REPL if uncommented, so only
-            # do that if actually debugging subactor but keep it
-            # disabled for the test.
-            # debug_mode=True,
         ) as n:
 
             actor = tractor.current_actor()
@@ -123,7 +95,6 @@ def test_rpc_errors(
                 exposed_mods=exposed_mods,
                 func_defined=True if func_defined else False,
                 enable_modules=subactor_exposed_mods,
-                reg_addr=reg_addr,
             )
 
     def run():
@@ -134,20 +105,18 @@ def test_rpc_errors(
         run()
     else:
         # underlying errors aren't propagated upwards (yet)
-        with pytest.raises(
-            expected_exception=(remote_err, ExceptionGroup),
-        ) as err:
+        with pytest.raises(remote_err) as err:
             run()
 
         # get raw instance from pytest wrapper
         value = err.value
 
         # might get multiple `trio.Cancelled`s as well inside an inception
-        if isinstance(value, ExceptionGroup):
+        if isinstance(value, trio.MultiError):
             value = next(itertools.dropwhile(
                 lambda exc: not isinstance(exc, tractor.RemoteActorError),
                 value.exceptions
             ))
 
         if getattr(value, 'type', None):
-            assert value.boxed_type is inside_err
+            assert value.type is inside_err

tests/test_runtime.py

@@ -1,74 +0,0 @@
-"""
-Verifying internal runtime state and undocumented extras.
-
-"""
-import os
-
-import pytest
-import trio
-import tractor
-
-from tractor._testing 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,
-        BaseExceptionGroup,
-    ):
-        pass
-
-    # tmp file should have been wiped by
-    # teardown stack.
-    assert not child_tmp_file.exists()

tests/test_spawning.py

@@ -1,38 +1,38 @@
 """
 Spawning basics
-
 """
-from typing import (
-    Any,
-)
+from typing import Dict, Tuple, Optional
 
 import pytest
 import trio
 import tractor
 
-from tractor._testing import tractor_test
+from conftest import tractor_test
 
 data_to_pass_down = {'doggy': 10, 'kitty': 4}
 
 
 async def spawn(
     is_arbiter: bool,
-    data: dict,
-    reg_addr: tuple[str, int],
+    data: Dict,
+    arb_addr: Tuple[str, int],
 ):
     namespaces = [__name__]
 
     await trio.sleep(0.1)
 
     async with tractor.open_root_actor(
-        arbiter_addr=reg_addr,
+        arbiter_addr=arb_addr,
     ):
+
         actor = tractor.current_actor()
         assert actor.is_arbiter == is_arbiter
         data = data_to_pass_down
 
         if actor.is_arbiter:
-            async with tractor.open_nursery() as nursery:
+
+            async with tractor.open_nursery(
+            ) as nursery:
 
                 # forks here
                 portal = await nursery.run_in_actor(
@@ -40,7 +40,7 @@ async def spawn(
                     is_arbiter=False,
                     name='sub-actor',
                     data=data,
-                    reg_addr=reg_addr,
+                    arb_addr=arb_addr,
                     enable_modules=namespaces,
                 )
 
@@ -54,14 +54,12 @@ async def spawn(
             return 10
 
 
-def test_local_arbiter_subactor_global_state(
-    reg_addr,
-):
+def test_local_arbiter_subactor_global_state(arb_addr):
     result = trio.run(
         spawn,
         True,
         data_to_pass_down,
-        reg_addr,
+        arb_addr,
     )
     assert result == 10
 
@@ -95,9 +93,7 @@ async def test_movie_theatre_convo(start_method):
         await portal.cancel_actor()
 
 
-async def cellar_door(
-    return_value: str|None,
-):
+async def cellar_door(return_value: Optional[str]):
     return return_value
 
 
@@ -107,18 +103,16 @@ async def cellar_door(
 )
 @tractor_test
 async def test_most_beautiful_word(
-    start_method: str,
-    return_value: Any,
-    debug_mode: bool,
+    start_method,
+    return_value
 ):
     '''
     The main ``tractor`` routine.
 
     '''
     with trio.fail_after(1):
-        async with tractor.open_nursery(
-            debug_mode=debug_mode,
-        ) as n:
+        async with tractor.open_nursery() as n:
+
             portal = await n.run_in_actor(
                 cellar_door,
                 return_value=return_value,
@@ -145,9 +139,9 @@ async def check_loglevel(level):
 def test_loglevel_propagated_to_subactor(
     start_method,
     capfd,
-    reg_addr,
+    arb_addr,
 ):
-    if start_method == 'mp_forkserver':
+    if start_method == 'forkserver':
         pytest.skip(
             "a bug with `capfd` seems to make forkserver capture not work?")
 
@@ -156,13 +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=reg_addr,
+            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 tractor._testing import tractor_test
-
 
 def test_must_define_ctx():
 
@@ -38,13 +37,10 @@ async def async_gen_stream(sequence):
     assert cs.cancelled_caught
 
 
-# TODO: deprecated either remove entirely
-# or re-impl in terms of `MsgStream` one-sides
-# wrapper, but at least remove `Portal.open_stream_from()`
 @tractor.stream
 async def context_stream(
     ctx: tractor.Context,
-    sequence: list[int],
+    sequence
 ):
     for i in sequence:
         await ctx.send_yield(i)
@@ -58,7 +54,7 @@ async def context_stream(
 
 
 async def stream_from_single_subactor(
-    reg_addr,
+    arb_addr,
     start_method,
     stream_func,
 ):
@@ -67,7 +63,7 @@ async def stream_from_single_subactor(
     # only one per host address, spawns an actor if None
 
     async with tractor.open_nursery(
-        registry_addrs=[reg_addr],
+        arbiter_addr=arb_addr,
         start_method=start_method,
     ) as nursery:
 
@@ -118,13 +114,13 @@ async def stream_from_single_subactor(
 @pytest.mark.parametrize(
     'stream_func', [async_gen_stream, context_stream]
 )
-def test_stream_from_single_subactor(reg_addr, start_method, stream_func):
+def test_stream_from_single_subactor(arb_addr, start_method, stream_func):
     """Verify streaming from a spawned async generator.
     """
     trio.run(
         partial(
             stream_from_single_subactor,
-            reg_addr,
+            arb_addr,
             start_method,
             stream_func=stream_func,
         ),
@@ -228,14 +224,14 @@ async def a_quadruple_example():
         return result_stream
 
 
-async def cancel_after(wait, reg_addr):
-    async with tractor.open_root_actor(registry_addrs=[reg_addr]):
+async def cancel_after(wait, arb_addr):
+    async with tractor.open_root_actor(arbiter_addr=arb_addr):
         with trio.move_on_after(wait):
             return await a_quadruple_example()
 
 
 @pytest.fixture(scope='module')
-def time_quad_ex(reg_addr, ci_env, spawn_backend):
+def time_quad_ex(arb_addr, ci_env, spawn_backend):
     if spawn_backend == 'mp':
         """no idea but the  mp *nix runs are flaking out here often...
         """
@@ -243,7 +239,7 @@ def time_quad_ex(reg_addr, ci_env, spawn_backend):
 
     timeout = 7 if platform.system() in ('Windows', 'Darwin') else 4
     start = time.time()
-    results = trio.run(cancel_after, timeout, reg_addr)
+    results = trio.run(cancel_after, timeout, arb_addr)
     diff = time.time() - start
     assert results
     return results, diff
@@ -254,7 +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
 
 
@@ -263,14 +259,14 @@ def test_a_quadruple_example(time_quad_ex, ci_env, spawn_backend):
     list(map(lambda i: i/10, range(3, 9)))
 )
 def test_not_fast_enough_quad(
-    reg_addr, time_quad_ex, cancel_delay, ci_env, spawn_backend
+    arb_addr, time_quad_ex, cancel_delay, ci_env, spawn_backend
 ):
     """Verify we can cancel midway through the quad example and all actors
     cancel gracefully.
     """
     results, diff = time_quad_ex
     delay = max(diff - cancel_delay, 0)
-    results = trio.run(cancel_after, delay, reg_addr)
+    results = trio.run(cancel_after, delay, arb_addr)
     system = platform.system()
     if system in ('Windows', 'Darwin') and results is not None:
         # In CI envoirments it seems later runs are quicker then the first
@@ -283,7 +279,7 @@ def test_not_fast_enough_quad(
 
 @tractor_test
 async def test_respawn_consumer_task(
-    reg_addr,
+    arb_addr,
     spawn_backend,
     loglevel,
 ):

tests/test_task_broadcasting.py

@@ -2,23 +2,17 @@
 Broadcast channels for fan-out to local tasks.
 
 """
-from contextlib import (
-    asynccontextmanager as acm,
-)
+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 (
-    broadcast_receiver,
-    Lagged,
-    collapse_eg,
-)
+from tractor.trionics import broadcast_receiver, Lagged
 
 
 @tractor.context
@@ -43,7 +37,7 @@ async def echo_sequences(
 
 async def ensure_sequence(
 
-    stream: tractor.MsgStream,
+    stream: tractor.ReceiveMsgStream,
     sequence: list,
     delay: Optional[float] = None,
 
@@ -65,21 +59,21 @@ async def ensure_sequence(
                 break
 
 
-@acm
+@asynccontextmanager
 async def open_sequence_streamer(
 
-    sequence: list[int],
-    reg_addr: tuple[str, int],
+    sequence: List[int],
+    arb_addr: Tuple[str, int],
     start_method: str,
 
 ) -> tractor.MsgStream:
 
     async with tractor.open_nursery(
-        arbiter_addr=reg_addr,
+        arbiter_addr=arb_addr,
         start_method=start_method,
-    ) as an:
+    ) as tn:
 
-        portal = await an.start_actor(
+        portal = await tn.start_actor(
             'sequence_echoer',
             enable_modules=[__name__],
         )
@@ -89,14 +83,14 @@ async def open_sequence_streamer(
         ) as (ctx, first):
 
             assert first is None
-            async with ctx.open_stream(allow_overruns=True) as stream:
+            async with ctx.open_stream(backpressure=True) as stream:
                 yield stream
 
         await portal.cancel_actor()
 
 
 def test_stream_fan_out_to_local_subscriptions(
-    reg_addr,
+    arb_addr,
     start_method,
 ):
 
@@ -106,7 +100,7 @@ def test_stream_fan_out_to_local_subscriptions(
 
         async with open_sequence_streamer(
             sequence,
-            reg_addr,
+            arb_addr,
             start_method,
         ) as stream:
 
@@ -141,7 +135,7 @@ def test_stream_fan_out_to_local_subscriptions(
     ]
 )
 def test_consumer_and_parent_maybe_lag(
-    reg_addr,
+    arb_addr,
     start_method,
     task_delays,
 ):
@@ -153,17 +147,14 @@ def test_consumer_and_parent_maybe_lag(
 
         async with open_sequence_streamer(
             sequence,
-            reg_addr,
+            arb_addr,
             start_method,
         ) as stream:
 
             try:
-                async with (
-                    collapse_eg(),
-                    trio.open_nursery() as tn,
-                ):
+                async with trio.open_nursery() as n:
 
-                    tn.start_soon(
+                    n.start_soon(
                         ensure_sequence,
                         stream,
                         sequence.copy(),
@@ -217,11 +208,10 @@ def test_consumer_and_parent_maybe_lag(
 
 
 def test_faster_task_to_recv_is_cancelled_by_slower(
-    reg_addr,
+    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.
 
     '''
@@ -231,13 +221,13 @@ def test_faster_task_to_recv_is_cancelled_by_slower(
 
         async with open_sequence_streamer(
             sequence,
-            reg_addr,
+            arb_addr,
             start_method,
 
         ) as stream:
 
-            async with trio.open_nursery() as tn:
-                tn.start_soon(
+            async with trio.open_nursery() as n:
+                n.start_soon(
                     ensure_sequence,
                     stream,
                     sequence.copy(),
@@ -259,7 +249,7 @@ def test_faster_task_to_recv_is_cancelled_by_slower(
                         continue
 
                 print('cancelling faster subtask')
-                tn.cancel_scope.cancel()
+                n.cancel_scope.cancel()
 
             try:
                 value = await stream.receive()
@@ -277,7 +267,7 @@ def test_faster_task_to_recv_is_cancelled_by_slower(
                         # the faster subtask was cancelled
                         break
 
-                # await tractor.pause()
+                # await tractor.breakpoint()
                 # await stream.receive()
                 print(f'final value: {value}')
 
@@ -308,7 +298,7 @@ def test_subscribe_errors_after_close():
 
 
 def test_ensure_slow_consumers_lag_out(
-    reg_addr,
+    arb_addr,
     start_method,
 ):
     '''This is a pure local task test; no tractor
@@ -377,13 +367,13 @@ def test_ensure_slow_consumers_lag_out(
                                     f'on {lags}:{value}')
                                 return
 
-            async with trio.open_nursery() as tn:
+            async with trio.open_nursery() as nursery:
 
                 for i in range(1, num_laggers):
 
                     task_name = f'sub_{i}'
                     laggers[task_name] = 0
-                    tn.start_soon(
+                    nursery.start_soon(
                         partial(
                             sub_and_print,
                             delay=i*0.001,
@@ -419,8 +409,8 @@ def test_ensure_slow_consumers_lag_out(
                     seq = brx._state.subs[brx.key]
                     assert seq == len(brx._state.queue) - 1
 
-                # all no_overruns entries in the underlying
-                # channel should have been copied into the bcaster
+                # all backpressured entries in the underlying
+                # channel should have been copied into the caster
                 # queue trailing-window
                 async for i in rx:
                     print(f'bped: {i}')
@@ -470,52 +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',
-            ),
-            collapse_eg(),
-            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

@@ -3,13 +3,9 @@ Reminders for oddities in `trio` that we need to stay aware of and/or
 want to see changed.
 
 '''
-from contextlib import (
-    asynccontextmanager as acm,
-)
-
 import pytest
 import trio
-from trio import TaskStatus
+from trio_typing import TaskStatus
 
 
 @pytest.mark.parametrize(
@@ -64,9 +60,7 @@ def test_stashed_child_nursery(use_start_soon):
     async def main():
 
         async with (
-            trio.open_nursery(
-                strict_exception_groups=False,
-            ) as pn,
+            trio.open_nursery() as pn,
         ):
             cn = await pn.start(mk_child_nursery)
             assert cn
@@ -86,118 +80,3 @@ def test_stashed_child_nursery(use_start_soon):
 
     with pytest.raises(NameError):
         trio.run(main)
-
-
-@pytest.mark.parametrize(
-    ('unmask_from_canc', 'canc_from_finally'),
-    [
-        (True, False),
-        (True, True),
-        pytest.param(False, True,
-                     marks=pytest.mark.xfail(reason="never raises!")
-        ),
-    ],
-    # TODO, ask ronny how to impl this .. XD
-    # ids='unmask_from_canc={0}, canc_from_finally={1}',#.format,
-)
-def test_acm_embedded_nursery_propagates_enter_err(
-    canc_from_finally: bool,
-    unmask_from_canc: bool,
-    debug_mode: bool,
-):
-    '''
-    Demo how a masking `trio.Cancelled` could be handled by unmasking from the
-    `.__context__` field when a user (by accident) re-raises from a `finally:`.
-
-    '''
-    import tractor
-
-    @acm
-    async def maybe_raise_from_masking_exc(
-        tn: trio.Nursery,
-        unmask_from: BaseException|None = trio.Cancelled
-
-        # TODO, maybe offer a collection?
-        # unmask_from: set[BaseException] = {
-        #     trio.Cancelled,
-        # },
-    ):
-        if not unmask_from:
-            yield
-            return
-
-        try:
-            yield
-        except* unmask_from as be_eg:
-
-            # TODO, if we offer `unmask_from: set`
-            # for masker_exc_type in unmask_from:
-
-            matches, rest = be_eg.split(unmask_from)
-            if not matches:
-                raise
-
-            for exc_match in be_eg.exceptions:
-                if (
-                    (exc_ctx := exc_match.__context__)
-                    and
-                    type(exc_ctx) not in {
-                        # trio.Cancelled,  # always by default?
-                        unmask_from,
-                    }
-                ):
-                    exc_ctx.add_note(
-                        f'\n'
-                        f'WARNING: the above error was masked by a {unmask_from!r} !?!\n'
-                        f'Are you always cancelling? Say from a `finally:` ?\n\n'
-
-                        f'{tn!r}'
-                    )
-                    raise exc_ctx from exc_match
-
-
-    @acm
-    async def wraps_tn_that_always_cancels():
-        async with (
-            trio.open_nursery() as tn,
-            maybe_raise_from_masking_exc(
-                tn=tn,
-                unmask_from=(
-                    trio.Cancelled
-                    if unmask_from_canc
-                    else None
-                ),
-            )
-        ):
-            try:
-                yield tn
-            finally:
-                if canc_from_finally:
-                    tn.cancel_scope.cancel()
-                    await trio.lowlevel.checkpoint()
-
-    async def _main():
-        with tractor.devx.maybe_open_crash_handler(
-            pdb=debug_mode,
-        ) as bxerr:
-            assert not bxerr.value
-
-            async with (
-                wraps_tn_that_always_cancels() as tn,
-            ):
-                assert not tn.cancel_scope.cancel_called
-                assert 0
-
-        assert (
-            (err := bxerr.value)
-            and
-            type(err) is AssertionError
-        )
-
-    with pytest.raises(ExceptionGroup) as excinfo:
-        trio.run(_main)
-
-    eg: ExceptionGroup = excinfo.value
-    assert_eg, rest_eg = eg.split(AssertionError)
-
-    assert len(assert_eg.exceptions) == 1

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

@@ -15,56 +15,64 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 """
-tractor: structured concurrent ``trio``-"actors".
+tractor: structured concurrent "actors".
 
 """
+from trio import MultiError
 
-from ._clustering import (
-    open_actor_cluster as open_actor_cluster,
-)
-from ._context import (
-    Context as Context,  # the type
-    context as context,  # a func-decorator
-)
+from ._clustering import open_actor_cluster
+from ._ipc import Channel
 from ._streaming import (
-    MsgStream as MsgStream,
-    stream as stream,
+    Context,
+    ReceiveMsgStream,
+    MsgStream,
+    stream,
+    context,
 )
 from ._discovery import (
-    get_registry as get_registry,
-    find_actor as find_actor,
-    wait_for_actor as wait_for_actor,
-    query_actor as query_actor,
-)
-from ._supervise import (
-    open_nursery as open_nursery,
-    ActorNursery as ActorNursery,
-)
-from ._state import (
-    current_actor as current_actor,
-    is_root_process as is_root_process,
-    current_ipc_ctx as current_ipc_ctx,
-    debug_mode as debug_mode
+    get_arbiter,
+    find_actor,
+    wait_for_actor,
+    query_actor,
 )
+from ._supervise import open_nursery
+from ._state import current_actor, is_root_process
 from ._exceptions import (
-    ContextCancelled as ContextCancelled,
-    ModuleNotExposed as ModuleNotExposed,
-    MsgTypeError as MsgTypeError,
-    RemoteActorError as RemoteActorError,
-    TransportClosed as TransportClosed,
+    RemoteActorError,
+    ModuleNotExposed,
+    ContextCancelled,
 )
-from .devx import (
-    breakpoint as breakpoint,
-    pause as pause,
-    pause_from_sync as pause_from_sync,
-    post_mortem as post_mortem,
-)
-from . import msg as msg
-from ._root import (
-    run_daemon as run_daemon,
-    open_root_actor as open_root_actor,
-)
-from ._ipc import Channel as Channel
-from ._portal import Portal as Portal
-from ._runtime import Actor as Actor
-# from . import hilevel as hilevel
+from ._debug import breakpoint, post_mortem
+from . import msg
+from ._root import run, run_daemon, open_root_actor
+from ._portal import Portal
+
+
+__all__ = [
+    'Channel',
+    'Context',
+    'ContextCancelled',
+    'ModuleNotExposed',
+    'MsgStream',
+    'MultiError',
+    'Portal',
+    'ReceiveMsgStream',
+    'RemoteActorError',
+    'breakpoint',
+    'context',
+    'current_actor',
+    'find_actor',
+    'get_arbiter',
+    'is_root_process',
+    'msg',
+    'open_actor_cluster',
+    'open_nursery',
+    'open_root_actor',
+    'post_mortem',
+    'query_actor',
+    'run',
+    'run_daemon',
+    'stream',
+    'to_asyncio',
+    'wait_for_actor',
+]

tractor/_child.py

@@ -18,11 +18,13 @@
 This is the "bootloader" for actors started using the native trio backend.
 
 """
+import sys
+import trio
 import argparse
 
 from ast import literal_eval
 
-from ._runtime import Actor
+from ._actor import Actor
 from ._entry import _trio_main
 
 
@@ -35,8 +37,9 @@ def parse_ipaddr(arg):
     return (str(host), int(port))
 
 
+from ._entry import _trio_main
+
 if __name__ == "__main__":
-    __tracebackhide__: bool = True
 
     parser = argparse.ArgumentParser()
     parser.add_argument("--uid", type=parse_uid)

tractor/_clustering.py

@@ -19,13 +19,10 @@ Actor cluster helpers.
 
 '''
 from __future__ import annotations
-from contextlib import (
-    asynccontextmanager as acm,
-)
+
+from contextlib import asynccontextmanager as acm
 from multiprocessing import cpu_count
-from typing import (
-    AsyncGenerator,
-)
+from typing import AsyncGenerator, Optional
 
 import trio
 import tractor
@@ -35,12 +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,
@@ -55,9 +49,7 @@ async def open_actor_cluster(
         raise ValueError(
             'Number of names is {len(names)} but count it {count}')
 
-    async with tractor.open_nursery(
-        **runtime_kwargs,
-    ) as an:
+    async with tractor.open_nursery(start_method=start_method) as an:
         async with trio.open_nursery() as n:
             uid = tractor.current_actor().uid
 

tractor/_debug.py

@@ -0,0 +1,652 @@
+# 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/>.
+
+"""
+Multi-core debugging for da peeps!
+
+"""
+import bdb
+import sys
+from functools import partial
+from contextlib import asynccontextmanager as acm
+from typing import (
+    Tuple,
+    Optional,
+    Callable,
+    AsyncIterator,
+    AsyncGenerator,
+)
+
+import tractor
+import trio
+from trio_typing import TaskStatus
+
+from .log import get_logger
+from . import _state
+from ._discovery import get_root
+from ._state import is_root_process, debug_mode
+from ._exceptions import is_multi_cancelled
+
+try:
+    # wtf: only exported when installed in dev mode?
+    import pdbpp
+except ImportError:
+    # pdbpp is installed in regular mode...it monkey patches stuff
+    import pdb
+    assert pdb.xpm, "pdbpp is not installed?"  # type: ignore
+    pdbpp = pdb
+
+log = get_logger(__name__)
+
+
+__all__ = ['breakpoint', 'post_mortem']
+
+
+# TODO: wrap all these in a static global class: ``DebugLock`` maybe?
+
+# placeholder for function to set a ``trio.Event`` on debugger exit
+_pdb_release_hook: Optional[Callable] = None
+
+# actor-wide variable pointing to current task name using debugger
+_local_task_in_debug: Optional[str] = None
+
+# actor tree-wide actor uid that supposedly has the tty lock
+_global_actor_in_debug: Optional[Tuple[str, str]] = None
+
+# lock in root actor preventing multi-access to local tty
+_debug_lock: trio.StrictFIFOLock = trio.StrictFIFOLock()
+_local_pdb_complete: Optional[trio.Event] = None
+_no_remote_has_tty: Optional[trio.Event] = None
+
+# XXX: set by the current task waiting on the root tty lock
+# and must be cancelled if this actor is cancelled via message
+# otherwise deadlocks with the parent actor may ensure
+_debugger_request_cs: Optional[trio.CancelScope] = None
+
+
+class TractorConfig(pdbpp.DefaultConfig):
+    """Custom ``pdbpp`` goodness.
+    """
+    # sticky_by_default = True
+
+
+class PdbwTeardown(pdbpp.Pdb):
+    """Add teardown hooks to the regular ``pdbpp.Pdb``.
+    """
+    # override the pdbpp config with our coolio one
+    DefaultConfig = TractorConfig
+
+    # TODO: figure out how to disallow recursive .set_trace() entry
+    # since that'll cause deadlock for us.
+    def set_continue(self):
+        try:
+            super().set_continue()
+        finally:
+            global _local_task_in_debug
+            _local_task_in_debug = None
+            _pdb_release_hook()
+
+    def set_quit(self):
+        try:
+            super().set_quit()
+        finally:
+            global _local_task_in_debug
+            _local_task_in_debug = None
+            _pdb_release_hook()
+
+
+# TODO: will be needed whenever we get to true remote debugging.
+# XXX see https://github.com/goodboy/tractor/issues/130
+
+# # TODO: is there some way to determine this programatically?
+# _pdb_exit_patterns = tuple(
+#     str.encode(patt + "\n") for patt in (
+#         'c', 'cont', 'continue', 'q', 'quit')
+# )
+
+# def subactoruid2proc(
+#     actor: 'Actor',  # noqa
+#     uid: Tuple[str, str]
+# ) -> trio.Process:
+#     n = actor._actoruid2nursery[uid]
+#     _, proc, _ = n._children[uid]
+#     return proc
+
+# async def hijack_stdin():
+#     log.info(f"Hijacking stdin from {actor.uid}")
+
+#     trap std in and relay to subproc
+#     async_stdin = trio.wrap_file(sys.stdin)
+
+#     async with aclosing(async_stdin):
+#         async for msg in async_stdin:
+#             log.runtime(f"Stdin input:\n{msg}")
+#             # encode to bytes
+#             bmsg = str.encode(msg)
+
+#             # relay bytes to subproc over pipe
+#             # await proc.stdin.send_all(bmsg)
+
+#             if bmsg in _pdb_exit_patterns:
+#                 log.info("Closing stdin hijack")
+#                 break
+
+
+@acm
+async def _acquire_debug_lock(
+    uid: Tuple[str, str]
+
+) -> AsyncIterator[trio.StrictFIFOLock]:
+    '''Acquire a root-actor local FIFO lock which tracks mutex access of
+    the process tree's global debugger breakpoint.
+
+    This lock avoids tty clobbering (by preventing multiple processes
+    reading from stdstreams) and ensures multi-actor, sequential access
+    to the ``pdb`` repl.
+
+    '''
+    global _debug_lock, _global_actor_in_debug, _no_remote_has_tty
+
+    task_name = trio.lowlevel.current_task().name
+
+    log.debug(
+        f"Attempting to acquire TTY lock, remote task: {task_name}:{uid}"
+    )
+
+    we_acquired = False
+
+    if _no_remote_has_tty is None:
+        # mark the tty lock as being in use so that the runtime
+        # can try to avoid clobbering any connection from a child
+        # that's currently relying on it.
+        _no_remote_has_tty = trio.Event()
+
+    try:
+        log.debug(
+            f"entering lock checkpoint, remote task: {task_name}:{uid}"
+        )
+        we_acquired = True
+        await _debug_lock.acquire()
+
+        _global_actor_in_debug = uid
+        log.debug(f"TTY lock acquired, remote task: {task_name}:{uid}")
+
+        # NOTE: critical section: this yield is unshielded!
+
+        # IF we received a cancel during the shielded lock entry of some
+        # next-in-queue requesting task, then the resumption here will
+        # result in that ``trio.Cancelled`` being raised to our caller
+        # (likely from ``_hijack_stdin_for_child()`` below)!  In
+        # this case the ``finally:`` below should trigger and the
+        # surrounding caller side context should cancel normally
+        # relaying back to the caller.
+
+        yield _debug_lock
+
+    finally:
+        # if _global_actor_in_debug == uid:
+        if we_acquired and _debug_lock.locked():
+            _debug_lock.release()
+
+        # IFF there are no more requesting tasks queued up fire, the
+        # "tty-unlocked" event thereby alerting any monitors of the lock that
+        # we are now back in the "tty unlocked" state. This is basically
+        # and edge triggered signal around an empty queue of sub-actor
+        # tasks that may have tried to acquire the lock.
+        stats = _debug_lock.statistics()
+        if (
+            not stats.owner
+        ):
+            log.debug(f"No more tasks waiting on tty lock! says {uid}")
+            _no_remote_has_tty.set()
+            _no_remote_has_tty = None
+
+        _global_actor_in_debug = None
+
+        log.debug(f"TTY lock released, remote task: {task_name}:{uid}")
+
+
+def handler(signum, frame, *args):
+    """Specialized debugger compatible SIGINT handler.
+
+    In childred we always ignore to avoid deadlocks since cancellation
+    should always be managed by the parent supervising actor. The root
+    is always cancelled on ctrl-c.
+    """
+    if is_root_process():
+        tractor.current_actor().cancel_soon()
+    else:
+        print(
+            "tractor ignores SIGINT while in debug mode\n"
+            "If you have a special need for it please open an issue.\n"
+        )
+
+
+@tractor.context
+async def _hijack_stdin_for_child(
+
+    ctx: tractor.Context,
+    subactor_uid: Tuple[str, str]
+
+) -> str:
+    '''
+    Hijack the tty in the root process of an actor tree such that
+    the pdbpp debugger console can be allocated to a sub-actor for repl
+    bossing.
+
+    '''
+    task_name = trio.lowlevel.current_task().name
+
+    # TODO: when we get to true remote debugging
+    # this will deliver stdin data?
+
+    log.debug(
+        "Attempting to acquire TTY lock\n"
+        f"remote task: {task_name}:{subactor_uid}"
+    )
+
+    log.debug(f"Actor {subactor_uid} is WAITING on stdin hijack lock")
+
+    with trio.CancelScope(shield=True):
+
+        try:
+            lock = None
+            async with _acquire_debug_lock(subactor_uid) as lock:
+
+                # indicate to child that we've locked stdio
+                await ctx.started('Locked')
+                log.debug(f"Actor {subactor_uid} acquired stdin hijack lock")
+
+                # wait for unlock pdb by child
+                async with ctx.open_stream() as stream:
+                    assert await stream.receive() == 'pdb_unlock'
+
+                # try:
+                #     assert await stream.receive() == 'pdb_unlock'
+
+        except (
+            # BaseException,
+            trio.MultiError,
+            trio.BrokenResourceError,
+            trio.Cancelled,  # by local cancellation
+            trio.ClosedResourceError,  # by self._rx_chan
+        ) as err:
+            # XXX: there may be a race with the portal teardown
+            # with the calling actor which we can safely ignore.
+            # The alternative would be sending an ack message
+            # and allowing the client to wait for us to teardown
+            # first?
+            if lock and lock.locked():
+                lock.release()
+
+            if isinstance(err, trio.Cancelled):
+                raise
+        finally:
+            log.debug(
+                "TTY lock released, remote task:"
+                f"{task_name}:{subactor_uid}")
+
+    return "pdb_unlock_complete"
+
+
+async def wait_for_parent_stdin_hijack(
+    actor_uid: Tuple[str, str],
+    task_status: TaskStatus[trio.CancelScope] = trio.TASK_STATUS_IGNORED
+):
+    '''
+    Connect to the root actor via a ctx and invoke a task which locks
+    a root-local TTY lock.
+
+    This function is used by any sub-actor to acquire mutex access to
+    pdb and the root's TTY for interactive debugging (see below inside
+    ``_breakpoint()``). It can be used to ensure that an intermediate
+    nursery-owning actor does not clobber its children if they are in
+    debug (see below inside ``maybe_wait_for_debugger()``).
+
+    '''
+    global _debugger_request_cs
+
+    with trio.CancelScope(shield=True) as cs:
+        _debugger_request_cs = cs
+
+        try:
+            async with get_root() as portal:
+
+                # this syncs to child's ``Context.started()`` call.
+                async with portal.open_context(
+
+                    tractor._debug._hijack_stdin_for_child,
+                    subactor_uid=actor_uid,
+
+                ) as (ctx, val):
+
+                    log.pdb('locked context')
+                    assert val == 'Locked'
+
+                    async with ctx.open_stream() as stream:
+                        # unblock local caller
+                        task_status.started(cs)
+
+                        try:
+                            assert _local_pdb_complete
+                            await _local_pdb_complete.wait()
+
+                        finally:
+                            # TODO: shielding currently can cause hangs...
+                            with trio.CancelScope(shield=True):
+                                await stream.send('pdb_unlock')
+
+                        # sync with callee termination
+                        assert await ctx.result() == "pdb_unlock_complete"
+
+        except tractor.ContextCancelled:
+            log.warning('Root actor cancelled debug lock')
+
+        finally:
+            log.debug(f"Exiting debugger for actor {actor_uid}")
+            global _local_task_in_debug
+            _local_task_in_debug = None
+            log.debug(f"Child {actor_uid} released parent stdio lock")
+
+
+async def _breakpoint(
+
+    debug_func,
+
+    # TODO:
+    # shield: bool = False
+
+) -> None:
+    '''``tractor`` breakpoint entry for engaging pdb machinery
+    in the root or a subactor.
+
+    '''
+    # TODO: is it possible to debug a trio.Cancelled except block?
+    # right now it seems like we can kinda do with by shielding
+    # around ``tractor.breakpoint()`` but not if we move the shielded
+    # scope here???
+    # with trio.CancelScope(shield=shield):
+
+    actor = tractor.current_actor()
+    task_name = trio.lowlevel.current_task().name
+
+    global _local_pdb_complete, _pdb_release_hook
+    global _local_task_in_debug, _global_actor_in_debug
+
+    await trio.lowlevel.checkpoint()
+
+    if not _local_pdb_complete or _local_pdb_complete.is_set():
+        _local_pdb_complete = trio.Event()
+
+    # TODO: need a more robust check for the "root" actor
+    if actor._parent_chan and not is_root_process():
+
+        if _local_task_in_debug:
+            if _local_task_in_debug == task_name:
+                # this task already has the lock and is
+                # likely recurrently entering a breakpoint
+                return
+
+            # if **this** actor is already in debug mode block here
+            # waiting for the control to be released - this allows
+            # support for recursive entries to `tractor.breakpoint()`
+            log.warning(f"{actor.uid} already has a debug lock, waiting...")
+
+            await _local_pdb_complete.wait()
+            await trio.sleep(0.1)
+
+        # mark local actor as "in debug mode" to avoid recurrent
+        # entries/requests to the root process
+        _local_task_in_debug = task_name
+
+        # assign unlock callback for debugger teardown hooks
+        _pdb_release_hook = _local_pdb_complete.set
+
+        # this **must** be awaited by the caller and is done using the
+        # root nursery so that the debugger can continue to run without
+        # being restricted by the scope of a new task nursery.
+
+        # NOTE: if we want to debug a trio.Cancelled triggered exception
+        # we have to figure out how to avoid having the service nursery
+        # cancel on this task start? I *think* this works below?
+        # actor._service_n.cancel_scope.shield = shield
+        with trio.CancelScope(shield=True):
+            await actor._service_n.start(
+                wait_for_parent_stdin_hijack,
+                actor.uid,
+            )
+
+    elif is_root_process():
+
+        # we also wait in the root-parent for any child that
+        # may have the tty locked prior
+        global _debug_lock
+
+        # TODO: wait, what about multiple root tasks acquiring it though?
+        # root process (us) already has it; ignore
+        if _global_actor_in_debug == actor.uid:
+            return
+
+        # XXX: since we need to enter pdb synchronously below,
+        # we have to release the lock manually from pdb completion
+        # callbacks. Can't think of a nicer way then this atm.
+        if _debug_lock.locked():
+            log.warning(
+                'Root actor attempting to shield-acquire active tty lock'
+                f' owned by {_global_actor_in_debug}')
+
+            # must shield here to avoid hitting a ``Cancelled`` and
+            # a child getting stuck bc we clobbered the tty
+            with trio.CancelScope(shield=True):
+                await _debug_lock.acquire()
+        else:
+            # may be cancelled
+            await _debug_lock.acquire()
+
+        _global_actor_in_debug = actor.uid
+        _local_task_in_debug = task_name
+
+        # the lock must be released on pdb completion
+        def teardown():
+            global _local_pdb_complete, _debug_lock
+            global _global_actor_in_debug, _local_task_in_debug
+
+            _debug_lock.release()
+            _global_actor_in_debug = None
+            _local_task_in_debug = None
+            _local_pdb_complete.set()
+
+        _pdb_release_hook = teardown
+
+    # block here one (at the appropriate frame *up*) where
+    # ``breakpoint()`` was awaited and begin handling stdio.
+    log.debug("Entering the synchronous world of pdb")
+    debug_func(actor)
+
+
+def _mk_pdb() -> PdbwTeardown:
+
+    # XXX: setting these flags on the pdb instance are absolutely
+    # critical to having ctrl-c work in the ``trio`` standard way!  The
+    # stdlib's pdb supports entering the current sync frame on a SIGINT,
+    # with ``trio`` we pretty much never want this and if we did we can
+    # handle it in the ``tractor`` task runtime.
+
+    pdb = PdbwTeardown()
+    pdb.allow_kbdint = True
+    pdb.nosigint = True
+
+    return pdb
+
+
+def _set_trace(actor=None):
+    pdb = _mk_pdb()
+
+    if actor is not None:
+        log.pdb(f"\nAttaching pdb to actor: {actor.uid}\n")
+
+        pdb.set_trace(
+            # start 2 levels up in user code
+            frame=sys._getframe().f_back.f_back,
+        )
+
+    else:
+        # we entered the global ``breakpoint()`` built-in from sync code
+        global _local_task_in_debug, _pdb_release_hook
+        _local_task_in_debug = 'sync'
+
+        def nuttin():
+            pass
+
+        _pdb_release_hook = nuttin
+
+        pdb.set_trace(
+            # start 2 levels up in user code
+            frame=sys._getframe().f_back,
+        )
+
+
+breakpoint = partial(
+    _breakpoint,
+    _set_trace,
+)
+
+
+def _post_mortem(actor):
+    log.pdb(f"\nAttaching to pdb in crashed actor: {actor.uid}\n")
+    pdb = _mk_pdb()
+
+    # custom Pdb post-mortem entry
+    pdbpp.xpm(Pdb=lambda: pdb)
+
+
+post_mortem = partial(
+    _breakpoint,
+    _post_mortem,
+)
+
+
+async def _maybe_enter_pm(err):
+    if (
+        debug_mode()
+
+        # NOTE: don't enter debug mode recursively after quitting pdb
+        # Iow, don't re-enter the repl if the `quit` command was issued
+        # by the user.
+        and not isinstance(err, bdb.BdbQuit)
+
+        # XXX: if the error is the likely result of runtime-wide
+        # cancellation, we don't want to enter the debugger since
+        # there's races between when the parent actor has killed all
+        # comms and when the child tries to contact said parent to
+        # acquire the tty lock.
+
+        # Really we just want to mostly avoid catching KBIs here so there
+        # might be a simpler check we can do?
+        and not is_multi_cancelled(err)
+    ):
+        log.debug("Actor crashed, entering debug mode")
+        await post_mortem()
+        return True
+
+    else:
+        return False
+
+
+@acm
+async def acquire_debug_lock(
+    subactor_uid: Tuple[str, str],
+) -> AsyncGenerator[None, tuple]:
+    '''
+    Grab root's debug lock on entry, release on exit.
+
+    This helper is for actor's who don't actually need
+    to acquired the debugger but want to wait until the
+    lock is free in the tree root.
+
+    '''
+    if not debug_mode():
+        yield None
+        return
+
+    async with trio.open_nursery() as n:
+        cs = await n.start(
+            wait_for_parent_stdin_hijack,
+            subactor_uid,
+        )
+        yield None
+        cs.cancel()
+
+
+async def maybe_wait_for_debugger(
+    poll_steps: int = 2,
+    poll_delay: float = 0.1,
+    child_in_debug: bool = False,
+
+) -> None:
+
+    if not debug_mode() and not child_in_debug:
+        return
+
+    if (
+        is_root_process()
+    ):
+        global _no_remote_has_tty, _global_actor_in_debug, _wait_all_tasks_lock
+
+        # If we error in the root but the debugger is
+        # engaged we don't want to prematurely kill (and
+        # thus clobber access to) the local tty since it
+        # will make the pdb repl unusable.
+        # Instead try to wait for pdb to be released before
+        # tearing down.
+
+        sub_in_debug = None
+
+        for _ in range(poll_steps):
+
+            if _global_actor_in_debug:
+                sub_in_debug = tuple(_global_actor_in_debug)
+
+            log.debug(
+                'Root polling for debug')
+
+            with trio.CancelScope(shield=True):
+                await trio.sleep(poll_delay)
+
+                # TODO: could this make things more deterministic?  wait
+                # to see if a sub-actor task will be scheduled and grab
+                # the tty lock on the next tick?
+                # XXX: doesn't seem to work
+                # await trio.testing.wait_all_tasks_blocked(cushion=0)
+
+                debug_complete = _no_remote_has_tty
+                if (
+                    (debug_complete and
+                     not debug_complete.is_set())
+                ):
+                    log.debug(
+                        'Root has errored but pdb is in use by '
+                        f'child {sub_in_debug}\n'
+                        'Waiting on tty lock to release..')
+
+                    await debug_complete.wait()
+
+                await trio.sleep(poll_delay)
+                continue
+        else:
+            log.debug(
+                    'Root acquired TTY LOCK'
+            )

tractor/_discovery.py

@@ -15,71 +15,46 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 """
-Discovery (protocols) API for automatic addressing and location
-management of (service) actors.
+Actor discovery API.
 
 """
-from __future__ import annotations
-from typing import (
-    AsyncGenerator,
-    AsyncContextManager,
-    TYPE_CHECKING,
-)
+from typing import Tuple, Optional, Union, AsyncGenerator
 from contextlib import asynccontextmanager as acm
 
-from tractor.log import get_logger
-from .trionics import gather_contexts
 from ._ipc import _connect_chan, Channel
 from ._portal import (
     Portal,
     open_portal,
     LocalPortal,
 )
-from ._state import (
-    current_actor,
-    _runtime_vars,
-)
-
-if TYPE_CHECKING:
-    from ._runtime import Actor
-
-
-log = get_logger(__name__)
+from ._state import current_actor, _runtime_vars
 
 
 @acm
-async def get_registry(
+async def get_arbiter(
+
     host: str,
     port: int,
 
-) -> AsyncGenerator[
-    Portal | LocalPortal | None,
-    None,
-]:
+) -> AsyncGenerator[Union[Portal, LocalPortal], None]:
+    '''Return a portal instance connected to a local or remote
+    arbiter.
     '''
-    Return a portal instance connected to a local or remote
-    registry-service actor; if a connection already exists re-use it
-    (presumably to call a `.register_actor()` registry runtime RPC
-    ep).
+    actor = current_actor()
 
-    '''
-    actor: Actor = current_actor()
-    if actor.is_registrar:
+    if not actor:
+        raise RuntimeError("No actor instance has been defined yet?")
+
+    if actor.is_arbiter:
         # we're already the arbiter
         # (likely a re-entrant call from the arbiter actor)
-        yield LocalPortal(
-            actor,
-            Channel((host, port))
-        )
+        yield LocalPortal(actor, Channel((host, port)))
     else:
-        # TODO: try to look pre-existing connection from
-        # `Actor._peers` and use it instead?
-        async with (
-            _connect_chan(host, port) as chan,
-            open_portal(chan) as regstr_ptl,
-        ):
-            yield regstr_ptl
+        async with _connect_chan(host, port) as chan:
 
+            async with open_portal(chan) as arb_portal:
+
+                yield arb_portal
 
 
 @acm
@@ -87,125 +62,51 @@ async def get_root(
     **kwargs,
 ) -> AsyncGenerator[Portal, None]:
 
-    # TODO: rename mailbox to `_root_maddr` when we finally
-    # add and impl libp2p multi-addrs?
     host, port = _runtime_vars['_root_mailbox']
     assert host is not None
 
-    async with (
-        _connect_chan(host, port) as chan,
-        open_portal(chan, **kwargs) as portal,
-    ):
-        yield portal
-
-
-def get_peer_by_name(
-    name: str,
-    # uuid: str|None = None,
-
-) -> list[Channel]|None:  # at least 1
-    '''
-    Scan for an existing connection (set) to a named actor
-    and return any channels from `Actor._peers`.
-
-    This is an optimization method over querying the registrar for
-    the same info.
-
-    '''
-    actor: Actor = current_actor()
-    to_scan: dict[tuple, list[Channel]] = actor._peers.copy()
-    pchan: Channel|None = actor._parent_chan
-    if pchan:
-        to_scan[pchan.uid].append(pchan)
-
-    for aid, chans in to_scan.items():
-        _, peer_name = aid
-        if name == peer_name:
-            if not chans:
-                log.warning(
-                    'No IPC chans for matching peer {peer_name}\n'
-                )
-                continue
-            return chans
-
-    return None
+    async with _connect_chan(host, port) as chan:
+        async with open_portal(chan, **kwargs) as portal:
+            yield portal
 
 
 @acm
 async def query_actor(
     name: str,
-    regaddr: tuple[str, int]|None = None,
+    arbiter_sockaddr: Optional[tuple[str, int]] = None,
 
-) -> AsyncGenerator[
-    tuple[str, int]|None,
-    None,
-]:
+) -> AsyncGenerator[tuple[str, int], None]:
     '''
-    Lookup a transport address (by actor name) via querying a registrar
-    listening @ `regaddr`.
+    Simple address lookup for a given actor name.
 
-    Returns the transport protocol (socket) address or `None` if no
-    entry under that name exists.
+    Returns the (socket) address or ``None``.
 
     '''
-    actor: Actor = current_actor()
-    if (
-        name == 'registrar'
-        and actor.is_registrar
-    ):
-        raise RuntimeError(
-            'The current actor IS the registry!?'
-        )
+    actor = current_actor()
+    async with get_arbiter(
+        *arbiter_sockaddr or actor._arb_addr
+    ) as arb_portal:
 
-    maybe_peers: list[Channel]|None = get_peer_by_name(name)
-    if maybe_peers:
-        yield maybe_peers[0].raddr
-        return
-
-    reg_portal: Portal
-    regaddr: tuple[str, int] = regaddr or actor.reg_addrs[0]
-    async with get_registry(*regaddr) as reg_portal:
-        # TODO: return portals to all available actors - for now
-        # just the last one that registered
-        sockaddr: tuple[str, int] = await reg_portal.run_from_ns(
+        sockaddr = await arb_portal.run_from_ns(
             'self',
             'find_actor',
             name=name,
         )
-        yield sockaddr
 
+        # 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")
 
-@acm
-async def maybe_open_portal(
-    addr: tuple[str, int],
-    name: str,
-):
-    async with query_actor(
-        name=name,
-        regaddr=addr,
-    ) as sockaddr:
-        pass
-
-    if sockaddr:
-        async with _connect_chan(*sockaddr) as chan:
-            async with open_portal(chan) as portal:
-                yield portal
-    else:
-        yield None
+        yield sockaddr if sockaddr else None
 
 
 @acm
 async def find_actor(
     name: str,
-    registry_addrs: list[tuple[str, int]]|None = None,
+    arbiter_sockaddr: Tuple[str, int] = None
 
-    only_first: bool = True,
-    raise_on_none: bool = False,
-
-) -> AsyncGenerator[
-    Portal | list[Portal] | None,
-    None,
-]:
+) -> AsyncGenerator[Optional[Portal], None]:
     '''
     Ask the arbiter to find actor(s) by name.
 
@@ -213,102 +114,39 @@ async def find_actor(
     known to the arbiter.
 
     '''
-    # optimization path, use any pre-existing peer channel
-    maybe_peers: list[Channel]|None = get_peer_by_name(name)
-    if maybe_peers and only_first:
-        async with open_portal(maybe_peers[0]) as peer_portal:
-            yield peer_portal
-            return
-
-    if not registry_addrs:
-        # XXX NOTE: make sure to dynamically read the value on
-        # every call since something may change it globally (eg.
-        # like in our discovery test suite)!
-        from . import _root
-        registry_addrs = (
-            _runtime_vars['_registry_addrs']
-            or
-            _root._default_lo_addrs
-        )
-
-    maybe_portals: list[
-        AsyncContextManager[tuple[str, int]]
-    ] = list(
-        maybe_open_portal(
-            addr=addr,
-            name=name,
-        )
-        for addr in registry_addrs
-    )
-    portals: list[Portal]
-    async with gather_contexts(
-        mngrs=maybe_portals,
-    ) as portals:
-        # log.runtime(
-        #     'Gathered portals:\n'
-        #     f'{portals}'
-        # )
-        # NOTE: `gather_contexts()` will return a
-        # `tuple[None, None, ..., None]` if no contact
-        # can be made with any regstrar at any of the
-        # N provided addrs!
-        if not any(portals):
-            if raise_on_none:
-                raise RuntimeError(
-                    f'No actor "{name}" found registered @ {registry_addrs}'
-                )
-            yield None
-            return
-
-        portals: list[Portal] = list(portals)
-        if only_first:
-            yield portals[0]
+    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
         else:
-            # TODO: currently this may return multiple portals
-            # given there are multi-homed or multiple registrars..
-            # SO, we probably need de-duplication logic?
-            yield portals
+            yield None
 
 
 @acm
 async def wait_for_actor(
     name: str,
-    registry_addr: tuple[str, int] | None = None,
-
+    arbiter_sockaddr: Tuple[str, int] = None
 ) -> AsyncGenerator[Portal, None]:
-    '''
-    Wait on at least one peer actor to register `name` with the
-    registrar, yield a `Portal to the first registree.
+    """Wait on an actor to register with the arbiter.
 
-    '''
-    actor: Actor = current_actor()
+    A portal to the first registered actor is returned.
+    """
+    actor = current_actor()
 
-    # optimization path, use any pre-existing peer channel
-    maybe_peers: list[Channel]|None = get_peer_by_name(name)
-    if maybe_peers:
-        async with open_portal(maybe_peers[0]) as peer_portal:
-            yield peer_portal
-            return
-
-    regaddr: tuple[str, int] = (
-        registry_addr
-        or
-        actor.reg_addrs[0]
-    )
-    # TODO: use `.trionics.gather_contexts()` like
-    # above in `find_actor()` as well?
-    reg_portal: Portal
-    async with get_registry(*regaddr) as reg_portal:
-        sockaddrs = await reg_portal.run_from_ns(
+    async with get_arbiter(
+        *arbiter_sockaddr or actor._arb_addr,
+    ) as arb_portal:
+        sockaddrs = await arb_portal.run_from_ns(
             'self',
             'wait_for_actor',
             name=name,
         )
-
-        # get latest registered addr by default?
-        # TODO: offer multi-portal yields in multi-homed case?
-        sockaddr: tuple[str, int] = sockaddrs[-1]
+        sockaddr = sockaddrs[-1]
 
         async with _connect_chan(*sockaddr) as chan:
             async with open_portal(chan) as portal:

tractor/_entry.py

@@ -18,32 +18,15 @@
 Sub-process entry points.
 
 """
-from __future__ import annotations
 from functools import partial
-import multiprocessing as mp
-import os
-import textwrap
-from typing import (
-    Any,
-    TYPE_CHECKING,
-)
+from typing import Tuple, Any
+import signal
 
 import trio  # type: ignore
 
-from .log import (
-    get_console_log,
-    get_logger,
-)
+from .log import get_console_log, get_logger
 from . import _state
-from .devx import _debug
 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__)
@@ -51,40 +34,37 @@ log = get_logger(__name__)
 
 def _mp_main(
 
-    actor: Actor,
-    accept_addrs: list[tuple[str, int]],
-    forkserver_info: tuple[Any, Any, Any, Any, Any],
-    start_method: SpawnMethodKey,
-    parent_addr: tuple[str, int] | None = None,
+    actor: 'Actor',  # type: ignore
+    accept_addr: Tuple[str, int],
+    forkserver_info: Tuple[Any, Any, Any, Any, Any],
+    start_method: str,
+    parent_addr: Tuple[str, int] = None,
     infect_asyncio: bool = False,
 
 ) -> None:
     '''
-    The routine called *after fork* which invokes a fresh `trio.run()`
+    The routine called *after fork* which invokes a fresh ``trio.run``
 
     '''
     actor._forkserver_info = forkserver_info
     from ._spawn import try_set_start_method
-    spawn_ctx: mp.context.BaseContext = try_set_start_method(start_method)
-    assert spawn_ctx
+    spawn_ctx = try_set_start_method(start_method)
 
     if actor.loglevel is not None:
         log.info(
-            f'Setting loglevel for {actor.uid} to {actor.loglevel}'
-        )
+            f"Setting loglevel for {actor.uid} to {actor.loglevel}")
         get_console_log(actor.loglevel)
 
-    # TODO: use scops headers like for `trio` below!
-    # (well after we libify it maybe..)
+    assert spawn_ctx
     log.info(
-        f'Started new {spawn_ctx.current_process()} for {actor.uid}'
-    #     f"parent_addr is {parent_addr}"
-    )
-    _state._current_actor: Actor = actor
+        f"Started new {spawn_ctx.current_process()} for {actor.uid}")
+
+    _state._current_actor = actor
+
+    log.debug(f"parent_addr is {parent_addr}")
     trio_main = partial(
-        async_main,
-        actor=actor,
-        accept_addrs=accept_addrs,
+        actor._async_main,
+        accept_addr,
         parent_addr=parent_addr
     )
     try:
@@ -97,116 +77,14 @@ def _mp_main(
         pass  # handle it the same way trio does?
 
     finally:
-        log.info(
-            f'`mp`-subactor {actor.uid} exited'
-        )
-
-
-# TODO: move this func to some kinda `.devx._conc_lang.py` eventually
-# as we work out our multi-domain state-flow-syntax!
-def nest_from_op(
-    input_op: str,
-    #
-    # ?TODO? an idea for a syntax to the state of concurrent systems
-    # as a "3-domain" (execution, scope, storage) model and using
-    # a minimal ascii/utf-8 operator-set.
-    #
-    # try not to take any of this seriously yet XD
-    #
-    # > is a "play operator" indicating (CPU bound)
-    #   exec/work/ops required at the "lowest level computing"
-    #
-    # execution primititves (tasks, threads, actors..) denote their
-    # lifetime with '(' and ')' since parentheses normally are used
-    # in many langs to denote function calls.
-    #
-    # starting = (
-    # >(  opening/starting; beginning of the thread-of-exec (toe?)
-    # (>  opened/started,  (finished spawning toe)
-    # |_<Task: blah blah..>  repr of toe, in py these look like <objs>
-    #
-    # >) closing/exiting/stopping,
-    # )> closed/exited/stopped,
-    # |_<Task: blah blah..>
-    #   [OR <), )< ?? ]
-    #
-    # ending = )
-    # >c) cancelling to close/exit
-    # c)> cancelled (caused close), OR?
-    #  |_<Actor: ..>
-    #   OR maybe "<c)" which better indicates the cancel being
-    #   "delivered/returned" / returned" to LHS?
-    #
-    # >x)  erroring to eventuall exit
-    # x)>  errored and terminated
-    #  |_<Actor: ...>
-    #
-    # scopes: supers/nurseries, IPC-ctxs, sessions, perms, etc.
-    # >{  opening
-    # {>  opened
-    # }>  closed
-    # >}  closing
-    #
-    # storage: like queues, shm-buffers, files, etc..
-    # >[  opening
-    # [>  opened
-    #  |_<FileObj: ..>
-    #
-    # >]  closing
-    # ]>  closed
-
-    # IPC ops: channels, transports, msging
-    # =>  req msg
-    # <=  resp msg
-    # <=> 2-way streaming (of msgs)
-    # <-  recv 1 msg
-    # ->  send 1 msg
-    #
-    # TODO: still not sure on R/L-HS approach..?
-    # =>(  send-req to exec start (task, actor, thread..)
-    # (<=  recv-req to ^
-    #
-    # (<=  recv-req ^
-    # <=(  recv-resp opened remote exec primitive
-    # <=)  recv-resp closed
-    #
-    # )<=c req to stop due to cancel
-    # c=>) req to stop due to cancel
-    #
-    # =>{  recv-req to open
-    # <={  send-status that it closed
-
-    tree_str: str,
-
-    # NOTE: so move back-from-the-left of the `input_op` by
-    # this amount.
-    back_from_op: int = 0,
-) -> str:
-    '''
-    Depth-increment the input (presumably hierarchy/supervision)
-    input "tree string" below the provided `input_op` execution
-    operator, so injecting a `"\n|_{input_op}\n"`and indenting the
-    `tree_str` to nest content aligned with the ops last char.
-
-    '''
-    return (
-        f'{input_op}\n'
-        +
-        textwrap.indent(
-            tree_str,
-            prefix=(
-                len(input_op)
-                -
-                (back_from_op + 1)
-            ) * ' ',
-        )
-    )
+        log.info(f"Actor {actor.uid} terminated")
 
 
 def _trio_main(
-    actor: Actor,
+
+    actor: 'Actor',  # type: ignore
     *,
-    parent_addr: tuple[str, int] | None = None,
+    parent_addr: Tuple[str, int] = None,
     infect_asyncio: bool = False,
 
 ) -> None:
@@ -214,73 +92,32 @@ def _trio_main(
     Entry point for a `trio_run_in_process` subactor.
 
     '''
-    _debug.hide_runtime_frames()
+    log.info(f"Started new trio process for {actor.uid}")
+
+    if actor.loglevel is not None:
+        log.info(
+            f"Setting loglevel for {actor.uid} to {actor.loglevel}")
+        get_console_log(actor.loglevel)
+
+    log.info(
+        f"Started {actor.uid}")
 
     _state._current_actor = actor
+
+    log.debug(f"parent_addr is {parent_addr}")
     trio_main = partial(
-        async_main,
-        actor,
+        actor._async_main,
         parent_addr=parent_addr
     )
 
-    if actor.loglevel is not None:
-        get_console_log(actor.loglevel)
-        actor_info: str = (
-            f'|_{actor}\n'
-            f'  uid: {actor.uid}\n'
-            f'  pid: {os.getpid()}\n'
-            f'  parent_addr: {parent_addr}\n'
-            f'  loglevel: {actor.loglevel}\n'
-        )
-        log.info(
-            'Starting new `trio` subactor:\n'
-            +
-            nest_from_op(
-                input_op='>(',  # see syntax ideas above
-                tree_str=actor_info,
-                back_from_op=2,  # since "complete"
-            )
-        )
-    logmeth = log.info
-    exit_status: str = (
-        'Subactor exited\n'
-        +
-        nest_from_op(
-            input_op=')>',  # like a "closed-to-play"-icon from super perspective
-            tree_str=actor_info,
-            back_from_op=1,
-        )
-    )
     try:
         if infect_asyncio:
             actor._infected_aio = True
             run_as_asyncio_guest(trio_main)
         else:
             trio.run(trio_main)
-
     except KeyboardInterrupt:
-        logmeth = log.cancel
-        exit_status: str = (
-            'Actor received KBI (aka an OS-cancel)\n'
-            +
-            nest_from_op(
-                input_op='c)>',  # closed due to cancel (see above)
-                tree_str=actor_info,
-            )
-        )
-    except BaseException as err:
-        logmeth = log.error
-        exit_status: str = (
-            'Main actor task exited due to crash?\n'
-            +
-            nest_from_op(
-                input_op='x)>',  # closed by error
-                tree_str=actor_info,
-            )
-        )
-        # NOTE since we raise a tb will already be shown on the
-        # console, thus we do NOT use `.exception()` above.
-        raise err
+        log.warning(f"Actor {actor.uid} received KBI")
 
     finally:
-        logmeth(exit_status)
+        log.info(f"Actor {actor.uid} terminated")

tractor/_ipc.py

@@ -19,64 +19,31 @@ Inter-process comms abstractions
 
 """
 from __future__ import annotations
-from collections.abc import (
-    AsyncGenerator,
-    AsyncIterator,
-)
-from contextlib import (
-    asynccontextmanager as acm,
-    contextmanager as cm,
-)
 import platform
-from pprint import pformat
 import struct
 import typing
+from collections.abc import AsyncGenerator, AsyncIterator
 from typing import (
-    Any,
-    Callable,
-    runtime_checkable,
-    Protocol,
-    Type,
-    TypeVar,
+    Any, Tuple, Optional,
+    Type, Protocol, TypeVar,
 )
 
-import msgspec
 from tricycle import BufferedReceiveStream
+import msgpack
 import trio
+from async_generator import asynccontextmanager
 
-from tractor.log import get_logger
-from tractor._exceptions import (
-    MsgTypeError,
-    pack_from_raise,
-    TransportClosed,
-    _mk_send_mte,
-    _mk_recv_mte,
-)
-from tractor.msg import (
-    _ctxvar_MsgCodec,
-    # _codec,  XXX see `self._codec` sanity/debug checks
-    MsgCodec,
-    types as msgtypes,
-    pretty_struct,
-)
-
+from .log import get_logger
+from ._exceptions import TransportClosed
 log = get_logger(__name__)
 
+
 _is_windows = platform.system() == 'Windows'
+log = get_logger(__name__)
 
 
-def get_stream_addrs(
-    stream: trio.SocketStream
-) -> tuple[
-    tuple[str, int],  # local
-    tuple[str, int],  # remote
-]:
-    '''
-    Return the `trio` streaming transport prot's socket-addrs for
-    both the local and remote sides as a pair.
-
-    '''
-    # rn, should both be IP sockets
+def get_stream_addrs(stream: trio.SocketStream) -> Tuple:
+    # should both be IP sockets
     lsockname = stream.socket.getsockname()
     rsockname = stream.socket.getpeername()
     return (
@@ -85,22 +52,15 @@ def get_stream_addrs(
     )
 
 
-# from tractor.msg.types import MsgType
-# ?TODO? this should be our `Union[*msgtypes.__spec__]` alias now right..?
-# => BLEH, except can't bc prots must inherit typevar or param-spec
-#   vars..
-MsgType = TypeVar('MsgType')
+MsgType = TypeVar("MsgType")
 
-
-# TODO: break up this mod into a subpkg so we can start adding new
-# backends and move this type stuff into a dedicated file.. Bo
-#
-@runtime_checkable
-class MsgTransport(Protocol[MsgType]):
-#
-# ^-TODO-^ consider using a generic def and indexing with our
-# eventual msg definition/types?
+# TODO: consider using a generic def and indexing with our eventual
+# msg definition/types?
 # - https://docs.python.org/3/library/typing.html#typing.Protocol
+# - https://jcristharif.com/msgspec/usage.html#structs
+
+
+class MsgTransport(Protocol[MsgType]):
 
     stream: trio.SocketStream
     drained: list[MsgType]
@@ -127,44 +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: typing oddity.. not sure why we have to inherit here, but it
-# seems to be an issue with `get_msg_transport()` returning
-# a `Type[Protocol]`; probably should make a `mypy` issue?
-class MsgpackTCPStream(MsgTransport):
+class MsgpackTCPStream:
     '''
     A ``trio.SocketStream`` delivering ``msgpack`` formatted data
-    using the ``msgspec`` codec lib.
+    using ``msgpack-python``.
 
     '''
-    layer_key: int = 4
-    name_key: str = 'tcp'
-
-    # TODO: better naming for this?
-    # -[ ] check how libp2p does naming for such things?
-    codec_key: str = 'msgpack'
-
     def __init__(
         self,
         stream: trio.SocketStream,
-        prefix_size: int = 4,
-
-        # XXX optionally provided codec pair for `msgspec`:
-        # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
-        #
-        # TODO: define this as a `Codec` struct which can be
-        # overriden dynamically by the application/runtime?
-        codec: tuple[
-            Callable[[Any], Any]|None,  # coder
-            Callable[[type, Any], Any]|None,  # decoder
-        ]|None = None,
 
     ) -> None:
 
@@ -175,277 +114,74 @@ class MsgpackTCPStream(MsgTransport):
         self._laddr, self._raddr = get_stream_addrs(stream)
 
         # create read loop instance
-        self._aiter_pkts = self._iter_packets()
+        self._agen = self._iter_packets()
         self._send_lock = trio.StrictFIFOLock()
 
         # public i guess?
         self.drained: list[dict] = []
 
-        self.recv_stream = BufferedReceiveStream(
-            transport_stream=stream
-        )
-        self.prefix_size = prefix_size
-
-        # allow for custom IPC msg interchange format
-        # dynamic override Bo
-        self._task = trio.lowlevel.current_task()
-
-        # XXX for ctxvar debug only!
-        # self._codec: MsgCodec = (
-        #     codec
-        #     or
-        #     _codec._ctxvar_MsgCodec.get()
-        # )
-
     async def _iter_packets(self) -> AsyncGenerator[dict, None]:
         '''
-        Yield `bytes`-blob decoded packets from the underlying TCP
-        stream using the current task's `MsgCodec`.
-
-        This is a streaming routine implemented as an async generator
-        func (which was the original design, but could be changed?)
-        and is allocated by a `.__call__()` inside `.__init__()` where
-        it is assigned to the `._aiter_pkts` attr.
+        Yield packets from the underlying stream.
 
         '''
-        decodes_failed: int = 0
-
+        unpacker = msgpack.Unpacker(
+            raw=False,
+        )
         while True:
             try:
-                header: bytes = await self.recv_stream.receive_exactly(4)
-            except (
-                ValueError,
-                ConnectionResetError,
+                data = await self.stream.receive_some(2**10)
 
-                # 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,
+            except trio.BrokenResourceError as err:
+                msg = err.args[0]
 
-            ) as trans_err:
+                # XXX: handle connection-reset-by-peer the same as a EOF.
+                # we're currently remapping this since we allow
+                # a quick connect then drop for root actors when
+                # checking to see if there exists an "arbiter"
+                # on the chosen sockaddr (``_root.py:108`` or thereabouts)
+                if (
+                    # nix
+                    '[Errno 104]' in msg or
 
-                loglevel = 'transport'
-                match trans_err:
-                    # case (
-                    #     ConnectionResetError()
-                    # ):
-                    #     loglevel = 'transport'
-
-                    # peer actor (graceful??) TCP EOF but `tricycle`
-                    # seems to raise a 0-bytes-read?
-                    case ValueError() if (
-                        'unclean EOF' in trans_err.args[0]
-                    ):
-                        pass
-
-                    # peer actor (task) prolly shutdown quickly due
-                    # to cancellation
-                    case trio.BrokenResourceError() if (
-                        'Connection reset by peer' in trans_err.args[0]
-                    ):
-                        pass
-
-                    # unless the disconnect condition falls under "a
-                    # normal operation breakage" we usualy console warn
-                    # about it.
-                    case _:
-                        loglevel: str = 'warning'
-
-
-                raise TransportClosed(
-                    message=(
-                        f'IPC transport already closed by peer\n'
-                        f'x]> {type(trans_err)}\n'
-                        f'  |_{self}\n'
-                    ),
-                    loglevel=loglevel,
-                ) from trans_err
-
-            # XXX definitely can happen if transport is closed
-            # manually by another `trio.lowlevel.Task` in the
-            # same actor; we use this in some simulated fault
-            # testing for ex, but generally should never happen
-            # under normal operation!
-            #
-            # NOTE: as such we always re-raise this error from the
-            #       RPC msg loop!
-            except trio.ClosedResourceError as closure_err:
-                raise TransportClosed(
-                    message=(
-                        f'IPC transport already manually closed locally?\n'
-                        f'x]> {type(closure_err)} \n'
-                        f'  |_{self}\n'
-                    ),
-                    loglevel='error',
-                    raise_on_report=(
-                        closure_err.args[0] == 'another task closed this fd'
-                        or
-                        closure_err.args[0] in ['another task closed this fd']
-                    ),
-                ) from closure_err
-
-            # graceful TCP EOF disconnect
-            if header == b'':
-                raise TransportClosed(
-                    message=(
-                        f'IPC transport already gracefully closed\n'
-                        f']>\n'
-                        f' |_{self}\n'
-                    ),
-                    loglevel='transport',
-                    # cause=???  # handy or no?
-                )
-
-            size: int
-            size, = struct.unpack("<I", header)
-
-            log.transport(f'received header {size}')  # type: ignore
-            msg_bytes: bytes = await self.recv_stream.receive_exactly(size)
-
-            log.transport(f"received {msg_bytes}")  # type: ignore
-            try:
-                # NOTE: lookup the `trio.Task.context`'s var for
-                # the current `MsgCodec`.
-                codec: MsgCodec = _ctxvar_MsgCodec.get()
-
-                # XXX for ctxvar debug only!
-                # if self._codec.pld_spec != codec.pld_spec:
-                #     assert (
-                #         task := trio.lowlevel.current_task()
-                #     ) is not self._task
-                #     self._task = task
-                #     self._codec = codec
-                #     log.runtime(
-                #         f'Using new codec in {self}.recv()\n'
-                #         f'codec: {self._codec}\n\n'
-                #         f'msg_bytes: {msg_bytes}\n'
-                #     )
-                yield codec.decode(msg_bytes)
-
-            # XXX NOTE: since the below error derives from
-            # `DecodeError` we need to catch is specially
-            # and always raise such that spec violations
-            # are never allowed to be caught silently!
-            except msgspec.ValidationError as verr:
-                msgtyperr: MsgTypeError = _mk_recv_mte(
-                    msg=msg_bytes,
-                    codec=codec,
-                    src_validation_error=verr,
-                )
-                # XXX deliver up to `Channel.recv()` where
-                # a re-raise and `Error`-pack can inject the far
-                # end actor `.uid`.
-                yield msgtyperr
-
-            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.exception(
-                        'Failed to decode msg?\n'
-                        f'{codec}\n\n'
-                        'Rxed bytes from wire:\n\n'
-                        f'{msg_str!r}\n'
+                    # on windows it seems there are a variety of errors
+                    # to handle..
+                    _is_windows
+                ):
+                    raise TransportClosed(
+                        f'{self} was broken with {msg}'
                     )
-                    decodes_failed += 1
+
                 else:
                     raise
 
-    async def send(
-        self,
-        msg: msgtypes.MsgType,
+            log.transport(f"received {data}")  # type: ignore
 
-        strict_types: bool = True,
-        hide_tb: bool = False,
-
-    ) -> None:
-        '''
-        Send a msgpack encoded py-object-blob-as-msg over TCP.
-
-        If `strict_types == True` then a `MsgTypeError` will be raised on any
-        invalid msg type
-
-        '''
-        __tracebackhide__: bool = hide_tb
-
-        # XXX see `trio._sync.AsyncContextManagerMixin` for details
-        # on the `.acquire()`/`.release()` sequencing..
-        async with self._send_lock:
-
-            # NOTE: lookup the `trio.Task.context`'s var for
-            # the current `MsgCodec`.
-            codec: MsgCodec = _ctxvar_MsgCodec.get()
-
-            # XXX for ctxvar debug only!
-            # if self._codec.pld_spec != codec.pld_spec:
-            #     self._codec = codec
-            #     log.runtime(
-            #         f'Using new codec in {self}.send()\n'
-            #         f'codec: {self._codec}\n\n'
-            #         f'msg: {msg}\n'
-            #     )
-
-            if type(msg) not in msgtypes.__msg_types__:
-                if strict_types:
-                    raise _mk_send_mte(
-                        msg,
-                        codec=codec,
-                    )
-                else:
-                    log.warning(
-                        'Sending non-`Msg`-spec msg?\n\n'
-                        f'{msg}\n'
-                    )
-
-            try:
-                bytes_data: bytes = codec.encode(msg)
-            except TypeError as _err:
-                typerr = _err
-                msgtyperr: MsgTypeError = _mk_send_mte(
-                    msg,
-                    codec=codec,
-                    message=(
-                        f'IPC-msg-spec violation in\n\n'
-                        f'{pretty_struct.Struct.pformat(msg)}'
-                    ),
-                    src_type_error=typerr,
+            if data == b'':
+                raise TransportClosed(
+                    f'transport {self} was already closed prior to read'
                 )
-                raise msgtyperr from typerr
 
-            # 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)
-
-        # ?TODO? does it help ever to dynamically show this
-        # frame?
-        # try:
-        #     <the-above_code>
-        # except BaseException as _err:
-        #     err = _err
-        #     if not isinstance(err, MsgTypeError):
-        #         __tracebackhide__: bool = False
-        #     raise
+            unpacker.feed(data)
+            for packet in unpacker:
+                yield packet
 
     @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._aiter_pkts.asend(None)
+        return await self._agen.asend(None)
 
     async def drain(self) -> AsyncIterator[dict]:
         '''
@@ -462,20 +198,105 @@ class MsgpackTCPStream(MsgTransport):
                 yield msg
 
     def __aiter__(self):
-        return self._aiter_pkts
+        return self._agen
 
     def connected(self) -> bool:
         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.DecodeError,
+                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]
 
 
@@ -484,18 +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``
-    codec libary.
+    (aka TCP).
 
     '''
     def __init__(
 
         self,
-        destaddr: tuple[str, int]|None,
+        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,
@@ -506,36 +325,31 @@ 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
 
         # Either created in ``.connect()`` or passed in by
         # user in ``.from_stream()``.
-        self._stream: trio.SocketStream|None = None
-        self._transport: MsgTransport|None = None
+        self._stream: Optional[trio.SocketStream] = None
+        self.msgstream: Optional[MsgTransport] = None
 
         # set after handshake - always uid of far end
-        self.uid: tuple[str, str]|None = None
+        self.uid: Optional[Tuple[str, str]] = None
 
-        self._aiter_msgs = self._iter_msgs()
-        self._exc: Exception|None = None  # set if far end actor errors
+        self._agen = self._aiter_recv()
+        self._exc: Optional[Exception] = None  # set if far end actor errors
         self._closed: bool = False
-
-        # flag set by ``Portal.cancel_actor()`` indicating remote
-        # (possibly peer) cancellation of the far end actor
-        # runtime.
-        self._cancel_called: bool = False
-
-    @property
-    def msgstream(self) -> MsgTransport:
-        log.info(
-            '`Channel.msgstream` is an old name, use `._transport`'
-        )
-        return self._transport
-
-    @property
-    def transport(self) -> MsgTransport:
-        return self._transport
+        # flag set on ``Portal.cancel_actor()`` indicating
+        # remote (peer) cancellation of the far end actor runtime.
+        self._cancel_called: bool = False  # set on ``Portal.cancel_actor()``
 
     @classmethod
     def from_stream(
@@ -546,82 +360,41 @@ class Channel:
     ) -> Channel:
 
         src, dst = get_stream_addrs(stream)
-        chan = Channel(
-            destaddr=dst,
-            **kwargs,
-        )
+        chan = Channel(destaddr=dst, **kwargs)
 
         # set immediately here from provided instance
-        chan._stream: trio.SocketStream = stream
+        chan._stream = stream
         chan.set_msg_transport(stream)
         return chan
 
     def set_msg_transport(
         self,
         stream: trio.SocketStream,
-        type_key: tuple[str, str]|None = None,
-
-        # XXX optionally provided codec pair for `msgspec`:
-        # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
-        codec: MsgCodec|None = None,
+        type_key: Optional[Tuple[str, str]] = None,
 
     ) -> MsgTransport:
-        type_key = (
-            type_key
-            or
-            self._transport_key
-        )
-        # get transport type, then
-        self._transport = get_msg_transport(
-            type_key
-        # instantiate an instance of the msg-transport
-        )(
-            stream,
-            codec=codec,
-        )
-        return self._transport
+        type_key = type_key or self._transport_key
+        self.msgstream = get_msg_transport(type_key)(stream)
+        return self.msgstream
 
-    @cm
-    def apply_codec(
-        self,
-        codec: MsgCodec,
-
-    ) -> None:
-        '''
-        Temporarily override the underlying IPC msg codec for
-        dynamic enforcement of messaging schema.
-
-        '''
-        orig: MsgCodec = self._transport.codec
-        try:
-            self._transport.codec = codec
-            yield
-        finally:
-            self._transport.codec = orig
-
-    # TODO: do a .src/.dst: str for maddrs?
     def __repr__(self) -> str:
-        if not self._transport:
-            return '<Channel with inactive transport?>'
-
-        return repr(
-            self._transport.stream.socket._sock
-        ).replace(  # type: ignore
-            "socket.socket",
-            "Channel",
-        )
+        if self.msgstream:
+            return repr(
+                self.msgstream.stream.socket._sock).replace(  # type: ignore
+                        "socket.socket", "Channel")
+        return object.__repr__(self)
 
     @property
-    def laddr(self) -> tuple[str, int]|None:
-        return self._transport.laddr if self._transport else None
+    def laddr(self) -> Optional[Tuple[str, int]]:
+        return self.msgstream.laddr if self.msgstream else None
 
     @property
-    def raddr(self) -> tuple[str, int]|None:
-        return self._transport.raddr if self._transport else None
+    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:
@@ -636,62 +409,26 @@ class Channel:
             *destaddr,
             **kwargs
         )
-        transport = self.set_msg_transport(stream)
+        msgstream = self.set_msg_transport(stream)
 
         log.transport(
-            f'Opened channel[{type(transport)}]: {self.laddr} -> {self.raddr}'
+            f'Opened channel[{type(msgstream)}]: {self.laddr} -> {self.raddr}'
         )
-        return transport
+        return msgstream
 
-    # TODO: something like,
-    # `pdbp.hideframe_on(errors=[MsgTypeError])`
-    # instead of the `try/except` hack we have rn..
-    # seems like a pretty useful thing to have in general
-    # along with being able to filter certain stack frame(s / sets)
-    # possibly based on the current log-level?
-    async def send(
-        self,
-        payload: Any,
+    async def send(self, item: Any) -> None:
 
-        hide_tb: bool = False,
+        log.transport(f"send `{item}`")  # type: ignore
+        assert self.msgstream
 
-    ) -> None:
-        '''
-        Send a coded msg-blob over the transport.
-
-        '''
-        __tracebackhide__: bool = hide_tb
-        try:
-            log.transport(
-                '=> send IPC msg:\n\n'
-                f'{pformat(payload)}\n'
-            )
-            # assert self._transport  # but why typing?
-            await self._transport.send(
-                payload,
-                hide_tb=hide_tb,
-            )
-        except BaseException as _err:
-            err = _err  # bind for introspection
-            if not isinstance(_err, MsgTypeError):
-                # assert err
-                __tracebackhide__: bool = False
-            else:
-                assert err.cid
-
-            raise
+        await self.msgstream.send(item)
 
     async def recv(self) -> Any:
-        assert self._transport
-        return await self._transport.recv()
+        assert self.msgstream
+        return await self.msgstream.recv()
 
-        # TODO: auto-reconnect features like 0mq/nanomsg?
-        # -[ ] implement it manually with nods to SC prot
-        #      possibly on multiple transport backends?
-        #  -> seems like that might be re-inventing scalability
-        #     prots tho no?
         # try:
-        #     return await self._transport.recv()
+        #     return await self.msgstream.recv()
         # except trio.BrokenResourceError:
         #     if self._autorecon:
         #         await self._reconnect()
@@ -704,8 +441,8 @@ class Channel:
             f'Closing channel to {self.uid} '
             f'{self.laddr} -> {self.raddr}'
         )
-        assert self._transport
-        await self._transport.stream.aclose()
+        assert self.msgstream
+        await self.msgstream.stream.aclose()
         self._closed = True
 
     async def __aenter__(self):
@@ -716,11 +453,8 @@ class Channel:
         await self.aclose(*args)
 
     def __aiter__(self):
-        return self._aiter_msgs
+        return self._agen
 
-    # ?TODO? run any reconnection sequence?
-    # -[ ] prolly should be impl-ed as deco-API?
-    #
     # async def _reconnect(self) -> None:
     #     """Handle connection failures by polling until a reconnect can be
     #     established.
@@ -738,6 +472,7 @@ class Channel:
     #             else:
     #                 log.transport("Stream connection re-established!")
 
+    #                 # TODO: run any reconnection sequence
     #                 # on_recon = self._recon_seq
     #                 # if on_recon:
     #                 #     await on_recon(self)
@@ -751,42 +486,23 @@ class Channel:
     #                     " for re-establishment")
     #             await trio.sleep(1)
 
-    async def _iter_msgs(
+    async def _aiter_recv(
         self
     ) -> AsyncGenerator[Any, None]:
         '''
-        Yield `MsgType` IPC msgs decoded and deliverd from
-        an underlying `MsgTransport` protocol.
-
-        This is a streaming routine alo implemented as an async-gen
-        func (same a `MsgTransport._iter_pkts()`) gets allocated by
-        a `.__call__()` inside `.__init__()` where it is assigned to
-        the `._aiter_msgs` attr.
+        Async iterate items from underlying stream.
 
         '''
-        assert self._transport
+        assert self.msgstream
         while True:
             try:
-                async for msg in self._transport:
-                    match msg:
-                        # NOTE: if transport/interchange delivers
-                        # a type error, we pack it with the far
-                        # end peer `Actor.uid` and relay the
-                        # `Error`-msg upward to the `._rpc` stack
-                        # for normal RAE handling.
-                        case MsgTypeError():
-                            yield pack_from_raise(
-                                local_err=msg,
-                                cid=msg.cid,
-
-                                # XXX we pack it here bc lower
-                                # layers have no notion of an
-                                # actor-id ;)
-                                src_uid=self.uid,
-                            )
-                        case _:
-                            yield msg
-
+                async for item in self.msgstream:
+                    yield item
+                    # sent = yield item
+                    # if sent is not None:
+                    #     # optimization, passing None through all the
+                    #     # time is pointless
+                    #     await self.msgstream.send(sent)
             except trio.BrokenResourceError:
 
                 # if not self._autorecon:
@@ -799,14 +515,12 @@ class Channel:
             #     continue
 
     def connected(self) -> bool:
-        return self._transport.connected() if self._transport else False
+        return self.msgstream.connected() if self.msgstream else False
 
 
-@acm
+@asynccontextmanager
 async def _connect_chan(
-    host: str,
-    port: int
-
+    host: str, port: int
 ) -> typing.AsyncGenerator[Channel, None]:
     '''
     Create and connect a channel with disconnect on context manager
@@ -816,5 +530,4 @@ async def _connect_chan(
     chan = Channel((host, port))
     await chan.connect()
     yield chan
-    with trio.CancelScope(shield=True):
-        await chan.aclose()
+    await chan.aclose()