Decouple registery addresses from binding addresses

Since a local-actor-nursery-parented subactor might also use the root as
its registry, we need to avoid warning when short lived IPC `Channel`
connections establish and then disconnect (quickly, bc the apparently
the subactor isn't re-using an already cached parente-peer<->child conn
as you'd expect efficiency..) since such cases currently considered
normal operation of our super shoddy/naive "discovery sys" XD

As such, (un)guard the whole local-actor-nursery OR channel-draining
waiting blocks with the additional `or Actor._cancel_called` branch
since really we should also be waiting on the parent nurse to exit (at
least, for sure and always) when the local `Actor` indeed has been
"globally" cancelled-called. Further add separate timeout warnings for
channel-draining vs. local-actor-nursery-exit waiting since they are
technically orthogonal cases (at least, afaik).

Also,
- adjust the `Actor._stream_handler()` connection status log-emit to
  `.runtime()`, especially to reduce noise around the aforementioned
  ephemeral registree connection-requests.
- if we do wait on a local actor-nurse to exit, report its `._children`
  table (which should help figure out going forward how useful the
  warning is, if at all).

.github/workflows/ci.yml

@@ -8,70 +8,46 @@ on:
   workflow_dispatch:
 
 jobs:
-  # ------ sdist ------
+
+  mypy:
+    name: 'MyPy'
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.10'
+
+      - name: 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.
-  #
-  # -[x] produce sdist with uv
-  # ------ - ------
   sdist-linux:
     name: 'sdist'
     runs-on: ubuntu-latest
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v2
 
-      - name: Install latest uv
-        uses: astral-sh/setup-uv@v6
+      - name: Setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.10'
 
-      - name: Build sdist as tar.gz
-        run: uv build --sdist --python=3.13
+      - name: Build sdist
+        run: python setup.py sdist --formats=zip
 
-      - name: Install sdist from .tar.gz
-        run: python -m pip install dist/*.tar.gz
-
-  # ------ type-check ------
-  # mypy:
-  #   name: 'MyPy'
-  #   runs-on: ubuntu-latest
-
-  #   steps:
-  #     - name: Checkout
-  #       uses: actions/checkout@v4
-
-  #     - name: Install latest uv
-  #       uses: astral-sh/setup-uv@v6
-
-  #     # faster due to server caching?
-  #     # https://docs.astral.sh/uv/guides/integration/github/#setting-up-python
-  #     - name: "Set up Python"
-  #       uses: actions/setup-python@v6
-  #       with:
-  #         python-version-file: "pyproject.toml"
-
-  #     # w uv
-  #     # - name: Set up Python
-  #     #   run: uv python install
-
-  #     - name: Setup uv venv
-  #       run: uv venv .venv --python=3.13
-
-  #     - name: Install
-  #       run: uv sync --dev
-
-  #     # TODO, ty cmd over repo
-  #     # - name: type check with ty
-  #     #   run: ty ./tractor/
-
-  #     # - uses: actions/cache@v3
-  #     #     name: Cache uv virtenv as default .venv
-  #     #     with:
-  #     #       path: ./.venv
-  #     #       key: venv-${{ hashFiles('uv.lock') }}
-
-  #     - name: Run MyPy check
-  #       run: mypy tractor/ --ignore-missing-imports --show-traceback
+      - name: Install sdist from .zips
+        run: python -m pip install dist/*.zip
 
 
   testing-linux:
@@ -83,45 +59,32 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ['3.13']
+        python: ['3.10']
         spawn_backend: [
           'trio',
-          # 'mp_spawn',
-          # 'mp_forkserver',
+          'mp_spawn',
+          'mp_forkserver',
         ]
 
     steps:
 
-      - uses: actions/checkout@v4
+      - name: Checkout
+        uses: actions/checkout@v2
 
-      - name: 'Install uv + py-${{ matrix.python-version }}'
-        uses: astral-sh/setup-uv@v6
+      - name: Setup python
+        uses: actions/setup-python@v2
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: '${{ matrix.python }}'
 
-      # GH way.. faster?
-      # - name: setup-python@v6
-      #   uses: actions/setup-python@v6
-      #   with:
-      #     python-version: '${{ matrix.python-version }}'
+      - name: Install dependencies
+        run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
 
-      # consider caching for speedups?
-      # https://docs.astral.sh/uv/guides/integration/github/#caching
-
-      - name: Install the project w uv
-        run: uv sync --all-extras --dev
-
-      # - name: Install dependencies
-      #   run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
-
-      - name: List deps tree
-        run: uv tree
+      - name: List dependencies
+        run: pip list
 
       - name: Run tests
-        run: uv run pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rsx
+        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rsx
 
-  # XXX legacy NOTE XXX
-  #
   # 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.

default.nix

@@ -1,19 +0,0 @@
-{ pkgs ? import <nixpkgs> {} }:
-let
-  nativeBuildInputs = with pkgs; [
-    stdenv.cc.cc.lib
-    uv
-  ];
-
-in
-pkgs.mkShell {
-  inherit nativeBuildInputs;
-
-  LD_LIBRARY_PATH = pkgs.lib.makeLibraryPath nativeBuildInputs;
-  TMPDIR = "/tmp";
-
-  shellHook = ''
-    set -e
-    uv venv .venv --python=3.12
-  '';
-}

docs/README.rst

@@ -1,20 +1,20 @@
-|logo| ``tractor``: distributed structurred concurrency
+|logo| ``tractor``: next-gen Python parallelism
 
-``tractor`` is a `structured concurrency`_ (SC), multi-processing_ runtime built on trio_.
+|gh_actions|
+|docs|
 
-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*.
+``tractor`` is a `structured concurrent`_, (optionally
+distributed_) multi-processing_ runtime built on trio_.
+
+Fundamentally, ``tractor`` gives you parallelism via
+``trio``-"*actors*": independent Python processes (aka
+non-shared-memory threads) which maintain structured
+concurrency (SC) *end-to-end* inside a *supervision tree*.
 
 Cross-process (and thus cross-host) SC is accomplished through the
-combined use of our,
-
-- "actor nurseries_" 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.
+combined use of our "actor nurseries_" and an "SC-transitive IPC
+protocol" constructed on top of multiple Pythons each running a ``trio``
+scheduled runtime - a call to ``trio.run()``.
 
 We believe the system adheres to the `3 axioms`_ of an "`actor model`_"
 but likely **does not** look like what **you** probably *think* an "actor
@@ -27,7 +27,6 @@ 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
@@ -36,91 +35,22 @@ Some great places to start are,
 
 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.
-
-
-Status of `main` / infra
-------------------------
-
-- |gh_actions|
-- |docs|
-
-
-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 "native" multi-core debugger REPL using `pdbp`_ (a fork & fix of
+  `pdb++`_ thanks to @mdmintz!)
+- Support for a swappable, OS specific, process spawning layer
+- A modular transport stack, allowing for custom serialization (eg. with
+  `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
@@ -178,7 +108,7 @@ 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
@@ -234,7 +164,7 @@ it **is a bug**.
 
 
 "Native" multi-process debugging
-********************************
+--------------------------------
 Using the magic of `pdbp`_ and our internal IPC, we've
 been able to create a native feeling debugging experience for
 any (sub-)process in your ``tractor`` tree.
@@ -289,7 +219,7 @@ 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.
 
@@ -381,7 +311,7 @@ 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?"*.
 
@@ -403,10 +333,10 @@ 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
@@ -512,7 +442,7 @@ 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
@@ -569,6 +499,18 @@ 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
+
+
+From git::
+
+    pip install git+git://github.com/goodboy/tractor.git
+
+
 Under the hood
 --------------
 ``tractor`` is an attempt to pair trionic_ `structured concurrency`_ with
@@ -672,32 +614,25 @@ channel`_!
 .. _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
 .. _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
 
-..
-   NOTE, on generating badge links from the UI
-   https://docs.github.com/en/actions/how-tos/monitoring-and-troubleshooting-workflows/monitoring-workflows/adding-a-workflow-status-badge?ref=gitguardian-blog-automated-secrets-detection#using-the-ui
-.. |gh_actions| image:: https://github.com/goodboy/tractor/actions/workflows/ci.yml/badge.svg?branch=main
-    :target: https://github.com/goodboy/tractor/actions/workflows/ci.yml
+
+.. |gh_actions| image:: https://img.shields.io/endpoint.svg?url=https%3A%2F%2Factions-badge.atrox.dev%2Fgoodboy%2Ftractor%2Fbadge&style=popout-square
+    :target: https://actions-badge.atrox.dev/goodboy/tractor/goto
 
 .. |docs| image:: https://readthedocs.org/projects/tractor/badge/?version=latest
     :target: https://tractor.readthedocs.io/en/latest/?badge=latest

examples/advanced_faults/ipc_failure_during_stream.py

@@ -16,7 +16,6 @@ from tractor import (
     ContextCancelled,
     MsgStream,
     _testing,
-    trionics,
 )
 import trio
 import pytest
@@ -63,8 +62,7 @@ async def recv_and_spawn_net_killers(
     await ctx.started()
     async with (
         ctx.open_stream() as stream,
-        trionics.collapse_eg(),
-        trio.open_nursery() as tn,
+        trio.open_nursery() as n,
     ):
         async for i in stream:
             print(f'child echoing {i}')
@@ -79,11 +77,11 @@ async def recv_and_spawn_net_killers(
                 i >= break_ipc_after
             ):
                 broke_ipc = True
-                tn.start_soon(
+                n.start_soon(
                     iter_ipc_stream,
                     stream,
                 )
-                tn.start_soon(
+                n.start_soon(
                     partial(
                         break_ipc_then_error,
                         stream=stream,
@@ -120,7 +118,6 @@ async def main(
     break_parent_ipc_after: int|bool = False,
     break_child_ipc_after: int|bool = False,
     pre_close: bool = False,
-    tpt_proto: str = 'tcp',
 
 ) -> None:
 
@@ -132,7 +129,6 @@ async def main(
             # a hang since it never engages due to broken IPC
             debug_mode=debug_mode,
             loglevel=loglevel,
-            enable_transports=[tpt_proto],
 
         ) as an,
     ):
@@ -147,8 +143,7 @@ async def main(
             _testing.expect_ctxc(
                 yay=(
                     break_parent_ipc_after
-                    or
-                    break_child_ipc_after
+                    or break_child_ipc_after
                 ),
                 # TODO: we CAN'T remove this right?
                 # since we need the ctxc to bubble up from either

examples/debugging/asyncio_bp.py

@@ -1,16 +1,8 @@
-'''
-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,
-)
+from tractor import to_asyncio
 
 
 async def aio_sleep_forever():
@@ -25,21 +17,21 @@ async def bp_then_error(
 
 ) -> None:
 
-    # sync with `trio`-side (caller) task
+    # 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
+    # => 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
+    #    some further, at least, meta-data about the task/actoq in debug
+    #    in terms of making it clear it's asyncio mucking about.
+    breakpoint()
 
     # short checkpoint / delay
-    await asyncio.sleep(0.5)  # asyncio-side
+    await asyncio.sleep(0.5)
 
     if raise_after_bp:
-        raise ValueError('asyncio side error!')
+        raise ValueError('blah')
 
     # TODO: test case with this so that it gets cancelled?
     else:
@@ -57,21 +49,23 @@ async def trio_ctx(
     # 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,
+            raise_after_bp=not bp_before_started,
         ) as (first, chan),
 
-        trio.open_nursery() as tn,
+        trio.open_nursery() as n,
     ):
+
         assert first == 'start'
 
         if bp_before_started:
-            await tractor.pause()  # trio-side
+            await tractor.breakpoint()
 
-        await ctx.started(first)  # trio-side
+        await ctx.started(first)
 
-        tn.start_soon(
+        n.start_soon(
             to_asyncio.run_task,
             aio_sleep_forever,
         )
@@ -79,50 +73,39 @@ async def trio_ctx(
 
 
 async def main(
-    bps_all_over: bool = True,
-
-    # TODO, WHICH OF THESE HAZ BUGZ?
-    cancel_from_root: bool = False,
-    err_from_root: bool = False,
+    bps_all_over: 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(
+        # debug_mode=True,
+    ) as n:
+
+        p = await n.start_actor(
             'aio_daemon',
             enable_modules=[__name__],
             infect_asyncio=True,
             debug_mode=True,
-            # loglevel='cancel',
+            loglevel='cancel',
         )
 
-        async with ptl.open_context(
+        async with p.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()
+            if bps_all_over:
+                await tractor.breakpoint()
 
+            # await trio.sleep_forever()
+            await ctx.cancel()
+            assert 0
 
         # TODO: case where we cancel from trio-side while asyncio task
         # has debugger lock?
-        # await ptl.cancel_actor()
+        # await p.cancel_actor()
 
 
 if __name__ == '__main__':

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

@@ -7,7 +7,7 @@ async def breakpoint_forever():
     try:
         while True:
             yield 'yo'
-            await tractor.pause()
+            await tractor.breakpoint()
     except BaseException:
         tractor.log.get_console_log().exception(
             'Cancelled while trying to enter pause point!'
@@ -21,14 +21,11 @@ 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',
     ) as n:
 
         p0 = await n.start_actor('bp_forever', enable_modules=[__name__])

examples/debugging/multi_nested_subactors_error_up_through_nurseries.py

@@ -10,7 +10,7 @@ async def name_error():
 async def breakpoint_forever():
     "Indefinitely re-enter debugger in child actor."
     while True:
-        await tractor.pause()
+        await tractor.breakpoint()
 
         # NOTE: if the test never sent 'q'/'quit' commands
         # on the pdb repl, without this checkpoint line the

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():

examples/debugging/restore_builtin_breakpoint.py

@@ -4,55 +4,21 @@ import sys
 import trio
 import tractor
 
-# ensure mod-path is correct!
-from tractor.devx.debug import (
-    _sync_pause_from_builtin as _sync_pause_from_builtin,
-)
-
 
 async def main() -> None:
+    async with tractor.open_nursery(debug_mode=True) as an:
 
-    # 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,
-        loglevel='devx',
-        maybe_enable_greenback=True,
-        # ^XXX REQUIRED to enable `breakpoint()` support (from sync
-        # fns) and thus required here to avoid an assertion err
-        # on the next line
-    ):
-        assert (
-            (pybp_var := os.environ['PYTHONBREAKPOINT'])
-            ==
-            'tractor.devx.debug._sync_pause_from_builtin'
-        )
+        assert os.environ['PYTHONBREAKPOINT'] == 'tractor._debug._set_trace'
 
         # TODO: an assert that verifies the hook has indeed been, hooked
         # XD
-        assert (
-            (pybp_hook := sys.breakpointhook)
-            is not tractor.devx.debug._set_trace
-        )
+        assert sys.breakpointhook is not tractor._debug._set_trace
 
-        print(
-            f'$PYTHONOBREAKPOINT: {pybp_var!r}\n'
-            f'`sys.breakpointhook`: {pybp_hook!r}\n'
-        )
-        breakpoint()  # first bp, tractor hook set.
+        breakpoint()
 
-    # 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
+    # TODO: an assert that verifies the hook is unhooked..
     assert sys.breakpointhook
-
-    # now ensure a regular builtin pause still works
-    breakpoint()  # last bp, stdlib hook restored
-
+    breakpoint()
 
 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

@@ -11,7 +11,7 @@ async def main(
         # loglevel='runtime',
     ):
         while True:
-            await tractor.pause()
+            await tractor.breakpoint()
 
 
 if __name__ == '__main__':

examples/debugging/root_cancelled_but_child_is_in_tty_lock.py

@@ -24,9 +24,10 @@ async def spawn_until(depth=0):
 
 
 async def main():
-    '''
-    The process tree should look as approximately as follows when the
-    debugger first engages:
+    """The main ``tractor`` routine.
+
+    The process tree should look as approximately as follows when the debugger
+    first engages:
 
     python examples/debugging/multi_nested_subactors_bp_forever.py
     ├─ python -m tractor._child --uid ('spawner1', '7eab8462 ...)
@@ -36,11 +37,10 @@ async def main():
     └─ python -m tractor._child --uid ('spawner0', '1d42012b ...)
        └─ python -m tractor._child --uid ('name_error', '6c2733b8 ...)
 
-    '''
+    """
     async with tractor.open_nursery(
         debug_mode=True,
-        loglevel='devx',
-        enable_transports=['uds'],
+        loglevel='warning'
     ) as n:
 
         # spawn both actors

examples/debugging/root_self_cancelled_w_error.py

@@ -1,35 +0,0 @@
-import trio
-import tractor
-
-
-async def main():
-    async with tractor.open_root_actor(
-        debug_mode=True,
-        loglevel='cancel',
-    ) as _root:
-
-        # manually trigger self-cancellation and wait
-        # for it to fully trigger.
-        _root.cancel_soon()
-        await _root._cancel_complete.wait()
-        print('root cancelled')
-
-        # now ensure we can still use the REPL
-        try:
-            await tractor.pause()
-        except trio.Cancelled as _taskc:
-            assert (root_cs := _root._root_tn.cancel_scope).cancel_called
-            # NOTE^^ above logic but inside `open_root_actor()` and
-            # passed to the `shield=` expression is effectively what
-            # we're testing here!
-            await tractor.pause(shield=root_cs.cancel_called)
-
-        # XXX, if shield logic *is wrong* inside `open_root_actor()`'s
-        # crash-handler block this should never be interacted,
-        # instead `trio.Cancelled` would be bubbled up: the original
-        # BUG.
-        assert 0
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/debugging/shield_hang_in_sub.py

@@ -1,84 +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',
-            enable_transports=['uds'],
-        ) 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/subactor_bp_in_ctx.py

@@ -4,9 +4,9 @@ import trio
 
 async def gen():
     yield 'yo'
-    await tractor.pause()
+    await tractor.breakpoint()
     yield 'yo'
-    await tractor.pause()
+    await tractor.breakpoint()
 
 
 @tractor.context
@@ -15,7 +15,7 @@ async def just_bp(
 ) -> None:
 
     await ctx.started()
-    await tractor.pause()
+    await tractor.breakpoint()
 
     # TODO: bps and errors in this call..
     async for val in gen():
@@ -33,11 +33,8 @@ async def just_bp(
 
 
 async def main():
-
     async with tractor.open_nursery(
         debug_mode=True,
-        enable_transports=['uds'],
-        loglevel='devx',
     ) as n:
         p = await n.start_actor(
             'bp_boi',

examples/debugging/sync_bp.py

@@ -4,13 +4,6 @@ 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,
@@ -25,13 +18,7 @@ def sync_pause(
         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')
@@ -54,11 +41,10 @@ async def start_n_sync_pause(
 async def main() -> None:
     async with (
         tractor.open_nursery(
-            debug_mode=True,
+            # NOTE: required for pausing from sync funcs
             maybe_enable_greenback=True,
-            enable_stack_on_sig=True,
-            # loglevel='warning',
-            # loglevel='devx',
+            debug_mode=True,
+            # loglevel='cancel',
         ) as an,
         trio.open_nursery() as tn,
     ):
@@ -152,9 +138,7 @@ async def main() -> None:
                     # 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,
+                abandon_on_cancel=False,
                 thread_name='inline_root_bg_thread',
             )
 

examples/full_fledged_streaming_service.py

@@ -91,7 +91,7 @@ async def main() -> list[int]:
     an: ActorNursery
     async with tractor.open_nursery(
         loglevel='cancel',
-        # debug_mode=True,
+        debug_mode=True,
     ) as an:
 
         seed = int(1e3)

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 (
@@ -23,15 +25,11 @@ async def main():
             modules=[__name__]
         ) as portal_map,
 
-        tractor.trionics.collapse_eg(),
-        trio.open_nursery() 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)
 
@@ -43,4 +41,4 @@ if __name__ == '__main__':
     try:
         trio.run(main)
     except KeyboardInterrupt:
-        print('trio cancelled by KBI')
+        pass

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() 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:

examples/trio/lockacquire_not_unmasked.py

@@ -1,85 +0,0 @@
-from contextlib import (
-    asynccontextmanager as acm,
-)
-from functools import partial
-
-import tractor
-import trio
-
-
-log = tractor.log.get_logger(
-    name=__name__
-)
-
-_lock: trio.Lock|None = None
-
-
-@acm
-async def acquire_singleton_lock(
-) -> None:
-    global _lock
-    if _lock is None:
-        log.info('Allocating LOCK')
-        _lock = trio.Lock()
-
-    log.info('TRYING TO LOCK ACQUIRE')
-    async with _lock:
-        log.info('ACQUIRED')
-        yield _lock
-
-    log.info('RELEASED')
-
-
-
-async def hold_lock_forever(
-    task_status=trio.TASK_STATUS_IGNORED
-):
-    async with (
-        tractor.trionics.maybe_raise_from_masking_exc(),
-        acquire_singleton_lock() as lock,
-    ):
-        task_status.started(lock)
-        await trio.sleep_forever()
-
-
-async def main(
-    ignore_special_cases: bool,
-    loglevel: str = 'info',
-    debug_mode: bool = True,
-):
-    async with (
-        trio.open_nursery() as tn,
-
-        # tractor.trionics.maybe_raise_from_masking_exc()
-        # ^^^ XXX NOTE, interestingly putting the unmasker
-        # here does not exhibit the same behaviour ??
-    ):
-        if not ignore_special_cases:
-            from tractor.trionics import _taskc
-            _taskc._mask_cases.clear()
-
-        _lock = await tn.start(
-            hold_lock_forever,
-        )
-        with trio.move_on_after(0.2):
-            await tn.start(
-                hold_lock_forever,
-            )
-
-        tn.cancel_scope.cancel()
-
-
-# XXX, manual test as script
-if __name__ == '__main__':
-    tractor.log.get_console_log(level='info')
-    for case in [True, False]:
-        log.info(
-            f'\n'
-            f'------ RUNNING SCRIPT TRIAL ------\n'
-            f'ignore_special_cases: {case!r}\n'
-        )
-        trio.run(partial(
-            main,
-            ignore_special_cases=case,
-            loglevel='info',
-        ))

examples/trio/send_chan_aclose_masks_beg.py

@@ -1,195 +0,0 @@
-from contextlib import (
-    contextmanager as cm,
-    # TODO, any diff in async case(s)??
-    # asynccontextmanager as acm,
-)
-from functools import partial
-
-import tractor
-import trio
-
-
-log = tractor.log.get_logger(
-    name=__name__
-)
-
-
-@cm
-def teardown_on_exc(
-    raise_from_handler: bool = False,
-):
-    '''
-    You could also have a teardown handler which catches any exc and
-    does some required teardown. In this case the problem is
-    compounded UNLESS you ensure the handler's scope is OUTSIDE the
-    `ux.aclose()`.. that is in the caller's enclosing scope.
-
-    '''
-    try:
-        yield
-    except BaseException as _berr:
-        berr = _berr
-        log.exception(
-            f'Handling termination teardown in child due to,\n'
-            f'{berr!r}\n'
-        )
-        if raise_from_handler:
-            # XXX teardown ops XXX
-            # on termination these steps say need to be run to
-            # ensure wider system consistency (like the state of
-            # remote connections/services).
-            #
-            # HOWEVER, any bug in this teardown code is also
-            # masked by the `tx.aclose()`!
-            # this is also true if `_tn.cancel_scope` is
-            # `.cancel_called` by the parent in a graceful
-            # request case..
-
-            # simulate a bug in teardown handler.
-            raise RuntimeError(
-                'woopsie teardown bug!'
-            )
-
-        raise  # no teardown bug.
-
-
-async def finite_stream_to_rent(
-    tx: trio.abc.SendChannel,
-    child_errors_mid_stream: bool,
-    raise_unmasked: bool,
-
-    task_status: trio.TaskStatus[
-        trio.CancelScope,
-    ] = trio.TASK_STATUS_IGNORED,
-):
-    async with (
-        # XXX without this unmasker the mid-streaming RTE is never
-        # reported since it is masked by the `tx.aclose()`
-        # call which in turn raises `Cancelled`!
-        #
-        # NOTE, this is WITHOUT doing any exception handling
-        # inside the child  task!
-        #
-        # TODO, uncomment next LoC to see the supprsessed beg[RTE]!
-        tractor.trionics.maybe_raise_from_masking_exc(
-            raise_unmasked=raise_unmasked,
-        ),
-
-        tx as tx,  # .aclose() is the guilty masker chkpt!
-
-        # XXX, this ONLY matters in the
-        # `child_errors_mid_stream=False` case oddly!?
-        # THAT IS, if no tn is opened in that case then the
-        # test will not fail; it raises the RTE correctly?
-        #
-        # -> so it seems this new scope somehow affects the form of
-        #    eventual in the parent EG?
-        tractor.trionics.maybe_open_nursery(
-            nursery=(
-                None
-                if not child_errors_mid_stream
-                else True
-            ),
-        ) as _tn,
-    ):
-        # pass our scope back to parent for supervision\
-        # control.
-        cs: trio.CancelScope|None = (
-            None
-            if _tn is True
-            else _tn.cancel_scope
-        )
-        task_status.started(cs)
-
-        with teardown_on_exc(
-            raise_from_handler=not child_errors_mid_stream,
-        ):
-            for i in range(100):
-                log.debug(
-                    f'Child tx {i!r}\n'
-                )
-                if (
-                    child_errors_mid_stream
-                    and
-                    i == 66
-                ):
-                    # oh wait but WOOPS there's a bug
-                    # in that teardown code!?
-                    raise RuntimeError(
-                        'woopsie, a mid-streaming bug!?'
-                    )
-
-                await tx.send(i)
-
-
-async def main(
-    # TODO! toggle this for the 2 cases!
-    # 1. child errors mid-stream while parent is also requesting
-    #   (graceful) cancel of that child streamer.
-    #
-    # 2. child contains a teardown handler which contains a
-    #   bug and raises.
-    #
-    child_errors_mid_stream: bool,
-
-    raise_unmasked: bool = False,
-    loglevel: str = 'info',
-):
-    tractor.log.get_console_log(level=loglevel)
-
-    # the `.aclose()` being checkpoints on these
-    # is the source of the problem..
-    tx, rx = trio.open_memory_channel(1)
-
-    async with (
-        tractor.trionics.collapse_eg(),
-        trio.open_nursery() as tn,
-        rx as rx,
-    ):
-        _child_cs = await tn.start(
-            partial(
-                finite_stream_to_rent,
-                child_errors_mid_stream=child_errors_mid_stream,
-                raise_unmasked=raise_unmasked,
-                tx=tx,
-            )
-        )
-        async for msg in rx:
-            log.debug(
-                f'Rent rx {msg!r}\n'
-            )
-
-            # simulate some external cancellation
-            # request **JUST BEFORE** the child errors.
-            if msg == 65:
-                log.cancel(
-                    f'Cancelling parent on,\n'
-                    f'msg={msg}\n'
-                    f'\n'
-                    f'Simulates OOB cancel request!\n'
-                )
-                tn.cancel_scope.cancel()
-
-
-# XXX, manual test as script
-if __name__ == '__main__':
-    tractor.log.get_console_log(level='info')
-    for case in [True, False]:
-        log.info(
-            f'\n'
-            f'------ RUNNING SCRIPT TRIAL ------\n'
-            f'child_errors_midstream: {case!r}\n'
-        )
-        try:
-            trio.run(partial(
-                main,
-                child_errors_mid_stream=case,
-                # raise_unmasked=True,
-                loglevel='info',
-            ))
-        except Exception as _exc:
-            exc = _exc
-            log.exception(
-                'Should have raised an RTE or Cancelled?\n'
-            )
-            breakpoint()

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

@@ -1,116 +1,71 @@
 [build-system]
-requires = ["hatchling"]
-build-backend = "hatchling.build"
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
 
-# ------ build-system ------
+# ------ - ------
 
-[project]
+[tool.poetry]
 name = "tractor"
 version = "0.1.0a6dev0"
-description = 'structured concurrent `trio`-"actors"'
-authors = [{ name = "Tyler Goodlet", email = "goodboy_foss@protonmail.com" }]
-requires-python = ">= 3.11"
+description='structured concurrent `trio`-"actors"'
+authors = ["Tyler Goodlet <goodboy_foss@protonmail.com>"]
+license = "AGPlv3"
 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",
-  "cffi>=1.17.1",
-  "bidict>=0.23.1",
+
+# TODO: do we need this xontrib loader at all given pep420
+# and xonsh's xontrib global-autoload-via-setuptools?
+# https://xon.sh/tutorial_xontrib.html#authoring-xontribs
+packages = [
+  {include = 'tractor' },
+  # {include = 'tractor.experimental' },
+  # {include = 'tractor.trionics' },
+  # {include = 'tractor.msg' },
+  # {include = 'tractor.devx' },
 ]
 
-# ------ 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",
-  # ^ requires this?
-  "typing-extensions>=4.14.1",
+[tool.poetry.dependencies]
+python = "^3.11"
 
-  "pyperclip>=1.9.0",
-  "prompt-toolkit>=3.0.50",
-  "xonsh>=0.19.2",
-  "psutil>=7.0.0",
-]
-# TODO, add these with sane versions; were originally in
-# `requirements-docs.txt`..
-# docs = [
-#   "sphinx>="
-#   "sphinx_book_theme>="
-# ]
+# trio runtime related
+# proper range spec:
+# https://packaging.python.org/en/latest/discussions/install-requires-vs-requirements/#id5
+trio='^0.24'
+tricycle = "^0.4.1"
+trio-typing = "^0.10.0"
 
-# ------ dependency-groups ------
+msgspec='^0.18.5'  # interchange
+wrapt = "^1.16.0"  # decorators
+colorlog = "^6.8.2"  # logging
 
-# ------ dependency-groups ------
+# built-in multi-actor `pdb` REPL
+pdbp = "^1.5.0"
 
-[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
+# TODO: distributed transport using
 # 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.poetry.group.dev]
+optional = false
+[tool.poetry.group.dev.dependencies]
+# testing
+pytest = "^8.2.0"
+pexpect = "^4.9.0"
 
-# ------ tool.uv ------
+# .devx tooling
+greenback = "^1.2.1"
+stackscope = "^0.2.2"
 
-[tool.hatch.build.targets.sdist]
-include = ["tractor"]
+# (light) xonsh usage/integration
+xontrib-vox = "^0.0.1"
+prompt-toolkit = "^3.0.43"
+xonsh-vox-tabcomplete = "^0.5"
 
-[tool.hatch.build.targets.wheel]
-include = ["tractor"]
-
-# ------ tool.hatch ------
+# ------ - ------
 
 [tool.towncrier]
 package = "tractor"
@@ -121,27 +76,27 @@ title_format = "tractor {version} ({project_date})"
 template = "nooz/_template.rst"
 all_bullets = true
 
-[[tool.towncrier.type]]
+  [[tool.towncrier.type]]
   directory = "feature"
   name = "Features"
   showcontent = true
 
-[[tool.towncrier.type]]
+  [[tool.towncrier.type]]
   directory = "bugfix"
   name = "Bug Fixes"
   showcontent = true
 
-[[tool.towncrier.type]]
+  [[tool.towncrier.type]]
   directory = "doc"
   name = "Improved Documentation"
   showcontent = true
 
-[[tool.towncrier.type]]
+  [[tool.towncrier.type]]
   directory = "trivial"
   name = "Trivial/Internal Changes"
   showcontent = true
 
-# ------ tool.towncrier ------
+# ------ - ------
 
 [tool.pytest.ini_options]
 minversion = '6.0'
@@ -157,8 +112,31 @@ addopts = [
   '--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 ------
+# ------ - ------
+
+[project]
+name = "tractor"
+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",
+]

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 +1,9 @@
+pytest
+pytest-trio
+pytest-timeout
+pdbp
+mypy
+trio_typing
+pexpect
+towncrier
+numpy

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 +1,102 @@
+#!/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='0.1.0a6dev0',  # alpha zone
+    description='structured concurrent `trio`-"actors"',
+    long_description=readme,
+    license='AGPLv3',
+    author='Tyler Goodlet',
+    maintainer='Tyler Goodlet',
+    maintainer_email='goodboy_foss@protonmail.com',
+    url='https://github.com/goodboy/tractor',
+    platforms=['linux', 'windows'],
+    packages=[
+        'tractor',
+        'tractor.experimental',  # wacky ideas
+        'tractor.trionics',  # trio extensions
+        'tractor.msg',  # lowlevel data types
+        'tractor.devx',  # "dev-experience"
+    ],
+    install_requires=[
+
+        # trio related
+        # proper range spec:
+        # https://packaging.python.org/en/latest/discussions/install-requires-vs-requirements/#id5
+        'trio >= 0.24',
+
+        # 'async_generator',  # in stdlib mostly!
+        # 'trio_typing',  # trio==0.23.0 has type hints!
+        # 'exceptiongroup',  # in stdlib as of 3.11!
+
+        # tooling
+        'stackscope',
+        'tricycle',
+        'trio_typing',
+        'colorlog',
+        'wrapt',
+
+        # IPC serialization
+        'msgspec>=0.18.5',
+
+        # debug mode REPL
+        'pdbp',
+
+        # TODO: distributed transport using
+        # linux kernel networking
+        # 'pyroute2',
+
+        # pip ref docs on these specs:
+        # https://pip.pypa.io/en/stable/reference/requirement-specifiers/#examples
+        # and pep:
+        # https://peps.python.org/pep-0440/#version-specifiers
+
+    ],
+    tests_require=['pytest'],
+    python_requires=">=3.10",
+    keywords=[
+        'trio',
+        'async',
+        'concurrency',
+        'structured 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 :: 3.10",
+        "Intended Audience :: Science/Research",
+        "Intended Audience :: Developers",
+        "Topic :: System :: Distributed Computing",
+    ],
+)

tests/conftest.py

@@ -1,27 +1,24 @@
 """
-Top level of the testing suites!
-
+``tractor`` testing!!
 """
-from __future__ import annotations
 import sys
 import subprocess
 import os
+import random
 import signal
 import platform
 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,
 )
 
-pytest_plugins: list[str] = [
-    'pytester',
-    'tractor._testing.pytest',
-]
-
+# TODO: include wtv plugin(s) we build in `._testing.pytest`?
+pytest_plugins = ['pytester']
 
 # Sending signal.SIGINT on subprocess fails on windows. Use CTRL_* alternatives
 if platform.system() == 'Windows':
@@ -33,11 +30,7 @@ else:
     _KILL_SIGNAL = signal.SIGKILL
     _INT_SIGNAL = signal.SIGINT
     _INT_RETURN_CODE = 1 if sys.version_info < (3, 8) else -signal.SIGINT.value
-    _PROC_SPAWN_WAIT = (
-        0.6
-        if sys.version_info < (3, 7)
-        else 0.4
-    )
+    _PROC_SPAWN_WAIT = 0.6 if sys.version_info < (3, 7) else 0.4
 
 
 no_windows = pytest.mark.skipif(
@@ -46,12 +39,7 @@ no_windows = pytest.mark.skipif(
 )
 
 
-def pytest_addoption(
-    parser: pytest.Parser,
-):
-    # ?TODO? should this be exposed from our `._testing.pytest`
-    # plugin or should we make it more explicit with `--tl` for
-    # tractor logging like we do in other client projects?
+def pytest_addoption(parser):
     parser.addoption(
         "--ll",
         action="store",
@@ -59,10 +47,39 @@ def pytest_addoption(
         default='ERROR', help="logging level to set when testing"
     )
 
+    parser.addoption(
+        "--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):
+    return request.config.option.tractor_debug_mode
+
 
 @pytest.fixture(scope='session', autouse=True)
 def loglevel(request):
-    import tractor
     orig = tractor.log._default_loglevel
     level = tractor.log._default_loglevel = request.config.option.loglevel
     tractor.log.get_console_log(level)
@@ -70,44 +87,88 @@ def loglevel(request):
     tractor.log._default_loglevel = orig
 
 
+@pytest.fixture(scope='session')
+def spawn_backend(request) -> str:
+    return request.config.option.spawn_backend
+
+
 _ci_env: bool = os.environ.get('CI', False)
 
 
 @pytest.fixture(scope='session')
 def ci_env() -> bool:
     '''
-    Detect CI environment.
+    Detect CI envoirment.
 
     '''
     return _ci_env
 
 
-def sig_prog(
-    proc: subprocess.Popen,
-    sig: int,
-    canc_timeout: float = 0.1,
-) -> int:
+# 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),
+)
+
+
+@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 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'
+
+    # 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')
+
+
+def sig_prog(proc, sig):
     "Kill the actor-process with ``sig``."
     proc.send_signal(sig)
-    time.sleep(canc_timeout)
+    time.sleep(0.1)
     if not proc.poll():
         # TODO: why sometimes does SIGINT not work on teardown?
         # seems to happen only when trace logging enabled?
         proc.send_signal(_KILL_SIGNAL)
-    ret: int = proc.wait()
+    ret = proc.wait()
     assert ret
 
 
 # TODO: factor into @cm and move to `._testing`?
 @pytest.fixture
 def daemon(
-    debug_mode: bool,
     loglevel: str,
-    testdir: pytest.Pytester,
+    testdir,
     reg_addr: tuple[str, int],
-    tpt_proto: str,
-
-) -> subprocess.Popen:
+):
     '''
     Run a daemon root actor as a separate actor-process tree and
     "remote registrar" for discovery-protocol related tests.
@@ -118,100 +179,28 @@ def daemon(
         loglevel: str = 'info'
 
     code: str = (
-        "import tractor; "
-        "tractor.run_daemon([], "
-        "registry_addrs={reg_addrs}, "
-        "debug_mode={debug_mode}, "
-        "loglevel={ll})"
+            "import tractor; "
+            "tractor.run_daemon([], registry_addrs={reg_addrs}, loglevel={ll})"
     ).format(
         reg_addrs=str([reg_addr]),
         ll="'{}'".format(loglevel) if loglevel else None,
-        debug_mode=debug_mode,
     )
     cmd: list[str] = [
         sys.executable,
         '-c', code,
     ]
-    # breakpoint()
     kwargs = {}
     if platform.system() == 'Windows':
         # without this, tests hang on windows forever
         kwargs['creationflags'] = subprocess.CREATE_NEW_PROCESS_GROUP
 
-    proc: subprocess.Popen = testdir.popen(
+    proc = testdir.popen(
         cmd,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
         **kwargs,
     )
-
-    # UDS sockets are **really** fast to bind()/listen()/connect()
-    # so it's often required that we delay a bit more starting
-    # the first actor-tree..
-    if tpt_proto == 'uds':
-        global _PROC_SPAWN_WAIT
-        _PROC_SPAWN_WAIT = 0.6
-
-    time.sleep(_PROC_SPAWN_WAIT)
-
     assert not proc.returncode
+    time.sleep(_PROC_SPAWN_WAIT)
     yield proc
     sig_prog(proc, _INT_SIGNAL)
-
-    # XXX! yeah.. just be reaaal careful with this bc sometimes it
-    # can lock up on the `_io.BufferedReader` and hang..
-    stderr: str = proc.stderr.read().decode()
-    if stderr:
-        print(
-            f'Daemon actor tree produced STDERR:\n'
-            f'{proc.args}\n'
-            f'\n'
-            f'{stderr}\n'
-        )
-    if proc.returncode != -2:
-        raise RuntimeError(
-            'Daemon actor tree failed !?\n'
-            f'{proc.args}\n'
-        )
-
-
-# @pytest.fixture(autouse=True)
-# def shared_last_failed(pytestconfig):
-#     val = pytestconfig.cache.get("example/value", None)
-#     breakpoint()
-#     if val is None:
-#         pytestconfig.cache.set("example/value", val)
-#     return val
-
-
-# TODO: a way to let test scripts (like from `examples/`)
-# guarantee they won't `registry_addrs` collide!
-# -[ ] maybe use some kinda standard `def main()` arg-spec that
-#     we can introspect from a fixture that is called from the test
-#     body?
-# -[ ] test and figure out typing for below prototype! Bp
-#
-# @pytest.fixture
-# def set_script_runtime_args(
-#     reg_addr: tuple,
-# ) -> Callable[[...], None]:
-
-#     def import_n_partial_in_args_n_triorun(
-#         script: Path,  # under examples?
-#         **runtime_args,
-#     ) -> Callable[[], Any]:  # a `partial`-ed equiv of `trio.run()`
-
-#         # NOTE, below is taken from
-#         # `.test_advanced_faults.test_ipc_channel_break_during_stream`
-#         mod: ModuleType = import_path(
-#             examples_dir() / 'advanced_faults'
-#             / 'ipc_failure_during_stream.py',
-#             root=examples_dir(),
-#             consider_namespace_packages=False,
-#         )
-#         return partial(
-#             trio.run,
-#             partial(
-#                 mod.main,
-#                 **runtime_args,
-#             )
-#         )
-#     return import_n_partial_in_args_n_triorun

tests/devx/conftest.py

@@ -1,253 +0,0 @@
-'''
-`tractor.devx.*` tooling sub-pkg test space.
-
-'''
-from __future__ import annotations
-import time
-from typing import (
-    Callable,
-    TYPE_CHECKING,
-)
-
-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,
-)
-
-if TYPE_CHECKING:
-    from pexpect import pty_spawn
-
-
-# a fn that sub-instantiates a `pexpect.spawn()`
-# and returns it.
-type PexpectSpawner = Callable[[str], pty_spawn.spawn]
-
-
-@pytest.fixture
-def spawn(
-    start_method: str,
-    testdir: pytest.Pytester,
-    reg_addr: tuple[str, int],
-
-) -> PexpectSpawner:
-    '''
-    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,
-    ) -> pty_spawn.spawn:
-        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  # the `PexpectSpawner`, type alias.
-
-
-@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

@@ -1,306 +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.
-
-'''
-from __future__ import annotations
-from contextlib import (
-    contextmanager as cm,
-)
-import os
-import signal
-import time
-from typing import (
-    TYPE_CHECKING,
-)
-
-from .conftest import (
-    expect,
-    assert_before,
-    in_prompt_msg,
-    PROMPT,
-    _pause_msg,
-)
-
-import pytest
-from pexpect.exceptions import (
-    # TIMEOUT,
-    EOF,
-)
-
-if TYPE_CHECKING:
-    from ..conftest import PexpectSpawner
-
-
-def test_shield_pause(
-    spawn: PexpectSpawner,
-):
-    '''
-    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,
-    )
-    from tractor._supervise import _shutdown_msg
-    expect(
-        child,
-        # 'Shutting down actor runtime',
-        _shutdown_msg,
-        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: PexpectSpawner,
-):
-    '''
-    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)
-    try:
-        assert_before(
-            child,
-            [
-                _pause_msg,
-                "<Task '__main__.main'",
-                "('root'",
-                "first bp, tractor hook set",
-            ]
-        )
-    # XXX if the above raises `AssertionError`, without sending
-    # the final 'continue' cmd to the REPL-active sub-process,
-    # we'll hang waiting for that pexpect instance to terminate..
-    finally:
-        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)
-
-
-
-_to_raise = Exception('Triggering a crash')
-
-
-@pytest.mark.parametrize(
-    'to_raise',
-    [
-        None,
-        _to_raise,
-        RuntimeError('Never crash handle this!'),
-    ],
-)
-@pytest.mark.parametrize(
-    'raise_on_exit',
-    [
-        True,
-        [type(_to_raise)],
-        False,
-    ]
-)
-def test_crash_handler_cms(
-    debug_mode: bool,
-    to_raise: Exception,
-    raise_on_exit: bool|list[Exception],
-):
-    '''
-    Verify the `.devx.open_crash_handler()` API(s) by also
-    (conveniently enough) tesing its `repl_fixture: ContextManager`
-    param support which for this suite allows use to avoid use of
-    a `pexpect`-style-test since we use the fixture to avoid actually
-    entering `PdbpREPL.iteract()` :smirk:
-
-    '''
-    import tractor
-    # import trio
-
-    # state flags
-    repl_acquired: bool = False
-    repl_released: bool = False
-
-    @cm
-    def block_repl_ux(
-        repl: tractor.devx.debug.PdbREPL,
-        maybe_bxerr: (
-            tractor.devx._debug.BoxedMaybeException
-            |None
-        ) = None,
-        enter_repl: bool = True,
-
-    ) -> bool:
-        '''
-        Set pre/post-REPL state vars and bypass actual conole
-        interaction.
-
-        '''
-        nonlocal repl_acquired, repl_released
-
-        # task: trio.Task = trio.lowlevel.current_task()
-        # print(f'pre-REPL active_task={task.name}')
-
-        print('pre-REPL')
-        repl_acquired = True
-        yield False  # never actually .interact()
-        print('post-REPL')
-        repl_released = True
-
-    try:
-        # TODO, with runtime's `debug_mode` setting
-        # -[ ] need to open runtime tho obvi..
-        #
-        # with tractor.devx.maybe_open_crash_handler(
-        #     pdb=True,
-
-        with tractor.devx.open_crash_handler(
-            raise_on_exit=raise_on_exit,
-            repl_fixture=block_repl_ux
-        ) as bxerr:
-            if to_raise is not None:
-                raise to_raise
-
-    except Exception as _exc:
-        exc = _exc
-        if (
-            raise_on_exit is True
-            or
-            type(to_raise) in raise_on_exit
-        ):
-            assert (
-                exc
-                is
-                to_raise
-                is
-                bxerr.value
-            )
-
-        else:
-            raise
-    else:
-        assert (
-            to_raise is None
-            or
-            not raise_on_exit
-            or
-            type(to_raise) not in raise_on_exit
-        )
-        assert bxerr.value is to_raise
-
-    assert bxerr.raise_on_exit == raise_on_exit
-
-    if to_raise is not None:
-        assert repl_acquired
-        assert repl_released

tests/ipc/__init__.py

@@ -1,4 +0,0 @@
-'''
-`tractor.ipc` subsystem(s)/unit testing suites.
-
-'''

tests/ipc/test_each_tpt.py

@@ -1,114 +0,0 @@
-'''
-Unit-ish tests for specific IPC transport protocol backends.
-
-'''
-from __future__ import annotations
-from pathlib import Path
-
-import pytest
-import trio
-import tractor
-from tractor import (
-    Actor,
-    _state,
-    _addr,
-)
-
-
-@pytest.fixture
-def bindspace_dir_str() -> str:
-
-    rt_dir: Path = tractor._state.get_rt_dir()
-    bs_dir: Path = rt_dir / 'doggy'
-    bs_dir_str: str = str(bs_dir)
-    assert not bs_dir.is_dir()
-
-    yield bs_dir_str
-
-    # delete it on suite teardown.
-    # ?TODO? should we support this internally
-    # or is leaking it ok?
-    if bs_dir.is_dir():
-        bs_dir.rmdir()
-
-
-def test_uds_bindspace_created_implicitly(
-    debug_mode: bool,
-    bindspace_dir_str: str,
-):
-    registry_addr: tuple = (
-        f'{bindspace_dir_str}',
-        'registry@doggy.sock',
-    )
-    bs_dir_str: str = registry_addr[0]
-
-    # XXX, ensure bindspace-dir DNE beforehand!
-    assert not Path(bs_dir_str).is_dir()
-
-    async def main():
-        async with tractor.open_nursery(
-            enable_transports=['uds'],
-            registry_addrs=[registry_addr],
-            debug_mode=debug_mode,
-        ) as _an:
-
-            # XXX MUST be created implicitly by
-            # `.ipc._uds.start_listener()`!
-            assert Path(bs_dir_str).is_dir()
-
-            root: Actor = tractor.current_actor()
-            assert root.is_registrar
-
-            assert registry_addr in root.reg_addrs
-            assert (
-                registry_addr
-                in
-                _state._runtime_vars['_registry_addrs']
-            )
-            assert (
-                _addr.wrap_address(registry_addr)
-                in
-                root.registry_addrs
-            )
-
-    trio.run(main)
-
-
-def test_uds_double_listen_raises_connerr(
-    debug_mode: bool,
-    bindspace_dir_str: str,
-):
-    registry_addr: tuple = (
-        f'{bindspace_dir_str}',
-        'registry@doggy.sock',
-    )
-
-    async def main():
-        async with tractor.open_nursery(
-            enable_transports=['uds'],
-            registry_addrs=[registry_addr],
-            debug_mode=debug_mode,
-        ) as _an:
-
-            # runtime up
-            root: Actor = tractor.current_actor()
-
-            from tractor.ipc._uds import (
-                start_listener,
-                UDSAddress,
-            )
-            ya_bound_addr: UDSAddress = root.registry_addrs[0]
-            try:
-                await start_listener(
-                    addr=ya_bound_addr,
-                )
-            except ConnectionError as connerr:
-                assert type(src_exc := connerr.__context__) is OSError
-                assert 'Address already in use' in src_exc.args
-                # complete, exit test.
-
-            else:
-                pytest.fail('It dint raise a connerr !?')
-
-
-    trio.run(main)

tests/ipc/test_multi_tpt.py

@@ -1,95 +0,0 @@
-'''
-Verify the `enable_transports` param drives various
-per-root/sub-actor IPC endpoint/server settings.
-
-'''
-from __future__ import annotations
-
-import pytest
-import trio
-import tractor
-from tractor import (
-    Actor,
-    Portal,
-    ipc,
-    msg,
-    _state,
-    _addr,
-)
-
-@tractor.context
-async def chk_tpts(
-    ctx: tractor.Context,
-    tpt_proto_key: str,
-):
-    rtvars = _state._runtime_vars
-    assert (
-        tpt_proto_key
-        in
-        rtvars['_enable_tpts']
-    )
-    actor: Actor = tractor.current_actor()
-    spec: msg.types.SpawnSpec = actor._spawn_spec
-    assert spec._runtime_vars == rtvars
-
-    # ensure individual IPC ep-addr types
-    serv: ipc._server.Server = actor.ipc_server
-    addr: ipc._types.Address
-    for addr in serv.addrs:
-        assert addr.proto_key == tpt_proto_key
-
-    # Actor delegate-props enforcement
-    assert (
-        actor.accept_addrs
-        ==
-        serv.accept_addrs
-    )
-
-    await ctx.started(serv.accept_addrs)
-
-
-# TODO, parametrize over mis-matched-proto-typed `registry_addrs`
-# since i seems to work in `piker` but not exactly sure if both tcp
-# & uds are being deployed then?
-#
-@pytest.mark.parametrize(
-    'tpt_proto_key',
-    ['tcp', 'uds'],
-    ids=lambda item: f'ipc_tpt={item!r}'
-)
-def test_root_passes_tpt_to_sub(
-    tpt_proto_key: str,
-    reg_addr: tuple,
-    debug_mode: bool,
-):
-    async def main():
-        async with tractor.open_nursery(
-            enable_transports=[tpt_proto_key],
-            registry_addrs=[reg_addr],
-            debug_mode=debug_mode,
-        ) as an:
-
-            assert (
-                tpt_proto_key
-                in
-                _state._runtime_vars['_enable_tpts']
-            )
-
-            ptl: Portal = await an.start_actor(
-                name='sub',
-                enable_modules=[__name__],
-            )
-            async with ptl.open_context(
-                chk_tpts,
-                tpt_proto_key=tpt_proto_key,
-            ) as (ctx, accept_addrs):
-
-                uw_addr: tuple
-                for uw_addr in accept_addrs:
-                    addr = _addr.wrap_address(uw_addr)
-                    assert addr.is_valid
-
-            # shudown sub-actor(s)
-            await an.cancel()
-
-    trio.run(main)

tests/ipc/test_server.py

@@ -1,72 +0,0 @@
-'''
-High-level `.ipc._server` unit tests.
-
-'''
-from __future__ import annotations
-
-import pytest
-import trio
-from tractor import (
-    devx,
-    ipc,
-    log,
-)
-from tractor._testing.addr import (
-    get_rando_addr,
-)
-# TODO, use/check-roundtripping with some of these wrapper types?
-#
-# from .._addr import Address
-# from ._chan import Channel
-# from ._transport import MsgTransport
-# from ._uds import UDSAddress
-# from ._tcp import TCPAddress
-
-
-@pytest.mark.parametrize(
-    '_tpt_proto',
-    ['uds', 'tcp']
-)
-def test_basic_ipc_server(
-    _tpt_proto: str,
-    debug_mode: bool,
-    loglevel: str,
-):
-
-    # so we see the socket-listener reporting on console
-    log.get_console_log("INFO")
-
-    rando_addr: tuple = get_rando_addr(
-        tpt_proto=_tpt_proto,
-    )
-    async def main():
-        async with ipc._server.open_ipc_server() as server:
-
-            assert (
-                server._parent_tn
-                and
-                server._parent_tn is server._stream_handler_tn
-            )
-            assert server._no_more_peers.is_set()
-
-            eps: list[ipc._server.Endpoint] = await server.listen_on(
-                accept_addrs=[rando_addr],
-                stream_handler_nursery=None,
-            )
-            assert (
-                len(eps) == 1
-                and
-                (ep := eps[0])._listener
-                and
-                not ep.peer_tpts
-            )
-
-            server._parent_tn.cancel_scope.cancel()
-
-        # !TODO! actually make a bg-task connection from a client
-        # using `ipc._chan._connect_chan()`
-
-    with devx.maybe_open_crash_handler(
-        pdb=debug_mode,
-    ):
-        trio.run(main)

tests/test_advanced_faults.py

@@ -3,6 +3,7 @@ Sketchy network blackoutz, ugly byzantine gens, puedes eschuchar la
 cancelacion?..
 
 '''
+import itertools
 from functools import partial
 from types import ModuleType
 
@@ -10,9 +11,6 @@ import pytest
 from _pytest.pathlib import import_path
 import trio
 import tractor
-from tractor import (
-    TransportClosed,
-)
 from tractor._testing import (
     examples_dir,
     break_ipc,
@@ -77,7 +75,6 @@ def test_ipc_channel_break_during_stream(
     spawn_backend: str,
     ipc_break: dict|None,
     pre_aclose_msgstream: bool,
-    tpt_proto: str,
 ):
     '''
     Ensure we can have an IPC channel break its connection during
@@ -94,8 +91,7 @@ def test_ipc_channel_break_during_stream(
 
         # 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 = TransportClosed
+        expect_final_exc = trio.ClosedResourceError
 
     mod: ModuleType = import_path(
         examples_dir() / 'advanced_faults'
@@ -108,8 +104,6 @@ def test_ipc_channel_break_during_stream(
     # period" wherein the user eventually hits ctl-c to kill the
     # root-actor tree.
     expect_final_exc: BaseException = KeyboardInterrupt
-    expect_final_cause: BaseException|None = None
-
     if (
         # only expect EoC if trans is broken on the child side,
         ipc_break['break_child_ipc_after'] is not False
@@ -144,9 +138,6 @@ def test_ipc_channel_break_during_stream(
         # a user sending ctl-c by raising a KBI.
         if pre_aclose_msgstream:
             expect_final_exc = KeyboardInterrupt
-            if tpt_proto == 'uds':
-                expect_final_exc = TransportClosed
-                expect_final_cause = trio.BrokenResourceError
 
             # XXX OLD XXX
             # if child calls `MsgStream.aclose()` then expect EoC.
@@ -166,11 +157,7 @@ def test_ipc_channel_break_during_stream(
         if pre_aclose_msgstream:
             expect_final_exc = KeyboardInterrupt
 
-            if tpt_proto == 'uds':
-                expect_final_exc = TransportClosed
-                expect_final_cause = trio.BrokenResourceError
-
-    # NOTE when the parent IPC side dies (even if the child does as well
+    # NOTE when the parent IPC side dies (even if the child's does as well
     # but the child fails BEFORE the parent) we always expect the
     # IPC layer to raise a closed-resource, NEVER do we expect
     # a stop msg since the parent-side ctx apis will error out
@@ -182,8 +169,7 @@ def test_ipc_channel_break_during_stream(
         and
         ipc_break['break_child_ipc_after'] is False
     ):
-        expect_final_exc = tractor.TransportClosed
-        expect_final_cause = trio.ClosedResourceError
+        expect_final_exc = trio.ClosedResourceError
 
     # BOTH but, PARENT breaks FIRST
     elif (
@@ -194,8 +180,7 @@ def test_ipc_channel_break_during_stream(
             ipc_break['break_parent_ipc_after']
         )
     ):
-        expect_final_exc = tractor.TransportClosed
-        expect_final_cause = trio.ClosedResourceError
+        expect_final_exc = trio.ClosedResourceError
 
     with pytest.raises(
         expected_exception=(
@@ -211,12 +196,11 @@ def test_ipc_channel_break_during_stream(
                     start_method=spawn_backend,
                     loglevel=loglevel,
                     pre_close=pre_aclose_msgstream,
-                    tpt_proto=tpt_proto,
                     **ipc_break,
                 )
             )
-        except KeyboardInterrupt as _kbi:
-            kbi = _kbi
+        except KeyboardInterrupt as kbi:
+            _err = kbi
             if expect_final_exc is not KeyboardInterrupt:
                 pytest.fail(
                     'Rxed unexpected KBI !?\n'
@@ -225,33 +209,16 @@ def test_ipc_channel_break_during_stream(
 
             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
-                type(cause) is expect_final_cause
-
-                # TODO, should we expect a certain exc-message (per
-                # tpt) as well??
-                # 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)
+        value = next(
+            itertools.dropwhile(
+                lambda exc: not isinstance(exc, expect_final_exc),
+                value.exceptions,
+            )
+        )
+        assert value
 
 
 @tractor.context
@@ -274,16 +241,15 @@ async def break_ipc_after_started(
 
 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".
+    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(
+            async with tractor.open_nursery() as n:
+                portal = await n.start_actor(
                     'ipc_breaker',
                     enable_modules=[__name__],
                 )

tests/test_advanced_streaming.py

@@ -307,13 +307,6 @@ 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?
-        tractor.trionics.collapse_eg(),
         trio.open_nursery() as tn,
     ):
         async def close_stream_on_sentinel():

tests/test_cancellation.py

@@ -14,7 +14,7 @@ import tractor
 from tractor._testing import (
     tractor_test,
 )
-from .conftest import no_windows
+from conftest import no_windows
 
 
 def is_win():
@@ -130,7 +130,7 @@ def test_multierror(
             try:
                 await portal2.result()
             except tractor.RemoteActorError as err:
-                assert err.boxed_type is AssertionError
+                assert err.boxed_type == AssertionError
                 print("Look Maa that first actor failed hard, hehh")
                 raise
 
@@ -182,7 +182,7 @@ 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.boxed_type == AssertionError
 
 
 async def do_nothing():
@@ -236,10 +236,7 @@ async def stream_forever():
 async def test_cancel_infinite_streamer(start_method):
 
     # stream for at most 1 seconds
-    with (
-        trio.fail_after(4),
-        trio.move_on_after(1) as cancel_scope
-    ):
+    with trio.move_on_after(1) as cancel_scope:
         async with tractor.open_nursery() as n:
             portal = await n.start_actor(
                 'donny',
@@ -287,32 +284,20 @@ async def test_cancel_infinite_streamer(start_method):
     ],
 )
 @tractor_test
-async def test_some_cancels_all(
-    num_actors_and_errs: tuple,
-    start_method: str,
-    loglevel: str,
-):
-    '''
-    Verify a subset of failed subactors causes all others in
+async def test_some_cancels_all(num_actors_and_errs, start_method, loglevel):
+    """Verify a subset of failed subactors causes all others in
     the nursery to be cancelled just like the strategy in trio.
 
     This is the first and only supervisory strategy at the moment.
-
-    '''
-    (
-        num_actors,
-        first_err,
-        err_type,
-        ria_func,
-        da_func,
-    ) = num_actors_and_errs
+    """
+    num_actors, first_err, err_type, ria_func, da_func = num_actors_and_errs
     try:
-        async with tractor.open_nursery() as an:
+        async with tractor.open_nursery() as n:
 
             # spawn the same number of deamon actors which should be cancelled
             dactor_portals = []
             for i in range(num_actors):
-                dactor_portals.append(await an.start_actor(
+                dactor_portals.append(await n.start_actor(
                     f'deamon_{i}',
                     enable_modules=[__name__],
                 ))
@@ -322,7 +307,7 @@ async def test_some_cancels_all(
             for i in range(num_actors):
                 # start actor(s) that will fail immediately
                 riactor_portals.append(
-                    await an.run_in_actor(
+                    await n.run_in_actor(
                         func,
                         name=f'actor_{i}',
                         **kwargs
@@ -352,8 +337,7 @@ async def test_some_cancels_all(
 
         # should error here with a ``RemoteActorError`` or ``MultiError``
 
-    except first_err as _err:
-        err = _err
+    except first_err as err:
         if isinstance(err, BaseExceptionGroup):
             assert len(err.exceptions) == num_actors
             for exc in err.exceptions:
@@ -364,8 +348,8 @@ async def test_some_cancels_all(
         elif isinstance(err, tractor.RemoteActorError):
             assert err.boxed_type == err_type
 
-        assert an.cancelled is True
-        assert not an._children
+        assert n.cancelled is True
+        assert not n._children
     else:
         pytest.fail("Should have gotten a remote assertion error?")
 
@@ -520,9 +504,7 @@ 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(
@@ -535,15 +517,8 @@ 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 (
-
-                # XXX ?TODO? why no work!?
-                # tractor.trionics.collapse_eg(),
-                trio.open_nursery(
-                    strict_exception_groups=False,
-                ) as tn,
-            ):
-                await tn.start(spawn_and_sleep_forever)
+            async with trio.open_nursery() as n:
+                await n.start(spawn_and_sleep_forever)
                 if 'mp' in spawn_backend:
                     time.sleep(0.1)
                 os.kill(pid, signal.SIGINT)
@@ -554,123 +529,38 @@ def test_cancel_via_SIGINT_other_task(
 
 async def spin_for(period=3):
     "Sync sleep."
-    print(f'sync sleeping in sub-sub for {period}\n')
     time.sleep(period)
 
 
-async def spawn_sub_with_sync_blocking_task():
-    async with tractor.open_nursery() as an:
-        print('starting sync blocking subactor..\n')
-        await an.run_in_actor(
+async def spawn():
+    async with tractor.open_nursery() as tn:
+        await tn.run_in_actor(
             spin_for,
             name='sleeper',
         )
-        print('exiting first subactor layer..\n')
 
 
-@pytest.mark.parametrize(
-    'man_cancel_outer',
-    [
-        False,  # passes if delay != 2
-
-        # always causes an unexpected eg-w-embedded-assert-err?
-        pytest.param(True,
-             marks=pytest.mark.xfail(
-                 reason=(
-                    'always causes an unexpected eg-w-embedded-assert-err?'
-                )
-            ),
-        ),
-    ],
-)
 @no_windows
 def test_cancel_while_childs_child_in_sync_sleep(
-    loglevel: str,
-    start_method: str,
-    spawn_backend: str,
-    debug_mode: bool,
-    reg_addr: tuple,
-    man_cancel_outer: bool,
+    loglevel,
+    start_method,
+    spawn_backend,
 ):
-    '''
-    Verify that a child cancelled while executing sync code is torn
+    """Verify that a child cancelled while executing sync code is torn
     down even when that cancellation is triggered by the parent
     2 nurseries "up".
-
-    Though the grandchild should stay blocking its actor runtime, its
-    parent should issue a "zombie reaper" to hard kill it after
-    sufficient timeout.
-
-    '''
+    """
     if start_method == 'forkserver':
         pytest.skip("Forksever sux hard at resuming from sync sleep...")
 
     async def main():
-        #
-        # XXX BIG TODO NOTE XXX
-        #
-        # it seems there's a strange race that can happen
-        # where where the fail-after will trigger outer scope
-        # .cancel() which then causes the inner scope to raise,
-        #
-        # BaseExceptionGroup('Exceptions from Trio nursery', [
-        #   BaseExceptionGroup('Exceptions from Trio nursery',
-        #   [
-        #       Cancelled(),
-        #       Cancelled(),
-        #   ]
-        #   ),
-        #   AssertionError('assert 0')
-        # ])
-        #
-        # WHY THIS DOESN'T MAKE SENSE:
-        # ---------------------------
-        # - it should raise too-slow-error when too slow..
-        #  * verified that using simple-cs and manually cancelling
-        #    you get same outcome -> indicates that the fail-after
-        #    can have its TooSlowError overriden!
-        #  |_ to check this it's easy, simplly decrease the timeout
-        #     as per the var below.
-        #
-        # - when using the manual simple-cs the outcome is different
-        #   DESPITE the `assert 0` which means regardless of the
-        #   inner scope effectively failing in the same way, the
-        #   bubbling up **is NOT the same**.
-        #
-        # delays trigger diff outcomes..
-        # ---------------------------
-        # as seen by uncommenting various lines below there is from
-        # my POV an unexpected outcome due to the delay=2 case.
-        #
-        # delay = 1  # no AssertionError in eg, TooSlowError raised.
-        # delay = 2  # is AssertionError in eg AND no TooSlowError !?
-        delay = 4  # is AssertionError in eg AND no _cs cancellation.
-
-        with trio.fail_after(delay) as _cs:
-        # with trio.CancelScope() as cs:
-        # ^XXX^ can be used instead to see same outcome.
-
-            async with (
-                # tractor.trionics.collapse_eg(),  # doesn't help
-                tractor.open_nursery(
-                    hide_tb=False,
-                    debug_mode=debug_mode,
-                    registry_addrs=[reg_addr],
-                ) as an,
-            ):
-                await an.run_in_actor(
-                    spawn_sub_with_sync_blocking_task,
-                    name='sync_blocking_sub',
+        with trio.fail_after(2):
+            async with tractor.open_nursery() as tn:
+                await tn.run_in_actor(
+                    spawn,
+                    name='spawn',
                 )
                 await trio.sleep(1)
-
-                if man_cancel_outer:
-                    print('Cancelling manually in root')
-                    _cs.cancel()
-
-                # trigger exc-srced taskc down
-                # the actor tree.
-                print('RAISING IN ROOT')
                 assert 0
 
     with pytest.raises(AssertionError):
@@ -720,12 +610,6 @@ 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_caps_based_msging.py

@@ -0,0 +1,930 @@
+'''
+Low-level functional audits for our
+"capability based messaging"-spec feats.
+
+B~)
+
+'''
+import typing
+from typing import (
+    Any,
+    Type,
+    Union,
+)
+from contextvars import (
+    Context,
+)
+
+from msgspec import (
+    structs,
+    msgpack,
+    Struct,
+    ValidationError,
+)
+import pytest
+
+import tractor
+from tractor import (
+    _state,
+    MsgTypeError,
+)
+from tractor.msg import (
+    _codec,
+    _ctxvar_MsgCodec,
+
+    NamespacePath,
+    MsgCodec,
+    mk_codec,
+    apply_codec,
+    current_codec,
+)
+from tractor.msg.types import (
+    _payload_msgs,
+    log,
+    Msg,
+    Started,
+    mk_msg_spec,
+)
+import trio
+
+
+def mk_custom_codec(
+    pld_spec: Union[Type]|Any,
+    add_hooks: bool,
+
+) -> MsgCodec:
+    '''
+    Create custom `msgpack` enc/dec-hooks and set a `Decoder`
+    which only loads `pld_spec` (like `NamespacePath`) types.
+
+    '''
+    uid: tuple[str, str] = tractor.current_actor().uid
+
+    # XXX NOTE XXX: despite defining `NamespacePath` as a type
+    # field on our `Msg.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
+
+    def enc_nsp(obj: Any) -> Any:
+        print(f'{uid} ENC HOOK')
+        match obj:
+            case NamespacePath():
+                print(
+                    f'{uid}: `NamespacePath`-Only ENCODE?\n'
+                    f'obj-> `{obj}`: {type(obj)}\n'
+                )
+                # if type(obj) != NamespacePath:
+                #     breakpoint()
+                return str(obj)
+
+        print(
+            f'{uid}\n'
+            'CUSTOM ENCODE\n'
+            f'obj-arg-> `{obj}`: {type(obj)}\n'
+        )
+        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:
+        print(
+            f'{uid}\n'
+            'CUSTOM DECODE\n'
+            f'type-arg-> {obj_type}\n'
+            f'obj-arg-> `{obj}`: {type(obj)}\n'
+        )
+        nsp = None
+
+        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)
+
+    nsp_codec: MsgCodec = mk_codec(
+        ipc_pld_spec=pld_spec,
+
+        # 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?
+        dec_hook=dec_nsp if add_hooks else None,
+    )
+    return nsp_codec
+
+
+def chk_codec_applied(
+    expect_codec: MsgCodec,
+    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]
+
+    # 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:
+        enter_value is same_codec
+
+
+def iter_maybe_sends(
+    send_items: dict[Union[Type], Any] | list[tuple],
+    ipc_pld_spec: Union[Type] | Any,
+    add_codec_hooks: bool,
+
+    codec: MsgCodec|None = None,
+
+) -> tuple[Any, bool]:
+
+    if isinstance(send_items, dict):
+        send_items = send_items.items()
+
+    for (
+        send_type_spec,
+        send_value,
+    ) in send_items:
+
+        expect_roundtrip: bool = False
+
+        # values-to-typespec santiy
+        send_type = type(send_value)
+        assert send_type == send_type_spec or (
+            (subtypes := getattr(send_type_spec, '__args__', None))
+            and send_type in subtypes
+        )
+
+        spec_subtypes: set[Union[Type]] = (
+             getattr(
+                 ipc_pld_spec,
+                 '__args__',
+                 {ipc_pld_spec,},
+             )
+        )
+        send_in_spec: bool = (
+            send_type == ipc_pld_spec
+            or (
+                ipc_pld_spec != Any
+                and  # presume `Union` of types
+                send_type in spec_subtypes
+            )
+            or (
+                ipc_pld_spec == Any
+                and
+                send_type != NamespacePath
+            )
+        )
+        expect_roundtrip = (
+            send_in_spec
+            # any spec should support all other
+            # builtin py values that we send
+            # except our custom nsp type which
+            # we should be able to send as long
+            # as we provide the custom codec hooks.
+            or (
+                ipc_pld_spec == Any
+                and
+                send_type == NamespacePath
+                and
+                add_codec_hooks
+            )
+        )
+
+        if codec is not None:
+            # XXX FIRST XXX ensure roundtripping works
+            # before touching any IPC primitives/APIs.
+            wire_bytes: bytes = codec.encode(
+                Started(
+                    cid='blahblah',
+                    pld=send_value,
+                )
+            )
+            # NOTE: demonstrates the decoder loading
+            # to via our native SCIPP msg-spec
+            # (structurred-conc-inter-proc-protocol)
+            # implemented as per,
+            try:
+                msg: Started = codec.decode(wire_bytes)
+                if not expect_roundtrip:
+                    pytest.fail(
+                        f'NOT-EXPECTED able to roundtrip value given spec:\n'
+                        f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                        f'value -> {send_value}: {send_type}\n'
+                    )
+
+                pld = msg.pld
+                assert pld == send_value
+
+            except ValidationError:
+                if expect_roundtrip:
+                    pytest.fail(
+                        f'EXPECTED to roundtrip value given spec:\n'
+                        f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                        f'value -> {send_value}: {send_type}\n'
+                    )
+
+        yield (
+            str(send_type),
+            send_value,
+            expect_roundtrip,
+        )
+
+
+def dec_type_union(
+    type_names: list[str],
+) -> Type:
+    '''
+    Look up types by name, compile into a list and then create and
+    return a `typing.Union` from the full set.
+
+    '''
+    import importlib
+    types: list[Type] = []
+    for type_name in type_names:
+        for ns in [
+            typing,
+            importlib.import_module(__name__),
+        ]:
+            if type_ref := getattr(
+                ns,
+                type_name,
+                False,
+            ):
+                types.append(type_ref)
+
+    # special case handling only..
+    # ipc_pld_spec: Union[Type] = eval(
+    #     pld_spec_str,
+    #     {},  # globals
+    #     {'typing': typing},  # locals
+    # )
+
+    return Union[*types]
+
+
+def enc_type_union(
+    union_or_type: Union[Type]|Type,
+) -> list[str]:
+    '''
+    Encode a type-union or single type to a list of type-name-strings
+    ready for IPC interchange.
+
+    '''
+    type_strs: list[str] = []
+    for typ in getattr(
+        union_or_type,
+        '__args__',
+        {union_or_type,},
+    ):
+        type_strs.append(typ.__qualname__)
+
+    return type_strs
+
+
+@tractor.context
+async def send_back_values(
+    ctx: Context,
+    expect_debug: bool,
+    pld_spec_type_strs: list[str],
+    add_hooks: bool,
+    started_msg_bytes: bytes,
+    expect_ipc_send: dict[str, tuple[Any, 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
+
+    # debug mode sanity check (prolly superfluous but, meh)
+    assert expect_debug == _state.debug_mode()
+
+    # init state in sub-actor should be default
+    chk_codec_applied(
+        expect_codec=_codec._def_tractor_codec,
+    )
+
+    # load pld spec from input str
+    ipc_pld_spec = dec_type_union(
+        pld_spec_type_strs,
+    )
+    pld_spec_str = str(ipc_pld_spec)
+
+    # same as on parent side config.
+    nsp_codec: MsgCodec = mk_custom_codec(
+        pld_spec=ipc_pld_spec,
+        add_hooks=add_hooks,
+    )
+    with (
+        apply_codec(nsp_codec) as codec,
+    ):
+        chk_codec_applied(
+            expect_codec=nsp_codec,
+            enter_value=codec,
+        )
+
+        print(
+            f'{uid}: attempting `Started`-bytes DECODE..\n'
+        )
+        try:
+            msg: Started = nsp_codec.decode(started_msg_bytes)
+            expected_pld_spec_str: str = msg.pld
+            assert pld_spec_str == expected_pld_spec_str
+
+        # 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 ValidationError:
+
+            # NOTE: only in the `Any` spec case do we expect this to
+            # work since otherwise no spec covers a plain-ol'
+            # `.pld: str`
+            if pld_spec_str == 'Any':
+                raise
+            else:
+                print(
+                    f'{uid}: (correctly) unable to DECODE `Started`-bytes\n'
+                    f'{started_msg_bytes}\n'
+                )
+
+        iter_send_val_items = iter(expect_ipc_send.values())
+        sent: list[Any] = []
+        for send_value, expect_send in iter_send_val_items:
+            try:
+                print(
+                    f'{uid}: attempting to `.started({send_value})`\n'
+                    f'=> expect_send: {expect_send}\n'
+                    f'SINCE, ipc_pld_spec: {ipc_pld_spec}\n'
+                    f'AND, codec: {codec}\n'
+                )
+                await ctx.started(send_value)
+                sent.append(send_value)
+                if not expect_send:
+
+                    # XXX NOTE XXX THIS WON'T WORK WITHOUT SPECIAL
+                    # `str` handling! or special debug mode IPC
+                    # msgs!
+                    await tractor.pause()
+
+                    raise RuntimeError(
+                        f'NOT-EXPECTED able to roundtrip value given spec:\n'
+                        f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                        f'value -> {send_value}: {type(send_value)}\n'
+                    )
+
+                break  # move on to streaming block..
+
+            except tractor.MsgTypeError:
+                await tractor.pause()
+
+                if expect_send:
+                    raise RuntimeError(
+                        f'EXPECTED to `.started()` value given spec:\n'
+                        f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                        f'value -> {send_value}: {type(send_value)}\n'
+                    )
+
+        async with ctx.open_stream() as ipc:
+            print(
+                f'{uid}: Entering streaming block to send remaining values..'
+            )
+
+            for send_value, expect_send in iter_send_val_items:
+                send_type: Type = type(send_value)
+                print(
+                    '------ - ------\n'
+                    f'{uid}: SENDING NEXT VALUE\n'
+                    f'ipc_pld_spec: {ipc_pld_spec}\n'
+                    f'expect_send: {expect_send}\n'
+                    f'val: {send_value}\n'
+                    '------ - ------\n'
+                )
+                try:
+                    await ipc.send(send_value)
+                    print(f'***\n{uid}-CHILD sent {send_value!r}\n***\n')
+                    sent.append(send_value)
+
+                    # NOTE: should only raise above on
+                    # `.started()` or a `Return`
+                    # if not expect_send:
+                    #     raise RuntimeError(
+                    #         f'NOT-EXPECTED able to roundtrip value given spec:\n'
+                    #         f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                    #         f'value -> {send_value}: {send_type}\n'
+                    #     )
+
+                except ValidationError:
+                    print(f'{uid} FAILED TO SEND {send_value}!')
+
+                    # await tractor.pause()
+                    if expect_send:
+                        raise RuntimeError(
+                            f'EXPECTED to roundtrip value given spec:\n'
+                            f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                            f'value -> {send_value}: {send_type}\n'
+                        )
+                    # continue
+
+            else:
+                print(
+                    f'{uid}: finished sending all values\n'
+                    'Should be exiting stream block!\n'
+                )
+
+        print(f'{uid}: exited streaming block!')
+
+        # TODO: this won't be true bc in streaming phase we DO NOT
+        # msgspec check outbound msgs!
+        # -[ ] once we implement the receiver side `InvalidMsg`
+        #   then we can expect it here?
+        # assert (
+        #     len(sent)
+        #     ==
+        #     len([val
+        #          for val, expect in
+        #          expect_ipc_send.values()
+        #          if expect is True])
+        # )
+
+
+def ex_func(*args):
+    print(f'ex_func({args})')
+
+
+@pytest.mark.parametrize(
+    'ipc_pld_spec',
+    [
+        Any,
+        NamespacePath,
+        NamespacePath|None,  # the "maybe" spec Bo
+    ],
+    ids=[
+        'any_type',
+        'nsp_type',
+        'maybe_nsp_type',
+    ]
+)
+@pytest.mark.parametrize(
+    'add_codec_hooks',
+    [
+        True,
+        False,
+    ],
+    ids=['use_codec_hooks', 'no_codec_hooks'],
+)
+def test_codec_hooks_mod(
+    debug_mode: bool,
+    ipc_pld_spec: Union[Type]|Any,
+    # send_value: None|str|NamespacePath,
+    add_codec_hooks: bool,
+):
+    '''
+    Audit the `.msg.MsgCodec` override apis details given our impl
+    uses `contextvars` to accomplish per `trio` task codec
+    application around an inter-proc-task-comms context.
+
+    '''
+    async def main():
+        nsp = NamespacePath.from_ref(ex_func)
+        send_items: dict[Union, Any] = {
+            Union[None]: None,
+            Union[NamespacePath]: nsp,
+            Union[str]: str(nsp),
+        }
+
+        # init default state for actor
+        chk_codec_applied(
+            expect_codec=_codec._def_tractor_codec,
+        )
+
+        async with tractor.open_nursery(
+            debug_mode=debug_mode,
+        ) as an:
+            p: tractor.Portal = await an.start_actor(
+                'sub',
+                enable_modules=[__name__],
+            )
+
+            # TODO: 2 cases:
+            # - codec not modified -> decode nsp as `str`
+            # - codec modified with hooks -> decode nsp as
+            #   `NamespacePath`
+            nsp_codec: MsgCodec = mk_custom_codec(
+                pld_spec=ipc_pld_spec,
+                add_hooks=add_codec_hooks,
+            )
+            with apply_codec(nsp_codec) as codec:
+                chk_codec_applied(
+                    expect_codec=nsp_codec,
+                    enter_value=codec,
+                )
+
+                expect_ipc_send: dict[str, tuple[Any, bool]] = {}
+
+                report: str = (
+                    'Parent report on send values with\n'
+                    f'ipc_pld_spec: {ipc_pld_spec}\n'
+                    '       ------ - ------\n'
+                )
+                for val_type_str, val, expect_send in iter_maybe_sends(
+                    send_items,
+                    ipc_pld_spec,
+                    add_codec_hooks=add_codec_hooks,
+                ):
+                    report += (
+                        f'send_value: {val}: {type(val)} '
+                        f'=> expect_send: {expect_send}\n'
+                    )
+                    expect_ipc_send[val_type_str] = (val, expect_send)
+
+                print(
+                    report +
+                    '       ------ - ------\n'
+                )
+                assert len(expect_ipc_send) == len(send_items)
+                # now try over real IPC with a the subactor
+                # expect_ipc_rountrip: bool = True
+                expected_started = Started(
+                    cid='cid',
+                    pld=str(ipc_pld_spec),
+                )
+                # build list of values we expect to receive from
+                # the subactor.
+                expect_to_send: list[Any] = [
+                    val
+                    for val, expect_send in expect_ipc_send.values()
+                    if expect_send
+                ]
+
+                pld_spec_type_strs: list[str] = enc_type_union(ipc_pld_spec)
+
+                # XXX should raise an mte (`MsgTypeError`)
+                # when `add_codec_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?
+                if not add_codec_hooks:
+                    try:
+                        async with p.open_context(
+                            send_back_values,
+                            expect_debug=debug_mode,
+                            pld_spec_type_strs=pld_spec_type_strs,
+                            add_hooks=add_codec_hooks,
+                            started_msg_bytes=nsp_codec.encode(expected_started),
+
+                            # XXX NOTE bc we send a `NamespacePath` in this kwarg
+                            expect_ipc_send=expect_ipc_send,
+
+                        ) as (ctx, first):
+                            pytest.fail('ctx should fail to open without custom enc_hook!?')
+
+                    # this test passes bc we can go no further!
+                    except MsgTypeError:
+                        # teardown nursery
+                        await p.cancel_actor()
+                        return
+
+                # TODO: send the original nsp here and
+                # test with `limit_msg_spec()` above?
+                # await tractor.pause()
+                print('PARENT opening IPC ctx!\n')
+                async with (
+
+                    # XXX should raise an mte (`MsgTypeError`)
+                    # when `add_codec_hooks == False`..
+                    p.open_context(
+                        send_back_values,
+                        expect_debug=debug_mode,
+                        pld_spec_type_strs=pld_spec_type_strs,
+                        add_hooks=add_codec_hooks,
+                        started_msg_bytes=nsp_codec.encode(expected_started),
+                        expect_ipc_send=expect_ipc_send,
+                    ) as (ctx, first),
+
+                    ctx.open_stream() as ipc,
+                ):
+                    # ensure codec is still applied across
+                    # `tractor.Context` + its embedded nursery.
+                    chk_codec_applied(
+                        expect_codec=nsp_codec,
+                        enter_value=codec,
+                    )
+                    print(
+                        'root: ENTERING CONTEXT BLOCK\n'
+                        f'type(first): {type(first)}\n'
+                        f'first: {first}\n'
+                    )
+                    expect_to_send.remove(first)
+
+                    # TODO: explicit values we expect depending on
+                    # codec config!
+                    # assert first == first_val
+                    # assert first == f'{__name__}:ex_func'
+
+                    async for next_sent in ipc:
+                        print(
+                            'Parent: child sent next value\n'
+                            f'{next_sent}: {type(next_sent)}\n'
+                        )
+                        if expect_to_send:
+                            expect_to_send.remove(next_sent)
+                        else:
+                            print('PARENT should terminate stream loop + block!')
+
+                    # all sent values should have arrived!
+                    assert not expect_to_send
+
+            await p.cancel_actor()
+
+    trio.run(main)
+
+
+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 `Msg.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[Msg[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 `Msg[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: Msg = 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
+
+
+def test_limit_msgspec():
+
+    async def main():
+        async with tractor.open_root_actor(
+            debug_mode=True
+        ):
+
+            # ensure we can round-trip a boxing `Msg`
+            assert chk_pld_type(
+                # Msg,
+                Any,
+                None,
+                expect_roundtrip=True,
+            )
+
+            # TODO: don't need this any more right since
+            # `msgspec>=0.15` has the nice generics stuff yah??
+            #
+            # manually override the type annot of the payload
+            # field and ensure it propagates to all msg-subtypes.
+            # Msg.__annotations__['pld'] = Any
+
+            # verify that a mis-typed payload value won't decode
+            assert not chk_pld_type(
+                # Msg,
+                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(
+                # Msg,
+                CustomPayload,
+                pld='doggy',
+            )
+
+            assert chk_pld_type(
+                # Msg,
+                CustomPayload,
+                pld=CustomPayload(name='doggy', value='urmom')
+            )
+
+            # uhh bc we can `.pause_from_sync()` now! :surfer:
+            # breakpoint()
+
+    trio.run(main)

tests/test_child_manages_service_nursery.py

@@ -95,8 +95,8 @@ 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 +104,10 @@ 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()
 
@@ -117,11 +117,8 @@ async def open_actor_local_nursery(
     ctx: tractor.Context,
 ):
     global _nursery
-    async with (
-        tractor.trionics.collapse_eg(),
-        trio.open_nursery() as tn
-    ):
-        _nursery = tn
+    async with trio.open_nursery() as n:
+        _nursery = n
         await ctx.started()
         await trio.sleep(10)
         # await trio.sleep(1)
@@ -135,7 +132,7 @@ 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(
@@ -160,7 +157,7 @@ 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 (

tests/test_clustering.py

@@ -13,24 +13,26 @@ MESSAGE = 'tractoring at full speed'
 def test_empty_mngrs_input_raises() -> None:
 
     async def main():
-        with trio.fail_after(3):
+        with trio.fail_after(1):
             async with (
                 open_actor_cluster(
                     modules=[__name__],
 
                     # NOTE: ensure we can passthrough runtime opts
-                    loglevel='cancel',
-                    debug_mode=False,
+                    loglevel='info',
+                    # debug_mode=True,
 
                 ) as portals,
 
-                gather_contexts(mngrs=()),
+                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()
+                    ),
+                ),
             ):
-                # should fail before this?
-                assert portals
-
-                # test should fail if we mk it here!
-                assert 0, 'Should have raised val-err !?'
+                assert 0
 
     with pytest.raises(ValueError):
         trio.run(main)

tests/test_context_stream_semantics.py

@@ -38,9 +38,9 @@ from tractor._testing import (
 # - standard setup/teardown:
 #   ``Portal.open_context()`` starts a new
 #   remote task context in another actor. The target actor's task must
-#   call ``Context.started()`` to unblock this entry on the parent side.
-#   the child task executes until complete and returns a final value
-#   which is delivered to the parent side and retreived via
+#   call ``Context.started()`` to unblock this entry on the caller side.
+#   the callee task executes until complete and returns a final value
+#   which is delivered to the caller side and retreived via
 #   ``Context.result()``.
 
 # - cancel termination:
@@ -170,9 +170,9 @@ async def assert_state(value: bool):
     [False, ValueError, KeyboardInterrupt],
 )
 @pytest.mark.parametrize(
-    'child_blocks_forever',
+    'callee_blocks_forever',
     [False, True],
-    ids=lambda item: f'child_blocks_forever={item}'
+    ids=lambda item: f'callee_blocks_forever={item}'
 )
 @pytest.mark.parametrize(
     'pointlessly_open_stream',
@@ -181,7 +181,7 @@ async def assert_state(value: bool):
 )
 def test_simple_context(
     error_parent,
-    child_blocks_forever,
+    callee_blocks_forever,
     pointlessly_open_stream,
     debug_mode: bool,
 ):
@@ -204,13 +204,13 @@ def test_simple_context(
                         portal.open_context(
                             simple_setup_teardown,
                             data=10,
-                            block_forever=child_blocks_forever,
+                            block_forever=callee_blocks_forever,
                         ) as (ctx, sent),
                     ):
                         assert current_ipc_ctx() is ctx
                         assert sent == 11
 
-                        if child_blocks_forever:
+                        if callee_blocks_forever:
                             await portal.run(assert_state, value=True)
                         else:
                             assert await ctx.result() == 'yo'
@@ -220,7 +220,7 @@ def test_simple_context(
                                 if error_parent:
                                     raise error_parent
 
-                                if child_blocks_forever:
+                                if callee_blocks_forever:
                                     await ctx.cancel()
                                 else:
                                     # in this case the stream will send a
@@ -252,16 +252,16 @@ def test_simple_context(
             pass
         except BaseExceptionGroup as beg:
             # XXX: on windows it seems we may have to expect the group error
-            from tractor.trionics import is_multi_cancelled
+            from tractor._exceptions import is_multi_cancelled
             assert is_multi_cancelled(beg)
     else:
         trio.run(main)
 
 
 @pytest.mark.parametrize(
-    'child_returns_early',
+    'callee_returns_early',
     [True, False],
-    ids=lambda item: f'child_returns_early={item}'
+    ids=lambda item: f'callee_returns_early={item}'
 )
 @pytest.mark.parametrize(
     'cancel_method',
@@ -273,14 +273,14 @@ def test_simple_context(
     [True, False],
     ids=lambda item: f'chk_ctx_result_before_exit={item}'
 )
-def test_parent_cancels(
+def test_caller_cancels(
     cancel_method: str,
     chk_ctx_result_before_exit: bool,
-    child_returns_early: bool,
+    callee_returns_early: bool,
     debug_mode: bool,
 ):
     '''
-    Verify that when the opening side of a context (aka the parent)
+    Verify that when the opening side of a context (aka the caller)
     cancels that context, the ctx does not raise a cancelled when
     either calling `.result()` or on context exit.
 
@@ -294,7 +294,7 @@ def test_parent_cancels(
 
         if (
             cancel_method == 'portal'
-            and not child_returns_early
+            and not callee_returns_early
         ):
             try:
                 res = await ctx.result()
@@ -318,7 +318,7 @@ def test_parent_cancels(
                 pytest.fail(f'should not have raised ctxc\n{ctxc}')
 
         # we actually get a result
-        if child_returns_early:
+        if callee_returns_early:
             assert res == 'yo'
             assert ctx.outcome is res
             assert ctx.maybe_error is None
@@ -362,14 +362,14 @@ def test_parent_cancels(
             )
             timeout: float = (
                 0.5
-                if not child_returns_early
+                if not callee_returns_early
                 else 2
             )
             with trio.fail_after(timeout):
                 async with (
                     expect_ctxc(
                         yay=(
-                            not child_returns_early
+                            not callee_returns_early
                             and cancel_method == 'portal'
                         )
                     ),
@@ -377,13 +377,13 @@ def test_parent_cancels(
                     portal.open_context(
                         simple_setup_teardown,
                         data=10,
-                        block_forever=not child_returns_early,
+                        block_forever=not callee_returns_early,
                     ) as (ctx, sent),
                 ):
 
-                    if child_returns_early:
+                    if callee_returns_early:
                         # ensure we block long enough before sending
-                        # a cancel such that the child has already
+                        # a cancel such that the callee has already
                         # returned it's result.
                         await trio.sleep(0.5)
 
@@ -421,7 +421,7 @@ def test_parent_cancels(
             #   which should in turn cause `ctx._scope` to
             # catch any cancellation?
             if (
-                not child_returns_early
+                not callee_returns_early
                 and cancel_method != 'portal'
             ):
                 assert not ctx._scope.cancelled_caught
@@ -430,11 +430,11 @@ def test_parent_cancels(
 
 
 # basic stream terminations:
-# - child context closes without using stream
-# - parent context closes without using stream
-# - parent context calls `Context.cancel()` while streaming
-#   is ongoing resulting in child being cancelled
-# - child calls `Context.cancel()` while streaming and parent
+# - callee context closes without using stream
+# - caller context closes without using stream
+# - caller context calls `Context.cancel()` while streaming
+#   is ongoing resulting in callee being cancelled
+# - callee calls `Context.cancel()` while streaming and caller
 #   sees stream terminated in `RemoteActorError`
 
 # TODO: future possible features
@@ -443,6 +443,7 @@ def test_parent_cancels(
 
 @tractor.context
 async def close_ctx_immediately(
+
     ctx: Context,
 
 ) -> None:
@@ -453,24 +454,13 @@ async def close_ctx_immediately(
     async with ctx.open_stream():
         pass
 
-    print('child returning!')
 
-
-@pytest.mark.parametrize(
-    'parent_send_before_receive',
-    [
-        False,
-        True,
-    ],
-    ids=lambda item: f'child_send_before_receive={item}'
-)
 @tractor_test
-async def test_child_exits_ctx_after_stream_open(
+async def test_callee_closes_ctx_after_stream_open(
     debug_mode: bool,
-    parent_send_before_receive: bool,
 ):
     '''
-    child context closes without using stream.
+    callee context closes without using stream.
 
     This should result in a msg sequence
     |_<root>_
@@ -484,9 +474,6 @@ async def test_child_exits_ctx_after_stream_open(
     => {'stop': True, 'cid': <str>}
 
     '''
-    timeout: float = (
-        0.5 if not debug_mode else 999
-    )
     async with tractor.open_nursery(
         debug_mode=debug_mode,
     ) as an:
@@ -495,7 +482,7 @@ async def test_child_exits_ctx_after_stream_open(
             enable_modules=[__name__],
         )
 
-        with trio.fail_after(timeout):
+        with trio.fail_after(0.5):
             async with portal.open_context(
                 close_ctx_immediately,
 
@@ -507,56 +494,41 @@ async def test_child_exits_ctx_after_stream_open(
 
                 with trio.fail_after(0.4):
                     async with ctx.open_stream() as stream:
-                        if parent_send_before_receive:
-                            print('sending first msg from parent!')
-                            await stream.send('yo')
 
                         # should fall through since ``StopAsyncIteration``
                         # should be raised through translation of
                         # a ``trio.EndOfChannel`` by
                         # ``trio.abc.ReceiveChannel.__anext__()``
-                        msg = 10
-                        async for msg in stream:
+                        async for _ in stream:
                             # trigger failure if we DO NOT
                             # get an EOC!
                             assert 0
                         else:
-                            # never should get anythinig new from
-                            # the underlying stream
-                            assert msg == 10
 
                             # verify stream is now closed
                             try:
                                 with trio.fail_after(0.3):
-                                    print('parent trying to `.receive()` on EoC stream!')
                                     await stream.receive()
-                                    assert 0, 'should have raised eoc!?'
                             except trio.EndOfChannel:
-                                print('parent got EoC as expected!')
                                 pass
-                                # raise
 
                 # TODO: should be just raise the closed resource err
                 # directly here to enforce not allowing a re-open
                 # of a stream to the context (at least until a time of
                 # if/when we decide that's a good idea?)
                 try:
-                    with trio.fail_after(timeout):
+                    with trio.fail_after(0.5):
                         async with ctx.open_stream() as stream:
                             pass
                 except trio.ClosedResourceError:
                     pass
 
-                # if ctx._rx_chan._state.data:
-                #     await tractor.pause()
-
         await portal.cancel_actor()
 
 
 @tractor.context
 async def expect_cancelled(
     ctx: Context,
-    send_before_receive: bool = False,
 
 ) -> None:
     global _state
@@ -566,10 +538,6 @@ async def expect_cancelled(
 
     try:
         async with ctx.open_stream() as stream:
-
-            if send_before_receive:
-                await stream.send('yo')
-
             async for msg in stream:
                 await stream.send(msg)  # echo server
 
@@ -596,49 +564,26 @@ async def expect_cancelled(
         raise
 
     else:
-        assert 0, "child wasn't cancelled !?"
+        assert 0, "callee wasn't cancelled !?"
 
 
-@pytest.mark.parametrize(
-    'child_send_before_receive',
-    [
-        False,
-        True,
-    ],
-    ids=lambda item: f'child_send_before_receive={item}'
-)
-@pytest.mark.parametrize(
-    'rent_wait_for_msg',
-    [
-        False,
-        True,
-    ],
-    ids=lambda item: f'rent_wait_for_msg={item}'
-)
 @pytest.mark.parametrize(
     'use_ctx_cancel_method',
-    [
-        False,
-        'pre_stream',
-        'post_stream_open',
-        'post_stream_close',
-    ],
-    ids=lambda item: f'use_ctx_cancel_method={item}'
+    [False, True],
 )
 @tractor_test
-async def test_parent_exits_ctx_after_child_enters_stream(
-    use_ctx_cancel_method: bool|str,
+async def test_caller_closes_ctx_after_callee_opens_stream(
+    use_ctx_cancel_method: bool,
     debug_mode: bool,
-    rent_wait_for_msg: bool,
-    child_send_before_receive: bool,
 ):
     '''
-    Parent-side of IPC context closes without sending on `MsgStream`.
+    caller context closes without using/opening stream
 
     '''
     async with tractor.open_nursery(
         debug_mode=debug_mode,
     ) as an:
+
         root: Actor = current_actor()
         portal = await an.start_actor(
             'ctx_cancelled',
@@ -647,52 +592,41 @@ async def test_parent_exits_ctx_after_child_enters_stream(
 
         async with portal.open_context(
             expect_cancelled,
-            send_before_receive=child_send_before_receive,
         ) as (ctx, sent):
             assert sent is None
 
             await portal.run(assert_state, value=True)
 
             # call `ctx.cancel()` explicitly
-            if use_ctx_cancel_method == 'pre_stream':
+            if use_ctx_cancel_method:
                 await ctx.cancel()
 
                 # NOTE: means the local side `ctx._scope` will
                 # have been cancelled by an ctxc ack and thus
                 # `._scope.cancelled_caught` should be set.
-                async with (
-                    expect_ctxc(
-                        # XXX: the cause is US since we call
-                        # `Context.cancel()` just above!
-                        yay=True,
-
-                        # XXX: must be propagated to __aexit__
-                        # and should be silently absorbed there
-                        # since we called `.cancel()` just above ;)
-                        reraise=True,
-                    ) as maybe_ctxc,
-                ):
+                try:
                     async with ctx.open_stream() as stream:
+                        async for msg in stream:
+                            pass
 
-                        if rent_wait_for_msg:
-                            async for msg in stream:
-                                print(f'PARENT rx: {msg!r}\n')
-                                break
+                except tractor.ContextCancelled as ctxc:
+                    # XXX: the cause is US since we call
+                    # `Context.cancel()` just above!
+                    assert (
+                        ctxc.canceller
+                        ==
+                        current_actor().uid
+                        ==
+                        root.uid
+                    )
 
-                        if use_ctx_cancel_method == 'post_stream_open':
-                            await ctx.cancel()
+                    # XXX: must be propagated to __aexit__
+                    # and should be silently absorbed there
+                    # since we called `.cancel()` just above ;)
+                    raise
 
-                    if use_ctx_cancel_method == 'post_stream_close':
-                        await ctx.cancel()
-
-                ctxc: tractor.ContextCancelled = maybe_ctxc.value
-                assert (
-                    ctxc.canceller
-                    ==
-                    current_actor().uid
-                    ==
-                    root.uid
-                )
+                else:
+                    assert 0, "Should have context cancelled?"
 
                 # channel should still be up
                 assert portal.channel.connected()
@@ -703,20 +637,13 @@ async def test_parent_exits_ctx_after_child_enters_stream(
                     value=False,
                 )
 
-            # XXX CHILD-BLOCKS case, we SHOULD NOT exit from the
-            # `.open_context()` before the child has returned,
-            # errored or been cancelled!
             else:
                 try:
-                    with trio.fail_after(
-                        0.5  # if not debug_mode else 999
-                    ):
-                        res = await ctx.wait_for_result()
-                        assert res is not tractor._context.Unresolved
+                    with trio.fail_after(0.2):
+                        await ctx.result()
                         assert 0, "Callee should have blocked!?"
                 except trio.TooSlowError:
-                    # NO-OP -> since already triggered by
-                    # `trio.fail_after()` above!
+                    # NO-OP -> since already called above
                     await ctx.cancel()
 
         # NOTE: local scope should have absorbed the cancellation since
@@ -756,7 +683,7 @@ async def test_parent_exits_ctx_after_child_enters_stream(
 
 
 @tractor_test
-async def test_multitask_parent_cancels_from_nonroot_task(
+async def test_multitask_caller_cancels_from_nonroot_task(
     debug_mode: bool,
 ):
     async with tractor.open_nursery(
@@ -808,6 +735,7 @@ async def test_multitask_parent_cancels_from_nonroot_task(
 
 @tractor.context
 async def cancel_self(
+
     ctx: Context,
 
 ) -> None:
@@ -847,11 +775,11 @@ async def cancel_self(
 
 
 @tractor_test
-async def test_child_cancels_before_started(
+async def test_callee_cancels_before_started(
     debug_mode: bool,
 ):
     '''
-    Callee calls `Context.cancel()` while streaming and parent
+    Callee calls `Context.cancel()` while streaming and caller
     sees stream terminated in `ContextCancelled`.
 
     '''
@@ -898,13 +826,14 @@ async def never_open_stream(
 
 
 @tractor.context
-async def keep_sending_from_child(
+async def keep_sending_from_callee(
+
     ctx:  Context,
     msg_buffer_size: int|None = None,
 
 ) -> None:
     '''
-    Send endlessly on the child stream.
+    Send endlessly on the calleee stream.
 
     '''
     await ctx.started()
@@ -912,7 +841,7 @@ async def keep_sending_from_child(
         msg_buffer_size=msg_buffer_size,
     ) as stream:
         for msg in count():
-            print(f'child sending {msg}')
+            print(f'callee sending {msg}')
             await stream.send(msg)
             await trio.sleep(0.01)
 
@@ -920,12 +849,12 @@ async def keep_sending_from_child(
 @pytest.mark.parametrize(
     'overrun_by',
     [
-        ('parent', 1, never_open_stream),
-        ('child', 0, keep_sending_from_child),
+        ('caller', 1, never_open_stream),
+        ('callee', 0, keep_sending_from_callee),
     ],
     ids=[
-         ('parent_1buf_never_open_stream'),
-         ('child_0buf_keep_sending_from_child'),
+         ('caller_1buf_never_open_stream'),
+         ('callee_0buf_keep_sending_from_callee'),
     ]
 )
 def test_one_end_stream_not_opened(
@@ -956,7 +885,8 @@ def test_one_end_stream_not_opened(
                 ) as (ctx, sent):
                     assert sent is None
 
-                    if 'parent' in overrunner:
+                    if 'caller' in overrunner:
+
                         async with ctx.open_stream() as stream:
 
                             # itersend +1 msg more then the buffer size
@@ -971,7 +901,7 @@ def test_one_end_stream_not_opened(
                                 await trio.sleep_forever()
 
                     else:
-                        # child overruns parent case so we do nothing here
+                        # callee overruns caller case so we do nothing here
                         await trio.sleep_forever()
 
             await portal.cancel_actor()
@@ -979,19 +909,19 @@ def test_one_end_stream_not_opened(
     # 2 overrun cases and the no overrun case (which pushes right up to
     # the msg limit)
     if (
-        overrunner == 'parent'
+        overrunner == 'caller'
     ):
         with pytest.raises(tractor.RemoteActorError) as excinfo:
             trio.run(main)
 
         assert excinfo.value.boxed_type == StreamOverrun
 
-    elif overrunner == 'child':
+    elif overrunner == 'callee':
         with pytest.raises(tractor.RemoteActorError) as excinfo:
             trio.run(main)
 
         # TODO: embedded remote errors so that we can verify the source
-        # error? the child delivers an error which is an overrun
+        # error? the callee delivers an error which is an overrun
         # wrapped in a remote actor error.
         assert excinfo.value.boxed_type == tractor.RemoteActorError
 
@@ -1001,7 +931,8 @@ def test_one_end_stream_not_opened(
 
 @tractor.context
 async def echo_back_sequence(
-    ctx: Context,
+
+    ctx:  Context,
     seq: list[int],
     wait_for_cancel: bool,
     allow_overruns_side: str,
@@ -1010,12 +941,12 @@ async def echo_back_sequence(
 
 ) -> None:
     '''
-    Send endlessly on the child stream using a small buffer size
+    Send endlessly on the calleee stream using a small buffer size
     setting on the contex to simulate backlogging that would normally
     cause overruns.
 
     '''
-    # NOTE: ensure that if the parent is expecting to cancel this task
+    # NOTE: ensure that if the caller is expecting to cancel this task
     # that we stay echoing much longer then they are so we don't
     # return early instead of receive the cancel msg.
     total_batches: int = (
@@ -1024,7 +955,7 @@ async def echo_back_sequence(
     )
 
     await ctx.started()
-    # await tractor.pause()
+    # await tractor.breakpoint()
     async with ctx.open_stream(
         msg_buffer_size=msg_buffer_size,
 
@@ -1065,18 +996,18 @@ async def echo_back_sequence(
                 if be_slow:
                     await trio.sleep(0.05)
 
-                print('child waiting on next')
+                print('callee waiting on next')
 
-            print(f'child echoing back latest batch\n{batch}')
+            print(f'callee echoing back latest batch\n{batch}')
             for msg in batch:
-                print(f'child sending msg\n{msg}')
+                print(f'callee sending msg\n{msg}')
                 await stream.send(msg)
 
     try:
         return 'yo'
     finally:
         print(
-            'exiting child with context:\n'
+            'exiting callee with context:\n'
             f'{pformat(ctx)}\n'
         )
 
@@ -1130,7 +1061,7 @@ def test_maybe_allow_overruns_stream(
             debug_mode=debug_mode,
         ) as an:
             portal = await an.start_actor(
-                'child_sends_forever',
+                'callee_sends_forever',
                 enable_modules=[__name__],
                 loglevel=loglevel,
                 debug_mode=debug_mode,

tests/test_debugger.py

@@ -1,45 +1,39 @@
 """
 That "native" debug mode better work!
 
-All these tests can be understood (somewhat) by running the
-equivalent `examples/debugging/` scripts manually.
+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?
+    - 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?
 
 """
-from __future__ import annotations
 from functools import partial
 import itertools
 import platform
+import pathlib
 import time
-from typing import (
-    TYPE_CHECKING,
-)
 
 import pytest
+import pexpect
 from pexpect.exceptions import (
     TIMEOUT,
     EOF,
 )
 
-from .conftest import (
-    do_ctlc,
-    PROMPT,
+from tractor.devx._debug import (
     _pause_msg,
     _crash_msg,
     _repl_fail_msg,
 )
-from .conftest import (
-    expect,
-    in_prompt_msg,
-    assert_before,
+from tractor._testing import (
+    examples_dir,
+)
+from conftest import (
+    _ci_env,
 )
-
-if TYPE_CHECKING:
-    from ..conftest import PexpectSpawner
 
 # TODO: The next great debugger audit could be done by you!
 # - recurrent entry to breakpoint() from single actor *after* and an
@@ -58,6 +52,15 @@ if platform.system() == 'Windows':
     )
 
 
+def mk_cmd(ex_name: str) -> str:
+    '''
+    Generate a command suitable to pass to ``pexpect.spawn()``.
+
+    '''
+    script_path: pathlib.Path = examples_dir() / 'debugging' / f'{ex_name}.py'
+    return ' '.join(['python', str(script_path)])
+
+
 # TODO: was trying to this xfail style but some weird bug i see in CI
 # that's happening at collect time.. pretty soon gonna dump actions i'm
 # thinkin...
@@ -76,6 +79,142 @@ has_nested_actors = pytest.mark.has_nested_actors
 # )
 
 
+@pytest.fixture
+def spawn(
+    start_method,
+    testdir,
+    reg_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
+
+
+PROMPT = r"\(Pdb\+\)"
+
+
+def expect(
+    child,
+
+    # prompt by default
+    patt: str = PROMPT,
+
+    **kwargs,
+
+) -> None:
+    '''
+    Expect wrapper that prints last seen console
+    data before failing.
+
+    '''
+    try:
+        child.expect(
+            patt,
+            **kwargs,
+        )
+    except TIMEOUT:
+        before = str(child.before.decode())
+        print(before)
+        raise
+
+
+def in_prompt_msg(
+    prompt: str,
+    parts: list[str],
+
+    pause_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
+
+    for part in parts:
+        if part not in prompt:
+            if pause_on_false:
+                import pdbp
+                pdbp.set_trace()
+
+            if print_prompt_on_false:
+                print(prompt)
+
+            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,
+    patts: list[str],
+
+    **kwargs,
+
+) -> None:
+    __tracebackhide__: bool = False
+
+    # as in before the prompt end
+    before: str = str(child.before.decode())
+    assert in_prompt_msg(
+        prompt=before,
+        parts=patts,
+
+        **kwargs
+    )
+
+
+@pytest.fixture(
+    params=[False, True],
+    ids='ctl-c={}'.format,
+)
+def ctlc(
+    request,
+    ci_env: bool,
+
+) -> bool:
+
+    use_ctlc = request.param
+
+    node = request.node
+    markers = node.own_markers
+    for mark in markers:
+        if mark.name == 'has_nested_actors':
+            pytest.skip(
+                f'Test {node} has nested actors and fails with Ctrl-C.\n'
+                f'The test can sometimes run fine locally but until'
+                ' we solve' 'this issue this CI test will be xfail:\n'
+                'https://github.com/goodboy/tractor/issues/320'
+            )
+
+    if use_ctlc:
+        # XXX: disable pygments highlighting for auto-tests
+        # since some envs (like actions CI) will struggle
+        # the the added color-char encoding..
+        from tractor.devx._debug import TractorConfig
+        TractorConfig.use_pygements = False
+
+    yield use_ctlc
+
+
 @pytest.mark.parametrize(
     'user_in_out',
     [
@@ -99,15 +238,14 @@ def test_root_actor_error(
     # scan for the prompt
     expect(child, PROMPT)
 
+    before = str(child.before.decode())
+
     # make sure expected logging and error arrives
     assert in_prompt_msg(
-        child,
-        [
-            _crash_msg,
-            "('root'",
-            'AssertionError',
-        ]
+        before,
+        [_crash_msg, "('root'"]
     )
+    assert 'AssertionError' in before
 
     # send user command
     child.sendline(user_input)
@@ -126,10 +264,8 @@ def test_root_actor_error(
     ids=lambda item: f'{item[0]} -> {item[1]}',
 )
 def test_root_actor_bp(spawn, user_in_out):
-    '''
-    Demonstrate breakpoint from in root actor.
-
-    '''
+    """Demonstrate breakpoint from in root actor.
+    """
     user_input, expect_err_str = user_in_out
     child = spawn('root_actor_breakpoint')
 
@@ -143,7 +279,7 @@ def test_root_actor_bp(spawn, user_in_out):
     child.expect('\r\n')
 
     # process should exit
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
     if expect_err_str is None:
         assert 'Error' not in str(child.before)
@@ -151,6 +287,38 @@ def test_root_actor_bp(spawn, user_in_out):
         assert expect_err_str in str(child.before)
 
 
+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,
+
+) -> None:
+
+    # make sure ctl-c sends don't do anything but repeat output
+    for _ in range(count):
+        time.sleep(delay)
+        child.sendcontrol('c')
+
+        # TODO: figure out why this makes CI fail..
+        # if you run this test manually it works just fine..
+        if expect_prompt:
+            before = str(child.before.decode())
+            time.sleep(delay)
+            child.expect(PROMPT)
+            time.sleep(delay)
+
+            if patt:
+                # should see the last line on console
+                assert patt in before
+
+
 def test_root_actor_bp_forever(
     spawn,
     ctlc: bool,
@@ -190,7 +358,7 @@ def test_root_actor_bp_forever(
 
     # quit out of the loop
     child.sendline('q')
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
 
 @pytest.mark.parametrize(
@@ -212,12 +380,10 @@ def test_subactor_error(
     # scan for the prompt
     child.expect(PROMPT)
 
+    before = str(child.before.decode())
     assert in_prompt_msg(
-        child,
-        [
-            _crash_msg,
-            "('name_error'",
-        ]
+        before,
+        [_crash_msg, "('name_error'"]
     )
 
     if do_next:
@@ -236,15 +402,17 @@ def test_subactor_error(
         child.sendline('continue')
 
     child.expect(PROMPT)
+    before = str(child.before.decode())
+
+    # root actor gets debugger engaged
     assert in_prompt_msg(
-        child,
-        [
-            _crash_msg,
-            # root actor gets debugger engaged
-            "('root'",
-            # error is a remote error propagated from the subactor
-            "('name_error'",
-        ]
+        before,
+        [_crash_msg, "('root'"]
+    )
+    # error is a remote error propagated from the subactor
+    assert in_prompt_msg(
+        before,
+        [_crash_msg, "('name_error'"]
     )
 
     # another round
@@ -255,7 +423,7 @@ def test_subactor_error(
     child.expect('\r\n')
 
     # process should exit
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
 
 def test_subactor_breakpoint(
@@ -265,11 +433,14 @@ def test_subactor_breakpoint(
     "Single subactor with an infinite breakpoint loop"
 
     child = spawn('subactor_breakpoint')
+
+    # scan for the prompt
     child.expect(PROMPT)
+
+    before = str(child.before.decode())
     assert in_prompt_msg(
-        child,
-        [_pause_msg,
-         "('breakpoint_forever'",]
+        before,
+        [_pause_msg, "('breakpoint_forever'"]
     )
 
     # do some "next" commands to demonstrate recurrent breakpoint
@@ -285,8 +456,9 @@ def test_subactor_breakpoint(
     for _ in range(5):
         child.sendline('continue')
         child.expect(PROMPT)
+        before = str(child.before.decode())
         assert in_prompt_msg(
-            child,
+            before,
             [_pause_msg, "('breakpoint_forever'"]
         )
 
@@ -299,8 +471,9 @@ def test_subactor_breakpoint(
     # child process should exit but parent will capture pdb.BdbQuit
     child.expect(PROMPT)
 
+    before = str(child.before.decode())
     assert in_prompt_msg(
-        child,
+        before,
         ['RemoteActorError:',
          "('breakpoint_forever'",
          'bdb.BdbQuit',]
@@ -313,15 +486,14 @@ def test_subactor_breakpoint(
     child.sendline('c')
 
     # process should exit
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
+    before = str(child.before.decode())
     assert in_prompt_msg(
-        child, [
-        'RemoteActorError:',
+        before,
+        ['RemoteActorError:',
          "('breakpoint_forever'",
-         'bdb.BdbQuit',
-        ],
-        pause_on_false=True,
+         'bdb.BdbQuit',]
     )
 
 
@@ -342,7 +514,7 @@ def test_multi_subactors(
 
     before = str(child.before.decode())
     assert in_prompt_msg(
-        child,
+        before,
         [_pause_msg, "('breakpoint_forever'"]
     )
 
@@ -363,14 +535,12 @@ def test_multi_subactors(
 
     # first name_error failure
     child.expect(PROMPT)
+    before = str(child.before.decode())
     assert in_prompt_msg(
-        child,
-        [
-            _crash_msg,
-            "('name_error'",
-            "NameError",
-        ]
+        before,
+        [_crash_msg, "('name_error'"]
     )
+    assert "NameError" in before
 
     if ctlc:
         do_ctlc(child)
@@ -394,8 +564,9 @@ def test_multi_subactors(
     # breakpoint loop should re-engage
     child.sendline('c')
     child.expect(PROMPT)
+    before = str(child.before.decode())
     assert in_prompt_msg(
-        child,
+        before,
         [_pause_msg, "('breakpoint_forever'"]
     )
 
@@ -458,7 +629,7 @@ def test_multi_subactors(
 
     # process should exit
     child.sendline('c')
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
     # repeat of previous multierror for final output
     assert_before(child, [
@@ -488,28 +659,25 @@ def test_multi_daemon_subactors(
     # the root's tty lock first so anticipate either crash
     # message on the first entry.
 
-    bp_forev_parts = [
-        _pause_msg,
-        "('bp_forever'",
-    ]
+    bp_forev_parts = [_pause_msg, "('bp_forever'"]
     bp_forev_in_msg = partial(
         in_prompt_msg,
         parts=bp_forev_parts,
     )
 
-    name_error_msg: str = "NameError: name 'doggypants' is not defined"
-    name_error_parts: list[str] = [name_error_msg]
+    name_error_msg = "NameError: name 'doggypants' is not defined"
+    name_error_parts = [name_error_msg]
 
     before = str(child.before.decode())
 
-    if bp_forev_in_msg(child=child):
+    if bp_forev_in_msg(prompt=before):
         next_parts = name_error_parts
 
     elif name_error_msg in before:
         next_parts = bp_forev_parts
 
     else:
-        raise ValueError('Neither log msg was found !?')
+        raise ValueError("Neither log msg was found !?")
 
     if ctlc:
         do_ctlc(child)
@@ -534,7 +702,7 @@ def test_multi_daemon_subactors(
     # now the root actor won't clobber the bp_forever child
     # during it's first access to the debug lock, but will instead
     # wait for the lock to release, by the edge triggered
-    # ``devx.debug.Lock.no_remote_has_tty`` event before sending cancel messages
+    # ``devx._debug.Lock.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
@@ -578,12 +746,14 @@ def test_multi_daemon_subactors(
     # wait for final error in root
     # where it crashs with boxed error
     while True:
-        child.sendline('c')
-        child.expect(PROMPT)
-        if not in_prompt_msg(
-            child,
-            bp_forev_parts
-        ):
+        try:
+            child.sendline('c')
+            child.expect(PROMPT)
+            assert_before(
+                child,
+                bp_forev_parts
+            )
+        except AssertionError:
             break
 
     assert_before(
@@ -599,7 +769,7 @@ def test_multi_daemon_subactors(
     )
 
     child.sendline('c')
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
 
 @has_nested_actors
@@ -675,7 +845,7 @@ def test_multi_subactors_root_errors(
     ])
 
     child.sendline('c')
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
     assert_before(child, [
         # "Attaching to pdb in crashed actor: ('root'",
@@ -764,13 +934,10 @@ def test_root_nursery_cancels_before_child_releases_tty_lock(
     child = spawn('root_cancelled_but_child_is_in_tty_lock')
 
     child.expect(PROMPT)
-    assert_before(
-        child,
-        [
-            "NameError: name 'doggypants' is not defined",
-            "tractor._exceptions.RemoteActorError: ('name_error'",
-        ],
-    )
+
+    before = str(child.before.decode())
+    assert "NameError: name 'doggypants' is not defined" in before
+    assert "tractor._exceptions.RemoteActorError: ('name_error'" not in before
     time.sleep(0.5)
 
     if ctlc:
@@ -808,7 +975,7 @@ def test_root_nursery_cancels_before_child_releases_tty_lock(
 
     for i in range(3):
         try:
-            child.expect(EOF, timeout=0.5)
+            child.expect(pexpect.EOF, timeout=0.5)
             break
         except TIMEOUT:
             child.sendline('c')
@@ -850,7 +1017,7 @@ def test_root_cancels_child_context_during_startup(
         do_ctlc(child)
 
     child.sendline('c')
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
 
 def test_different_debug_mode_per_actor(
@@ -861,8 +1028,9 @@ def test_different_debug_mode_per_actor(
     child.expect(PROMPT)
 
     # only one actor should enter the debugger
+    before = str(child.before.decode())
     assert in_prompt_msg(
-        child,
+        before,
         [_crash_msg, "('debugged_boi'", "RuntimeError"],
     )
 
@@ -870,7 +1038,9 @@ def test_different_debug_mode_per_actor(
         do_ctlc(child)
 
     child.sendline('c')
-    child.expect(EOF)
+    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
@@ -889,6 +1059,103 @@ def test_different_debug_mode_per_actor(
     )
 
 
+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)
+
+    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!
+    before = str(child.before.decode())
+    assert not in_prompt_msg(
+        before,
+        ['`greenback` portal opened!'],
+    )
+    # should be same root task
+    assert_before(
+        child,
+        [
+            _pause_msg,
+            "<Task '__main__.main'",
+            "('root'",
+        ]
+    )
+
+    if ctlc:
+        do_ctlc(child)
+
+    # 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'",
+        ],
+    }
+    while attach_patts:
+        child.sendline('c')
+        child.expect(PROMPT)
+        before = str(child.before.decode())
+        for key in attach_patts.copy():
+            if key in before:
+                expected_patts: str = attach_patts.pop(key)
+                assert_before(
+                    child,
+                    [_pause_msg] + expected_patts
+                )
+                break
+
+        # 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.items():
+            assert not in_prompt_msg(
+                before,
+                other_patts,
+            )
+
+        if ctlc:
+            do_ctlc(child)
+
+    child.sendline('c')
+    child.expect(pexpect.EOF)
+
+
 def test_post_mortem_api(
     spawn,
     ctlc: bool,
@@ -925,7 +1192,6 @@ def test_post_mortem_api(
             "<Task 'name_error'",
             "NameError",
             "('child'",
-            'getattr(doggypants)',  # exc-LoC
         ]
     )
     if ctlc:
@@ -942,8 +1208,8 @@ def test_post_mortem_api(
             "<Task '__main__.main'",
             "('root'",
             "NameError",
+            "tractor.post_mortem()",
             "src_uid=('child'",
-            "tractor.post_mortem()",  # in `main()`-LoC
         ]
     )
     if ctlc:
@@ -961,10 +1227,6 @@ def test_post_mortem_api(
             "('root'",
             "NameError",
             "src_uid=('child'",
-
-            # raising line in `main()` but from crash-handling
-            # in `tractor.open_nursery()`.
-            'async with p.open_context(name_error) as (ctx, first):',
         ]
     )
     if ctlc:
@@ -996,7 +1258,7 @@ def test_post_mortem_api(
     # )
 
     child.sendline('c')
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
 
 def test_shield_pause(
@@ -1071,156 +1333,9 @@ def test_shield_pause(
         ]
     )
     child.sendline('c')
-    child.expect(EOF)
+    child.expect(pexpect.EOF)
 
 
-@pytest.mark.parametrize(
-    'quit_early', [False, True]
-)
-def test_ctxep_pauses_n_maybe_ipc_breaks(
-    spawn: PexpectSpawner,
-    quit_early: bool,
-):
-    '''
-    Audit generator embedded `.pause()`es from within a `@context`
-    endpoint with a chan close at the end, requiring that ctl-c is
-    mashed and zombie reaper kills sub with no hangs.
-
-    '''
-    child = spawn('subactor_bp_in_ctx')
-    child.expect(PROMPT)
-
-    # 3 iters for the `gen()` pause-points
-    for i in range(3):
-        assert_before(
-            child,
-            [
-                _pause_msg,
-                "('bp_boi'",  # actor name
-                "<Task 'just_bp'",  # task name
-            ]
-        )
-        if (
-            i == 1
-            and
-            quit_early
-        ):
-            child.sendline('q')
-            child.expect(PROMPT)
-            assert_before(
-                child,
-                ["tractor._exceptions.RemoteActorError: remote task raised a 'BdbQuit'",
-                 "bdb.BdbQuit",
-                 "('bp_boi'",
-                ]
-            )
-            child.sendline('c')
-            child.expect(EOF)
-            assert_before(
-                child,
-                ["tractor._exceptions.RemoteActorError: remote task raised a 'BdbQuit'",
-                 "bdb.BdbQuit",
-                 "('bp_boi'",
-                ]
-            )
-            break  # end-of-test
-
-        child.sendline('c')
-        try:
-            child.expect(PROMPT)
-        except TIMEOUT:
-            # no prompt since we hang due to IPC chan purposely
-            # closed so verify we see error reporting as well as
-            # a failed crash-REPL request msg and can CTL-c our way
-            # out.
-            assert_before(
-                child,
-                ['peer IPC channel closed abruptly?',
-                 'another task closed this fd',
-                 'Debug lock request was CANCELLED?',
-                 "TransportClosed: 'MsgpackUDSStream' was already closed locally ?",]
-
-                # XXX races on whether these show/hit?
-                 # 'Failed to REPl via `_pause()` You called `tractor.pause()` from an already cancelled scope!',
-                 # 'AssertionError',
-            )
-            # OSc(ancel) the hanging tree
-            do_ctlc(
-                child=child,
-                expect_prompt=False,
-            )
-            child.expect(EOF)
-            assert_before(
-                child,
-                ['KeyboardInterrupt'],
-            )
-
-
-def test_crash_handling_within_cancelled_root_actor(
-    spawn: PexpectSpawner,
-):
-    '''
-    Ensure that when only a root-actor is started via `open_root_actor()`
-    we can crash-handle in debug-mode despite self-cancellation.
-
-    More-or-less ensures we conditionally shield the pause in
-    `._root.open_root_actor()`'s `await debug._maybe_enter_pm()`
-    call.
-
-    '''
-    child = spawn('root_self_cancelled_w_error')
-    child.expect(PROMPT)
-
-    assert_before(
-        child,
-        [
-            "Actor.cancel_soon()` was called!",
-            "root cancelled",
-            _pause_msg,
-            "('root'",  # actor name
-        ]
-    )
-
-    child.sendline('c')
-    child.expect(PROMPT)
-    assert_before(
-        child,
-        [
-            _crash_msg,
-            "('root'",  # actor name
-            "AssertionError",
-            "assert 0",
-        ]
-    )
-
-    child.sendline('c')
-    child.expect(EOF)
-    assert_before(
-        child,
-        [
-            "AssertionError",
-            "assert 0",
-        ]
-    )
-
-
-# TODO: better error for "non-ideal" usage from the root actor.
-# -[ ] if called from an async scope emit a message that suggests
-#    using `await tractor.pause()` instead since it's less overhead
-#    (in terms of `greenback` and/or extra threads) and if it's from
-#    a sync scope suggest that usage must first call
-#    `ensure_portal()` in the (eventual parent) async calling scope?
-def test_sync_pause_from_bg_task_in_root_actor_():
-    '''
-    When used from the root actor, normally we can only implicitly
-    support `.pause_from_sync()` from the main-parent-task (that
-    opens the runtime via `open_root_actor()`) since `greenback`
-    requires a `.ensure_portal()` call per `trio.Task` where it is
-    used.
-
-    '''
-    ...
-
 # TODO: needs ANSI code stripping tho, see `assert_before()` # above!
 def test_correct_frames_below_hidden():
     '''

tests/test_discovery.py

@@ -7,11 +7,8 @@ import platform
 from functools import partial
 import itertools
 
-import psutil
 import pytest
-import subprocess
 import tractor
-from tractor.trionics import collapse_eg
 from tractor._testing import tractor_test
 import trio
 
@@ -29,7 +26,7 @@ async def test_reg_then_unreg(reg_addr):
         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(*reg_addr) as aportal:
             # this local actor should be the arbiter
             assert actor is aportal.actor
 
@@ -155,25 +152,15 @@ async def unpack_reg(actor_or_portal):
 async def spawn_and_check_registry(
     reg_addr: tuple,
     use_signal: bool,
-    debug_mode: bool = False,
     remote_arbiter: bool = False,
     with_streaming: bool = False,
-    maybe_daemon: tuple[
-        subprocess.Popen,
-        psutil.Process,
-    ]|None = None,
 
 ) -> None:
 
-    if maybe_daemon:
-        popen, proc = maybe_daemon
-        # breakpoint()
-
     async with tractor.open_root_actor(
         registry_addrs=[reg_addr],
-        debug_mode=debug_mode,
     ):
-        async with tractor.get_registry(reg_addr) as portal:
+        async with tractor.get_arbiter(*reg_addr) as portal:
             # runtime needs to be up to call this
             actor = tractor.current_actor()
 
@@ -189,30 +176,28 @@ async def spawn_and_check_registry(
                 extra = 2  # local root actor + remote arbiter
 
             # ensure current actor is registered
-            registry: dict = await get_reg()
+            registry = await get_reg()
             assert actor.uid in registry
 
             try:
-                async with tractor.open_nursery() as an:
-                    async with (
-                        collapse_eg(),
-                        trio.open_nursery() as trion,
-                    ):
+                async with tractor.open_nursery() as n:
+                    async with trio.open_nursery() as trion:
+
                         portals = {}
                         for i in range(3):
                             name = f'a{i}'
                             if with_streaming:
-                                portals[name] = await an.start_actor(
+                                portals[name] = await n.start_actor(
                                     name=name, enable_modules=[__name__])
 
                             else:  # no streaming
-                                portals[name] = await an.run_in_actor(
+                                portals[name] = await n.run_in_actor(
                                     trio.sleep_forever, name=name)
 
                         # wait on last actor to come up
                         async with tractor.wait_for_actor(name):
                             registry = await get_reg()
-                            for uid in an._children:
+                            for uid in n._children:
                                 assert uid in registry
 
                         assert len(portals) + extra == len(registry)
@@ -245,7 +230,6 @@ async def spawn_and_check_registry(
 @pytest.mark.parametrize('use_signal', [False, True])
 @pytest.mark.parametrize('with_streaming', [False, True])
 def test_subactors_unregister_on_cancel(
-    debug_mode: bool,
     start_method,
     use_signal,
     reg_addr,
@@ -262,7 +246,6 @@ def test_subactors_unregister_on_cancel(
                 spawn_and_check_registry,
                 reg_addr,
                 use_signal,
-                debug_mode=debug_mode,
                 remote_arbiter=False,
                 with_streaming=with_streaming,
             ),
@@ -272,8 +255,7 @@ def test_subactors_unregister_on_cancel(
 @pytest.mark.parametrize('use_signal', [False, True])
 @pytest.mark.parametrize('with_streaming', [False, True])
 def test_subactors_unregister_on_cancel_remote_daemon(
-    daemon: subprocess.Popen,
-    debug_mode: bool,
+    daemon,
     start_method,
     use_signal,
     reg_addr,
@@ -289,13 +271,8 @@ def test_subactors_unregister_on_cancel_remote_daemon(
                 spawn_and_check_registry,
                 reg_addr,
                 use_signal,
-                debug_mode=debug_mode,
                 remote_arbiter=True,
                 with_streaming=with_streaming,
-                maybe_daemon=(
-                    daemon,
-                    psutil.Process(daemon.pid)
-                ),
             ),
         )
 
@@ -321,7 +298,7 @@ async def close_chans_before_nursery(
     async with tractor.open_root_actor(
         registry_addrs=[reg_addr],
     ):
-        async with tractor.get_registry(reg_addr) as aportal:
+        async with tractor.get_arbiter(*reg_addr) as aportal:
             try:
                 get_reg = partial(unpack_reg, aportal)
 
@@ -339,12 +316,9 @@ async def close_chans_before_nursery(
                         async with portal2.open_stream_from(
                             stream_forever
                         ) as agen2:
-                            async with (
-                                collapse_eg(),
-                                trio.open_nursery() as tn,
-                            ):
-                                tn.start_soon(streamer, agen1)
-                                tn.start_soon(cancel, use_signal, .5)
+                            async with trio.open_nursery() as n:
+                                n.start_soon(streamer, agen1)
+                                n.start_soon(cancel, use_signal, .5)
                                 try:
                                     await streamer(agen2)
                                 finally:
@@ -395,7 +369,7 @@ def test_close_channel_explicit(
 
 @pytest.mark.parametrize('use_signal', [False, True])
 def test_close_channel_explicit_remote_arbiter(
-    daemon: subprocess.Popen,
+    daemon,
     start_method,
     use_signal,
     reg_addr,

tests/test_docs_examples.py

@@ -19,7 +19,7 @@ from tractor._testing import (
 @pytest.fixture
 def run_example_in_subproc(
     loglevel: str,
-    testdir: pytest.Pytester,
+    testdir,
     reg_addr: tuple[str, int],
 ):
 
@@ -66,9 +66,6 @@ def run_example_in_subproc(
         # due to backpressure!!!
         proc = testdir.popen(
             cmdargs,
-            stdin=subprocess.PIPE,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
             **kwargs,
         )
         assert not proc.returncode
@@ -84,37 +81,27 @@ def run_example_in_subproc(
 
     # walk yields: (dirpath, dirnames, filenames)
     [
-        (p[0], f)
-        for p in os.walk(examples_dir())
-        for f in p[2]
+        (p[0], f) for p in os.walk(examples_dir()) for f in p[2]
 
-        if (
-            '__' not in f
-            and f[0] != '_'
-            and 'debugging' not in p[0]
-            and 'integration' not in p[0]
-            and 'advanced_faults' not in p[0]
-            and 'multihost' not in p[0]
-            and 'trio' 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]
     ],
+
     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")
@@ -123,14 +110,10 @@ def test_example(
         code = ex.read()
 
         with run_example_in_subproc(code) as proc:
-            err = None
-            try:
-                if not proc.poll():
-                    _, err = proc.communicate(timeout=15)
-
-            except subprocess.TimeoutExpired as e:
-                proc.kill()
-                err = e.stderr
+            proc.wait()
+            err, _ = proc.stderr.read(), proc.stdout.read()
+            # print(f'STDERR: {err}')
+            # print(f'STDOUT: {out}')
 
             # if we get some gnarly output let's aggregate and raise
             if err:
@@ -144,8 +127,7 @@ def test_example(
                     # 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
+                    and 'asyncio.exceptions.CancelledError' not in last_error
                 ):
                     raise Exception(errmsg)
 

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_inter_peer_cancellation.py

@@ -24,10 +24,14 @@ from tractor._testing import (
 )
 
 # XXX TODO cases:
+# - [ ] peer cancelled itself - so other peers should
+#   get errors reflecting that the peer was itself the .canceller?
+
 # - [x] WE cancelled the peer and thus should not see any raised
 #   `ContextCancelled` as it should be reaped silently?
 #   => pretty sure `test_context_stream_semantics::test_caller_cancels()`
 #      already covers this case?
+
 # - [x] INTER-PEER: some arbitrary remote peer cancels via
 #   Portal.cancel_actor().
 #   => all other connected peers should get that cancel requesting peer's
@@ -40,6 +44,16 @@ from tractor._testing import (
 #   that also spawned a remote task task in that same peer-parent.
 
 
+# def test_self_cancel():
+#     '''
+#     2 cases:
+#     - calls `Actor.cancel()` locally in some task
+#     - calls LocalPortal.cancel_actor()` ?
+
+#     '''
+#     ...
+
+
 @tractor.context
 async def open_stream_then_sleep_forever(
     ctx: Context,
@@ -156,7 +170,7 @@ def test_do_not_swallow_error_before_started_by_remote_contextcancelled(
         trio.run(main)
 
     rae = excinfo.value
-    assert rae.boxed_type is TypeError
+    assert rae.boxed_type == TypeError
 
 
 @tractor.context
@@ -396,6 +410,7 @@ def test_peer_canceller(
     '''
     async def main():
         async with tractor.open_nursery(
+            # NOTE: to halt the peer tasks on ctxc, uncomment this.
             debug_mode=debug_mode,
         ) as an:
             canceller: Portal = await an.start_actor(
@@ -792,7 +807,7 @@ async def basic_echo_server(
     ctx: Context,
     peer_name: str = 'wittle_bruv',
 
-    err_after_imsg: int|None = None,
+    err_after: int|None = None,
 
 ) -> None:
     '''
@@ -821,9 +836,8 @@ async def basic_echo_server(
             await ipc.send(resp)
 
             if (
-                err_after_imsg
-                and
-                i > err_after_imsg
+                err_after
+                and i > err_after
             ):
                 raise RuntimeError(
                     f'Simulated error in `{peer_name}`'
@@ -857,7 +871,7 @@ async def serve_subactors(
                 )
                 await ipc.send((
                     peer.chan.uid,
-                    peer.chan.raddr.unwrap(),
+                    peer.chan.raddr,
                 ))
 
         print('Spawner exiting spawn serve loop!')
@@ -965,8 +979,7 @@ async def tell_little_bro(
     actor_name: str,
 
     caller: str = '',
-    err_after: float|None = None,
-    rng_seed: int = 50,
+    err_after: int|None = None,
 ):
     # contact target actor, do a stream dialog.
     async with (
@@ -977,18 +990,14 @@ async def tell_little_bro(
             basic_echo_server,
 
             # XXX proxy any delayed err condition
-            err_after_imsg=(
-                err_after * rng_seed
-                if err_after is not None
-                else None
-            ),
+            err_after=err_after,
         ) as (sub_ctx, first),
 
         sub_ctx.open_stream() as echo_ipc,
     ):
         actor: Actor = current_actor()
         uid: tuple = actor.uid
-        for i in range(rng_seed):
+        for i in range(100):
             msg: tuple = (
                 uid,
                 i,
@@ -1013,13 +1022,13 @@ async def tell_little_bro(
 )
 @pytest.mark.parametrize(
     'raise_sub_spawn_error_after',
-    [None, 0.5],
+    [None, 50],
 )
 def test_peer_spawns_and_cancels_service_subactor(
     debug_mode: bool,
     raise_client_error: str,
     reg_addr: tuple[str, int],
-    raise_sub_spawn_error_after: float|None,
+    raise_sub_spawn_error_after: int|None,
 ):
     # NOTE: this tests for the modden `mod wks open piker` bug
     # discovered as part of implementing workspace ctx
@@ -1033,7 +1042,6 @@ def test_peer_spawns_and_cancels_service_subactor(
     #   and the server's spawned child should cancel and terminate!
     peer_name: str = 'little_bro'
 
-
     def check_inner_rte(rae: RemoteActorError):
         '''
         Validate the little_bro's relayed inception!
@@ -1127,7 +1135,8 @@ def test_peer_spawns_and_cancels_service_subactor(
                         )
 
                     try:
-                        res = await client_ctx.wait_for_result(hide_tb=False)
+                        res = await client_ctx.result(hide_tb=False)
+
                         # in remote (relayed inception) error
                         # case, we should error on the line above!
                         if raise_sub_spawn_error_after:
@@ -1138,23 +1147,6 @@ def test_peer_spawns_and_cancels_service_subactor(
                         assert isinstance(res, ContextCancelled)
                         assert client_ctx.cancel_acked
                         assert res.canceller == root.uid
-                        assert not raise_sub_spawn_error_after
-
-                        # cancelling the spawner sub should
-                        # transitively cancel it's sub, the little
-                        # bruv.
-                        print('root cancelling server/client sub-actors')
-                        await spawn_ctx.cancel()
-                        async with tractor.find_actor(
-                            name=peer_name,
-                        ) as sub:
-                            assert not sub
-
-                    # XXX, only for tracing
-                    # except BaseException as _berr:
-                    #     berr = _berr
-                    #     await tractor.pause(shield=True)
-                    #     raise berr
 
                     except RemoteActorError as rae:
                         _err = rae
@@ -1183,8 +1175,19 @@ def test_peer_spawns_and_cancels_service_subactor(
                         raise
                         # await tractor.pause()
 
+                    else:
+                        assert not raise_sub_spawn_error_after
+
+                        # cancelling the spawner sub should
+                        # transitively cancel it's sub, the little
+                        # bruv.
+                        print('root cancelling server/client sub-actors')
+                        await spawn_ctx.cancel()
+                        async with tractor.find_actor(
+                            name=peer_name,
+                        ) as sub:
+                            assert not sub
 
-                    # await tractor.pause()
                     # await server.cancel_actor()
 
             except RemoteActorError as rae:
@@ -1197,7 +1200,7 @@ def test_peer_spawns_and_cancels_service_subactor(
 
             # since we called `.cancel_actor()`, `.cancel_ack`
             # will not be set on the ctx bc `ctx.cancel()` was not
-            # called directly for this confext.
+            # called directly fot this confext.
             except ContextCancelled as ctxc:
                 _ctxc = ctxc
                 print(
@@ -1237,19 +1240,12 @@ def test_peer_spawns_and_cancels_service_subactor(
 
                 # assert spawn_ctx.cancelled_caught
 
-    async def _main():
-        with trio.fail_after(
-            3 if not debug_mode
-            else 999
-        ):
-            await main()
-
     if raise_sub_spawn_error_after:
         with pytest.raises(RemoteActorError) as excinfo:
-            trio.run(_main)
+            trio.run(main)
 
         rae: RemoteActorError = excinfo.value
         check_inner_rte(rae)
 
     else:
-        trio.run(_main)
+        trio.run(main)

tests/test_legacy_one_way_streaming.py

@@ -235,16 +235,10 @@ async def cancel_after(wait, reg_addr):
 
 
 @pytest.fixture(scope='module')
-def time_quad_ex(
-    reg_addr: tuple,
-    ci_env: bool,
-    spawn_backend: str,
-):
+def time_quad_ex(reg_addr, ci_env, spawn_backend):
     if spawn_backend == 'mp':
-        '''
-        no idea but the  mp *nix runs are flaking out here often...
-
-        '''
+        """no idea but the  mp *nix runs are flaking out here often...
+        """
         pytest.skip("Test is too flaky on mp in CI")
 
     timeout = 7 if platform.system() in ('Windows', 'Darwin') else 4
@@ -255,24 +249,12 @@ def time_quad_ex(
     return results, diff
 
 
-def test_a_quadruple_example(
-    time_quad_ex: tuple,
-    ci_env: bool,
-    spawn_backend: str,
-):
-    '''
-    This also serves as a kind of "we'd like to be this fast test".
+def test_a_quadruple_example(time_quad_ex, ci_env, spawn_backend):
+    """This also serves as a kind of "we'd like to be this fast test"."""
 
-    '''
     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 3
     assert diff < this_fast
 
 

tests/test_local.py

@@ -38,7 +38,7 @@ async def test_self_is_registered_localportal(reg_addr):
     "Verify waiting on the arbiter to register itself using a local portal."
     actor = tractor.current_actor()
     assert actor.is_arbiter
-    async with tractor.get_registry(reg_addr) as portal:
+    async with tractor.get_arbiter(*reg_addr) as portal:
         assert isinstance(portal, tractor._portal.LocalPortal)
 
         with trio.fail_after(0.2):

tests/test_multi_program.py

@@ -10,7 +10,7 @@ import tractor
 from tractor._testing import (
     tractor_test,
 )
-from .conftest import (
+from conftest import (
     sig_prog,
     _INT_SIGNAL,
     _INT_RETURN_CODE,
@@ -32,7 +32,7 @@ def test_abort_on_sigint(daemon):
 @tractor_test
 async def test_cancel_remote_arbiter(daemon, reg_addr):
     assert not tractor.current_actor().is_arbiter
-    async with tractor.get_registry(reg_addr) as portal:
+    async with tractor.get_arbiter(*reg_addr) as portal:
         await portal.cancel_actor()
 
     time.sleep(0.1)
@@ -41,7 +41,7 @@ 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(*reg_addr) as portal:
             pass
 
 

tests/test_oob_cancellation.py

@@ -1,239 +0,0 @@
-'''
-Define the details of inter-actor "out-of-band" (OoB) cancel
-semantics, that is how cancellation works when a cancel request comes
-from the different concurrency (primitive's) "layer" then where the
-eventual `trio.Task` actually raises a signal.
-
-'''
-from functools import partial
-# from contextlib import asynccontextmanager as acm
-# import itertools
-
-import pytest
-import trio
-import tractor
-from tractor import (  # typing
-    ActorNursery,
-    Portal,
-    Context,
-    # ContextCancelled,
-    # RemoteActorError,
-)
-# from tractor._testing import (
-#     tractor_test,
-#     expect_ctxc,
-# )
-
-# XXX TODO cases:
-# - [ ] peer cancelled itself - so other peers should
-#   get errors reflecting that the peer was itself the .canceller?
-
-# def test_self_cancel():
-#     '''
-#     2 cases:
-#     - calls `Actor.cancel()` locally in some task
-#     - calls LocalPortal.cancel_actor()` ?
-#
-# things to ensure!
-# -[ ] the ctxc raised in a child should ideally show the tb of the
-#     underlying `Cancelled` checkpoint, i.e.
-#     `raise scope_error from ctxc`?
-#
-# -[ ] a self-cancelled context, if not allowed to block on
-#     `ctx.result()` at some point will hang since the `ctx._scope`
-#     is never `.cancel_called`; cases for this include,
-#     - an `open_ctx()` which never starteds before being OoB actor
-#       cancelled.
-#       |_ parent task will be blocked in `.open_context()` for the
-#         `Started` msg, and when the OoB ctxc arrives `ctx._scope`
-#         will never have been signalled..
-
-#     '''
-#     ...
-
-# TODO, sanity test against the case in `/examples/trio/lockacquire_not_unmasked.py`
-# but with the `Lock.acquire()` from a `@context` to ensure the
-# implicit ignore-case-non-unmasking.
-#
-# @tractor.context
-# async def acquire_actor_global_lock(
-#     ctx: tractor.Context,
-#     ignore_special_cases: bool,
-# ):
-
-#     async with maybe_unmask_excs(
-#         ignore_special_cases=ignore_special_cases,
-#     ):
-#         await ctx.started('locked')
-
-#     # block til cancelled
-#     await trio.sleep_forever()
-
-
-@tractor.context
-async def sleep_forever(
-    ctx: tractor.Context,
-    # ignore_special_cases: bool,
-    do_started: bool,
-):
-
-    # async with maybe_unmask_excs(
-    #     ignore_special_cases=ignore_special_cases,
-    # ):
-    #     await ctx.started('locked')
-    if do_started:
-        await ctx.started()
-
-    # block til cancelled
-    print('sleepin on child-side..')
-    await trio.sleep_forever()
-
-
-@pytest.mark.parametrize(
-    'cancel_ctx',
-    [True, False],
-)
-def test_cancel_ctx_with_parent_side_entered_in_bg_task(
-    debug_mode: bool,
-    loglevel: str,
-    cancel_ctx: bool,
-):
-    '''
-    The most "basic" out-of-band-task self-cancellation case where
-    `Portal.open_context()` is entered in a bg task and the
-    parent-task (of the containing nursery) calls `Context.cancel()`
-    without the child knowing; the `Context._scope` should be
-    `.cancel_called` when the IPC ctx's child-side relays
-    a `ContextCancelled` with a `.canceller` set to the parent
-    actor('s task).
-
-    '''
-    async def main():
-        with trio.fail_after(
-            2 if not debug_mode else 999,
-        ):
-            an: ActorNursery
-            async with (
-                tractor.open_nursery(
-                    debug_mode=debug_mode,
-                    loglevel='devx',
-                    enable_stack_on_sig=True,
-                ) as an,
-                trio.open_nursery() as tn,
-            ):
-                ptl: Portal = await an.start_actor(
-                    'sub',
-                    enable_modules=[__name__],
-                )
-
-                async def _open_ctx_async(
-                    do_started: bool = True,
-                    task_status=trio.TASK_STATUS_IGNORED,
-                ):
-                    # do we expect to never enter the
-                    # `.open_context()` below.
-                    if not do_started:
-                        task_status.started()
-
-                    async with ptl.open_context(
-                        sleep_forever,
-                        do_started=do_started,
-                    ) as (ctx, first):
-                        task_status.started(ctx)
-                        await trio.sleep_forever()
-
-                # XXX, this is the key OoB part!
-                #
-                # - start the `.open_context()` in a bg task which
-                #   blocks inside the embedded scope-body,
-                #
-                # -  when we call `Context.cancel()` it **is
-                #   not** from the same task which eventually runs
-                #   `.__aexit__()`,
-                #
-                # - since the bg "opener" task will be in
-                #   a `trio.sleep_forever()`, it must be interrupted
-                #   by the `ContextCancelled` delivered from the
-                #   child-side; `Context._scope: CancelScope` MUST
-                #   be `.cancel_called`!
-                #
-                print('ASYNC opening IPC context in subtask..')
-                maybe_ctx: Context|None = await tn.start(partial(
-                    _open_ctx_async,
-                ))
-
-                if (
-                    maybe_ctx
-                    and
-                    cancel_ctx
-                ):
-                    print('cancelling first IPC ctx!')
-                    await maybe_ctx.cancel()
-
-                # XXX, note that despite `maybe_context.cancel()`
-                # being called above, it's the parent (bg) task
-                # which was originally never interrupted in
-                # the `ctx._scope` body due to missing case logic in
-                # `ctx._maybe_cancel_and_set_remote_error()`.
-                #
-                # It didn't matter that the subactor process was
-                # already terminated and reaped, nothing was
-                # cancelling the ctx-parent task's scope!
-                #
-                print('cancelling subactor!')
-                await ptl.cancel_actor()
-
-                if maybe_ctx:
-                    try:
-                        await maybe_ctx.wait_for_result()
-                    except tractor.ContextCancelled as ctxc:
-                        assert not cancel_ctx
-                        assert (
-                            ctxc.canceller
-                            ==
-                            tractor.current_actor().aid.uid
-                        )
-                        # don't re-raise since it'll trigger
-                        # an EG from the above tn.
-
-    if cancel_ctx:
-        # graceful self-cancel
-        trio.run(main)
-
-    else:
-        # ctx parent task should see OoB ctxc due to
-        # `ptl.cancel_actor()`.
-        with pytest.raises(tractor.ContextCancelled) as excinfo:
-            trio.run(main)
-
-        assert 'root' in excinfo.value.canceller[0]
-
-
-# def test_parent_actor_cancels_subactor_with_gt1_ctxs_open_to_it(
-#     debug_mode: bool,
-#     loglevel: str,
-# ):
-#     '''
-#     Demos OoB cancellation from the perspective of a ctx opened with
-#     a child subactor where the parent cancels the child at the "actor
-#     layer" using `Portal.cancel_actor()` and thus the
-#     `ContextCancelled.canceller` received by the ctx's parent-side
-#     task will appear to be a "self cancellation" even though that
-#     specific task itself was not cancelled and thus
-#     `Context.cancel_called ==False`.
-#     '''
-                # TODO, do we have an existing implied ctx
-                # cancel test like this?
-                # with trio.move_on_after(0.5):# as cs:
-                #     await _open_ctx_async(
-                #         do_started=False,
-                #     )
-
-
-                # in-line ctx scope should definitely raise
-                # a ctxc with `.canceller = 'root'`
-                # async with ptl.open_context(
-                #     sleep_forever,
-                #     do_started=True,
-                # ) as pair:
-

tests/test_pldrx_limiting.py

@@ -285,14 +285,14 @@ def test_basic_payload_spec(
 
             if invalid_started:
                 msg_type_str: str = 'Started'
-                bad_value: int = 10
+                bad_value_str: str = '10'
             elif invalid_return:
                 msg_type_str: str = 'Return'
-                bad_value: str = 'yo'
+                bad_value_str: str = "'yo'"
             else:
                 # XXX but should never be used below then..
                 msg_type_str: str = ''
-                bad_value: str = ''
+                bad_value_str: str = ''
 
             maybe_mte: MsgTypeError|None = None
             should_raise: Exception|None = (
@@ -307,10 +307,8 @@ def test_basic_payload_spec(
                     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`',
+                        f"value: `{bad_value_str}` does not "
+                        f"match type-spec: `{msg_type_str}.pld: PldMsg|NoneType`",
                     ],
                     # only for debug
                     # post_mortem=True,

tests/test_remote_exc_relay.py

@@ -1,237 +0,0 @@
-'''
-Special case testing for issues not (dis)covered in the primary
-`Context` related functional/scenario suites.
-
-**NOTE: this mod is a WIP** space for handling
-odd/rare/undiscovered/not-yet-revealed faults which either
-loudly (ideal case) breakl our supervision protocol
-or (worst case) result in distributed sys hangs.
-
-Suites here further try to clarify (if [partially] ill-defined) and
-verify our edge case semantics for inter-actor-relayed-exceptions
-including,
-
-- lowlevel: what remote obj-data is interchanged for IPC and what is
-  native-obj form is expected from unpacking in the the new
-  mem-domain.
-
-- which kinds of `RemoteActorError` (and its derivs) are expected by which
-  (types of) peers (parent, child, sibling, etc) with what
-  particular meta-data set such as,
-
-  - `.src_uid`: the original (maybe) peer who raised.
-  - `.relay_uid`: the next-hop-peer who sent it.
-  - `.relay_path`: the sequence of peer actor hops.
-  - `.is_inception`: a predicate that denotes multi-hop remote errors.
-
-- when should `ExceptionGroup`s be relayed from a particular
-  remote endpoint, they should never be caused by implicit `._rpc`
-  nursery machinery!
-
-- various special `trio` edge cases around its cancellation semantics
-  and how we (currently) leverage `trio.Cancelled` as a signal for
-  whether a `Context` task should raise `ContextCancelled` (ctx).
-
-'''
-import pytest
-import trio
-import tractor
-from tractor import (  # typing
-    ActorNursery,
-    Portal,
-    Context,
-    ContextCancelled,
-)
-
-
-@tractor.context
-async def sleep_n_chkpt_in_finally(
-    ctx: Context,
-    sleep_n_raise: bool,
-
-    chld_raise_delay: float,
-    chld_finally_delay: float,
-
-    rent_cancels: bool,
-    rent_ctxc_delay: float,
-
-    expect_exc: str|None = None,
-
-) -> None:
-    '''
-    Sync, open a tn, then wait for cancel, run a chkpt inside
-    the user's `finally:` teardown.
-
-    This covers a footgun case that `trio` core doesn't seem to care about
-    wherein an exc can be masked by a `trio.Cancelled` raised inside a tn emedded
-    `finally:`.
-
-    Also see `test_trioisms::test_acm_embedded_nursery_propagates_enter_err`
-    for the down and gritty details.
-
-    Since a `@context` endpoint fn can also contain code like this,
-    **and** bc we currently have no easy way other then
-    `trio.Cancelled` to signal cancellation on each side of an IPC `Context`,
-    the footgun issue can compound itself as demonstrated in this suite..
-
-    Here are some edge cases codified with our WIP "sclang" syntax
-    (note the parent(rent)/child(chld) naming here is just
-    pragmatism, generally these most of these cases can occurr
-    regardless of the distributed-task's supervision hiearchy),
-
-    - rent c)=> chld.raises-then-taskc-in-finally
-     |_ chld's body raises an `exc: BaseException`.
-      _ in its `finally:` block it runs a chkpoint
-        which raises a taskc (`trio.Cancelled`) which
-        masks `exc` instead raising taskc up to the first tn.
-      _ the embedded/chld tn captures the masking taskc and then
-        raises it up to the ._rpc-ep-tn instead of `exc`.
-      _ the rent thinks the child ctxc-ed instead of errored..
-
-    '''
-    await ctx.started()
-
-    if expect_exc:
-        expect_exc: BaseException = tractor._exceptions.get_err_type(
-            type_name=expect_exc,
-        )
-
-    berr: BaseException|None = None
-    try:
-        if not sleep_n_raise:
-            await trio.sleep_forever()
-        elif sleep_n_raise:
-
-            # XXX this sleep is less then the sleep the parent
-            # does before calling `ctx.cancel()`
-            await trio.sleep(chld_raise_delay)
-
-            # XXX this will be masked by a taskc raised in
-            # the `finally:` if this fn doesn't terminate
-            # before any ctxc-req arrives AND a checkpoint is hit
-            # in that `finally:`.
-            raise RuntimeError('my app krurshed..')
-
-    except BaseException as _berr:
-        berr = _berr
-
-        # TODO: it'd sure be nice to be able to inject our own
-        # `ContextCancelled` here instead of of `trio.Cancelled`
-        # so that our runtime can expect it and this "user code"
-        # would be able to tell the diff between a generic trio
-        # cancel and a tractor runtime-IPC cancel.
-        if expect_exc:
-            if not isinstance(
-                berr,
-                expect_exc,
-            ):
-                raise ValueError(
-                    f'Unexpected exc type ??\n'
-                    f'{berr!r}\n'
-                    f'\n'
-                    f'Expected a {expect_exc!r}\n'
-                )
-
-        raise berr
-
-    # simulate what user code might try even though
-    # it's a known boo-boo..
-    finally:
-        # maybe wait for rent ctxc to arrive
-        with trio.CancelScope(shield=True):
-            await trio.sleep(chld_finally_delay)
-
-        # !!XXX this will raise `trio.Cancelled` which
-        # will mask the RTE from above!!!
-        #
-        # YES, it's the same case as our extant
-        # `test_trioisms::test_acm_embedded_nursery_propagates_enter_err`
-        try:
-            await trio.lowlevel.checkpoint()
-        except trio.Cancelled as taskc:
-            if (scope_err := taskc.__context__):
-                print(
-                    f'XXX MASKED REMOTE ERROR XXX\n'
-                    f'ENDPOINT exception -> {scope_err!r}\n'
-                    f'will be masked by -> {taskc!r}\n'
-                )
-                # await tractor.pause(shield=True)
-
-            raise taskc
-
-
-@pytest.mark.parametrize(
-    'chld_callspec',
-    [
-        dict(
-            sleep_n_raise=None,
-            chld_raise_delay=0.1,
-            chld_finally_delay=0.1,
-            expect_exc='Cancelled',
-            rent_cancels=True,
-            rent_ctxc_delay=0.1,
-        ),
-        dict(
-            sleep_n_raise='RuntimeError',
-            chld_raise_delay=0.1,
-            chld_finally_delay=1,
-            expect_exc='RuntimeError',
-            rent_cancels=False,
-            rent_ctxc_delay=0.1,
-        ),
-    ],
-    ids=lambda item: f'chld_callspec={item!r}'
-)
-def test_unmasked_remote_exc(
-    debug_mode: bool,
-    chld_callspec: dict,
-    tpt_proto: str,
-):
-    expect_exc_str: str|None = chld_callspec['sleep_n_raise']
-    rent_ctxc_delay: float|None = chld_callspec['rent_ctxc_delay']
-    async def main():
-        an: ActorNursery
-        async with tractor.open_nursery(
-            debug_mode=debug_mode,
-            enable_transports=[tpt_proto],
-        ) as an:
-            ptl: Portal = await an.start_actor(
-                'cancellee',
-                enable_modules=[__name__],
-            )
-            ctx: Context
-            async with (
-                ptl.open_context(
-                    sleep_n_chkpt_in_finally,
-                    **chld_callspec,
-                ) as (ctx, sent),
-            ):
-                assert not sent
-                await trio.sleep(rent_ctxc_delay)
-                await ctx.cancel()
-
-                # recv error or result from chld
-                ctxc: ContextCancelled = await ctx.wait_for_result()
-                assert (
-                    ctxc is ctx.outcome
-                    and
-                    isinstance(ctxc, ContextCancelled)
-                )
-
-            # always graceful terminate the sub in non-error cases
-            await an.cancel()
-
-    if expect_exc_str:
-        expect_exc: BaseException = tractor._exceptions.get_err_type(
-            type_name=expect_exc_str,
-        )
-        with pytest.raises(
-            expected_exception=tractor.RemoteActorError,
-        ) as excinfo:
-            trio.run(main)
-
-        rae = excinfo.value
-        assert expect_exc == rae.boxed_type
-
-    else:
-        trio.run(main)

tests/test_resource_cache.py

@@ -1,6 +1,5 @@
 '''
-Suites for our `.trionics.maybe_open_context()` multi-task
-shared-cached `@acm` API.
+Async context manager cache api testing: ``trionics.maybe_open_context():``
 
 '''
 from contextlib import asynccontextmanager as acm
@@ -10,15 +9,6 @@ from typing import Awaitable
 import pytest
 import trio
 import tractor
-from tractor.trionics import (
-    maybe_open_context,
-)
-from tractor.log import (
-    get_console_log,
-    get_logger,
-)
-log = get_logger(__name__)
-
 
 
 _resource: int = 0
@@ -62,7 +52,7 @@ def test_resource_only_entered_once(key_on):
                 # different task names per task will be used
                 kwargs = {'task_name': name}
 
-            async with maybe_open_context(
+            async with tractor.trionics.maybe_open_context(
                 maybe_increment_counter,
                 kwargs=kwargs,
                 key=key,
@@ -82,13 +72,11 @@ def test_resource_only_entered_once(key_on):
         with trio.move_on_after(0.5):
             async with (
                 tractor.open_root_actor(),
-                trio.open_nursery() as tn,
+                trio.open_nursery() as n,
             ):
+
                 for i in range(10):
-                    tn.start_soon(
-                        enter_cached_mngr,
-                        f'task_{i}',
-                    )
+                    n.start_soon(enter_cached_mngr, f'task_{i}')
                     await trio.sleep(0.001)
 
     trio.run(main)
@@ -110,55 +98,27 @@ async def streamer(
 
 
 @acm
-async def open_stream() -> Awaitable[
-    tuple[
-        tractor.ActorNursery,
-        tractor.MsgStream,
-    ]
-]:
-    try:
-        async with tractor.open_nursery() as an:
-            portal = await an.start_actor(
-                'streamer',
-                enable_modules=[__name__],
-            )
-            try:
-                async with (
-                    portal.open_context(streamer) as (ctx, first),
-                    ctx.open_stream() as stream,
-                ):
-                    print('Entered open_stream() caller')
-                    yield an, stream
-                    print('Exited open_stream() caller')
+async def open_stream() -> Awaitable[tractor.MsgStream]:
 
-            finally:
-                print(
-                    'Cancelling streamer with,\n'
-                    '=> `Portal.cancel_actor()`'
-                )
-                await portal.cancel_actor()
-                print('Cancelled streamer')
+    async with tractor.open_nursery() as tn:
+        portal = await tn.start_actor('streamer', enable_modules=[__name__])
+        async with (
+            portal.open_context(streamer) as (ctx, first),
+            ctx.open_stream() as stream,
+        ):
+            yield stream
 
-    except Exception as err:
-        print(
-            f'`open_stream()` errored?\n'
-            f'{err!r}\n'
-        )
-        await tractor.pause(shield=True)
-        raise err
+        await portal.cancel_actor()
+    print('CANCELLED STREAMER')
 
 
 @acm
 async def maybe_open_stream(taskname: str):
-    async with maybe_open_context(
+    async with tractor.trionics.maybe_open_context(
         # NOTE: all secondary tasks should cache hit on the same key
         acm_func=open_stream,
-    ) as (
-        cache_hit,
-        (an, stream)
-    ):
-        # when the actor + portal + ctx + stream has already been
-        # allocated we want to just bcast to this task.
+    ) as (cache_hit, stream):
+
         if cache_hit:
             print(f'{taskname} loaded from cache')
 
@@ -166,77 +126,27 @@ async def maybe_open_stream(taskname: str):
             # if this feed is already allocated by the first
             # task that entereed
             async with stream.subscribe() as bstream:
-                yield an, bstream
-                print(
-                    f'cached task exited\n'
-                    f')>\n'
-                    f' |_{taskname}\n'
-                )
-
-            # we should always unreg the "cloned" bcrc for this
-            # consumer-task
-            assert id(bstream) not in bstream._state.subs
-
+                yield bstream
         else:
             # yield the actual stream
-            try:
-                yield an, stream
-            finally:
-                print(
-                    f'NON-cached task exited\n'
-                    f')>\n'
-                    f' |_{taskname}\n'
-                )
-
-        first_bstream = stream._broadcaster
-        bcrx_state = first_bstream._state
-        subs: dict[int, int] = bcrx_state.subs
-        if len(subs) == 1:
-            assert id(first_bstream) in subs
-            # ^^TODO! the bcrx should always de-allocate all subs,
-            # including the implicit first one allocated on entry
-            # by the first subscribing peer task, no?
-            #
-            # -[ ] adjust `MsgStream.subscribe()` to do this mgmt!
-            #  |_ allows reverting `MsgStream.receive()` to the
-            #    non-bcaster method.
-            #  |_ we can decide whether to reset `._broadcaster`?
-            #
-            # await tractor.pause(shield=True)
+            yield stream
 
 
-def test_open_local_sub_to_stream(
-    debug_mode: bool,
-):
+def test_open_local_sub_to_stream():
     '''
     Verify a single inter-actor stream can can be fanned-out shared to
-    N local tasks using `trionics.maybe_open_context()`.
+    N local tasks using ``trionics.maybe_open_context():``.
 
     '''
-    timeout: float = 3.6
-    if platform.system() == "Windows":
-        timeout: float = 10
-
-    if debug_mode:
-        timeout = 999
-        print(f'IN debug_mode, setting large timeout={timeout!r}..')
+    timeout: float = 3.6 if platform.system() != "Windows" else 10
 
     async def main():
 
         full = list(range(1000))
-        an: tractor.ActorNursery|None = None
-        num_tasks: int = 10
 
         async def get_sub_and_pull(taskname: str):
-
-            nonlocal an
-
-            stream: tractor.MsgStream
             async with (
-                maybe_open_stream(taskname) as (
-                    an,
-                    stream,
-                ),
+                maybe_open_stream(taskname) as stream,
             ):
                 if '0' in taskname:
                     assert isinstance(stream, tractor.MsgStream)
@@ -248,159 +158,24 @@ def test_open_local_sub_to_stream(
 
                 first = await stream.receive()
                 print(f'{taskname} started with value {first}')
-                seq: list[int] = []
+                seq = []
                 async for msg in stream:
                     seq.append(msg)
 
                 assert set(seq).issubset(set(full))
-
-            # end of @acm block
             print(f'{taskname} finished')
 
-        root: tractor.Actor
-        with trio.fail_after(timeout) as cs:
+        with trio.fail_after(timeout):
             # TODO: turns out this isn't multi-task entrant XD
             # We probably need an indepotent entry semantic?
-            async with tractor.open_root_actor(
-                debug_mode=debug_mode,
-                # maybe_enable_greenback=True,
-                #
-                # ^TODO? doesn't seem to mk breakpoint() usage work
-                # bc each bg task needs to open a portal??
-                # - [ ] we should consider making this part of
-                #      our taskman defaults?
-                #   |_see https://github.com/goodboy/tractor/pull/363
-                #
-            ) as root:
-                assert root.is_registrar
-
+            async with tractor.open_root_actor():
                 async with (
-                    trio.open_nursery() as tn,
+                    trio.open_nursery() as nurse,
                 ):
-                    for i in range(num_tasks):
-                        tn.start_soon(
-                            get_sub_and_pull,
-                            f'task_{i}',
-                        )
+                    for i in range(10):
+                        nurse.start_soon(get_sub_and_pull, f'task_{i}')
                         await trio.sleep(0.001)
 
-                print('all consumer tasks finished!')
-
-                # ?XXX, ensure actor-nursery is shutdown or we might
-                # hang here due to a minor task deadlock/race-condition?
-                #
-                # - seems that all we need is a checkpoint to ensure
-                #   the last suspended task, which is inside
-                #   `.maybe_open_context()`, can do the
-                #   `Portal.cancel_actor()` call?
-                #
-                # - if that bg task isn't resumed, then this blocks
-                #   timeout might hit before that?
-                #
-                if root.ipc_server.has_peers():
-                    await trio.lowlevel.checkpoint()
-
-                    # alt approach, cancel the entire `an`
-                    # await tractor.pause()
-                    # await an.cancel()
-
-            # end of runtime scope
-            print('root actor terminated.')
-
-        if cs.cancelled_caught:
-            pytest.fail(
-                'Should NOT time out in `open_root_actor()` ?'
-            )
-
-        print('exiting main.')
-
-    trio.run(main)
-
-
-
-@acm
-async def cancel_outer_cs(
-    cs: trio.CancelScope|None = None,
-    delay: float = 0,
-):
-    # on first task delay this enough to block
-    # the 2nd task but then cancel it mid sleep
-    # so that the tn.start() inside the key-err handler block
-    # is cancelled and would previously corrupt the
-    # mutext state.
-    log.info(f'task entering sleep({delay})')
-    await trio.sleep(delay)
-    if cs:
-        log.info('task calling cs.cancel()')
-        cs.cancel()
-    trio.lowlevel.checkpoint()
-    yield
-    await trio.sleep_forever()
-
-
-def test_lock_not_corrupted_on_fast_cancel(
-    debug_mode: bool,
-    loglevel: str,
-):
-    '''
-    Verify that if the caching-task (the first to enter
-    `maybe_open_context()`) is cancelled mid-cache-miss, the embedded
-    mutex can never be left in a corrupted state.
-
-    That is, the lock is always eventually released ensuring a peer
-    (cache-hitting) task will never,
-
-    - be left to inf-block/hang on the `lock.acquire()`.
-    - try to release the lock when still owned by the caching-task
-      due to it having erronously exited without calling
-      `lock.release()`.
-
-
-    '''
-    delay: float = 1.
-
-    async def use_moc(
-        cs: trio.CancelScope|None,
-        delay: float,
-    ):
-        log.info('task entering moc')
-        async with maybe_open_context(
-            cancel_outer_cs,
-            kwargs={
-                'cs': cs,
-                'delay': delay,
-            },
-        ) as (cache_hit, _null):
-            if cache_hit:
-                log.info('2nd task entered')
-            else:
-                log.info('1st task entered')
-
-            await trio.sleep_forever()
-
-    async def main():
-        with trio.fail_after(delay + 2):
-            async with (
-                tractor.open_root_actor(
-                    debug_mode=debug_mode,
-                    loglevel=loglevel,
-                ),
-                trio.open_nursery() as tn,
-            ):
-                get_console_log('info')
-                log.info('yo starting')
-                cs = tn.cancel_scope
-                tn.start_soon(
-                    use_moc,
-                    cs,
-                    delay,
-                    name='child',
-                )
-                with trio.CancelScope() as rent_cs:
-                    await use_moc(
-                        cs=rent_cs,
-                        delay=delay,
-                    )
-
+                print('all consumer tasks finished')
 
     trio.run(main)

tests/test_ringbuf.py

@@ -1,211 +0,0 @@
-import time
-
-import trio
-import pytest
-
-import tractor
-from tractor.ipc._ringbuf import (
-    open_ringbuf,
-    RBToken,
-    RingBuffSender,
-    RingBuffReceiver
-)
-from tractor._testing.samples import (
-    generate_sample_messages,
-)
-
-# in case you don't want to melt your cores, uncomment dis!
-pytestmark = pytest.mark.skip
-
-
-@tractor.context
-async def child_read_shm(
-    ctx: tractor.Context,
-    msg_amount: int,
-    token: RBToken,
-    total_bytes: int,
-) -> None:
-    recvd_bytes = 0
-    await ctx.started()
-    start_ts = time.time()
-    async with RingBuffReceiver(token) as receiver:
-        while recvd_bytes < total_bytes:
-            msg = await receiver.receive_some()
-            recvd_bytes += len(msg)
-
-        # make sure we dont hold any memoryviews
-        # before the ctx manager aclose()
-        msg = None
-
-    end_ts = time.time()
-    elapsed = end_ts - start_ts
-    elapsed_ms = int(elapsed * 1000)
-
-    print(f'\n\telapsed ms: {elapsed_ms}')
-    print(f'\tmsg/sec: {int(msg_amount / elapsed):,}')
-    print(f'\tbytes/sec: {int(recvd_bytes / elapsed):,}')
-
-
-@tractor.context
-async def child_write_shm(
-    ctx: tractor.Context,
-    msg_amount: int,
-    rand_min: int,
-    rand_max: int,
-    token: RBToken,
-) -> None:
-    msgs, total_bytes = generate_sample_messages(
-        msg_amount,
-        rand_min=rand_min,
-        rand_max=rand_max,
-    )
-    await ctx.started(total_bytes)
-    async with RingBuffSender(token) as sender:
-        for msg in msgs:
-            await sender.send_all(msg)
-
-
-@pytest.mark.parametrize(
-    'msg_amount,rand_min,rand_max,buf_size',
-    [
-        # simple case, fixed payloads, large buffer
-        (100_000, 0, 0, 10 * 1024),
-
-        # guaranteed wrap around on every write
-        (100, 10 * 1024, 20 * 1024, 10 * 1024),
-
-        # large payload size, but large buffer
-        (10_000, 256 * 1024, 512 * 1024, 10 * 1024 * 1024)
-    ],
-    ids=[
-        'fixed_payloads_large_buffer',
-        'wrap_around_every_write',
-        'large_payloads_large_buffer',
-    ]
-)
-def test_ringbuf(
-    msg_amount: int,
-    rand_min: int,
-    rand_max: int,
-    buf_size: int
-):
-    async def main():
-        with open_ringbuf(
-            'test_ringbuf',
-            buf_size=buf_size
-        ) as token:
-            proc_kwargs = {
-                'pass_fds': (token.write_eventfd, token.wrap_eventfd)
-            }
-
-            common_kwargs = {
-                'msg_amount': msg_amount,
-                'token': token,
-            }
-            async with tractor.open_nursery() as an:
-                send_p = await an.start_actor(
-                    'ring_sender',
-                    enable_modules=[__name__],
-                    proc_kwargs=proc_kwargs
-                )
-                recv_p = await an.start_actor(
-                    'ring_receiver',
-                    enable_modules=[__name__],
-                    proc_kwargs=proc_kwargs
-                )
-                async with (
-                    send_p.open_context(
-                        child_write_shm,
-                        rand_min=rand_min,
-                        rand_max=rand_max,
-                        **common_kwargs
-                    ) as (sctx, total_bytes),
-                    recv_p.open_context(
-                        child_read_shm,
-                        **common_kwargs,
-                        total_bytes=total_bytes,
-                    ) as (sctx, _sent),
-                ):
-                    await recv_p.result()
-
-                await send_p.cancel_actor()
-                await recv_p.cancel_actor()
-
-
-    trio.run(main)
-
-
-@tractor.context
-async def child_blocked_receiver(
-    ctx: tractor.Context,
-    token: RBToken
-):
-    async with RingBuffReceiver(token) as receiver:
-        await ctx.started()
-        await receiver.receive_some()
-
-
-def test_ring_reader_cancel():
-    async def main():
-        with open_ringbuf('test_ring_cancel_reader') as token:
-            async with (
-                tractor.open_nursery() as an,
-                RingBuffSender(token) as _sender,
-            ):
-                recv_p = await an.start_actor(
-                    'ring_blocked_receiver',
-                    enable_modules=[__name__],
-                    proc_kwargs={
-                        'pass_fds': (token.write_eventfd, token.wrap_eventfd)
-                    }
-                )
-                async with (
-                    recv_p.open_context(
-                        child_blocked_receiver,
-                        token=token
-                    ) as (sctx, _sent),
-                ):
-                    await trio.sleep(1)
-                    await an.cancel()
-
-
-    with pytest.raises(tractor._exceptions.ContextCancelled):
-        trio.run(main)
-
-
-@tractor.context
-async def child_blocked_sender(
-    ctx: tractor.Context,
-    token: RBToken
-):
-    async with RingBuffSender(token) as sender:
-        await ctx.started()
-        await sender.send_all(b'this will wrap')
-
-
-def test_ring_sender_cancel():
-    async def main():
-        with open_ringbuf(
-            'test_ring_cancel_sender',
-            buf_size=1
-        ) as token:
-            async with tractor.open_nursery() as an:
-                recv_p = await an.start_actor(
-                    'ring_blocked_sender',
-                    enable_modules=[__name__],
-                    proc_kwargs={
-                        'pass_fds': (token.write_eventfd, token.wrap_eventfd)
-                    }
-                )
-                async with (
-                    recv_p.open_context(
-                        child_blocked_sender,
-                        token=token
-                    ) as (sctx, _sent),
-                ):
-                    await trio.sleep(1)
-                    await an.cancel()
-
-
-    with pytest.raises(tractor._exceptions.ContextCancelled):
-        trio.run(main)

tests/test_root_infect_asyncio.py

@@ -1,240 +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 if not debug_mode else 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()
-
-    # 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',
-    ):
-        patt: str = 'trio-side'
-        expect_exc = TypeError
-
-    # when aio errors BEFORE (last) trio task is scheduled, we should
-    # never see anythinb but the aio-side.
-    else:
-        patt: str = 'asyncio-side'
-        expect_exc = RuntimeError
-
-    with pytest.raises(expect_exc) as excinfo:
-        tractor.to_asyncio.run_as_asyncio_guest(
-            trio_main=_trio_main,
-        )
-
-    caught_exc = excinfo.value
-    assert patt in caught_exc.args

tests/test_root_runtime.py

@@ -1,108 +0,0 @@
-'''
-Runtime boot/init sanity.
-
-'''
-
-import pytest
-import trio
-
-import tractor
-from tractor._exceptions import RuntimeFailure
-
-
-@tractor.context
-async def open_new_root_in_sub(
-    ctx: tractor.Context,
-) -> None:
-
-    async with tractor.open_root_actor():
-        pass
-
-
-@pytest.mark.parametrize(
-    'open_root_in',
-    ['root', 'sub'],
-    ids='open_2nd_root_in={}'.format,
-)
-def test_only_one_root_actor(
-    open_root_in: str,
-    reg_addr: tuple,
-    debug_mode: bool
-):
-    '''
-    Verify we specially fail whenever more then one root actor
-    is attempted to be opened within an already opened tree.
-
-    '''
-    async def main():
-        async with tractor.open_nursery() as an:
-
-            if open_root_in == 'root':
-                async with tractor.open_root_actor(
-                    registry_addrs=[reg_addr],
-                ):
-                    pass
-
-            ptl: tractor.Portal = await an.start_actor(
-                name='bad_rooty_boi',
-                enable_modules=[__name__],
-            )
-
-            async with ptl.open_context(
-                open_new_root_in_sub,
-            ) as (ctx, first):
-                pass
-
-    if open_root_in == 'root':
-        with pytest.raises(
-            RuntimeFailure
-        ) as excinfo:
-            trio.run(main)
-
-    else:
-        with pytest.raises(
-            tractor.RemoteActorError,
-        ) as excinfo:
-            trio.run(main)
-
-        assert excinfo.value.boxed_type is RuntimeFailure
-
-
-def test_implicit_root_via_first_nursery(
-    reg_addr: tuple,
-    debug_mode: bool
-):
-    '''
-    The first `ActorNursery` open should implicitly call
-    `_root.open_root_actor()`.
-
-    '''
-    async def main():
-        async with tractor.open_nursery() as an:
-            assert an._implicit_runtime_started
-            assert tractor.current_actor().aid.name == 'root'
-
-    trio.run(main)
-
-
-def test_runtime_vars_unset(
-    reg_addr: tuple,
-    debug_mode: bool
-):
-    '''
-    Ensure any `._state._runtime_vars` are restored to default values
-    after the root actor-runtime exits!
-
-    '''
-    assert not tractor._state._runtime_vars['_debug_mode']
-    async def main():
-        assert not tractor._state._runtime_vars['_debug_mode']
-        async with tractor.open_nursery(
-            debug_mode=True,
-        ):
-            assert tractor._state._runtime_vars['_debug_mode']
-
-        # after runtime closure, should be reverted!
-        assert not tractor._state._runtime_vars['_debug_mode']
-
-    trio.run(main)

tests/test_shm.py

@@ -8,7 +8,7 @@ import uuid
 import pytest
 import trio
 import tractor
-from tractor.ipc._shm import (
+from tractor._shm import (
     open_shm_list,
     attach_shm_list,
 )

tests/test_spawning.py

@@ -2,7 +2,6 @@
 Spawning basics
 
 """
-from functools import partial
 from typing import (
     Any,
 )
@@ -13,99 +12,74 @@ import tractor
 
 from tractor._testing import tractor_test
 
-data_to_pass_down = {
-    'doggy': 10,
-    'kitty': 4,
-}
+data_to_pass_down = {'doggy': 10, 'kitty': 4}
 
 
 async def spawn(
-    should_be_root: bool,
+    is_arbiter: bool,
     data: dict,
     reg_addr: tuple[str, int],
-
-    debug_mode: bool = False,
 ):
+    namespaces = [__name__]
+
     await trio.sleep(0.1)
-    actor = tractor.current_actor(err_on_no_runtime=False)
 
-    if should_be_root:
-        assert actor is None  # no runtime yet
-        async with (
-            tractor.open_root_actor(
-                arbiter_addr=reg_addr,
-            ),
-            tractor.open_nursery() as an,
-        ):
-            # now runtime exists
-            actor: tractor.Actor = tractor.current_actor()
-            assert actor.is_arbiter == should_be_root
+    async with tractor.open_root_actor(
+        arbiter_addr=reg_addr,
+    ):
+        actor = tractor.current_actor()
+        assert actor.is_arbiter == is_arbiter
+        data = data_to_pass_down
 
-            # spawns subproc here
-            portal: tractor.Portal = await an.run_in_actor(
-                fn=spawn,
+        if actor.is_arbiter:
+            async with tractor.open_nursery() as nursery:
 
-                # spawning args
-                name='sub-actor',
-                enable_modules=[__name__],
+                # forks here
+                portal = await nursery.run_in_actor(
+                    spawn,
+                    is_arbiter=False,
+                    name='sub-actor',
+                    data=data,
+                    reg_addr=reg_addr,
+                    enable_modules=namespaces,
+                )
 
-                # passed to a subactor-recursive RPC invoke
-                # of this same `spawn()` fn.
-                should_be_root=False,
-                data=data_to_pass_down,
-                reg_addr=reg_addr,
-            )
-
-            assert len(an._children) == 1
-            assert (
-                portal.channel.uid
-                in
-                tractor.current_actor().ipc_server._peers
-            )
-
-            # get result from child subactor
-            result = await portal.result()
-            assert result == 10
-            return result
-    else:
-        assert actor.is_arbiter == should_be_root
-        return 10
+                assert len(nursery._children) == 1
+                assert portal.channel.uid in tractor.current_actor()._peers
+                # be sure we can still get the result
+                result = await portal.result()
+                assert result == 10
+                return result
+        else:
+            return 10
 
 
-def test_run_in_actor_same_func_in_child(
-    reg_addr: tuple,
-    debug_mode: bool,
+def test_local_arbiter_subactor_global_state(
+    reg_addr,
 ):
     result = trio.run(
-        partial(
-            spawn,
-            should_be_root=True,
-            data=data_to_pass_down,
-            reg_addr=reg_addr,
-            debug_mode=debug_mode,
-        )
+        spawn,
+        True,
+        data_to_pass_down,
+        reg_addr,
     )
     assert result == 10
 
 
 async def movie_theatre_question():
-    '''
-    A question asked in a dark theatre, in a tangent
+    """A question asked in a dark theatre, in a tangent
     (errr, I mean different) process.
-
-    '''
+    """
     return 'have you ever seen a portal?'
 
 
 @tractor_test
 async def test_movie_theatre_convo(start_method):
-    '''
-    The main ``tractor`` routine.
+    """The main ``tractor`` routine.
+    """
+    async with tractor.open_nursery() as n:
 
-    '''
-    async with tractor.open_nursery(debug_mode=True) as an:
-
-        portal = await an.start_actor(
+        portal = await n.start_actor(
             'frank',
             # enable the actor to run funcs from this current module
             enable_modules=[__name__],
@@ -144,8 +118,8 @@ async def test_most_beautiful_word(
     with trio.fail_after(1):
         async with tractor.open_nursery(
             debug_mode=debug_mode,
-        ) as an:
-            portal = await an.run_in_actor(
+        ) as n:
+            portal = await n.run_in_actor(
                 cellar_door,
                 return_value=return_value,
                 name='some_linguist',

tests/test_task_broadcasting.py

@@ -2,9 +2,7 @@
 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
@@ -17,7 +15,6 @@ import tractor
 from tractor.trionics import (
     broadcast_receiver,
     Lagged,
-    collapse_eg,
 )
 
 
@@ -65,7 +62,7 @@ async def ensure_sequence(
                 break
 
 
-@acm
+@asynccontextmanager
 async def open_sequence_streamer(
 
     sequence: list[int],
@@ -77,9 +74,9 @@ async def open_sequence_streamer(
     async with tractor.open_nursery(
         arbiter_addr=reg_addr,
         start_method=start_method,
-    ) as an:
+    ) as tn:
 
-        portal = await an.start_actor(
+        portal = await tn.start_actor(
             'sequence_echoer',
             enable_modules=[__name__],
         )
@@ -158,12 +155,9 @@ def test_consumer_and_parent_maybe_lag(
         ) 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(),
@@ -236,8 +230,8 @@ def test_faster_task_to_recv_is_cancelled_by_slower(
 
         ) 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 +253,7 @@ 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 +271,7 @@ 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}')
 
@@ -377,13 +371,13 @@ 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,
@@ -503,7 +497,6 @@ def test_no_raise_on_lag():
                 # internals when the no raise flag is set.
                 loglevel='warning',
             ),
-            collapse_eg(),
             trio.open_nursery() as n,
         ):
             n.start_soon(slow)

tests/test_trioisms.py

@@ -3,21 +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,
-)
-from types import ModuleType
-
-from functools import partial
-
 import pytest
-from _pytest import pathlib
-from tractor.trionics import collapse_eg
 import trio
 from trio import TaskStatus
-from tractor._testing import (
-    examples_dir,
-)
 
 
 @pytest.mark.parametrize(
@@ -72,7 +60,6 @@ def test_stashed_child_nursery(use_start_soon):
     async def main():
 
         async with (
-            collapse_eg(),
             trio.open_nursery() as pn,
         ):
             cn = await pn.start(mk_child_nursery)
@@ -93,210 +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 wraps_tn_that_always_cancels():
-        async with (
-            trio.open_nursery() as tn,
-            tractor.trionics.maybe_raise_from_masking_exc(
-                unmask_from=(
-                    (trio.Cancelled,) if unmask_from_canc
-                    else ()
-                ),
-            )
-        ):
-            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
-
-        if debug_mode:
-            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
-
-
-def test_gatherctxs_with_memchan_breaks_multicancelled(
-    debug_mode: bool,
-):
-    '''
-    Demo how a using an `async with sndchan` inside
-    a `.trionics.gather_contexts()` task will break a strict-eg-tn's
-    multi-cancelled absorption..
-
-    '''
-    from tractor import (
-        trionics,
-    )
-
-    @acm
-    async def open_memchan() -> trio.abc.ReceiveChannel:
-
-        task: trio.Task = trio.lowlevel.current_task()
-        print(
-            f'Opening {task!r}\n'
-        )
-
-        # 1 to force eager sending
-        send, recv = trio.open_memory_channel(16)
-
-        try:
-            async with send:
-                yield recv
-        finally:
-            print(
-                f'Closed {task!r}\n'
-            )
-
-    async def main():
-        async with (
-            # XXX should ensure ONLY the KBI
-            # is relayed upward
-            collapse_eg(),
-            trio.open_nursery(), # as tn,
-
-            trionics.gather_contexts([
-                open_memchan(),
-                open_memchan(),
-            ]) as recv_chans,
-        ):
-            assert len(recv_chans) == 2
-
-            await trio.sleep(1)
-            raise KeyboardInterrupt
-            # tn.cancel_scope.cancel()
-
-    with pytest.raises(KeyboardInterrupt):
-        trio.run(main)
-
-
-@pytest.mark.parametrize(
-    'raise_unmasked', [
-        True,
-        pytest.param(
-            False,
-            marks=pytest.mark.xfail(
-                reason="see examples/trio/send_chan_aclose_masks.py"
-            )
-        ),
-    ]
-)
-@pytest.mark.parametrize(
-    'child_errors_mid_stream',
-    [True, False],
-)
-def test_unmask_aclose_as_checkpoint_on_aexit(
-    raise_unmasked: bool,
-    child_errors_mid_stream: bool,
-    debug_mode: bool,
-):
-    '''
-    Verify that our unmasker util works over the common case where
-    a mem-chan's `.aclose()` is included in an `@acm` stack
-    and it being currently a checkpoint, can `trio.Cancelled`-mask an embedded
-    exception from user code resulting in a silent failure which
-    appears like graceful cancellation.
-
-    This test suite is mostly implemented as an example script so it
-    could more easily be shared with `trio`-core peeps as `tractor`-less
-    minimum reproducing example.
-
-    '''
-    mod: ModuleType = pathlib.import_path(
-        examples_dir()
-        / 'trio'
-        / 'send_chan_aclose_masks_beg.py',
-        root=examples_dir(),
-        consider_namespace_packages=False,
-    )
-    with pytest.raises(RuntimeError):
-        trio.run(partial(
-            mod.main,
-            raise_unmasked=raise_unmasked,
-            child_errors_mid_stream=child_errors_mid_stream,
-        ))
-
-
-
-@pytest.mark.parametrize(
-    'ignore_special_cases', [
-        True,
-        pytest.param(
-            False,
-            marks=pytest.mark.xfail(
-                reason="see examples/trio/lockacquire_not_umasked.py"
-            )
-        ),
-    ]
-)
-def test_cancelled_lockacquire_in_ipctx_not_unmasked(
-    ignore_special_cases: bool,
-    loglevel: str,
-    debug_mode: bool,
-):
-    mod: ModuleType = pathlib.import_path(
-        examples_dir()
-        / 'trio'
-        / 'lockacquire_not_unmasked.py',
-        root=examples_dir(),
-        consider_namespace_packages=False,
-    )
-    async def _main():
-        with trio.fail_after(2):
-            await mod.main(
-                ignore_special_cases=ignore_special_cases,
-                loglevel=loglevel,
-                debug_mode=debug_mode,
-            )
-
-    trio.run(_main)

tractor/__init__.py

@@ -18,7 +18,6 @@
 tractor: structured concurrent ``trio``-"actors".
 
 """
-
 from ._clustering import (
     open_actor_cluster as open_actor_cluster,
 )
@@ -31,7 +30,7 @@ from ._streaming import (
     stream as stream,
 )
 from ._discovery import (
-    get_registry as get_registry,
+    get_arbiter as get_arbiter,
     find_actor as find_actor,
     wait_for_actor as wait_for_actor,
     query_actor as query_actor,
@@ -44,14 +43,12 @@ 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
 )
 from ._exceptions import (
     ContextCancelled as ContextCancelled,
     ModuleNotExposed as ModuleNotExposed,
     MsgTypeError as MsgTypeError,
     RemoteActorError as RemoteActorError,
-    TransportClosed as TransportClosed,
 )
 from .devx import (
     breakpoint as breakpoint,
@@ -64,7 +61,6 @@ from ._root import (
     run_daemon as run_daemon,
     open_root_actor as open_root_actor,
 )
-from .ipc import Channel as Channel
+from ._ipc import Channel as Channel
 from ._portal import Portal as Portal
 from ._runtime import Actor as Actor
-# from . import hilevel as hilevel

tractor/_addr.py

@@ -1,282 +0,0 @@
-# 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 __future__ import annotations
-from uuid import uuid4
-from typing import (
-    Protocol,
-    ClassVar,
-    Type,
-    TYPE_CHECKING,
-)
-
-from bidict import bidict
-from trio import (
-    SocketListener,
-)
-
-from .log import get_logger
-from ._state import (
-    _def_tpt_proto,
-)
-from .ipc._tcp import TCPAddress
-from .ipc._uds import UDSAddress
-
-if TYPE_CHECKING:
-    from ._runtime import Actor
-
-log = get_logger(__name__)
-
-
-# TODO, maybe breakout the netns key to a struct?
-# class NetNs(Struct)[str, int]:
-#     ...
-
-# TODO, can't we just use a type alias
-# for this? namely just some `tuple[str, int, str, str]`?
-#
-# -[ ] would also just be simpler to keep this as SockAddr[tuple]
-#     or something, implying it's just a simple pair of values which can
-#     presumably be mapped to all transports?
-# -[ ] `pydoc socket.socket.getsockname()` delivers a 4-tuple for
-#     ipv6 `(hostaddr, port, flowinfo, scope_id)`.. so how should we
-#     handle that?
-# -[ ] as a further alternative to this wrap()/unwrap() approach we
-#     could just implement `enc/dec_hook()`s for the `Address`-types
-#     and just deal with our internal objs directly and always and
-#     leave it to the codec layer to figure out marshalling?
-#    |_ would mean only one spot to do the `.unwrap()` (which we may
-#       end up needing to call from the hook()s anyway?)
-# -[x] rename to `UnwrappedAddress[Descriptor]` ??
-#    seems like the right name as per,
-#    https://www.geeksforgeeks.org/introduction-to-address-descriptor/
-#
-UnwrappedAddress = (
-    # tcp/udp/uds
-    tuple[
-        str,  # host/domain(tcp), filesys-dir(uds)
-        int|str,  # port/path(uds)
-    ]
-    # ?TODO? should we also include another 2 fields from
-    # our `Aid` msg such that we include the runtime `Actor.uid`
-    # of `.name` and `.uuid`?
-    # - would ensure uniqueness across entire net?
-    # - allows for easier runtime-level filtering of "actors by
-    #   service name"
-)
-
-
-# TODO, maybe rename to `SocketAddress`?
-class Address(Protocol):
-    proto_key: ClassVar[str]
-    unwrapped_type: ClassVar[UnwrappedAddress]
-
-    # TODO, i feel like an `.is_bound()` is a better thing to
-    # support?
-    # Lke, what use does this have besides a noop and if it's not
-    # valid why aren't we erroring on creation/use?
-    @property
-    def is_valid(self) -> bool:
-        ...
-
-    # TODO, maybe `.netns` is a better name?
-    @property
-    def namespace(self) -> tuple[str, int]|None:
-        '''
-        The if-available, OS-specific "network namespace" key.
-
-        '''
-        ...
-
-    @property
-    def bindspace(self) -> str:
-        '''
-        Deliver the socket address' "bindable space" from
-        a `socket.socket.bind()` and thus from the perspective of
-        specific transport protocol domain.
-
-        I.e. for most (layer-4) network-socket protocols this is
-        normally the ipv4/6 address, for UDS this is normally
-        a filesystem (sub-directory).
-
-        For (distributed) network protocols this is normally the routing
-        layer's domain/(ip-)address, though it might also include a "network namespace"
-        key different then the default.
-
-        For local-host-only transports this is either an explicit
-        namespace (with types defined by the OS: netns, Cgroup, IPC,
-        pid, etc. on linux) or failing that the sub-directory in the
-        filesys in which socket/shm files are located *under*.
-
-        '''
-        ...
-
-    @classmethod
-    def from_addr(cls, addr: UnwrappedAddress) -> Address:
-        ...
-
-    def unwrap(self) -> UnwrappedAddress:
-        '''
-        Deliver the underying minimum field set in
-        a primitive python data type-structure.
-        '''
-        ...
-
-    @classmethod
-    def get_random(
-        cls,
-        current_actor: Actor,
-        bindspace: str|None = None,
-    ) -> Address:
-        ...
-
-    # TODO, this should be something like a `.get_def_registar_addr()`
-    # or similar since,
-    # - it should be a **host singleton** (not root/tree singleton)
-    # - we **only need this value** when one isn't provided to the
-    #   runtime at boot and we want to implicitly provide a host-wide
-    #   registrar.
-    # - each rooted-actor-tree should likely have its own
-    #   micro-registry (likely the root being it), also see
-    @classmethod
-    def get_root(cls) -> Address:
-        ...
-
-    def __repr__(self) -> str:
-        ...
-
-    def __eq__(self, other) -> bool:
-        ...
-
-    async def open_listener(
-        self,
-        **kwargs,
-    ) -> SocketListener:
-        ...
-
-    async def close_listener(self):
-        ...
-
-
-_address_types: bidict[str, Type[Address]] = {
-    'tcp': TCPAddress,
-    'uds': UDSAddress
-}
-
-
-# TODO! really these are discovery sys default addrs ONLY useful for
-# when none is provided to a root actor on first boot.
-_default_lo_addrs: dict[
-    str,
-    UnwrappedAddress
-] = {
-    'tcp': TCPAddress.get_root().unwrap(),
-    'uds': UDSAddress.get_root().unwrap(),
-}
-
-
-def get_address_cls(name: str) -> Type[Address]:
-    return _address_types[name]
-
-
-def is_wrapped_addr(addr: any) -> bool:
-    return type(addr) in _address_types.values()
-
-
-def mk_uuid() -> str:
-    '''
-    Encapsulate creation of a uuid4 as `str` as used
-    for creating `Actor.uid: tuple[str, str]` and/or
-    `.msg.types.Aid`.
-
-    '''
-    return str(uuid4())
-
-
-def wrap_address(
-    addr: UnwrappedAddress
-) -> Address:
-    '''
-    Wrap an `UnwrappedAddress` as an `Address`-type based
-    on matching builtin python data-structures which we adhoc
-    use for each.
-
-    XXX NOTE, careful care must be placed to ensure
-    `UnwrappedAddress` cases are **definitely unique** otherwise the
-    wrong transport backend may be loaded and will break many
-    low-level things in our runtime in a not-fun-to-debug way!
-
-    XD
-
-    '''
-    if is_wrapped_addr(addr):
-        return addr
-
-    cls: Type|None = None
-    # if 'sock' in addr[0]:
-    #     import pdbp; pdbp.set_trace()
-    match addr:
-
-        # classic network socket-address as tuple/list
-        case (
-            (str(), int())
-            |
-            [str(), int()]
-        ):
-            cls = TCPAddress
-
-        case (
-            # (str()|Path(), str()|Path()),
-            # ^TODO? uhh why doesn't this work!?
-
-            (_, filename)
-        ) if type(filename) is str:
-            cls = UDSAddress
-
-        # likely an unset UDS or TCP reg address as defaulted in
-        # `_state._runtime_vars['_root_mailbox']`
-        #
-        # TODO? figure out when/if we even need this?
-        case (
-            None
-            |
-            [None, None]
-        ):
-            cls: Type[Address] = get_address_cls(_def_tpt_proto)
-            addr: UnwrappedAddress = cls.get_root().unwrap()
-
-        case _:
-            # import pdbp; pdbp.set_trace()
-            raise TypeError(
-                f'Can not wrap unwrapped-address ??\n'
-                f'type(addr): {type(addr)!r}\n'
-                f'addr: {addr!r}\n'
-            )
-
-    return cls.from_addr(addr)
-
-
-def default_lo_addrs(
-    transports: list[str],
-) -> list[Type[Address]]:
-    '''
-    Return the default, host-singleton, registry address
-    for an input transport key set.
-
-    '''
-    return [
-        _default_lo_addrs[transport]
-        for transport in transports
-    ]

tractor/_child.py

@@ -31,12 +31,8 @@ def parse_uid(arg):
     return str(name), str(uuid)  # ensures str encoding
 
 def parse_ipaddr(arg):
-    try:
-        return literal_eval(arg)
-
-    except (ValueError, SyntaxError):
-        # UDS: try to interpret as a straight up str
-        return arg
+    host, port = literal_eval(arg)
+    return (str(host), int(port))
 
 
 if __name__ == "__main__":
@@ -50,8 +46,8 @@ if __name__ == "__main__":
     args = parser.parse_args()
 
     subactor = Actor(
-        name=args.uid[0],
-        uuid=args.uid[1],
+        args.uid[0],
+        uid=args.uid[1],
         loglevel=args.loglevel,
         spawn_method="trio"
     )

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
@@ -55,17 +52,10 @@ async def open_actor_cluster(
         raise ValueError(
             'Number of names is {len(names)} but count it {count}')
 
-    async with (
-        # tractor.trionics.collapse_eg(),
-        tractor.open_nursery(
-            **runtime_kwargs,
-        ) as an
-    ):
-        async with (
-            # tractor.trionics.collapse_eg(),
-            trio.open_nursery() as tn,
-            tractor.trionics.maybe_raise_from_masking_exc()
-        ):
+    async with tractor.open_nursery(
+        **runtime_kwargs,
+    ) as an:
+        async with trio.open_nursery() as n:
             uid = tractor.current_actor().uid
 
             async def _start(name: str) -> None:
@@ -76,8 +66,9 @@ async def open_actor_cluster(
                 )
 
             for name in names:
-                tn.start_soon(_start, name)
+                n.start_soon(_start, name)
 
         assert len(portals) == count
         yield portals
+
         await an.cancel(hard_kill=hard_kill)

tractor/_discovery.py

@@ -26,18 +26,10 @@ from typing import (
     TYPE_CHECKING,
 )
 from contextlib import asynccontextmanager as acm
+import warnings
 
-from tractor.log import get_logger
-from .trionics import (
-    gather_contexts,
-    collapse_eg,
-)
-from .ipc import _connect_chan, Channel
-from ._addr import (
-    UnwrappedAddress,
-    Address,
-    wrap_address
-)
+from .trionics import gather_contexts
+from ._ipc import _connect_chan, Channel
 from ._portal import (
     Portal,
     open_portal,
@@ -46,50 +38,61 @@ from ._portal import (
 from ._state import (
     current_actor,
     _runtime_vars,
-    _def_tpt_proto,
 )
 
+
 if TYPE_CHECKING:
     from ._runtime import Actor
 
 
-log = get_logger(__name__)
-
-
 @acm
 async def get_registry(
-    addr: UnwrappedAddress|None = None,
+    host: str,
+    port: int,
+
 ) -> AsyncGenerator[
     Portal | LocalPortal | None,
     None,
 ]:
     '''
     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).
+    arbiter.
 
     '''
-    actor: Actor = current_actor()
+    actor = current_actor()
+
+    if not actor:
+        raise RuntimeError("No actor instance has been defined yet?")
+
     if actor.is_registrar:
         # we're already the arbiter
         # (likely a re-entrant call from the arbiter actor)
         yield LocalPortal(
             actor,
-            Channel(transport=None)
-            # ^XXX, we DO NOT actually provide nor connect an
-            # underlying transport since this is merely an API shim.
+            Channel((host, port))
         )
     else:
-        # TODO: try to look pre-existing connection from
-        # `Server._peers` and use it instead?
         async with (
-            _connect_chan(addr) as chan,
+            _connect_chan(host, port) as chan,
             open_portal(chan) as regstr_ptl,
         ):
             yield regstr_ptl
 
 
+
+# TODO: deprecate and this remove _arbiter form!
+@acm
+async def get_arbiter(*args, **kwargs):
+    warnings.warn(
+        '`tractor.get_arbiter()` is now deprecated!\n'
+        'Use `.get_registry()` instead!',
+        DeprecationWarning,
+        stacklevel=2,
+    )
+    async with get_registry(*args, **kwargs) as to_yield:
+        yield to_yield
+
+
 @acm
 async def get_root(
     **kwargs,
@@ -97,68 +100,32 @@ async def get_root(
 
     # TODO: rename mailbox to `_root_maddr` when we finally
     # add and impl libp2p multi-addrs?
-    addr = _runtime_vars['_root_mailbox']
+    host, port = _runtime_vars['_root_mailbox']
+    assert host is not None
 
     async with (
-        _connect_chan(addr) as chan,
+        _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 `Server._peers: dict`.
-
-    This is an optimization method over querying the registrar for
-    the same info.
-
-    '''
-    actor: Actor = current_actor()
-    to_scan: dict[tuple, list[Channel]] = actor.ipc_server._peers.copy()
-
-    # TODO: is this ever needed? creates a duplicate channel on actor._peers
-    # when multiple find_actor calls are made to same actor from a single ctx
-    # which causes actor exit to hang waiting forever on
-    # `actor._no_more_peers.wait()` in `_runtime.async_main`
-
-    # pchan: Channel|None = actor._parent_chan
-    # if pchan and pchan.uid not in to_scan:
-    #     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
-
-
 @acm
 async def query_actor(
     name: str,
-    regaddr: UnwrappedAddress|None = None,
+    arbiter_sockaddr: tuple[str, int] | None = None,
+    regaddr: tuple[str, int] | None = None,
 
 ) -> AsyncGenerator[
-    UnwrappedAddress|None,
+    tuple[str, int] | None,
     None,
 ]:
     '''
-    Lookup a transport address (by actor name) via querying a registrar
-    listening @ `regaddr`.
+    Make a transport address lookup for an actor name to a specific
+    registrar.
 
-    Returns the transport protocol (socket) address or `None` if no
-    entry under that name exists.
+    Returns the (socket) address or ``None`` if no entry under that
+    name exists for the given registrar listening @ `regaddr`.
 
     '''
     actor: Actor = current_actor()
@@ -170,48 +137,33 @@ async def query_actor(
             'The current actor IS the registry!?'
         )
 
-    maybe_peers: list[Channel]|None = get_peer_by_name(name)
-    if maybe_peers:
-        yield maybe_peers[0].raddr
-        return
+    if arbiter_sockaddr is not None:
+        warnings.warn(
+            '`tractor.query_actor(regaddr=<blah>)` is deprecated.\n'
+            'Use `registry_addrs: list[tuple]` instead!',
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        regaddr: list[tuple[str, int]] = arbiter_sockaddr
 
     reg_portal: Portal
-    regaddr: Address = wrap_address(regaddr) or actor.reg_addrs[0]
-    async with get_registry(regaddr) as reg_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
-        addr: UnwrappedAddress = await reg_portal.run_from_ns(
+        sockaddr: tuple[str, int] = await reg_portal.run_from_ns(
             'self',
             'find_actor',
             name=name,
         )
-        yield addr
-
-
-@acm
-async def maybe_open_portal(
-    addr: UnwrappedAddress,
-    name: str,
-):
-    async with query_actor(
-        name=name,
-        regaddr=addr,
-    ) as addr:
-        pass
-
-    if addr:
-        async with _connect_chan(addr) as chan:
-            async with open_portal(chan) as portal:
-                yield portal
-    else:
-        yield None
+        yield sockaddr
 
 
 @acm
 async def find_actor(
     name: str,
-    registry_addrs: list[UnwrappedAddress]|None = None,
-    enable_transports: list[str] = [_def_tpt_proto],
+    arbiter_sockaddr: tuple[str, int]|None = None,
+    registry_addrs: list[tuple[str, int]]|None = None,
 
     only_first: bool = True,
     raise_on_none: bool = False,
@@ -227,40 +179,51 @@ 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 arbiter_sockaddr is not None:
+        warnings.warn(
+            '`tractor.find_actor(arbiter_sockaddr=<blah>)` is deprecated.\n'
+            'Use `registry_addrs: list[tuple]` instead!',
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        registry_addrs: list[tuple[str, int]] = [arbiter_sockaddr]
+
+    @acm
+    async def maybe_open_portal_from_reg_addr(
+        addr: tuple[str, int],
+    ):
+        async with query_actor(
+            name=name,
+            regaddr=addr,
+        ) as sockaddr:
+            if sockaddr:
+                async with _connect_chan(*sockaddr) as chan:
+                    async with open_portal(chan) as portal:
+                        yield portal
+            else:
+                yield None
 
     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 ._addr import default_lo_addrs
+        from . import _root
         registry_addrs = (
             _runtime_vars['_registry_addrs']
             or
-            default_lo_addrs(enable_transports)
+            _root._default_lo_addrs
         )
 
     maybe_portals: list[
-        AsyncContextManager[UnwrappedAddress]
+        AsyncContextManager[tuple[str, int]]
     ] = list(
-        maybe_open_portal(
-            addr=addr,
-            name=name,
-        )
+        maybe_open_portal_from_reg_addr(addr)
         for addr in registry_addrs
     )
-    portals: list[Portal]
-    async with (
-        collapse_eg(),
-        gather_contexts(
-            mngrs=maybe_portals,
-        ) as portals,
-    ):
+
+    async with gather_contexts(
+        mngrs=maybe_portals,
+    ) as portals:
         # log.runtime(
         #     'Gathered portals:\n'
         #     f'{portals}'
@@ -291,33 +254,33 @@ async def find_actor(
 @acm
 async def wait_for_actor(
     name: str,
-    registry_addr: UnwrappedAddress | None = None,
+    arbiter_sockaddr: tuple[str, int] | None = None,
+    registry_addr: tuple[str, int] | None = 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.
+
+    A portal to the first registered actor is returned.
 
     '''
     actor: 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
+    if arbiter_sockaddr is not None:
+        warnings.warn(
+            '`tractor.wait_for_actor(arbiter_sockaddr=<foo>)` is deprecated.\n'
+            'Use `registry_addr: tuple` instead!',
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        registry_addr: tuple[str, int] = arbiter_sockaddr
 
-    regaddr: UnwrappedAddress = (
-        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:
-        addrs = await reg_portal.run_from_ns(
+    regaddr: tuple[str, int] = registry_addr or actor.reg_addrs[0]
+    async with get_registry(*regaddr) as reg_portal:
+        sockaddrs = await reg_portal.run_from_ns(
             'self',
             'wait_for_actor',
             name=name,
@@ -325,8 +288,8 @@ async def wait_for_actor(
 
         # get latest registered addr by default?
         # TODO: offer multi-portal yields in multi-homed case?
-        addr: UnwrappedAddress = addrs[-1]
+        sockaddr: tuple[str, int] = sockaddrs[-1]
 
-        async with _connect_chan(addr) as chan:
+        async with _connect_chan(*sockaddr) as chan:
             async with open_portal(chan) as portal:
                 yield portal

tractor/_entry.py

@@ -20,8 +20,7 @@ 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,
@@ -34,13 +33,8 @@ from .log import (
     get_logger,
 )
 from . import _state
-from .devx import (
-    _frame_stack,
-    pformat,
-)
-# from .msg import pretty_struct
+from .devx import _debug
 from .to_asyncio import run_as_asyncio_guest
-from ._addr import UnwrappedAddress
 from ._runtime import (
     async_main,
     Actor,
@@ -56,35 +50,33 @@ log = get_logger(__name__)
 def _mp_main(
 
     actor: Actor,
-    accept_addrs: list[UnwrappedAddress],
+    accept_addrs: list[tuple[str, int]],
     forkserver_info: tuple[Any, Any, Any, Any, Any],
     start_method: SpawnMethodKey,
-    parent_addr: UnwrappedAddress | None = None,
+    parent_addr: tuple[str, int] | None = 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,
@@ -101,15 +93,13 @@ def _mp_main(
         pass  # handle it the same way trio does?
 
     finally:
-        log.info(
-            f'`mp`-subactor {actor.uid} exited'
-        )
+        log.info(f"Subactor {actor.uid} terminated")
 
 
 def _trio_main(
     actor: Actor,
     *,
-    parent_addr: UnwrappedAddress|None = None,
+    parent_addr: tuple[str, int] | None = None,
     infect_asyncio: bool = False,
 
 ) -> None:
@@ -117,7 +107,8 @@ def _trio_main(
     Entry point for a `trio_run_in_process` subactor.
 
     '''
-    _frame_stack.hide_runtime_frames()
+    # __tracebackhide__: bool = True
+    _debug.hide_runtime_frames()
 
     _state._current_actor = actor
     trio_main = partial(
@@ -128,25 +119,22 @@ def _trio_main(
 
     if actor.loglevel is not None:
         get_console_log(actor.loglevel)
+        import os
+        actor_info: str = (
+            f'|_{actor}\n'
+            f'  uid: {actor.uid}\n'
+            f'  pid: {os.getpid()}\n'
+            f'  parent_addr: {parent_addr}\n'
+            f'  loglevel: {actor.loglevel}\n'
+        )
         log.info(
-            f'Starting `trio` subactor from parent @ '
-            f'{parent_addr}\n'
+            'Started new trio subactor:\n'
             +
-            pformat.nest_from_op(
-                input_op='>(',  # see syntax ideas above
-                text=f'{actor}',
-            )
+            '>\n'  # like a "started/play"-icon from super perspective
+            +
+            actor_info,
         )
-    logmeth = log.info
-    exit_status: str = (
-        'Subactor exited\n'
-        +
-        pformat.nest_from_op(
-            input_op=')>',  # like a "closed-to-play"-icon from super perspective
-            text=f'{actor}',
-            nest_indent=1,
-        )
-    )
+
     try:
         if infect_asyncio:
             actor._infected_aio = True
@@ -155,28 +143,16 @@ def _trio_main(
             trio.run(trio_main)
 
     except KeyboardInterrupt:
-        logmeth = log.cancel
-        exit_status: str = (
-            'Actor received KBI (aka an OS-cancel)\n'
+        log.cancel(
+            'Actor received KBI\n'
             +
-            pformat.nest_from_op(
-                input_op='c)>',  # closed due to cancel (see above)
-                text=f'{actor}',
-            )
+            actor_info
         )
-    except BaseException as err:
-        logmeth = log.error
-        exit_status: str = (
-            'Main actor task exited due to crash?\n'
-            +
-            pformat.nest_from_op(
-                input_op='x)>',  # closed by error
-                text=f'{actor}',
-            )
-        )
-        # NOTE since we raise a tb will already be shown on the
-        # console, thus we do NOT use `.exception()` above.
-        raise err
-
     finally:
-        logmeth(exit_status)
+        log.info(
+            'Subactor terminated\n'
+            +
+            'x\n'  # like a "crossed-out/killed" from super perspective
+            +
+            actor_info
+        )

tractor/_exceptions.py

@@ -22,7 +22,7 @@ from __future__ import annotations
 import builtins
 import importlib
 from pprint import pformat
-from pdb import bdb
+import sys
 from types import (
     TracebackType,
 )
@@ -64,29 +64,15 @@ if TYPE_CHECKING:
     from ._context import Context
     from .log import StackLevelAdapter
     from ._stream import MsgStream
-    from .ipc import Channel
+    from ._ipc import Channel
 
 log = get_logger('tractor')
 
 _this_mod = importlib.import_module(__name__)
 
 
-class RuntimeFailure(RuntimeError):
-    '''
-    General `Actor`-runtime failure due to,
-
-    - a bad runtime-env,
-    - falied spawning (bad input to process),
-    -   API usage.
-
-    '''
-
-
-class ActorFailure(RuntimeFailure):
-    '''
-    `Actor` failed to boot before/after spawn
-
-    '''
+class ActorFailure(Exception):
+    "General actor failure"
 
 
 class InternalError(RuntimeError):
@@ -96,54 +82,6 @@ class InternalError(RuntimeError):
 
     '''
 
-class AsyncioCancelled(Exception):
-    '''
-    Asyncio cancelled translation (non-base) error
-    for use with the ``to_asyncio`` module
-    to be raised in the ``trio`` side task
-
-    NOTE: this should NOT inherit from `asyncio.CancelledError` or
-    tests should break!
-
-    '''
-
-
-class AsyncioTaskExited(Exception):
-    '''
-    asyncio.Task "exited" translation error for use with the
-    `to_asyncio` APIs to be raised in the `trio` side task indicating
-    on `.run_task()`/`.open_channel_from()` exit that the aio side
-    exited early/silently.
-
-    '''
-
-class TrioCancelled(Exception):
-    '''
-    Trio cancelled translation (non-base) error
-    for use with the `to_asyncio` module
-    to be raised in the `asyncio.Task` to indicate
-    that the `trio` side raised `Cancelled` or an error.
-
-    '''
-
-class TrioTaskExited(Exception):
-    '''
-    The `trio`-side task exited without explicitly cancelling the
-    `asyncio.Task` peer.
-
-    This is very similar to how `trio.ClosedResource` acts as
-    a "clean shutdown" signal to the consumer side of a mem-chan,
-
-    https://trio.readthedocs.io/en/stable/reference-core.html#clean-shutdown-with-channels
-
-    '''
-
-
-class DebugRequestError(RuntimeError):
-    '''
-    Failed to request stdio lock from root actor!
-
-    '''
 
 # NOTE: more or less should be close to these:
 # 'boxed_type',
@@ -189,8 +127,8 @@ _body_fields: list[str] = list(
 
 def get_err_type(type_name: str) -> BaseException|None:
     '''
-    Look up an exception type by name from the set of locally known
-    namespaces:
+    Look up an exception type by name from the set of locally
+    known namespaces:
 
     - `builtins`
     - `tractor._exceptions`
@@ -201,7 +139,6 @@ def get_err_type(type_name: str) -> BaseException|None:
         builtins,
         _this_mod,
         trio,
-        bdb,
     ]:
         if type_ref := getattr(
             ns,
@@ -210,8 +147,6 @@ def get_err_type(type_name: str) -> BaseException|None:
         ):
             return type_ref
 
-    return None
-
 
 def pack_from_raise(
     local_err: (
@@ -423,13 +358,6 @@ class RemoteActorError(Exception):
                 self._ipc_msg.src_type_str
             )
 
-            if not self._src_type:
-                raise TypeError(
-                    f'Failed to lookup src error type with '
-                    f'`tractor._exceptions.get_err_type()` :\n'
-                    f'{self.src_type_str}'
-                )
-
         return self._src_type
 
     @property
@@ -438,9 +366,6 @@ class RemoteActorError(Exception):
         String-name of the (last hop's) boxed error type.
 
         '''
-        # TODO, maybe support also serializing the
-        # `ExceptionGroup.exeptions: list[BaseException]` set under
-        # certain conditions?
         bt: Type[BaseException] = self.boxed_type
         if bt:
             return str(bt.__name__)
@@ -453,13 +378,9 @@ class RemoteActorError(Exception):
         Error type boxed by last actor IPC hop.
 
         '''
-        if (
-            self._boxed_type is None
-            and
-            (ipc_msg := self._ipc_msg)
-        ):
+        if self._boxed_type is None:
             self._boxed_type = get_err_type(
-                ipc_msg.boxed_type_str
+                self._ipc_msg.boxed_type_str
             )
 
         return self._boxed_type
@@ -542,6 +463,7 @@ class RemoteActorError(Exception):
             if val:
                 _repr += f'{key}={val_str}{end_char}'
 
+
         return _repr
 
     def reprol(self) -> str:
@@ -620,9 +542,56 @@ class RemoteActorError(Exception):
             the type name is already implicitly shown by python).
 
         '''
+        header: str = ''
+        body: str = ''
+        message: str = ''
+
+        # XXX when the currently raised exception is this instance,
+        # we do not ever use the "type header" style repr.
+        is_being_raised: bool = False
+        if (
+            (exc := sys.exception())
+            and
+            exc is self
+        ):
+            is_being_raised: bool = True
+
+        with_type_header: bool = (
+            with_type_header
+            and
+            not is_being_raised
+        )
+
+        # <RemoteActorError( .. )> style
+        if with_type_header:
+            header: str = f'<{type(self).__name__}('
+
+        if message := self._message:
+
+            # split off the first line so, if needed, it isn't
+            # indented the same like the "boxed content" which
+            # since there is no `.tb_str` is just the `.message`.
+            lines: list[str] = message.splitlines()
+            first: str = lines[0]
+            message: str = message.removeprefix(first)
+
+            # with a type-style header we,
+            # - have no special message "first line" extraction/handling
+            # - place the message a space in from the header:
+            #  `MsgTypeError( <message> ..`
+            #                 ^-here
+            # - indent the `.message` inside the type body.
+            if with_type_header:
+                first = f' {first} )>'
+
+            message: str = textwrap.indent(
+                message,
+                prefix=' '*2,
+            )
+            message: str = first + message
+
         # IFF there is an embedded traceback-str we always
         # draw the ascii-box around it.
-        body: str = ''
         if tb_str := self.tb_str:
             fields: str = self._mk_fields_str(
                 _body_fields
@@ -640,18 +609,23 @@ class RemoteActorError(Exception):
                 # just after <Type(
                 #             |___ ..
                 tb_body_indent=1,
-                boxer_header=self.relay_uid,
             )
 
-        # !TODO, it'd be nice to import these top level without
-        # cycles!
-        from tractor.devx.pformat import (
-            pformat_exc,
-        )
-        return pformat_exc(
-            exc=self,
-            with_type_header=with_type_header,
-            body=body,
+        tail = ''
+        if (
+            with_type_header
+            and not message
+        ):
+            tail: str = '>'
+
+        return (
+            header
+            +
+            message
+            +
+            f'{body}'
+            +
+            tail
         )
 
     __repr__ = pformat
@@ -677,10 +651,16 @@ class RemoteActorError(Exception):
         failing actor's remote env.
 
         '''
+        src_type_ref: Type[BaseException] = self.src_type
+        if not src_type_ref:
+            raise TypeError(
+                'Failed to lookup src error type:\n'
+                f'{self.src_type_str}'
+            )
+
         # TODO: better tb insertion and all the fancier dunder
         # metadata stuff as per `.__context__` etc. and friends:
         # https://github.com/python-trio/trio/issues/611
-        src_type_ref: Type[BaseException] = self.src_type
         return src_type_ref(self.tb_str)
 
     # TODO: local recontruction of nested inception for a given
@@ -806,11 +786,8 @@ class MsgTypeError(
         '''
         if (
             (_bad_msg := self.msgdata.get('_bad_msg'))
-            and (
-                isinstance(_bad_msg, PayloadMsg)
-                or
-                isinstance(_bad_msg, msgtypes.Start)
-            )
+            and
+            isinstance(_bad_msg, PayloadMsg)
         ):
             return _bad_msg
 
@@ -929,148 +906,8 @@ class StreamOverrun(
     '''
 
 
-class TransportClosed(Exception):
-    '''
-    IPC transport (protocol) connection was closed or broke and
-    indicates that the wrapping communication `Channel` can no longer
-    be used to send/receive msgs from the remote peer.
-
-    '''
-    def __init__(
-        self,
-        message: str,
-        loglevel: str = 'transport',
-        src_exc: Exception|None = None,
-        raise_on_report: bool = False,
-
-    ) -> None:
-        self.message: str = message
-        self._loglevel: str = loglevel
-        super().__init__(message)
-
-        self._src_exc = src_exc
-        # set the cause manually if not already set by python
-        if (
-            src_exc is not None
-            and
-            not self.__cause__
-        ):
-            self.__cause__ = src_exc
-
-        # flag to toggle whether the msg loop should raise
-        # the exc in its `TransportClosed` handler block.
-        self._raise_on_report = raise_on_report
-
-    @property
-    def src_exc(self) -> Exception:
-        return (
-            self.__cause__
-            or
-            self._src_exc
-        )
-
-    def report_n_maybe_raise(
-        self,
-        message: str|None = None,
-        hide_tb: bool = True,
-
-    ) -> None:
-        '''
-        Using the init-specified log level emit a logging report
-        for this error.
-
-        '''
-        __tracebackhide__: bool = hide_tb
-        message: str = message or self.message
-        # when a cause is set, slap it onto the log emission.
-        if cause := self.src_exc:
-            cause_tb_str: str = ''.join(
-                traceback.format_tb(cause.__traceback__)
-            )
-            message += (
-                f'{cause_tb_str}\n'  # tb
-                f'    {cause}\n'  # exc repr
-            )
-
-        getattr(
-            log,
-            self._loglevel
-        )(message)
-
-        # some errors we want to blow up from
-        # inside the RPC msg loop
-        if self._raise_on_report:
-            raise self from cause
-
-    @classmethod
-    def repr_src_exc(
-        self,
-        src_exc: Exception|None = None,
-    ) -> str:
-
-        if src_exc is None:
-            return '<unknown>'
-
-        src_msg: tuple[str] = src_exc.args
-        src_exc_repr: str = (
-            f'{type(src_exc).__name__}[ {src_msg} ]'
-        )
-        return src_exc_repr
-
-    def pformat(self) -> str:
-        from tractor.devx.pformat import (
-            pformat_exc,
-        )
-        return pformat_exc(
-            exc=self,
-        )
-
-    # delegate to `str`-ified pformat
-    __repr__ = pformat
-
-    @classmethod
-    def from_src_exc(
-        cls,
-        src_exc: (
-            Exception|
-            trio.ClosedResource|
-            trio.BrokenResourceError
-        ),
-        message: str,
-        body: str = '',
-        **init_kws,
-    ) -> TransportClosed:
-        '''
-        Convenience constructor for creation from an underlying
-        `trio`-sourced async-resource/chan/stream error.
-
-        Embeds the original `src_exc`'s repr within the
-        `Exception.args` via a first-line-in-`.message`-put-in-header
-        pre-processing and allows inserting additional content beyond
-        the main message via a `body: str`.
-
-        '''
-        repr_src_exc: str = cls.repr_src_exc(
-            src_exc,
-        )
-        next_line: str = f'  src_exc: {repr_src_exc}\n'
-        if body:
-            body: str = textwrap.indent(
-                body,
-                prefix=' '*2,
-            )
-
-        return TransportClosed(
-            message=(
-                message
-                +
-                next_line
-                +
-                body
-            ),
-            src_exc=src_exc,
-            **init_kws,
-        )
+class TransportClosed(trio.ClosedResourceError):
+    "Underlying channel transport was closed prior to use"
 
 
 class NoResult(RuntimeError):
@@ -1085,6 +922,15 @@ class NoRuntime(RuntimeError):
     "The root actor has not been initialized yet"
 
 
+
+class AsyncioCancelled(Exception):
+    '''
+    Asyncio cancelled translation (non-base) error
+    for use with the ``to_asyncio`` module
+    to be raised in the ``trio`` side task
+
+    '''
+
 class MessagingError(Exception):
     '''
     IPC related msg (typing), transaction (ordering) or dialog
@@ -1092,6 +938,7 @@ class MessagingError(Exception):
 
     '''
 
+
 def pack_error(
     exc: BaseException|RemoteActorError,
 
@@ -1203,8 +1050,6 @@ def unpack_error(
     which is the responsibilitiy of the caller.
 
     '''
-    # XXX, apparently we pass all sorts of msgs here?
-    # kinda odd but seems like maybe they shouldn't be?
     if not isinstance(msg, Error):
         return None
 
@@ -1246,6 +1091,23 @@ def unpack_error(
     return exc
 
 
+def is_multi_cancelled(
+    exc: BaseException|BaseExceptionGroup
+) -> bool:
+    '''
+    Predicate to determine if a possible ``BaseExceptionGroup`` contains
+    only ``trio.Cancelled`` sub-exceptions (and is likely the result of
+    cancelling a collection of subtasks.
+
+    '''
+    if isinstance(exc, BaseExceptionGroup):
+        return exc.subgroup(
+            lambda exc: isinstance(exc, trio.Cancelled)
+        ) is not None
+
+    return False
+
+
 def _raise_from_unexpected_msg(
     ctx: Context,
     msg: MsgType,
@@ -1462,9 +1324,7 @@ def _mk_recv_mte(
         any_pld: Any = msgpack.decode(msg.pld)
         message: str = (
             f'invalid `{msg_type.__qualname__}` msg payload\n\n'
-            f'{any_pld!r}\n\n'
-            f'has type {type(any_pld)!r}\n\n'
-            f'and does not match type-spec '
+            f'value: `{any_pld!r}` does not match type-spec: '
             f'`{type(msg).__qualname__}.pld: {codec.pld_spec_str}`'
         )
         bad_msg = msg

tractor/_ipc.py

@@ -0,0 +1,722 @@
+# 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/>.
+
+"""
+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 typing import (
+    Any,
+    Callable,
+    runtime_checkable,
+    Protocol,
+    Type,
+    TypeVar,
+)
+
+import msgspec
+from tricycle import BufferedReceiveStream
+import trio
+
+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,
+    MsgCodec,
+    types as msgtypes,
+    pretty_struct,
+)
+
+log = get_logger(__name__)
+
+_is_windows = platform.system() == 'Windows'
+
+
+def get_stream_addrs(stream: trio.SocketStream) -> tuple:
+    # should both be IP sockets
+    lsockname = stream.socket.getsockname()
+    rsockname = stream.socket.getpeername()
+    return (
+        tuple(lsockname[:2]),
+        tuple(rsockname[:2]),
+    )
+
+
+# TODO: this should be our `Union[*msgtypes.__spec__]` now right?
+MsgType = TypeVar("MsgType")
+
+# 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
+
+
+@runtime_checkable
+class MsgTransport(Protocol[MsgType]):
+
+    stream: trio.SocketStream
+    drained: list[MsgType]
+
+    def __init__(self, stream: trio.SocketStream) -> None:
+        ...
+
+    # XXX: should this instead be called `.sendall()`?
+    async def send(self, msg: MsgType) -> None:
+        ...
+
+    async def recv(self) -> MsgType:
+        ...
+
+    def __aiter__(self) -> MsgType:
+        ...
+
+    def connected(self) -> bool:
+        ...
+
+    # defining this sync otherwise it causes a mypy error because it
+    # can't figure out it's a generator i guess?..?
+    def drain(self) -> AsyncIterator[dict]:
+        ...
+
+    @property
+    def laddr(self) -> tuple[str, int]:
+        ...
+
+    @property
+    def raddr(self) -> tuple[str, int]:
+        ...
+
+
+# TODO: 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):
+    '''
+    A ``trio.SocketStream`` delivering ``msgpack`` formatted data
+    using the ``msgspec`` codec lib.
+
+    '''
+    layer_key: int = 4
+    name_key: str = 'tcp'
+
+    # TODO: better naming for this?
+    # -[ ] check how libp2p does naming for such things?
+    codec_key: str = 'msgpack'
+
+    def __init__(
+        self,
+        stream: trio.SocketStream,
+        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:
+
+        self.stream = stream
+        assert self.stream.socket
+
+        # should both be IP sockets
+        self._laddr, self._raddr = get_stream_addrs(stream)
+
+        # create read loop instance
+        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()
+        self._codec: MsgCodec = (
+            codec
+            or
+            _codec._ctxvar_MsgCodec.get()
+        )
+        # TODO: mask out before release?
+        # log.runtime(
+        #     f'New {self} created with codec\n'
+        #     f'codec: {self._codec}\n'
+        # )
+
+    async def _iter_packets(self) -> AsyncGenerator[dict, None]:
+        '''
+        Yield `bytes`-blob decoded packets from the underlying TCP
+        stream using the current task's `MsgCodec`.
+
+        '''
+        decodes_failed: int = 0
+
+        while True:
+            try:
+                header: bytes = await self.recv_stream.receive_exactly(4)
+            except (
+                ValueError,
+                ConnectionResetError,
+
+                # 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: 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()
+
+                # TODO: mask out before release?
+                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)
+
+                # TODO: remove, was only for orig draft impl
+                # testing.
+                #
+                # curr_codec: MsgCodec = _ctxvar_MsgCodec.get()
+                # obj = curr_codec.decode(msg_bytes)
+                # if (
+                #     curr_codec is not
+                #     _codec._def_msgspec_codec
+                # ):
+                #     print(f'OBJ: {obj}\n')
+                #
+                # yield obj
+
+            # 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'
+                    )
+                    decodes_failed += 1
+                else:
+                    raise
+
+    async def send(
+        self,
+        msg: msgtypes.MsgType,
+
+        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
+        async with self._send_lock:
+
+            # NOTE: lookup the `trio.Task.context`'s var for
+            # the current `MsgCodec`.
+            codec: MsgCodec = _ctxvar_MsgCodec.get()
+
+            # TODO: mask out before release?
+            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,
+                )
+                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)
+
+    @property
+    def laddr(self) -> tuple[str, int]:
+        return self._laddr
+
+    @property
+    def raddr(self) -> tuple[str, int]:
+        return self._raddr
+
+    async def recv(self) -> Any:
+        return await self._agen.asend(None)
+
+    async def drain(self) -> AsyncIterator[dict]:
+        '''
+        Drain the stream's remaining messages sent from
+        the far end until the connection is closed by
+        the peer.
+
+        '''
+        try:
+            async for msg in self._iter_packets():
+                self.drained.append(msg)
+        except TransportClosed:
+            for msg in self.drained:
+                yield msg
+
+    def __aiter__(self):
+        return self._agen
+
+    def connected(self) -> bool:
+        return self.stream.socket.fileno() != -1
+
+
+def get_msg_transport(
+
+    key: tuple[str, str],
+
+) -> Type[MsgTransport]:
+
+    return {
+        ('msgpack', 'tcp'): MsgpackTCPStream,
+    }[key]
+
+
+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.
+
+    '''
+    def __init__(
+
+        self,
+        destaddr: tuple[str, int]|None,
+
+        msg_transport_type_key: tuple[str, str] = ('msgpack', 'tcp'),
+
+        # TODO: optional reconnection support?
+        # auto_reconnect: bool = False,
+        # on_reconnect: typing.Callable[..., typing.Awaitable] = None,
+
+    ) -> None:
+
+        # self._recon_seq = on_reconnect
+        # self._autorecon = auto_reconnect
+
+        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
+
+        # set after handshake - always uid of far end
+        self.uid: tuple[str, str]|None = None
+
+        self._agen = self._aiter_recv()
+        self._exc: Exception|None = 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
+
+    @classmethod
+    def from_stream(
+        cls,
+        stream: trio.SocketStream,
+        **kwargs,
+
+    ) -> Channel:
+
+        src, dst = get_stream_addrs(stream)
+        chan = Channel(
+            destaddr=dst,
+            **kwargs,
+        )
+
+        # set immediately here from provided instance
+        chan._stream: trio.SocketStream = 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,
+
+    ) -> 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
+
+    # TODO: something simliar at the IPC-`Context`
+    # level so as to support 
+    @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
+
+    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",
+        )
+
+    @property
+    def laddr(self) -> tuple[str, int]|None:
+        return self._transport.laddr if self._transport else None
+
+    @property
+    def raddr(self) -> tuple[str, int]|None:
+        return self._transport.raddr if self._transport else None
+
+    async def connect(
+        self,
+        destaddr: tuple[Any, ...] | None = None,
+        **kwargs
+
+    ) -> MsgTransport:
+
+        if self.connected():
+            raise RuntimeError("channel is already connected?")
+
+        destaddr = destaddr or self._destaddr
+        assert isinstance(destaddr, tuple)
+
+        stream = await trio.open_tcp_stream(
+            *destaddr,
+            **kwargs
+        )
+        transport = self.set_msg_transport(stream)
+
+        log.transport(
+            f'Opened channel[{type(transport)}]: {self.laddr} -> {self.raddr}'
+        )
+        return transport
+
+    async def send(
+        self,
+        payload: Any,
+
+        # hide_tb: bool = False,
+
+    ) -> None:
+        '''
+        Send a coded msg-blob over the transport.
+
+        '''
+        # __tracebackhide__: bool = hide_tb
+        log.transport(
+            '=> send IPC msg:\n\n'
+            f'{pformat(payload)}\n'
+        )  # type: ignore
+        assert self._transport
+        await self._transport.send(
+            payload,
+            # hide_tb=hide_tb,
+        )
+
+    async def recv(self) -> Any:
+        assert self._transport
+        return await self._transport.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()
+        # except trio.BrokenResourceError:
+        #     if self._autorecon:
+        #         await self._reconnect()
+        #         return await self.recv()
+        #     raise
+
+    async def aclose(self) -> None:
+
+        log.transport(
+            f'Closing channel to {self.uid} '
+            f'{self.laddr} -> {self.raddr}'
+        )
+        assert self._transport
+        await self._transport.stream.aclose()
+        self._closed = True
+
+    async def __aenter__(self):
+        await self.connect()
+        return self
+
+    async def __aexit__(self, *args):
+        await self.aclose(*args)
+
+    def __aiter__(self):
+        return self._agen
+
+    # async def _reconnect(self) -> None:
+    #     """Handle connection failures by polling until a reconnect can be
+    #     established.
+    #     """
+    #     down = False
+    #     while True:
+    #         try:
+    #             with trio.move_on_after(3) as cancel_scope:
+    #                 await self.connect()
+    #             cancelled = cancel_scope.cancelled_caught
+    #             if cancelled:
+    #                 log.transport(
+    #                     "Reconnect timed out after 3 seconds, retrying...")
+    #                 continue
+    #             else:
+    #                 log.transport("Stream connection re-established!")
+
+    #                 # TODO: run any reconnection sequence
+    #                 # on_recon = self._recon_seq
+    #                 # if on_recon:
+    #                 #     await on_recon(self)
+
+    #                 break
+    #         except (OSError, ConnectionRefusedError):
+    #             if not down:
+    #                 down = True
+    #                 log.transport(
+    #                     f"Connection to {self.raddr} went down, waiting"
+    #                     " for re-establishment")
+    #             await trio.sleep(1)
+
+    async def _aiter_recv(
+        self
+    ) -> AsyncGenerator[Any, None]:
+        '''
+        Async iterate items from underlying stream.
+
+        '''
+        assert self._transport
+        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
+
+                    # TODO: if we were gonna do this it should be
+                    # done up at the `MsgStream` layer!
+                    #
+                    # sent = yield item
+                    # if sent is not None:
+                    #     # optimization, passing None through all the
+                    #     # time is pointless
+                    #     await self._transport.send(sent)
+
+            except trio.BrokenResourceError:
+
+                # if not self._autorecon:
+                raise
+
+            await self.aclose()
+
+            # if self._autorecon:  # attempt reconnect
+            #     await self._reconnect()
+            #     continue
+
+    def connected(self) -> bool:
+        return self._transport.connected() if self._transport else False
+
+
+@acm
+async def _connect_chan(
+    host: str,
+    port: int
+
+) -> typing.AsyncGenerator[Channel, None]:
+    '''
+    Create and connect a channel with disconnect on context manager
+    teardown.
+
+    '''
+    chan = Channel((host, port))
+    await chan.connect()
+    yield chan
+    with trio.CancelScope(shield=True):
+        await chan.aclose()

tractor/_portal.py

@@ -39,14 +39,11 @@ import warnings
 
 import trio
 
-from .trionics import (
-    maybe_open_nursery,
-    collapse_eg,
-)
+from .trionics import maybe_open_nursery
 from ._state import (
     current_actor,
 )
-from .ipc import Channel
+from ._ipc import Channel
 from .log import get_logger
 from .msg import (
     # Error,
@@ -55,8 +52,8 @@ from .msg import (
     Return,
 )
 from ._exceptions import (
+    # unpack_error,
     NoResult,
-    TransportClosed,
 )
 from ._context import (
     Context,
@@ -100,7 +97,7 @@ class Portal:
         channel: Channel,
     ) -> None:
 
-        self._chan: Channel = channel
+        self.chan = channel
         # during the portal's lifetime
         self._final_result_pld: Any|None = None
         self._final_result_msg: PayloadMsg|None = None
@@ -110,20 +107,8 @@ class Portal:
         # point.
         self._expect_result_ctx: Context|None = None
         self._streams: set[MsgStream] = set()
-
-        # TODO, this should be PRIVATE (and never used publicly)! since it's just
-        # a cached ref to the local runtime instead of calling
-        # `current_actor()` everywhere.. XD
         self.actor: Actor = current_actor()
 
-    @property
-    def chan(self) -> Channel:
-        '''
-        Ref to this ctx's underlying `tractor.ipc.Channel`.
-
-        '''
-        return self._chan
-
     @property
     def channel(self) -> Channel:
         '''
@@ -136,8 +121,7 @@ class Portal:
         )
         return self.chan
 
-    # TODO: factor this out into a `.highlevel` API-wrapper that uses
-    # a single `.open_context()` call underneath.
+    # TODO: factor this out into an `ActorNursery` wrapper
     async def _submit_for_result(
         self,
         ns: str,
@@ -157,22 +141,13 @@ class Portal:
             portal=self,
         )
 
-    # TODO: we should deprecate this API right? since if we remove
-    # `.run_in_actor()` (and instead move it to a `.highlevel`
-    # wrapper api (around a single `.open_context()` call) we don't
-    # really have any notion of a "main" remote task any more?
-    #
     # @api_frame
-    async def wait_for_result(
-        self,
-        hide_tb: bool = True,
-    ) -> Any:
+    async def result(self) -> Any:
         '''
-        Return the final result delivered by a `Return`-msg from the
-        remote peer actor's "main" task's `return` statement.
+        Return the result(s) from the remote actor's "main" task.
 
         '''
-        __tracebackhide__: bool = hide_tb
+        __tracebackhide__ = True
         # Check for non-rpc errors slapped on the
         # channel for which we always raise
         exc = self.channel._exc
@@ -181,17 +156,10 @@ class Portal:
 
         # not expecting a "main" result
         if self._expect_result_ctx is None:
-            peer_id: str = f'{self.channel.aid.reprol()!r}'
             log.warning(
-                f'Portal to peer {peer_id} will not deliver a final result?\n'
-                f'\n'
-                f'Context.result() can only be called by the parent of '
-                f'a sub-actor when it was spawned with '
-                f'`ActorNursery.run_in_actor()`'
-                f'\n'
-                f'Further this `ActorNursery`-method-API will deprecated in the'
-                f'near fututre!\n'
-            )
+                f"Portal for {self.channel.uid} not expecting a final"
+                " result?\nresult() should only be called if subactor"
+                " was spawned with `ActorNursery.run_in_actor()`")
             return NoResult
 
         # expecting a "main" result
@@ -202,7 +170,7 @@ class Portal:
                 (
                     self._final_result_msg,
                     self._final_result_pld,
-                ) = await self._expect_result_ctx._pld_rx.recv_msg(
+                ) = await self._expect_result_ctx._pld_rx.recv_msg_w_pld(
                     ipc=self._expect_result_ctx,
                     expect_msg=Return,
                 )
@@ -214,32 +182,12 @@ class Portal:
 
         return self._final_result_pld
 
-    # TODO: factor this out into a `.highlevel` API-wrapper that uses
-    # a single `.open_context()` call underneath.
-    async def result(
-        self,
-        *args,
-        **kwargs,
-    ) -> Any|Exception:
-        typname: str = type(self).__name__
-        log.warning(
-            f'`{typname}.result()` is DEPRECATED!\n'
-            f'\n'
-            f'Use `{typname}.wait_for_result()` instead!\n'
-        )
-        return await self.wait_for_result(
-            *args,
-            **kwargs,
-        )
-
     async def _cancel_streams(self):
         # terminate all locally running async generator
         # IPC calls
         if self._streams:
-            peer_id: str = f'{self.channel.aid.reprol()!r}'
-            report: str = (
-                f'Cancelling all msg-streams with {peer_id}\n'
-            )
+            log.cancel(
+                f"Cancelling all streams with {self.channel.uid}")
             for stream in self._streams.copy():
                 try:
                     await stream.aclose()
@@ -248,18 +196,10 @@ class Portal:
                     # (unless of course at some point down the road we
                     # won't expect this to always be the case or need to
                     # detect it for respawning purposes?)
-                    report += (
-                        f'->) {stream!r} already closed\n'
-                    )
-
-            log.cancel(report)
+                    log.debug(f"{stream} was already closed.")
 
     async def aclose(self):
-        log.debug(
-            f'Closing portal\n'
-            f'>}}\n'
-            f'|_{self}\n'
-        )
+        log.debug(f"Closing {self}")
         # TODO: once we move to implementing our own `ReceiveChannel`
         # (including remote task cancellation inside its `.aclose()`)
         # we'll need to .aclose all those channels here
@@ -285,22 +225,22 @@ class Portal:
         __runtimeframe__: int = 1  # noqa
 
         chan: Channel = self.channel
-        peer_id: str = f'{self.channel.aid.reprol()!r}'
         if not chan.connected():
             log.runtime(
-                'Peer {peer_id} is already disconnected\n'
-                '-> skipping cancel request..\n'
+                'This channel is already closed, skipping cancel request..'
             )
             return False
 
+        reminfo: str = (
+            f'Portal.cancel_actor() => {self.channel.uid}\n'
+            f'|_{chan}\n'
+        )
         log.cancel(
-            f'Sending actor-runtime-cancel-req to peer\n'
-            f'\n'
-            f'c)=> {peer_id}\n'
+            f'Requesting runtime cancel for peer\n\n'
+            f'{reminfo}'
         )
 
-        # XXX the one spot we set it?
-        chan._cancel_called: bool = True
+        self.channel._cancel_called: bool = True
         try:
             # send cancel cmd - might not get response
             # XXX: sure would be nice to make this work with
@@ -321,47 +261,24 @@ class Portal:
                 # may timeout and we never get an ack (obvi racy)
                 # but that doesn't mean it wasn't cancelled.
                 log.debug(
-                    f'May have failed to cancel peer?\n'
-                    f'\n'
-                    f'c)=?> {peer_id}\n'
+                    'May have failed to cancel peer?\n'
+                    f'{reminfo}'
                 )
 
             # if we get here some weird cancellation case happened
             return False
 
         except (
-            # XXX, should never really get raised unless we aren't
-            # wrapping them in the below type by mistake?
-            #
-            # Leaving the catch here for now until we're very sure
-            # all the cases (for various tpt protos) have indeed been
-            # re-wrapped ;p
             trio.ClosedResourceError,
             trio.BrokenResourceError,
-
-            TransportClosed,
-        ) as tpt_err:
-            ipc_borked_report: str = (
-                f'IPC for actor already closed/broken?\n\n'
-                f'\n'
-                f'c)=x> {peer_id}\n'
+        ):
+            log.debug(
+                'IPC chan for actor already closed or broken?\n\n'
+                f'{self.channel.uid}\n'
+                f' |_{self.channel}\n'
             )
-            match tpt_err:
-                case TransportClosed():
-                    log.debug(ipc_borked_report)
-                case _:
-                    ipc_borked_report += (
-                        f'\n'
-                        f'Unhandled low-level transport-closed/error during\n'
-                        f'Portal.cancel_actor()` request?\n'
-                        f'<{type(tpt_err).__name__}( {tpt_err} )>\n'
-                    )
-                    log.warning(ipc_borked_report)
-
             return False
 
-    # TODO: do we still need this for low level `Actor`-runtime
-    # method calls or can we also remove it?
     async def run_from_ns(
         self,
         namespace_path: str,
@@ -399,8 +316,6 @@ class Portal:
             expect_msg=Return,
         )
 
-    # TODO: factor this out into a `.highlevel` API-wrapper that uses
-    # a single `.open_context()` call underneath.
     async def run(
         self,
         func: str,
@@ -455,8 +370,6 @@ class Portal:
             expect_msg=Return,
         )
 
-    # TODO: factor this out into a `.highlevel` API-wrapper that uses
-    # a single `.open_context()` call underneath.
     @acm
     async def open_stream_from(
         self,
@@ -513,13 +426,10 @@ class Portal:
                 with trio.CancelScope(shield=True):
                     await ctx.cancel()
 
-            except trio.ClosedResourceError as cre:
+            except trio.ClosedResourceError:
                 # if the far end terminates before we send a cancel the
                 # underlying transport-channel may already be closed.
-                log.cancel(
-                    f'Context.cancel() -> {cre!r}\n'
-                    f'cid: {ctx.cid!r} already closed?\n'
-                )
+                log.cancel(f'Context {ctx} was already closed?')
 
             # XXX: should this always be done?
             # await recv_chan.aclose()
@@ -556,12 +466,8 @@ class LocalPortal:
         return it's result.
 
         '''
-        obj = (
-            self.actor
-            if ns == 'self'
-            else importlib.import_module(ns)
-        )
-        func: Callable = getattr(obj, func_name)
+        obj = self.actor if ns == 'self' else importlib.import_module(ns)
+        func = getattr(obj, func_name)
         return await func(**kwargs)
 
 
@@ -586,30 +492,26 @@ async def open_portal(
     assert actor
     was_connected: bool = False
 
-    async with (
-        collapse_eg(),
-        maybe_open_nursery(
-            tn,
-            shield=shield,
-        ) as tn,
-    ):
+    async with maybe_open_nursery(
+        tn,
+        shield=shield,
+    ) as tn:
 
         if not channel.connected():
             await channel.connect()
             was_connected = True
 
-        if channel.aid is None:
-            await channel._do_handshake(
-                aid=actor.aid,
-            )
+        if channel.uid is None:
+            await actor._do_handshake(channel)
 
         msg_loop_cs: trio.CancelScope|None = None
         if start_msg_loop:
-            from . import _rpc
+            from ._runtime import process_messages
             msg_loop_cs = await tn.start(
                 partial(
-                    _rpc.process_messages,
-                    chan=channel,
+                    process_messages,
+                    actor,
+                    channel,
                     # if the local task is cancelled we want to keep
                     # the msg loop running until our block ends
                     shield=True,

tractor/_root.py

@@ -18,65 +18,95 @@
 Root actor runtime ignition(s).
 
 '''
-from contextlib import (
-    asynccontextmanager as acm,
-)
+from contextlib import asynccontextmanager as acm
 from functools import partial
 import importlib
-import inspect
 import logging
 import os
 import signal
 import sys
-from typing import (
-    Any,
-    Callable,
-)
+from typing import Callable
 import warnings
 
 
 import trio
 
-from . import _runtime
-from .devx import (
-    debug,
-    _frame_stack,
-    pformat as _pformat,
+from ._runtime import (
+    Actor,
+    Arbiter,
+    # TODO: rename and make a non-actor subtype?
+    # Arbiter as Registry,
+    async_main,
 )
+from .devx import _debug
 from . import _spawn
 from . import _state
 from . import log
-from .ipc import (
-    _connect_chan,
-)
-from ._addr import (
-    Address,
-    UnwrappedAddress,
-    default_lo_addrs,
-    mk_uuid,
-    wrap_address,
-)
-from .trionics import (
-    is_multi_cancelled,
-    collapse_eg,
-)
-from ._exceptions import (
-    RuntimeFailure,
-)
+from ._ipc import _connect_chan
+from ._exceptions import is_multi_cancelled
+
+
+# set at startup and after forks
+_default_host: str = '127.0.0.1'
+_default_port: int = 1616
+
+# default registry always on localhost
+_default_lo_addrs: list[tuple[str, int]] = [(
+    _default_host,
+    _default_port,
+)]
 
 
 logger = log.get_logger('tractor')
 
 
-# TODO: stick this in a `@acm` defined in `devx.debug`?
-# -[ ] also maybe consider making this a `wrapt`-deco to
-#     save an indent level?
-#
 @acm
-async def maybe_block_bp(
-    debug_mode: bool,
-    maybe_enable_greenback: bool,
-) -> bool:
+async def open_root_actor(
+
+    *,
+    # defaults are above
+    registry_addrs: list[tuple[str, int]]|None = None,
+
+    # defaults are above
+    arbiter_addr: tuple[str, int]|None = None,
+    
+    # binding addrs for the transport layer server
+    trans_bind_addrs: list[tuple[str, int]] = [(_default_host, _default_port)],
+    
+    name: str|None = 'root',
+
+    # either the `multiprocessing` start method:
+    # https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
+    # OR `trio` (the new default).
+    start_method: _spawn.SpawnMethodKey|None = None,
+
+    # enables the multi-process debugger support
+    debug_mode: bool = False,
+    maybe_enable_greenback: bool = False,  # `.pause_from_sync()/breakpoint()` support
+    enable_stack_on_sig: bool = False,
+
+    # internal logging
+    loglevel: str|None = None,
+
+    enable_modules: list|None = None,
+    rpc_module_paths: list|None = None,
+
+    # NOTE: allow caller to ensure that only one registry exists
+    # and that this call creates it.
+    ensure_registry: bool = False,
+
+    hide_tb: bool = True,
+
+) -> Actor:
+    '''
+    Runtime init entry point for ``tractor``.
+
+    '''
+    __tracebackhide__: bool = hide_tb
+    _debug.hide_runtime_frames()
+
+    # TODO: stick this in a `@cm` defined in `devx._debug`?
+    #
     # Override the global debugger hook to make it play nice with
     # ``trio``, see much discussion in:
     # https://github.com/python-trio/trio/issues/1155#issuecomment-742964018
@@ -85,25 +115,17 @@ async def maybe_block_bp(
         'PYTHONBREAKPOINT',
         None,
     )
-    bp_blocked: bool
     if (
         debug_mode
         and maybe_enable_greenback
-        and (
-            maybe_mod := await debug.maybe_init_greenback(
-                raise_not_found=False,
-            )
+        and await _debug.maybe_init_greenback(
+            raise_not_found=False,
         )
     ):
-        logger.info(
-            f'Found `greenback` installed @ {maybe_mod}\n'
-            f'Enabling `tractor.pause_from_sync()` support!\n'
-        )
         os.environ['PYTHONBREAKPOINT'] = (
-            'tractor.devx.debug._sync_pause_from_builtin'
+            'tractor.devx._debug._sync_pause_from_builtin'
         )
         _state._runtime_vars['use_greenback'] = True
-        bp_blocked = False
 
     else:
         # TODO: disable `breakpoint()` by default (without
@@ -122,505 +144,299 @@ async def maybe_block_bp(
         # lol ok,
         # https://docs.python.org/3/library/sys.html#sys.breakpointhook
         os.environ['PYTHONBREAKPOINT'] = "0"
-        bp_blocked = True
 
-    try:
-        yield bp_blocked
-    finally:
-        # restore any prior built-in `breakpoint()` hook state
-        if builtin_bp_handler is not None:
-            sys.breakpointhook = builtin_bp_handler
+    # attempt to retreive ``trio``'s sigint handler and stash it
+    # on our debugger lock state.
+    _debug.DebugStatus._trio_handler = signal.getsignal(signal.SIGINT)
 
-        if orig_bp_path is not None:
-            os.environ['PYTHONBREAKPOINT'] = orig_bp_path
+    # mark top most level process as root actor
+    _state._runtime_vars['_is_root'] = True
 
-        else:
-            # clear env back to having no entry
-            os.environ.pop('PYTHONBREAKPOINT', None)
+    # caps based rpc list
+    enable_modules = (
+        enable_modules
+        or
+        []
+    )
 
+    if rpc_module_paths:
+        warnings.warn(
+            "`rpc_module_paths` is now deprecated, use "
+            " `enable_modules` instead.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        enable_modules.extend(rpc_module_paths)
 
+    if start_method is not None:
+        _spawn.try_set_start_method(start_method)
 
-@acm
-async def open_root_actor(
-    *,
-    # defaults are above
-    registry_addrs: list[UnwrappedAddress]|None = None,
+    if arbiter_addr is not None:
+        warnings.warn(
+            '`arbiter_addr` is now deprecated\n'
+            'Use `registry_addrs: list[tuple]` instead..',
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        registry_addrs = [arbiter_addr]
 
-    # defaults are above
-    arbiter_addr: tuple[UnwrappedAddress]|None = None,
+    registry_addrs: list[tuple[str, int]] = (
+        registry_addrs
+        or
+        _default_lo_addrs
+    )
+    assert registry_addrs
+    
+    assert trans_bind_addrs
 
-    enable_transports: list[
-        # TODO, this should eventually be the pairs as
-        # defined by (codec, proto) as on `MsgTransport.
-        _state.TransportProtocolKey,
-    ]|None = None,
+    loglevel = (
+        loglevel
+        or log._default_loglevel
+    ).upper()
 
-    name: str|None = 'root',
-
-    # either the `multiprocessing` start method:
-    # https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
-    # OR `trio` (the new default).
-    start_method: _spawn.SpawnMethodKey|None = None,
-
-    # enables the multi-process debugger support
-    debug_mode: bool = False,
-    maybe_enable_greenback: bool = False,  # `.pause_from_sync()/breakpoint()` support
-    # ^XXX NOTE^ the perf implications of use,
-    # https://greenback.readthedocs.io/en/latest/principle.html#performance
-    enable_stack_on_sig: bool = False,
-
-    # internal logging
-    loglevel: str|None = None,
-
-    enable_modules: list|None = None,
-    rpc_module_paths: list|None = None,
-
-    # NOTE: allow caller to ensure that only one registry exists
-    # and that this call creates it.
-    ensure_registry: bool = False,
-
-    hide_tb: bool = True,
-
-    # XXX, proxied directly to `.devx.debug._maybe_enter_pm()`
-    # for REPL-entry logic.
-    debug_filter: Callable[
-        [BaseException|BaseExceptionGroup],
-        bool,
-    ] = lambda err: not is_multi_cancelled(err),
-
-    # TODO, a way for actors to augment passing derived
-    # read-only state to sublayers?
-    # extra_rt_vars: dict|None = None,
-
-) -> _runtime.Actor:
-    '''
-    Initialize the `tractor` runtime by starting a "root actor" in
-    a parent-most Python process.
-
-    All (disjoint) actor-process-trees-as-programs are created via
-    this entrypoint.
-
-    '''
-    # XXX NEVER allow nested actor-trees!
-    if already_actor := _state.current_actor(
-        err_on_no_runtime=False,
+    if (
+        debug_mode
+        and _spawn._spawn_method == 'trio'
     ):
-        rtvs: dict[str, Any] = _state._runtime_vars
-        root_mailbox: list[str, int] = rtvs['_root_mailbox']
-        registry_addrs: list[list[str, int]] = rtvs['_registry_addrs']
-        raise RuntimeFailure(
-            f'A current actor already exists !?\n'
-            f'({already_actor}\n'
-            f'\n'
-            f'You can NOT open a second root actor from within '
-            f'an existing tree and the current root of this '
-            f'already exists !!\n'
-            f'\n'
-            f'_root_mailbox: {root_mailbox!r}\n'
-            f'_registry_addrs: {registry_addrs!r}\n'
+        _state._runtime_vars['_debug_mode'] = True
+
+        # expose internal debug module to every actor allowing for
+        # use of ``await tractor.pause()``
+        enable_modules.append('tractor.devx._debug')
+
+        # if debug mode get's enabled *at least* use that level of
+        # logging for some informative console prompts.
+        if (
+            logging.getLevelName(
+                # lul, need the upper case for the -> int map?
+                # sweet "dynamic function behaviour" stdlib...
+                loglevel,
+            ) > logging.getLevelName('PDB')
+        ):
+            loglevel = 'PDB'
+
+
+    elif debug_mode:
+        raise RuntimeError(
+            "Debug mode is only supported for the `trio` backend!"
         )
 
-    async with maybe_block_bp(
-        debug_mode=debug_mode,
-        maybe_enable_greenback=maybe_enable_greenback,
+    assert loglevel
+    _log = log.get_console_log(loglevel)
+    assert _log
+
+    # TODO: factor this into `.devx._stackscope`!!
+    if (
+        debug_mode
+        and
+        enable_stack_on_sig
     ):
-        if enable_transports is None:
-            enable_transports: list[str] = _state.current_ipc_protos()
-        else:
-            _state._runtime_vars['_enable_tpts'] = enable_transports
-
-        # TODO! support multi-tpts per actor!
-        # Bo
-        if not len(enable_transports) == 1:
-            raise RuntimeError(
-                f'No multi-tpt support yet!\n'
-                f'enable_transports={enable_transports!r}\n'
-            )
-
-        _frame_stack.hide_runtime_frames()
-        __tracebackhide__: bool = hide_tb
-
-        # attempt to retreive ``trio``'s sigint handler and stash it
-        # on our debugger lock state.
-        debug.DebugStatus._trio_handler = signal.getsignal(signal.SIGINT)
-
-        # mark top most level process as root actor
-        _state._runtime_vars['_is_root'] = True
-
-        # caps based rpc list
-        enable_modules = (
-            enable_modules
-            or
-            []
-        )
-
-        if rpc_module_paths:
-            warnings.warn(
-                "`rpc_module_paths` is now deprecated, use "
-                " `enable_modules` instead.",
-                DeprecationWarning,
-                stacklevel=2,
-            )
-            enable_modules.extend(rpc_module_paths)
-
-        if start_method is not None:
-            _spawn.try_set_start_method(start_method)
-
-        # TODO! remove this ASAP!
-        if arbiter_addr is not None:
-            warnings.warn(
-                '`arbiter_addr` is now deprecated\n'
-                'Use `registry_addrs: list[tuple]` instead..',
-                DeprecationWarning,
-                stacklevel=2,
-            )
-            uw_reg_addrs = [arbiter_addr]
-
-        uw_reg_addrs = registry_addrs
-        if not uw_reg_addrs:
-            uw_reg_addrs: list[UnwrappedAddress] = default_lo_addrs(
-                enable_transports
-            )
-
-        # must exist by now since all below code is dependent
-        assert uw_reg_addrs
-        registry_addrs: list[Address] = [
-            wrap_address(uw_addr)
-            for uw_addr in uw_reg_addrs
-        ]
-
-        loglevel = (
-            loglevel
-            or log._default_loglevel
-        ).upper()
-
-        if (
-            debug_mode
-            and
-            _spawn._spawn_method == 'trio'
-        ):
-            _state._runtime_vars['_debug_mode'] = True
-
-            # expose internal debug module to every actor allowing for
-            # use of ``await tractor.pause()``
-            enable_modules.append('tractor.devx.debug._tty_lock')
-
-            # if debug mode get's enabled *at least* use that level of
-            # logging for some informative console prompts.
-            if (
-                logging.getLevelName(
-                    # lul, need the upper case for the -> int map?
-                    # sweet "dynamic function behaviour" stdlib...
-                    loglevel,
-                ) > logging.getLevelName('PDB')
-            ):
-                loglevel = 'PDB'
-
-
-        elif debug_mode:
-            raise RuntimeError(
-                "Debug mode is only supported for the `trio` backend!"
-            )
-
-        assert loglevel
-        _log = log.get_console_log(loglevel)
-        assert _log
-
-        # TODO: factor this into `.devx._stackscope`!!
-        if (
-            debug_mode
-            and
-            enable_stack_on_sig
-        ):
-            from .devx._stackscope import enable_stack_on_sig
-            enable_stack_on_sig()
-
-        # closed into below ping task-func
-        ponged_addrs: list[Address] = []
-
-        async def ping_tpt_socket(
-            addr: Address,
-            timeout: float = 1,
-        ) -> None:
-            '''
-            Attempt temporary connection to see if a registry is
-            listening at the requested address by a tranport layer
-            ping.
-
-            If a connection can't be made quickly we assume none no
-            server is listening at that addr.
-
-            '''
-            try:
-                # TODO: this connect-and-bail forces us to have to
-                # carefully rewrap TCP 104-connection-reset errors as
-                # EOF so as to avoid propagating cancel-causing errors
-                # to the channel-msg loop machinery. Likely it would
-                # be better to eventually have a "discovery" protocol
-                # with basic handshake instead?
-                with trio.move_on_after(timeout):
-                    async with _connect_chan(addr.unwrap()):
-                        ponged_addrs.append(addr)
-
-            except OSError:
-                # ?TODO, make this a "discovery" log level?
-                logger.info(
-                    f'No root-actor registry found @ {addr!r}\n'
-                )
-
-        # !TODO, this is basically just another (abstract)
-        # happy-eyeballs, so we should try for formalize it somewhere
-        # in a `.[_]discovery` ya?
-        #
-        async with trio.open_nursery() as tn:
-            for uw_addr in uw_reg_addrs:
-                addr: Address = wrap_address(uw_addr)
-                tn.start_soon(
-                    ping_tpt_socket,
-                    addr,
-                )
-
-        trans_bind_addrs: list[UnwrappedAddress] = []
-
-        # Create a new local root-actor instance which IS NOT THE
-        # REGISTRAR
-        if ponged_addrs:
-            if ensure_registry:
-                raise RuntimeError(
-                     f'Failed to open `{name}`@{ponged_addrs}: '
-                    'registry socket(s) already bound'
-                )
-
-            # we were able to connect to an arbiter
-            logger.info(
-                f'Registry(s) seem(s) to exist @ {ponged_addrs}'
-            )
-
-            actor = _runtime.Actor(
-                name=name or 'anonymous',
-                uuid=mk_uuid(),
-                registry_addrs=ponged_addrs,
-                loglevel=loglevel,
-                enable_modules=enable_modules,
-            )
-            # **DO NOT** use the registry_addrs as the
-            # ipc-transport-server's bind-addrs as this is
-            # a new NON-registrar, ROOT-actor.
-            #
-            # XXX INSTEAD, bind random addrs using the same tpt
-            # proto.
-            for addr in ponged_addrs:
-                trans_bind_addrs.append(
-                    addr.get_random(
-                        bindspace=addr.bindspace,
-                    )
-                )
-
-        # Start this local actor as the "registrar", aka a regular
-        # actor who manages the local registry of "mailboxes" of
-        # other process-tree-local sub-actors.
-        else:
-            # NOTE that if the current actor IS THE REGISTAR, the
-            # following init steps are taken:
-            # - the tranport layer server is bound to each addr
-            #   pair defined in provided registry_addrs, or the default.
-            trans_bind_addrs = uw_reg_addrs
-
-            # - it is normally desirable for any registrar to stay up
-            #   indefinitely until either all registered (child/sub)
-            #   actors are terminated (via SC supervision) or,
-            #   a re-election process has taken place.
-            # NOTE: all of ^ which is not implemented yet - see:
-            # https://github.com/goodboy/tractor/issues/216
-            # https://github.com/goodboy/tractor/pull/348
-            # https://github.com/goodboy/tractor/issues/296
-
-            # TODO: rename as `RootActor` or is that even necessary?
-            actor = _runtime.Arbiter(
-                name=name or 'registrar',
-                uuid=mk_uuid(),
-                registry_addrs=registry_addrs,
-                loglevel=loglevel,
-                enable_modules=enable_modules,
-            )
-            # XXX, in case the root actor runtime was actually run from
-            # `tractor.to_asyncio.run_as_asyncio_guest()` and NOt
-            # `.trio.run()`.
-            actor._infected_aio = _state._runtime_vars['_is_infected_aio']
-
-        # NOTE, only set the loopback addr for the
-        # process-tree-global "root" mailbox since all sub-actors
-        # should be able to speak to their root actor over that
-        # channel.
-        raddrs: list[Address] = _state._runtime_vars['_root_addrs']
-        raddrs.extend(trans_bind_addrs)
-        # TODO, remove once we have also removed all usage;
-        # eventually all (root-)registry apis should expect > 1 addr.
-        _state._runtime_vars['_root_mailbox'] = raddrs[0]
-
-        # Start up main task set via core actor-runtime nurseries.
         try:
-            # assign process-local actor
-            _state._current_actor = actor
-
-            # start local channel-server and fake the portal API
-            # NOTE: this won't block since we provide the nursery
-            report: str = f'Starting actor-runtime for {actor.aid.reprol()!r}\n'
-            if reg_addrs := actor.registry_addrs:
-                report += (
-                    '-> Opening new registry @ '
-                    +
-                    '\n'.join(
-                        f'{addr}' for addr in reg_addrs
-                    )
-                )
-            logger.info(f'{report}\n')
-
-            # start runtime in a bg sub-task, yield to caller.
-            async with (
-                collapse_eg(),
-                trio.open_nursery() as root_tn,
-
-                # ?TODO? finally-footgun below?
-                # -> see note on why shielding.
-                # maybe_raise_from_masking_exc(),
-            ):
-                actor._root_tn = root_tn
-                # `_runtime.async_main()` creates an internal nursery
-                # and blocks here until any underlying actor(-process)
-                # tree has terminated thereby conducting so called
-                # "end-to-end" structured concurrency throughout an
-                # entire hierarchical python sub-process set; all
-                # "actor runtime" primitives are SC-compat and thus all
-                # transitively spawned actors/processes must be as
-                # well.
-                await root_tn.start(
-                    partial(
-                        _runtime.async_main,
-                        actor,
-                        accept_addrs=trans_bind_addrs,
-                        parent_addr=None
-                    )
-                )
-                try:
-                    yield actor
-                except (
-                    Exception,
-                    BaseExceptionGroup,
-                ) as err:
-
-                    # TODO, in beginning to handle the subsubactor with
-                    # crashed grandparent cases..
-                    #
-                    # was_locked: bool = await debug.maybe_wait_for_debugger(
-                    #     child_in_debug=True,
-                    # )
-                    # XXX NOTE XXX see equiv note inside
-                    # `._runtime.Actor._stream_handler()` where in the
-                    # non-root or root-that-opened-this-mahually case we
-                    # wait for the local actor-nursery to exit before
-                    # exiting the transport channel handler.
-                    entered: bool = await debug._maybe_enter_pm(
-                        err,
-                        api_frame=inspect.currentframe(),
-                        debug_filter=debug_filter,
-
-                        # XXX NOTE, required to debug root-actor
-                        # crashes under cancellation conditions; so
-                        # most of them!
-                        shield=root_tn.cancel_scope.cancel_called,
-                    )
-
-                    if (
-                        not entered
-                        and
-                        not is_multi_cancelled(
-                            err,
-                        )
-                    ):
-                        logger.exception(
-                            'Root actor crashed\n'
-                            f'>x)\n'
-                            f' |_{actor}\n'
-                        )
-
-                    # ALWAYS re-raise any error bubbled up from the
-                    # runtime!
-                    raise
-
-                finally:
-                    # NOTE/TODO?, not sure if we'll ever need this but it's
-                    # possibly better for even more determinism?
-                    # logger.cancel(
-                    #     f'Waiting on {len(nurseries)} nurseries in root..')
-                    # nurseries = actor._actoruid2nursery.values()
-                    # async with trio.open_nursery() as tempn:
-                    #     for an in nurseries:
-                    #         tempn.start_soon(an.exited.wait)
-
-                    op_nested_actor_repr: str = _pformat.nest_from_op(
-                        input_op='>) ',
-                        text=actor.pformat(),
-                        nest_prefix='|_',
-                    )
-                    logger.info(
-                        f'Closing down root actor\n'
-                        f'{op_nested_actor_repr}'
-                    )
-                    # XXX, THIS IS A *finally-footgun*!
-                    # (also mentioned in with-block above)
-                    # -> though already shields iternally it can
-                    # taskc here and mask underlying errors raised in
-                    # the try-block above?
-                    with trio.CancelScope(shield=True):
-                        await actor.cancel(None)  # self cancel
-        finally:
-            # revert all process-global runtime state
-            if (
-                debug_mode
-                and
-                _spawn._spawn_method == 'trio'
-            ):
-                _state._runtime_vars['_debug_mode'] = False
-
-            _state._current_actor = None
-            _state._last_actor_terminated = actor
-
-            sclang_repr: str = _pformat.nest_from_op(
-                input_op=')>',
-                text=actor.pformat(),
-                nest_prefix='|_',
-                nest_indent=1,
+            logger.info('Enabling `stackscope` traces on SIGUSR1')
+            from .devx import enable_stack_on_sig
+            enable_stack_on_sig()
+        except ImportError:
+            logger.warning(
+                '`stackscope` not installed for use in debug mode!'
             )
 
-            logger.info(
-                f'Root actor terminated\n'
-                f'{sclang_repr}'
+    # closed into below ping task-func
+    ponged_addrs: list[tuple[str, int]] = []
+
+    async def ping_tpt_socket(
+        addr: tuple[str, int],
+        timeout: float = 1,
+    ) -> None:
+        '''
+        Attempt temporary connection to see if a registry is
+        listening at the requested address by a tranport layer
+        ping.
+
+        If a connection can't be made quickly we assume none no
+        server is listening at that addr.
+
+        '''
+        try:
+            # TODO: this connect-and-bail forces us to have to
+            # carefully rewrap TCP 104-connection-reset errors as
+            # EOF so as to avoid propagating cancel-causing errors
+            # to the channel-msg loop machinery. Likely it would
+            # be better to eventually have a "discovery" protocol
+            # with basic handshake instead?
+            with trio.move_on_after(timeout):
+                async with _connect_chan(*addr):
+                    ponged_addrs.append(addr)
+
+        except OSError:
+            # TODO: make this a "discovery" log level?
+            logger.warning(f'No actor registry found @ {addr}')
+
+    async with trio.open_nursery() as tn:
+        for addr in registry_addrs:
+            tn.start_soon(
+                ping_tpt_socket,
+                tuple(addr),  # TODO: just drop this requirement?
             )
 
+    # Create a new local root-actor instance which IS NOT THE
+    # REGISTRAR
+    if ponged_addrs:
+
+        if ensure_registry:
+            raise RuntimeError(
+                 f'Failed to open `{name}`@{ponged_addrs}: '
+                'registry socket(s) already bound'
+            )
+
+        # we were able to connect to an arbiter
+        logger.info(
+            f'Registry(s) seem(s) to exist @ {ponged_addrs}'
+        )
+
+        actor = Actor(
+            name=name or 'anonymous',
+            registry_addrs=ponged_addrs,
+            loglevel=loglevel,
+            enable_modules=enable_modules,
+        )
+
+    # Start this local actor as the "registrar", aka a regular
+    # actor who manages the local registry of "mailboxes" of
+    # other process-tree-local sub-actors.
+    else:
+
+        # NOTE that if the current actor IS THE REGISTAR, the
+        # following init steps are taken:
+        # - the tranport layer server is bound to each (host, port)
+        #   pair defined in provided registry_addrs, or the default.
+        trans_bind_addrs = registry_addrs
+
+        # - it is normally desirable for any registrar to stay up
+        #   indefinitely until either all registered (child/sub)
+        #   actors are terminated (via SC supervision) or,
+        #   a re-election process has taken place. 
+        # NOTE: all of ^ which is not implemented yet - see:
+        # https://github.com/goodboy/tractor/issues/216
+        # https://github.com/goodboy/tractor/pull/348
+        # https://github.com/goodboy/tractor/issues/296
+
+        actor = Arbiter(
+            name or 'registrar',
+            registry_addrs=registry_addrs,
+            loglevel=loglevel,
+            enable_modules=enable_modules,
+        )
+
+    # Start up main task set via core actor-runtime nurseries.
+    try:
+        # assign process-local actor
+        _state._current_actor = actor
+
+        # start local channel-server and fake the portal API
+        # NOTE: this won't block since we provide the nursery
+        ml_addrs_str: str = '\n'.join(
+            f'@{addr}' for addr in trans_bind_addrs
+        )
+        logger.info(
+            f'Starting local {actor.uid} on the following transport addrs:\n'
+            f'{ml_addrs_str}'
+        )
+
+        # start the actor runtime in a new task
+        async with trio.open_nursery() as nursery:
+
+            # ``_runtime.async_main()`` creates an internal nursery
+            # and blocks here until any underlying actor(-process)
+            # tree has terminated thereby conducting so called
+            # "end-to-end" structured concurrency throughout an
+            # entire hierarchical python sub-process set; all
+            # "actor runtime" primitives are SC-compat and thus all
+            # transitively spawned actors/processes must be as
+            # well.
+            await nursery.start(
+                partial(
+                    async_main,
+                    actor,
+                    accept_addrs=trans_bind_addrs,
+                    parent_addr=None
+                )
+            )
+            try:
+                yield actor
+
+            except (
+                Exception,
+                BaseExceptionGroup,
+            ) as err:
+
+                import inspect
+                entered: bool = await _debug._maybe_enter_pm(
+                    err,
+                    api_frame=inspect.currentframe(),
+                )
+
+                if (
+                    not entered
+                    and not is_multi_cancelled(err)
+                ):
+                    logger.exception('Root actor crashed:\n')
+
+                # ALWAYS re-raise any error bubbled up from the
+                # runtime!
+                raise
+
+            finally:
+                # NOTE: not sure if we'll ever need this but it's
+                # possibly better for even more determinism?
+                # logger.cancel(
+                #     f'Waiting on {len(nurseries)} nurseries in root..')
+                # nurseries = actor._actoruid2nursery.values()
+                # async with trio.open_nursery() as tempn:
+                #     for an in nurseries:
+                #         tempn.start_soon(an.exited.wait)
+
+                logger.info(
+                    'Closing down root actor'
+                )
+                await actor.cancel(None)  # self cancel
+    finally:
+        _state._current_actor = None
+        _state._last_actor_terminated = actor
+
+        # restore built-in `breakpoint()` hook state
+        if (
+            debug_mode
+            and
+            maybe_enable_greenback
+        ):
+            if builtin_bp_handler is not None:
+                sys.breakpointhook = builtin_bp_handler
+
+            if orig_bp_path is not None:
+                os.environ['PYTHONBREAKPOINT'] = orig_bp_path
+
+            else:
+                # clear env back to having no entry
+                os.environ.pop('PYTHONBREAKPOINT', None)
+
+        logger.runtime("Root actor terminated")
+
 
 def run_daemon(
     enable_modules: list[str],
 
     # runtime kwargs
     name: str | None = 'root',
-    registry_addrs: list[UnwrappedAddress]|None = None,
+    registry_addrs: list[tuple[str, int]] = _default_lo_addrs,
 
     start_method: str | None = None,
     debug_mode: bool = False,
-
-    # TODO, support `infected_aio=True` mode by,
-    # - calling the appropriate entrypoint-func from `.to_asyncio`
-    # - maybe init-ing `greenback` as done above in
-    #   `open_root_actor()`.
-
     **kwargs
 
 ) -> None:
     '''
-    Spawn a root (daemon) actor which will respond to RPC; the main
-    task simply starts the runtime and then blocks via embedded
-    `trio.sleep_forever()`.
+    Spawn daemon actor which will respond to RPC; the main task simply
+    starts the runtime and then sleeps forever.
 
     This is a very minimal convenience wrapper around starting
     a "run-until-cancelled" root actor which can be started with a set
@@ -633,6 +449,7 @@ def run_daemon(
         importlib.import_module(path)
 
     async def _main():
+
         async with open_root_actor(
             registry_addrs=registry_addrs,
             name=name,

tractor/_rpc.py

@@ -37,13 +37,12 @@ import warnings
 
 import trio
 from trio import (
-    Cancelled,
     CancelScope,
     Nursery,
     TaskStatus,
 )
 
-from .ipc import Channel
+from ._ipc import Channel
 from ._context import (
     Context,
 )
@@ -53,18 +52,14 @@ from ._exceptions import (
     ModuleNotExposed,
     MsgTypeError,
     TransportClosed,
+    is_multi_cancelled,
     pack_error,
     unpack_error,
 )
-from .trionics import (
-    collapse_eg,
-    is_multi_cancelled,
-    maybe_raise_from_masking_exc,
-)
 from .devx import (
-    debug,
+    maybe_wait_for_debugger,
+    _debug,
     add_div,
-    pformat as _pformat,
 )
 from . import _state
 from .log import get_logger
@@ -94,16 +89,6 @@ if TYPE_CHECKING:
 log = get_logger('tractor')
 
 
-# ?TODO? move to a `tractor.lowlevel._rpc` with the below
-# func-type-cases implemented "on top of" `@context` defs:
-# -[ ] std async func helper decorated with `@rpc_func`?
-# -[ ] `Portal.open_stream_from()` with async-gens?
-#  |_ possibly a duplex form of this with a
-#    `sent_from_peer = yield send_to_peer` form, which would require
-#    syncing the send/recv side with possibly `.receive_nowait()`
-#    on each `yield`?
-# -[ ] some kinda `@rpc_acm` maybe that does a fixture style with
-#     user only defining a single-`yield` generator-func?
 async def _invoke_non_context(
     actor: Actor,
     cancel_scope: CancelScope,
@@ -123,9 +108,8 @@ async def _invoke_non_context(
     ] = trio.TASK_STATUS_IGNORED,
 ):
     __tracebackhide__: bool = True
-    cs: CancelScope|None = None  # ref when activated
 
-    # ?TODO? can we unify this with the `context=True` impl below?
+    # TODO: can we unify this with the `context=True` impl below?
     if inspect.isasyncgen(coro):
         await chan.send(
             StartAck(
@@ -176,6 +160,10 @@ async def _invoke_non_context(
                 functype='asyncgen',
             )
         )
+        # XXX: the async-func may spawn further tasks which push
+        # back values like an async-generator would but must
+        # manualy construct the response dict-packet-responses as
+        # above
         with cancel_scope as cs:
             ctx._scope = cs
             task_status.started(ctx)
@@ -187,13 +175,15 @@ async def _invoke_non_context(
             await chan.send(
                 Stop(cid=cid)
             )
-
-    # simplest function/method request-response pattern
-    # XXX: in the most minimally used case, just a scheduled internal runtime
-    # call to `Actor._cancel_task()` from the ctx-peer task since we
-    # don't (yet) have a dedicated IPC msg.
-    # ------ - ------
     else:
+        # regular async function/method
+        # XXX: possibly just a scheduled `Actor._cancel_task()`
+        # from a remote request to cancel some `Context`.
+        # ------ - ------
+        # TODO: ideally we unify this with the above `context=True`
+        # block such that for any remote invocation ftype, we
+        # always invoke the far end RPC task scheduling the same
+        # way: using the linked IPC context machinery.
         failed_resp: bool = False
         try:
             ack = StartAck(
@@ -221,18 +211,11 @@ async def _invoke_non_context(
             task_status.started(ctx)
             result = await coro
             fname: str = func.__name__
-
-            op_nested_task: str = _pformat.nest_from_op(
-                input_op=f')> cid: {ctx.cid!r}',
-                text=f'{ctx._task}',
-                nest_indent=1,  # under >
-            )
             log.runtime(
-                f'RPC task complete\n'
-                f'\n'
-                f'{op_nested_task}\n'
-                f'\n'
-                f')> {fname}() -> {pformat(result)}\n'
+                'RPC complete:\n'
+                f'task: {ctx._task}\n'
+                f'|_cid={ctx.cid}\n'
+                f'|_{fname}() -> {pformat(result)}\n'
             )
 
             # NOTE: only send result if we know IPC isn't down
@@ -263,7 +246,7 @@ async def _errors_relayed_via_ipc(
     ctx: Context,
     is_rpc: bool,
 
-    hide_tb: bool = True,
+    hide_tb: bool = False,
     debug_kbis: bool = False,
     task_status: TaskStatus[
         Context | BaseException
@@ -279,7 +262,7 @@ async def _errors_relayed_via_ipc(
 
     # TODO: a debug nursery when in debug mode!
     # async with maybe_open_debugger_nursery() as debug_tn:
-    # => see matching comment in side `.debug._pause()`
+    # => see matching comment in side `._debug._pause()`
     rpc_err: BaseException|None = None
     try:
         yield  # run RPC invoke body
@@ -331,7 +314,7 @@ async def _errors_relayed_via_ipc(
                     'RPC task crashed, attempting to enter debugger\n'
                     f'|_{ctx}'
                 )
-                entered_debug = await debug._maybe_enter_pm(
+                entered_debug = await _debug._maybe_enter_pm(
                     err,
                     api_frame=inspect.currentframe(),
                 )
@@ -371,26 +354,19 @@ async def _errors_relayed_via_ipc(
             # channel.
             task_status.started(err)
 
-        # always propagate KBIs at the sys-process level.
-        if (
-            isinstance(err, KeyboardInterrupt)
-
-            # ?TODO? except when running in asyncio mode?
-            # |_ wut if you want to open a `@context` FROM an
-            # infected_aio task?
-            # and not actor.is_infected_aio()
-        ):
+        # always reraise KBIs so they propagate at the sys-process level.
+        if isinstance(err, KeyboardInterrupt):
             raise
 
     # RPC task bookeeping.
     # since RPC tasks are scheduled inside a flat
-    # `Actor._service_tn`, we add "handles" to each such that
+    # `Actor._service_n`, we add "handles" to each such that
     # they can be individually ccancelled.
     finally:
 
-        # if the error is not from user code and instead a failure of
-        # an internal-runtime-RPC or IPC-connection, we do (prolly) want
-        # to show this frame!
+        # if the error is not from user code and instead a failure
+        # of a runtime RPC or transport failure we do prolly want to
+        # show this frame
         if (
             rpc_err
             and (
@@ -462,7 +438,7 @@ async def _invoke(
     connected IPC channel.
 
     This is the core "RPC" `trio.Task` scheduling machinery used to start every
-    remotely invoked function, normally in `Actor._service_tn: Nursery`.
+    remotely invoked function, normally in `Actor._service_n: Nursery`.
 
     '''
     __tracebackhide__: bool = hide_tb
@@ -475,13 +451,14 @@ async def _invoke(
     ):
         # XXX for .pause_from_sync()` usage we need to make sure
         # `greenback` is boostrapped in the subactor!
-        await debug.maybe_init_greenback()
+        await _debug.maybe_init_greenback()
 
     # TODO: possibly a specially formatted traceback
     # (not sure what typing is for this..)?
     # tb: TracebackType = None
 
     cancel_scope = CancelScope()
+    cs: CancelScope|None = None  # ref when activated
     ctx = actor.get_context(
         chan=chan,
         cid=cid,
@@ -629,39 +606,26 @@ async def _invoke(
         #  -> the below scope is never exposed to the
         #     `@context` marked RPC function.
         # - `._portal` is never set.
-        scope_err: BaseException|None = None
         try:
-            # TODO: better `trionics` primitive/tooling usage here!
-            # -[ ] should would be nice to have our `TaskMngr`
-            #   nursery here!
-            # -[ ] payload value checking like we do with
-            #   `.started()` such that the debbuger can engage
-            #   here in the child task instead of waiting for the
-            #   parent to crash with it's own MTE..
-            #
-            tn: Nursery
-            rpc_ctx_cs: CancelScope
             async with (
-                collapse_eg(hide_tb=False),
                 trio.open_nursery() as tn,
                 msgops.maybe_limit_plds(
                     ctx=ctx,
                     spec=ctx_meta.get('pld_spec'),
                     dec_hook=ctx_meta.get('dec_hook'),
                 ),
-
-                # XXX NOTE, this being the "most embedded"
-                # scope ensures unasking of the `await coro` below
-                # *should* never be interfered with!!
-                maybe_raise_from_masking_exc(
-                    unmask_from=(Cancelled,),
-                ) as _mbme,  # maybe boxed masked exc
             ):
                 ctx._scope_nursery = tn
-                rpc_ctx_cs = ctx._scope = tn.cancel_scope
+                ctx._scope = tn.cancel_scope
                 task_status.started(ctx)
 
-                # invoke user endpoint fn.
+                # TODO: better `trionics` tooling:
+                # -[ ] should would be nice to have our `TaskMngr`
+                #   nursery here!
+                # -[ ] payload value checking like we do with
+                #   `.started()` such that the debbuger can engage
+                #   here in the child task instead of waiting for the
+                #   parent to crash with it's own MTE..
                 res: Any|PayloadT = await coro
                 return_msg: Return|CancelAck = return_msg_type(
                     cid=cid,
@@ -669,11 +633,6 @@ async def _invoke(
                 )
                 # set and shuttle final result to "parent"-side task.
                 ctx._result = res
-                log.runtime(
-                    f'Sending result msg and exiting {ctx.side!r}\n'
-                    f'\n'
-                    f'{pretty_struct.pformat(return_msg)}\n'
-                )
                 await chan.send(return_msg)
 
             # NOTE: this happens IFF `ctx._scope.cancel()` is
@@ -683,7 +642,7 @@ async def _invoke(
             #   itself calls `ctx._maybe_cancel_and_set_remote_error()`
             #   which cancels the scope presuming the input error
             #   is not a `.cancel_acked` pleaser.
-            if rpc_ctx_cs.cancelled_caught:
+            if ctx._scope.cancelled_caught:
                 our_uid: tuple = actor.uid
 
                 # first check for and raise any remote error
@@ -693,7 +652,9 @@ async def _invoke(
                 if re := ctx._remote_error:
                     ctx._maybe_raise_remote_err(re)
 
-                if rpc_ctx_cs.cancel_called:
+                cs: CancelScope = ctx._scope
+
+                if cs.cancel_called:
                     canceller: tuple = ctx.canceller
                     explain: str = f'{ctx.side!r}-side task was cancelled by '
 
@@ -719,14 +680,8 @@ async def _invoke(
                     elif canceller == ctx.chan.uid:
                         explain += f'its {ctx.peer_side!r}-side peer'
 
-                    elif canceller == our_uid:
-                        explain += 'itself'
-
-                    elif canceller:
-                        explain += 'a remote peer'
-
                     else:
-                        explain += 'an unknown cause?'
+                        explain += 'a remote peer'
 
                     explain += (
                         add_div(message=explain)
@@ -762,54 +717,45 @@ async def _invoke(
         # XXX: do we ever trigger this block any more?
         except (
             BaseExceptionGroup,
-            BaseException,
             trio.Cancelled,
-        ) as _scope_err:
-            scope_err = _scope_err
+            BaseException,
+
+        ) as scope_error:
             if (
-                isinstance(scope_err, RuntimeError)
-                and
-                scope_err.args
-                and
-                'Cancel scope stack corrupted' in scope_err.args[0]
+                isinstance(scope_error, RuntimeError)
+                and scope_error.args
+                and 'Cancel scope stack corrupted' in scope_error.args[0]
             ):
                 log.exception('Cancel scope stack corrupted!?\n')
-                # debug.mk_pdb().set_trace()
+                # _debug.mk_pdb().set_trace()
 
             # always set this (child) side's exception as the
             # local error on the context
-            ctx._local_error: BaseException = scope_err
+            ctx._local_error: BaseException = scope_error
             # ^-TODO-^ question,
             # does this matter other then for
             # consistentcy/testing?
             # |_ no user code should be in this scope at this point
             #    AND we already set this in the block below?
 
-            # XXX if a remote error was set then likely the
-            # exc group was raised due to that, so
+            # if a remote error was set then likely the
+            # exception group was raised due to that, so
             # and we instead raise that error immediately!
-            maybe_re: (
-                ContextCancelled|RemoteActorError
-            ) = ctx.maybe_raise()
-            if maybe_re:
-                log.cancel(
-                    f'Suppressing remote-exc from peer,\n'
-                    f'{maybe_re!r}\n'
-                )
+            ctx.maybe_raise()
 
             # maybe TODO: pack in come kinda
             # `trio.Cancelled.__traceback__` here so they can be
             # unwrapped and displayed on the caller side? no se..
-            raise scope_err
+            raise
 
         # `@context` entrypoint task bookeeping.
         # i.e. only pop the context tracking if used ;)
         finally:
-            assert chan.aid
+            assert chan.uid
 
             # don't pop the local context until we know the
             # associated child isn't in debug any more
-            await debug.maybe_wait_for_debugger()
+            await maybe_wait_for_debugger()
             ctx: Context = actor._contexts.pop((
                 chan.uid,
                 cid,
@@ -822,49 +768,26 @@ async def _invoke(
                 f'after having {ctx.repr_state!r}\n'
             )
             if merr:
+
                 logmeth: Callable = log.error
-                if (
-                    # ctxc: by `Context.cancel()`
-                    isinstance(merr, ContextCancelled)
+                if isinstance(merr, ContextCancelled):
+                    logmeth: Callable = log.runtime
 
-                    # out-of-layer cancellation, one of:
-                    # - actorc: by `Portal.cancel_actor()`
-                    # - OSc: by SIGINT or `Process.signal()`
-                    or (
-                        isinstance(merr, trio.Cancelled)
-                        and
-                        ctx.canceller
-                    )
-                ):
-                    logmeth: Callable = log.cancel
-                    descr_str += (
-                        f' with {merr!r}\n'
-                    )
-
-                elif (
-                    not isinstance(merr, RemoteActorError)
-                ):
-                    tb_str: str = ''.join(
-                        traceback.format_exception(merr)
-                    )
+                if not isinstance(merr, RemoteActorError):
+                    tb_str: str = ''.join(traceback.format_exception(merr))
                     descr_str += (
                         f'\n{merr!r}\n'  # needed?
                         f'{tb_str}\n'
                     )
                 else:
-                    descr_str += (
-                        f'{merr!r}\n'
-                    )
+                    descr_str += f'\n{merr!r}\n'
             else:
-                descr_str += (
-                    f'\n'
-                    f'with final result {ctx.outcome!r}\n'
-                )
+                descr_str += f'\nand final result {ctx.outcome!r}\n'
 
             logmeth(
-                f'{message}\n'
-                f'\n'
-                f'{descr_str}\n'
+                message
+                +
+                descr_str
             )
 
 
@@ -908,8 +831,8 @@ async def try_ship_error_to_remote(
             log.critical(
                 'IPC transport failure -> '
                 f'failed to ship error to {remote_descr}!\n\n'
-                f'{type(msg)!r}[{msg.boxed_type_str}] X=> {channel.uid}\n'
-                f'\n'
+                f'X=> {channel.uid}\n\n'
+
                 # TODO: use `.msg.preetty_struct` for this!
                 f'{msg}\n'
             )
@@ -922,6 +845,7 @@ async def try_ship_error_to_remote(
 
 
 async def process_messages(
+    actor: Actor,
     chan: Channel,
     shield: bool = False,
     task_status: TaskStatus[CancelScope] = trio.TASK_STATUS_IGNORED,
@@ -935,7 +859,7 @@ async def process_messages(
 
     Receive (multiplexed) per-`Channel` RPC requests as msgs from
     remote processes; schedule target async funcs as local
-    `trio.Task`s inside the `Actor._service_tn: Nursery`.
+    `trio.Task`s inside the `Actor._service_n: Nursery`.
 
     Depending on msg type, non-`cmd` (task spawning/starting)
     request payloads (eg. `started`, `yield`, `return`, `error`)
@@ -959,8 +883,7 @@ async def process_messages(
       (as utilized inside `Portal.cancel_actor()` ).
 
     '''
-    actor: Actor = _state.current_actor()
-    assert actor._service_tn  # runtime state sanity
+    assert actor._service_n  # runtime state sanity
 
     # TODO: once `trio` get's an "obvious way" for req/resp we
     # should use it?
@@ -988,10 +911,7 @@ async def process_messages(
                     f'IPC msg from peer\n'
                     f'<= {chan.uid}\n\n'
 
-                    # TODO: use of the pprinting of structs is
-                    # FRAGILE and should prolly not be
-                    #
-                    # avoid fmting depending on loglevel for perf?
+                    # TODO: avoid fmting depending on loglevel for perf?
                     # -[ ] specifically `pretty_struct.pformat()` sub-call..?
                     #   - how to only log-level-aware actually call this?
                     # -[ ] use `.msg.pretty_struct` here now instead!
@@ -1031,10 +951,12 @@ async def process_messages(
                         cid=cid,
                         kwargs=kwargs,
                     ):
+                        kwargs |= {'req_chan': chan}
+
                         # XXX NOTE XXX don't start entire actor
                         # runtime cancellation if this actor is
                         # currently in debug mode!
-                        pdb_complete: trio.Event|None = debug.DebugStatus.repl_release
+                        pdb_complete: trio.Event|None = _debug.DebugStatus.repl_release
                         if pdb_complete:
                             await pdb_complete.wait()
 
@@ -1049,14 +971,14 @@ async def process_messages(
                                 cid,
                                 chan,
                                 actor.cancel,
-                                kwargs | {'req_chan': chan},
+                                kwargs,
                                 is_rpc=False,
                                 return_msg_type=CancelAck,
                             )
 
                         log.runtime(
-                            'Cancelling RPC-msg-loop with peer\n'
-                            f'->c}} {chan.aid.reprol()}@[{chan.maddr}]\n'
+                            'Cancelling IPC transport msg-loop with peer:\n'
+                            f'|_{chan}\n'
                         )
                         loop_cs.cancel()
                         break
@@ -1069,7 +991,7 @@ async def process_messages(
                     ):
                         target_cid: str = kwargs['cid']
                         kwargs |= {
-                            'requesting_aid': chan.aid,
+                            'requesting_uid': chan.uid,
                             'ipc_msg': msg,
 
                             # XXX NOTE! ONLY the rpc-task-owning
@@ -1105,34 +1027,21 @@ async def process_messages(
                         ns=ns,
                         func=funcname,
                         kwargs=kwargs,  # type-spec this? see `msg.types`
-                        uid=actor_uuid,
+                        uid=actorid,
                     ):
-                        if actor_uuid != chan.aid.uid:
-                            raise RuntimeError(
-                                f'IPC <Start> msg <-> chan.aid mismatch!?\n'
-                                f'Channel.aid = {chan.aid!r}\n'
-                                f'Start.uid = {actor_uuid!r}\n'
-                            )
-                        # await debug.pause()
-                        op_repr: str = 'Start <=) '
-                        req_repr: str = _pformat.nest_from_op(
-                            input_op=op_repr,
-                            op_suffix='',
-                            nest_prefix='',
-                            text=f'{chan}',
-
-                            nest_indent=len(op_repr)-1,
-                            rm_from_first_ln='<',
-                            # ^XXX, subtract -1 to account for
-                            # <Channel
-                            # ^_chevron to be stripped
-                        )
                         start_status: str = (
-                            'Handling RPC request\n'
-                            f'{req_repr}\n'
-                            f'\n'
-                            f'->{{ ipc-context-id: {cid!r}\n'
-                            f'->{{ nsp for fn: `{ns}.{funcname}({kwargs})`\n'
+                            'Handling RPC `Start` request\n'
+                            f'<= peer: {actorid}\n\n'
+                            f'  |_{chan}\n'
+                            f'  |_cid: {cid}\n\n'
+                            # f'  |_{ns}.{funcname}({kwargs})\n'
+                            f'>> {actor.uid}\n'
+                            f'  |_{actor}\n'
+                            f'   -> nsp: `{ns}.{funcname}({kwargs})`\n'
+
+                            # f'  |_{ns}.{funcname}({kwargs})\n\n'
+
+                            # f'{pretty_struct.pformat(msg)}\n'
                         )
 
                         # runtime-internal endpoint: `Actor.<funcname>`
@@ -1161,6 +1070,10 @@ async def process_messages(
                                 await chan.send(err_msg)
                                 continue
 
+                        start_status += (
+                            f'   -> func: {func}\n'
+                        )
+
                         # schedule a task for the requested RPC function
                         # in the actor's main "service nursery".
                         #
@@ -1168,10 +1081,10 @@ async def process_messages(
                         # supervision isolation? would avoid having to
                         # manage RPC tasks individually in `._rpc_tasks`
                         # table?
-                        start_status += '->( scheduling new task..\n'
+                        start_status += '   -> scheduling new task..\n'
                         log.runtime(start_status)
                         try:
-                            ctx: Context = await actor._service_tn.start(
+                            ctx: Context = await actor._service_n.start(
                                 partial(
                                     _invoke,
                                     actor,
@@ -1216,7 +1129,7 @@ async def process_messages(
                                 trio.Event(),
                             )
 
-                    # XXX RUNTIME-SCOPED! remote (likely internal) error
+                    # runtime-scoped remote (internal) error
                     # (^- bc no `Error.cid` -^)
                     #
                     # NOTE: this is the non-rpc error case, that
@@ -1252,31 +1165,19 @@ async def process_messages(
             # END-OF `async for`:
             # IPC disconnected via `trio.EndOfChannel`, likely
             # due to a (graceful) `Channel.aclose()`.
-
-            chan_op_repr: str = '<=x] '
-            chan_repr: str = _pformat.nest_from_op(
-                input_op=chan_op_repr,
-                op_suffix='',
-                nest_prefix='',
-                text=chan.pformat(),
-                nest_indent=len(chan_op_repr)-1,
-                rm_from_first_ln='<',
-            )
             log.runtime(
-                f'IPC channel disconnected\n'
-                f'{chan_repr}\n'
-                f'\n'
-                f'->c) cancelling RPC tasks.\n'
+                f'channel for {chan.uid} disconnected, cancelling RPC tasks\n'
+                f'|_{chan}\n'
             )
             await actor.cancel_rpc_tasks(
-                req_aid=actor.aid,
+                req_uid=actor.uid,
                 # a "self cancel" in terms of the lifetime of the
                 # IPC connection which is presumed to be the
                 # source of any requests for spawned tasks.
                 parent_chan=chan,
             )
 
-    except TransportClosed as tc:
+    except TransportClosed:
         # channels "breaking" (for TCP streams by EOF or 104
         # connection-reset) is ok since we don't have a teardown
         # handshake for them (yet) and instead we simply bail out of
@@ -1284,22 +1185,12 @@ async def process_messages(
         # up..
         #
         # TODO: maybe add a teardown handshake? and,
-        # -[x] don't show this msg if it's an ephemeral discovery ep call?
-        #  |_ see the below `.report_n_maybe_raise()` impl as well as
-        #     tc-exc input details in `MsgpackTCPStream._iter_pkts()`
-        #     for different read-failure cases.
+        # -[ ] don't show this msg if it's an ephemeral discovery ep call?
         # -[ ] figure out how this will break with other transports?
-        tc.report_n_maybe_raise(
-            message=(
-                f'peer IPC channel closed abruptly?\n'
-                f'\n'
-                f'<=x[\n'
-                f'  {chan}\n'
-                f'  |_{chan.raddr}\n\n'
-            )
-            +
-            tc.message
-
+        log.runtime(
+            f'IPC channel closed abruptly\n'
+            f'<=x peer: {chan.uid}\n'
+            f'   |_{chan.raddr}\n'
         )
 
         # transport **WAS** disconnected
@@ -1311,7 +1202,7 @@ async def process_messages(
     ) as err:
 
         if nursery_cancelled_before_task:
-            sn: Nursery = actor._service_tn
+            sn: Nursery = actor._service_n
             assert sn and sn.cancel_scope.cancel_called  # sanity
             log.cancel(
                 f'Service nursery cancelled before it handled {funcname}'
@@ -1341,37 +1232,13 @@ async def process_messages(
     finally:
         # msg debugging for when he machinery is brokey
         if msg is None:
-            message: str = 'Exiting RPC-loop without receiving a msg?'
+            message: str = 'Exiting IPC msg loop without receiving a msg?'
         else:
-            task_op_repr: str = ')>'
-            task: trio.Task = trio.lowlevel.current_task()
-
-            # maybe add cancelled opt prefix
-            if task._cancel_status.effectively_cancelled:
-                task_op_repr = 'c' + task_op_repr
-
-            task_repr: str = _pformat.nest_from_op(
-                input_op=task_op_repr,
-                text=f'{task!r}',
-                nest_indent=1,
-            )
-            # chan_op_repr: str = '<=} '
-            # chan_repr: str = _pformat.nest_from_op(
-            #     input_op=chan_op_repr,
-            #     op_suffix='',
-            #     nest_prefix='',
-            #     text=chan.pformat(),
-            #     nest_indent=len(chan_op_repr)-1,
-            #     rm_from_first_ln='<',
-            # )
             message: str = (
-                f'Exiting RPC-loop with final msg\n'
-                f'\n'
-                # f'{chan_repr}\n'
-                f'{task_repr}\n'
-                f'\n'
+                'Exiting IPC msg loop with final msg\n\n'
+                f'<= peer: {chan.uid}\n'
+                f'  |_{chan}\n\n'
                 f'{pretty_struct.pformat(msg)}'
-                f'\n'
             )
 
         log.runtime(message)

tractor/_shm.py

@@ -23,24 +23,19 @@ considered optional within the context of this runtime-library.
 
 """
 from __future__ import annotations
-from multiprocessing import shared_memory as shm
-from multiprocessing.shared_memory import (
-    # SharedMemory,
-    ShareableList,
-)
-import platform
 from sys import byteorder
 import time
 from typing import Optional
-
-from msgspec import (
-    Struct,
-    to_builtins
+from multiprocessing import shared_memory as shm
+from multiprocessing.shared_memory import (
+    SharedMemory,
+    ShareableList,
 )
+
+from msgspec import Struct
 import tractor
 
-from tractor.ipc._mp_bs import disable_mantracker
-from tractor.log import get_logger
+from .log import get_logger
 
 
 _USE_POSIX = getattr(shm, '_USE_POSIX', False)
@@ -51,10 +46,7 @@ if _USE_POSIX:
 try:
     import numpy as np
     from numpy.lib import recfunctions as rfn
-    # TODO ruff complains with,
-    # warning| F401: `nptyping` imported but unused; consider using
-    # `importlib.util.find_spec` to test for availability
-    import nptyping  # noqa
+    # import nptyping
 except ImportError:
     pass
 
@@ -62,7 +54,35 @@ except ImportError:
 log = get_logger(__name__)
 
 
-SharedMemory = disable_mantracker()
+def disable_mantracker():
+    '''
+    Disable all ``multiprocessing``` "resource tracking" machinery since
+    it's an absolute multi-threaded mess of non-SC madness.
+
+    '''
+    from multiprocessing import resource_tracker as mantracker
+
+    # Tell the "resource tracker" thing to fuck off.
+    class ManTracker(mantracker.ResourceTracker):
+        def register(self, name, rtype):
+            pass
+
+        def unregister(self, name, rtype):
+            pass
+
+        def ensure_running(self):
+            pass
+
+    # "know your land and know your prey"
+    # https://www.dailymotion.com/video/x6ozzco
+    mantracker._resource_tracker = ManTracker()
+    mantracker.register = mantracker._resource_tracker.register
+    mantracker.ensure_running = mantracker._resource_tracker.ensure_running
+    mantracker.unregister = mantracker._resource_tracker.unregister
+    mantracker.getfd = mantracker._resource_tracker.getfd
+
+
+disable_mantracker()
 
 
 class SharedInt:
@@ -122,7 +142,7 @@ class NDToken(Struct, frozen=True):
         ).descr
 
     def as_msg(self):
-        return to_builtins(self)
+        return self.to_dict()
 
     @classmethod
     def from_msg(cls, msg: dict) -> NDToken:
@@ -790,23 +810,11 @@ def open_shm_list(
         readonly=readonly,
     )
 
-    # TODO, factor into a @actor_fixture acm-API?
-    # -[ ] also `@maybe_actor_fixture()` which inludes
-    #     the .current_actor() convenience check?
-    #   |_ orr can that just be in the sin-maybe-version?
-    #
     # "close" attached shm on actor teardown
     try:
         actor = tractor.current_actor()
-
         actor.lifetime_stack.callback(shml.shm.close)
-
-        # XXX on 3.13+ we don't need to call this?
-        # -> bc we pass `track=False` for `SharedMemeory` orr?
-        if (
-            platform.python_version_tuple()[:-1] < ('3', '13')
-        ):
-            actor.lifetime_stack.callback(shml.shm.unlink)
+        actor.lifetime_stack.callback(shml.shm.unlink)
     except RuntimeError:
         log.warning('tractor runtime not active, skipping teardown steps')
 

tractor/_spawn.py

@@ -34,9 +34,9 @@ from typing import (
 import trio
 from trio import TaskStatus
 
-from .devx import (
-    debug,
-    pformat as _pformat
+from tractor.devx import (
+    maybe_wait_for_debugger,
+    acquire_debug_lock,
 )
 from tractor._state import (
     current_actor,
@@ -46,26 +46,19 @@ from tractor._state import (
     _runtime_vars,
 )
 from tractor.log import get_logger
-from tractor._addr import UnwrappedAddress
 from tractor._portal import Portal
 from tractor._runtime import Actor
 from tractor._entry import _mp_main
 from tractor._exceptions import ActorFailure
-from tractor.msg import (
-    types as msgtypes,
-    pretty_struct,
+from tractor.msg.types import (
+    SpawnSpec,
 )
 
 
 if TYPE_CHECKING:
-    from ipc import (
-        _server,
-        Channel,
-    )
     from ._supervise import ActorNursery
     ProcessType = TypeVar('ProcessType', mp.Process, trio.Process)
 
-
 log = get_logger('tractor')
 
 # placeholder for an mp start context if so using that backend
@@ -156,7 +149,7 @@ async def exhaust_portal(
 
         # XXX: streams should never be reaped here since they should
         # always be established and shutdown using a context manager api
-        final: Any = await portal.wait_for_result()
+        final: Any = await portal.result()
 
     except (
         Exception,
@@ -170,7 +163,7 @@ async def exhaust_portal(
         # TODO: merge with above?
         log.warning(
             'Cancelled portal result waiter task:\n'
-            f'uid: {portal.channel.aid}\n'
+            f'uid: {portal.channel.uid}\n'
             f'error: {err}\n'
         )
         return err
@@ -178,7 +171,7 @@ async def exhaust_portal(
     else:
         log.debug(
             f'Returning final result from portal:\n'
-            f'uid: {portal.channel.aid}\n'
+            f'uid: {portal.channel.uid}\n'
             f'result: {final}\n'
         )
         return final
@@ -230,8 +223,8 @@ async def cancel_on_completion(
 
 async def hard_kill(
     proc: trio.Process,
-
     terminate_after: int = 1.6,
+
     # NOTE: for mucking with `.pause()`-ing inside the runtime
     # whilst also hacking on it XD
     # terminate_after: int = 99999,
@@ -253,9 +246,8 @@ async def hard_kill(
 
     '''
     log.cancel(
-        'Terminating sub-proc\n'
-        f'>x)\n'
-        f' |_{proc}\n'
+        'Terminating sub-proc:\n'
+        f'|_{proc}\n'
     )
     # NOTE: this timeout used to do nothing since we were shielding
     # the ``.wait()`` inside ``new_proc()`` which will pretty much
@@ -297,29 +289,12 @@ async def hard_kill(
     # zombies (as a feature) we ask the OS to do send in the
     # removal swad as the last resort.
     if cs.cancelled_caught:
-
-        # TODO? attempt at intermediary-rent-sub
-        # with child in debug lock?
-        # |_https://github.com/goodboy/tractor/issues/320
-        #
-        # if not is_root_process():
-        #     log.warning(
-        #         'Attempting to acquire debug-REPL-lock before zombie reap!'
-        #     )
-        #     with trio.CancelScope(shield=True):
-        #         async with debug.acquire_debug_lock(
-        #             subactor_uid=current_actor().uid,
-        #         ) as _ctx:
-        #             log.warning(
-        #                 'Acquired debug lock, child ready to be killed ??\n'
-        #             )
-
         # TODO: toss in the skynet-logo face as ascii art?
         log.critical(
             # 'Well, the #ZOMBIE_LORD_IS_HERE# to collect\n'
             '#T-800 deployed to collect zombie B0\n'
-            f'>x)\n'
-            f' |_{proc}\n'
+            f'|\n'
+            f'|_{proc}\n'
         )
         proc.kill()
 
@@ -344,21 +319,18 @@ async def soft_kill(
     see `.hard_kill()`).
 
     '''
-    chan: Channel = portal.channel
-    peer_aid: msgtypes.Aid = chan.aid
+    uid: tuple[str, str] = portal.channel.uid
     try:
         log.cancel(
-            f'Soft killing sub-actor via portal request\n'
-            f'\n'
-            f'c)=> {peer_aid.reprol()}@[{chan.maddr}]\n'
-            f'   |_{proc}\n'
+            'Soft killing sub-actor via `Portal.cancel_actor()`\n'
+            f'|_{proc}\n'
         )
         # wait on sub-proc to signal termination
         await wait_func(proc)
 
     except trio.Cancelled:
         with trio.CancelScope(shield=True):
-            await debug.maybe_wait_for_debugger(
+            await maybe_wait_for_debugger(
                 child_in_debug=_runtime_vars.get(
                     '_debug_mode', False
                 ),
@@ -399,7 +371,7 @@ async def soft_kill(
             if proc.poll() is None:  # type: ignore
                 log.warning(
                     'Subactor still alive after cancel request?\n\n'
-                    f'uid: {peer_aid}\n'
+                    f'uid: {uid}\n'
                     f'|_{proc}\n'
                 )
                 n.cancel_scope.cancel()
@@ -413,15 +385,14 @@ async def new_proc(
     errors: dict[tuple[str, str], Exception],
 
     # passed through to actor main
-    bind_addrs: list[UnwrappedAddress],
-    parent_addr: UnwrappedAddress,
+    bind_addrs: list[tuple[str, int]],
+    parent_addr: tuple[str, int],
     _runtime_vars: dict[str, Any],  # serialized and sent to _child
 
     *,
 
     infect_asyncio: bool = False,
-    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED,
-    proc_kwargs: dict[str, any] = {}
+    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
 
 ) -> None:
 
@@ -441,7 +412,6 @@ async def new_proc(
         _runtime_vars,  # run time vars
         infect_asyncio=infect_asyncio,
         task_status=task_status,
-        proc_kwargs=proc_kwargs
     )
 
 
@@ -452,13 +422,12 @@ async def trio_proc(
     errors: dict[tuple[str, str], Exception],
 
     # passed through to actor main
-    bind_addrs: list[UnwrappedAddress],
-    parent_addr: UnwrappedAddress,
+    bind_addrs: list[tuple[str, int]],
+    parent_addr: tuple[str, int],
     _runtime_vars: dict[str, Any],  # serialized and sent to _child
     *,
     infect_asyncio: bool = False,
-    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED,
-    proc_kwargs: dict[str, any] = {}
+    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
 
 ) -> None:
     '''
@@ -480,9 +449,6 @@ async def trio_proc(
         # the OS; it otherwise can be passed via the parent channel if
         # we prefer in the future (for privacy).
         "--uid",
-        # TODO, how to pass this over "wire" encodings like
-        # cmdline args?
-        # -[ ] maybe we can add an `msgtypes.Aid.min_tuple()` ?
         str(subactor.uid),
         # Address the child must connect to on startup
         "--parent_addr",
@@ -500,20 +466,18 @@ async def trio_proc(
 
     cancelled_during_spawn: bool = False
     proc: trio.Process|None = None
-    ipc_server: _server.Server = actor_nursery._actor.ipc_server
     try:
         try:
-            proc: trio.Process = await trio.lowlevel.open_process(spawn_cmd, **proc_kwargs)
+            proc: trio.Process = await trio.lowlevel.open_process(spawn_cmd)
             log.runtime(
-                f'Started new child subproc\n'
-                f'(>\n'
-                f' |_{proc}\n'
+                'Started new child\n'
+                f'|_{proc}\n'
             )
 
             # wait for actor to spawn and connect back to us
             # channel should have handshake completed by the
             # local actor by the time we get a ref to it
-            event, chan = await ipc_server.wait_for_peer(
+            event, chan = await actor_nursery._actor.wait_for_peer(
                 subactor.uid
             )
 
@@ -525,10 +489,10 @@ async def trio_proc(
                 with trio.CancelScope(shield=True):
                     # don't clobber an ongoing pdb
                     if is_root_process():
-                        await debug.maybe_wait_for_debugger()
+                        await maybe_wait_for_debugger()
 
                     elif proc is not None:
-                        async with debug.acquire_debug_lock(subactor.uid):
+                        async with acquire_debug_lock(subactor.uid):
                             # soft wait on the proc to terminate
                             with trio.move_on_after(0.5):
                                 await proc.wait()
@@ -546,20 +510,15 @@ async def trio_proc(
 
         # send a "spawning specification" which configures the
         # initial runtime state of the child.
-        sspec = msgtypes.SpawnSpec(
-            _parent_main_data=subactor._parent_main_data,
-            enable_modules=subactor.enable_modules,
-            reg_addrs=subactor.reg_addrs,
-            bind_addrs=bind_addrs,
-            _runtime_vars=_runtime_vars,
+        await chan.send(
+            SpawnSpec(
+                _parent_main_data=subactor._parent_main_data,
+                enable_modules=subactor.enable_modules,
+                reg_addrs=subactor.reg_addrs,
+                bind_addrs=bind_addrs,
+                _runtime_vars=_runtime_vars,
+            )
         )
-        log.runtime(
-            f'Sending spawn spec to child\n'
-            f'{{}}=> {chan.aid.reprol()!r}\n'
-            f'\n'
-            f'{pretty_struct.pformat(sspec)}\n'
-        )
-        await chan.send(sspec)
 
         # track subactor in current nursery
         curr_actor: Actor = current_actor()
@@ -586,15 +545,15 @@ async def trio_proc(
             # condition.
             await soft_kill(
                 proc,
-                trio.Process.wait,  # XXX, uses `pidfd_open()` below.
+                trio.Process.wait,
                 portal
             )
 
             # cancel result waiter that may have been spawned in
             # tandem if not done already
             log.cancel(
-                'Cancelling portal result reaper task\n'
-                f'c)> {subactor.aid.reprol()!r}\n'
+                'Cancelling existing result waiter task for '
+                f'{subactor.uid}'
             )
             nursery.cancel_scope.cancel()
 
@@ -603,24 +562,17 @@ async def trio_proc(
         # allowed! Do this **after** cancellation/teardown to avoid
         # killing the process too early.
         if proc:
-            reap_repr: str = _pformat.nest_from_op(
-                input_op='>x)',
-                text=subactor.pformat(),
-            )
-            log.cancel(
-                f'Hard reap sequence starting for subactor\n'
-                f'{reap_repr}'
-            )
+            log.cancel(f'Hard reap sequence starting for {subactor.uid}')
 
             with trio.CancelScope(shield=True):
                 # don't clobber an ongoing pdb
                 if cancelled_during_spawn:
                     # Try again to avoid TTY clobbering.
-                    async with debug.acquire_debug_lock(subactor.uid):
+                    async with acquire_debug_lock(subactor.uid):
                         with trio.move_on_after(0.5):
                             await proc.wait()
 
-                await debug.maybe_wait_for_debugger(
+                await maybe_wait_for_debugger(
                     child_in_debug=_runtime_vars.get(
                         '_debug_mode', False
                     ),
@@ -649,7 +601,7 @@ async def trio_proc(
                 #     acquire the lock and get notified of who has it,
                 #     check that uid against our known children?
                 # this_uid: tuple[str, str] = current_actor().uid
-                # await debug.acquire_debug_lock(this_uid)
+                # await acquire_debug_lock(this_uid)
 
                 if proc.poll() is None:
                     log.cancel(f"Attempting to hard kill {proc}")
@@ -671,13 +623,12 @@ async def mp_proc(
     subactor: Actor,
     errors: dict[tuple[str, str], Exception],
     # passed through to actor main
-    bind_addrs: list[UnwrappedAddress],
-    parent_addr: UnwrappedAddress,
+    bind_addrs: list[tuple[str, int]],
+    parent_addr: tuple[str, int],
     _runtime_vars: dict[str, Any],  # serialized and sent to _child
     *,
     infect_asyncio: bool = False,
-    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED,
-    proc_kwargs: dict[str, any] = {}
+    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
 
 ) -> None:
 
@@ -752,14 +703,12 @@ async def mp_proc(
 
     log.runtime(f"Started {proc}")
 
-    ipc_server: _server.Server = actor_nursery._actor.ipc_server
     try:
         # wait for actor to spawn and connect back to us
         # channel should have handshake completed by the
         # local actor by the time we get a ref to it
-        event, chan = await ipc_server.wait_for_peer(
-            subactor.uid,
-        )
+        event, chan = await actor_nursery._actor.wait_for_peer(
+            subactor.uid)
 
         # XXX: monkey patch poll API to match the ``subprocess`` API..
         # not sure why they don't expose this but kk.

tractor/_state.py

@@ -14,19 +14,16 @@
 # 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/>.
 
-'''
-Per actor-process runtime state mgmt APIs.
+"""
+Per process state
 
-'''
+"""
 from __future__ import annotations
 from contextvars import (
     ContextVar,
 )
-import os
-from pathlib import Path
 from typing import (
     Any,
-    Literal,
     TYPE_CHECKING,
 )
 
@@ -37,39 +34,18 @@ if TYPE_CHECKING:
     from ._context import Context
 
 
-# default IPC transport protocol settings
-TransportProtocolKey = Literal[
-    'tcp',
-    'uds',
-]
-_def_tpt_proto: TransportProtocolKey = 'tcp'
-
 _current_actor: Actor|None = None  # type: ignore # noqa
 _last_actor_terminated: Actor|None = None
 
 # TODO: mk this a `msgspec.Struct`!
-# -[ ] type out all fields obvi!
-# -[ ] (eventually) mk wire-ready for monitoring?
 _runtime_vars: dict[str, Any] = {
-    # root of actor-process tree info
-    '_is_root': False,  # bool
-    '_root_mailbox': (None, None),  # tuple[str|None, str|None]
-    '_root_addrs': [],  # tuple[str|None, str|None]
-
-    # parent->chld ipc protocol caps
-    '_enable_tpts': [_def_tpt_proto],
-
-    # registrar info
+    '_debug_mode': False,
+    '_is_root': False,
+    '_root_mailbox': (None, None),
     '_registry_addrs': [],
 
-    # `debug_mode: bool` settings
-    '_debug_mode': False,  # bool
-    'repl_fixture': False,  # |AbstractContextManager[bool]
-    # for `tractor.pause_from_sync()` & `breakpoint()` support
+    # for `breakpoint()` support
     'use_greenback': False,
-
-    # infected-`asyncio`-mode: `trio` running as guest.
-    '_is_infected_aio': False,
 }
 
 
@@ -94,8 +70,7 @@ def current_actor(
     '''
     if (
         err_on_no_runtime
-        and
-        _current_actor is None
+        and _current_actor is None
     ):
         msg: str = 'No local actor has been initialized yet?\n'
         from ._exceptions import NoRuntime
@@ -121,7 +96,7 @@ def current_actor(
     return _current_actor
 
 
-def is_root_process() -> bool:
+def is_main_process() -> bool:
     '''
     Bool determining if this actor is running in the top-most process.
 
@@ -130,10 +105,7 @@ def is_root_process() -> bool:
     return mp.current_process().name == 'MainProcess'
 
 
-is_main_process = is_root_process
-
-
-def is_debug_mode() -> bool:
+def debug_mode() -> bool:
     '''
     Bool determining if "debug mode" is on which enables
     remote subactor pdb entry on crashes.
@@ -142,9 +114,6 @@ def is_debug_mode() -> bool:
     return bool(_runtime_vars['_debug_mode'])
 
 
-debug_mode = is_debug_mode
-
-
 def is_root_process() -> bool:
     return _runtime_vars['_is_root']
 
@@ -170,34 +139,3 @@ def current_ipc_ctx(
             f'|_{current_task()}\n'
         )
     return ctx
-
-
-# std ODE (mutable) app state location
-_rtdir: Path = Path(os.environ['XDG_RUNTIME_DIR'])
-
-
-def get_rt_dir(
-    subdir: str = 'tractor'
-) -> Path:
-    '''
-    Return the user "runtime dir" where most userspace apps stick
-    their IPC and cache related system util-files; we take hold
-    of a `'XDG_RUNTIME_DIR'/tractor/` subdir by default.
-
-    '''
-    rtdir: Path = _rtdir / subdir
-    if not rtdir.is_dir():
-        rtdir.mkdir()
-    return rtdir
-
-
-def current_ipc_protos() -> list[str]:
-    '''
-    Return the list of IPC transport protocol keys currently
-    in use by this actor.
-
-    The keys are as declared by `MsgTransport` and `Address`
-    concrete-backend sub-types defined throughout `tractor.ipc`.
-
-    '''
-    return _runtime_vars['_enable_tpts']

tractor/_streaming.py

@@ -36,8 +36,8 @@ import warnings
 import trio
 
 from ._exceptions import (
+    # _raise_from_no_key_in_msg,
     ContextCancelled,
-    RemoteActorError,
 )
 from .log import get_logger
 from .trionics import (
@@ -45,18 +45,16 @@ from .trionics import (
     BroadcastReceiver,
 )
 from tractor.msg import (
-    Error,
-    Return,
-    Stop,
+    # Return,
+    # Stop,
     MsgType,
-    PayloadT,
     Yield,
 )
 
 if TYPE_CHECKING:
     from ._runtime import Actor
     from ._context import Context
-    from .ipc import Channel
+    from ._ipc import Channel
 
 
 log = get_logger(__name__)
@@ -72,7 +70,8 @@ class MsgStream(trio.abc.Channel):
     A bidirectional message stream for receiving logically sequenced
     values over an inter-actor IPC `Channel`.
 
-
+    This is the type returned to a local task which entered either
+    `Portal.open_stream_from()` or `Context.open_stream()`.
 
     Termination rules:
 
@@ -95,9 +94,6 @@ class MsgStream(trio.abc.Channel):
         self._rx_chan = rx_chan
         self._broadcaster = _broadcaster
 
-        # any actual IPC msg which is effectively an `EndOfStream`
-        self._stop_msg: bool|Stop = False
-
         # flag to denote end of stream
         self._eoc: bool|trio.EndOfChannel = False
         self._closed: bool|trio.ClosedResourceError = False
@@ -105,7 +101,7 @@ class MsgStream(trio.abc.Channel):
     @property
     def ctx(self) -> Context:
         '''
-        A read-only ref to this stream's inter-actor-task `Context`.
+        This stream's IPC `Context` ref.
 
         '''
         return self._ctx
@@ -129,67 +125,16 @@ class MsgStream(trio.abc.Channel):
     def receive_nowait(
         self,
         expect_msg: MsgType = Yield,
-    ) -> PayloadT:
+    ):
         ctx: Context = self._ctx
-        (
-            msg,
-            pld,
-        ) = ctx._pld_rx.recv_msg_nowait(
+        return ctx._pld_rx.recv_pld_nowait(
             ipc=self,
             expect_msg=expect_msg,
         )
 
-        # ?TODO, maybe factor this into a hyper-common `unwrap_pld()`
-        #
-        match msg:
-
-            # XXX, these never seems to ever hit? cool?
-            case Stop():
-                log.cancel(
-                    f'Msg-stream was ended via stop msg\n'
-                    f'{msg}'
-                )
-            case Error():
-                log.error(
-                    f'Msg-stream was ended via error msg\n'
-                    f'{msg}'
-                )
-
-            # XXX NOTE, always set any final result on the ctx to
-            # avoid teardown race conditions where previously this msg
-            # would be consumed silently (by `.aclose()` doing its
-            # own "msg drain loop" but WITHOUT those `drained: lists[MsgType]`
-            # being post-close-processed!
-            #
-            # !!TODO, see the equiv todo-comment in `.receive()`
-            # around the `if drained:` where we should prolly
-            # ACTUALLY be doing this post-close processing??
-            #
-            case Return(pld=pld):
-                log.warning(
-                    f'Msg-stream final result msg for IPC ctx?\n'
-                    f'{msg}'
-                )
-                # XXX TODO, this **should be covered** by higher
-                # scoped runtime-side method calls such as
-                # `Context._deliver_msg()`, so you should never
-                # really see the warning above or else something
-                # racy/out-of-order is likely going on between
-                # actor-runtime-side push tasks and the user-app-side
-                # consume tasks!
-                # -[ ] figure out that set of race cases and fix!
-                # -[ ] possibly return the `msg` given an input
-                #     arg-flag is set so we can process the `Return`
-                #     from the `.aclose()` caller?
-                #
-                # breakpoint()  # to debug this RACE CASE!
-                ctx._result = pld
-                ctx._outcome_msg = msg
-
-        return pld
-
     async def receive(
         self,
+
         hide_tb: bool = False,
     ):
         '''
@@ -200,8 +145,9 @@ class MsgStream(trio.abc.Channel):
         '''
         __tracebackhide__: bool = hide_tb
 
-        # NOTE FYI: `trio.ReceiveChannel` implements EOC handling as
-        # follows (aka uses it to gracefully exit async for loops):
+        # NOTE: `trio.ReceiveChannel` implements
+        # EOC handling as follows (aka uses it
+        # to gracefully exit async for loops):
         #
         # async def __anext__(self) -> ReceiveType:
         #     try:
@@ -209,7 +155,7 @@ class MsgStream(trio.abc.Channel):
         #     except trio.EndOfChannel:
         #         raise StopAsyncIteration
         #
-        # see `.aclose()` for notes on the old behaviour prior to
+        # see ``.aclose()`` for notes on the old behaviour prior to
         # introducing this
         if self._eoc:
             raise self._eoc
@@ -219,33 +165,48 @@ class MsgStream(trio.abc.Channel):
 
         src_err: Exception|None = None  # orig tb
         try:
+
             ctx: Context = self._ctx
-            pld = await ctx._pld_rx.recv_pld(
-                ipc=self,
-                expect_msg=Yield,
-            )
-            return pld
+            return await ctx._pld_rx.recv_pld(ipc=self)
 
         # XXX: the stream terminates on either of:
-        # - `self._rx_chan.receive()` raising  after manual closure
-        #   by the rpc-runtime,
-        #   OR
-        # - via a `Stop`-msg received from remote peer task.
-        #   NOTE
-        #   |_ previously this was triggered by calling
-        #   `._rx_chan.aclose()` on the send side of the channel
-        #   inside `Actor._deliver_ctx_payload()`, but now the 'stop'
-        #   message handling gets delegated to `PldRFx.recv_pld()`
-        #   internals.
-        except trio.EndOfChannel as eoc:
-            # a graceful stream finished signal
-            self._eoc = eoc
+        # - via `self._rx_chan.receive()` raising  after manual closure
+        #   by the rpc-runtime OR,
+        # - via a received `{'stop': ...}` msg from remote side.
+        #   |_ NOTE: previously this was triggered by calling
+        #   ``._rx_chan.aclose()`` on the send side of the channel inside
+        #   `Actor._deliver_ctx_payload()`, but now the 'stop' message handling
+        #   has been put just above inside `_raise_from_no_key_in_msg()`.
+        except (
+            trio.EndOfChannel,
+        ) as eoc:
             src_err = eoc
+            self._eoc = eoc
 
-        # a `ClosedResourceError` indicates that the internal feeder
-        # memory receive channel was closed likely by the runtime
-        # after the associated transport-channel disconnected or
-        # broke.
+            # TODO: Locally, we want to close this stream gracefully, by
+            # terminating any local consumers tasks deterministically.
+            # Once we have broadcast support, we **don't** want to be
+            # closing this stream and not flushing a final value to
+            # remaining (clone) consumers who may not have been
+            # scheduled to receive it yet.
+            # try:
+            #     maybe_err_msg_or_res: dict = self._rx_chan.receive_nowait()
+            #     if maybe_err_msg_or_res:
+            #         log.warning(
+            #             'Discarding un-processed msg:\n'
+            #             f'{maybe_err_msg_or_res}'
+            #         )
+            # except trio.WouldBlock:
+            #     # no queued msgs that might be another remote
+            #     # error, so just raise the original EoC
+            #     pass
+
+            # raise eoc
+
+        # a ``ClosedResourceError`` indicates that the internal
+        # feeder memory receive channel was closed likely by the
+        # runtime after the associated transport-channel
+        # disconnected or broke.
         except trio.ClosedResourceError as cre:  # by self._rx_chan.receive()
             src_err = cre
             log.warning(
@@ -257,18 +218,14 @@ class MsgStream(trio.abc.Channel):
         # terminated and signal this local iterator to stop
         drained: list[Exception|dict] = await self.aclose()
         if drained:
-        #  ^^^^^^^^TODO? pass these to the `._ctx._drained_msgs:
-        #  deque` and then iterate them as part of any
-        #  `.wait_for_result()` call?
-        #
-        # -[ ] move the match-case processing from
-        #     `.receive_nowait()` instead to right here, use it from
-        #     a for msg in drained:` post-proc loop?
-        #
+            # from .devx import pause
+            # await pause()
             log.warning(
-                'Drained context msgs during closure\n\n'
+                'Drained context msgs during closure:\n'
                 f'{drained}'
             )
+        # TODO: pass these to the `._ctx._drained_msgs: deque`
+        # and then iterate them as part of any `.result()` call?
 
         # NOTE XXX: if the context was cancelled or remote-errored
         # but we received the stream close msg first, we
@@ -281,36 +238,28 @@ class MsgStream(trio.abc.Channel):
             from_src_exc=src_err,
         )
 
-        # propagate any error but hide low-level frame details from
-        # the caller by default for console/debug-REPL noise
-        # reduction.
+        # propagate any error but hide low-level frame details
+        # from the caller by default for debug noise reduction.
         if (
             hide_tb
-            and (
 
-                # XXX NOTE special conditions: don't reraise on
-                # certain stream-specific internal error types like,
-                #
-                # - `trio.EoC` since we want to use the exact instance
-                #   to ensure that it is the error that bubbles upward
-                #   for silent absorption by `Context.open_stream()`.
-                not self._eoc
+            # XXX NOTE XXX don't reraise on certain
+            # stream-specific internal error types like,
+            #
+            # - `trio.EoC` since we want to use the exact instance
+            #   to ensure that it is the error that bubbles upward
+            #   for silent absorption by `Context.open_stream()`.
+            and not self._eoc
 
-                # - `RemoteActorError` (or subtypes like ctxc)
-                #    since we want to present the error as though it is
-                #    "sourced" directly from this `.receive()` call and
-                #    generally NOT include the stack frames raised from
-                #    inside the `PldRx` and/or the transport stack
-                #    layers.
-                or isinstance(src_err, RemoteActorError)
-            )
+            # - `RemoteActorError` (or `ContextCancelled`) if it gets
+            #   raised from `_raise_from_no_key_in_msg()` since we
+            #   want the same (as the above bullet) for any
+            #   `.open_context()` block bubbled error raised by
+            #   any nearby ctx API remote-failures.
+            # and not isinstance(src_err, RemoteActorError)
         ):
             raise type(src_err)(*src_err.args) from src_err
         else:
-            # for any non-graceful-EOC we want to NOT hide this frame
-            if not self._eoc:
-                __tracebackhide__: bool = False
-
             raise src_err
 
     async def aclose(self) -> list[Exception|dict]:
@@ -327,6 +276,9 @@ class MsgStream(trio.abc.Channel):
          - more or less we try to maintain adherance to trio's `.aclose()` semantics:
            https://trio.readthedocs.io/en/stable/reference-io.html#trio.abc.AsyncResource.aclose
         '''
+
+        # rx_chan = self._rx_chan
+
         # XXX NOTE XXX
         # it's SUPER IMPORTANT that we ensure we don't DOUBLE
         # DRAIN msgs on closure so avoid getting stuck handing on
@@ -338,16 +290,15 @@ class MsgStream(trio.abc.Channel):
             # this stream has already been closed so silently succeed as
             # per ``trio.AsyncResource`` semantics.
             # https://trio.readthedocs.io/en/stable/reference-io.html#trio.abc.AsyncResource.aclose
-            # import tractor
-            # await tractor.pause()
             return []
 
         ctx: Context = self._ctx
         drained: list[Exception|dict] = []
         while not drained:
             try:
-                maybe_final_msg: Yield|Return = self.receive_nowait(
-                    expect_msg=Yield|Return,
+                maybe_final_msg = self.receive_nowait(
+                    # allow_msgs=[Yield, Return],
+                    expect_msg=Yield,
                 )
                 if maybe_final_msg:
                     log.debug(
@@ -426,37 +377,22 @@ class MsgStream(trio.abc.Channel):
             self._closed = re
 
         # if caught_eoc:
-        #     # from .devx import debug
-        #     # await debug.pause()
+        #     # from .devx import _debug
+        #     # await _debug.pause()
         #     with trio.CancelScope(shield=True):
         #         await rx_chan.aclose()
 
         if not self._eoc:
-            this_side: str = self._ctx.side
-            peer_side: str = self._ctx.peer_side
             message: str = (
-                f'Stream self-closed by {this_side!r}-side before EoC from {peer_side!r}\n'
-                # } bc a stream is a "scope"/msging-phase inside an IPC
-                f'c}}>\n'
-                f'  |_{self}\n'
+                f'Stream self-closed by {self._ctx.side!r}-side before EoC\n'
+                f'|_{self}\n'
             )
-            if (
-                (rx_chan := self._rx_chan)
-                and
-                (stats := rx_chan.statistics()).tasks_waiting_receive
-            ):
-                message += (
-                    f'AND there is still reader tasks,\n'
-                    f'\n'
-                    f'{stats}\n'
-                )
-
             log.cancel(message)
             self._eoc = trio.EndOfChannel(message)
 
         # ?XXX WAIT, why do we not close the local mem chan `._rx_chan` XXX?
         # => NO, DEFINITELY NOT! <=
-        # if we're a bi-dir `MsgStream` BECAUSE this same
+        # if we're a bi-dir ``MsgStream`` BECAUSE this same
         # core-msg-loop mem recv-chan is used to deliver the
         # potential final result from the surrounding inter-actor
         # `Context` so we don't want to close it until that
@@ -596,17 +532,8 @@ class MsgStream(trio.abc.Channel):
             trio.ClosedResourceError,
             trio.BrokenResourceError,
             BrokenPipeError,
-        ) as _trans_err:
-            trans_err = _trans_err
-            if (
-                hide_tb
-                and
-                self._ctx.chan._exc is trans_err
-                # ^XXX, IOW, only if the channel is marked errored
-                # for the same reason as whatever its underlying
-                # transport raised, do we keep the full low-level tb
-                # suppressed from the user.
-            ):
+        ) as trans_err:
+            if hide_tb:
                 raise type(trans_err)(
                     *trans_err.args
                 ) from trans_err
@@ -812,12 +739,13 @@ async def open_stream_from_ctx(
                 # sanity, can remove?
                 assert eoc is stream._eoc
 
-                log.runtime(
+                log.warning(
                     'Stream was terminated by EoC\n\n'
                     # NOTE: won't show the error <Type> but
                     # does show txt followed by IPC msg.
                     f'{str(eoc)}\n'
                 )
+
         finally:
             if ctx._portal:
                 try:

tractor/_supervise.py

@@ -21,49 +21,34 @@
 from contextlib import asynccontextmanager as acm
 from functools import partial
 import inspect
-from typing import (
-    TYPE_CHECKING,
-)
+from pprint import pformat
+from typing import TYPE_CHECKING
 import typing
 import warnings
 
 import trio
 
-
-from .devx import (
-    debug,
-    pformat as _pformat,
-)
-from ._addr import (
-    UnwrappedAddress,
-    mk_uuid,
-)
+from .devx._debug import maybe_wait_for_debugger
 from ._state import current_actor, is_main_process
 from .log import get_logger, get_loglevel
 from ._runtime import Actor
 from ._portal import Portal
-from .trionics import (
-    is_multi_cancelled,
-    collapse_eg,
-)
 from ._exceptions import (
+    is_multi_cancelled,
     ContextCancelled,
 )
-from ._root import (
-    open_root_actor,
-)
+from ._root import open_root_actor
 from . import _state
 from . import _spawn
 
 
 if TYPE_CHECKING:
     import multiprocessing as mp
-    # from .ipc._server import IPCServer
-    from .ipc import IPCServer
-
 
 log = get_logger(__name__)
 
+_default_bind_addr: tuple[str, int] = ('127.0.0.1', 0)
+
 
 class ActorNursery:
     '''
@@ -95,7 +80,6 @@ class ActorNursery:
     '''
     def __init__(
         self,
-        # TODO: maybe def these as fields of a struct looking type?
         actor: Actor,
         ria_nursery: trio.Nursery,
         da_nursery: trio.Nursery,
@@ -104,10 +88,8 @@ class ActorNursery:
     ) -> None:
         # self.supervisor = supervisor  # TODO
         self._actor: Actor = actor
-
-        # TODO: rename to `._tn` for our conventional "task-nursery"
+        self._ria_nursery = ria_nursery
         self._da_nursery = da_nursery
-
         self._children: dict[
             tuple[str, str],
             tuple[
@@ -116,12 +98,15 @@ class ActorNursery:
                 Portal | None,
             ]
         ] = {}
-
+        # portals spawned with ``run_in_actor()`` are
+        # cancelled when their "main" result arrives
+        self._cancel_after_result_on_exit: set = set()
+        self.cancelled: bool = False
         self._join_procs = trio.Event()
         self._at_least_one_child_in_debug: bool = False
         self.errors = errors
-        self._scope_error: BaseException|None = None
         self.exited = trio.Event()
+        self._scope_error: BaseException|None = None
 
         # NOTE: when no explicit call is made to
         # `.open_root_actor()` by application code,
@@ -131,76 +116,20 @@ class ActorNursery:
         # and syncing purposes to any actor opened nurseries.
         self._implicit_runtime_started: bool = False
 
-        # TODO: remove the `.run_in_actor()` API and thus this 2ndary
-        # nursery when that API get's moved outside this primitive!
-        self._ria_nursery = ria_nursery
-
-        # TODO, factor this into a .hilevel api!
-        #
-        # portals spawned with ``run_in_actor()`` are
-        # cancelled when their "main" result arrives
-        self._cancel_after_result_on_exit: set = set()
-
-        # trio.Nursery-like cancel (request) statuses
-        self._cancelled_caught: bool = False
-        self._cancel_called: bool = False
-
-    @property
-    def cancel_called(self) -> bool:
-        '''
-        Records whether cancellation has been requested for this
-        actor-nursery by a call to  `.cancel()` either due to,
-        - an explicit call by some actor-local-task,
-        - an implicit call due to an error/cancel emited inside
-          the `tractor.open_nursery()` block.
-
-        '''
-        return self._cancel_called
-
-    @property
-    def cancelled_caught(self) -> bool:
-        '''
-        Set when this nursery was able to cance all spawned subactors
-        gracefully via an (implicit) call to `.cancel()`.
-
-        '''
-        return self._cancelled_caught
-
-    # TODO! remove internal/test-suite usage!
-    @property
-    def cancelled(self) -> bool:
-        warnings.warn(
-            "`ActorNursery.cancelled` is now deprecated, use "
-            " `.cancel_called` instead.",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        return (
-            self._cancel_called
-            # and
-            # self._cancelled_caught
-        )
-
     async def start_actor(
         self,
         name: str,
 
         *,
 
-        bind_addrs: list[UnwrappedAddress]|None = None,
+        bind_addrs: list[tuple[str, int]] = [_default_bind_addr],
         rpc_module_paths: list[str]|None = None,
-        enable_transports: list[str] = [_state._def_tpt_proto],
         enable_modules: list[str]|None = None,
         loglevel: str|None = None,  # set log level per subactor
+        nursery: trio.Nursery|None = None,
         debug_mode: bool|None = None,
         infect_asyncio: bool = False,
 
-        # TODO: ideally we can rm this once we no longer have
-        # a `._ria_nursery` since the dependent APIs have been
-        # removed!
-        nursery: trio.Nursery|None = None,
-        proc_kwargs: dict[str, any] = {}
-
     ) -> Portal:
         '''
         Start a (daemon) actor: an process that has no designated
@@ -217,7 +146,6 @@ class ActorNursery:
         # configure and pass runtime state
         _rtv = _state._runtime_vars.copy()
         _rtv['_is_root'] = False
-        _rtv['_is_infected_aio'] = infect_asyncio
 
         # allow setting debug policy per actor
         if debug_mode is not None:
@@ -236,17 +164,15 @@ class ActorNursery:
             enable_modules.extend(rpc_module_paths)
 
         subactor = Actor(
-            name=name,
-            uuid=mk_uuid(),
-
+            name,
             # modules allowed to invoked funcs from
             enable_modules=enable_modules,
             loglevel=loglevel,
 
             # verbatim relay this actor's registrar addresses
-            registry_addrs=current_actor().registry_addrs,
+            registry_addrs=current_actor().reg_addrs,
         )
-        parent_addr: UnwrappedAddress = self._actor.accept_addr
+        parent_addr = self._actor.accept_addr
         assert parent_addr
 
         # start a task to spawn a process
@@ -265,7 +191,6 @@ class ActorNursery:
                 parent_addr,
                 _rtv,  # run time vars
                 infect_asyncio=infect_asyncio,
-                proc_kwargs=proc_kwargs
             )
         )
 
@@ -275,7 +200,6 @@ class ActorNursery:
     #  |_ dynamic @context decoration on child side
     #  |_ implicit `Portal.open_context() as (ctx, first):`
     #    and `return first` on parent side.
-    #  |_ mention how it's similar to `trio-parallel` API?
     # -[ ] use @api_frame on the wrapper
     async def run_in_actor(
         self,
@@ -284,12 +208,11 @@ class ActorNursery:
         *,
 
         name: str | None = None,
-        bind_addrs: UnwrappedAddress|None = None,
+        bind_addrs: tuple[str, int] = [_default_bind_addr],
         rpc_module_paths: list[str] | None = None,
         enable_modules: list[str] | None = None,
         loglevel: str | None = None,  # set log level per subactor
         infect_asyncio: bool = False,
-        proc_kwargs: dict[str, any] = {},
 
         **kwargs,  # explicit args to ``fn``
 
@@ -320,7 +243,6 @@ class ActorNursery:
             # use the run_in_actor nursery
             nursery=self._ria_nursery,
             infect_asyncio=infect_asyncio,
-            proc_kwargs=proc_kwargs
         )
 
         # XXX: don't allow stream funcs
@@ -347,32 +269,23 @@ class ActorNursery:
 
     ) -> None:
         '''
-        Cancel this actor-nursery by instructing each subactor's
-        runtime to cancel and wait for all underlying sub-processes
-        to terminate.
+        Cancel this nursery by instructing each subactor to cancel
+        itself and wait for all subactors to terminate.
 
-        If `hard_kill` is set then kill the processes directly using
-        the spawning-backend's API/OS-machinery without any attempt
-        at (graceful) `trio`-style cancellation using our
-        `Actor.cancel()`.
+        If ``hard_killl`` is set to ``True`` then kill the processes
+        directly without any far end graceful ``trio`` cancellation.
 
         '''
         __runtimeframe__: int = 1  # noqa
-        self._cancel_called = True
+        self.cancelled = True
 
         # TODO: impl a repr for spawn more compact
         # then `._children`..
         children: dict = self._children
         child_count: int = len(children)
         msg: str = f'Cancelling actor nursery with {child_count} children\n'
-
-        server: IPCServer = self._actor.ipc_server
-
         with trio.move_on_after(3) as cs:
-            async with (
-                collapse_eg(),
-                trio.open_nursery() as tn,
-            ):
+            async with trio.open_nursery() as tn:
 
                 subactor: Actor
                 proc: trio.Process
@@ -391,7 +304,7 @@ class ActorNursery:
 
                     else:
                         if portal is None:  # actor hasn't fully spawned yet
-                            event: trio.Event = server._peer_connected[subactor.uid]
+                            event = self._actor._peer_connected[subactor.uid]
                             log.warning(
                                 f"{subactor.uid} never 't finished spawning?"
                             )
@@ -407,7 +320,7 @@ class ActorNursery:
                             if portal is None:
                                 # cancelled while waiting on the event
                                 # to arrive
-                                chan = server._peers[subactor.uid][-1]
+                                chan = self._actor._peers[subactor.uid][-1]
                                 if chan:
                                     portal = Portal(chan)
                                 else:  # there's no other choice left
@@ -436,8 +349,6 @@ class ActorNursery:
             ) in children.values():
                 log.warning(f"Hard killing process {proc}")
                 proc.terminate()
-        else:
-            self._cancelled_caught
 
         # mark ourselves as having (tried to have) cancelled all subactors
         self._join_procs.set()
@@ -446,12 +357,11 @@ class ActorNursery:
 @acm
 async def _open_and_supervise_one_cancels_all_nursery(
     actor: Actor,
-    hide_tb: bool = True,
 
 ) -> typing.AsyncGenerator[ActorNursery, None]:
 
     # normally don't need to show user by default
-    __tracebackhide__: bool = hide_tb
+    __tracebackhide__: bool = True
 
     outer_err: BaseException|None = None
     inner_err: BaseException|None = None
@@ -467,23 +377,18 @@ async def _open_and_supervise_one_cancels_all_nursery(
     # `ActorNursery.start_actor()`).
 
     # errors from this daemon actor nursery bubble up to caller
-    async with (
-        collapse_eg(),
-        trio.open_nursery() as da_nursery,
-    ):
+    async with trio.open_nursery() as da_nursery:
         try:
             # This is the inner level "run in actor" nursery. It is
             # awaited first since actors spawned in this way (using
-            # `ActorNusery.run_in_actor()`) are expected to only
+            # ``ActorNusery.run_in_actor()``) are expected to only
             # return a single result and then complete (i.e. be canclled
             # gracefully). Errors collected from these actors are
             # immediately raised for handling by a supervisor strategy.
             # As such if the strategy propagates any error(s) upwards
             # the above "daemon actor" nursery will be notified.
-            async with (
-                collapse_eg(),
-                trio.open_nursery() as ria_nursery,
-            ):
+            async with trio.open_nursery() as ria_nursery:
+
                 an = ActorNursery(
                     actor,
                     ria_nursery,
@@ -500,7 +405,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # the "hard join phase".
                     log.runtime(
                         'Waiting on subactors to complete:\n'
-                        f'>}} {len(an._children)}\n'
+                        f'{pformat(an._children)}\n'
                     )
                     an._join_procs.set()
 
@@ -514,7 +419,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # will make the pdb repl unusable.
                     # Instead try to wait for pdb to be released before
                     # tearing down.
-                    await debug.maybe_wait_for_debugger(
+                    await maybe_wait_for_debugger(
                         child_in_debug=an._at_least_one_child_in_debug
                     )
 
@@ -549,8 +454,8 @@ async def _open_and_supervise_one_cancels_all_nursery(
                             ContextCancelled,
                         }:
                             log.cancel(
-                                'Actor-nursery caught remote cancellation\n'
-                                '\n'
+                                'Actor-nursery caught remote cancellation\n\n'
+
                                 f'{inner_err.tb_str}'
                             )
                         else:
@@ -590,7 +495,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
 
             # XXX: yet another guard before allowing the cancel
             # sequence in case a (single) child is in debug.
-            await debug.maybe_wait_for_debugger(
+            await maybe_wait_for_debugger(
                 child_in_debug=an._at_least_one_child_in_debug
             )
 
@@ -639,18 +544,10 @@ async def _open_and_supervise_one_cancels_all_nursery(
     # final exit
 
 
-_shutdown_msg: str = (
-    'Actor-runtime-shutdown'
-)
-
-
 @acm
 # @api_frame
 async def open_nursery(
-    *,  # named params only!
-    hide_tb: bool = True,
     **kwargs,
-    # ^TODO, paramspec for `open_root_actor()`
 
 ) -> typing.AsyncGenerator[ActorNursery, None]:
     '''
@@ -668,7 +565,7 @@ async def open_nursery(
     which cancellation scopes correspond to each spawned subactor set.
 
     '''
-    __tracebackhide__: bool = hide_tb
+    __tracebackhide__: bool = True
     implicit_runtime: bool = False
     actor: Actor = current_actor(err_on_no_runtime=False)
     an: ActorNursery|None = None
@@ -684,10 +581,7 @@ async def open_nursery(
             # mark us for teardown on exit
             implicit_runtime: bool = True
 
-            async with open_root_actor(
-                hide_tb=hide_tb,
-                **kwargs,
-            ) as actor:
+            async with open_root_actor(**kwargs) as actor:
                 assert actor is current_actor()
 
                 try:
@@ -725,33 +619,18 @@ async def open_nursery(
         # show frame on any internal runtime-scope error
         if (
             an
-            and
-            not an.cancelled
-            and
-            an._scope_error
+            and not an.cancelled
+            and an._scope_error
         ):
             __tracebackhide__: bool = False
 
-
-        op_nested_an_repr: str = _pformat.nest_from_op(
-            input_op=')>',
-            text=f'{an}',
-            # nest_prefix='|_',
-            nest_indent=1,  # under >
+        msg: str = (
+            'Actor-nursery exited\n'
+            f'|_{an}\n'
         )
-        an_msg: str = (
-            f'Actor-nursery exited\n'
-            f'{op_nested_an_repr}\n'
-        )
-        # keep noise low during std operation.
-        log.runtime(an_msg)
 
+        # shutdown runtime if it was started
         if implicit_runtime:
-            # shutdown runtime if it was started and report noisly
-            # that we're did so.
-            msg: str = (
-                '\n'
-                '\n'
-                f'{_shutdown_msg} )>\n'
-            )
-            log.info(msg)
+            msg += '=> Shutting down actor runtime <=\n'
+
+        log.info(msg)

tractor/_testing/__init__.py

@@ -19,16 +19,10 @@ Various helpers/utils for auditing your `tractor` app and/or the
 core runtime.
 
 '''
-from contextlib import (
-    asynccontextmanager as acm,
-)
-import os
+from contextlib import asynccontextmanager as acm
 import pathlib
 
 import tractor
-from tractor.devx.debug import (
-    BoxedMaybeException,
-)
 from .pytest import (
     tractor_test as tractor_test
 )
@@ -37,9 +31,6 @@ from .fault_simulation import (
 )
 
 
-# TODO, use dulwhich for this instead?
-# -> we're going to likely need it (or something similar)
-#   for supporting hot-coad reload feats eventually anyway!
 def repodir() -> pathlib.Path:
     '''
     Return the abspath to the repo directory.
@@ -63,35 +54,6 @@ def examples_dir() -> pathlib.Path:
     return repodir() / 'examples'
 
 
-def mk_cmd(
-    ex_name: str,
-    exs_subpath: str = 'debugging',
-) -> str:
-    '''
-    Generate a shell command suitable to pass to `pexpect.spawn()`
-    which runs the script as a python program's entrypoint.
-
-    In particular ensure we disable the new tb coloring via unsetting
-    `$PYTHON_COLORS` so that `pexpect` can pattern match without
-    color-escape-codes.
-
-    '''
-    script_path: pathlib.Path = (
-        examples_dir()
-        / exs_subpath
-        / f'{ex_name}.py'
-    )
-    py_cmd: str = ' '.join([
-        'python',
-        str(script_path)
-    ])
-    # XXX, required for py 3.13+
-    # https://docs.python.org/3/using/cmdline.html#using-on-controlling-color
-    # https://docs.python.org/3/using/cmdline.html#envvar-PYTHON_COLORS
-    os.environ['PYTHON_COLORS'] = '0'
-    return py_cmd
-
-
 @acm
 async def expect_ctxc(
     yay: bool,
@@ -104,13 +66,12 @@ async def expect_ctxc(
     '''
     if yay:
         try:
-            yield (maybe_exc := BoxedMaybeException())
+            yield
             raise RuntimeError('Never raised ctxc?')
-        except tractor.ContextCancelled as ctxc:
-            maybe_exc.value = ctxc
+        except tractor.ContextCancelled:
             if reraise:
                 raise
             else:
                 return
     else:
-        yield (maybe_exc := BoxedMaybeException())
+        yield

tractor/_testing/addr.py

@@ -1,70 +0,0 @@
-# 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/>.
-
-'''
-Random IPC addr generation for isolating
-the discovery space between test sessions.
-
-Might be eventually useful to expose as a util set from
-our `tractor.discovery` subsys?
-
-'''
-import random
-from typing import (
-    Type,
-)
-from tractor import (
-    _addr,
-)
-
-
-def get_rando_addr(
-    tpt_proto: str,
-    *,
-
-    # choose random port at import time
-    _rando_port: str = random.randint(1000, 9999)
-
-) -> tuple[str, str|int]:
-    '''
-    Used to 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.
-
-    '''
-    addr_type: Type[_addr.Addres] = _addr._address_types[tpt_proto]
-    def_reg_addr: tuple[str, int] = _addr._default_lo_addrs[tpt_proto]
-
-    # this is the "unwrapped" form expected to be passed to
-    # `.open_root_actor()` by test body.
-    testrun_reg_addr: tuple[str, int|str]
-    match tpt_proto:
-        case 'tcp':
-            testrun_reg_addr = (
-                addr_type.def_bindspace,
-                _rando_port,
-            )
-
-        # NOTE, file-name uniqueness (no-collisions) will be based on
-        # the runtime-directory and root (pytest-proc's) pid.
-        case 'uds':
-            testrun_reg_addr = addr_type.get_random().unwrap()
-
-    # XXX, as sanity it should never the same as the default for the
-    # host-singleton registry actor.
-    assert def_reg_addr != testrun_reg_addr
-
-    return testrun_reg_addr

tractor/_testing/pytest.py

@@ -26,46 +26,29 @@ from functools import (
 import inspect
 import platform
 
-import pytest
 import tractor
 import trio
 
 
 def tractor_test(fn):
     '''
-    Decorator for async test fns to decorator-wrap them as "native"
-    looking sync funcs runnable by `pytest` and auto invoked with
-    `trio.run()` (much like the `pytest-trio` plugin's approach).
+    Decorator for async test funcs to present them as "native"
+    looking sync funcs runnable by `pytest` using `trio.run()`.
 
-    Further the test fn body will be invoked AFTER booting the actor
-    runtime, i.e. from inside a `tractor.open_root_actor()` block AND
-    with various runtime and tooling parameters implicitly passed as
-    requested by by the test session's config; see immediately below.
+    Use:
 
-    Basic deco use:
-    ---------------
+    @tractor_test
+    async def test_whatever():
+        await ...
 
-      @tractor_test
-      async def test_whatever():
-          await ...
+    If fixtures:
 
+        - ``reg_addr`` (a socket addr tuple where arbiter is listening)
+        - ``loglevel`` (logging level passed to tractor internals)
+        - ``start_method`` (subprocess spawning backend)
 
-    Runtime config via special fixtures:
-    ------------------------------------
-    If any of the following fixture are requested by the wrapped test
-    fn (via normal func-args declaration),
-
-    - `reg_addr` (a socket addr tuple where arbiter is listening)
-    - `loglevel` (logging level passed to tractor internals)
-    - `start_method` (subprocess spawning backend)
-
-    (TODO support)
-    - `tpt_proto` (IPC transport protocol key)
-
-    they will be automatically injected to each test as normally
-    expected as well as passed to the initial
-    `tractor.open_root_actor()` funcargs.
-
+    are defined in the `pytest` fixture space they will be automatically
+    injected to tests declaring these funcargs.
     '''
     @wraps(fn)
     def wrapper(
@@ -128,164 +111,3 @@ def tractor_test(fn):
         return trio.run(main)
 
     return wrapper
-
-
-def pytest_addoption(
-    parser: pytest.Parser,
-):
-    # parser.addoption(
-    #     "--ll",
-    #     action="store",
-    #     dest='loglevel',
-    #     default='ERROR', help="logging level to set when testing"
-    # )
-
-    parser.addoption(
-        "--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.'
-        ),
-    )
-
-    # provide which IPC transport protocols opting-in test suites
-    # should accumulatively run against.
-    parser.addoption(
-        "--tpt-proto",
-        nargs='+',  # accumulate-multiple-args
-        action="store",
-        dest='tpt_protos',
-        default=['tcp'],
-        help="Transport protocol to use under the `tractor.ipc.Channel`",
-    )
-
-
-def pytest_configure(config):
-    backend = config.option.spawn_backend
-    tractor._spawn.try_set_start_method(backend)
-
-
-@pytest.fixture(scope='session')
-def debug_mode(request) -> bool:
-    '''
-    Flag state for whether `--tpdb` (for `tractor`-py-debugger)
-    was passed to the test run.
-
-    Normally tests should pass this directly to `.open_root_actor()`
-    to allow the user to opt into suite-wide crash handling.
-
-    '''
-    debug_mode: bool = request.config.option.tractor_debug_mode
-    return debug_mode
-
-
-@pytest.fixture(scope='session')
-def spawn_backend(request) -> str:
-    return request.config.option.spawn_backend
-
-
-@pytest.fixture(scope='session')
-def tpt_protos(request) -> list[str]:
-
-    # allow quoting on CLI
-    proto_keys: list[str] = [
-        proto_key.replace('"', '').replace("'", "")
-        for proto_key in request.config.option.tpt_protos
-    ]
-
-    # ?TODO, eventually support multiple protos per test-sesh?
-    if len(proto_keys) > 1:
-        pytest.fail(
-            'We only support one `--tpt-proto <key>` atm!\n'
-        )
-
-    # XXX ensure we support the protocol by name via lookup!
-    for proto_key in proto_keys:
-        addr_type = tractor._addr._address_types[proto_key]
-        assert addr_type.proto_key == proto_key
-
-    yield proto_keys
-
-
-@pytest.fixture(
-    scope='session',
-    autouse=True,
-)
-def tpt_proto(
-    tpt_protos: list[str],
-) -> str:
-    proto_key: str = tpt_protos[0]
-
-    from tractor import _state
-    if _state._def_tpt_proto != proto_key:
-        _state._def_tpt_proto = proto_key
-
-    yield proto_key
-
-
-@pytest.fixture(scope='session')
-def reg_addr(
-    tpt_proto: str,
-) -> tuple[str, int|str]:
-    '''
-    Deliver a test-sesh unique registry address such
-    that each run's (tests which use this fixture) will
-    have no conflicts/cross-talk when running simultaneously
-    nor will interfere with other live `tractor` apps active
-    on the same network-host (namespace).
-
-    '''
-    from tractor._testing.addr import get_rando_addr
-    return get_rando_addr(
-        tpt_proto=tpt_proto,
-    )
-
-
-def pytest_generate_tests(
-    metafunc: pytest.Metafunc,
-):
-    spawn_backend: str = metafunc.config.option.spawn_backend
-
-    if not spawn_backend:
-        # XXX some weird windows bug with `pytest`?
-        spawn_backend = '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',
-        )
-
-    # TODO, parametrize any `tpt_proto: str` declaring tests!
-    # proto_tpts: list[str] = metafunc.config.option.proto_tpts
-    # if 'tpt_proto' in metafunc.fixturenames:
-    #     metafunc.parametrize(
-    #         'tpt_proto',
-    #         proto_tpts,  # TODO, double check this list usage!
-    #         scope='module',
-    #     )

tractor/_testing/samples.py

@@ -1,35 +0,0 @@
-import os
-import random
-
-
-def generate_sample_messages(
-    amount: int,
-    rand_min: int = 0,
-    rand_max: int = 0,
-    silent: bool = False
-) -> tuple[list[bytes], int]:
-
-    msgs = []
-    size = 0
-
-    if not silent:
-        print(f'\ngenerating {amount} messages...')
-
-    for i in range(amount):
-        msg = f'[{i:08}]'.encode('utf-8')
-
-        if rand_max > 0:
-            msg += os.urandom(
-                random.randint(rand_min, rand_max))
-
-        size += len(msg)
-
-        msgs.append(msg)
-
-        if not silent and i and i % 10_000 == 0:
-            print(f'{i} generated')
-
-    if not silent:
-        print(f'done, {size:,} bytes in total')
-
-    return msgs, size

tractor/devx/__init__.py

@@ -20,16 +20,15 @@ Runtime "developer experience" utils and addons to aid our
 and working with/on the actor runtime.
 
 """
-from .debug import (
+from ._debug import (
     maybe_wait_for_debugger as maybe_wait_for_debugger,
     acquire_debug_lock as acquire_debug_lock,
     breakpoint as breakpoint,
     pause as pause,
     pause_from_sync as pause_from_sync,
-    sigint_shield as sigint_shield,
+    shield_sigint_handler as shield_sigint_handler,
     open_crash_handler as open_crash_handler,
     maybe_open_crash_handler as maybe_open_crash_handler,
-    maybe_init_greenback as maybe_init_greenback,
     post_mortem as post_mortem,
     mk_pdb as mk_pdb,
 )
@@ -41,38 +40,3 @@ from .pformat import (
     pformat_caller_frame as pformat_caller_frame,
     pformat_boxed_tb as pformat_boxed_tb,
 )
-
-
-# TODO, move this to a new `.devx._pdbp` mod?
-def _enable_readline_feats() -> str:
-    '''
-    Handle `readline` when compiled with `libedit` to avoid breaking
-    tab completion in `pdbp` (and its dep `tabcompleter`)
-    particularly since `uv` cpython distis are compiled this way..
-
-    See docs for deats,
-    https://docs.python.org/3/library/readline.html#module-readline
-
-    Originally discovered soln via SO answer,
-    https://stackoverflow.com/q/49287102
-
-    '''
-    import readline
-    if (
-        # 3.13+ attr
-        # https://docs.python.org/3/library/readline.html#readline.backend
-        (getattr(readline, 'backend', False) == 'libedit')
-        or
-        'libedit' in readline.__doc__
-    ):
-        readline.parse_and_bind("python:bind -v")
-        readline.parse_and_bind("python:bind ^I rl_complete")
-        return 'libedit'
-    else:
-        readline.parse_and_bind("tab: complete")
-        readline.parse_and_bind("set editing-mode vi")
-        readline.parse_and_bind("set keymap vi")
-        return 'readline'
-
-
-_enable_readline_feats()

tractor/devx/_frame_stack.py

@@ -20,18 +20,13 @@ as it pertains to improving the grok-ability of our runtime!
 
 '''
 from __future__ import annotations
-from contextlib import (
-    _GeneratorContextManager,
-    _AsyncGeneratorContextManager,
-)
 from functools import partial
 import inspect
-import textwrap
 from types import (
     FrameType,
     FunctionType,
     MethodType,
-    CodeType,
+    # CodeType,
 )
 from typing import (
     Any,
@@ -39,9 +34,6 @@ from typing import (
     Type,
 )
 
-import pdbp
-from tractor.log import get_logger
-import trio
 from tractor.msg import (
     pretty_struct,
     NamespacePath,
@@ -49,8 +41,6 @@ from tractor.msg import (
 import wrapt
 
 
-log = get_logger(__name__)
-
 # TODO: yeah, i don't love this and we should prolly just
 # write a decorator that actually keeps a stupid ref to the func
 # obj..
@@ -244,7 +234,7 @@ def find_caller_info(
 _frame2callerinfo_cache: dict[FrameType, CallerInfo] = {}
 
 
-# TODO: -[x] move all this into new `.devx._frame_stack`!
+# TODO: -[x] move all this into new `.devx._code`!
 # -[ ] consider rename to _callstack?
 # -[ ] prolly create a `@runtime_api` dec?
 #   |_ @api_frame seems better?
@@ -296,85 +286,3 @@ def api_frame(
     wrapped._call_infos: dict[FrameType, CallerInfo] = _frame2callerinfo_cache
     wrapped.__api_func__: bool = True
     return wrapper(wrapped)
-
-
-# TODO: something like this instead of the adhoc frame-unhiding
-# blocks all over the runtime!! XD
-# -[ ] ideally we can expect a certain error (set) and if something
-#     else is raised then all frames below the wrapped one will be
-#     un-hidden via `__tracebackhide__: bool = False`.
-# |_ might need to dynamically mutate the code objs like
-#    `pdbp.hideframe()` does?
-# -[ ] use this as a `@acm` decorator as introed in 3.10?
-# @acm
-# async def unhide_frame_when_not(
-#     error_set: set[BaseException],
-# ) -> TracebackType:
-#     ...
-
-
-def hide_runtime_frames() -> dict[FunctionType, CodeType]:
-    '''
-    Hide call-stack frames for various std-lib and `trio`-API primitives
-    such that the tracebacks presented from our runtime are as minimized
-    as possible, particularly from inside a `PdbREPL`.
-
-    '''
-    # XXX HACKZONE XXX
-    #  hide exit stack frames on nurseries and cancel-scopes!
-    # |_ so avoid seeing it when the `pdbp` REPL is first engaged from
-    #    inside a `trio.open_nursery()` scope (with no line after it
-    #    in before the block end??).
-    #
-    # TODO: FINALLY got this workin originally with
-    #  `@pdbp.hideframe` around the `wrapper()` def embedded inside
-    #  `_ki_protection_decoratior()`.. which is in the module:
-    #  /home/goodboy/.virtualenvs/tractor311/lib/python3.11/site-packages/trio/_core/_ki.py
-    #
-    # -[ ] make an issue and patch for `trio` core? maybe linked
-    #    to the long outstanding `pdb` one below?
-    #   |_ it's funny that there's frame hiding throughout `._run.py`
-    #      but not where it matters on the below exit funcs..
-    #
-    # -[ ] provide a patchset for the lonstanding
-    #   |_ https://github.com/python-trio/trio/issues/1155
-    #
-    # -[ ] make a linked issue to ^ and propose allowing all the
-    #     `._core._run` code to have their `__tracebackhide__` value
-    #     configurable by a `RunVar` to allow getting scheduler frames
-    #     if desired through configuration?
-    #
-    # -[ ] maybe dig into the core `pdb` issue why the extra frame is shown
-    #      at all?
-    #
-    funcs: list[FunctionType] = [
-        trio._core._run.NurseryManager.__aexit__,
-        trio._core._run.CancelScope.__exit__,
-         _GeneratorContextManager.__exit__,
-         _AsyncGeneratorContextManager.__aexit__,
-         _AsyncGeneratorContextManager.__aenter__,
-         trio.Event.wait,
-    ]
-    func_list_str: str = textwrap.indent(
-        "\n".join(f.__qualname__ for f in funcs),
-        prefix=' |_ ',
-    )
-    log.devx(
-        'Hiding the following runtime frames by default:\n'
-        f'{func_list_str}\n'
-    )
-
-    codes: dict[FunctionType, CodeType] = {}
-    for ref in funcs:
-        # stash a pre-modified version of each ref's code-obj
-        # so it can be reverted later if needed.
-        codes[ref] = ref.__code__
-        pdbp.hideframe(ref)
-    #
-    # pdbp.hideframe(trio._core._run.NurseryManager.__aexit__)
-    # pdbp.hideframe(trio._core._run.CancelScope.__exit__)
-    # pdbp.hideframe(_GeneratorContextManager.__exit__)
-    # pdbp.hideframe(_AsyncGeneratorContextManager.__aexit__)
-    # pdbp.hideframe(_AsyncGeneratorContextManager.__aenter__)
-    # pdbp.hideframe(trio.Event.wait)
-    return codes

tractor/devx/_stackscope.py

@@ -24,32 +24,19 @@ disjoint, parallel executing tasks in separate actors.
 
 '''
 from __future__ import annotations
-# from functools import partial
-from threading import (
-    current_thread,
-    Thread,
-    RLock,
-)
 import multiprocessing as mp
 from signal import (
     signal,
-    getsignal,
     SIGUSR1,
-    SIGINT,
-)
-# import traceback
-from types import ModuleType
-from typing import (
-    Callable,
-    TYPE_CHECKING,
 )
+import traceback
+from typing import TYPE_CHECKING
 
 import trio
 from tractor import (
     _state,
     log as logmod,
 )
-from tractor.devx import debug
 
 log = logmod.get_logger(__name__)
 
@@ -64,68 +51,26 @@ if TYPE_CHECKING:
 
 @trio.lowlevel.disable_ki_protection
 def dump_task_tree() -> None:
-    '''
-    Do a classic `stackscope.extract()` task-tree dump to console at
-    `.devx()` level.
-
-    '''
     import stackscope
+    from tractor.log import get_console_log
+
     tree_str: str = str(
         stackscope.extract(
             trio.lowlevel.current_root_task(),
             recurse_child_tasks=True
         )
     )
+    log = get_console_log(
+        name=__name__,
+        level='cancel',
+    )
     actor: Actor = _state.current_actor()
-    thr: Thread = current_thread()
-    current_sigint_handler: Callable = getsignal(SIGINT)
-    if (
-        current_sigint_handler
-        is not
-        debug.DebugStatus._trio_handler
-    ):
-        sigint_handler_report: str = (
-            'The default `trio` SIGINT handler was replaced?!'
-        )
-    else:
-        sigint_handler_report: str = (
-            'The default `trio` SIGINT handler is in use?!'
-        )
-
-    # sclang symbology
-    # |_<object>
-    # |_(Task/Thread/Process/Actor
-    # |_{Supervisor/Scope
-    # |_[Storage/Memory/IPC-Stream/Data-Struct
-
     log.devx(
         f'Dumping `stackscope` tree for actor\n'
-        f'(>: {actor.uid!r}\n'
-        f' |_{mp.current_process()}\n'
-        f'   |_{thr}\n'
-        f'     |_{actor}\n'
-        f'\n'
-        f'{sigint_handler_report}\n'
-        f'signal.getsignal(SIGINT) -> {current_sigint_handler!r}\n'
-        # f'\n'
-        # start-of-trace-tree delimiter (mostly for testing)
-        # f'------ {actor.uid!r} ------\n'
-        f'\n'
-        f'------ start-of-{actor.uid!r} ------\n'
-        f'|\n'
-        f'{tree_str}'
-        # end-of-trace-tree delimiter (mostly for testing)
-        f'|\n'
-        f'|_____ end-of-{actor.uid!r} ______\n'
+        f'{actor.name}: {actor}\n'
+        f' |_{mp.current_process()}\n\n'
+        f'{tree_str}\n'
     )
-    # TODO: can remove this right?
-    # -[ ] was original code from author
-    #
-    # print(
-    #     'DUMPING FROM PRINT\n'
-    #     +
-    #     content
-    # )
     # import logging
     # try:
     #     with open("/dev/tty", "w") as tty:
@@ -135,131 +80,58 @@ def dump_task_tree() -> None:
     #         "task_tree"
     #     ).exception("Error printing task tree")
 
-_handler_lock = RLock()
-_tree_dumped: bool = False
 
-
-def dump_tree_on_sig(
+def signal_handler(
     sig: int,
     frame: object,
 
     relay_to_subs: bool = True,
 
 ) -> None:
-    global _tree_dumped, _handler_lock
-    with _handler_lock:
-        # if _tree_dumped:
-        #     log.warning(
-        #         'Already dumped for this actor...??'
-        #     )
-        #     return
-
-        _tree_dumped = True
-
-        # actor: Actor = _state.current_actor()
-        log.devx(
-            'Trying to dump `stackscope` tree..\n'
-        )
-        try:
-            dump_task_tree()
-            # await actor._service_n.start_soon(
-            #     partial(
-            #         trio.to_thread.run_sync,
-            #         dump_task_tree,
-            #     )
-            # )
-            # trio.lowlevel.current_trio_token().run_sync_soon(
-            #     dump_task_tree
-            # )
-
-        except RuntimeError:
-            log.exception(
-                'Failed to dump `stackscope` tree..\n'
-            )
-            # not in async context -- print a normal traceback
-            # traceback.print_stack()
-            raise
-
-        except BaseException:
-            log.exception(
-                'Failed to dump `stackscope` tree..\n'
-            )
-            raise
-
-        # log.devx(
-        #     'Supposedly we dumped just fine..?'
-        # )
+    try:
+        trio.lowlevel.current_trio_token(
+        ).run_sync_soon(dump_task_tree)
+    except RuntimeError:
+        # not in async context -- print a normal traceback
+        traceback.print_stack()
 
     if not relay_to_subs:
         return
 
     an: ActorNursery
     for an in _state.current_actor()._actoruid2nursery.values():
+
         subproc: ProcessType
         subactor: Actor
         for subactor, subproc, _ in an._children.values():
-            log.warning(
+            log.devx(
                 f'Relaying `SIGUSR1`[{sig}] to sub-actor\n'
                 f'{subactor}\n'
                 f' |_{subproc}\n'
             )
 
-            # bc of course stdlib can't have a std API.. XD
-            match subproc:
-                case trio.Process():
-                    subproc.send_signal(sig)
+            if isinstance(subproc, trio.Process):
+                subproc.send_signal(sig)
 
-                case mp.Process():
-                    subproc._send_signal(sig)
+            elif isinstance(subproc, mp.Process):
+                subproc._send_signal(sig)
 
 
 def enable_stack_on_sig(
-    sig: int = SIGUSR1,
-) -> ModuleType:
+    sig: int = SIGUSR1
+) -> None:
     '''
     Enable `stackscope` tracing on reception of a signal; by
     default this is SIGUSR1.
 
-    HOT TIP: a task/ctx-tree dump can be triggered from a shell with
-    fancy cmds.
-
-    For ex. from `bash` using `pgrep` and cmd-sustitution
-    (https://www.gnu.org/software/bash/manual/bash.html#Command-Substitution)
-    you could use:
-
-    >> kill -SIGUSR1 $(pgrep -f <part-of-cmd: str>)
-
-    OR without a sub-shell,
-
-    >> pkill --signal SIGUSR1 -f <part-of-cmd: str>
-
     '''
-    try:
-        import stackscope
-    except ImportError:
-        log.warning(
-            'The `stackscope` lib is not installed!\n'
-            '`Ignoring enable_stack_on_sig() call!\n'
-        )
-        return None
-
-    handler: Callable|int = getsignal(sig)
-    if handler is dump_tree_on_sig:
-        log.devx(
-            'A `SIGUSR1` handler already exists?\n'
-            f'|_ {handler!r}\n'
-        )
-        return
-
     signal(
         sig,
-        dump_tree_on_sig,
+        signal_handler,
     )
-    log.devx(
-        f'Enabling trace-trees on `SIGUSR1` '
-        f'since `stackscope` is installed @ \n'
-        f'{stackscope!r}\n\n'
-        f'With `SIGUSR1` handler\n'
-        f'|_{dump_tree_on_sig}\n'
-    )
-    return stackscope
+    # NOTE: not the above can be triggered from
+    # a (xonsh) shell using:
+    # kill -SIGUSR1 @$(pgrep -f '<cmd>')
+    #
+    # for example if you were looking to trace a `pytest` run
+    # kill -SIGUSR1 @$(pgrep -f 'pytest')

tractor/devx/debug/__init__.py

@@ -1,100 +0,0 @@
-# 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-actor debugging for da peeps!
-
-'''
-from __future__ import annotations
-from tractor.log import get_logger
-from ._repl import (
-    PdbREPL as PdbREPL,
-    mk_pdb as mk_pdb,
-    TractorConfig as TractorConfig,
-)
-from ._tty_lock import (
-    DebugStatus as DebugStatus,
-    DebugStateError as DebugStateError,
-)
-from ._trace import (
-    Lock as Lock,
-    _pause_msg as _pause_msg,
-    _repl_fail_msg as _repl_fail_msg,
-    _set_trace as _set_trace,
-    _sync_pause_from_builtin as _sync_pause_from_builtin,
-    breakpoint as breakpoint,
-    maybe_init_greenback as maybe_init_greenback,
-    maybe_import_greenback as maybe_import_greenback,
-    pause as pause,
-    pause_from_sync as pause_from_sync,
-)
-from ._post_mortem import (
-    BoxedMaybeException as BoxedMaybeException,
-    maybe_open_crash_handler as maybe_open_crash_handler,
-    open_crash_handler as open_crash_handler,
-    post_mortem as post_mortem,
-    _crash_msg as _crash_msg,
-    _maybe_enter_pm as _maybe_enter_pm,
-)
-from ._sync import (
-    maybe_wait_for_debugger as maybe_wait_for_debugger,
-    acquire_debug_lock as acquire_debug_lock,
-)
-from ._sigint import (
-    sigint_shield as sigint_shield,
-    _ctlc_ignore_header as _ctlc_ignore_header
-)
-
-log = get_logger(__name__)
-
-# ----------------
-# XXX PKG TODO XXX
-# ----------------
-# refine the internal impl and APIs!
-#
-# -[ ] rework `._pause()` and it's branch-cases for root vs.
-#     subactor:
-#  -[ ] `._pause_from_root()` + `_pause_from_subactor()`?
-#  -[ ]  do the de-factor based on bg-thread usage in
-#    `.pause_from_sync()` & `_pause_from_bg_root_thread()`.
-#  -[ ] drop `debug_func == None` case which is confusing af..
-#  -[ ]  factor out `_enter_repl_sync()` into a util func for calling
-#    the `_set_trace()` / `_post_mortem()` APIs?
-#
-# -[ ] figure out if we need `acquire_debug_lock()` and/or re-implement
-#    it as part of the `.pause_from_sync()` rework per above?
-#
-# -[ ] pair the `._pause_from_subactor()` impl with a "debug nursery"
-#   that's dynamically allocated inside the `._rpc` task thus
-#   avoiding the `._service_n.start()` usage for the IPC request?
-#  -[ ] see the TODO inside `._rpc._errors_relayed_via_ipc()`
-#
-# -[ ] impl a `open_debug_request()` which encaps all
-#   `request_root_stdio_lock()` task scheduling deats
-#   + `DebugStatus` state mgmt; which should prolly be re-branded as
-#   a `DebugRequest` type anyway AND with suppoort for bg-thread
-#   (from root actor) usage?
-#
-# -[ ] handle the `xonsh` case for bg-root-threads in the SIGINT
-#     handler!
-#   -[ ] do we need to do the same for subactors?
-#   -[ ] make the failing tests finally pass XD
-#
-# -[ ] simplify `maybe_wait_for_debugger()` to be a root-task only
-#     API?
-#   -[ ] currently it's implemented as that so might as well make it
-#     formal?

tractor/devx/debug/_post_mortem.py

@@ -1,412 +0,0 @@
-# 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/>.
-
-'''
-Post-mortem debugging APIs and surrounding machinery for both
-sync and async contexts.
-
-Generally we maintain the same semantics a `pdb.post.mortem()` but
-with actor-tree-wide sync/cooperation around any (sub)actor's use of
-the root's TTY.
-
-'''
-from __future__ import annotations
-import bdb
-from contextlib import (
-    AbstractContextManager,
-    contextmanager as cm,
-    nullcontext,
-)
-from functools import (
-    partial,
-)
-import inspect
-import sys
-import traceback
-from typing import (
-    Callable,
-    Sequence,
-    Type,
-    TYPE_CHECKING,
-)
-from types import (
-    TracebackType,
-    FrameType,
-)
-
-from msgspec import Struct
-import trio
-from tractor._exceptions import (
-    NoRuntime,
-)
-from tractor import _state
-from tractor._state import (
-    current_actor,
-    debug_mode,
-)
-from tractor.log import get_logger
-from tractor.trionics import (
-    is_multi_cancelled,
-)
-from ._trace import (
-    _pause,
-)
-from ._tty_lock import (
-    DebugStatus,
-)
-from ._repl import (
-    PdbREPL,
-    mk_pdb,
-    TractorConfig as TractorConfig,
-)
-
-if TYPE_CHECKING:
-    from trio.lowlevel import Task
-    from tractor._runtime import (
-        Actor,
-    )
-
-_crash_msg: str = (
-    'Opening a pdb REPL in crashed actor'
-)
-
-log = get_logger(__package__)
-
-
-class BoxedMaybeException(Struct):
-    '''
-    Box a maybe-exception for post-crash introspection usage
-    from the body of a `open_crash_handler()` scope.
-
-    '''
-    value: BaseException|None = None
-
-    # handler can suppress crashes dynamically
-    raise_on_exit: bool|Sequence[Type[BaseException]] = True
-
-    def pformat(self) -> str:
-        '''
-        Repr the boxed `.value` error in more-than-string
-        repr form.
-
-        '''
-        if not self.value:
-            return f'<{type(self).__name__}( .value=None )>'
-
-        return (
-            f'<{type(self.value).__name__}(\n'
-            f' |_.value = {self.value}\n'
-            f')>\n'
-        )
-
-    __repr__ = pformat
-
-
-def _post_mortem(
-    repl: PdbREPL,  # normally passed by `_pause()`
-
-    # XXX all `partial`-ed in by `post_mortem()` below!
-    tb: TracebackType,
-    api_frame: FrameType,
-
-    shield: bool = False,
-    hide_tb: bool = True,
-
-    # maybe pre/post REPL entry
-    repl_fixture: (
-        AbstractContextManager[bool]
-        |None
-    ) = None,
-
-    boxed_maybe_exc: BoxedMaybeException|None = None,
-
-) -> None:
-    '''
-    Enter the ``pdbpp`` port mortem entrypoint using our custom
-    debugger instance.
-
-    '''
-    __tracebackhide__: bool = hide_tb
-
-    # maybe enter any user fixture
-    enter_repl: bool = DebugStatus.maybe_enter_repl_fixture(
-        repl=repl,
-        repl_fixture=repl_fixture,
-        boxed_maybe_exc=boxed_maybe_exc,
-    )
-    try:
-        if not enter_repl:
-            # XXX, trigger `.release()` below immediately!
-            return
-        try:
-            actor: Actor = current_actor()
-            actor_repr: str = str(actor.uid)
-            # ^TODO, instead a nice runtime-info + maddr + uid?
-            # -[ ] impl a `Actor.__repr()__`??
-            #  |_ <task>:<thread> @ <actor>
-
-        except NoRuntime:
-            actor_repr: str = '<no-actor-runtime?>'
-
-        try:
-            task_repr: Task = trio.lowlevel.current_task()
-        except RuntimeError:
-            task_repr: str = '<unknown-Task>'
-
-        # TODO: print the actor supervion tree up to the root
-        # here! Bo
-        log.pdb(
-            f'{_crash_msg}\n'
-            f'x>(\n'
-            f' |_ {task_repr} @ {actor_repr}\n'
-
-        )
-
-        # XXX NOTE(s) on `pdbp.xpm()` version..
-        #
-        # - seems to lose the up-stack tb-info?
-        # - currently we're (only) replacing this from `pdbp.xpm()`
-        #   to add the `end=''` to the print XD
-        #
-        print(traceback.format_exc(), end='')
-        caller_frame: FrameType = api_frame.f_back
-
-        # NOTE, see the impl details of these in the lib to
-        # understand usage:
-        # - `pdbp.post_mortem()`
-        # - `pdbp.xps()`
-        # - `bdb.interaction()`
-        repl.reset()
-        repl.interaction(
-            frame=caller_frame,
-            # frame=None,
-            traceback=tb,
-        )
-    finally:
-        # XXX NOTE XXX: this is abs required to avoid hangs!
-        #
-        # Since we presume the post-mortem was enaged to
-        # a task-ending error, we MUST release the local REPL request
-        # so that not other local task nor the root remains blocked!
-        DebugStatus.release()
-
-
-async def post_mortem(
-    *,
-    tb: TracebackType|None = None,
-    api_frame: FrameType|None = None,
-    hide_tb: bool = False,
-
-    # TODO: support shield here just like in `pause()`?
-    # shield: bool = False,
-
-    **_pause_kwargs,
-
-) -> None:
-    '''
-    Our builtin async equivalient of `pdb.post_mortem()` which can be
-    used inside exception handlers.
-
-    It's also used for the crash handler when `debug_mode == True` ;)
-
-    '''
-    __tracebackhide__: bool = hide_tb
-
-    tb: TracebackType = tb or sys.exc_info()[2]
-
-    # TODO: do upward stack scan for highest @api_frame and
-    # use its parent frame as the expected user-app code
-    # interact point.
-    api_frame: FrameType = api_frame or inspect.currentframe()
-
-    # TODO, move to submod `._pausing` or ._api? _trace
-    await _pause(
-        debug_func=partial(
-            _post_mortem,
-            api_frame=api_frame,
-            tb=tb,
-        ),
-        hide_tb=hide_tb,
-        **_pause_kwargs
-    )
-
-
-async def _maybe_enter_pm(
-    err: BaseException,
-    *,
-    tb: TracebackType|None = None,
-    api_frame: FrameType|None = None,
-    hide_tb: bool = True,
-
-    # only enter debugger REPL when returns `True`
-    debug_filter: Callable[
-        [BaseException|BaseExceptionGroup],
-        bool,
-    ] = lambda err: not is_multi_cancelled(err),
-    **_pause_kws,
-):
-    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
-        debug_filter(err)
-    ):
-        api_frame: FrameType = api_frame or inspect.currentframe()
-        tb: TracebackType = tb or sys.exc_info()[2]
-        await post_mortem(
-            api_frame=api_frame,
-            tb=tb,
-            **_pause_kws,
-        )
-        return True
-
-    else:
-        return False
-
-
-# TODO: better naming and what additionals?
-# - [ ] optional runtime plugging?
-# - [ ] detection for sync vs. async code?
-# - [ ] specialized REPL entry when in distributed mode?
-# -[x] hide tb by def
-# - [x] allow ignoring kbi Bo
-@cm
-def open_crash_handler(
-    catch: set[BaseException] = {
-        BaseException,
-    },
-    ignore: set[BaseException] = {
-        KeyboardInterrupt,
-        trio.Cancelled,
-    },
-    hide_tb: bool = True,
-
-    repl_fixture: (
-        AbstractContextManager[bool]  # pre/post REPL entry
-        |None
-    ) = None,
-    raise_on_exit: bool|Sequence[Type[BaseException]] = True,
-):
-    '''
-    Generic "post mortem" crash handler using `pdbp` REPL debugger.
-
-    We expose this as a CLI framework addon to both `click` and
-    `typer` users so they can quickly wrap cmd endpoints which get
-    automatically wrapped to use the runtime's `debug_mode: bool`
-    AND `pdbp.pm()` around any code that is PRE-runtime entry
-    - any sync code which runs BEFORE the main call to
-      `trio.run()`.
-
-    '''
-    __tracebackhide__: bool = hide_tb
-
-    # TODO, yield a `outcome.Error`-like boxed type?
-    # -[~] use `outcome.Value/Error` X-> frozen!
-    # -[x] write our own..?
-    # -[ ] consider just wtv is used by `pytest.raises()`?
-    #
-    boxed_maybe_exc = BoxedMaybeException(
-        raise_on_exit=raise_on_exit,
-    )
-    err: BaseException
-    try:
-        yield boxed_maybe_exc
-    except tuple(catch) as err:
-        boxed_maybe_exc.value = err
-        if (
-            type(err) not in ignore
-            and
-            not is_multi_cancelled(
-                err,
-                ignore_nested=ignore
-            )
-        ):
-            try:
-                # use our re-impl-ed version of `pdbp.xpm()`
-                _post_mortem(
-                    repl=mk_pdb(),
-                    tb=sys.exc_info()[2],
-                    api_frame=inspect.currentframe().f_back,
-                    hide_tb=hide_tb,
-
-                    repl_fixture=repl_fixture,
-                    boxed_maybe_exc=boxed_maybe_exc,
-                )
-            except bdb.BdbQuit:
-                __tracebackhide__: bool = False
-                raise err
-
-        if (
-            raise_on_exit is True
-            or (
-                raise_on_exit is not False
-                and (
-                    set(raise_on_exit)
-                    and
-                    type(err) in raise_on_exit
-                )
-            )
-            and
-            boxed_maybe_exc.raise_on_exit == raise_on_exit
-        ):
-            raise err
-
-
-@cm
-def maybe_open_crash_handler(
-    pdb: bool|None = None,
-    hide_tb: bool = True,
-
-    **kwargs,
-):
-    '''
-    Same as `open_crash_handler()` but with bool input flag
-    to allow conditional handling.
-
-    Normally this is used with CLI endpoints such that if the --pdb
-    flag is passed the pdb REPL is engaed on any crashes B)
-
-    '''
-    __tracebackhide__: bool = hide_tb
-
-    if pdb is None:
-        pdb: bool = _state.is_debug_mode()
-
-    rtctx = nullcontext(
-        enter_result=BoxedMaybeException()
-    )
-    if pdb:
-        rtctx = open_crash_handler(
-            hide_tb=hide_tb,
-            **kwargs,
-        )
-
-    with rtctx as boxed_maybe_exc:
-        yield boxed_maybe_exc

tractor/devx/debug/_repl.py

@@ -1,207 +0,0 @@
-# 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/>.
-
-'''
-`pdpp.Pdb` extentions/customization and other delegate usage.
-
-'''
-from functools import (
-    cached_property,
-)
-import os
-
-import pdbp
-from tractor._state import (
-    is_root_process,
-)
-
-from ._tty_lock import (
-    Lock,
-    DebugStatus,
-)
-
-
-class TractorConfig(pdbp.DefaultConfig):
-    '''
-    Custom `pdbp` config which tries to use the best tradeoff
-    between pretty and minimal.
-
-    '''
-    use_pygments: bool = True
-    sticky_by_default: bool = False
-    enable_hidden_frames: bool = True
-
-    # much thanks @mdmintz for the hot tip!
-    # fixes line spacing issue when resizing terminal B)
-    truncate_long_lines: bool = False
-
-    # ------ - ------
-    # our own custom config vars mostly
-    # for syncing with the actor tree's singleton
-    # TTY `Lock`.
-
-
-class PdbREPL(pdbp.Pdb):
-    '''
-    Add teardown hooks and local state describing any
-    ongoing TTY `Lock` request dialog.
-
-    '''
-    # override the pdbp config with our coolio one
-    # NOTE: this is only loaded when no `~/.pdbrc` exists
-    # so we should prolly pass it into the .__init__() instead?
-    # i dunno, see the `DefaultFactory` and `pdb.Pdb` impls.
-    DefaultConfig = TractorConfig
-
-    status = DebugStatus
-
-    # NOTE: see details in stdlib's `bdb.py`
-    # def user_exception(self, frame, exc_info):
-    #     '''
-    #     Called when we stop on an exception.
-    #     '''
-    #     log.warning(
-    #         'Exception during REPL sesh\n\n'
-    #         f'{frame}\n\n'
-    #         f'{exc_info}\n\n'
-    #     )
-
-    # NOTE: this actually hooks but i don't see anyway to detect
-    # if an error was caught.. this is why currently we just always
-    # call `DebugStatus.release` inside `_post_mortem()`.
-    # def preloop(self):
-    #     print('IN PRELOOP')
-    #     super().preloop()
-
-    # TODO: cleaner re-wrapping of all this?
-    # -[ ] figure out how to disallow recursive .set_trace() entry
-    #     since that'll cause deadlock for us.
-    # -[ ] maybe a `@cm` to call `super().<same_meth_name>()`?
-    # -[ ] look at hooking into the `pp` hook specially with our
-    #     own set of pretty-printers?
-    #    * `.pretty_struct.Struct.pformat()`
-    #    * `.pformat(MsgType.pld)`
-    #    * `.pformat(Error.tb_str)`?
-    #    * .. maybe more?
-    #
-    def set_continue(self):
-        try:
-            super().set_continue()
-        finally:
-            # NOTE: for subactors the stdio lock is released via the
-            # allocated RPC locker task, so for root we have to do it
-            # manually.
-            if (
-                is_root_process()
-                and
-                Lock._debug_lock.locked()
-                and
-                DebugStatus.is_main_trio_thread()
-            ):
-                # Lock.release(raise_on_thread=False)
-                Lock.release()
-
-            # XXX AFTER `Lock.release()` for root local repl usage
-            DebugStatus.release()
-
-    def set_quit(self):
-        try:
-            super().set_quit()
-        finally:
-            if (
-                is_root_process()
-                and
-                Lock._debug_lock.locked()
-                and
-                DebugStatus.is_main_trio_thread()
-            ):
-                # Lock.release(raise_on_thread=False)
-                Lock.release()
-
-            # XXX after `Lock.release()` for root local repl usage
-            DebugStatus.release()
-
-    # XXX NOTE: we only override this because apparently the stdlib pdb
-    # bois likes to touch the SIGINT handler as much as i like to touch
-    # my d$%&.
-    def _cmdloop(self):
-        self.cmdloop()
-
-    @cached_property
-    def shname(self) -> str | None:
-        '''
-        Attempt to return the login shell name with a special check for
-        the infamous `xonsh` since it seems to have some issues much
-        different from std shells when it comes to flushing the prompt?
-
-        '''
-        # SUPER HACKY and only really works if `xonsh` is not used
-        # before spawning further sub-shells..
-        shpath = os.getenv('SHELL', None)
-
-        if shpath:
-            if (
-                os.getenv('XONSH_LOGIN', default=False)
-                or 'xonsh' in shpath
-            ):
-                return 'xonsh'
-
-            return os.path.basename(shpath)
-
-        return None
-
-
-def mk_pdb() -> PdbREPL:
-    '''
-    Deliver a new `PdbREPL`: a multi-process safe `pdbp.Pdb`-variant
-    using the magic of `tractor`'s SC-safe IPC.
-
-    B)
-
-    Our `pdb.Pdb` subtype accomplishes multi-process safe debugging
-    by:
-
-    - mutexing access to the root process' std-streams (& thus parent
-      process TTY) via an IPC managed `Lock` singleton per
-      actor-process tree.
-
-    - temporarily overriding any subactor's SIGINT handler to shield
-      during live REPL sessions in sub-actors such that cancellation
-      is never (mistakenly) triggered by a ctrl-c and instead only by
-      explicit runtime API requests or after the
-      `pdb.Pdb.interaction()` call has returned.
-
-    FURTHER, the `pdbp.Pdb` instance is configured to be `trio`
-    "compatible" from a SIGINT handling perspective; we mask out
-    the default `pdb` handler and instead apply `trio`s default
-    which mostly addresses all issues described in:
-
-     - https://github.com/python-trio/trio/issues/1155
-
-    The instance returned from this factory should always be
-    preferred over the default `pdb[p].set_trace()` whenever using
-    a `pdb` REPL inside a `trio` based runtime.
-
-    '''
-    pdb = PdbREPL()
-
-    # XXX: These are the important flags mentioned in
-    # https://github.com/python-trio/trio/issues/1155
-    # which resolve the traceback spews to console.
-    pdb.allow_kbdint = True
-    pdb.nosigint = True
-    return pdb

tractor/devx/debug/_sigint.py

@@ -1,333 +0,0 @@
-# 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/>.
-
-'''
-A custom SIGINT handler which mainly shields actor (task)
-cancellation during REPL interaction.
-
-'''
-from __future__ import annotations
-from typing import (
-    TYPE_CHECKING,
-)
-import trio
-from tractor.log import get_logger
-from tractor._state import (
-    current_actor,
-    is_root_process,
-)
-from ._repl import (
-    PdbREPL,
-)
-from ._tty_lock import (
-    any_connected_locker_child,
-    DebugStatus,
-    Lock,
-)
-
-if TYPE_CHECKING:
-    from tractor.ipc import (
-        Channel,
-    )
-    from tractor._runtime import (
-        Actor,
-    )
-
-log = get_logger(__name__)
-
-_ctlc_ignore_header: str = (
-    'Ignoring SIGINT while debug REPL in use'
-)
-
-
-def sigint_shield(
-    signum: int,
-    frame: 'frame',  # type: ignore # noqa
-    *args,
-
-) -> None:
-    '''
-    Specialized, debugger-aware SIGINT handler.
-
-    In childred we always ignore/shield for SIGINT to avoid
-    deadlocks since cancellation should always be managed by the
-    supervising parent actor. The root actor-proces is always
-    cancelled on ctrl-c.
-
-    '''
-    __tracebackhide__: bool = True
-    actor: Actor = current_actor()
-
-    def do_cancel():
-        # If we haven't tried to cancel the runtime then do that instead
-        # of raising a KBI (which may non-gracefully destroy
-        # a ``trio.run()``).
-        if not actor._cancel_called:
-            actor.cancel_soon()
-
-        # If the runtime is already cancelled it likely means the user
-        # hit ctrl-c again because teardown didn't fully take place in
-        # which case we do the "hard" raising of a local KBI.
-        else:
-            raise KeyboardInterrupt
-
-    # only set in the actor actually running the REPL
-    repl: PdbREPL|None = DebugStatus.repl
-
-    # TODO: maybe we should flatten out all these cases using
-    # a match/case?
-    #
-    # root actor branch that reports whether or not a child
-    # has locked debugger.
-    if is_root_process():
-        # log.warning(
-        log.devx(
-            'Handling SIGINT in root actor\n'
-            f'{Lock.repr()}'
-            f'{DebugStatus.repr()}\n'
-        )
-        # try to see if the supposed (sub)actor in debug still
-        # has an active connection to *this* actor, and if not
-        # it's likely they aren't using the TTY lock / debugger
-        # and we should propagate SIGINT normally.
-        any_connected: bool = any_connected_locker_child()
-
-        problem = (
-            f'root {actor.uid} handling SIGINT\n'
-            f'any_connected: {any_connected}\n\n'
-
-            f'{Lock.repr()}\n'
-        )
-
-        if (
-            (ctx := Lock.ctx_in_debug)
-            and
-            (uid_in_debug := ctx.chan.uid) # "someone" is (ostensibly) using debug `Lock`
-        ):
-            name_in_debug: str = uid_in_debug[0]
-            assert not repl
-            # if not repl:  # but it's NOT us, the root actor.
-            # sanity: since no repl ref is set, we def shouldn't
-            # be the lock owner!
-            assert name_in_debug != 'root'
-
-            # IDEAL CASE: child has REPL as expected
-            if any_connected:  # there are subactors we can contact
-                # XXX: only if there is an existing connection to the
-                # (sub-)actor in debug do we ignore SIGINT in this
-                # parent! Otherwise we may hang waiting for an actor
-                # which has already terminated to unlock.
-                #
-                # NOTE: don't emit this with `.pdb()` level in
-                # root without a higher level.
-                log.runtime(
-                    _ctlc_ignore_header
-                    +
-                    f' by child '
-                    f'{uid_in_debug}\n'
-                )
-                problem = None
-
-            else:
-                problem += (
-                    '\n'
-                    f'A `pdb` REPL is SUPPOSEDLY in use by child {uid_in_debug}\n'
-                    f'BUT, no child actors are IPC contactable!?!?\n'
-                )
-
-        # IDEAL CASE: root has REPL as expected
-        else:
-            # root actor still has this SIGINT handler active without
-            # an actor using the `Lock` (a bug state) ??
-            # => so immediately cancel any stale lock cs and revert
-            # the handler!
-            if not DebugStatus.repl:
-                # TODO: WHEN should we revert back to ``trio``
-                # handler if this one is stale?
-                # -[ ] maybe after a counts work of ctl-c mashes?
-                # -[ ] use a state var like `stale_handler: bool`?
-                problem += (
-                    'No subactor is using a `pdb` REPL according `Lock.ctx_in_debug`?\n'
-                    'BUT, the root should be using it, WHY this handler ??\n\n'
-                    'So either..\n'
-                    '- some root-thread is using it but has no `.repl` set?, OR\n'
-                    '- something else weird is going on outside the runtime!?\n'
-                )
-            else:
-                # NOTE: since we emit this msg on ctl-c, we should
-                # also always re-print the prompt the tail block!
-                log.pdb(
-                    _ctlc_ignore_header
-                    +
-                    f' by root actor..\n'
-                    f'{DebugStatus.repl_task}\n'
-                    f' |_{repl}\n'
-                )
-                problem = None
-
-        # XXX if one is set it means we ARE NOT operating an ideal
-        # case where a child subactor or us (the root) has the
-        # lock without any other detected problems.
-        if problem:
-
-            # detect, report and maybe clear a stale lock request
-            # cancel scope.
-            lock_cs: trio.CancelScope = Lock.get_locking_task_cs()
-            maybe_stale_lock_cs: bool = (
-                lock_cs is not None
-                and not lock_cs.cancel_called
-            )
-            if maybe_stale_lock_cs:
-                problem += (
-                    '\n'
-                    'Stale `Lock.ctx_in_debug._scope: CancelScope` detected?\n'
-                    f'{Lock.ctx_in_debug}\n\n'
-
-                    '-> Calling ctx._scope.cancel()!\n'
-                )
-                lock_cs.cancel()
-
-            # TODO: wen do we actually want/need this, see above.
-            # DebugStatus.unshield_sigint()
-            log.warning(problem)
-
-    # child actor that has locked the debugger
-    elif not is_root_process():
-        log.debug(
-            f'Subactor {actor.uid} handling SIGINT\n\n'
-            f'{Lock.repr()}\n'
-        )
-
-        rent_chan: Channel = actor._parent_chan
-        if (
-            rent_chan is None
-            or
-            not rent_chan.connected()
-        ):
-            log.warning(
-                'This sub-actor thinks it is debugging '
-                'but it has no connection to its parent ??\n'
-                f'{actor.uid}\n'
-                'Allowing SIGINT propagation..'
-            )
-            DebugStatus.unshield_sigint()
-
-        repl_task: str|None = DebugStatus.repl_task
-        req_task: str|None = DebugStatus.req_task
-        if (
-            repl_task
-            and
-            repl
-        ):
-            log.pdb(
-                _ctlc_ignore_header
-                +
-                f' by local task\n\n'
-                f'{repl_task}\n'
-                f' |_{repl}\n'
-            )
-        elif req_task:
-            log.debug(
-                _ctlc_ignore_header
-                +
-                f' by local request-task and either,\n'
-                f'- someone else is already REPL-in and has the `Lock`, or\n'
-                f'- some other local task already is replin?\n\n'
-                f'{req_task}\n'
-            )
-
-        # TODO can we remove this now?
-        # -[ ] does this path ever get hit any more?
-        else:
-            msg: str = (
-                'SIGINT shield handler still active BUT, \n\n'
-            )
-            if repl_task is None:
-                msg += (
-                    '- No local task claims to be in debug?\n'
-                )
-
-            if repl is None:
-                msg += (
-                    '- No local REPL is currently active?\n'
-                )
-
-            if req_task is None:
-                msg += (
-                    '- No debug request task is active?\n'
-                )
-
-            log.warning(
-                msg
-                +
-                'Reverting handler to `trio` default!\n'
-            )
-            DebugStatus.unshield_sigint()
-
-            # XXX ensure that the reverted-to-handler actually is
-            # able to rx what should have been **this** KBI ;)
-            do_cancel()
-
-        # TODO: how to handle the case of an intermediary-child actor
-        # that **is not** marked in debug mode? See oustanding issue:
-        # https://github.com/goodboy/tractor/issues/320
-        # elif debug_mode():
-
-    # maybe redraw/print last REPL output to console since
-    # we want to alert the user that more input is expect since
-    # nothing has been done dur to ignoring sigint.
-    if (
-        DebugStatus.repl  # only when current actor has a REPL engaged
-    ):
-        flush_status: str = (
-            'Flushing stdout to ensure new prompt line!\n'
-        )
-
-        # XXX: yah, mega hack, but how else do we catch this madness XD
-        if (
-            repl.shname == 'xonsh'
-        ):
-            flush_status += (
-                '-> ALSO re-flushing due to `xonsh`..\n'
-            )
-            repl.stdout.write(repl.prompt)
-
-        # log.warning(
-        log.devx(
-            flush_status
-        )
-        repl.stdout.flush()
-
-        # TODO: better console UX to match the current "mode":
-        # -[ ] for example if in sticky mode where if there is output
-        #   detected as written to the tty we redraw this part underneath
-        #   and erase the past draw of this same bit above?
-        # repl.sticky = True
-        # repl._print_if_sticky()
-
-        # also see these links for an approach from `ptk`:
-        # https://github.com/goodboy/tractor/issues/130#issuecomment-663752040
-        # https://github.com/prompt-toolkit/python-prompt-toolkit/blob/c2c6af8a0308f9e5d7c0e28cb8a02963fe0ce07a/prompt_toolkit/patch_stdout.py
-    else:
-        log.devx(
-        # log.warning(
-            'Not flushing stdout since not needed?\n'
-            f'|_{repl}\n'
-        )
-
-    # XXX only for tracing this handler
-    log.devx('exiting SIGINT')

tractor/devx/debug/_sync.py

@@ -1,220 +0,0 @@
-# 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/>.
-
-'''
-Debugger synchronization APIs to ensure orderly access and
-non-TTY-clobbering graceful teardown.
-
-
-'''
-from __future__ import annotations
-from contextlib import (
-    asynccontextmanager as acm,
-)
-from functools import (
-    partial,
-)
-from typing import (
-    AsyncGenerator,
-    Callable,
-)
-
-from tractor.log import get_logger
-import trio
-from trio.lowlevel import (
-    current_task,
-    Task,
-)
-from tractor._context import Context
-from tractor._state import (
-    current_actor,
-    debug_mode,
-    is_root_process,
-)
-from ._repl import (
-    TractorConfig as TractorConfig,
-)
-from ._tty_lock import (
-    Lock,
-    request_root_stdio_lock,
-    any_connected_locker_child,
-)
-from ._sigint import (
-    sigint_shield as sigint_shield,
-    _ctlc_ignore_header as _ctlc_ignore_header
-)
-
-log = get_logger(__package__)
-
-
-async def maybe_wait_for_debugger(
-    poll_steps: int = 2,
-    poll_delay: float = 0.1,
-    child_in_debug: bool = False,
-
-    header_msg: str = '',
-    _ll: str = 'devx',
-
-) -> bool:  # was locked and we polled?
-
-    if (
-        not debug_mode()
-        and
-        not child_in_debug
-    ):
-        return False
-
-    logmeth: Callable = getattr(log, _ll)
-
-    msg: str = header_msg
-    if (
-        is_root_process()
-    ):
-        # 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.
-        ctx_in_debug: Context|None = Lock.ctx_in_debug
-        in_debug: tuple[str, str]|None = (
-            ctx_in_debug.chan.uid
-            if ctx_in_debug
-            else None
-        )
-        if in_debug == current_actor().uid:
-            log.debug(
-                msg
-                +
-                'Root already owns the TTY LOCK'
-            )
-            return True
-
-        elif in_debug:
-            msg += (
-                f'Debug `Lock` in use by subactor\n|\n|_{in_debug}\n'
-            )
-            # 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 => but it doesn't seem to work..
-            # await trio.testing.wait_all_tasks_blocked(cushion=0)
-        else:
-            logmeth(
-                msg
-                +
-                'Root immediately acquired debug TTY LOCK'
-            )
-            return False
-
-        for istep in range(poll_steps):
-            if (
-                Lock.req_handler_finished is not None
-                and not Lock.req_handler_finished.is_set()
-                and in_debug is not None
-            ):
-                # caller_frame_info: str = pformat_caller_frame()
-                logmeth(
-                    msg
-                    +
-                    '\n^^ Root is waiting on tty lock release.. ^^\n'
-                    # f'{caller_frame_info}\n'
-                )
-
-                if not any_connected_locker_child():
-                    Lock.get_locking_task_cs().cancel()
-
-                with trio.CancelScope(shield=True):
-                    await Lock.req_handler_finished.wait()
-
-                log.devx(
-                    f'Subactor released debug lock\n'
-                    f'|_{in_debug}\n'
-                )
-                break
-
-            # is no subactor locking debugger currently?
-            if (
-                in_debug is None
-                and (
-                    Lock.req_handler_finished is None
-                    or Lock.req_handler_finished.is_set()
-                )
-            ):
-                logmeth(
-                    msg
-                    +
-                    'Root acquired tty lock!'
-                )
-                break
-
-            else:
-                logmeth(
-                    'Root polling for debug:\n'
-                    f'poll step: {istep}\n'
-                    f'poll delya: {poll_delay}\n\n'
-                    f'{Lock.repr()}\n'
-                )
-                with trio.CancelScope(shield=True):
-                    await trio.sleep(poll_delay)
-                    continue
-
-        return True
-
-    # else:
-    #     # TODO: non-root call for #320?
-    #     this_uid: tuple[str, str] = current_actor().uid
-    #     async with acquire_debug_lock(
-    #         subactor_uid=this_uid,
-    #     ):
-    #         pass
-    return False
-
-
-@acm
-async def acquire_debug_lock(
-    subactor_uid: tuple[str, str],
-) -> AsyncGenerator[
-    trio.CancelScope|None,
-    tuple,
-]:
-    '''
-    Request to acquire the TTY `Lock` in the root actor, 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
-    process-tree root such that they don't clobber an ongoing pdb
-    REPL session in some peer or child!
-
-    '''
-    if not debug_mode():
-        yield None
-        return
-
-    task: Task = current_task()
-    async with trio.open_nursery() as n:
-        ctx: Context = await n.start(
-            partial(
-                request_root_stdio_lock,
-                actor_uid=subactor_uid,
-                task_uid=(task.name, id(task)),
-            )
-        )
-        yield ctx
-        ctx.cancel()