Add a `thread_ui: str` to record headers

Again using `Channel.aid.reprol()`, `.devx.pformat.nest_from_op()` and
 converting to multi-line code style an ' for str-report-contents. Tweak
 some imports to sub-mod level as well.

.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: '3.11'
+
+      - 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: '3.11'
 
-      - 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: ['3.11']
         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.

docs/README.rst

@@ -1,5 +1,8 @@
 |logo| ``tractor``: distributed structurred concurrency
 
+|gh_actions|
+|docs|
+
 ``tractor`` is a `structured concurrency`_ (SC), multi-processing_ runtime built on trio_.
 
 Fundamentally, ``tractor`` provides parallelism via
@@ -63,13 +66,6 @@ Features
   - (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
@@ -693,11 +689,9 @@ channel`_!
 .. _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
 
-..
-   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 +62,9 @@ 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(
+            strict_exception_groups=False,
+        ) as tn,
     ):
         async for i in stream:
             print(f'child echoing {i}')

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/quick_cluster.py

@@ -23,8 +23,9 @@ async def main():
             modules=[__name__]
         ) as portal_map,
 
-        tractor.trionics.collapse_eg(),
-        trio.open_nursery() as tn,
+        trio.open_nursery(
+            strict_exception_groups=False,
+        ) as tn,
     ):
 
         for (name, portal) in portal_map.items():

examples/threading/bg_thread_as_gen.py

@@ -0,0 +1,360 @@
+# 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 shm-thread-as-generator-fn-ctx **prototype** in anticipation of
+free-threading (aka GIL-less threads) in py 3.13+
+
+Bo
+
+Main rationale,
+- binding a bg-thread to a "suspendable fn scope" means avoiding any
+  locking around shm-data-structures and, except for a single
+  `threading.Condition` (or better) for thread-context-switching,
+  enables a "pure-ish" style semantic for inter-thread
+  value-passing-IO between a "parent" and (bg) "child" shm-thread
+  where the only (allowed) data-flow would be via immutable values in
+  a "coroutine-style" using,
+
+  - parent-side:
+   |_ `callee_sent = gen.send(caller_sent)`
+
+  - child-side:
+   |_ `caller_sent = yield callee_sent`
+
+Related (official) reading,
+- https://docs.python.org/3/glossary.html#term-free-threading
+- https://peps.python.org/pep-0703/
+ |_https://peps.python.org/pep-0703/#optimistic-avoiding-locking-in-dict-and-list-accesses
+
+
+'''
+from contextlib import (
+    contextmanager as cm,
+)
+import inspect
+# from functools import partial
+import time
+import threading
+from typing import (
+    Any,
+    Generator,
+)
+
+import tractor
+import trio
+
+
+log = tractor.log.get_console_log(
+    'info',
+    # ^ XXX causes latency with seed>=1e3
+    # 'warning',
+)
+_seed: int = int(1e3)
+
+
+def thread_gen(seed: int):
+    thr = threading.current_thread()
+    log.info(
+        f'thr: {thr.name} @ {thr.ident}\n'
+        f'    |_{thr!r}\n'
+        f'\n'
+        f'IN `thread_gen(seed={seed})`\n'
+        f'\n'
+        f'Starting range()-loop\n'
+    )
+    for i in range(seed):
+        log.info(
+            f'yielding i={i}\n'
+        )
+        from_main = yield i
+        log.info(
+            f'(from_main := {from_main}) = yield (i:={i})\n'
+        )
+        # time.sleep(0.0001)
+
+
+# TODO, how would we get the equiv from a pub trio-API?
+# -[ ] what about an inter-thread channel much like we have for
+# `to_asyncio` & guest mode??
+#
+# async def spawn_bg_thread_running_gen(fn):
+#     log.info('running trio.to_thread.run_sync()')
+#     await trio.to_thread.run_sync(
+#        partial(
+#          run_gen_in_thread,
+#          fn=fn,
+#          seed=_seed,
+#         )
+#     )
+
+
+# ?TODO? once correct, wrap this as a @deco-API?
+# -[ ] @generator_thread or similar?
+#
+def run_gen_in_thread(
+    cond: threading.Condition,
+    gen: Generator,
+    # ^NOTE, already closure-bound-in tgt generator-fn-instance which
+    # will be yielded to in the bg-thread!
+):
+    thr: threading.Thread = threading.current_thread()
+    log.info(
+        f'thr: {thr.name} @ {thr.ident}\n'
+        f'    |_{thr!r}\n'
+        f'\n'
+        f'IN `run_gen_in_thread(gen={gen})`\n'
+        f'\n'
+        f'entering gen blocking: {gen!r}\n'
+    )
+    try:
+        log.runtime('locking cond..')
+        with cond:
+            log.runtime('LOCKED cond..')
+            first_yielded = gen.send(None)
+            assert cond.to_yield is None
+            cond.to_yield = first_yielded
+            log.runtime('notifying cond..')
+            cond.notify()
+            log.runtime('waiting cond..')
+            cond.wait()
+
+            while (to_send := cond.to_send) is not None:
+                try:
+                    yielded = gen.send(to_send)
+                except StopIteration as siter:
+                    # TODO, check for return value?
+                    # if (ret := siter.value):
+                    #     cond.to_return = ret
+                    assert siter
+                    log.exception(f'{gen} exited')
+                    raise
+
+                cond.to_yield = yielded
+                log.runtime('LOOP notifying cond..')
+                cond.notify()
+                log.runtime('LOOP waiting cond..')
+                cond.wait()
+
+            # out = (yield from gen)
+            log.runtime('RELEASE-ing cond..')
+
+        # with cond block-end
+        log.runtime('RELEASE-ed cond..')
+
+    except BaseException:
+        log.exception(f'exited gen: {gen!r}\n')
+        raise
+
+    finally:
+        log.warning(
+            'Exiting bg thread!\n'
+        )
+        # TODO! better then this null setting naivety!
+        # -[ ] maybe an Unresolved or similar like for our `Context`?
+        #
+        # apply sentinel
+        cond.to_yield = None
+        with cond:
+            cond.notify_all()
+
+@cm
+def start_in_bg_thread(
+    gen: Generator,
+
+    # ?TODO?, is this useful to pass startup-ctx to the thread?
+    name: str|None = None,
+    **kwargs,
+
+) -> tuple[
+    threading.Thread,
+    Generator,
+    Any,
+]:
+    if not inspect.isgenerator(gen):
+        raise ValueError(
+            f'You must pass a `gen: Generator` instance\n'
+            f'gen={gen!r}\n'
+        )
+
+    # ?TODO? wrap this stuff into some kinda
+    # single-entry-inter-thread mem-chan?
+    #
+    cond = threading.Condition()
+    cond.to_send = None
+    cond.to_yield = None
+    cond.to_return = None
+
+    thr = threading.Thread(
+        target=run_gen_in_thread,
+        # args=(),  # ?TODO, useful?
+        kwargs={
+            'cond': cond,
+            'gen': gen,
+        } | kwargs,
+        name=name or gen.__name__,
+    )
+    log.info(
+        f'starting bg thread\n'
+        f'>(\n'
+        f'|_{thr!r}\n'
+    )
+    thr.start()
+
+    # TODO, Event or cond.wait() here to sync!?
+    time.sleep(0.01)
+
+    try:
+        log.info(f'locking cond {cond}..')
+        with cond:
+            log.runtime(f'LOCKED cond {cond}..')
+            first_yielded = cond.to_yield
+            log.runtime(f'cond.to_yield: {first_yielded}')
+
+            # delegator shim generator which proxies values from
+            # caller to callee-in-bg-thread
+            def wrapper():
+
+                # !?TODO, minimize # of yields during startup?
+                # -[ ] we can do i in <=1 manual yield pre while-loop no?
+                #
+                first_sent = yield first_yielded
+                cond.to_send = first_sent
+
+                # !TODO, exactly why we need a conditional-emit-sys!
+                log.runtime(
+                    f'cond.notify()\n'
+                    f'cond.to_send={cond.to_send!r}\n'
+                    f'cond.to_yield={cond.to_yield!r}\n'
+                )
+                cond.notify()
+                log.runtime(
+                    f'cond.wait()\n'
+                    f'cond.to_send={cond.to_send!r}\n'
+                    f'cond.to_yield={cond.to_yield!r}\n'
+                )
+                cond.wait()
+
+                to_yield = cond.to_yield
+                log.runtime(
+                    f'yielding to caller\n'
+                    f'cond.to_send={cond.to_send!r}\n'
+                    f'cond.to_yield={cond.to_yield!r}\n'
+                )
+                to_send = yield to_yield
+                log.runtime(
+                    f'post-yield to caller\n'
+                    f'to_send={to_send!r}\n'
+                    f'to_yield={to_yield!r}\n'
+                )
+
+                # !TODO, proper sentinel-to-break type-condition!
+                while to_send is not None:
+                    cond.to_send = to_send
+                    log.runtime(
+                        f'cond.nofity()\n'
+                        f'cond.to_send={cond.to_send!r}\n'
+                        f'cond.to_yield={cond.to_yield!r}\n'
+                    )
+                    cond.notify()
+                    if cond.to_yield is None:
+                        log.runtime(
+                            'BREAKING from wrapper-LOOP!\n'
+                        )
+                        break
+                        return
+
+                    log.runtime(
+                        f'cond.wait()\n'
+                        f'cond.to_send={cond.to_send!r}\n'
+                        f'cond.to_yield={cond.to_yield!r}\n'
+                    )
+                    cond.wait()
+
+                    log.runtime(
+                        f'yielding to caller\n'
+                        f'cond.to_send={cond.to_send!r}\n'
+                        f'cond.to_yield={cond.to_yield!r}\n'
+                    )
+                    to_yield = cond.to_yield
+                    to_send = yield to_yield
+                    log.runtime(
+                        f'post-yield to caller\n'
+                        f'to_send={to_send!r}\n'
+                        f'to_yield={to_yield!r}\n'
+                    )
+
+            log.info('creating wrapper..')
+            wrapper_gen = wrapper()
+            log.info(f'first .send(None): {wrapper_gen}\n')
+            first_yielded = wrapper_gen.send(None)
+            log.info(f'first yielded: {first_yielded}\n')
+
+            yield (
+                thr,
+                wrapper_gen,
+                first_yielded,
+            )
+    finally:
+        thr.join()
+        log.info(f'bg thread joined: {thr!r}')
+
+
+async def main():
+    async with trio.open_nursery() as tn:
+        assert tn
+
+        with (
+            start_in_bg_thread(
+                gen=(
+                    _gen:=thread_gen(
+                        seed=_seed,
+                    )
+                ),
+            ) as (
+                thr,
+                wrapped_gen,
+                first,
+            ),
+        ):
+            assert (
+                _gen is not wrapped_gen
+                and
+                wrapped_gen is not None
+            )
+            log.info(
+                'Entering wrapped_gen loop\n'
+            )
+
+            # NOTE, like our `Context.started` value
+            assert first == 0
+
+            # !TODO, proper sentinel-to-break type-condition!
+            yielded = first
+            while yielded is not None:
+
+                # XXX, compute callers new value to send to bg-thread
+                to_send = yielded * yielded
+
+                # send to bg-thread
+                yielded = wrapped_gen.send(to_send)
+                log.info(
+                    f'(yielded:={yielded!r}) = wrapped_gen.send((to_send:={to_send!r})'
+                )
+
+
+if __name__ == '__main__':
+    trio.run(main)

pyproject.toml

@@ -61,9 +61,7 @@ dev = [
   # `tractor.devx` tooling
   "greenback>=1.2.1,<2",
   "stackscope>=0.2.2,<0.3",
-  # ^ requires this?
-  "typing-extensions>=4.14.1",
-
+  "typing-extensions>=4.13.2",  # needed for stackscope
   "pyperclip>=1.9.0",
   "prompt-toolkit>=3.0.50",
   "xonsh>=0.19.2",

tests/devx/test_debugger.py

@@ -1,13 +1,13 @@
 """
 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
@@ -925,7 +925,6 @@ def test_post_mortem_api(
             "<Task 'name_error'",
             "NameError",
             "('child'",
-            'getattr(doggypants)',  # exc-LoC
         ]
     )
     if ctlc:
@@ -942,8 +941,8 @@ 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 +960,6 @@ 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:
@@ -1156,54 +1151,6 @@ def test_ctxep_pauses_n_maybe_ipc_breaks(
             )
 
 
-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

tests/devx/test_tooling.py

@@ -14,9 +14,6 @@ TODO:
 
 '''
 from __future__ import annotations
-from contextlib import (
-    contextmanager as cm,
-)
 import os
 import signal
 import time
@@ -31,8 +28,6 @@ from .conftest import (
     PROMPT,
     _pause_msg,
 )
-
-import pytest
 from pexpect.exceptions import (
     # TIMEOUT,
     EOF,
@@ -190,117 +185,3 @@ def test_breakpoint_hook_restored(
     )
     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/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/test_advanced_streaming.py

@@ -313,8 +313,9 @@ async def inf_streamer(
         # `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,
+        trio.open_nursery(
+            strict_exception_groups=False,
+        ) as tn,
     ):
         async def close_stream_on_sentinel():
             async for msg in stream:

tests/test_cancellation.py

@@ -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?")
 
@@ -535,15 +519,10 @@ 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(
+                strict_exception_groups=False,
+            ) 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 +533,38 @@ 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):

tests/test_child_manages_service_nursery.py

@@ -117,10 +117,9 @@ async def open_actor_local_nursery(
     ctx: tractor.Context,
 ):
     global _nursery
-    async with (
-        tractor.trionics.collapse_eg(),
-        trio.open_nursery() as tn
-    ):
+    async with trio.open_nursery(
+        strict_exception_groups=False,
+    ) as tn:
         _nursery = tn
         await ctx.started()
         await trio.sleep(10)

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_discovery.py

@@ -11,7 +11,6 @@ import psutil
 import pytest
 import subprocess
 import tractor
-from tractor.trionics import collapse_eg
 from tractor._testing import tractor_test
 import trio
 
@@ -194,10 +193,10 @@ async def spawn_and_check_registry(
 
             try:
                 async with tractor.open_nursery() as an:
-                    async with (
-                        collapse_eg(),
-                        trio.open_nursery() as trion,
-                    ):
+                    async with trio.open_nursery(
+                        strict_exception_groups=False,
+                    ) as trion:
+
                         portals = {}
                         for i in range(3):
                             name = f'a{i}'
@@ -339,12 +338,11 @@ 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(
+                                strict_exception_groups=False,
+                            ) as n:
+                                n.start_soon(streamer, agen1)
+                                n.start_soon(cancel, use_signal, .5)
                                 try:
                                     await streamer(agen2)
                                 finally:

tests/test_infected_asyncio.py

@@ -234,8 +234,10 @@ async def trio_ctx(
     with trio.fail_after(1 + delay):
         try:
             async with (
-                tractor.trionics.collapse_eg(),
-                trio.open_nursery() as tn,
+                trio.open_nursery(
+                    # TODO, for new `trio` / py3.13
+                    # strict_exception_groups=False,
+                ) as tn,
                 tractor.to_asyncio.open_channel_from(
                     sleep_and_err,
                 ) as (first, chan),
@@ -571,16 +573,14 @@ def test_basic_interloop_channel_stream(
     fan_out: bool,
 ):
     async def main():
-        # TODO, figure out min timeout here!
-        with trio.fail_after(6):
-            async with tractor.open_nursery() as an:
-                portal = await an.run_in_actor(
-                    stream_from_aio,
-                    infect_asyncio=True,
-                    fan_out=fan_out,
-                )
-                # should raise RAE diectly
-                await portal.result()
+        async with tractor.open_nursery() as an:
+            portal = await an.run_in_actor(
+                stream_from_aio,
+                infect_asyncio=True,
+                fan_out=fan_out,
+            )
+            # should raise RAE diectly
+            await portal.result()
 
     trio.run(main)
 
@@ -1088,108 +1088,6 @@ def test_sigint_closes_lifetime_stack(
     trio.run(main)
 
 
-
-# ?TODO asyncio.Task fn-deco?
-# -[ ] do sig checkingat import time like @context?
-# -[ ] maybe name it @aio_task ??
-# -[ ] chan: to_asyncio.InterloopChannel ??
-async def raise_before_started(
-    # from_trio: asyncio.Queue,
-    # to_trio: trio.abc.SendChannel,
-    chan: to_asyncio.LinkedTaskChannel,
-
-) -> None:
-    '''
-    `asyncio.Task` entry point which RTEs before calling
-    `to_trio.send_nowait()`.
-
-    '''
-    await asyncio.sleep(0.2)
-    raise RuntimeError('Some shite went wrong before `.send_nowait()`!!')
-
-    # to_trio.send_nowait('Uhh we shouldve RTE-d ^^ ??')
-    chan.started_nowait('Uhh we shouldve RTE-d ^^ ??')
-    await asyncio.sleep(float('inf'))
-
-
-@tractor.context
-async def caching_ep(
-    ctx: tractor.Context,
-):
-
-    log = tractor.log.get_logger('caching_ep')
-    log.info('syncing via `ctx.started()`')
-    await ctx.started()
-
-    # XXX, allocate the `open_channel_from()` inside
-    # a `.trionics.maybe_open_context()`.
-    chan: to_asyncio.LinkedTaskChannel
-    async with (
-        tractor.trionics.maybe_open_context(
-            acm_func=tractor.to_asyncio.open_channel_from,
-            kwargs={
-                'target': raise_before_started,
-                # ^XXX, kwarg to `open_channel_from()`
-            },
-
-            # lock around current actor task access
-            key=tractor.current_actor().uid,
-
-        ) as (cache_hit, (clients, chan)),
-    ):
-        if cache_hit:
-            log.error(
-                'Re-using cached `.open_from_channel()` call!\n'
-            )
-
-        else:
-            log.info(
-                'Allocating SHOULD-FAIL `.open_from_channel()`\n'
-            )
-
-        await trio.sleep_forever()
-
-
-def test_aio_side_raises_before_started(
-    reg_addr: tuple[str, int],
-    debug_mode: bool,
-    loglevel: str,
-):
-    '''
-    Simulates connection-err from `piker.brokers.ib.api`..
-
-    Ensure any error raised by child-`asyncio.Task` BEFORE
-    `chan.started()`
-
-    '''
-    # delay = 999 if debug_mode else 1
-    async def main():
-        with trio.fail_after(3):
-            an: tractor.ActorNursery
-            async with tractor.open_nursery(
-                debug_mode=debug_mode,
-                loglevel=loglevel,
-            ) as an:
-                p: tractor.Portal = await an.start_actor(
-                    'lchan_cacher_that_raises_fast',
-                    enable_modules=[__name__],
-                    infect_asyncio=True,
-                )
-                async with p.open_context(
-                    caching_ep,
-                ) as (ctx, first):
-                    assert not first
-
-    with pytest.raises(
-        expected_exception=(RemoteActorError),
-    ) as excinfo:
-        trio.run(main)
-
-    # ensure `asyncio.Task` exception is bubbled
-    # allll the way erp!!
-    rae = excinfo.value
-    assert rae.boxed_type is RuntimeError
-
 # TODO: debug_mode tests once we get support for `asyncio`!
 #
 # -[ ] need tests to wrap both scripts:

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_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)
@@ -110,34 +98,23 @@ async def streamer(
 
 
 @acm
-async def open_stream() -> Awaitable[
-    tuple[
-        tractor.ActorNursery,
-        tractor.MsgStream,
-    ]
-]:
+async def open_stream() -> Awaitable[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 with (
+                portal.open_context(streamer) as (ctx, first),
+                ctx.open_stream() as stream,
+            ):
+                yield stream
 
-            finally:
-                print(
-                    'Cancelling streamer with,\n'
-                    '=> `Portal.cancel_actor()`'
-                )
-                await portal.cancel_actor()
-                print('Cancelled streamer')
+            print('Cancelling streamer')
+            await portal.cancel_actor()
+            print('Cancelled streamer')
 
     except Exception as err:
         print(
@@ -150,15 +127,11 @@ async def open_stream() -> Awaitable[
 
 @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')
 
@@ -166,43 +139,10 @@ 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(
@@ -219,24 +159,16 @@ def test_open_local_sub_to_stream(
 
     if debug_mode:
         timeout = 999
-        print(f'IN debug_mode, setting large timeout={timeout!r}..')
 
     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 +180,34 @@ 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:
             # 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 (
                     trio.open_nursery() as tn,
                 ):
-                    for i in range(num_tasks):
+                    for i in range(10):
                         tn.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.')
+                print('all consumer tasks finished')
 
         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,
-                    )
-
-
     trio.run(main)

tests/test_root_infect_asyncio.py

@@ -147,7 +147,8 @@ def test_trio_prestarted_task_bubbles(
         await trio.sleep_forever()
 
     async def _trio_main():
-        with trio.fail_after(2 if not debug_mode else 999):
+        # with trio.fail_after(2):
+        with trio.fail_after(999):
             first: str
             chan: to_asyncio.LinkedTaskChannel
             aio_ev = asyncio.Event()
@@ -216,25 +217,32 @@ def test_trio_prestarted_task_bubbles(
                         ):
                             aio_ev.set()
 
+    with pytest.raises(
+        expected_exception=ExceptionGroup,
+    ) as excinfo:
+        tractor.to_asyncio.run_as_asyncio_guest(
+            trio_main=_trio_main,
+        )
+
+    eg = excinfo.value
+    rte_eg, rest_eg = eg.split(RuntimeError)
+
     # ensure the trio-task's error bubbled despite the aio-side
     # having (maybe) errored first.
     if aio_err_trigger in (
         'after_trio_task_starts',
         'after_start_point',
     ):
-        patt: str = 'trio-side'
-        expect_exc = TypeError
+        assert len(errs := rest_eg.exceptions) == 1
+        typerr = errs[0]
+        assert (
+            type(typerr) is TypeError
+            and
+            'trio-side' in typerr.args
+        )
 
     # when aio errors BEFORE (last) trio task is scheduled, we should
     # never see anythinb but the aio-side.
     else:
-        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
+        assert len(rtes := rte_eg.exceptions) == 1
+        assert 'asyncio-side' in rtes[0].args[0]

tests/test_trioisms.py

@@ -8,7 +8,6 @@ from contextlib import (
 )
 
 import pytest
-from tractor.trionics import collapse_eg
 import trio
 from trio import TaskStatus
 
@@ -65,8 +64,9 @@ def test_stashed_child_nursery(use_start_soon):
     async def main():
 
         async with (
-            collapse_eg(),
-            trio.open_nursery() as pn,
+            trio.open_nursery(
+                strict_exception_groups=False,
+            ) as pn,
         ):
             cn = await pn.start(mk_child_nursery)
             assert cn
@@ -197,8 +197,10 @@ def test_gatherctxs_with_memchan_breaks_multicancelled(
         async with (
             # XXX should ensure ONLY the KBI
             # is relayed upward
-            collapse_eg(),
-            trio.open_nursery(), # as tn,
+            trionics.collapse_eg(),
+            trio.open_nursery(
+                # strict_exception_groups=False,
+            ), # as tn,
 
             trionics.gather_contexts([
                 open_memchan(),

tractor/_clustering.py

@@ -55,17 +55,10 @@ 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 +69,9 @@ 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/_context.py

@@ -154,7 +154,7 @@ class Context:
     2 cancel-scope-linked, communicating and parallel executing
     `Task`s. Contexts are allocated on each side of any task
     RPC-linked msg dialog, i.e. for every request to a remote
-    actor from a `Portal`. On the "child" side a context is
+    actor from a `Portal`. On the "callee" side a context is
     always allocated inside `._rpc._invoke()`.
 
     TODO: more detailed writeup on cancellation, error and
@@ -222,8 +222,8 @@ class Context:
     # `._runtime.invoke()`.
     _remote_func_type: str | None = None
 
-    # NOTE: (for now) only set (a portal) on the parent side since
-    # the child doesn't generally need a ref to one and should
+    # NOTE: (for now) only set (a portal) on the caller side since
+    # the callee doesn't generally need a ref to one and should
     # normally need to explicitly ask for handle to its peer if
     # more the the `Context` is needed?
     _portal: Portal | None = None
@@ -252,12 +252,12 @@ class Context:
     _outcome_msg: Return|Error|ContextCancelled = Unresolved
 
     # on a clean exit there should be a final value
-    # delivered from the far end "child" task, so
+    # delivered from the far end "callee" task, so
     # this value is only set on one side.
     # _result: Any | int = None
     _result: PayloadT|Unresolved = Unresolved
 
-    # if the local "parent"  task errors this value is always set
+    # if the local "caller"  task errors this value is always set
     # to the error that was captured in the
     # `Portal.open_context().__aexit__()` teardown block OR, in
     # 2 special cases when an (maybe) expected remote error
@@ -293,7 +293,7 @@ class Context:
     # a `ContextCancelled` due to a call to `.cancel()` triggering
     # "graceful closure" on either side:
     # - `._runtime._invoke()` will check this flag before engaging
-    #   the crash handler REPL in such cases where the "child"
+    #   the crash handler REPL in such cases where the "callee"
     #   raises the cancellation,
     # - `.devx.debug.lock_stdio_for_peer()` will set it to `False` if
     #   the global tty-lock has been configured to filter out some
@@ -307,8 +307,8 @@ class Context:
     _stream_opened: bool = False
     _stream: MsgStream|None = None
 
-    # the parent-task's calling-fn's frame-info, the frame above
-    # `Portal.open_context()`, for introspection/logging.
+    # caller of `Portal.open_context()` for
+    # logging purposes mostly
     _caller_info: CallerInfo|None = None
 
     # overrun handling machinery
@@ -529,11 +529,11 @@ class Context:
         '''
         Exactly the value of `self._scope.cancelled_caught`
         (delegation) and should only be (able to be read as)
-        `True` for a `.side == "parent"` ctx wherein the
+        `True` for a `.side == "caller"` ctx wherein the
         `Portal.open_context()` block was exited due to a call to
         `._scope.cancel()` - which should only ocurr in 2 cases:
 
-        - a parent side calls `.cancel()`, the far side cancels
+        - a caller side calls `.cancel()`, the far side cancels
           and delivers back a `ContextCancelled` (making
           `.cancel_acked == True`) and `._scope.cancel()` is
           called by `._maybe_cancel_and_set_remote_error()` which
@@ -542,20 +542,20 @@ class Context:
           => `._scope.cancelled_caught == True` by normal `trio`
           cs semantics.
 
-        - a parent side is delivered a `._remote_error:
+        - a caller side is delivered a `._remote_error:
           RemoteActorError` via `._deliver_msg()` and a transitive
           call to `_maybe_cancel_and_set_remote_error()` calls
           `._scope.cancel()` and that cancellation eventually
           results in `trio.Cancelled`(s) caught in the
           `.open_context()` handling around the @acm's `yield`.
 
-        Only as an FYI, in the "child" side case it can also be
+        Only as an FYI, in the "callee" side case it can also be
         set but never is readable by any task outside the RPC
         machinery in `._invoke()` since,:
-        - when a child side calls `.cancel()`, `._scope.cancel()`
+        - when a callee side calls `.cancel()`, `._scope.cancel()`
           is called immediately and handled specially inside
           `._invoke()` to raise a `ContextCancelled` which is then
-          sent to the parent side.
+          sent to the caller side.
 
           However, `._scope.cancelled_caught` can NEVER be
           accessed/read as `True` by any RPC invoked task since it
@@ -666,7 +666,7 @@ class Context:
         when called/closed by actor local task(s).
 
         NOTEs: 
-          - It is expected that the parent has previously unwrapped
+          - It is expected that the caller has previously unwrapped
             the remote error using a call to `unpack_error()` and
             provides that output exception value as the input
             `error` argument *here*.
@@ -676,7 +676,7 @@ class Context:
             `Portal.open_context()` (ideally) we want to interrupt
             any ongoing local tasks operating within that
             `Context`'s cancel-scope so as to be notified ASAP of
-            the remote error and engage any parent handling (eg.
+            the remote error and engage any caller handling (eg.
             for cross-process task supervision).
 
           - In some cases we may want to raise the remote error
@@ -886,11 +886,6 @@ class Context:
 
     @property
     def repr_caller(self) -> str:
-        '''
-        Render a "namespace-path" style representation of the calling
-        task-fn.
-
-        '''
         ci: CallerInfo|None = self._caller_info
         if ci:
             return (
@@ -904,7 +899,7 @@ class Context:
     def repr_api(self) -> str:
         return 'Portal.open_context()'
 
-        # TODO: use `.dev._frame_stack` scanning to find caller fn!
+        # TODO: use `.dev._frame_stack` scanning to find caller!
         # ci: CallerInfo|None = self._caller_info
         # if ci:
         #     return (
@@ -939,7 +934,7 @@ class Context:
         => That is, an IPC `Context` (this) **does not**
            have the same semantics as a `trio.CancelScope`.
 
-        If the parent (who entered the `Portal.open_context()`)
+        If the caller (who entered the `Portal.open_context()`)
         desires that the internal block's cancel-scope  be
         cancelled it should open its own `trio.CancelScope` and
         manage it as needed.
@@ -1011,6 +1006,7 @@ class Context:
                 else:
                     log.cancel(
                         f'Timed out on cancel request of remote task?\n'
+                        f'\n'
                         f'{reminfo}'
                     )
 
@@ -1021,7 +1017,7 @@ class Context:
         # `_invoke()` RPC task.
         #
         # NOTE: on this side we ALWAYS cancel the local scope
-        # since the parent expects a `ContextCancelled` to be sent
+        # since the caller expects a `ContextCancelled` to be sent
         # from `._runtime._invoke()` back to the other side. The
         # logic for catching the result of the below
         # `._scope.cancel()` is inside the `._runtime._invoke()`
@@ -1194,8 +1190,8 @@ class Context:
 
     ) -> Any|Exception:
         '''
-        From some (parent) side task, wait for and return the final
-        result from the remote (child) side's task.
+        From some (caller) side task, wait for and return the final
+        result from the remote (callee) side's task.
 
         This provides a mechanism for one task running in some actor to wait
         on another task at the other side, in some other actor, to terminate.
@@ -1491,12 +1487,6 @@ class Context:
                 ):
                     status = 'peer-cancelled'
 
-            case (
-                Unresolved,
-                trio.Cancelled(),  # any error-type
-            ) if self.canceller:
-                status = 'actor-cancelled'
-
             # (remote) error condition
             case (
                 Unresolved,
@@ -1610,7 +1600,7 @@ class Context:
                 raise err
 
         # TODO: maybe a flag to by-pass encode op if already done
-        # here in parent?
+        # here in caller?
         await self.chan.send(started_msg)
 
         # set msg-related internal runtime-state
@@ -1686,7 +1676,7 @@ class Context:
 
          XXX RULES XXX
         ------ - ------
-        - NEVER raise remote errors from this method; a calling runtime-task.
+        - NEVER raise remote errors from this method; a runtime task caller.
           An error "delivered" to a ctx should always be raised by
           the corresponding local task operating on the
           `Portal`/`Context` APIs.
@@ -1762,7 +1752,7 @@ class Context:
 
             else:
                 report = (
-                    'Queueing OVERRUN msg on parent task:\n\n'
+                    'Queueing OVERRUN msg on caller task:\n\n'
                     + report
                 )
                 log.debug(report)
@@ -1958,12 +1948,12 @@ async def open_context_from_portal(
     IPC protocol.
 
     The yielded `tuple` is a pair delivering a `tractor.Context`
-    and any first value "sent" by the "child" task via a call
+    and any first value "sent" by the "callee" task via a call
     to `Context.started(<value: Any>)`; this side of the
-    context does not unblock until the "child" task calls
+    context does not unblock until the "callee" task calls
     `.started()` in similar style to `trio.Nursery.start()`.
-    When the "child" (side that is "called"/started by a call
-    to *this* method) returns, the parent side (this) unblocks
+    When the "callee" (side that is "called"/started by a call
+    to *this* method) returns, the caller side (this) unblocks
     and any final value delivered from the other end can be
     retrieved using the `Contex.wait_for_result()` api.
 
@@ -1976,7 +1966,7 @@ async def open_context_from_portal(
     __tracebackhide__: bool = hide_tb
 
     # denote this frame as a "runtime frame" for stack
-    # introspection where we report the parent code in logging
+    # introspection where we report the caller code in logging
     # and error message content.
     # NOTE: 2 bc of the wrapping `@acm`
     __runtimeframe__: int = 2  # noqa
@@ -2035,7 +2025,7 @@ async def open_context_from_portal(
     # placeholder for any exception raised in the runtime
     # or by user tasks which cause this context's closure.
     scope_err: BaseException|None = None
-    ctxc_from_child: ContextCancelled|None = None
+    ctxc_from_callee: ContextCancelled|None = None
     try:
         async with (
             collapse_eg(),
@@ -2114,7 +2104,7 @@ async def open_context_from_portal(
             # that we can re-use it around the `yield` ^ here
             # or vice versa?
             #
-            # maybe TODO NOTE: between the parent exiting and
+            # maybe TODO NOTE: between the caller exiting and
             # arriving here the far end may have sent a ctxc-msg or
             # other error, so the quetion is whether we should check
             # for it here immediately and maybe raise so as to engage
@@ -2180,16 +2170,16 @@ async def open_context_from_portal(
     #   request in which case we DO let the error bubble to the
     #   opener.
     #
-    # 2-THIS "parent" task somewhere invoked `Context.cancel()`
-    #   and received a `ContextCanclled` from the "child"
+    # 2-THIS "caller" task somewhere invoked `Context.cancel()`
+    #   and received a `ContextCanclled` from the "callee"
     #   task, in which case we mask the `ContextCancelled` from
-    #   bubbling to this "parent" (much like how `trio.Nursery`
+    #   bubbling to this "caller" (much like how `trio.Nursery`
     #   swallows any `trio.Cancelled` bubbled by a call to
     #   `Nursery.cancel_scope.cancel()`)
     except ContextCancelled as ctxc:
         scope_err = ctxc
         ctx._local_error: BaseException = scope_err
-        ctxc_from_child = ctxc
+        ctxc_from_callee = ctxc
 
         # XXX TODO XXX: FIX THIS debug_mode BUGGGG!!!
         # using this code and then resuming the REPL will
@@ -2226,11 +2216,11 @@ async def open_context_from_portal(
     # the above `._scope` can be cancelled due to:
     # 1. an explicit self cancel via `Context.cancel()` or
     #    `Actor.cancel()`,
-    # 2. any "child"-side remote error, possibly also a cancellation
+    # 2. any "callee"-side remote error, possibly also a cancellation
     #    request by some peer,
-    # 3. any "parent" (aka THIS scope's) local error raised in the above `yield`
+    # 3. any "caller" (aka THIS scope's) local error raised in the above `yield`
     except (
-        # CASE 3: standard local error in this parent/yieldee
+        # CASE 3: standard local error in this caller/yieldee
         Exception,
 
         # CASES 1 & 2: can manifest as a `ctx._scope_nursery`
@@ -2244,9 +2234,9 @@ async def open_context_from_portal(
         #   any `Context._maybe_raise_remote_err()` call.
         #
         # 2.-`BaseExceptionGroup[ContextCancelled | RemoteActorError]`
-        #    from any error delivered from the "child" side
+        #    from any error delivered from the "callee" side
         #    AND a group-exc is only raised if there was > 1
-        #    tasks started *here* in the "parent" / opener
+        #    tasks started *here* in the "caller" / opener
         #    block. If any one of those tasks calls
         #    `.wait_for_result()` or `MsgStream.receive()`
         #    `._maybe_raise_remote_err()` will be transitively
@@ -2259,8 +2249,8 @@ async def open_context_from_portal(
         trio.Cancelled,  # NOTE: NOT from inside the ctx._scope
         KeyboardInterrupt,
 
-    ) as rent_err:
-        scope_err = rent_err
+    ) as caller_err:
+        scope_err = caller_err
         ctx._local_error: BaseException = scope_err
 
         # XXX: ALWAYS request the context to CANCEL ON any ERROR.
@@ -2270,7 +2260,7 @@ async def open_context_from_portal(
         # await debug.pause()
         # log.cancel(
         match scope_err:
-            case trio.Cancelled():
+            case trio.Cancelled:
                 logmeth = log.cancel
 
             # XXX explicitly report on any non-graceful-taskc cases
@@ -2278,7 +2268,7 @@ async def open_context_from_portal(
                 logmeth = log.exception
 
         logmeth(
-            f'ctx {ctx.side!r}-side exited with {ctx.repr_outcome()!r}\n'
+            f'ctx {ctx.side!r}-side exited with {ctx.repr_outcome()}\n'
         )
 
         if debug_mode():
@@ -2299,9 +2289,9 @@ async def open_context_from_portal(
                     'Calling `ctx.cancel()`!\n'
                 )
 
-        # we don't need to cancel the child if it already
+        # we don't need to cancel the callee if it already
         # told us it's cancelled ;p
-        if ctxc_from_child is None:
+        if ctxc_from_callee is None:
             try:
                 await ctx.cancel()
             except (
@@ -2332,8 +2322,8 @@ async def open_context_from_portal(
             # via a call to
             # `Context._maybe_cancel_and_set_remote_error()`.
             # As per `Context._deliver_msg()`, that error IS
-            # ALWAYS SET any time "child" side fails and causes
-            # "parent side" cancellation via a `ContextCancelled` here.
+            # ALWAYS SET any time "callee" side fails and causes "caller
+            # side" cancellation via a `ContextCancelled` here.
             try:
                 result_or_err: Exception|Any = await ctx.wait_for_result()
             except BaseException as berr:
@@ -2369,7 +2359,7 @@ async def open_context_from_portal(
                     )
                 case (None, _):
                     log.runtime(
-                        'Context returned final result from child task:\n'
+                        'Context returned final result from callee task:\n'
                         f'<= peer: {uid}\n'
                         f'  |_ {nsf}()\n\n'
 
@@ -2464,7 +2454,7 @@ async def open_context_from_portal(
                 )
 
             # TODO: should we add a `._cancel_req_received`
-            # flag to determine if the child manually called
+            # flag to determine if the callee manually called
             # `ctx.cancel()`?
             # -[ ] going to need a cid check no?
 
@@ -2520,7 +2510,7 @@ def mk_context(
     recv_chan: trio.MemoryReceiveChannel
     send_chan, recv_chan = trio.open_memory_channel(msg_buffer_size)
 
-    # TODO: only scan parent-info if log level so high!
+    # TODO: only scan caller-info if log level so high!
     from .devx._frame_stack import find_caller_info
     caller_info: CallerInfo|None = find_caller_info()
 

tractor/_discovery.py

@@ -51,6 +51,7 @@ from ._state import (
 
 if TYPE_CHECKING:
     from ._runtime import Actor
+    from .ipc._server import IPCServer
 
 
 log = get_logger(__name__)
@@ -82,7 +83,7 @@ async def get_registry(
         )
     else:
         # TODO: try to look pre-existing connection from
-        # `Server._peers` and use it instead?
+        # `IPCServer._peers` and use it instead?
         async with (
             _connect_chan(addr) as chan,
             open_portal(chan) as regstr_ptl,
@@ -113,23 +114,18 @@ def get_peer_by_name(
 ) -> list[Channel]|None:  # at least 1
     '''
     Scan for an existing connection (set) to a named actor
-    and return any channels from `Server._peers: dict`.
+    and return any channels from `IPCServer._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)
+    server: IPCServer = actor.ipc_server
+    to_scan: dict[tuple, list[Channel]] = server._peers.copy()
+    pchan: Channel|None = actor._parent_chan
+    if pchan:
+        to_scan[pchan.uid].append(pchan)
 
     for aid, chans in to_scan.items():
         _, peer_name = aid

tractor/_portal.py

@@ -300,7 +300,7 @@ class Portal:
         )
 
         # 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

tractor/_root.py

@@ -97,7 +97,7 @@ async def maybe_block_bp(
     ):
         logger.info(
             f'Found `greenback` installed @ {maybe_mod}\n'
-            f'Enabling `tractor.pause_from_sync()` support!\n'
+            'Enabling `tractor.pause_from_sync()` support!\n'
         )
         os.environ['PYTHONBREAKPOINT'] = (
             'tractor.devx.debug._sync_pause_from_builtin'
@@ -471,7 +471,7 @@ async def open_root_actor(
                     '-> Opening new registry @ '
                     +
                     '\n'.join(
-                        f'{addr}' for addr in reg_addrs
+                        f'@{addr}' for addr in reg_addrs
                     )
                 )
             logger.info(f'{report}\n')
@@ -481,11 +481,10 @@ async def open_root_actor(
                 collapse_eg(),
                 trio.open_nursery() as root_tn,
 
-                # ?TODO? finally-footgun below?
+                # XXX, 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
@@ -524,11 +523,6 @@ async def open_root_actor(
                         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 (
@@ -549,7 +543,7 @@ async def open_root_actor(
                     raise
 
                 finally:
-                    # NOTE/TODO?, not sure if we'll ever need this but it's
+                    # 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..')
@@ -568,7 +562,6 @@ async def open_root_actor(
                         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?

tractor/_rpc.py

@@ -384,7 +384,7 @@ async def _errors_relayed_via_ipc(
 
     # 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:
 
@@ -462,7 +462,7 @@ 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
@@ -642,7 +642,7 @@ async def _invoke(
             tn: Nursery
             rpc_ctx_cs: CancelScope
             async with (
-                collapse_eg(hide_tb=False),
+                collapse_eg(),
                 trio.open_nursery() as tn,
                 msgops.maybe_limit_plds(
                     ctx=ctx,
@@ -823,44 +823,24 @@ 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'
+                        f'\n'
+                        f'scope_error:\n'
+                        f'{scope_err!r}\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'\nwith final result {ctx.outcome!r}\n'
 
             logmeth(
                 f'{message}\n'
@@ -936,7 +916,7 @@ 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`)
@@ -961,7 +941,7 @@ async def process_messages(
 
     '''
     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?
@@ -1172,7 +1152,7 @@ async def process_messages(
                         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,
@@ -1312,7 +1292,7 @@ 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}'

tractor/_runtime.py

@@ -35,15 +35,6 @@ for running all lower level spawning, supervision and msging layers:
   SC-transitive RPC via scheduling of `trio` tasks.
 - registration of newly spawned actors with the discovery sys.
 
-Glossary:
---------
- - tn: a `trio.Nursery` or "task nursery".
- - an: an `ActorNursery` or "actor nursery".
- - root: top/parent-most scope/task/process/actor (or other runtime
-         primitive) in a hierarchical tree.
- - parent-ish: "higher-up" in the runtime-primitive hierarchy.
- - child-ish: "lower-down" in the runtime-primitive hierarchy.
-
 '''
 from __future__ import annotations
 from contextlib import (
@@ -85,7 +76,6 @@ from tractor.msg import (
 )
 from .trionics import (
     collapse_eg,
-    maybe_open_nursery,
 )
 from .ipc import (
     Channel,
@@ -183,11 +173,10 @@ class Actor:
 
     msg_buffer_size: int = 2**6
 
-    # nursery placeholders filled in by `async_main()`,
-    # - after fork for subactors.
-    # - during boot for the root actor.
-    _root_tn: Nursery|None = None
-    _service_tn: Nursery|None = None
+    # nursery placeholders filled in by `async_main()` after fork
+    _root_n: Nursery|None = None
+    _service_n: Nursery|None = None
+
     _ipc_server: _server.IPCServer|None = None
 
     @property
@@ -563,14 +552,6 @@ class Actor:
             )
             raise
 
-    # ?TODO, factor this meth-iface into a new `.rpc` subsys primitive?
-    # - _get_rpc_func(),
-    # - _deliver_ctx_payload(),
-    # - get_context(),
-    # - start_remote_task(),
-    # - cancel_rpc_tasks(),
-    # - _cancel_task(),
-    #
     def _get_rpc_func(self, ns, funcname):
         '''
         Try to lookup and return a target RPC func from the
@@ -1021,48 +1002,12 @@ class Actor:
         the RPC service nursery.
 
         '''
-        actor_repr: str = _pformat.nest_from_op(
-            input_op='>c(',
-            text=self.pformat(),
-            nest_indent=1,
-        )
-        log.cancel(
-            'Actor.cancel_soon()` was called!\n'
-            f'>> scheduling `Actor.cancel()`\n'
-            f'{actor_repr}'
-        )
-        assert self._service_tn
-        self._service_tn.start_soon(
+        assert self._service_n
+        self._service_n.start_soon(
             self.cancel,
             None,  # self cancel all rpc tasks
         )
 
-        # schedule a "canceller task" in the `._root_tn` once the
-        # `._service_tn` is fully shutdown; task waits for child-ish
-        # scopes to fully exit then finally cancels its parent,
-        # root-most, scope.
-        async def cancel_root_tn_after_services():
-            log.runtime(
-                'Waiting on service-tn to cancel..\n'
-                f'c>)\n'
-                f'|_{self._service_tn.cancel_scope!r}\n'
-            )
-            await self._cancel_complete.wait()
-            log.cancel(
-                f'`._service_tn` cancelled\n'
-                f'>c)\n'
-                f'|_{self._service_tn.cancel_scope!r}\n'
-                f'\n'
-                f'>> cancelling `._root_tn`\n'
-                f'c>(\n'
-                f' |_{self._root_tn.cancel_scope!r}\n'
-            )
-            self._root_tn.cancel_scope.cancel()
-
-        self._root_tn.start_soon(
-            cancel_root_tn_after_services
-        )
-
     @property
     def cancel_complete(self) -> bool:
         return self._cancel_complete.is_set()
@@ -1167,13 +1112,21 @@ class Actor:
                 await ipc_server.wait_for_shutdown()
 
             # cancel all rpc tasks permanently
-            if self._service_tn:
-                self._service_tn.cancel_scope.cancel()
+            if self._service_n:
+                self._service_n.cancel_scope.cancel()
 
         log_meth(msg)
         self._cancel_complete.set()
         return True
 
+    # XXX: hard kill logic if needed?
+    # def _hard_mofo_kill(self):
+    #     # If we're the root actor or zombied kill everything
+    #     if self._parent_chan is None:  # TODO: more robust check
+    #         root = trio.lowlevel.current_root_task()
+    #         for n in root.child_nurseries:
+    #             n.cancel_scope.cancel()
+
     async def _cancel_task(
         self,
         cid: str,
@@ -1305,7 +1258,7 @@ class Actor:
         '''
         Cancel all ongoing RPC tasks owned/spawned for a given
         `parent_chan: Channel` or simply all tasks (inside
-        `._service_tn`) when `parent_chan=None`.
+        `._service_n`) when `parent_chan=None`.
 
         '''
         tasks: dict = self._rpc_tasks
@@ -1408,13 +1361,25 @@ class Actor:
         '''
         return self.accept_addrs[0]
 
-    # TODO, this should delegate ONLY to the
-    # `._spawn_spec._runtime_vars: dict` / `._state` APIs?
-    #
-    # XXX, AH RIGHT that's why..
-    #   it's bc we pass this as a CLI flag to the child.py precisely
-    #   bc we need the bootstrapping pre `async_main()`.. but maybe
-    #   keep this as an impl deat and not part of the pub iface impl?
+    def get_parent(self) -> Portal:
+        '''
+        Return a `Portal` to our parent.
+
+        '''
+        assert self._parent_chan, "No parent channel for this actor?"
+        return Portal(self._parent_chan)
+
+    def get_chans(
+        self,
+        uid: tuple[str, str],
+
+    ) -> list[Channel]:
+        '''
+        Return all IPC channels to the actor with provided `uid`.
+
+        '''
+        return self._ipc_server._peers[uid]
+
     def is_infected_aio(self) -> bool:
         '''
         If `True`, this actor is running `trio` in guest mode on
@@ -1425,23 +1390,6 @@ class Actor:
         '''
         return self._infected_aio
 
-    # ?TODO, is this the right type for this method?
-    def get_parent(self) -> Portal:
-        '''
-        Return a `Portal` to our parent.
-
-        '''
-        assert self._parent_chan, "No parent channel for this actor?"
-        return Portal(self._parent_chan)
-
-    # XXX: hard kill logic if needed?
-    # def _hard_mofo_kill(self):
-    #     # If we're the root actor or zombied kill everything
-    #     if self._parent_chan is None:  # TODO: more robust check
-    #         root = trio.lowlevel.current_root_task()
-    #         for n in root.child_nurseries:
-    #             n.cancel_scope.cancel()
-
 
 async def async_main(
     actor: Actor,
@@ -1517,55 +1465,46 @@ async def async_main(
                     accept_addrs.append(addr.unwrap())
 
         assert accept_addrs
-
-        ya_root_tn: bool = bool(actor._root_tn)
-        ya_service_tn: bool = bool(actor._service_tn)
-
-        # NOTE, a top-most "root" nursery in each actor-process
-        # enables a lifetime priority for the IPC-channel connection
-        # with a sub-actor's immediate parent. I.e. this connection
-        # is kept alive as a resilient service connection until all
-        # other machinery has exited, cancellation of all
-        # embedded/child scopes have completed. This helps ensure
-        # a deterministic (and thus "graceful")
-        # first-class-supervision style teardown where a parent actor
-        # (vs. say peers) is always the last to be contacted before
-        # disconnect.
+        # The "root" nursery ensures the channel with the immediate
+        # parent is kept alive as a resilient service until
+        # cancellation steps have (mostly) occurred in
+        # a deterministic way.
         root_tn: trio.Nursery
         async with (
             collapse_eg(),
-            maybe_open_nursery(
-                nursery=actor._root_tn,
-            ) as root_tn,
+            trio.open_nursery() as root_tn,
         ):
-            if ya_root_tn:
-                assert root_tn is actor._root_tn
-            else:
-                actor._root_tn = root_tn
+            actor._root_n = root_tn
+            assert actor._root_n
 
             ipc_server: _server.IPCServer
             async with (
                 collapse_eg(),
-                maybe_open_nursery(
-                    nursery=actor._service_tn,
-                ) as service_tn,
+                trio.open_nursery() as service_nursery,
                 _server.open_ipc_server(
-                    parent_tn=service_tn,  # ?TODO, why can't this be the root-tn
-                    stream_handler_tn=service_tn,
+                    parent_tn=service_nursery,
+                    stream_handler_tn=service_nursery,
                 ) as ipc_server,
+                # ) as actor._ipc_server,
+                # ^TODO? prettier?
 
             ):
-                if ya_service_tn:
-                    assert service_tn is actor._service_tn
-                else:
-                    # This nursery is used to handle all inbound
-                    # connections to us such that if the TCP server
-                    # is killed, connections can continue to process
-                    # in the background until this nursery is cancelled.
-                    actor._service_tn = service_tn
-
-                # set after allocate
+                # This nursery is used to handle all inbound
+                # connections to us such that if the TCP server
+                # is killed, connections can continue to process
+                # in the background until this nursery is cancelled.
+                actor._service_n = service_nursery
                 actor._ipc_server = ipc_server
+                assert (
+                    actor._service_n
+                    and (
+                        actor._service_n
+                        is
+                        actor._ipc_server._parent_tn
+                        is
+                        ipc_server._stream_handler_tn
+                    )
+                )
 
                 # load exposed/allowed RPC modules
                 # XXX: do this **after** establishing a channel to the parent
@@ -1591,11 +1530,10 @@ async def async_main(
                 # - root actor: the ``accept_addr`` passed to this method
 
                 # TODO: why is this not with the root nursery?
-                # - see above that the `._service_tn` is what's used?
                 try:
                     eps: list = await ipc_server.listen_on(
                         accept_addrs=accept_addrs,
-                        stream_handler_nursery=service_tn,
+                        stream_handler_nursery=service_nursery,
                     )
                     log.runtime(
                         f'Booted IPC server\n'
@@ -1603,7 +1541,7 @@ async def async_main(
                     )
                     assert (
                         (eps[0].listen_tn)
-                        is not service_tn
+                        is not service_nursery
                     )
 
                 except OSError as oserr:
@@ -1765,7 +1703,7 @@ async def async_main(
 
         # XXX TODO but hard XXX
         # we can't actually do this bc the debugger uses the
-        # _service_tn to spawn the lock task, BUT, in theory if we had
+        # _service_n to spawn the lock task, BUT, in theory if we had
         # the root nursery surround this finally block it might be
         # actually possible to debug THIS machinery in the same way
         # as user task code?
@@ -1817,7 +1755,9 @@ async def async_main(
                 f'   {pformat(ipc_server._peers)}'
             )
             log.runtime(teardown_report)
-            await ipc_server.wait_for_no_more_peers()
+            await ipc_server.wait_for_no_more_peers(
+                shield=True,
+            )
 
         teardown_report += (
             '-]> all peer channels are complete.\n'

tractor/_spawn.py

@@ -236,6 +236,10 @@ async def hard_kill(
     # whilst also hacking on it XD
     # terminate_after: int = 99999,
 
+    # NOTE: for mucking with `.pause()`-ing inside the runtime
+    # whilst also hacking on it XD
+    # terminate_after: int = 99999,
+
 ) -> None:
     '''
     Un-gracefully terminate an OS level `trio.Process` after timeout.
@@ -297,23 +301,6 @@ 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'

tractor/_supervise.py

@@ -117,6 +117,7 @@ class ActorNursery:
             ]
         ] = {}
 
+        self.cancelled: bool = False
         self._join_procs = trio.Event()
         self._at_least_one_child_in_debug: bool = False
         self.errors = errors
@@ -134,53 +135,10 @@ class ActorNursery:
         # 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,
@@ -358,7 +316,7 @@ class ActorNursery:
 
         '''
         __runtimeframe__: int = 1  # noqa
-        self._cancel_called = True
+        self.cancelled = True
 
         # TODO: impl a repr for spawn more compact
         # then `._children`..
@@ -436,8 +394,6 @@ 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()
@@ -643,9 +599,8 @@ _shutdown_msg: str = (
     'Actor-runtime-shutdown'
 )
 
-
-@acm
 # @api_frame
+@acm
 async def open_nursery(
     *,  # named params only!
     hide_tb: bool = True,

tractor/devx/_stackscope.py

@@ -237,9 +237,9 @@ def enable_stack_on_sig(
     try:
         import stackscope
     except ImportError:
-        log.warning(
-            'The `stackscope` lib is not installed!\n'
-            '`Ignoring enable_stack_on_sig() call!\n'
+        log.error(
+            '`stackscope` not installed for use in debug mode!\n'
+            '`Ignoring {enable_stack_on_sig!r} call!\n'
         )
         return None
 

tractor/devx/debug/_post_mortem.py

@@ -148,61 +148,59 @@ def _post_mortem(
         repl_fixture=repl_fixture,
         boxed_maybe_exc=boxed_maybe_exc,
     )
+    if not enter_repl:
+        return
     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>
+        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?>'
+    except NoRuntime:
+        actor_repr: str = '<no-actor-runtime?>'
 
-        try:
-            task_repr: Task = trio.lowlevel.current_task()
-        except RuntimeError:
-            task_repr: str = '<unknown-Task>'
+    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'
+    # 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
+    # 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()
+    # 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,
+    )
+
+    # 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(
@@ -250,7 +248,7 @@ async def _maybe_enter_pm(
     *,
     tb: TracebackType|None = None,
     api_frame: FrameType|None = None,
-    hide_tb: bool = True,
+    hide_tb: bool = False,
 
     # only enter debugger REPL when returns `True`
     debug_filter: Callable[

tractor/devx/debug/_trace.py

@@ -58,7 +58,6 @@ from tractor._context import Context
 from tractor import _state
 from tractor._exceptions import (
     NoRuntime,
-    InternalError,
 )
 from tractor._state import (
     current_actor,
@@ -80,9 +79,6 @@ from ._sigint import (
     sigint_shield as sigint_shield,
     _ctlc_ignore_header as _ctlc_ignore_header
 )
-from ..pformat import (
-    ppfmt,
-)
 
 if TYPE_CHECKING:
     from trio.lowlevel import Task
@@ -481,12 +477,12 @@ async def _pause(
             # we have to figure out how to avoid having the service nursery
             # cancel on this task start? I *think* this works below:
             # ```python
-            #   actor._service_tn.cancel_scope.shield = shield
+            #   actor._service_n.cancel_scope.shield = shield
             # ```
             # but not entirely sure if that's a sane way to implement it?
 
             # NOTE currently we spawn the lock request task inside this
-            # subactor's global `Actor._service_tn` so that the
+            # subactor's global `Actor._service_n` so that the
             # lifetime of the lock-request can outlive the current
             # `._pause()` scope while the user steps through their
             # application code and when they finally exit the
@@ -510,7 +506,7 @@ async def _pause(
                 f'|_{task}\n'
             )
             with trio.CancelScope(shield=shield):
-                req_ctx: Context = await actor._service_tn.start(
+                req_ctx: Context = await actor._service_n.start(
                     partial(
                         request_root_stdio_lock,
                         actor_uid=actor.uid,
@@ -544,7 +540,7 @@ async def _pause(
             _repl_fail_report = None
 
         # when the actor is mid-runtime cancellation the
-        # `Actor._service_tn` might get closed before we can spawn
+        # `Actor._service_n` might get closed before we can spawn
         # the request task, so just ignore expected RTE.
         elif (
             isinstance(pause_err, RuntimeError)
@@ -989,7 +985,7 @@ def pause_from_sync(
                 # that output and assign the `repl` created above!
                 bg_task, _ = trio.from_thread.run(
                     afn=partial(
-                        actor._service_tn.start,
+                        actor._service_n.start,
                         partial(
                             _pause_from_bg_root_thread,
                             behalf_of_thread=thread,
@@ -1157,10 +1153,9 @@ def pause_from_sync(
                         'use_greenback',
                         False,
                 ):
-                    raise InternalError(
-                        f'`greenback` was never initialized in this actor?\n'
-                        f'\n'
-                        f'{ppfmt(_state._runtime_vars)}\n'
+                    raise RuntimeError(
+                        '`greenback` was never initialized in this actor!?\n\n'
+                        f'{_state._runtime_vars}\n'
                     ) from rte
 
                 raise

tractor/devx/debug/_tty_lock.py

@@ -846,9 +846,9 @@ class DebugStatus:
 
         '''
         if not (
-            (rt_repl_fixture := _state._runtime_vars.get('repl_fixture'))
-            or
             repl_fixture
+            or
+            (rt_repl_fixture := _state._runtime_vars.get('repl_fixture'))
         ):
             return True  # YES always enter
 

tractor/ipc/_chan.py

@@ -101,27 +101,11 @@ class Channel:
         # ^XXX! ONLY set if a remote actor sends an `Error`-msg
         self._closed: bool = False
 
-        # flag set by `Portal.cancel_actor()` indicating remote
-        # (possibly peer) cancellation of the far end actor runtime.
+        # flag set by ``Portal.cancel_actor()`` indicating remote
+        # (possibly peer) cancellation of the far end actor
+        # runtime.
         self._cancel_called: bool = False
 
-    @property
-    def closed(self) -> bool:
-        '''
-        Was `.aclose()` successfully called?
-
-        '''
-        return self._closed
-
-    @property
-    def cancel_called(self) -> bool:
-        '''
-        Set when `Portal.cancel_actor()` is called on a portal which
-        wraps this IPC channel.
-
-        '''
-        return self._cancel_called
-
     @property
     def uid(self) -> tuple[str, str]:
         '''
@@ -185,9 +169,7 @@ class Channel:
             addr,
             **kwargs,
         )
-        # XXX, for UDS *no!* since we recv the peer-pid and build out
-        # a new addr..
-        # assert transport.raddr == addr
+        assert transport.raddr == addr
         chan = Channel(transport=transport)
 
         # ?TODO, compact this into adapter level-methods?
@@ -303,7 +285,7 @@ class Channel:
         self,
         payload: Any,
 
-        hide_tb: bool = False,
+        hide_tb: bool = True,
 
     ) -> None:
         '''

tractor/ipc/_mp_bs.py

@@ -17,59 +17,36 @@
 Utils to tame mp non-SC madeness
 
 '''
-import platform
-
 
+# !TODO! in 3.13 this can be disabled (the-same/similarly) using
+# a flag,
+# - [ ] soo if it works like this, drop this module entirely for
+#   3.13+ B)
+#  |_https://docs.python.org/3/library/multiprocessing.shared_memory.html
+#
 def disable_mantracker():
     '''
     Disable all `multiprocessing` "resource tracking" machinery since
     it's an absolute multi-threaded mess of non-SC madness.
 
     '''
-    from multiprocessing.shared_memory import SharedMemory
+    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
 
-    # 3.13+ only.. can pass `track=False` to disable
-    # all the resource tracker bs.
-    # https://docs.python.org/3/library/multiprocessing.shared_memory.html
-    if (_py_313 := (
-            platform.python_version_tuple()[:-1]
-            >=
-            ('3', '13')
-        )
-    ):
-        from functools import partial
-        return partial(
-            SharedMemory,
-            track=False,
-        )
+        def unregister(self, name, rtype):
+            pass
 
-    # !TODO, once we drop 3.12- we can obvi remove all this!
-    else:
-        from multiprocessing import (
-            resource_tracker as mantracker,
-        )
+        def ensure_running(self):
+            pass
 
-        # 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
-
-        # use std type verbatim
-        shmT = SharedMemory
-
-    return shmT
+    # "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

tractor/ipc/_server.py

@@ -814,14 +814,10 @@ class Server(Struct):
 
     async def wait_for_no_more_peers(
         self,
-        # XXX, should this even be allowed?
-        # -> i've seen it cause hangs on teardown
-        #    in `test_resource_cache.py`
-        # _shield: bool = False,
+        shield: bool = False,
     ) -> None:
-        await self._no_more_peers.wait()
-        # with trio.CancelScope(shield=_shield):
-        #     await self._no_more_peers.wait()
+        with trio.CancelScope(shield=shield):
+            await self._no_more_peers.wait()
 
     async def wait_for_peer(
         self,
@@ -1001,11 +997,7 @@ class Server(Struct):
             partial(
                 _serve_ipc_eps,
                 server=self,
-                stream_handler_tn=(
-                    stream_handler_nursery
-                    or
-                    self._stream_handler_tn
-                ),
+                stream_handler_tn=stream_handler_nursery,
                 listen_addrs=accept_addrs,
             )
         )
@@ -1149,17 +1141,13 @@ async def open_ipc_server(
 
     async with maybe_open_nursery(
         nursery=parent_tn,
-    ) as parent_tn:
+    ) as rent_tn:
         no_more_peers = trio.Event()
         no_more_peers.set()
 
         ipc_server = IPCServer(
-            _parent_tn=parent_tn,
-            _stream_handler_tn=(
-                stream_handler_tn
-                or
-                parent_tn
-            ),
+            _parent_tn=rent_tn,
+            _stream_handler_tn=stream_handler_tn or rent_tn,
             _no_more_peers=no_more_peers,
         )
         try:

tractor/ipc/_shm.py

@@ -23,15 +23,14 @@ 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 multiprocessing import shared_memory as shm
+from multiprocessing.shared_memory import (
+    SharedMemory,
+    ShareableList,
+)
 
 from msgspec import (
     Struct,
@@ -62,7 +61,7 @@ except ImportError:
 log = get_logger(__name__)
 
 
-SharedMemory = disable_mantracker()
+disable_mantracker()
 
 
 class SharedInt:
@@ -790,23 +789,11 @@ 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/ipc/_tcp.py

@@ -18,7 +18,6 @@ TCP implementation of tractor.ipc._transport.MsgTransport protocol
 
 '''
 from __future__ import annotations
-import ipaddress
 from typing import (
     ClassVar,
 )
@@ -51,45 +50,13 @@ class TCPAddress(
     _host: str
     _port: int
 
-    def __post_init__(self):
-        try:
-            ipaddress.ip_address(self._host)
-        except ValueError as valerr:
-            raise ValueError(
-                'Invalid {type(self).__name__}._host = {self._host!r}\n'
-            ) from valerr
-
     proto_key: ClassVar[str] = 'tcp'
     unwrapped_type: ClassVar[type] = tuple[str, int]
     def_bindspace: ClassVar[str] = '127.0.0.1'
 
-    # ?TODO, actually validate ipv4/6 with stdlib's `ipaddress`
     @property
     def is_valid(self) -> bool:
-        '''
-        Predicate to ensure a valid socket-address pair.
-
-        '''
-        return (
-            self._port != 0
-            and
-            (ipaddr := ipaddress.ip_address(self._host))
-            and not (
-                ipaddr.is_reserved
-                or
-                ipaddr.is_unspecified
-                or
-                ipaddr.is_link_local
-                or
-                ipaddr.is_link_local
-                or
-                ipaddr.is_multicast
-                or
-                ipaddr.is_global
-            )
-        )
-        # ^XXX^ see various properties of invalid addrs here,
-        # https://docs.python.org/3/library/ipaddress.html#ipaddress.IPv4Address
+        return self._port != 0
 
     @property
     def bindspace(self) -> str:

tractor/ipc/_transport.py

@@ -430,25 +430,20 @@ class MsgpackTransport(MsgTransport):
                 return await self.stream.send_all(size + bytes_data)
             except (
                 trio.BrokenResourceError,
-                trio.ClosedResourceError,
-            ) as _re:
-                trans_err = _re
+            ) as bre:
+                trans_err = bre
                 tpt_name: str = f'{type(self).__name__!r}'
-
                 match trans_err:
-
-                    # XXX, specifc to UDS transport and its,
-                    # well, "speediness".. XD
-                    # |_ likely todo with races related to how fast
-                    #    the socket is setup/torn-down on linux
-                    #    as it pertains to rando pings from the
-                    #    `.discovery` subsys and protos.
                     case trio.BrokenResourceError() if (
-                        '[Errno 32] Broken pipe'
-                        in
-                        trans_err.args[0]
+                        '[Errno 32] Broken pipe' in trans_err.args[0]
+                        # ^XXX, specifc to UDS transport and its,
+                        # well, "speediness".. XD
+                        # |_ likely todo with races related to how fast
+                        #    the socket is setup/torn-down on linux
+                        #    as it pertains to rando pings from the
+                        #    `.discovery` subsys and protos.
                     ):
-                        tpt_closed = TransportClosed.from_src_exc(
+                        raise TransportClosed.from_src_exc(
                             message=(
                                 f'{tpt_name} already closed by peer\n'
                             ),
@@ -456,31 +451,14 @@ class MsgpackTransport(MsgTransport):
                             src_exc=trans_err,
                             raise_on_report=True,
                             loglevel='transport',
-                        )
-                        raise tpt_closed from trans_err
-
-                    # case trio.ClosedResourceError() if (
-                    #     'this socket was already closed'
-                    #     in
-                    #     trans_err.args[0]
-                    # ):
-                    #     tpt_closed = TransportClosed.from_src_exc(
-                    #         message=(
-                    #             f'{tpt_name} already closed by peer\n'
-                    #         ),
-                    #         body=f'{self}\n',
-                    #         src_exc=trans_err,
-                    #         raise_on_report=True,
-                    #         loglevel='transport',
-                    #     )
-                    #     raise tpt_closed from trans_err
+                        ) from bre
 
                     # unless the disconnect condition falls under "a
                     # normal operation breakage" we usualy console warn
                     # about it.
                     case _:
                         log.exception(
-                            f'{tpt_name} layer failed pre-send ??\n'
+                            '{tpt_name} layer failed pre-send ??\n'
                         )
                         raise trans_err
 
@@ -525,7 +503,7 @@ class MsgpackTransport(MsgTransport):
     def pformat(self) -> str:
         return (
             f'<{type(self).__name__}(\n'
-            f' |_peers: 1\n'
+            f' |_peers: 2\n'
             f'   laddr: {self._laddr}\n'
             f'   raddr: {self._raddr}\n'
             # f'\n'

tractor/ipc/_uds.py

@@ -18,9 +18,6 @@ Unix Domain Socket implementation of tractor.ipc._transport.MsgTransport protoco
 
 '''
 from __future__ import annotations
-from contextlib import (
-    contextmanager as cm,
-)
 from pathlib import Path
 import os
 from socket import (
@@ -32,7 +29,6 @@ from socket import (
 )
 import struct
 from typing import (
-    Type,
     TYPE_CHECKING,
     ClassVar,
 )
@@ -103,6 +99,8 @@ class UDSAddress(
             self.filedir
             or
             self.def_bindspace
+            # or
+            # get_rt_dir()
         )
 
     @property
@@ -207,35 +205,12 @@ class UDSAddress(
             f']'
         )
 
-@cm
-def _reraise_as_connerr(
-    src_excs: tuple[Type[Exception]],
-    addr: UDSAddress,
-):
-    try:
-        yield
-    except src_excs as src_exc:
-        raise ConnectionError(
-            f'Bad UDS socket-filepath-as-address ??\n'
-            f'{addr}\n'
-            f' |_sockpath: {addr.sockpath}\n'
-            f'\n'
-            f'from src: {src_exc!r}\n'
-        ) from src_exc
-
 
 async def start_listener(
     addr: UDSAddress,
     **kwargs,
 ) -> SocketListener:
-    '''
-    Start listening for inbound connections via
-    a `trio.SocketListener` (task) which `socket.bind()`s on `addr`.
-
-    Note, if the `UDSAddress.bindspace: Path` directory dne it is
-    implicitly created.
-
-    '''
+    # sock = addr._sock = socket.socket(
     sock = socket.socket(
         socket.AF_UNIX,
         socket.SOCK_STREAM
@@ -246,25 +221,17 @@ async def start_listener(
         f'|_{addr}\n'
     )
 
-    # ?TODO? should we use the `actor.lifetime_stack`
-    # to rm on shutdown?
     bindpath: Path = addr.sockpath
-    if not (bs := addr.bindspace).is_dir():
-        log.info(
-            'Creating bindspace dir in file-sys\n'
-            f'>{{\n'
-            f'|_{bs!r}\n'
-        )
-        bs.mkdir()
-
-    with _reraise_as_connerr(
-        src_excs=(
-            FileNotFoundError,
-            OSError,
-        ),
-        addr=addr
-    ):
+    try:
         await sock.bind(str(bindpath))
+    except (
+        FileNotFoundError,
+    ) as fdne:
+        raise ConnectionError(
+            f'Bad UDS socket-filepath-as-address ??\n'
+            f'{addr}\n'
+            f' |_sockpath: {addr.sockpath}\n'
+        ) from fdne
 
     sock.listen(1)
     log.info(
@@ -389,30 +356,27 @@ class MsgpackUDSStream(MsgpackTransport):
         # `.setsockopt()` call tells the OS provide it; the client
         # pid can then be read on server/listen() side via
         # `get_peer_info()` above.
-
-        with _reraise_as_connerr(
-            src_excs=(
-                FileNotFoundError,
-            ),
-            addr=addr
-        ):
+        try:
             stream = await open_unix_socket_w_passcred(
                 str(sockpath),
                 **kwargs
             )
+        except (
+            FileNotFoundError,
+        ) as fdne:
+            raise ConnectionError(
+                f'Bad UDS socket-filepath-as-address ??\n'
+                f'{addr}\n'
+                f' |_sockpath: {sockpath}\n'
+            ) from fdne
 
-        tpt_stream = MsgpackUDSStream(
+        stream = MsgpackUDSStream(
             stream,
             prefix_size=prefix_size,
             codec=codec
         )
-        # XXX assign from new addrs after peer-PID extract!
-        (
-            tpt_stream._laddr,
-            tpt_stream._raddr,
-        ) = cls.get_stream_addrs(stream)
-
-        return tpt_stream
+        stream._raddr = addr
+        return stream
 
     @classmethod
     def get_stream_addrs(

tractor/log.py

@@ -26,8 +26,9 @@ from logging import (
     Logger,
     StreamHandler,
 )
-import colorlog  # type: ignore
+import threading
 
+import colorlog  # type: ignore
 import trio
 
 from ._state import current_actor
@@ -44,7 +45,7 @@ LOG_FORMAT = (
     "{log_color}{asctime}{reset}"
     " {bold_white}{thin_white}({reset}"
     "{thin_white}{actor_name}[{actor_uid}], "
-    "{process}, {task}){reset}{bold_white}{thin_white})"
+    "{process}, {thread_uid}, {task_uid}){reset}{bold_white}{thin_white})"
     " {reset}{log_color}[{reset}{bold_log_color}{levelname}{reset}{log_color}]"
     " {log_color}{name}"
     " {thin_white}{filename}{log_color}:{reset}{thin_white}{lineno}{log_color}"
@@ -248,11 +249,19 @@ def pformat_task_uid(
     return f'{task.name}[{tid_part}]'
 
 
+def pformat_thread_uid() -> str:
+    curr_thr: threading.Thread = threading.current_thread()
+    return (
+        f'{curr_thr.name}@{curr_thr.ident}'
+    )
+
+
 _conc_name_getters = {
-    'task': pformat_task_uid,
+    'task_uid': pformat_task_uid,
     'actor': lambda: current_actor(),
     'actor_name': lambda: current_actor().name,
     'actor_uid': lambda: current_actor().uid[1][:6],
+    'thread_uid': pformat_thread_uid,
 }
 
 
@@ -262,10 +271,11 @@ class ActorContextInfo(Mapping):
 
     '''
     _context_keys = (
-        'task',
+        'task_uid',
         'actor',
         'actor_name',
         'actor_uid',
+        'thread_uid',
     )
 
     def __len__(self):

tractor/msg/_ops.py

@@ -210,14 +210,12 @@ class PldRx(Struct):
         match msg:
             case Return()|Error():
                 log.runtime(
-                    f'Rxed final-outcome msg\n'
-                    f'\n'
+                    f'Rxed final outcome msg\n'
                     f'{msg}\n'
                 )
             case Stop():
                 log.runtime(
                     f'Rxed stream stopped msg\n'
-                    f'\n'
                     f'{msg}\n'
                 )
                 if passthrough_non_pld_msgs:
@@ -263,9 +261,8 @@ class PldRx(Struct):
         if (
             type(msg) is Return
         ):
-            log.runtime(
+            log.info(
                 f'Rxed final result msg\n'
-                f'\n'
                 f'{msg}\n'
             )
         return self.decode_pld(
@@ -307,13 +304,10 @@ class PldRx(Struct):
                 try:
                     pld: PayloadT = self._pld_dec.decode(pld)
                     log.runtime(
-                        f'Decoded payload for\n'
-                        # f'\n'
+                        'Decoded msg payload\n\n'
                         f'{msg}\n'
-                        # ^TODO?, ideally just render with `,
-                        # pld={decode}` in the `msg.pformat()`??
-                        f'where, '
-                        f'{type(msg).__name__}.pld={pld!r}\n'
+                        f'where payload decoded as\n'
+                        f'|_pld={pld!r}\n'
                     )
                     return pld
                 except TypeError as typerr:
@@ -500,8 +494,7 @@ def limit_plds(
 
     finally:
         log.runtime(
-            f'Reverted to previous payload-decoder\n'
-            f'\n'
+            'Reverted to previous payload-decoder\n\n'
             f'{orig_pldec}\n'
         )
         # sanity on orig settings
@@ -636,8 +629,7 @@ async def drain_to_final_msg(
                     (local_cs := rent_n.cancel_scope).cancel_called
                 ):
                     log.cancel(
-                        f'RPC-ctx cancelled by local-parent scope during drain!\n'
-                        f'\n'
+                        'RPC-ctx cancelled by local-parent scope during drain!\n\n'
                         f'c}}>\n'
                         f' |_{rent_n}\n'
                         f'   |_.cancel_scope = {local_cs}\n'
@@ -671,8 +663,7 @@ async def drain_to_final_msg(
             # final result arrived!
             case Return():
                 log.runtime(
-                    f'Context delivered final draining msg\n'
-                    f'\n'
+                    'Context delivered final draining msg:\n'
                     f'{pretty_struct.pformat(msg)}'
                 )
                 ctx._result: Any = pld
@@ -706,14 +697,12 @@ async def drain_to_final_msg(
                 ):
                     log.cancel(
                         'Cancelling `MsgStream` drain since '
-                        f'{reason}\n'
-                        f'\n'
+                        f'{reason}\n\n'
                         f'<= {ctx.chan.uid}\n'
-                        f'  |_{ctx._nsf}()\n'
-                        f'\n'
+                        f'  |_{ctx._nsf}()\n\n'
                         f'=> {ctx._task}\n'
-                        f'  |_{ctx._stream}\n'
-                        f'\n'
+                        f'  |_{ctx._stream}\n\n'
+
                         f'{pretty_struct.pformat(msg)}\n'
                     )
                     break
@@ -750,8 +739,7 @@ async def drain_to_final_msg(
             case Stop():
                 pre_result_drained.append(msg)
                 log.runtime(  # normal/expected shutdown transaction
-                    f'Remote stream terminated due to "stop" msg\n'
-                    f'\n'
+                    'Remote stream terminated due to "stop" msg:\n\n'
                     f'{pretty_struct.pformat(msg)}\n'
                 )
                 continue
@@ -826,8 +814,7 @@ async def drain_to_final_msg(
 
     else:
         log.cancel(
-            f'Skipping `MsgStream` drain since final outcome is set\n'
-            f'\n'
+            'Skipping `MsgStream` drain since final outcome is set\n\n'
             f'{ctx.outcome}\n'
         )
 

tractor/to_asyncio.py

@@ -130,7 +130,6 @@ class LinkedTaskChannel(
     _trio_task: trio.Task
     _aio_task_complete: trio.Event
 
-    _closed_by_aio_task: bool = False
     _suppress_graceful_exits: bool = True
 
     _trio_err: BaseException|None = None
@@ -209,15 +208,10 @@ class LinkedTaskChannel(
     async def aclose(self) -> None:
         await self._from_aio.aclose()
 
-    # ?TODO? async version of this?
-    def started_nowait(
+    def started(
         self,
         val: Any = None,
     ) -> None:
-        '''
-        Synchronize aio-side with its trio-parent.
-
-        '''
         self._aio_started_val = val
         return self._to_trio.send_nowait(val)
 
@@ -248,7 +242,6 @@ class LinkedTaskChannel(
             # cycle on the trio side?
             # await trio.lowlevel.checkpoint()
             return await self._from_aio.receive()
-
         except BaseException as err:
             async with translate_aio_errors(
                 chan=self,
@@ -326,7 +319,7 @@ def _run_asyncio_task(
     qsize: int = 1,
     provide_channels: bool = False,
     suppress_graceful_exits: bool = True,
-    hide_tb: bool = True,
+    hide_tb: bool = False,
     **kwargs,
 
 ) -> LinkedTaskChannel:
@@ -354,6 +347,18 @@ def _run_asyncio_task(
         # value otherwise it would just return ;P
         assert qsize > 1
 
+    if provide_channels:
+        assert 'to_trio' in args
+
+    # allow target func to accept/stream results manually by name
+    if 'to_trio' in args:
+        kwargs['to_trio'] = to_trio
+
+    if 'from_trio' in args:
+        kwargs['from_trio'] = from_trio
+
+    coro = func(**kwargs)
+
     trio_task: trio.Task = trio.lowlevel.current_task()
     trio_cs = trio.CancelScope()
     aio_task_complete = trio.Event()
@@ -368,25 +373,6 @@ def _run_asyncio_task(
         _suppress_graceful_exits=suppress_graceful_exits,
     )
 
-    # allow target func to accept/stream results manually by name
-    if 'to_trio' in args:
-        kwargs['to_trio'] = to_trio
-
-    if 'from_trio' in args:
-        kwargs['from_trio'] = from_trio
-
-    if 'chan' in args:
-        kwargs['chan'] = chan
-
-    if provide_channels:
-        assert (
-            'to_trio' in args
-            or
-            'chan' in args
-        )
-
-    coro = func(**kwargs)
-
     async def wait_on_coro_final_result(
         to_trio: trio.MemorySendChannel,
         coro: Awaitable,
@@ -459,23 +445,9 @@ def _run_asyncio_task(
                         f'Task exited with final result: {result!r}\n'
                     )
 
-                # XXX ALWAYS close the child-`asyncio`-task-side's
-                # `to_trio` handle which will in turn relay
-                # a `trio.EndOfChannel` to the `trio`-parent.
-                # Consequently the parent `trio` task MUST ALWAYS
-                # check for any `chan._aio_err` to be raised when it
-                # receives an EoC.
-                #
-                # NOTE, there are 2 EoC cases,
-                # - normal/graceful EoC due to the aio-side actually
-                #   terminating its "streaming", but the task did not
-                #   error and is not yet complete.
-                #
-                # - the aio-task terminated and we specially mark the
-                #   closure as due to the `asyncio.Task`'s exit.
-                #
+                # only close the sender side which will relay
+                # a `trio.EndOfChannel` to the trio (consumer) side.
                 to_trio.close()
-                chan._closed_by_aio_task = True
 
             aio_task_complete.set()
             log.runtime(
@@ -673,9 +645,8 @@ def _run_asyncio_task(
                 not trio_cs.cancel_called
             ):
                 log.cancel(
-                    f'Cancelling trio-side due to aio-side src exc\n'
-                    f'\n'
-                    f'{curr_aio_err!r}\n'
+                    f'Cancelling `trio` side due to aio-side src exc\n'
+                    f'{curr_aio_err}\n'
                     f'\n'
                     f'(c>\n'
                     f'  |_{trio_task}\n'
@@ -787,7 +758,6 @@ async def translate_aio_errors(
     aio_done_before_trio: bool = aio_task.done()
     assert aio_task
     trio_err: BaseException|None = None
-    eoc: trio.EndOfChannel|None = None
     try:
         yield  # back to one of the cross-loop apis
     except trio.Cancelled as taskc:
@@ -819,48 +789,12 @@ async def translate_aio_errors(
         # )
         # raise
 
-    # XXX EoC is a special SIGNAL from the aio-side here!
-    # There are 2 cases to handle:
-    # 1. the "EoC passthrough" case.
-    #   - the aio-task actually closed the channel "gracefully" and
-    #     the trio-task should unwind any ongoing channel
-    #     iteration/receiving,
-    #  |_this exc-translator wraps calls to `LinkedTaskChannel.receive()`
-    #    in which case we want to relay the actual "end-of-chan" for
-    #    iteration purposes.
-    #
-    # 2. relaying the "asyncio.Task termination" case.
-    #   - if the aio-task terminates, maybe with an error, AND the
-    #    `open_channel_from()` API was used, it will always signal
-    #    that termination.
-    #  |_`wait_on_coro_final_result()` always calls
-    #    `to_trio.close()` when `provide_channels=True` so we need to
-    #    always check if there is an aio-side exc which needs to be
-    #    relayed to the parent trio side!
-    #  |_in this case the special `chan._closed_by_aio_task` is
-    #    ALWAYS set.
-    #
-    except trio.EndOfChannel as _eoc:
-        eoc = _eoc
-        if (
-            chan._closed_by_aio_task
-            and
-            aio_err
-        ):
-            log.cancel(
-                f'The asyncio-child task terminated due to error\n'
-                f'{aio_err!r}\n'
-            )
-            chan._trio_to_raise = aio_err
-            trio_err = chan._trio_err = eoc
-            #
-            # ?TODO?, raise something like a,
-            # chan._trio_to_raise = AsyncioErrored()
-            # BUT, with the tb rewritten to reflect the underlying
-            # call stack?
-        else:
-            trio_err = chan._trio_err = eoc
-
+    # XXX always passthrough EoC since this translator is often
+    # called from `LinkedTaskChannel.receive()` which we want
+    # passthrough and further we have no special meaning for it in
+    # terms of relaying errors or signals from the aio side!
+    except trio.EndOfChannel as eoc:
+        trio_err = chan._trio_err = eoc
         raise eoc
 
     # NOTE ALSO SEE the matching note in the `cancel_trio()` asyncio
@@ -1113,7 +1047,7 @@ async def translate_aio_errors(
         #
         if wait_on_aio_task:
             await chan._aio_task_complete.wait()
-            log.debug(
+            log.info(
                 'asyncio-task is done and unblocked trio-side!\n'
             )
 
@@ -1130,17 +1064,11 @@ async def translate_aio_errors(
         trio_to_raise: (
             AsyncioCancelled|
             AsyncioTaskExited|
-            Exception|  # relayed from aio-task
             None
         ) = chan._trio_to_raise
 
-        raise_from: Exception = (
-            trio_err if (aio_err is trio_to_raise)
-            else aio_err
-        )
-
         if not suppress_graceful_exits:
-            raise trio_to_raise from raise_from
+            raise trio_to_raise from (aio_err or trio_err)
 
         if trio_to_raise:
             match (
@@ -1173,7 +1101,7 @@ async def translate_aio_errors(
                         )
                         return
                 case _:
-                    raise trio_to_raise from raise_from
+                    raise trio_to_raise from (aio_err or trio_err)
 
         # Check if the asyncio-side is the cause of the trio-side
         # error.
@@ -1239,6 +1167,7 @@ async def run_task(
 
 @acm
 async def open_channel_from(
+
     target: Callable[..., Any],
     suppress_graceful_exits: bool = True,
     **target_kwargs,
@@ -1272,6 +1201,7 @@ async def open_channel_from(
                     # deliver stream handle upward
                     yield first, chan
             except trio.Cancelled as taskc:
+                # await tractor.pause(shield=True)  # ya it worx ;)
                 if cs.cancel_called:
                     if isinstance(chan._trio_to_raise, AsyncioCancelled):
                         log.cancel(

tractor/trionics/__init__.py

@@ -31,7 +31,7 @@ from ._broadcast import (
 )
 from ._beg import (
     collapse_eg as collapse_eg,
-    get_collapsed_eg as get_collapsed_eg,
+    maybe_collapse_eg as maybe_collapse_eg,
     is_multi_cancelled as is_multi_cancelled,
 )
 from ._taskc import (

tractor/trionics/_beg.py

@@ -15,9 +15,8 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 '''
-`BaseExceptionGroup` utils and helpers pertaining to
-first-class-`trio` from a "historical" perspective, like "loose
-exception group" task-nurseries.
+`BaseExceptionGroup` related utils and helpers pertaining to
+first-class-`trio` from a historical perspective B)
 
 '''
 from contextlib import (
@@ -25,83 +24,28 @@ from contextlib import (
 )
 from typing import (
     Literal,
-    Type,
 )
 
 import trio
-# from trio._core._concat_tb import (
-#     concat_tb,
-# )
 
 
-# XXX NOTE
-# taken verbatim from `trio._core._run` except,
-# - remove the NONSTRICT_EXCEPTIONGROUP_NOTE deprecation-note
-#   guard-check; we know we want an explicit collapse.
-# - mask out tb rewriting in collapse case, i don't think it really
-#   matters?
-#
-def collapse_exception_group(
-    excgroup: BaseExceptionGroup[BaseException],
-) -> BaseException:
-    """Recursively collapse any single-exception groups into that single contained
-    exception.
-
-    """
-    exceptions = list(excgroup.exceptions)
-    modified = False
-    for i, exc in enumerate(exceptions):
-        if isinstance(exc, BaseExceptionGroup):
-            new_exc = collapse_exception_group(exc)
-            if new_exc is not exc:
-                modified = True
-                exceptions[i] = new_exc
-
-    if (
-        len(exceptions) == 1
-        and isinstance(excgroup, BaseExceptionGroup)
-
-        # XXX trio's loose-setting condition..
-        # and NONSTRICT_EXCEPTIONGROUP_NOTE in getattr(excgroup, "__notes__", ())
-    ):
-        # exceptions[0].__traceback__ = concat_tb(
-        #     excgroup.__traceback__,
-        #     exceptions[0].__traceback__,
-        # )
-        return exceptions[0]
-    elif modified:
-        return excgroup.derive(exceptions)
-    else:
-        return excgroup
-
-
-def get_collapsed_eg(
+def maybe_collapse_eg(
     beg: BaseExceptionGroup,
-
-) -> BaseException|None:
+) -> BaseException|bool:
     '''
-    If the input beg can collapse to a single sub-exception which is
-    itself **not** an eg, return it.
+    If the input beg can collapse to a single non-eg sub-exception,
+    return it instead.
 
     '''
-    maybe_exc = collapse_exception_group(beg)
-    if maybe_exc is beg:
-        return None
+    if len(excs := beg.exceptions) == 1:
+        return excs[0]
 
-    return maybe_exc
+    return False
 
 
 @acm
 async def collapse_eg(
     hide_tb: bool = True,
-
-    # XXX, for ex. will always show begs containing single taskc
-    ignore: set[Type[BaseException]] = {
-        # trio.Cancelled,
-    },
-    add_notes: bool = True,
-
-    bp: bool = False,
 ):
     '''
     If `BaseExceptionGroup` raised in the body scope is
@@ -113,55 +57,16 @@ async def collapse_eg(
     __tracebackhide__: bool = hide_tb
     try:
         yield
-    except BaseExceptionGroup as _beg:
-        beg = _beg
-
+    except* BaseException as beg:
         if (
-            bp
-            and
-            len(beg.exceptions) > 1
+            exc := maybe_collapse_eg(beg)
         ):
-            import tractor
-            if tractor.current_actor(
-                err_on_no_runtime=False,
-            ):
-                await tractor.pause(shield=True)
-            else:
-                breakpoint()
-
-        if (
-            (exc := get_collapsed_eg(beg))
-            and
-            type(exc) not in ignore
-        ):
-
-            # TODO? report number of nested groups it was collapsed
-            # *from*?
-            if add_notes:
-                from_group_note: str = (
-                    '( ^^^ this exc was collapsed from a group ^^^ )\n'
-                )
-                if (
-                    from_group_note
-                    not in
-                    getattr(exc, "__notes__", ())
-                ):
-                    exc.add_note(from_group_note)
-
-            # raise exc
-            # ^^ this will leave the orig beg tb above with the
-            # "during the handling of <beg> the following.."
-            # So, instead do..
-            #
             if cause := exc.__cause__:
                 raise exc from cause
-            else:
-                # suppress "during handling of <the beg>"
-                # output in tb/console.
-                raise exc from None
 
-        # keep original
-        raise # beg
+            raise exc
+
+        raise beg
 
 
 def is_multi_cancelled(

tractor/trionics/_mngrs.py

@@ -40,10 +40,7 @@ from typing import (
 import trio
 from tractor._state import current_actor
 from tractor.log import get_logger
-# from ._beg import collapse_eg
-# from ._taskc import (
-#     maybe_raise_from_masking_exc,
-# )
+from ._beg import collapse_eg
 
 
 if TYPE_CHECKING:
@@ -75,8 +72,7 @@ async def maybe_open_nursery(
         yield nursery
     else:
         async with lib.open_nursery(**kwargs) as nursery:
-            if lib == trio:
-                nursery.cancel_scope.shield = shield
+            nursery.cancel_scope.shield = shield
             yield nursery
 
 
@@ -109,9 +105,6 @@ async def _enter_and_wait(
 async def gather_contexts(
     mngrs: Sequence[AsyncContextManager[T]],
 
-    # caller can provide their own scope
-    tn: trio.Nursery|None = None,
-
 ) -> AsyncGenerator[
     tuple[
         T | None,
@@ -154,45 +147,34 @@ async def gather_contexts(
             '`.trionics.gather_contexts()` input mngrs is empty?\n'
             '\n'
             'Did try to use inline generator syntax?\n'
-            'Check that list({mngrs}) works!\n'
-            # 'or sequence-type intead!\n'
-            # 'Use a non-lazy iterator or sequence-type intead!\n'
+            'Use a non-lazy iterator or sequence-type intead!\n'
         )
 
-    try:
-        async with (
-            #
-            # ?TODO, does including these (eg-collapsing,
-            # taskc-unmasking) improve tb noise-reduction/legibility?
-            #
-            # collapse_eg(),
-            maybe_open_nursery(
-                nursery=tn,
-            ) as tn,
-            # maybe_raise_from_masking_exc(),
-        ):
-            for mngr in mngrs:
-                tn.start_soon(
-                    _enter_and_wait,
-                    mngr,
-                    unwrapped,
-                    all_entered,
-                    parent_exit,
-                    seed,
-                )
+    async with (
+        collapse_eg(),
+        trio.open_nursery() as tn,
+    ):
+        for mngr in mngrs:
+            tn.start_soon(
+                _enter_and_wait,
+                mngr,
+                unwrapped,
+                all_entered,
+                parent_exit,
+                seed,
+            )
 
-            # deliver control to caller once all ctx-managers have
-            # started (yielded back to us).
-            await all_entered.wait()
+        # deliver control once all managers have started up
+        await all_entered.wait()
+
+        try:
             yield tuple(unwrapped.values())
+        finally:
+            # XXX NOTE: this is ABSOLUTELY REQUIRED to avoid
+            # the following wacky bug:
+            # <tractorbugurlhere>
             parent_exit.set()
 
-    finally:
-        # XXX NOTE: this is ABSOLUTELY REQUIRED to avoid
-        # the following wacky bug:
-        # <tractorbugurlhere>
-        parent_exit.set()
-
 
 # Per actor task caching helpers.
 # Further potential examples of interest:
@@ -204,7 +186,7 @@ class _Cache:
     a kept-alive-while-in-use async resource.
 
     '''
-    service_tn: Optional[trio.Nursery] = None
+    service_n: Optional[trio.Nursery] = None
     locks: dict[Hashable, trio.Lock] = {}
     users: int = 0
     values: dict[Any,  Any] = {}
@@ -245,9 +227,6 @@ async def maybe_open_context(
     kwargs: dict = {},
     key: Hashable | Callable[..., Hashable] = None,
 
-    # caller can provide their own scope
-    tn: trio.Nursery|None = None,
-
 ) -> AsyncIterator[tuple[bool, T]]:
     '''
     Maybe open an async-context-manager (acm) if there is not already
@@ -280,94 +259,40 @@ async def maybe_open_context(
     # have it not be closed until all consumers have exited (which is
     # currently difficult to implement any other way besides using our
     # pre-allocated runtime instance..)
-    if tn:
-        # TODO, assert tn is eventual parent of this task!
-        task: trio.Task = trio.lowlevel.current_task()
-        task_tn: trio.Nursery = task.parent_nursery
-        if not tn._cancel_status.encloses(
-            task_tn._cancel_status
-        ):
-            raise RuntimeError(
-                f'Mis-nesting of task under provided {tn} !?\n'
-                f'Current task is NOT a child(-ish)!!\n'
-                f'\n'
-                f'task: {task}\n'
-                f'task_tn: {task_tn}\n'
-            )
-        service_tn = tn
-    else:
-        service_tn: trio.Nursery = current_actor()._service_tn
+    service_n: trio.Nursery = current_actor()._service_n
 
     # TODO: is there any way to allocate
     # a 'stays-open-till-last-task-finshed nursery?
-    # service_tn: trio.Nursery
-    # async with maybe_open_nursery(_Cache.service_tn) as service_tn:
-    #     _Cache.service_tn = service_tn
+    # service_n: trio.Nursery
+    # async with maybe_open_nursery(_Cache.service_n) as service_n:
+    #     _Cache.service_n = service_n
 
-    cache_miss_ke: KeyError|None = None
-    maybe_taskc: trio.Cancelled|None = None
     try:
         # **critical section** that should prevent other tasks from
         # checking the _Cache until complete otherwise the scheduler
         # may switch and by accident we create more then one resource.
         yielded = _Cache.values[ctx_key]
 
-    except KeyError as _ke:
-        # XXX, stay mutexed up to cache-miss yield
-        try:
-            cache_miss_ke = _ke
-            log.debug(
-                f'Allocating new @acm-func entry\n'
-                f'ctx_key={ctx_key}\n'
-                f'acm_func={acm_func}\n'
-            )
-            mngr = acm_func(**kwargs)
-            resources = _Cache.resources
-            assert not resources.get(ctx_key), f'Resource exists? {ctx_key}'
-            resources[ctx_key] = (service_tn, trio.Event())
-            yielded: Any = await service_tn.start(
-                _Cache.run_ctx,
-                mngr,
-                ctx_key,
-            )
-            _Cache.users += 1
-        finally:
-            # XXX, since this runs from an `except` it's a checkpoint
-            # whih can be `trio.Cancelled`-masked.
-            #
-            # NOTE, in that case the mutex is never released by the
-            # (first and) caching task and **we can't** simply shield
-            # bc that will inf-block on the `await
-            # no_more_users.wait()`.
-            #
-            # SO just always unlock!
-            lock.release()
+    except KeyError:
+        log.debug(f'Allocating new {acm_func} for {ctx_key}')
+        mngr = acm_func(**kwargs)
+        resources = _Cache.resources
+        assert not resources.get(ctx_key), f'Resource exists? {ctx_key}'
+        resources[ctx_key] = (service_n, trio.Event())
 
-        try:
-            yield (
-                False,  # cache_hit = "no"
-                yielded,
-            )
-        except trio.Cancelled as taskc:
-            maybe_taskc = taskc
-            log.cancel(
-                f'Cancelled from cache-miss entry\n'
-                f'\n'
-                f'ctx_key: {ctx_key!r}\n'
-                f'mngr: {mngr!r}\n'
-            )
-            # XXX, always unset ke from cancelled context
-            # since we never consider it a masked exc case!
-            # - bc this can be called directly ty `._rpc._invoke()`?
-            #
-            if maybe_taskc.__context__ is cache_miss_ke:
-                maybe_taskc.__context__ = None
-
-            raise taskc
+        # sync up to the mngr's yielded value
+        yielded = await service_n.start(
+            _Cache.run_ctx,
+            mngr,
+            ctx_key,
+        )
+        _Cache.users += 1
+        lock.release()
+        yield False, yielded
 
     else:
         _Cache.users += 1
-        log.debug(
+        log.runtime(
             f'Re-using cached resource for user {_Cache.users}\n\n'
             f'{ctx_key!r} -> {type(yielded)}\n'
 
@@ -377,19 +302,9 @@ async def maybe_open_context(
             # f'{ctx_key!r} -> {yielded!r}\n'
         )
         lock.release()
-        yield (
-            True,  # cache_hit = "yes"
-            yielded,
-        )
+        yield True, yielded
 
     finally:
-        if lock.locked():
-            stats: trio.LockStatistics = lock.statistics()
-            log.error(
-                f'Lock left locked by last owner !?\n'
-                f'{stats}\n'
-            )
-
         _Cache.users -= 1
 
         if yielded is not None:

tractor/trionics/_taskc.py

@@ -60,8 +60,8 @@ def find_masked_excs(
     return None
 
 
-# XXX, relevant discussion @ `trio`-core,
-# https://github.com/python-trio/trio/issues/455
+# XXX, relevant ish discussion @ `trio`-core,
+# https://github.com/python-trio/trio/issues/455#issuecomment-2785122216
 #
 @acm
 async def maybe_raise_from_masking_exc(
@@ -113,6 +113,7 @@ async def maybe_raise_from_masking_exc(
     )
     matching: list[BaseException]|None = None
     maybe_eg: ExceptionGroup|None
+    maybe_eg: ExceptionGroup|None
 
     if tn:
         try:  # handle egs

uv.lock

@@ -417,7 +417,7 @@ dev = [
     { name = "pyperclip", specifier = ">=1.9.0" },
     { name = "pytest", specifier = ">=8.3.5" },
     { name = "stackscope", specifier = ">=0.2.2,<0.3" },
-    { name = "typing-extensions", specifier = ">=4.14.1" },
+    { name = "typing-extensions", specifier = ">=4.13.2" },
     { name = "xonsh", specifier = ">=0.19.2" },
 ]
 
@@ -452,11 +452,11 @@ wheels = [
 
 [[package]]
 name = "typing-extensions"
-version = "4.14.1"
+version = "4.13.2"
 source = { registry = "https://pypi.org/simple" }
-sdist = { url = "https://files.pythonhosted.org/packages/98/5a/da40306b885cc8c09109dc2e1abd358d5684b1425678151cdaed4731c822/typing_extensions-4.14.1.tar.gz", hash = "sha256:38b39f4aeeab64884ce9f74c94263ef78f3c22467c8724005483154c26648d36", size = 107673, upload-time = "2025-07-04T13:28:34.16Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f6/37/23083fcd6e35492953e8d2aaaa68b860eb422b34627b13f2ce3eb6106061/typing_extensions-4.13.2.tar.gz", hash = "sha256:e6c81219bd689f51865d9e372991c540bda33a0379d5573cddb9a3a23f7caaef", size = 106967, upload-time = "2025-04-10T14:19:05.416Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/b5/00/d631e67a838026495268c2f6884f3711a15a9a2a96cd244fdaea53b823fb/typing_extensions-4.14.1-py3-none-any.whl", hash = "sha256:d1e1e3b58374dc93031d6eda2420a48ea44a36c2b4766a4fdeb3710755731d76", size = 43906, upload-time = "2025-07-04T13:28:32.743Z" },
+    { url = "https://files.pythonhosted.org/packages/8b/54/b1ae86c0973cc6f0210b53d508ca3641fb6d0c56823f288d108bc7ab3cc8/typing_extensions-4.13.2-py3-none-any.whl", hash = "sha256:a439e7c04b49fec3e5d3e2beaa21755cadbbdc391694e28ccdd36ca4a1408f8c", size = 45806, upload-time = "2025-04-10T14:19:03.967Z" },
 ]
 
 [[package]]