Add basic ctl-c testing cases to suite

See https://github.com/pdbpp/pdbpp/issues/496

.github/workflows/ci.yml

@@ -120,4 +120,4 @@ jobs:
         run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
 
       - name: Run tests
-        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rs
+        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rs --full-trace

tests/test_debugger.py

@@ -1,5 +1,5 @@
 """
-That native debug better work!
+That "native" debug mode better work!
 
 All these tests can be understood (somewhat) by running the equivalent
 `examples/debugging/` scripts manually.
@@ -13,6 +13,7 @@ TODO:
 import time
 from os import path
 import platform
+from typing import Optional
 
 import pytest
 import pexpect
@@ -73,6 +74,14 @@ def spawn(
     return _spawn
 
 
+@pytest.fixture(
+    params=[False, True],
+    ids='ctl-c={}'.format,
+)
+def ctlc(request) -> bool:
+    yield request.param
+
+
 @pytest.mark.parametrize(
     'user_in_out',
     [
@@ -137,20 +146,50 @@ def test_root_actor_bp(spawn, user_in_out):
         assert expect_err_str in str(child.before)
 
 
-def test_root_actor_bp_forever(spawn):
+def do_ctlc(
+    child,
+    count: int = 3,
+    patt: Optional[str] = None,
+
+) -> None:
+
+    # make sure ctl-c sends don't do anything but repeat output
+    for _ in range(count):
+        child.sendcontrol('c')
+        child.expect(r"\(Pdb\+\+\)")
+
+        if patt:
+            # should see the last line on console
+            before = str(child.before.decode())
+            assert patt in before
+
+
+def test_root_actor_bp_forever(
+    spawn,
+    ctlc: bool,
+):
     "Re-enter a breakpoint from the root actor-task."
     child = spawn('root_actor_breakpoint_forever')
 
     # do some "next" commands to demonstrate recurrent breakpoint
     # entries
     for _ in range(10):
-        child.sendline('next')
+
         child.expect(r"\(Pdb\+\+\)")
 
-    # do one continue which should trigger a new task to lock the tty
+        if ctlc:
+            do_ctlc(child)
+
+        child.sendline('next')
+
+    # do one continue which should trigger a
+    # new task to lock the tty
     child.sendline('continue')
     child.expect(r"\(Pdb\+\+\)")
 
+    if ctlc:
+        do_ctlc(child)
+
     # XXX: this previously caused a bug!
     child.sendline('n')
     child.expect(r"\(Pdb\+\+\)")
@@ -158,8 +197,15 @@ def test_root_actor_bp_forever(spawn):
     child.sendline('n')
     child.expect(r"\(Pdb\+\+\)")
 
+    # quit out of the loop
+    child.sendline('q')
+    child.expect(pexpect.EOF)
 
-def test_subactor_error(spawn):
+
+def test_subactor_error(
+    spawn,
+    ctlc: bool,
+):
     "Single subactor raising an error"
 
     child = spawn('subactor_error')
@@ -170,23 +216,29 @@ def test_subactor_error(spawn):
     before = str(child.before.decode())
     assert "Attaching to pdb in crashed actor: ('name_error'" in before
 
-    # send user command
-    # (in this case it's the same for 'continue' vs. 'quit')
-    child.sendline('continue')
+    # make sure ctl-c sends don't do anything but repeat output
+    if ctlc:
+        do_ctlc(
+            child,
+            patt='(doggypants)',
+        )
 
-    # the debugger should enter a second time in the nursery
+    # send user command and (in this case it's the same for 'continue'
+    # vs. 'quit') the debugger should enter a second time in the nursery
     # creating actor
-
+    child.sendline('continue')
     child.expect(r"\(Pdb\+\+\)")
 
     before = str(child.before.decode())
-
     # root actor gets debugger engaged
     assert "Attaching to pdb in crashed actor: ('root'" in before
-
     # error is a remote error propagated from the subactor
     assert "RemoteActorError: ('name_error'" in before
 
+    # another round
+    if ctlc:
+        do_ctlc(child)
+
     child.sendline('c')
     child.expect('\r\n')
 

tests/test_docs_examples.py

@@ -81,11 +81,14 @@ def run_example_in_subproc(loglevel, testdir, arb_addr):
     'example_script',
 
     # walk yields: (dirpath, dirnames, filenames)
-    [(p[0], f) for p in os.walk(examples_dir()) for f in p[2]
+    [
+        (p[0], f) for p in os.walk(examples_dir()) for f in p[2]
 
         if '__' not in f
         and f[0] != '_'
-        and 'debugging' not in p[0]],
+        and 'debugging' not in p[0]
+        and 'integration' not in p[0]
+    ],
 
     ids=lambda t: t[1],
 )

tractor/_actor.py

@@ -611,7 +611,8 @@ class Actor:
                     entry = local_nursery._children.get(uid)
                     if entry:
                         _, proc, _ = entry
-                        log.warning(f'Actor {uid}@{proc} IPC connection broke!?')
+                        log.warning(
+                            f'Actor {uid}@{proc} IPC connection broke!?')
                         # if proc.poll() is not None:
                         #     log.error('Actor {uid} proc died and IPC broke?')
 
@@ -630,6 +631,11 @@ class Actor:
                     # Attempt to wait for the far end to close the channel
                     # and bail after timeout (2-generals on closure).
                     assert chan.msgstream
+
+                    log.runtime(
+                        f'Draining lingering msgs from stream {chan.msgstream}'
+                    )
+
                     async for msg in chan.msgstream.drain():
                         # try to deliver any lingering msgs
                         # before we destroy the channel.

tractor/_debug.py

@@ -41,6 +41,7 @@ from .log import get_logger
 from ._discovery import get_root
 from ._state import is_root_process, debug_mode
 from ._exceptions import is_multi_cancelled
+from ._ipc import Channel
 
 
 try:
@@ -396,6 +397,10 @@ def mk_mpdb() -> tuple[MultiActorPdb, Callable]:
         signal.SIGINT,
         partial(shield_sigint, pdb_obj=pdb),
     )
+
+    # XXX: These are the important flags mentioned in
+    # https://github.com/python-trio/trio/issues/1155
+    # which resolve the traceback spews to console.
     pdb.allow_kbdint = True
     pdb.nosigint = True
 
@@ -464,11 +469,15 @@ async def _breakpoint(
         _local_task_in_debug = task_name
 
         def child_release_hook():
-            # _local_task_in_debug = None
+            try:
+                # sometimes the ``trio`` might already be termianated in
+                # which case this call will raise.
                 _local_pdb_complete.set()
-
+            finally:
                 # restore original sigint handler
                 undo_sigint()
+                # should always be cleared in the hijack hook aboved right?
+                # _local_task_in_debug = None
 
         # assign unlock callback for debugger teardown hooks
         # _pdb_release_hook = _local_pdb_complete.set
@@ -539,8 +548,12 @@ async def _breakpoint(
 
             _global_actor_in_debug = None
             _local_task_in_debug = None
-            _local_pdb_complete.set()
 
+            try:
+                # sometimes the ``trio`` might already be termianated in
+                # which case this call will raise.
+                _local_pdb_complete.set()
+            finally:
                 # restore original sigint handler
                 undo_sigint()
 
@@ -600,7 +613,21 @@ def shield_sigint(
 
     actor = tractor.current_actor()
 
+    def do_cancel():
+        # If we haven't tried to cancel the runtime then do that instead
+        # of raising a KBI (which may non-gracefully destroy
+        # a ``trio.run()``).
+        if not actor._cancel_called:
+            actor.cancel_soon()
+
+        # If the runtime is already cancelled it likely means the user
+        # hit ctrl-c again because teardown didn't full take place in
+        # which case we do the "hard" raising of a local KBI.
+        else:
+            raise KeyboardInterrupt
+
     any_connected = False
+
     if uid_in_debug is not None:
         # try to see if the supposed (sub)actor in debug still
         # has an active connection to *this* actor, and if not
@@ -616,6 +643,7 @@ def shield_sigint(
                     f'{uid_in_debug}\n'
                     'Allowing SIGINT propagation..'
                 )
+                return do_cancel()
 
     # root actor branch that reports whether or not a child
     # has locked debugger.
@@ -644,6 +672,16 @@ def shield_sigint(
     elif (
         not is_root_process()
     ):
+        chan: Channel = actor._parent_chan
+        if not chan or not chan.connected():
+            log.warning(
+                'A global actor reported to be in debug '
+                'but no connection exists for its parent:\n'
+                f'{uid_in_debug}\n'
+                'Allowing SIGINT propagation..'
+            )
+            return do_cancel()
+
         task = _local_task_in_debug
         if task:
             log.pdb(
@@ -659,20 +697,6 @@ def shield_sigint(
                 "Ignoring SIGINT since debug mode is enabled"
             )
 
-    # noone has the debugger so raise KBI
-    else:
-        # If we haven't tried to cancel the runtime then do that instead
-        # of raising a KBI (which may non-gracefully destroy
-        # a ``trio.run()``).
-        if not actor._cancel_called:
-            actor.cancel_soon()
-
-        # If the runtime is already cancelled it likely means the user
-        # hit ctrl-c again because teardown didn't full take place in
-        # which case we do the "hard" raising of a local KBI.
-        else:
-            raise KeyboardInterrupt
-
     # maybe redraw/print last REPL output to console
     if pdb_obj:
 
@@ -687,8 +711,13 @@ def shield_sigint(
         # https://github.com/prompt-toolkit/python-prompt-toolkit/blob/c2c6af8a0308f9e5d7c0e28cb8a02963fe0ce07a/prompt_toolkit/patch_stdout.py
 
         try:
-            pdb_obj.do_longlist(None)
-            print(pdb_obj.prompt, end='', flush=True)
+            # XXX: lol, see ``pdbpp`` issue:
+            # https://github.com/pdbpp/pdbpp/issues/496
+            # pdb_obj.do_longlist(None)
+            # pdb_obj.lastcmd = 'longlist'
+            pdb_obj._printlonglist(max_lines=False)
+            # print(pdb_obj.prompt, end='', flush=True)
+
         except AttributeError:
             log.exception('pdbpp longlist failed...')
             raise KeyboardInterrupt
@@ -709,7 +738,7 @@ def _set_trace(
     # start 2 levels up in user code
     frame: FrameType = sys._getframe()
     if frame:
-        frame = frame.f_back.f_back  # type: ignore
+        frame = frame.f_back  # type: ignore
 
     if pdb and actor is not None:
         log.pdb(f"\nAttaching pdb to actor: {actor.uid}\n")

tractor/_ipc.py

@@ -231,7 +231,7 @@ class MsgspecTCPStream(MsgpackTCPStream):
 
         '''
         import msgspec  # noqa
-        last_decode_failed: bool = False
+        decodes_failed: int = 0
 
         while True:
             try:
@@ -268,12 +268,17 @@ class MsgspecTCPStream(MsgpackTCPStream):
                 msgspec.DecodeError,
                 UnicodeDecodeError,
             ):
-                if not last_decode_failed:
+                if decodes_failed < 4:
                     # ignore decoding errors for now and assume they have to
                     # do with a channel drop - hope that receiving from the
                     # channel will raise an expected error and bubble up.
-                    log.error('`msgspec` failed to decode!?')
-                    last_decode_failed = True
+                    decoded_bytes = msg_bytes.decode()
+                    log.error(
+                        '`msgspec` failed to decode!?\n'
+                        'dumping bytes:\n'
+                        f'{decoded_bytes}'
+                    )
+                    decodes_failed += 1
                 else:
                     raise
 

tractor/_portal.py

@@ -511,8 +511,8 @@ class Portal:
             if ctx.chan.connected():
                 log.info(
                     'Waiting on final context-task result for\n'
-                    f'task:{cid}\n'
-                    f'actor:{uid}'
+                    f'task: {cid}\n'
+                    f'actor: {uid}'
                 )
                 result = await ctx.result()
 

tractor/to_asyncio.py

@@ -259,6 +259,7 @@ def _run_asyncio_task(
         nonlocal chan
         aio_err = chan._aio_err
         task_err: Optional[BaseException] = None
+        tname = task.get_name()
 
         # only to avoid ``asyncio`` complaining about uncaptured
         # task exceptions
@@ -268,9 +269,10 @@ def _run_asyncio_task(
             task_err = terr
 
             if isinstance(terr, CancelledError):
-                log.cancel(f'`asyncio` task cancelled: {task.get_name()}')
+                log.cancel(
+                    f'infected `asyncio` task cancelled: {tname}')
             else:
-                log.exception(f'`asyncio` task: {task.get_name()} errored')
+                log.exception(f'`asyncio` task: {tname} errored')
 
             assert type(terr) is type(aio_err), 'Asyncio task error mismatch?'
 
@@ -285,21 +287,24 @@ def _run_asyncio_task(
             # We might want to change this in the future though.
             from_aio.close()
 
-            if type(aio_err) is CancelledError:
-                log.cancel("infected task was cancelled")
+            # if type(aio_err) is CancelledError:
+            #     if not task_err:
+            #         log.cancel(
+            #             f"infected task {tname} cancelled itself, was not ``trio``"
+            #         )
 
                 # TODO: show that the cancellation originated
                 # from the ``trio`` side? right?
                 # if cancel_scope.cancelled:
                 #     raise aio_err from err
 
-            elif task_err is None:
+            if task_err is None:
                 assert aio_err
                 aio_err.with_traceback(aio_err.__traceback__)
-                msg = ''.join(traceback.format_exception(type(aio_err)))
-                log.error(
-                    f'infected task errorred:\n{msg}'
-                )
+                # msg = ''.join(traceback.format_exception(type(aio_err)))
+                # log.error(
+                #     f'infected task errorred:\n{msg}'
+                # )
 
             # raise any ``asyncio`` side error.
             raise aio_err
@@ -392,8 +397,8 @@ async def run_task(
 
 ) -> Any:
     '''
-    Run an ``asyncio`` async function or generator in a task, return
-    or stream the result back to ``trio``.
+    Run an ``asyncio`` async function or generator in a new task, block
+    and return the result back to ``trio``.
 
     '''
     # simple async func