extmod/uasyncio: Delay calling Loop.call_exception_handler by 1 loop.

When a tasks raises an exception which is uncaught, and no other task
await's on that task, then an error message is printed (or a user function
called) via a call to Loop.call_exception_handler.  In CPython this call is
made when the Task object is freed (eg via reference counting) because it's
at that point that it is known that the exception that was raised will
never be handled.

MicroPython does not have reference counting and the current behaviour is
to deal with uncaught exceptions as early as possible, ie as soon as they
terminate the task.  But this can be undesirable because in certain cases
a task can start and raise an exception immediately (before any await is
executed in that task's coro) and before any other task gets a chance to
await on it to catch the exception.

This commit changes the behaviour so that tasks which end due to an
uncaught exception are scheduled one more time for execution, and if they
are not await'ed on by the next scheduling loop, then the exception handler
is called (eg the exception is printed out).

Signed-off-by: Damien George <damien@micropython.org>

1 files changed, 2 insertions, 2 deletions

diff --git a/extmod/uasyncio/funcs.py b/extmod/uasyncio/funcs.py
index 6e1305c94..d30675231 100644
--- a/extmod/uasyncio/funcs.py
+++ b/extmod/uasyncio/funcs.py
@@ -21,9 +21,9 @@ async def wait_for(aw, timeout, sleep=core.sleep):
         pass
     finally:
         # Cancel the "cancel" task if it's still active (optimisation instead of cancel_task.cancel())
-        if cancel_task.coro is not None:
+        if cancel_task.coro is not cancel_task:
             core._task_queue.remove(cancel_task)
-    if cancel_task.coro is None:
+    if cancel_task.coro is cancel_task:
         # Cancel task ran to completion, ie there was a timeout
         raise core.TimeoutError
     return ret