Some serial sources clear their RX buffers and others didn't. This
cause CP to skip into the REPL based on characters typed before the
CTRL-C. The serial file transfer code looks for "press any key"
which is skipped in this case.
Fixes https://github.com/circuitpython/web-editor/issues/238
Espressif's Characteristics allocate memory that may be on the
supervisor heap. We need to free it when stopping BLE workflow.
Otherwise, we leak the memory and eventually safe mode.
Fixes#9599
The Funhouse problem was due to a locking change for SPI. The
Funhouse is one of a few boards with DotStar status LEDs that use
SPI and have this bug.
I thought it might be IDF related so I updated it first. :-)
Fixes#9486
In 9.0.x, serial_bytes_available returned a bool and tud_cdc_available was
harmlessly checked twice for any characters.
When the routine was changed to return an int, the double checking led to
over-reporting the number of characters available. In code that would attempt
to read this many bytes from sys.stdin, this made the read call block since
only 1 byte was actually available.
This behavior came up in the discussion of #9393. I don't mark this bug as
closing that one, because that issue seems to be reporting multiple things that
this change would not address, such as delays in `sys.stdout.write()` or
problems seen while using webserial.
The previous implementation would always start BLE and rely on
advertising logic to make the workflow not available when on USB.
This change removes the "always enable" call in favor of a default
value that is on if 1) we determine we should be discoverable or 2)
we're already bonded over BLE.
This runs in the Renode simulator and enables easier tracing and
debugging of the CircuitPython core. This port can also serve as
a starting point for new ports because it implements the minimal
necessary for the CP core to run.
It is enabled on:
* SAMD51 boards with 1MB flash (SKU ending in 20A)
* Feather RP2040 DVI. Others have PIO usb host.
* All ESP32 boards.
* All nRF boards
Fixes#8676
