examples/echoserver, scripts: hold what a send did not take

- WS_AppCtx stages each direction on its own: buffer, bufferIdx and
  bufferOff from appFd to the channel; fdBuffer, fdIdx and fdOff from
  the channel to appFd. thread_ctx_t drops channelBuffer and
  eofBuffer.
- app_drain_to_channel() advances bufferOff by what
  wolfSSH_ChannelIdSend() took, and holds the rest on WS_WANT_WRITE,
  WS_WINDOW_FULL, WS_REKEYING, WS_CHANNEL_NOT_CONF and WS_CHAN_RXD,
  putting back the ssh->error from before that send for all but
  WS_WANT_WRITE. A zero or over-reported send ends the session.
- app_pump_to_fd() reads the channel into fdBuffer and writes it to
  the pty or forward socket, both now nonblocking, keeping what would
  block.
- ssh_worker() leaves appFd out of the read set while buffer holds
  bytes, puts it in the write set while fdBuffer does, and runs both
  pumps on every pass.
- A pty read of zero ends the loop whatever errno holds.
- app_echo_pump() echoes the shell channel through shellCtx.buffer
  and then hands each new chunk to process_bytes(). It replaces the
  EOF drain along with eofOff and eofRead. A negative read ends the
  session.
- app_flush_fd() gives a connected forward up to APP_FLUSH_SECS
  without progress after the loop to take what fdBuffer still holds.
- The agent keeps blocking writes, through app_write_all(), which
  retries an interrupted send.
- A forward clears both of its buffers as it connects.
- fwd-bulk.test phase 3 logs in with a password and echoes 32 MB
  through ssh -L while the client keeps sending but stops reading for
  10 s. Phase 4 ends a forward while bytes are held for its target
  and checks the next forward's target gets only its own.

Issue: F-10544

Author: yosuke-wolfssl