>>> (setq tramp-optimize-remote-path nil >>> tramp-remote-path '(tramp-own-remote-path)) >> >> Isn't the idea to use the remote $PATH as-it-is, w/o any change from >> Tramp side? In this case, we could make it easy, and allow >> tramp-remote-path to be just t, instead of a list of strings. Tramp >> wouldn't try to read or set the remote path then. > > Perhaps it is even more intuitive, if we allow tramp-remote-path to be > nil (instead of t). The semantice would be, that it is the same as > '(tramp-own-remote-path), but w/o any check or setting on the remote > side.
I like it, makes sense. >>> If you think this can go in, I will follow up with an addition to the >>> manual and etc/NEWS. Let me know if you'd like me to adapt the patch in >>> any way or make any other changes. >> >> Perhaps you try a patch along this idea? > > WDYT? I will work on a patch to implement that, thanks!
