LLDB handles shell expansion by running lldb-argdumper under a shell. Currently, this is always /bin/sh on POSIX. This potentially leads to different behavior between lldb and the user's current shell. Here's an example of different expansions between shells:
$ /bin/bash -c 'echo -config={Options:[{key:foo_key,value:foo_value}]}' -config={Options:[key:foo_key]} -config={Options:[value:foo_value]} $ /bin/zsh -c 'echo -config={Options:[{key:foo_key,value:foo_value}]}' zsh:1: no matches found: -config={Options:[key:foo_key]} $ /bin/sh -c 'echo -config={Options:[{key:foo_key,value:foo_value}]}' -config={Options:[key:foo_key]} -config={Options:[value:foo_value]} $ /bin/fish -c 'echo -config={Options:[{key:foo_key,value:foo_value}]}' -config=Options:[key:foo_key] -config=Options:[value:foo_value]
To reduce surprises, this patch returns the user's current shell. It first looks at the SHELL environment variable. If that isn't set, it'll ask for the user's default shell. Only if that fails, we'll fallback to /bin/sh, which should always be available.
Is there a reliable way to check that the expansion we get in lldb matches the one in the shell? For example, could we have the program dump its arguments once without lldb and match them against the lldb output?
I guess the zsh example that errors out in your description makes this hard?