…lothai#7307 P7)

_smart_apt_install printed an "Accept? [Y/n]" prompt, and when /dev/tty was
unreadable it set REPLY=y and escalated anyway. Every sudo call in that branch
redirects stdin from /dev/null, so on any host where sudo needs a password the
install died on sudo's own error rather than the actionable message the no-sudo
path already prints. Containers, CI and locked-down corporate machines hit this.

Probe with `sudo -n true` first. If there is no terminal to prompt on and sudo
would need a password, exit with the missing packages and the exact command to
run, matching the no-sudo path. Passwordless sudo still escalates unattended,
which is the one case where that is legitimate, and says so in the log.

With a readable /dev/tty the behaviour is unchanged, and the prompt now only
prints when something can actually answer it.

Extend tests/sh/test_apt_distro_prompt.sh to drive the real function across all
four TTY/sudo combinations, rewriting /dev/tty to a fixture path the same way
the existing cases rewrite /etc/os-release. Against the old install.sh five of
these assertions fail. Register the file in studio-backend-ci.yml's shell suite,
which did not run it before.

…7307)

Codex review follow-ups on the no-TTY sudo escalation guard.

`test -r /dev/tty` only reads the device node's permission bits. Inside
containers and systemd units those bits look fine while open() fails with
ENXIO, so the guard still fell through to a prompt nobody could answer.
_can_read_tty() does a real open. The subshell is load-bearing: in dash a
failed redirection on the special builtin `:` exits the script.

`sudo -n true` proves only that `true` is allowed. Under a command-specific
rule like `NOPASSWD: /usr/bin/apt-get` it is the wrong question in both
directions. _sudo_runs_unattended() asks the sudoers policy about the exact
argument vectors we are about to elevate, via `sudo -n -l --`, which checks
without running and fails instead of prompting.

Tests cover both: a NOPASSWD-on-trivia-but-not-apt-get sudoers stub, and a
readable-but-unopenable /dev/tty faked with a unix socket (skipped where the
platform cannot produce that shape).

Codex follow-up. `sudo -n -l -- apt-get ...` answers authorization, not
authentication: on a host where apt-get is permitted but still carries the
PASSWD tag, list mode exits 0 while the actual run needs a password, so the
guard reported unattended and the escalation died exactly as unslothai#7307 described.

Inferring the answer from list output means parsing for `!authenticate`, which
is human-readable text that varies by sudo version. Drop the inference. In the
no-terminal branch, run the real commands with `sudo -n`: -n never prompts, so
it cannot block on a closed stdin, and its exit status is the question we were
trying to answer. If it is refused, print the actionable manual command as
before. The terminal branch is unchanged: prompt, then plain sudo, which may
ask for a password because someone is there to type it.

The test stub now models sudo properly (-n refuses and runs nothing when a
password is needed) instead of special-casing the probe's argv.

…rd for apt failures

Two review findings on the headless escalation branch.

A cached authentication timestamp from an earlier, unrelated elevation made
`-n` succeed for a PASSWD-tagged apt-get, so packages installed with nobody
having answered the prompt. Add `-k` so the probe ignores the timestamp and
only a real NOPASSWD rule counts as passwordless. Per sudo(8), `-k` alongside
a command ignores the cached credentials for that invocation and "will not
update the user's cached credentials", so an interactive session elsewhere
does not have to re-authenticate afterwards.

A nonzero status from the elevated apt-get was reported as "likely needs a
password" even when sudo had authenticated fine and apt itself failed on a bad
repository, a dpkg lock or a network outage. sudo returns the command's own
exit status when the command runs, so the two cases are not distinguishable
from the status alone. Report both possibilities and point at the real error.

tests/sh/test_apt_distro_prompt.sh: teach the sudo stub about -k, add a cached
mode, and assert both behaviours. The three new assertions fail against the
previous commit.

…tus claim

Comment-only. The earlier note said a nonzero status from the elevated apt-get
was not distinguishable from the status alone; sudo(8) is more specific than
that. sudo exits 1 on an authentication or configuration failure and passes the
command's own status through when the command runs, while apt-get(8) returns
100 on error, so the two usually are distinguishable. sudo also exits 1 when
the command cannot be executed, which is why the message still states both
causes rather than naming one.

Comment-only pass over the branch's own comments in both files. Same intent,
fewer lines: drop restatement, keep the parts a reader cannot derive from the
code (why test -r is the wrong probe, why the subshell around the redirection
is load-bearing under dash, what -k buys over -n, and why a nonzero status
does not by itself name the cause).

Verified to touch nothing but comments and blank lines.