A message starting with `?` in a mapped room runs `claude -p` one-shot in that
repo on the Mac and posts the full answer back into the room — Matrix as a
request/response interface, not just a trigger. Non-`?` messages keep launching
interactive sessions as before.
New scripts/ask-claude.sh is a login-shell wrapper (so ~/.zprofile puts claude on
PATH) that exports CLAUDE_CODE_OAUTH_TOKEN from the Mac's .env and runs
`claude -p "$prompt" < /dev/null`, printing the answer to stdout. The bot adds a
`?`-dispatch with run_ask/ask: SSH stdout captured, 300s timeout, fail-loud, output
chunked under Matrix's event cap (no truncation).
Headless claude -p needs the long-lived token because a non-GUI SSH session can't
reach the login Keychain (reports "Not logged in") — the deliberate Approach A that
the interactive GUI-Terminal path (D11) avoided. Token is kept Mac-side only; the
Spark never runs claude. Sovereignty unchanged: claude -p uses the subscription, no
frontier API touches message payloads.
Proven live on the Spark; fresh-eyes reviewed before commit.
- src/bot.py: log in as the bot user with the stored token, prime past history,
and on a new message in a mapped room run `ssh -> gui-launch.sh` (built with
shlex.quote). The all-projects room fans out to every repo, each session named
"<repo> - <date>". Launch failures are reported back into the room.
- scripts/gui-launch.sh: propagate MB_SESSION_NAME into the launched session.
- requirements.txt: matrix-nio.
Connectivity (sub-step 1) verified on the Mac; launch (sub-step 2/3) to be tested
on the Spark, where the SSH alias resolves.
Keysat