v0.7.0 — owner-scoped list, bounded result --wait
0.7.0 (2026-08-03)
- Make
listowner-scoped likeclean: by default it shows only the current session's tasks, so a check-in in one chat no longer pulls a parallel chat's fleet into context on every look. Foreign tasks surface as askipped_foreigncount;list --any-owneris the deliberate machine-wide view andlist -C <repo>additionally shows that repo's tasks across owners (same escape hatches asclean). Breaking:list --jsonnow emits{"tasks": [...], "skipped_foreign": N}instead of a bare array, so the scoping is visible in-band. - Make
CDX_OWNERdoctrine instead of a footnote: the SKILL.md setup block now mints a stable per-chat slug unconditionally. The cwd fallback isolates separate worktrees but silently collides when two chats sit in the same checkout — in that caseclean --terminalin one chat could reap the other chat's uncollected results, andlistmixed both fleets. - Bound the collect wait:
result --waitdrops its default--timeoutfrom 3600 to 600 seconds, and SKILL.md step 4 makes the backgroundresult --wait+ exit-6-as-check-in the doctrine for long tasks. A lost completion notification previously meant up to an hour of silent staleness; now the wait resolves within 10 minutes no matter what, and exit 6 explicitly routes intolist+ re-arm instead of reading as a failure. Escalated questions still return immediately; the timeout only affects the still-workingcase.
To update an installed copy: ask your agent to update the cxcc-subagent skill (it follows references/update.md), or git pull in a source checkout.