fix(task): the verifier-rail auto-skip is now loud, and reversible (DIVE-1880)
Self-hosted AI team: Claude Code, Codex and more, from your phone
Brought to you by:
fivedive
Originally created by: lodar
Fixes DIVE-1880 — the silent verifier-rail skip Marcus filed after it bit DIVE-1877.
task add --priority=low auto-declines the DIVE-969 verifier rail. That behaviour is correct — grading a real chore is pure overhead — but it printed nothing, while medium+ prints a positive · verifier-graded by default → <grader> notice. So the filer could not distinguish a railed task from an unrailed one, and the maker's own task done closed work that was supposed to be graded.
· NOT verifier-graded (low priority) — 'task done' will close it outright; attach a grader with: 5dive task verifier <ident> <agent>--json carries verifySkipped + verifySkipReason (low priority / bodyless chore title).--no-verify stays quiet, since an explicit opt-out is already visible.5dive task verifier <id|DIVE-N> <agent> [--accept=<criteria>] [--max-iters=<n>] attaches the rail to an already-filed task — --verifier only ever existed on task add, so a mis-filing previously had no remedy but cancel-and-re-file. It derives acceptance criteria when there are none, clears the INST-2 verify_unavailable flag, and from then on task done hands off to the grader instead of closing.task reject, the real remedy there), a recurring template, and making a task's own assignee its grader (writer != grader, DIVE-474).--verifier=<agent> short-circuits the auto-skip and is stored verbatim, so the rail can be forced ON at low priority. The auto-skip is a default, not a ceiling.tests/task_verifier_rail_unit.sh — 17/17, isolated temp STATE_DIR, no root/network. Covers the announcement in text + JSON with reason, low priority still genuinely unrailed, medium still engaging, --verifier forcing it on at low, the chore-title reason, --no-verify silence, retro-attach + derived criteria, task done routing to the verifier after a retro-attach (the before/after that matters), --accept override, and all four guards.task_core_unit 35/35, gate_verifier_route_unit 7/7, loop_verify_unit 10/10, task_deliver_merge_gate_unit 11/11, task_merge_gate_autodetect_unit 11/11.STATE_DIR: low-priority add prints the skip notice, task verifier DIVE-1 boss attaches, the following task done reports "ready for review — delivered to verifier 'boss'", and the closed-task guard fires with the task reject hint.FIVE_VERSION 0.14.7 → 0.14.8, CHANGELOG entry added.🤖 Generated with Claude Code
Originally posted by: lodar
Good catch — it fell through, and wrongly. Fixed in 063b6d9, which is the second commit on this branch.
The middle state isn't a distinct status: a maker's
task donere-queues the row asstatus='todo'withassignee=<the verifier>,maker_agent=<the maker>andhandoff_delivered_atstamped (DIVE-477 + DIVE-1416). So mid-review the assignee IS the outgoing grader, not the maker — and my guards were written against the assignee. Two real bugs:assignee, so mid-review it blocked naming the grader who already held the task ("a maker can't grade itself" — nonsense there) while allowing the review to be handed back to the actual maker,alice. It now resolves the maker asmaker_agentwhen the row is mid-handoff, so handing a review back to its maker is refused and the message says "own maker".verifier. The task stayed on the old grader's board while the row claimed a grader who didn't hold it — precisely the "control that looks applied and is not" shape this task is about. It now moves the queue with the review:assigneefollows,handoff_ack_atclears,handoff_delivered_atis re-stamped so the DIVE-1416 stall sweep times the new review rather than inheriting the old one's clock, andstarted_atresets.maker_agentanditerationare untouched — the maker and the loop's history don't change just because the grader did.Naming the grader who already holds it is now an idempotent no-op on the handoff (criteria still refine) rather than an error.
Verified on the built binary against an isolated
STATE_DIR, not just the suite:tests/task_verifier_rail_unit.shis now 22 assertions (was 17); the five new ones cover queue-follows-review, ACK cleared, maker + iteration preserved, the idempotent same-grader call, maker-as-grader refused, and the re-pointed grader's owntask doneclosing the task for real.task_core_unit35/35,gate_verifier_route_unit7/7,loop_verify_unit10/10,task_deliver_merge_gate_unit11/11 all still green. Bundle rebuilt;pii-scanclean on both the diff andCHANGELOG.md.On your other two points: agreed on both, and the one-way rationale you gave (a detach flag would let a maker remove their own grader) is now written into the code comment above
cmd_task_verifierso it doesn't get "fixed" later. Your binary-and-real-store verification is the right call — my four guarded states are all reproducible with the commands above against a throwawaySTATE_DIR. Take the time you need on the merge; this one changes the hottest path we ship.Ticket changed by: lodar