Playbook 07: the reviewer is kept for the whole release, and a watcher waits for its checks #410

2026-10-17T16:26:13Z

mesh-tools commented

2026-10-17 16:26:13 +00:00

Issue 1042 (playbook 08, small fix).

The operator asked whether the reviewer continues its last session in later rounds and why review always takes so long. Playbook 07 said the fixing agents are continued by their ids, but not the reviewer; and the reviewer waited on the forge's checks before marking.

Phase 2: the reviewer is one agent kept for the whole release, continued by its id for every round, the extra cycle and the ready mark.
Phase 3: a failed check goes back to the same reviewer; the reviewer does not wait for the checks itself, a watcher does and wakes the lead, who continues the reviewer to mark.
Models table and How it is checked follow.

Checks run locally: records, index, cycle, words, each exit 0.

Issue 1042 (playbook 08, small fix). The operator asked whether the reviewer continues its last session in later rounds and why review always takes so long. Playbook 07 said the fixing agents are continued by their ids, but not the reviewer; and the reviewer waited on the forge's checks before marking. - Phase 2: the reviewer is one agent kept for the whole release, continued by its id for every round, the extra cycle and the ready mark. - Phase 3: a failed check goes back to the same reviewer; the reviewer does not wait for the checks itself, a watcher does and wakes the lead, who continues the reviewer to mark. - Models table and How it is checked follow. Checks run locally: records, index, cycle, words, each exit 0.

mesh-tools added 1 commit 2026-10-17 16:26:14 +00:00

Playbook 07: the reviewer is kept for the whole release, and a watcher waits for its checks (issue 1042)

mesh/merge-gate head e1987b365427 merged into trunk c87ab9af0f9a — pass: the change touches no module of the mesh's graph

Details

mesh/repo-check head e1987b365427 merged into trunk c87ab9af0f9a — pass: its merge-check.sh passed

Details

mesh/delivery delivered

Details

e1987b3654

The operator asked why review takes so long: a fresh reviewer per round or per mark reads
everything again, and a reviewer waiting on the forge's checks spends its run waiting.

mesh-tools commented

2026-10-17 16:26:17 +00:00

Delivery novox/hq@e1987b365427 — delivered since 2026-10-17T16:34:57Z

Delivery plan — builds nothing: the change touches no module of the mesh's graph

Transitions

2026-10-17 16:26 (new) → proposed (announced): novox/hq#410's head announced
2026-10-17 16:33 proposed → checked (checked): a verdict names this commit and the trunk's head as its trunk commit
2026-10-17 16:33 checked → ready (accepted): the gate passed or warned, and the repository's own check did not fail
2026-10-17 16:34 ready → published (merged): on the trunk its modules follow: merged there, and its walk opened — or nothing for a walk to move
2026-10-17 16:34 published → delivered (done): nothing for a walk to move

The commit's note under refs/notes/mesh-plan keeps every transition: git log --notes=mesh-plan.

**Delivery** `novox/hq@e1987b365427` — **delivered** since 2026-10-17T16:34:57Z **Delivery plan** — builds nothing: the change touches no module of the mesh's graph **Transitions** - 2026-10-17 16:26 (new) → proposed (announced): novox/hq#410's head announced - 2026-10-17 16:33 proposed → checked (checked): a verdict names this commit and the trunk's head as its trunk commit - 2026-10-17 16:33 checked → ready (accepted): the gate passed or warned, and the repository's own check did not fail - 2026-10-17 16:34 ready → published (merged): on the trunk its modules follow: merged there, and its walk opened — or nothing for a walk to move - 2026-10-17 16:34 published → delivered (done): nothing for a walk to move The commit's note under `refs/notes/mesh-plan` keeps every transition: `git log --notes=mesh-plan`.

mesh-tools added the mesh/ready label 2026-10-17 16:34:06 +00:00

mesh-tools commented

2026-10-17 16:34:06 +00:00

ready at e1987b3654

Reviewed by reviewer-1042@shanks: Approved against issue 1042: one reviewer kept per release and continued by its id; a watcher waits for the checks; both checks pass at this head. Marked through mesh-delivery.mark-ready (novox/hq issue 913).

ready at e1987b36542767dde155ff05216f0134f43e9eb9 Reviewed by reviewer-1042@shanks: Approved against issue 1042: one reviewer kept per release and continued by its id; a watcher waits for the checks; both checks pass at this head. Marked through mesh-delivery.mark-ready (novox/hq issue 913).

mesh-tools merged commit 2cf1c64e24 into main

2026-10-17 16:34:55 +00:00

mesh-tools deleted branch fix/pb07-reviewer-kept

2026-10-17 16:34:55 +00:00

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: novox/hq#410