From fa839454f6b8524690367e69fda921a597233889 Mon Sep 17 00:00:00 2001 From: jochen Date: Thu, 12 Nov 2026 09:50:04 +0100 Subject: [PATCH] Answer A-265: the tool runner answers a bundle's marked seat verb as AnswerSeat does Claude-Session: https://claude.ai/code/session_01NcbgfGKaxw984XyAPfLm4h --- 03-DESIGN/01-to-be/47-milestones/G-22-lead-answers-2.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/03-DESIGN/01-to-be/47-milestones/G-22-lead-answers-2.md b/03-DESIGN/01-to-be/47-milestones/G-22-lead-answers-2.md index 02160c59..58d77fb0 100644 --- a/03-DESIGN/01-to-be/47-milestones/G-22-lead-answers-2.md +++ b/03-DESIGN/01-to-be/47-milestones/G-22-lead-answers-2.md @@ -325,3 +325,7 @@ the principle that settles it, cited as "design 47 G A-n". a marked verb are added in mesh-sdk's `seatdef.Resolve`, which the seat generator and every reader of a definition (the seat list, the grants part, the validator, `AnswerSeat`) go through: one place, one definition for all; the seat files stay as written. +- **A-265** (A-264, design 46 approval mark ยง20; principles 4 and 7) A-264 holds for every marked definition. Where a + tool bundle holds the seat (the login shell's `execute`), the tool runner, which already holds that bundle's gate, + answers the marked verb by caller and serves `approvals` for the seats its bundles hold, as `AnswerSeat` does for a + process; no holder changes and no mark moves.