From bbefda66e2db77c68f1fdab40f15d92f49e516f0 Mon Sep 17 00:00:00 2001 From: claude Date: Sat, 8 Aug 2026 21:31:22 +0400 Subject: [PATCH] Read the source column off the badge, not off the wording (V-662) The third run of the same 140 turns, with the harness fix in. Sixty-eight turns name a source. Two findings the wording could not carry. The unfixed homelab turns are claimed by weather and by feeds, which the destination fixture predicted. And agenda questions are claimed by the personal boundary and by Praxis, not by the calendar: 3 of 6, the same 3 of 6 the destination fixture and every routing-head seed score. Co-Authored-By: Claude Opus 5 Claude-Session: https://claude.ai/code/session_013ptwopxyo3Z2kwFckHkLvN --- .../evals/2026-08-08-two-weeks-after-merge.md | 53 ++++++++++++++++--- 1 file changed, 47 insertions(+), 6 deletions(-) diff --git a/docs/evals/2026-08-08-two-weeks-after-merge.md b/docs/evals/2026-08-08-two-weeks-after-merge.md index 578ffb4..3e0c4b9 100644 --- a/docs/evals/2026-08-08-two-weeks-after-merge.md +++ b/docs/evals/2026-08-08-two-weeks-after-merge.md @@ -80,12 +80,53 @@ V-655 was never going to touch this. A parked clarify is dialogue state and not a query source. It remains the single worst thing about talking to her. The week test, the fortnight test and this re-run all report it unchanged. -## A gap in the harness +## A gap in the harness, fixed and re-run the same day `ipc.ChatReply.Source` came back empty on all 140 turns, in both runs. The -driver reads it from the redirect query string and there is nothing there. So -the badge that says which query source claimed a turn is invisible to the -harness, and every finding above is read off the reply text instead. +driver read the redirect parameter `src` and `cmd/mavweb/chat.go` writes `s`. +So every finding above is read off the reply text instead of off the badge. -That is worth fixing before the next re-run. Reading the source directly would -have shown the two homelab misses without inferring them from the wording. +Fixed in V-662 and the 140 turns were driven a third time. Sixty-eight of them +name a source. The rest are not query turns and never reach `queryWalk`. + +| source | turns | +|---|---| +| search | 27 | +| memory | 13 | +| personal | 9 | +| weather | 5 | +| calendar | 3 | +| attention | 3 | +| list | 2 | +| feeds | 2 | +| tasks, money, self, habits | 1 each | + +## What the badge shows that the wording did not + +The two unfixed homelab turns are now direct evidence. + +```text +какая скорость у меня сейчас? -> weather +хватает ли места под новые бэкапы? -> feeds +``` + +Both are guessing sources claiming a turn about the box, exactly as the +destination fixture predicted. + +The badge also names a defect the wording hid. **Agenda questions are being +claimed by the personal boundary and by Praxis, not by the calendar.** + +```text +во сколько у меня встреча? -> personal не нашла у тебя такой записи +когда у меня встреча? -> attention у Praxis нет источников +что у меня в понедельник? -> personal не нашла у тебя такой записи +``` + +Calendar claimed 3 turns of the 6 that asked about the calendar. That is the +same 3/6 the destination fixture scores and the same 3/6 every seed of the +routing head scores. Three measurements agree. The cause is the one V-660 named. The possessive +agenda rules claim these at stage 0 and name no destination, so the walk +reaches `personal` and `attention` first. + +This is the third independent confirmation that the possessive agenda rules +should name the calendar. That call is still the owner's.