open/ms-ai-architect
1
0
Fork 0
Code Issues Releases 1 Activity

fix(ms-ai-architect): idx-26t arvet ikke #21 — premisset om «ordrett samme form» var usant

Browse source 
STATE sendte denne oekten inn med at idx-26t baerer «ordrett samme form som
idx-26w», og at #21 derfor trolig kunne anvendes uten ny ratifisering. Maalt mot
fila er det usant, og forskjellen er noeyaktig det #21 dreier seg om.

GROUND TRUTH, :732:
  «**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research»
idx-26w leser «fra MCP-research» ALENE. STATEs gjengivelse droppet
«+ tavily-research». #21 fyrer kun der provenans-kvalifikatoren OVERKLAIMER;
her gjoer den det ikke, fordi den navngir web-research-benet som dekker
presis de URLene microsoft-learn-serveren ikke kan levere: a2a-protocol.org
(x2), linuxfoundation.org, developers.googleblog.com.

Uavhengig bekreftet FOER denne oekten maalte: idx-26w sin egen summary trakk
allerede denne kontrasten skriftlig, og navnga nabolinja som en som «does
cover its non-Learn sources». Tre kilder er enige.

URL-CENSUS, to populasjoner, kjoert og ikke resonnert:
  Kilder-seksjonen (:670-slutt): 11 forekomster, 11 distinkte — 7 Learn,
  2 a2a-protocol.org, 1 linuxfoundation.org, 1 googleblog — fordelt paa 10
  nummererte entries, der entry 8 baerer to URLer.
  Hele fila: 14 distinkte; de tre ekstra er kode-eksempel-verter
  (agents.nav.no, to example.com) som ingen lesning teller som kilder.
TELLINGEN ER 10 SOM KILDER OG 11 SOM UNIKE URLer, og linja sier «unike URLer»
mens den gir kildetallet. Defekten er tellingens REFERENT, ikke dens
provenans — en annen defekt enn idx-26w.

ALLE SEKS RATIFISERTE FORMER UTELUKKET, hver mot sitt eget uttalte vilkaar:
 #21 krever overklaimende kvalifikator (maalt usant).
 #22 klassifiserer linja som KEEP, ikke delete — og #22 antok at keep-klasse
     betyr avgjoerbar, noe denne linja falsifiserer: den er tellbar to ganger,
     til to ulike tall.
 #23 krever en mikset delete/keep-linje; her finnes ingen delete-halvdel.
 #24 krever en header-parentes. #25 krever en delete-klasse-telling inne i
     linja; det finnes ingen aa fjerne. #26 er scopet til en annen fil.

Ingen edit er gjort i korpus. Maalingen er bokfoert i idx-26t, status forblir
open, og saken gaar til operatoeren som ny ratifiseringsforespoersel — som
STATEs egen instruks foreskrev for nettopp dette utfallet.

Suite 1052/1052.
This commit is contained in:
Kjell Tore Guttormsen 2026-08-12 21:38:26 +02:00
commit 2ba3cee060
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
scripts/kb-eval/data/g7-review-queue.json
View file

@ -377,7 +377,7 @@
"class": "replacement",
"status": "open",
"raised": "2026-08-09",
"summary": "Booked while closing idx-26n, from the check the ratified form requires on what REMAINS in a footer after the MCP-calls line is deleted - the defect sits next to the edit, now for the twelfth time. '**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research' states both a source count and a URL count in one line, and they differ. MEASURED, not inferred: the Kilder section carries 10 numbered entries but 11 distinct URLs, because entry 8 (A2A Protocol Specification) lists two - https://a2a-protocol.org/latest/specification/ and https://a2a-protocol.org/latest/announcing-1.0/. So the line is TRUE read as 'sources cited' and FALSE read as 'unike URLer', and it says both. This is the undefined-referent defect the whole footer class is about, surviving INSIDE the line the ratified form told us to keep and verify - the form presumed kept counts would pass and does not say what to do when one fails. DIRECTION MATTERS AND WAS CHECKED: stated 10 < actual 11 runs the same way as all eight MCP-calls inconsistencies measured corpus-wide, with zero running the other way. DO NOT REPAIR BY PICKING A NUMBER: 10 and 11 are each correct under one reading, so choosing is a referent decision, not arithmetic - the same decision the operator took for the MCP-calls line, and it has not been taken for this field. Two candidate forms, neither ratified: drop the URL wording so the field counts sources only, or keep URLs and restate as 11. Raised as an open operator question in STATE.",
"summary": "Booked while closing idx-26n, from the check the ratified form requires on what REMAINS in a footer after the MCP-calls line is deleted - the defect sits next to the edit, now for the twelfth time. '**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research' states both a source count and a URL count in one line, and they differ. MEASURED, not inferred: the Kilder section carries 10 numbered entries but 11 distinct URLs, because entry 8 (A2A Protocol Specification) lists two - https://a2a-protocol.org/latest/specification/ and https://a2a-protocol.org/latest/announcing-1.0/. So the line is TRUE read as 'sources cited' and FALSE read as 'unike URLer', and it says both. This is the undefined-referent defect the whole footer class is about, surviving INSIDE the line the ratified form told us to keep and verify - the form presumed kept counts would pass and does not say what to do when one fails. DIRECTION MATTERS AND WAS CHECKED: stated 10 < actual 11 runs the same way as all eight MCP-calls inconsistencies measured corpus-wide, with zero running the other way. DO NOT REPAIR BY PICKING A NUMBER: 10 and 11 are each correct under one reading, so choosing is a referent decision, not arithmetic - the same decision the operator took for the MCP-calls line, and it has not been taken for this field. Two candidate forms, neither ratified: drop the URL wording so the field counts sources only, or keep URLs and restate as 11. Raised as an open operator question in STATE.\nMEASURED 2026-08-12, AND THE #21 INHERITANCE IS REFUSED ON MEASUREMENT RATHER THAN ON CAUTION. The session arrived here believing this line was word-for-word idx-26w and therefore already settled by #21. IT IS NOT, and the difference is exactly the thing #21 turns on. GROUND TRUTH, :732: \"**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research\". idx-26w reads \"fra MCP-research\" ALONE. #21 fires only where the provenance qualifier OVERCLAIMS; here it does not, because the qualifier names the web-research leg that covers precisely the URLs the microsoft-learn server cannot serve - a2a-protocol.org (x2), linuxfoundation.org, developers.googleblog.com. Independently corroborated BEFORE this session measured it: idx-26w own summary already drew this contrast in writing, naming the neighbouring line as one that \"does cover its non-Learn sources\". Three sources agree, so the non-overclaim is not this session reading.\nURL CENSUS, two populations, run rather than argued. Kilder section (:670-end): 11 URL occurrences, 11 distinct - 7 learn.microsoft.com, 2 a2a-protocol.org, 1 linuxfoundation.org, 1 developers.googleblog.com - across 10 numbered entries, entry 8 carrying two. Whole file: 14 distinct, the three extras being code-sample hosts (agents.nav.no, two example.com) that no reading counts as kilder. SO THE COUNT IS 10 AS SOURCES AND 11 AS UNIQUE URLS, and the line says \"unike URLer\" while giving the source number. The defect is the referent of the count, NOT the provenance of it - a different defect from idx-26w, which is why the same-form reading fails twice over.\nALL SIX RATIFIED FORMS EXCLUDED, each against its own stated condition: #21 needs an overclaiming qualifier (measured false). #22 classifies this line KEEP, not delete - its referent is the artifact - so it governs the line only to preserve it, and #22 assumed keep-class meant adjudicable, which this line falsifies: it is countable twice, to two different numbers. #23 needs a mixed delete/keep line; there is no delete-class half here, no generation referent anywhere in the line. #24 needs a header parenthetical. #25 needs a delete-class count restated in-line; there is no delete-class count to remove. #26 is scoped to one other file by its own text.\nTHE DECISION OWED, unchanged in substance from the original booking but now with the arithmetic settled: 10 and 11 are each correct under one reading, so this is a referent choice and not a calculation. Candidate A, drop the referent word so the field counts what its own name says: deleting the contiguous fragment \" unike URLer\" leaves \"**Total sources cited:** 10 fra MCP-research + tavily-research\" - grammatical, grounded in the 10 numbered entries, ZERO words authored, and the field name already says \"sources cited\". Candidate B, keep URLs as the referent and restate 10 as 11 - which authors a number, the idx-26v hazard. Candidate A satisfies all three of #25 conditions but NOT #25 scope, since nothing being deleted is a delete-class count; it therefore needs its own ratification rather than inheritance.",
"evidence": "footer of this file (last line after the idx-26n deletion); Kilder section entries 1-10, entry 8 carrying two URLs; idx-26n resolution; idx-26j scope addendum 2026-08-09",
"anchors": [
"**Total sources cited:** 10 unike URLer fra MCP-research + tavily-research"