fix(ms-ai-architect): idx-27 scope-addendum — orkestrerings-FAQ-ens rekkevidde skilt fra generative answers

Adversarielt gjenlest resolution avdekket at BEGGE reparerte påstander ble
skrevet inn under overskriften «Microsoft Copilot Studio» uten kvalifikator,
mens FAQ-ens egen scope-linje er «generative orchestration». Samme utvidings-
klasse som idx-27 ble reist for — reprodusert av sin egen reparasjon.

Sjekket mot dokumentasjonen, og de to påstandene falt fra hverandre:
- bekreftelses-sikringen står KUN i orkestrerings-FAQ-en → kvalifikator lagt til
- standardmeldingen står ordrett også i faqs-generative-answers, med bredere
  ramme → raden beholder ingen kvalifikator, og den andre FAQ-en er lagt til
  som sitert kilde så lesningen kan etterprøves

Standing: grounded-as-cited, ikke established-for-all-agents.
Kø: 6 åpne / 6 resolved. Suite 1047/1047.

[skip-docs]
This commit is contained in:
Kjell Tore Guttormsen 2026-08-03 22:14:42 +02:00
commit 66fb567ec6
3 changed files with 30 additions and 4 deletions

View file

@ -1081,6 +1081,31 @@ above. idx-26e was found by a **cross-file grep run before the edit** — the ch
asks whether a rename here creates an inconsistency there. It did not, but it found a
mirror the corpus was not known to contain.
**A scope defect caught in the resolution itself, before the closing line.** An
adversarial read of the idx-27 write-up asked a question the repair had not: the FAQ's
own scope line reads "the AI impact of **generative orchestration** for custom agents
built in Copilot Studio", and both repaired claims had been written into a section
headed *Microsoft Copilot Studio* with no qualifier. That is the widening class idx-27
was raised for, reproduced by its own repair — §9.7's pattern for a third time, and
§9.8's dropped-qualifier pattern for a second.
**Re-checked against the docs rather than reasoned about, and the two claims came
apart.** The maker-confirmation safeguard occurs *only* in the orchestration FAQ, in a
list about tool execution — orchestration-scoped, and the bullet now says so. The
default transparency message occurs there **and, verbatim, in `faqs-generative-answers`**
under the same protections question, framed there as a general best practice rather
than an orchestration feature. Two independent feature FAQs stating it without a
feature qualifier is why the Built-in disclosures row keeps none; the second FAQ was
added as a cited source so a reader can check that reasoning instead of trusting it.
Neither page is a Copilot-Studio-wide statement of record, so the standing is
**grounded-as-cited, not established-for-all-agents**.
The transferable part is not the fix. **A repair inherits the defect class it was
raised against unless something explicitly re-asks the question of the repair.** The
edit was correct on the axis the entry named (modality) and wrong on the axis it did
not (scope), and the resolution prose read as complete precisely because it answered
the named axis well.
**Queue state: 6 open, 6 resolved.** Suite 1047/1047.
## Appendix A — the 15 admitted proposals, hand-verified