STATE bar påstanden «uverifisert: om FoundryChatClient kan binde en Claude-
deployment» som en bisetning. Operatøren ba om at slikt ikke får ligge. Målt mot
Microsoft Learn i stedet, og antakelsen er FALSIFISERT.
Claude-modeller solgt via Azure Marketplace kalles med Anthropics egen Messages
API på en egen endepunkt-form:
https://<resource>.services.ai.azure.com/anthropic/v1/messages <- Claude
https://<resource>.services.ai.azure.com/api/projects/<project> <- FoundryChatClient
Klienter: `anthropic`-pakka, `@anthropic-ai/foundry-sdk`, eller REST med
`anthropic-version: 2023-06-01`. Kun /v1/messages og /v1/messages/count_tokens er
eksponert på «Hosted on Azure»-versjonen. Deployment-navnet er `model`-parameteren.
Konsekvens for M1 (fase 1b), og den er en BESLUTNING, ikke en detalj:
- Microsoft-solgt modell (gpt-5-mini o.l.) -> 1b er REN KONFIG, azure-profilen
som shippet er riktig søm, ingenting å bygge.
- Claude -> 1b krever en NY BACKEND-PROFIL i produksjonskode.
Samme klasse som notatet under «Endpoint format»: *.openai.azure.com og
*.cognitiveservices.azure.com er andre flater igjen. Tre flater, én ressurs-host.
Samme pass fanget forutsetningene som gater portalarbeidet: Marketplace-subscribe-
tillatelse, Contributor/Owner på ressursgruppa, prosjekt i støttet region, og data
retention PÅ abonnementet for Covered Models (ZDR gir 400, og Microsoft kan ikke
endre det for deg).
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X737cbkG2uAXJ2Bvhf6X5M
Operator ruling 2026-08-05, which settles decision (g): planning documents are
generally never public, and what OUR OWN sessions generate does not go out on
the forge at all. The example itself stays public so others can run the
process.
`.claude/projects/` is the Voyage session workbench -- 25 briefs/plans/reviews
this project's own sessions produced. Untracked and gitignored, exactly as
STATE.md already is, and for the same stated reason: this repo has a public
mirror, so that class of material is local-only rather than tracked.
The line is drawn at who wrote the document, and it is drawn deliberately:
`docs/plan/`, `docs/research/` and `docs/rapport/` stay tracked. Those are
curated, dated documents written for the repo's readers, three of them linked
from the README as the decision record. Move that line if it was meant wider.
Two files were NOT process artifacts and are not deleted. Both
`build_fixture.py` scripts are cited by tracked tests
(`test_ingest_golden_sql.py`, `test_ingest_golden_http.py`) as the documented
rebuild path for byte-exact goldens -- reproduction code that had landed in the
wrong directory. Moved next to the goldens they build; both docstrings updated,
so no tracked file is left pointing into an untracked tree (verified: the only
remaining `.claude/projects` string in a tracked file is the .gitignore rule
itself). One prose reference in the dated Foundry auth recipe was dropped for
the same reason.
652 tests still pass.
Does NOT address the 27 of these already readable on open/ since the S12
release -- untracking stops future publication only. That retraction is a
separate operator decision and is deliberately not taken here.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01GWsexbQjPo9rsV3aUE54ZS
