"Delivered speech vs derived artifact" is the line I should have drawn, and it's closer to where we landed than my original one. Since the post, the transcript replays turns as they were shown, cards included; a revoked capability now governs the next turn, not the record (note at the top).
That makes your provenance stamp more relevant, not less. If the record replays as seen, the honest version tells the reader the capability behind it is no longer granted, and the replay response carries no field for that today. "A card wearing prose" is the right name for the verbatim-quote case, too.
On timing: the existence oracle you're worried about is unknown-vs-foreign session id, and both go through the same owner-scoped lookup (session id, tenant and user in one WHERE), so same query, same plan. Malformed ids short-circuit before any query, but a malformed id reveals nothing about existence. Entitlement denial left the 404 bucket entirely: it's a typed 403 now, the same answer the turn gate gives, and it only tells a caller something about their own org. I still haven't put a number on any of it, and you're right that it's the first measurement to run.
Do come back with the supersession-banner result. That kind of leak never shows up in a response-shape test, which is the whole case for not-awaited assertions
For further actions, you may consider blocking this person and/or reporting abuse
We're a place where coders share, stay up-to-date and grow their careers.
"Delivered speech vs derived artifact" is the line I should have drawn, and it's closer to where we landed than my original one. Since the post, the transcript replays turns as they were shown, cards included; a revoked capability now governs the next turn, not the record (note at the top).
That makes your provenance stamp more relevant, not less. If the record replays as seen, the honest version tells the reader the capability behind it is no longer granted, and the replay response carries no field for that today. "A card wearing prose" is the right name for the verbatim-quote case, too.
On timing: the existence oracle you're worried about is unknown-vs-foreign session id, and both go through the same owner-scoped lookup (session id, tenant and user in one WHERE), so same query, same plan. Malformed ids short-circuit before any query, but a malformed id reveals nothing about existence. Entitlement denial left the 404 bucket entirely: it's a typed 403 now, the same answer the turn gate gives, and it only tells a caller something about their own org. I still haven't put a number on any of it, and you're right that it's the first measurement to run.
Do come back with the supersession-banner result. That kind of leak never shows up in a response-shape test, which is the whole case for not-awaited assertions