Development record
itd-98 leaves model-level benchmarking to itd-17; itd-2609221009495079 records itd-17 as superseded
issueopennitpickiss-2610262043598494
itd-98 leaves model-level benchmarking to itd-17; itd-2609221009495079 records itd-17 as superseded
A sequencing impossibility (severity nitpick) found by the cross-document consistency pass.
- End A:
.abcd/development/intents/drafts/itd-98-solo-vs-duo-is-measured-not-debated.md:68— "itd-17 and itd-64 own model-level" - End B:
.abcd/development/intents/planned/itd-2609221009495079-abcd-s-typed-judgements-can-run-through.md:52— "A learned per-request router for lane models (itd-17, superseded)."
itd-98 keeps model benchmarking out of its own scope because itd-17 and itd-64 own it. itd-2609221009495079 marks itd-17 as superseded and excludes its learned-router scope. Half of the dependency itd-98 names points at a record that no longer exists to satisfy it.
Evidence: .abcd/work/reviews/2026-10-26-consistency/00-summary.md, finding 1176.
Frontmatter
| id | iss-2610262043598494 |
|---|---|
| type | issue |
| lifecycle | open |
| severity | nitpick |
.abcd/work/issues/open/iss-2610262043598494-itd-98-leaves-model-level-benchmarking.md
open on GitHub ↗ · commit history ↗
References2
- itd-98Solo vs. Duo Is Measured, Not Debatedrelated
- itd-2609221009495079abcd's typed judgements can run through a decision adapter, measured in a lab before it decides anythingrelated