Skip to content

record(MODEL-MUSIC-MUSIC3): the row is ACTIVE, and the spec now meets the ACTIVE contract (#672) - #723

Merged
localai-bot merged 1 commit into
mainfrom
row/MUSIC3-W0-CLOSE
Aug 14, 2026
Merged

record(MODEL-MUSIC-MUSIC3): the row is ACTIVE, and the spec now meets the ACTIVE contract (#672)#723
localai-bot merged 1 commit into
mainfrom
row/MUSIC3-W0-CLOSE

Conversation

@localai-bot

Copy link
Copy Markdown
Collaborator

Records only. No src/, include/ or tests/ change.

W0 is done and W1 has landed, so the row's state was stale at SPIKE while real
loader code sat in the tree. Advancing it surfaced two things worth recording
rather than quietly fixing.

The ACTIVE contract is enforced, and the spec did not meet it

Moving the row to ACTIVE turned check-agent-record red on nine missing
structured fields — Scope, Upstream chain, Our baseline, Port map, Tests to port,
Gates, Dependencies, Work breakdown, Risks/decisions. A SPIKE spec is not held
to that; an ACTIVE one is.

My first attempt added them as prose sections and stayed red on all nine —
including the two the spec already had — because the checker does not read
headings at all. It reads table rows whose first cell names the field. Fixed
by writing the structured record in the shape minimax-h3.md already uses,
rather than by arguing with the gate. The failure was mine reading the
requirement as prose; the checker's message was right both times.

A wording fix that cost two implementers

§3 said both pins "go into .agents/oracles/ in W0" — future tense.
sglang-omni.md has existed since #679, yet agents reported it as still owed
three times. A record surface described in the future tense reads as a TODO
no matter what the tree holds. Now present tense, with links and a note saying
why.

What the row now claims, and nothing beyond it

oracle gateable = yes, 13 committed per-stage goldens (#708)
loader 1413/1413 assertions on the real 27 GB checkpoint, 1012 tensors accounted, native arm refused by name (#714)
checklist 📋 → 🚧; rollup SPIKE 9 → 8, ACTIVE 9 → 10

The lifecycle move owes STATUS, BENCHMARKS, FEATURES and the spec's ## Now, and
all four say what the row says. BENCHMARKS records every axis PENDING with
none owed yet
, and why: W0/W1 are correctness scaffolding, the oracle capture
was CPU-only because dgx.casa was down, and there is no forward pass to time. A
row with landed code is exactly where a speed claim tends to appear by
implication, so the absence is written down rather than left to be inferred.

Both public rows were first written over the house-style limits (a 402-char
BENCHMARKS cell; STATUS at 45 oversized cells against a 44 ratchet that may only
shrink). Shortened to fit rather than lowering a ratchet to accommodate prose.

Gate: check-agent-record OK (MODEL=373), check-model-checklist OK,
check-oracle-pins OK (8 pinned), check-public-doc-tables OK,
check-doc-checkpoint --base origin/main OK.

🤖 Generated with Claude Code

… the ACTIVE contract (#672)

W0 is done and W1 has landed, so the row's state was stale at `SPIKE` while real
loader code sat in the tree. Advancing it is what surfaced two things worth
recording rather than quietly fixing.

THE ACTIVE CONTRACT IS ENFORCED, AND THE SPEC DID NOT MEET IT. Moving the row to
`ACTIVE` turned check-agent-record red on nine missing structured fields -- Scope,
Upstream chain, Our baseline, Port map, Tests to port, Gates, Dependencies, Work
breakdown, Risks/decisions. A `SPIKE` spec is not held to that; an `ACTIVE` one is,
which is the checker doing exactly its job. My first attempt added them as PROSE
SECTIONS and stayed red on all nine, including the two the spec already had --
because the checker does not read headings at all, it reads TABLE ROWS whose first
cell names the field. Fixed by writing the structured record in the shape
`minimax-h3.md` already uses, rather than by arguing with the gate. Worth stating
plainly: the failure was mine reading the requirement as prose, and the checker's
message was right both times.

SECOND, A WORDING FIX THAT COST TWO IMPLEMENTERS. §3 said both pins "go into
`.agents/oracles/` in W0", which reads as future work. `sglang-omni.md` has existed
since #679, yet two separate agents reported it as still owed -- the same agent
twice. A record surface described in the future tense reads as a TODO no matter
what the tree holds, so it is now present tense with links, plus a note saying why.
That is a small edit that stops a recurring false report.

WHAT THE ROW NOW CLAIMS, and nothing beyond it: oracle gateable with 13 committed
per-stage goldens (#708), modular loader gated 1413/1413 against the real 27 GB
checkpoint with all 1012 tensors accounted and the native arm refused by name
(#714). Checklist mark 📋 -> 🚧; rollup SPIKE 9 -> 8, ACTIVE 9 -> 10.

The lifecycle change owes STATUS, BENCHMARKS and the spec's `## Now`, and all
three say the same thing the row does. BENCHMARKS records every axis PENDING with
NONE OWED YET and says why: W0/W1 are correctness scaffolding, the oracle capture
was CPU-only because dgx.casa was down, and there is no forward pass to time. A
row that has landed code is exactly where a speed claim tends to appear by
implication, so the absence is written down rather than left to be inferred.

Both public rows were first written over the house-style limits (a 402-char
BENCHMARKS cell, and STATUS at 45 oversized cells against a 44 ratchet that may
only shrink). Shortened to fit rather than lowering a ratchet to accommodate
prose.

Issue: #672

FOLLOWING_AGENTS_PROTOCOL

Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: AGENT:claude-opus-5 [Claude Code]
@localai-bot
localai-bot merged commit 7a0e6c8 into main Aug 14, 2026
9 of 16 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants