docs(ENG-EXPERT-STREAM-DEVICE): a decode figure called VOID one row above its replacement (#1442)

[localai-bot]

Two public pages and one row record all told a reader the streaming-ON decode
figure was void, after the measurement that replaced it had landed.

The public cells

docs/BENCHMARKS.md:8, the ENG-EXPERT-STREAM row, read "Streaming-ON decode
VOID (#912 F1); re-measure owed" while line 9, the row directly under it,
recorded 11.05 s/token at 4000 slots against a live cache with a decode-phase
exhausted delta of 0, explicitly as replacing that VOID figure.
docs/STATUS.md:129 also carried the VOID. A reader got the answer that
depended on which row they read first.

The two cells never said the same thing, so the repair is stated per file:

• docs/BENCHMARKS.md:8 named no cause and its replacement was one line down.
  It keeps its **VOID** (#912 F1) and now reads "re-measured LIVE by
  ENG-EXPERT-STREAM-DEVICE" where it said "the next row". A positional
  pointer breaks the moment a row is inserted above it, and no checker
  validates one; the table holds 253 rows, measured with the checker's own
  _table_rows parser.
• docs/STATUS.md:129 never said a re-measure was owed, and its replacement is
  not adjacent: that figure is at docs/STATUS.md:167, 38 rows further down
  the SAME table, which runs 126-190 as one unbroken block. It keeps the cause
  verbatim, the step clock that had no caller, and gains the same named
  pointer.

Neither cell repeats 11.05 s/token. docs/BENCHMARKS.md:9 and
docs/STATUS.md:167 already carry it, and one number stated in two keyed rows
is what lets the two drift apart.

The row record said the same thing one level down

.agents/specs/expert-streaming.md's ## Owed still read "Re-measure decode
on a LIVE cache ... is void", with its "why it is open" naming an unreachable
dgx.casa. So a fixed public cell routed a reader to the row record and the
row record told them the measurement was still owed and blocked. The entry is
struck as CLOSED by ENG-EXPERT-STREAM-DEVICE W0e and kept as a line, using
the convention the sibling spec already uses, because the void's cause is what
shaped the replacement: EndStep() had no caller, protected_this_step never
cleared, and every slice from partway through token 3 came from the mmap, which
is why W0e gates exhausted on its decode-phase DELTA rather than on a total.

.agents/specs/expert-stream-device-slots.md's ## Owed listed issue 1387 as
open while the same flow closed it. Struck, with the measured evidence beside
it and with issue 573 named as the surviving half.

Evidence for the figures

The re-measure stopped being owed at c805ccbb3, recorded in
.agents/benchmark-record.md under ENG-EXPERT-STREAM-DEVICE W0e: 11.05 is
rep 2's median over steps 4 to 32, and rep 1's 11.22 sits 1.54% above it. The
8000-slot arm is not a second figure for the same thing; it measures 39.98 to
45.40 s/token and consumed all 30,625 MiB of swap, which that record reads as
page-cache displacement and states as a reading of its columns rather than a
proven mechanism. No CUDA number moves: e67b2a4ba makes --device cuda
decode 32/32 steps at peak RSS 97.75 GiB, G0-CORRECT fails on a step-7 near-tie
whose cause is not identified, and the row's own stop condition therefore
leaves G0-SPEED VOID.

What the pointer cost the cell

The pointer clause grew 31 characters, from ; re-measure owed at 17 to
; re-measured LIVE by ENG-EXPERT-STREAM-DEVICE at 48. Two edits paid for it
and both belong in this sentence, because the second alone does not cover it:
the words "as 4 KiB faults" came out at 16 characters, and dropping bold from
three supporting numbers and moving "streaming OFF" out of parentheses freed 13
more. 31 against 29 is the +2 that takes the cell from 215 on main to 217
here, inside the 220 budget. No fact was lost. The 4 KiB demand-fault mechanism
survives verbatim at .agents/benchmark-record.md:22198 and
.agents/specs/expert-streaming.md:880, which is where this page's own legend
sends a reader, and the index row discloses the displacement in full. Bold now
marks the claim and the verdict. docs/STATUS.md's cell measures 195, and that
page's oversized_cells ratchet sits at 44 of 44, unmoved by this change.

No gate catches this class, by design. The rows are keyed on different IDs, so
check-public-doc-tables.py sees well-formed rows and check-agent-record.py
sees individually consistent lifecycle states, and no checker here compares a
claim in one keyed row against a claim in another.

The index row is corrected in place

.agents/issue-index.md is append-only. This row is corrected rather than
superseded by a second row, and the reason is the rule's own reason:
check-issue-index-append-only.py evaluates one aggregate diff against the
merge base, and its docstring says a union merge duplicates an EDITED line,
which needs that line to exist on both sides. Verified rather than assumed: the
row appears in no ref but this branch, checked across all 513 remote heads, and
git show origin/main:.agents/issue-index.md | grep -c returns 0 where the
same command on HEAD returns 1, so the absence comes from an instrument
proven to fire. The net diff against the merge base is one added line and no
removed line. Appending a second row for the same issue would leave a duplicate
key in an append-only log. This is flagged rather than done silently, and it is
not a precedent: the argument holds only while no other branch carries the row.

Gates

Run from this worktree's own scripts/, exit status captured unpiped, after
merging origin/main 4cde4762a: check-agent-record 0, re-run after the
merge; check-public-doc-tables 0, re-run after each edit; check-now-current
0; check-conflict-markers 0, the gate #1450 had just landed;
check-doc-checkpoint --base origin/main --head HEAD 0;
check-issue-index-append-only --base origin/main --head HEAD 0, with a
detached scratch commit editing row 168, a row that DOES exist on main, as
its positive control at 1 and the mutation proven applied by git diff --stat;
check-commit-trailers --range origin/main..HEAD 0; check-commit-style --range origin/main..HEAD 0; git grep -n '^<<<<<<< \|^>>>>>>> ' 1 with a
two-line fixture as its positive control at 0.

agent-preflight.sh reports one red, test_cpu_x86_llamacpp_floor, which
exits 4 NO_QUIET_WINDOW where its case asserts 2, at one-minute load averages
of 49.77, 52.96, 58.34 and 211.99 across four observations. That is the load
dependence tracked in issue 618. A quiet re-run was attempted and could not be
taken: the box was polled for 30 minutes and never fell below load 8, peaking
at 126. The independence argument is structural instead: this branch changes
five files, all .agents/ or docs/ Markdown, so neither the test nor
anything it drives differs from origin/main.

Issue 1387

It gets no product change here, and the reason is evidence rather than scope.
Its record half already landed: the stale string "CPU keep-quant towers only"
is absent from docs/FEATURES.md on origin/main and present at
5f4eb356e^, which is the positive control for that grep. 5f4eb356e (#1377)
wrote the row and e67b2a4ba (#1427) refined it again, so the page names the
staging device and both accepted residencies, keep-quant and keep-f16. Its
checker half, whether a per-commit record gate should be satisfiable after the
commit is published, is issue 573 and stays open under
ENG-RECORD-CONFLICT-SURFACES. This branch touches no file under scripts/.

Closes #1442

FOLLOWING_AGENTS_PROTOCOL

Following-Agents-Protocol: true
AI-Assisted: true
Assisted-by: AGENT:claude-opus-5 [Claude Code]