Ask the chip which decoder it is, and find four wrong axes where one was expected

ROADMAP P6a, on the machine. 68000 code programs HD63450 channel 3 with the
IPL ROM's own ADPCM bytes -- dual address, 8-bit port, cycle steal, external
request -- and feeds the MSM6258 a designed 1,678-nibble stream at the chip's
own pace: 839 B in 0.1074 s = 7,811.4 B/s against the format's 7,812.5, CER=$00.
That transport is P6b's, not scaffolding.

Sixteen candidate decoder models, three capture decimations and a searched
prologue are fitted to MAME's capture. Exactly one reproduces it sample-exact
over all 1,678 samples, and every axis carries a negative control: flip it
alone and the closest survivor disagrees on 826, 1,504, 156 and 1,522 samples.

The chip runs 'terms', takes the LOW nibble of a byte first, clamps the
accumulator at 10 bits and starts it at -2. tools/encoder/adpcm.py defaulted to
the opposite of all four, and 65.2 named the wrong axis as the risk: the delta
formula is worth -2.88 dB and the NIBBLE ORDER is worth -25.74 dB. 65.1's "high
first, measured" was a measurement of ffmpeg, i.e. of the VOX file convention,
which is a different question from what a chip does with a byte in its data
register.

The 10-bit clamp is free on the Singe window and only because that window peaks
at 435 of 511 -- 1.4 dB of headroom on a -13.4 dBFS passage, 12.1 dB below where
the encoder was clamping, and inside the recursion. So the audio level is an
open choice again, downward, and the loudest passage on the disc is unmeasured.

Session 33's silence had two ordinary causes: the PPI's port C is an input until
control word $92 says otherwise, and $01 is COMMAND_STOP. And a rig fact worth
the space: the 8 MHz ADPCM clock is CT1 in the YM2151's $1B, delivered on the
sound system's schedule rather than at the store, so a transfer started in the
same breath as the setup plays its first ~17 ms at the old clock and no model
fits a stream that changed rate part way through.

Name the layer: this is MAME 0.277's okim6258 device model measured end to end
through the machine's real transport. It settles the rig and not the silicon.
Also struck: 64.4's "no MAME source tree is on this machine" -- there is none on
disk, but the machine has network and the upstream tag fetches.

check.sh ALL GREEN before (tmp/check_s34_start.log) and after
(tmp/check_s34_end.log), with one new stage.

Claude-Session: https://claude.ai/code/session_01194oWYW8DQXK1SZ2DnChW6

tools/bench/check.sh

@@ -753,4 +753,21 @@ python3 tools/analysis/32_audio_wire.py tmp/packed_singe.dlxp \
   > tmp/audio_wire.log 2>&1 || { cat tmp/audio_wire.log; exit 1; }
 grep -aE "^  (   1|  11|  81) |THE FLOOR|F=1 |F=11|is ZERO|SOUND IS WHAT" tmp/audio_wire.log
 
+echo "--- session 34: THE CHIP'S OWN DECODER, off the machine (FINDINGS 66) ---"
+# ROADMAP P6a. 68000 code programs HD63450 channel 3 exactly as the IPL ROM
+# programs it and feeds the MSM6258 a designed nibble stream at the chip's own
+# pace; ONE of sixteen candidate decoder models reproduces MAME's capture
+# sample-exact, and every axis has a negative control. The encoder disagreed
+# with the chip on ALL FOUR axes, and the largest of them is not the delta
+# formula 65 named -- it is the NIBBLE ORDER, at -25.7 dB.
+bash tools/bench/adpcm_run.sh > tmp/adpcm_gate.log 2>&1 || {
+  cat tmp/adpcm_gate.log; exit 1; }
+grep -aE "^(OK|FAIL) |^     (feed|nibbles|delta|clamp|accumulator)" tmp/adpcm_gate.log \
+  | sed 's/^/  /'
+# And the bill, on the same ten seconds every other audio figure is quoted on.
+python3 tools/analysis/33_adpcm_model.py tmp/au_singe.raw > tmp/adpcm_model.log 2>&1 \
+  || { cat tmp/adpcm_model.log; exit 1; }
+grep -aE "wrong only here|played on the chip|decoded on the encoder|headroom left" \
+  tmp/adpcm_model.log
+
 echo "ALL GREEN"