fix(lanes): tells draws a SMALL band — the lane gap was a card-SIZE gap

Joined the campaign ledger to each wave's cards and to the functions its own commit
banked (removed INCLUDE_ASM lines), pooled over bb/bg (tells) vs bc/bf (default):

  nins      default        tells
  0-50      303/528  57%   27/ 67  40%
  50-80      43/145  30%   20/ 73  27%
  80-120      9/ 41  22%   10/100  10%
  120-200     1/ 30   3%    1/ 68   1%
  200+        2/ 35   6%    0/ 30   0%

At equal size the lanes are close below 80 instructions and both collapse above it.
What separated them is the card size MIX: default's cards are median 37-39 ins, the
tells pool median 89-95 (2.4x), so 'the tells lane is broken' measured the population,
not the lever. Tells now draws 5-80.

This also refutes the S58 handoff's one live hypothesis for tells (235, the phantom
symbol). Checked the recorded reloc_identity verdicts first (R38): among MISMATCH?
rows, the fraction whose instruction SHAPE already matched — the symbol-only class 235
describes — is 25/87, 16/79, 17/66, 13/57 on default waves but 6/66, 4/81, 5/47 on
tells. Tells drafts fail because the BODY is wrong, not the symbols, which is what a
2.4x larger median predicts.

Also adds tools/lanes/relaunch_drafter_shell.sh. bash parses a while...done body in
full before running it, so a lane-ARG change is invisible to the running shell and a
python bounce re-runs the OLD command line — measured at 11:02, when the bounced
python came back on the pre-S59 lane list 18 minutes after the file changed.

tools/lanes/drafter.sh

@@ -22,9 +22,23 @@
 # name symbols the target .s never references, i.e. cookbook §235 (the phantom symbol), which is a
 # BRIEF fix, not a lane deletion. R40: exonerate the instrument before blaming the subject.
 #
-# The rotation below pins the arithmetic: lane = index%4, band = index%4, so slot 1 (tells) always
-# draws the full band and slot 3 (the large band) is always default. Changing the length of either
-# list breaks that alignment — change both together.
+# S59 REFINEMENT, from the same ledger joined to the wave cards and to the BANKED FUNCTIONS the
+# wave's own commit names (bank rate by size, cards->banked, pooled over waves bb/bg vs bc/bf):
+#   nins    default        tells
+#   0-50    303/528  57%   27/ 67  40%
+#   50-80    43/145  30%   20/ 73  27%
+#   80-120    9/ 41  22%   10/100  10%
+#   120-200   1/ 30   3%    1/ 68   1%
+#   200+      2/ 35   6%    0/ 30   0%
+# At EQUAL SIZE the two lanes are close below 80 instructions and both collapse above it. What
+# actually separated them is the card SIZE MIX: default's cards are median 37-39 ins, the tells
+# pool is median 89-95 — 2.4x larger — so "the tells lane is broken" was measuring the population,
+# not the lever. Tells therefore draws a SMALL band (5-80), where its yield is within a few points
+# of default's; widen it only when that stratum is worked out.
+#
+# The rotation pins the arithmetic: lane = index%4, band = index%4, so slot 1 (tells) always draws
+# the small band and slot 3 (the large band) is always default. Changing the length of either list
+# breaks that alignment — change both together.
 #
 # NOTE: do NOT assume aprop_autodraft is the answer for tells. Its input population overlaps the
 # 1,040 tells member functions by only 44 (4.2%) — checked, after asserting the opposite three
@@ -45,7 +59,7 @@ while [ ! -e .run/ox_campaign.stop ]; do
       --workers 2000 \
       --models 'stealth/ox-alpha:1720,deepseek/deepseek-v4-flash-0731:280:REASON_EFFORT=high' \
       --lanes 'default:,tells:extend-tell;swaprepeat-tell;s16-div-tell,default:,default:' \
-      --bands '5-2000,5-2000,5-2000,120-2000' \
+      --bands '5-2000,5-80,5-2000,120-2000' \
       --cards-per-wave 3000 --queue-depth 2 2>&1
   echo "[$(date +%H:%M:%S)] [drafter] exited; restarting in 20s"
   sleep 20

tools/lanes/relaunch_drafter_shell.sh

@@ -0,0 +1,30 @@
+#!/usr/bin/env bash
+# Wait for the in-flight wave to QUEUE, then restart the drafter SHELL (not just its python).
+#
+# WHY THE SHELL. bash parses a `while … done` compound command in full before executing it, so the
+# loop body — including the python command line — is fixed in memory for the life of that shell.
+# Editing .run/drafter.sh, or bouncing only the python, therefore re-runs the OLD arguments: at
+# 11:02 the bounced python came back on the pre-S59 lane/band list even though the file on disk had
+# been updated 18 minutes earlier (it logged `lane tells, band (5, 2000)`, which only the old list
+# produces at rotation index 36). A lane-ARG change needs a fresh shell; only a lane-CODE change
+# (tools/*.py) is picked up by a python bounce.
+#
+# Cost is one shell exec, taken at the moment a wave has just queued, so no drafts are lost.
+set -u
+cd /home/musashi/bfm-decomp
+BEFORE=$(ls .run/ready/ 2>/dev/null | wc -l)
+DEADLINE=$(( $(date +%s) + 5400 ))
+say(){ echo "[$(date +%H:%M:%S)] [relaunch] $*"; }
+say "waiting for a new ready marker (have $BEFORE)"
+while [ "$(ls .run/ready/ 2>/dev/null | wc -l)" -le "$BEFORE" ]; do
+  [ "$(date +%s)" -ge "$DEADLINE" ] && { say "deadline passed — NOT restarting"; exit 1; }
+  [ -e .run/ox_campaign.stop ] && { say "campaign stopped"; exit 0; }
+  sleep 30
+done
+say "a wave queued; restarting the drafter shell"
+pkill -f 'bash .run/drafter.sh' 2>/dev/null || true
+pkill -f 'ox_campaign.py --drafter' 2>/dev/null || true
+sleep 3
+setsid nohup .run/drafter.sh >> .run/drafter.log 2>&1 < /dev/null &
+sleep 20
+say "new rotation line:"; grep 'resuming rotation' .run/drafter.log | tail -1