From 0ae923b879a78d0166224e36006d89b3af66cc24 Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Fri, 2 Oct 2026 23:52:04 -0700
Subject: [PATCH] autoresearch arms: add D/E context arms (KV 4.05e9 = 2.00x
 under MTP3; E adds MNBT 4096 + util 0.99)

---
 scripts/autoresearch/frank-primary-arms.sh | 38 ++++++++++++++++++++--
 1 file changed, 36 insertions(+), 2 deletions(-)

diff --git a/scripts/autoresearch/frank-primary-arms.sh b/scripts/autoresearch/frank-primary-arms.sh
index 90caa3d..5093bea 100755
--- a/scripts/autoresearch/frank-primary-arms.sh
+++ b/scripts/autoresearch/frank-primary-arms.sh
@@ -72,18 +72,52 @@ OVER_C=(
     'FRANK_PRIMARY_UTIL=0.95'
 )
 
+# D/E: the CONTEXT arms. Measured 2026-10-02 (arms run 20261002T233855Z): the
+# KV pool is a hard byte request divided by a PER-TOKEN PRICE, and MTP raises
+# that price because the drafter keeps its own KV per position:
+#   no spec: 3.15e9 / 398,658 tokens =  7,901 B/token  (1.99x of 200,704)
+#   MTP3:    3.15e9 / 313,002 tokens = 10,064 B/token  (1.56x)
+# So arm C lost a fifth of the context to the drafter, not to util. Frank's
+# contract is >=401,400 tokens over >=2 seqs = 2.00x of 200,704, which at
+# 10,064 B/token costs 4.04e9 -> ask 4.05e9 (+0.83 GiB/rank).
+# D is arm B with EXACTLY ONE variable changed (the KV bytes), so its result
+# says whether the 4k-depth collapse (B 23.09 vs baseline 33.99) was KV or the
+# batch shape.
+KV401K='FRANK_PRIMARY_KV_BYTES=4050000000'
+OVER_D=(
+    "FRANK_PRIMARY_SPEC='$SPEC3'"
+    "FRANK_PRIMARY_COMPCONFIG='$LADDER3'"
+    'FRANK_PRIMARY_GEN_CONFIG='"'$GEN07'"
+    "$KV401K"
+)
+# E: D with C's max_num_batched_tokens (4096 — C is the only arm that did NOT
+# collapse at 4k depth: 33.15 where B gave 23.09) and util 0.99, the value
+# Frank asked about. 0.99 is affordable on paper — production at util 0.98
+# measures 30.37/34.21 GiB per card, 3.58 GiB physically unused — but it leaves
+# only 0.32 GiB above the allowance while the CUDA-graph cost is an ANALYTIC
+# estimate (C's was 1.47 GiB over 24 graphs), so it is measured, not assumed.
+OVER_E=(
+    "FRANK_PRIMARY_SPEC='$SPEC3'"
+    "FRANK_PRIMARY_COMPCONFIG='$LADDER3'"
+    'FRANK_PRIMARY_GEN_CONFIG='"'$GEN07'"
+    "$KV401K"
+    'FRANK_PRIMARY_MNBT=4096'
+    'FRANK_PRIMARY_UTIL=0.99'
+)
+
 arm_overlay() {
     case "$1" in
         baseline) ;;                       # the shipped env, no overlay
         B)  printf '%s\n' "${OVER_B[@]}" ;;
         B2) printf '%s\n' "${OVER_B2[@]}" ;;
         C)  printf '%s\n' "${OVER_C[@]}" ;;
+        D)  printf '%s\n' "${OVER_D[@]}" ;;
+        E)  printf '%s\n' "${OVER_E[@]}" ;;
         *) return 1 ;;
     esac
 }
-
 if [ "${1:-}" = "--list" ]; then
-    printf 'baseline B B2 C\n'
+    printf 'baseline B B2 C D E\n'
     exit 0
 fi