frank-primary: pin radiance v1.2.0, translate expert-vs-cache-ratio to vram knobs

Engine v1.2.0 (Codeberg e95d397, Docker Hub tag 1.2.0, index digest
665775ed...) removes --expert-vs-cache-ratio. The explicit
--vram-weights-mib 26071 / --vram-kv-mib 3543 pair transcribes the live
1.0.13 boot ledger at ratio 0.82 (weights 25.46 GiB, KV 3.46 GiB per
card); bracket arms scale KV linearly in (1-r): 0.90 -> 1968, 0.95 -> 984.
Serve script, autoresearch harness, and bats gates follow; the bats
shape asserts are realigned to the deployed seqs=3/spec=2 sweep result
(95923d3, df6b5bb) they failed to track.

tests/frank_primary_unit.bats

@@ -118,19 +118,21 @@ TEMPLATE="$REPO_ROOT/scripts/qwen38-froggeric-v22.5.jinja"
     grep -q '^FRANK_PRIMARY_MAX_MODEL_LEN=200000$' "$ENV_FILE"
     ml=$(awk -F= '/^FRANK_PRIMARY_MAX_MODEL_LEN=/{print $2}' "$ENV_FILE")
     [ "$ml" -ge 177356 ]
-    # First-boot conservative shape (Frank's call): 2 decode slots. The
-    # fused TP all-reduce is declared over seqs x (1 + spec) rows = 8.
-    grep -q '^FRANK_PRIMARY_MAX_SEQS=2$' "$ENV_FILE"
+    # Decode-sweep shape (2026-10-06): 3 slots, spec depth 2 — the measured
+    # optimum (33.06 t/s). The fused TP all-reduce is declared over
+    # seqs x (1 + spec) rows = 9.
+    grep -q '^FRANK_PRIMARY_MAX_SEQS=3$' "$ENV_FILE"
     grep -q '^FRANK_PRIMARY_TP=2$' "$ENV_FILE"
     grep -q '^FRANK_PRIMARY_TP_WIRE=wht6$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_SPEC_TOKENS=3$' "$ENV_FILE"
+    grep -q '^FRANK_PRIMARY_SPEC_TOKENS=2$' "$ENV_FILE"
     # Native-precision economics: the expert pool is per rank (56.4 GiB
     # slice per rank at TP2), the PLE ngram table is pinned in host RAM per
     # Frank's law, KV is fp8, the ratio is the publisher's production
     # value.
     grep -q '^FRANK_PRIMARY_PLACEMENT=expert_tiered$' "$ENV_FILE"
     grep -q '^FRANK_PRIMARY_HOST_POOL_MIB=40960$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_EXPERT_VS_CACHE=0.82$' "$ENV_FILE"
+    grep -q '^FRANK_PRIMARY_VRAM_WEIGHTS_MIB=[1-9]' "$ENV_FILE"
+    grep -q '^FRANK_PRIMARY_VRAM_KV_MIB=[1-9]' "$ENV_FILE"
     grep -q '^FRANK_PRIMARY_KV_DTYPE=fp8$' "$ENV_FILE"
     grep -q '^FRANK_PRIMARY_NGRAM_PLACEMENT=ram$' "$ENV_FILE"
     # Prefix cache tiers (publisher pattern; disk tier sized for 2 slots).
@@ -162,7 +164,8 @@ TEMPLATE="$REPO_ROOT/scripts/qwen38-froggeric-v22.5.jinja"
     grep -q -- '--max-model-len "$FRANK_PRIMARY_MAX_MODEL_LEN"' "$SERVE"
     grep -q -- '--placement "$FRANK_PRIMARY_PLACEMENT"' "$SERVE"
     grep -q -- '--host-pool-mib "$FRANK_PRIMARY_HOST_POOL_MIB"' "$SERVE"
-    grep -q -- '--expert-vs-cache-ratio "$FRANK_PRIMARY_EXPERT_VS_CACHE"' "$SERVE"
+    grep -q -- '--vram-weights-mib "$FRANK_PRIMARY_VRAM_WEIGHTS_MIB"' "$SERVE"
+    grep -q -- '--vram-kv-mib "$FRANK_PRIMARY_VRAM_KV_MIB"' "$SERVE"
     grep -q -- '--kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE"' "$SERVE"
     grep -q -- '--prefix-cache-host-mib "$FRANK_PRIMARY_PREFIX_HOST_MIB"' "$SERVE"
     grep -q -- '--prefix-cache-disk-mib "$FRANK_PRIMARY_PREFIX_DISK_MIB"' "$SERVE"