frank-primary: wire --decode-context-parallel-size (opt-in)

DCP is passed only when FRANK_PRIMARY_DCP is set, so the deployed shape is
unchanged. Verified in this fork: DCP reuses the TP ranks when PCP is
disabled (tp % dcp == 0), so TP=2 + DCP=2 fits the two R9700s with no extra
ranks; the flash_attn backend carries DCP support, the 36 linear-attention
layers of this hybrid do not — which is what the A/B window tests.

scripts/serve-frank-primary.sh

@@ -111,6 +111,7 @@ podman run -d --name "$FRANK_PRIMARY_CONTAINER" \
   "$FRANK_PRIMARY_IMAGE" /models \
   --served-model-name "$FRANK_PRIMARY_SERVED_NAME" --port 7770 \
   --tensor-parallel-size 2 \
+  ${FRANK_PRIMARY_DCP:+--decode-context-parallel-size "$FRANK_PRIMARY_DCP"} \
   --max-model-len "$FRANK_PRIMARY_MAXLEN" \
   --max-num-seqs "$FRANK_PRIMARY_SEQS" \
   ${FRANK_PRIMARY_MNBT:+--max-num-batched-tokens "$FRANK_PRIMARY_MNBT"} \

tests/frank_primary_unit.bats

@@ -113,6 +113,10 @@ DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"
     grep -q -- '--tensor-parallel-size 2' "$SERVE"
     grep -q -- '--enable-prefix-caching' "$SERVE"
     grep -q -- '--trust-remote-code' "$SERVE"
+    # DCP is opt-in: the flag is passed only when FRANK_PRIMARY_DCP is set
+    # (DCP reuses the TP ranks when PCP is off, so TP=2 + DCP=2 fits two GPUs).
+    grep -q -- '--decode-context-parallel-size "$FRANK_PRIMARY_DCP"' "$SERVE"
+    ! grep -q '^FRANK_PRIMARY_DCP=' "$ENV_FILE"
 }
 
 @test "tools and reasoning are wired — the client contract is served" {