serve-frank-large: restore Qwen-Sharp chat template + reformat for readability

The v6 restore commits dropped --chat-template-file and
--chat-template-kwargs while the artifact check still validated the
template file, so the Sharp template was checked but never applied.
Re-add both flags (with --jinja) so reasoning is emitted in DeepSeek
format and preserve_thinking/preserve_reasoning are honoured.

Reformat the script one-flag-per-line with long flag aliases
(--gpu-layers, --ctx-size, --ubatch-size, --cache-type-k/v) like
serve-frank-small, and update the 2 frank_large_config assertions
that grep the old short-flag forms (-ctk/-ctv, -ub).

- scripts/serve-frank-large.sh
- tests/frank_large_config.bats

scripts/serve-frank-large.sh

@@ -1,6 +1,10 @@
 #!/usr/bin/env bash
 # Serve the kingjones Qwen3.8 Uncensored Q6 AGENT model as frank-default-large.
 # The deployment uses a standalone MTP draft head and f16 KV cache.
+#
+# The Qwen-Sharp chat template (scripts/chat-template.jinja) is applied at
+# runtime so the model emits reasoning in DeepSeek format; the reasoning
+# trail is preserved across turns via CHAT_TEMPLATE_KWARGS.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
@@ -12,11 +16,14 @@ if [[ -f "$ENV_FILE" ]]; then
     set +a
 fi
 
+# --- defaults (used when the env file does not set them) -------------------
 : "${LLAMA_BIN:=/home/dank/ciru-qwen38/ROCmFPX/build-promptforge/bin/llama-server}"
 : "${MODEL_DIR:=/home/dank/models/kingjones-Qwen3.8-27B-STRIX-MTP}"
 : "${MODEL_FILE:=Qwen3.8-27B-Uncensored-Q6_0_ROCMFPX_AGENT.gguf}"
 : "${MTP_DRAFT_FILE:=$MODEL_DIR/mtp-Qwen3.8-27B-Q4_0.gguf}"
 : "${MMPROJ_FILE:=mmproj-Qwen3.8-27B-Q8_0.gguf}"
+: "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
+: "${CHAT_TEMPLATE_KWARGS:={}}"
 : "${ALIAS:=frank-default-large}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7770}"
@@ -70,19 +77,47 @@ exec /usr/bin/env \
     GGML_CUDA_GRAPH_OPT=0 \
     LLAMA_TARGET_GREEDY_ARGMAX_FASTPATH=0 \
     LLAMA_MTP_CPU_ARGMAX_FASTPATH=1 \
-    "$LLAMA_BIN" -m "$MODEL" --alias "$ALIAS" \
-    --host "$BIND_ADDR" --port "$LISTEN_PORT" --jinja \
-    -dev ROCm0 -ngl 999 -np "$PARALLEL" -c "$CTX_SIZE" \
-    -b "$BATCH_SIZE" -ub "$UBATCH_SIZE" -fa on \
-    -ctk "$CACHE_TYPE_K" -ctv "$CACHE_TYPE_V" -t "$NUM_THREADS" -tb "$THREAD_BATCH" \
-    -ctxcp "$CTX_CHECKPOINTS" --cache-ram "$CACHE_RAM" --cache-prompt --cache-idle-slots --metrics \
-    --spec-type draft-mtp --model-draft "$MTP_DRAFT_FILE" \
+    "$LLAMA_BIN" \
+    --model "$MODEL" \
+    --alias "$ALIAS" \
+    --chat-template-file "$CHAT_TEMPLATE_FILE" \
+    --chat-template-kwargs "$CHAT_TEMPLATE_KWARGS" \
+    --host "$BIND_ADDR" \
+    --port "$LISTEN_PORT" \
+    --jinja \
+    --device ROCm0 \
+    --gpu-layers 999 \
+    --parallel "$PARALLEL" \
+    --ctx-size "$CTX_SIZE" \
+    --batch-size "$BATCH_SIZE" \
+    --ubatch-size "$UBATCH_SIZE" \
+    --flash-attn on \
+    --cache-type-k "$CACHE_TYPE_K" \
+    --cache-type-v "$CACHE_TYPE_V" \
+    --threads "$NUM_THREADS" \
+    --threads-batch "$THREAD_BATCH" \
+    --ctx-checkpoints "$CTX_CHECKPOINTS" \
+    --cache-ram "$CACHE_RAM" \
+    --cache-prompt \
+    --cache-idle-slots \
+    --metrics \
+    --spec-type draft-mtp \
+    --model-draft "$MTP_DRAFT_FILE" \
     --mmproj "$MODEL_DIR/$MMPROJ_FILE" \
-    --spec-draft-device ROCm0 --spec-draft-ngl 999 \
-    --spec-draft-type-k "$CACHE_TYPE_K" --spec-draft-type-v "$CACHE_TYPE_V" \
-    --spec-draft-n-max "$MTP_N_MAX" --spec-draft-n-min "$MTP_N_MIN" \
-    --spec-draft-p-min "$MTP_P_MIN" --spec-draft-p-split "$MTP_P_SPLIT" \
+    --spec-draft-device ROCm0 \
+    --spec-draft-ngl 999 \
+    --spec-draft-type-k "$CACHE_TYPE_K" \
+    --spec-draft-type-v "$CACHE_TYPE_V" \
+    --spec-draft-n-max "$MTP_N_MAX" \
+    --spec-draft-n-min "$MTP_N_MIN" \
+    --spec-draft-p-min "$MTP_P_MIN" \
+    --spec-draft-p-split "$MTP_P_SPLIT" \
     --spec-draft-backend-sampling \
-    --temp "$TEMPERATURE" --top-p "$TOP_P" --top-k "$TOP_K" --min-p "$MIN_P" \
+    --temp "$TEMPERATURE" \
+    --top-p "$TOP_P" \
+    --top-k "$TOP_K" \
+    --min-p "$MIN_P" \
     --presence-penalty "$PRESENCE_PENALTY" \
-    --reasoning "$REASONING" --reasoning-format "$REASONING_FORMAT" --reasoning-budget -1
+    --reasoning "$REASONING" \
+    --reasoning-format "$REASONING_FORMAT" \
+    --reasoning-budget -1

tests/frank_large_config.bats

@@ -54,13 +54,14 @@ TEMPLATE_FILE="$REPO_ROOT/scripts/chat-template.jinja"
 @test "frank-default-large uses f16 for both KV cache sides" {
     grep -q '^CACHE_TYPE_K=f16$' "$ENV_FILE"
     grep -q '^CACHE_TYPE_V=f16$' "$ENV_FILE"
-    grep -qF -- '-ctk "$CACHE_TYPE_K" -ctv "$CACHE_TYPE_V"' "$SERVE_FILE"
+    grep -qF -- '--cache-type-k "$CACHE_TYPE_K"' "$SERVE_FILE"
+    grep -qF -- '--cache-type-v "$CACHE_TYPE_V"' "$SERVE_FILE"
 }
 
 @test "frank-default-large exposes a swappable ubatch" {
     grep -q '^UBATCH_SIZE=4096$' "$ENV_FILE"
     grep -q ': "${UBATCH_SIZE:=4096}"' "$SERVE_FILE"
-    grep -q -- '-ub "$UBATCH_SIZE"' "$SERVE_FILE"
+    grep -q -- '--ubatch-size "$UBATCH_SIZE"' "$SERVE_FILE"
 }
 
 @test "llama-bench ubatch harness uses the active model" {