scripts: unified deploy.sh; units + bench point at the merged checkout

deploy.sh now deploys both workloads per target in one run:
push -> pull on /home/dank/serverAppConfigs -> podman stack steps
(dankclaw) -> LLM unit relink + daemon-reload + service restart ->
homepage health + LLM health (up to 20 min model-load wait).
Sudo: plain sudo on the fleet hosts (passwordless verified
2026-08-22); FRANK_SUDO_PW covers headless runs elsewhere. The
vllmScripts deploy.sh is superseded.

Units: frank-default-{small,large,npu}.service now reference
/home/dank/serverAppConfigs/scripts/... (the merged checkout).
bench-spec-stack.sh: env file path updated to the merged checkout.

scripts/bench-spec-stack.sh

@@ -16,7 +16,7 @@ SPEC="${1:?usage: bench-spec-stack.sh <spec> <ctx> [out_tokens]}"
 CTX="${2:?usage: bench-spec-stack.sh <spec> <ctx> [out_tokens]}"
 OUT_TOKENS="${3:-256}"
 
-ENV_FILE=/home/dank/vllmScripts/scripts/frank-default-large.env
+ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-default-large.env
 source "$ENV_FILE"
 
 # This harness benchmarks the retired v3 stack. Force the v3 values so the

scripts/deploy.sh

@@ -1,20 +1,29 @@
 #!/usr/bin/env bash
-# deploy.sh — Deploy the serverAppConfigs repo to a target and restart its stack.
+# deploy.sh — Deploy the serverAppConfigs repo to a target and restart its
+# podman stack and LLM fleet services.
 #
-# Implements the git deployment workflow from AGENTS.md. Assumes local changes
+# Implements the git deployment workflow from AGENTS.md. Assumes local
-# are committed and pushed, then:
+# changes are committed and pushed, then:
 #   1. Pushes main to origin
 #   2. Pulls the repo on the target
-#   3. Copies shared configs into place
+#   3. Copies shared configs into place and restarts the podman stack
-#   4. Restarts the podman stack (podman-compose up -d)
+#      (dankclaw only; the dankserver media stack runs as bare containers)
-#   5. Waits for the Caddy homepage to respond
+#   4. Relinks the LLM systemd units and restarts the active LLM service
+#   5. Waits for the Caddy homepage and the LLM health endpoint
+#
+# Sudo: the fleet hosts allow passwordless sudo for the deploy user. For
+# headless runs on a host without that, set FRANK_SUDO_PW so remote sudo
+# reads the password from stdin (`sudo -S`). The password is never stored
+# in this repo.
 #
 # Usage:
 #   ./scripts/deploy.sh <target> [--dry-run]
 #
 # Targets:
-#   dankclaw   - AI/search/dev/observability stack (dankclaw/compose.yaml)
+#   dankclaw   - AI/search/dev/observability stack + frank-default-large
-#   dankserver - media/library stack (dankserver/compose.yaml)
+#                (CIRU ROCmFPX llama.cpp, Qwen3.8-27B, port 52625)
+#   dankserver - media/library stack (bare containers) + frank-default-small
+#                (upstream llama.cpp, Qwen3.6-35B-A3B, port 7770)
 #
 # Example:
 #   ./scripts/deploy.sh dankclaw
@@ -25,10 +34,11 @@ set -euo pipefail
 # Target configuration
 # ---------------------------------------------------------------------------
 declare -A REMOTE_USER REMOTE_HOST REMOTE_DIR COMPOSE HEALTH_URL COMPOSE_UP COPY_SHARED
+declare -A LLM_SERVICES LLM_UNITS LLM_HEALTH LLM_WAIT
 
 # Caddy is consolidated on dankclaw: it fronts both hosts' services. The
 # dankserver media stack runs as bare containers (not this repo's compose),
-# so its deploy is pull-only; health is checked against the shared Caddy.
+# so its stack deploy is pull-only; health is checked against the shared Caddy.
 REMOTE_USER[dankclaw]=dank
 REMOTE_HOST[dankclaw]=dankclaw
 REMOTE_DIR[dankclaw]="/home/dank/serverAppConfigs"
@@ -36,6 +46,16 @@ COMPOSE[dankclaw]="dankclaw/compose.yaml"
 HEALTH_URL[dankclaw]="http://127.0.0.1/"
 COMPOSE_UP[dankclaw]=1
 COPY_SHARED[dankclaw]=1
+# LLM: frank-default-large is the active service (restart + health wait).
+# frank-default-npu is relinked only (not enabled on the host); its unit
+# picks up the new paths at its next manual start.
+LLM_SERVICES[dankclaw]="frank-default-large"
+LLM_UNITS[dankclaw]="frank-default-large frank-default-npu"
+LLM_HEALTH[dankclaw]="http://127.0.0.1:52625/health"
+# CIRU llama.cpp (ROCm 7.15) loads the v3 five-file payload (GGUF + FFN +
+# GDN + Output-K8 .pfs + mmproj, ~36.7 GiB) + MTP draft/Output-K8 proxy and
+# initializes PromptForge views; allow 20 minutes.
+LLM_WAIT[dankclaw]=600
 
 REMOTE_USER[dankserver]=dank
 REMOTE_HOST[dankserver]=dankserver
@@ -44,6 +64,13 @@ COMPOSE[dankserver]="dankserver/compose.yaml"
 HEALTH_URL[dankserver]="http://192.168.0.143/"
 COMPOSE_UP[dankserver]=0
 COPY_SHARED[dankserver]=0
+# LLM: frank-default-small is the active service (restart + health wait).
+LLM_SERVICES[dankserver]="frank-default-small"
+LLM_UNITS[dankserver]="frank-default-small"
+LLM_HEALTH[dankserver]="http://127.0.0.1:7770/health"
+# Cold load: --no-mmap reads the 30.6 GB Q6_K_P through RAM (MoE experts on
+# CPU); allow 20 minutes.
+LLM_WAIT[dankserver]=600
 
 TARGET="${1:-}"
 DRY_RUN=0
@@ -63,6 +90,14 @@ if [ -z "${REMOTE_HOST[$TARGET]:-}" ]; then
     exit 1
 fi
 
+# ---------------------------------------------------------------------------
+# Sudo wrapper (headless-friendly)
+# ---------------------------------------------------------------------------
+SUDO="sudo"
+if [ -n "${FRANK_SUDO_PW:-}" ]; then
+    SUDO="printf '%s\n' '$FRANK_SUDO_PW' | sudo -S"
+fi
+
 # ---------------------------------------------------------------------------
 # Local checks (pre-flight)
 # ---------------------------------------------------------------------------
@@ -77,10 +112,12 @@ if [ "$(git rev-parse --abbrev-ref HEAD)" != "main" ]; then
 fi
 
 echo "=== Deploying to ${TARGET} ==="
-echo "  host:    ${REMOTE_HOST[$TARGET]}"
+echo "  host:       ${REMOTE_HOST[$TARGET]}"
-echo "  dir:     ${REMOTE_DIR[$TARGET]}"
+echo "  dir:        ${REMOTE_DIR[$TARGET]}"
-echo "  compose: ${COMPOSE[$TARGET]}"
+echo "  compose:    ${COMPOSE[$TARGET]}"
-echo "  health:  ${HEALTH_URL[$TARGET]}"
+echo "  llm svc:    ${LLM_SERVICES[$TARGET]}"
+echo "  llm health: ${LLM_HEALTH[$TARGET]}"
+echo "  homepage:   ${HEALTH_URL[$TARGET]}"
 echo ""
 
 # ---------------------------------------------------------------------------
@@ -90,7 +127,7 @@ if [ "$DRY_RUN" = "1" ]; then
     echo "[dry-run] Would push local main to origin"
     echo "[dry-run] Would SSH to ${REMOTE_HOST[$TARGET]} and git pull"
 else
-    echo "[1/4] Pushing local main to origin..."
+    echo "[1/5] Pushing local main to origin..."
     git push origin main
 fi
 
@@ -99,13 +136,13 @@ REMOTE="$(
 )"
 
 # ---------------------------------------------------------------------------
-# Remote: pull + copy shared configs + restart stack
+# Remote: pull + copy shared configs + restart stack + restart LLM service
 # ---------------------------------------------------------------------------
 REMOTE_SCRIPT="
 set -euo pipefail
 cd '${REMOTE_DIR[$TARGET]}'
 
-echo '[2/4] Pulling repo on ${TARGET}...'
+echo '[2/5] Pulling repo on ${TARGET}...'
 git pull origin main
 
 if [ -f .env ]; then
@@ -115,7 +152,7 @@ else
 fi
 
 if [ '${COPY_SHARED[$TARGET]}' = '1' ]; then
-  echo '[3/4] Copying shared configs into place...'
+  echo '[3/5] Copying shared configs into place...'
   mkdir -p /opt/searxng/config /opt/prometheus/config /opt/loki/config /opt/alloy/config
   cp shared/searxng/settings.yml /opt/searxng/config/settings.yml
   cp shared/searxng/limiter.toml /opt/searxng/config/limiter.toml
@@ -138,7 +175,7 @@ if [ '${COPY_SHARED[$TARGET]}' = '1' ]; then
 fi
 
 if [ '${COMPOSE_UP[$TARGET]}' = '1' ]; then
-  echo '[4/4] Restarting stack...'
+  echo '[4/5] Restarting stack...'
   # Locally built images: caddy + porkbun module, and loki/alloy + a static
   # busybox (their upstream images lack the wget the healthchecks need).
   for dir in caddy loki alloy; do
@@ -177,8 +214,19 @@ if [ '${COMPOSE_UP[$TARGET]}' = '1' ]; then
     podman restart caddy
   fi
 else
-  echo '[4/4] Skipping compose restart (stack runs as bare containers on this host)'
+  echo '[4/5] Skipping compose restart (stack runs as bare containers on this host)'
 fi
+
+echo '[4/5] Relinking LLM units and restarting LLM services...'
+for unit in ${LLM_UNITS[$TARGET]}; do
+  ${SUDO} ln -sf '${REMOTE_DIR[$TARGET]}/scripts/\${unit}.service' /etc/systemd/system/\${unit}.service
+done
+${SUDO} systemctl daemon-reload
+for svc in ${LLM_SERVICES[$TARGET]}; do
+  ${SUDO} systemctl enable \"\${svc}\"
+  ${SUDO} systemctl restart \"\${svc}\"
+  echo \"  restarted \${svc}\"
+done
 "
 
 if [ "$DRY_RUN" = "1" ]; then
@@ -192,22 +240,37 @@ REMOTE_EOF
 fi
 
 # ---------------------------------------------------------------------------
-# Health check
+# Health checks: homepage, then the LLM endpoint
 # ---------------------------------------------------------------------------
 if [ "$DRY_RUN" = "1" ]; then
-    echo "[dry-run] Would wait for health at ${HEALTH_URL[$TARGET]}"
+    echo "[dry-run] Would wait for health at ${HEALTH_URL[$TARGET]} and ${LLM_HEALTH[$TARGET]}"
 else
-    echo "[5/4] Waiting for health endpoint ${HEALTH_URL[$TARGET]} (via ssh)..."
+    echo "[5/5] Waiting for homepage ${HEALTH_URL[$TARGET]} (via ssh)..."
     HEALTH="${HEALTH_URL[$TARGET]}"
     for i in $(seq 1 60); do
         if ssh "$REMOTE" "curl -sf '$HEALTH'" > /dev/null 2>&1; then
             echo "  Homepage healthy after approx $((i * 2))s"
+            break
+        fi
+        sleep 2
+    done
+    if ! ssh "$REMOTE" "curl -sf '$HEALTH'" > /dev/null 2>&1; then
+        echo "FAIL: Homepage did not become healthy in 120s"
+        exit 1
+    fi
+
+    echo "[5/5] Waiting for LLM health ${LLM_HEALTH[$TARGET]} (via ssh)..."
+    LLM_URL="${LLM_HEALTH[$TARGET]}"
+    LLM_ITERS="${LLM_WAIT[$TARGET]}"
+    for i in $(seq 1 "$LLM_ITERS"); do
+        if ssh "$REMOTE" "curl -sf '$LLM_URL'" > /dev/null 2>&1; then
+            echo "  LLM healthy after approx $((i * 2))s"
             echo ""
             echo "=== Deploy complete: ${TARGET} ==="
             exit 0
         fi
         sleep 2
     done
-    echo "FAIL: Homepage did not become healthy in 120s"
+    echo "FAIL: LLM service did not become healthy in $((LLM_ITERS * 2))s"
     exit 1
 fi

scripts/frank-default-large.service

@@ -7,8 +7,8 @@ Wants=network-online.target
 Type=simple
 User=dank
 Group=dank
-Environment="FRANK_LARGE_ENV_FILE=/home/dank/vllmScripts/scripts/frank-default-large.env"
+Environment="FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-default-large.env"
-ExecStart=/home/dank/vllmScripts/scripts/serve-frank-large.sh
+ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh
 Restart=on-failure
 RestartSec=10
 

scripts/frank-default-npu.service

@@ -7,8 +7,8 @@ Wants=network-online.target
 Type=simple
 User=dank
 Group=dank
-Environment="FLM_NPU_ENV_FILE=/home/dank/vllmScripts/scripts/frank-default-npu.env"
+Environment="FLM_NPU_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-default-npu.env"
-ExecStart=/home/dank/vllmScripts/scripts/serve-frank-default-npu.sh
+ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-default-npu.sh
 LimitMEMLOCK=infinity
 Restart=on-failure
 RestartSec=10

scripts/frank-default-small.service

@@ -7,8 +7,8 @@ Wants=network-online.target
 Type=simple
 User=dank
 Group=dank
-Environment="FRANK_SMALL_ENV_FILE=/home/dank/vLLM/scripts/frank-default-small.env"
+Environment="FRANK_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-default-small.env"
-ExecStart=/home/dank/vLLM/scripts/serve-frank-small.sh
+ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-small.sh
 Restart=on-failure
 RestartSec=10