feat(llm): rename inference services dropping 'default' from names

frank-default-large -> frank-large (Dankclaw :7770), frank-default-small ->
frank-small (Dankserver :7770), frank-default-sightsound -> frank-npu
(Dankclaw :7771). Units, env files, serve scripts, deploy-plan mappings,
deploy-remote dispatch (stop/disable old units + relink + enable new), and the
test seams move together. Retired frank-default-npu.* artifacts moved to
scripts/.AGENTTRASH/ (tracked-in-history; ignored on disk).

Served aliases become frank-large / frank-small via --alias; the NPU endpoint
serves the whole FLM registry, so its rename changes no served tags.

scripts/bench-decode-threads-batch.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Decode throughput benchmark for frank-default-large.
+Decode throughput benchmark for frank-large.
 Starts the server with a given --threads-batch value, sends an 8K+ token prompt,
 generates 256 tokens, measures generation tok/s.
 
@@ -13,7 +13,7 @@ SERVE = "/home/dank/GitPackages/ROCmFPX/build-qwen38/bin/llama-server"
 PORT = 7770
 N_GEN = 256
 PROMPT_FILE = "/tmp/bench-prompts/prompt_code.txt"
-ENV_FILE = os.path.join(os.path.dirname(__file__), "frank-default-large.env")
+ENV_FILE = os.path.join(os.path.dirname(__file__), "frank-large.env")
 SERVER_DIR = os.path.dirname(SERVE)
 ROCM_PATH = "/opt/rocm"
 
@@ -59,7 +59,7 @@ def wait_ready():
 def send_request(prompt, max_tokens=N_GEN):
     """Send chat completion, measure generation throughput."""
     body = json.dumps({
-        "model": "frank-default-large",
+        "model": "frank-large",
         "messages": [{"role": "user", "content": prompt}],
         "max_tokens": max_tokens,
         "stream": False,

scripts/bench-decode.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# Decode throughput benchmark for frank-default-large.
+# Decode throughput benchmark for frank-large.
 # Measures generation tok/s with 8K+ token prompts and 256 generated tokens.
 set -euo pipefail
 
@@ -57,7 +57,7 @@ run_bench() {
     # Warmup (small request)
     curl -s -m 60 http://127.0.0.1:$PORT/v1/chat/completions \
         -H "Content-Type: application/json" \
-        -d '{"model":"frank-default-large","messages":[{"role":"user","content":"Hi"}],"max_tokens":16,"stream":false}' > /dev/null 2>&1 || true
+        -d '{"model":"frank-large","messages":[{"role":"user","content":"Hi"}],"max_tokens":16,"stream":false}' > /dev/null 2>&1 || true
     
     # Build 8K prompt
     local prompt
@@ -75,7 +75,7 @@ print(json.dumps(' '.join(words)))
     t0=$(date +%s%N)
     resp=$(curl -s -m 600 http://127.0.0.1:$PORT/v1/chat/completions \
         -H "Content-Type: application/json" \
-        -d "{\"model\":\"frank-default-large\",\"messages\":[{\"role\":\"user\",\"content\":$prompt}],\"max_tokens\":$N_GEN,\"stream\":false}" 2>&1)
+        -d "{\"model\":\"frank-large\",\"messages\":[{\"role\":\"user\",\"content\":$prompt}],\"max_tokens\":$N_GEN,\"stream\":false}" 2>&1)
     t1=$(date +%s%N)
     
     if ! echo "$resp" | python3 -c "import sys,json; json.load(sys.stdin)" 2>/dev/null; then

scripts/bench-ngram-mod.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-Benchmark n-gram speculative decoding vs no-spec for frank-default-large.
+Benchmark n-gram speculative decoding vs no-spec for frank-large.
 
 Tests prompt-processing throughput with 16K token prompts (manageable request size).
 Code-heavy prompt (high n-gram redundancy) vs prose prompt (low redundancy).
@@ -103,7 +103,7 @@ def start_server(port, spec_type):
 def run_test(prompt_text, spec_type, port):
     """Send a request and extract prompt processing metrics."""
     data = json.dumps({
-        "model": "frank-default-large",
+        "model": "frank-large",
         "messages": [{"role": "user", "content": prompt_text}],
         "max_tokens": TEST_TOKENS,
         "stream": False,
@@ -189,7 +189,7 @@ def main():
         print(f"  Prose: {prose_prompt_file.stat().st_size:,} bytes")
 
     print("=" * 60)
-    print("  N-gram Mod Benchmark — frank-default-large")
+    print("  N-gram Mod Benchmark — frank-large")
     print(f"  STRIX ROCmFP4 · 64K context · 16K prompts")
     print("=" * 60)
 

scripts/bench-ngram-mod.sh

@@ -1,19 +1,19 @@
 #!/usr/bin/env bash
-# Benchmark n-gram speculative decoding vs no-spec for frank-default-large.
+# Benchmark n-gram speculative decoding vs no-spec for frank-large.
 #
 # This tests prompt-processing throughput at 64k context with two distinct
 # prompts: one code-heavy and one prose-heavy. Uses llama-server on scratch
 # ports with the OpenAI-compatible API to measure prompt_eval_duration_ms.
 #
 # Run on Dankclaw after stopping the production service:
-#   sudo systemctl stop frank-default-large
+#   sudo systemctl stop frank-large
 #   ./scripts/bench-ngram-mod.sh
-#   sudo systemctl start frank-default-large
+#   sudo systemctl start frank-large
 
 set -euo pipefail
 
 SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
-ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-default-large.env}"
+ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-large.env}"
 if [[ -f "$ENV_FILE" ]]; then
     set -a; source "$ENV_FILE"; set +a
 fi
@@ -184,7 +184,7 @@ run_single_test() {
     response=$(curl -s -X POST "http://127.0.0.1:$port/v1/completions" \
         -H "Content-Type: application/json" \
         -d "{
-            \"model\": \"frank-default-large\",
+            \"model\": \"frank-large\",
             \"prompt\": \"$prompt_text\",
             \"max_tokens\": 128,
             \"temperature\": 0,
@@ -220,7 +220,7 @@ run_single_test() {
 }
 
 echo "╔══════════════════════════════════════════════════════════╗"
-echo "║  N-gram Mod Benchmark — frank-default-large             ║"
+echo "║  N-gram Mod Benchmark — frank-large             ║"
 echo "║  STRIX ROCmFP4 · 64k context · two prompts             ║"
 echo "╚══════════════════════════════════════════════════════════╝"
 echo ""

scripts/bench-spec-decode.py

@@ -15,9 +15,9 @@ import time
 import urllib.request
 import urllib.error
 
-SERVICE = "frank-default-large"
-ENV_FILE = "/home/dank/serverAppConfigs/scripts/frank-default-large.env"
-ALIAS = "frank-default-large"
+SERVICE = "frank-large"
+ENV_FILE = "/home/dank/serverAppConfigs/scripts/frank-large.env"
+ALIAS = "frank-large"
 DEFAULT_HOST = "localhost"
 DEFAULT_PORT = 7770
 DEFAULT_MAX_TOKENS = 16384

scripts/bench-threads-batch-http.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 """
-HTTP-based prefill-throughput sweep for frank-default-large.
+HTTP-based prefill-throughput sweep for frank-large.
 Starts the server with a given --threads-batch value, sends a 64K-prompt via
 the chat API (max_tokens=0), measures prompt_tokens/wall_time.
 
@@ -39,7 +39,7 @@ def send_prefill_request():
     with open(PROMPT_FILE, "r") as f:
         prompt = f.read()
     body = json.dumps({
-        "model": "frank-default-large",
+        "model": "frank-large",
         "messages": [{"role": "user", "content": prompt}],
         "max_tokens": 1,
         "stream": False

scripts/bench-threads-batch.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# Threads-batch sweep for frank-default-large on dankclaw
+# Threads-batch sweep for frank-large on dankclaw
 # Benches prefill throughput at 65536 prompt tokens across threads-batch values.
 set -uo pipefail
 
@@ -10,7 +10,7 @@ TB_LIST=(16 32 48 64 80 96 128)
 ENV_FILE="/home/dank/GitPackages/ROCmFPX/build-qwen38/bin"
 
 echo "========================================"
-echo "THREADS-BATCH SWEEP — frank-default-large"
+echo "THREADS-BATCH SWEEP — frank-large"
 echo "Model: $(basename "$MODEL") ($(du -h "$MODEL" | cut -f1))"
 echo "Threads-batch values: ${TB_LIST[*]}"
 echo "Prompt: 65536 tokens, n-gen: 0 (prefill-only)"

scripts/bench-ubatch.sh

@@ -1,14 +1,14 @@
 #!/usr/bin/env bash
-# Benchmark ubatch with llama-bench for frank-default-large.
+# Benchmark ubatch with llama-bench for frank-large.
 #
 # This is intentionally a ubatch-only benchmark. It uses one llama-bench
 # process, an 8K prompt workload, and equal batch/ubatch values. No server
 # process, HTTP requests, or log scraping are used.
 #
-# Run on Dankclaw after stopping frank-default-large:
-#   sudo systemctl stop frank-default-large
+# Run on Dankclaw after stopping frank-large:
+#   sudo systemctl stop frank-large
 #   ./scripts/bench-ubatch.sh
-#   sudo systemctl start frank-default-large
+#   sudo systemctl start frank-large
 set -euo pipefail
 
 : "${LLAMA_BENCH:=/home/dank/GitPackages/ROCmFPX/build-strix-rocmfp4/bin/llama-bench}"

scripts/deploy-plan.py

@@ -58,10 +58,9 @@ SERVICE_ORDER = (
     "sonarr",
     "lidarr",
     "readarr",
-    "frank-default-large",
-    "frank-default-npu",
-    "frank-default-sightsound",
-    "frank-default-small",
+    "frank-large",
+    "frank-npu",
+    "frank-small",
 )
 
 DANKCLAW_SERVICES = {
@@ -89,9 +88,8 @@ DANKCLAW_SERVICES = {
     "authentik-outpost-ldap",
     "caddy",
     "homepage",
-    "frank-default-large",
-    "frank-default-npu",
-    "frank-default-sightsound",
+    "frank-large",
+    "frank-npu",
 }
 
 DANKSERVER_SERVICES = {
@@ -109,7 +107,7 @@ DANKSERVER_SERVICES = {
     "sonarr",
     "lidarr",
     "readarr",
-    "frank-default-small",
+    "frank-small",
 }
 
 # FrankBook-Pro runs the *arr stack + qBittorrent inside a podman machine on
@@ -352,17 +350,15 @@ def services_for_path(path: str, target: str) -> set[str]:
 
     if parts[0] == "scripts":
         name = p.name
-        if name in {"frank-default-large.env", "frank-default-large.service", "serve-frank-large.sh"}:
-            _add(services, "frank-default-large")
-        elif name in {"frank-default-npu.env", "frank-default-npu.service", "serve-frank-default-npu.sh"}:
-            _add(services, "frank-default-npu")
-        elif name in {"frank-default-sightsound.env", "frank-default-sightsound.service", "serve-frank-default-sightsound.sh"}:
-            _add(services, "frank-default-sightsound")
-        elif name in {"frank-default-small.env", "frank-default-small.service", "serve-frank-small.sh"}:
-            _add(services, "frank-default-small")
+        if name in {"frank-large.env", "frank-large.service", "serve-frank-large.sh"}:
+            _add(services, "frank-large")
+        elif name in {"frank-npu.env", "frank-npu.service", "serve-frank-npu.sh"}:
+            _add(services, "frank-npu")
+        elif name in {"frank-small.env", "frank-small.service", "serve-frank-small.sh"}:
+            _add(services, "frank-small")
         elif name == "chat-template.jinja":
             # Only the selected target's LLM consumes this shared template.
-            _add(services, "frank-default-large" if target == "dankclaw" else "frank-default-small")
+            _add(services, "frank-large" if target == "dankclaw" else "frank-small")
         elif name in {"homepage-status.py", "homepage-status.service", "homepage-status.timer"}:
             _add(services, "homepage")
         # Deployment/test/benchmark scripts and other repo tooling do not

scripts/deploy-remote.sh

@@ -90,13 +90,12 @@ service_is_allowed() {
         dankclaw:authentik-postgres|dankclaw:authentik-server|\
         dankclaw:authentik-worker|dankclaw:authentik-outpost|dankclaw:authentik-outpost-ldap|dankclaw:anubis|\
         dankclaw:caddy|dankclaw:homepage|dankclaw:seerr|\
-        dankclaw:frank-default-large|dankclaw:frank-default-npu|\
-        dankclaw:frank-default-sightsound|\
+        dankclaw:frank-large|dankclaw:frank-npu|\
         dankserver:romm-mariadb|dankserver:romm-redis|dankserver:romm|\
         dankserver:copyparty|dankserver:jellyfin|dankserver:calibre-web|dankserver:plex|dankserver:tautulli|\
         dankserver:prowlarr|dankserver:qbittorrent|dankserver:radarr|\
         dankserver:sonarr|dankserver:lidarr|dankserver:readarr|\
-        dankserver:frank-default-small|\
+        dankserver:frank-small|\
         frankbook-pro:gluetun|frankbook-pro:qbittorrent|frankbook-pro:prowlarr|\
         frankbook-pro:radarr|frankbook-pro:sonarr|frankbook-pro:lidarr|\
         frankbook-pro:readarr)
@@ -182,8 +181,9 @@ add_pending_services() {
             continue
         fi
         [[ -n "$recorded" && "$recorded" != "$REVISION" ]] || continue
-        if [[ "$TARGET" == dankclaw && "$service" == frank-default-small ]]; then continue; fi
-        if [[ "$TARGET" == dankserver && "$service" == frank-default-large ]]; then continue; fi
+        if [[ "$TARGET" == dankclaw && "$service" == frank-small ]]; then continue; fi
+        if [[ "$TARGET" == dankserver && "$service" == frank-large ]]; then continue; fi
+        if [[ "$TARGET" == dankserver && "$service" == frank-npu ]]; then continue; fi
         if ! changed="$(python3 scripts/deploy-plan.py --target "$TARGET" \
             --repo "$REMOTE_DIR" --base "$recorded" --head "$REVISION")"; then
             echo "WARN: unable to compare state for $service; retaining it as pending" >&2
@@ -826,40 +826,45 @@ deploy_anubis() {
     wait_container_healthy anubis 60 || return 1
 }
 
+# Rename cutover (2026-09-03): frank-default-large -> frank-large,
+# frank-default-small -> frank-small, frank-default-sightsound -> frank-npu.
+# The legacy units are stopped and disabled before the renamed unit takes the
+# port so no legacy process is left holding it; stop/disable of an already
+# unloaded legacy unit fail harmlessly and are tolerated.
 deploy_llm_large() {
-    relink_unit frank-default-large
-    # NPU is intentionally not restarted here. It is a separate, retired
-    # endpoint and its unit is only relinked when explicitly selected.
+    run_privileged systemctl stop frank-default-large || true
+    run_privileged systemctl disable frank-default-large || true
+    relink_unit frank-large
     run_privileged systemctl daemon-reload
-    run_privileged systemctl enable frank-default-large
-    run_privileged systemctl restart frank-default-large
-    wait_for_health frank-default-large http://127.0.0.1:7770/health 1200
+    run_privileged systemctl enable frank-large
+    run_privileged systemctl restart frank-large
+    wait_for_health frank-large http://127.0.0.1:7770/health 1200
 }
 
 deploy_llm_small() {
-    relink_unit frank-default-small
+    run_privileged systemctl stop frank-default-small || true
+    run_privileged systemctl disable frank-default-small || true
+    relink_unit frank-small
     run_privileged systemctl daemon-reload
-    run_privileged systemctl enable frank-default-small
-    run_privileged systemctl restart frank-default-small
-    wait_for_health frank-default-small http://127.0.0.1:7770/health 1200
+    run_privileged systemctl enable frank-small
+    run_privileged systemctl restart frank-small
+    wait_for_health frank-small http://127.0.0.1:7770/health 1200
 }
 
+# frank-npu is a live serving endpoint (FLM on the XDNA2 NPU), not a
+# relink-only unit: it is enabled at boot and restarted on deploy. The health
+# gate polls /v1/version, FLM's cheapest always-on route (there is no /health
+# route in the FLM server).
 deploy_llm_npu() {
-    relink_unit frank-default-npu
+    run_privileged systemctl stop frank-default-sightsound || true
+    run_privileged systemctl disable frank-default-sightsound || true
+    run_privileged systemctl stop frank-default-npu || true
+    run_privileged systemctl disable frank-default-npu || true
+    relink_unit frank-npu
     run_privileged systemctl daemon-reload
-    echo "Relinked frank-default-npu; it was not restarted."
-}
-
-# frank-default-sightsound is a live serving endpoint (FLM on the XDNA2 NPU),
-# not a relink-only unit: it is enabled at boot and restarted on deploy. The
-# health gate polls /v1/version, FLM's cheapest always-on route (there is no
-# /health route in the FLM server).
-deploy_llm_sightsound() {
-    relink_unit frank-default-sightsound
-    run_privileged systemctl daemon-reload
-    run_privileged systemctl enable frank-default-sightsound
-    run_privileged systemctl restart frank-default-sightsound
-    wait_for_health frank-default-sightsound http://127.0.0.1:7771/v1/version 300
+    run_privileged systemctl enable frank-npu
+    run_privileged systemctl restart frank-npu
+    wait_for_health frank-npu http://127.0.0.1:7771/v1/version 300
 }
 
 wait_for_health() {
@@ -1045,10 +1050,9 @@ deploy_service() {
             ;;
         anubis) deploy_anubis ;;
         seerr) deploy_seerr ;;
-        frank-default-large) deploy_llm_large ;;
-        frank-default-small) deploy_llm_small ;;
-        frank-default-npu) deploy_llm_npu ;;
-        frank-default-sightsound) deploy_llm_sightsound ;;
+        frank-large) deploy_llm_large ;;
+        frank-small) deploy_llm_small ;;
+        frank-npu) deploy_llm_npu ;;
         hermes|hermes-dashboard|hermes-webui) deploy_hermes ;;
         romm|romm-mariadb|romm-redis|mariadb|redis) deploy_romm_stack "$service" ;;
         jellyfin) deploy_jellyfin ;;

scripts/deploy.sh

@@ -34,7 +34,7 @@ Options:
 Examples:
   ./scripts/deploy.sh dankclaw
   ./scripts/deploy.sh dankclaw --service searxng
-  ./scripts/deploy.sh dankserver --service frank-default-small
+  ./scripts/deploy.sh dankserver --service frank-small
   ./scripts/deploy.sh dankclaw --dry-run
 EOF
 }
@@ -134,13 +134,12 @@ valid_service() {
         dankclaw:hermes-webui|dankclaw:prometheus|dankclaw:grafana|dankclaw:loki|dankclaw:alloy|\
         dankclaw:node-exporter|dankclaw:authentik-postgres|dankclaw:authentik-server|\
         dankclaw:authentik-worker|dankclaw:authentik-outpost|dankclaw:authentik-outpost-ldap|dankclaw:anubis|dankclaw:seerr|\
-        dankclaw:frank-default-large|dankclaw:frank-default-npu|\
-        dankclaw:frank-default-sightsound|\
+        dankclaw:frank-large|dankclaw:frank-npu|\
         dankserver:romm-mariadb|dankserver:romm-redis|dankserver:romm|\
         dankserver:copyparty|dankserver:jellyfin|dankserver:calibre-web|dankserver:plex|dankserver:tautulli|\
         dankserver:qbittorrent|dankserver:radarr|dankserver:sonarr|\
         dankserver:lidarr|dankserver:readarr|dankserver:node-exporter|\
-        dankserver:frank-default-small|\
+        dankserver:frank-small|\
         frankbook-pro:gluetun|frankbook-pro:qbittorrent|frankbook-pro:prowlarr|\
         frankbook-pro:radarr|frankbook-pro:sonarr|frankbook-pro:lidarr|\
         frankbook-pro:readarr)

scripts/download-q8agent.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # Download the kingjones Qwen3.8-27B-ROCmFPX-Q8_0-AGENT payload for
-# frank-default-large from HuggingFace into /home/dank/models/.../Q8_0-AGENT.
+# frank-large from HuggingFace into /home/dank/models/.../Q8_0-AGENT.
 #
 # Uses the token in ~/.cache/huggingface/token so the ~28 GB main file does not
 # hit the anonymous 10 GB/30 min rate limit. Run on Dankclaw.

scripts/frank-default-sightsound.service

@@ -1,17 +0,0 @@
-[Unit]
-Description=FastFlowLM NPU sight+sound inference (frank-default-sightsound) on Dankclaw
-After=network-online.target
-Wants=network-online.target
-
-[Service]
-Type=simple
-User=dank
-Group=dank
-Environment="FLM_SIGHTSOUND_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-default-sightsound.env"
-ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-default-sightsound.sh
-LimitMEMLOCK=infinity
-Restart=on-failure
-RestartSec=10
-
-[Install]
-WantedBy=multi-user.target

scripts/frank-large.env

@@ -1,4 +1,4 @@
-# Tunables for frank-default-large (kingjones777/Qwen3.8-Flash-Next-ROCmFP4-
+# Tunables for frank-large (kingjones777/Qwen3.8-Flash-Next-ROCmFP4-
 # STRIX-GGUF on the kingjones30/ROCmFPX llama.cpp runtime, Dankclaw,
 # Strix Halo gfx1151, unified memory).
 #
@@ -56,7 +56,7 @@ CHAT_TEMPLATE_FILE=/home/dank/serverAppConfigs/scripts/chat-template.jinja
 CHAT_TEMPLATE_KWARGS='{"enable_thinking":true,"preserve_thinking":true,"preserve_reasoning":true}'
 
 # Alias + network.
-ALIAS=frank-default-large
+ALIAS=frank-large
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7770
 

scripts/frank-large.service

@@ -1,5 +1,5 @@
 [Unit]
-Description=ROCmFPX (kingjones30 fork) llama.cpp Qwen3.8-Flash-Next ROCmFP4 STRIX 177B MoE (dankclaw, frank-default-large)
+Description=ROCmFPX (kingjones30 fork) llama.cpp Qwen3.8-Flash-Next ROCmFP4 STRIX 177B MoE (dankclaw, frank-large)
 After=network-online.target
 Wants=network-online.target
 
@@ -7,7 +7,7 @@ Wants=network-online.target
 Type=simple
 User=dank
 Group=dank
-Environment="FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-default-large.env"
+Environment="FRANK_LARGE_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-large.env"
 ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-large.sh
 Restart=on-failure
 RestartSec=10

scripts/frank-npu.env

@@ -1,11 +1,11 @@
-# Tunables for frank-default-sightsound (FastFlowLM NPU sight+sound endpoint, Dankclaw)
+# Tunables for frank-npu (FastFlowLM NPU sight+sound endpoint, Dankclaw)
 # Runtime: FLM 1.0.1 (/usr/bin/flm) on the XDNA2 NPU (50 TOPS). Model:
 # gemma4-it:e4b = Gemma4-E4B-IT-NPU2 (8B total / ~4.5B effective params,
 # Q4_1; vision + audio + reasoning; ~9.1 GB footprint). It is the only NPU2
 # model family with BOTH an image and an audio tower — the uncensored
 # candidate qwythos:9b is text-only and fails the audio requirement, so this
 # endpoint trades "uncensored" for "sight + sound". The NPU draws from the
-# unified RAM pool shared with frank-default-large (iGPU); ~31 GiB was
+# unified RAM pool shared with frank-large (iGPU); ~31 GiB was
 # available there at idle, so a 9.1 GB pack fits with headroom.
 FLM_MODEL=qwen3.8-distilled-heretic:9b
 FLM_HOST=0.0.0.0

scripts/frank-npu.service

@@ -0,0 +1,17 @@
+[Unit]
+Description=FastFlowLM NPU sight+sound inference (frank-npu) on Dankclaw
+After=network-online.target
+Wants=network-online.target
+
+[Service]
+Type=simple
+User=dank
+Group=dank
+Environment="FRANK_NPU_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-npu.env"
+ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-npu.sh
+LimitMEMLOCK=infinity
+Restart=on-failure
+RestartSec=10
+
+[Install]
+WantedBy=multi-user.target

scripts/frank-small.env

@@ -1,4 +1,4 @@
-# Tunables for frank-default-small (batsclamp/Huihui-Qwen3.6-35B-A3B-
+# Tunables for frank-small (batsclamp/Huihui-Qwen3.6-35B-A3B-
 # abliterated-FP8, qwen3_5_moe hybrid MoE, Dankserver, RTX 3090).
 #
 # Runtime: FreeToken v0.1.2 (edge-native MoE serving engine).
@@ -39,7 +39,7 @@ MODEL_DIR=/home/dank/models/huihui-qwen36-35b-a3b-abliterated-fp8
 FT_VENV=/home/dank/freetoken/.venv
 CUDA_HOME_DIR=/home/dank/freetoken/.venv/lib/python3.12/site-packages/nvidia/cu13
 
-ALIAS=frank-default-small
+ALIAS=frank-small
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7770
 

scripts/frank-small.service

@@ -1,5 +1,5 @@
 [Unit]
-Description=FreeToken Huihui-Qwen3.6-35B-A3B-abliterated-FP8 qwen3_5_moe hybrid MoE (dankserver, frank-default-small)
+Description=FreeToken Huihui-Qwen3.6-35B-A3B-abliterated-FP8 qwen3_5_moe hybrid MoE (dankserver, frank-small)
 After=network-online.target
 Wants=network-online.target
 
@@ -7,7 +7,7 @@ Wants=network-online.target
 Type=simple
 User=dank
 Group=dank
-Environment="FRANK_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-default-small.env"
+Environment="FRANK_SMALL_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-small.env"
 ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-small.sh
 Restart=on-failure
 RestartSec=10

scripts/serve-frank-large.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # Serve kingjones777/Qwen3.8-Flash-Next-ROCmFP4-STRIX-GGUF as
-# frank-default-large via the kingjones30/ROCmFPX llama.cpp runtime on
+# frank-large via the kingjones30/ROCmFPX llama.cpp runtime on
 # Dankclaw (Strix Halo gfx1151, unified memory).
 #
 # Runtime: kingjones30/ROCmFPX (fork of charlie12345/ROCmFPX with the
@@ -29,7 +29,7 @@
 set -euo pipefail
 
 SCRIPT_DIR="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")" && pwd)"
-ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-default-large.env}"
+ENV_FILE="${FRANK_LARGE_ENV_FILE:-$SCRIPT_DIR/frank-large.env}"
 if [[ -f "$ENV_FILE" ]]; then
     set -a
     # shellcheck disable=SC1090
@@ -44,7 +44,7 @@ fi
 : "${MMPROJ_PATH:=/home/dank/models/agentionai-Qwen3.8-Flash-Next-ROCmFP4-FAST/mmproj/mmproj-Qwen3.8-Flash-Next-f16.gguf}"
 : "${CHAT_TEMPLATE_FILE:=$SCRIPT_DIR/chat-template.jinja}"
 : "${CHAT_TEMPLATE_KWARGS:={}}"
-: "${ALIAS:=frank-default-large}"
+: "${ALIAS:=frank-large}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7770}"
 : "${CTX_SIZE:=401408}"

scripts/serve-frank-npu.sh

@@ -1,11 +1,11 @@
 #!/usr/bin/env bash
-# Serve the FastFlowLM (FLM) sight+sound endpoint — frank-default-sightsound.
+# Serve the FastFlowLM (FLM) sight+sound endpoint — frank-npu.
 #
 # Runs `flm serve <tag>` on the XDNA2 NPU (50 TOPS, Dankclaw). The NPU is a
 # single-lane device: generations serialize in FIFO order, so this is a
 # background/triage endpoint, not an interactive multi-user chat. The NPU
-# draws from the unified RAM pool shared with frank-default-large (the iGPU
-# llama.cpp service); see serverAppConfigs-docs/LLM/frank-default-sightsound.md
+# draws from the unified RAM pool shared with frank-large (the iGPU
+# llama.cpp service); see serverAppConfigs-docs/LLM/frank-npu.md
 # for the memory budget and the model-selection tradeoff.
 #
 # NOTE: FLM requires unlimited memlock. The unit sets LimitMEMLOCK=infinity.
@@ -18,7 +18,7 @@
 set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-ENV_FILE="${FLM_SIGHTSOUND_ENV_FILE:-$SCRIPT_DIR/frank-default-sightsound.env}"
+ENV_FILE="${FRANK_NPU_ENV_FILE:-$SCRIPT_DIR/frank-npu.env}"
 if [[ -f "$ENV_FILE" ]]; then
     set -a
     # shellcheck disable=SC1090

scripts/serve-frank-small.sh

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # Serve batsclamp/Huihui-Qwen3.6-35B-A3B-abliterated-FP8 as
-# frank-default-small via FreeToken on Dankserver (RTX 3090, 60 GB RAM).
+# frank-small via FreeToken on Dankserver (RTX 3090, 60 GB RAM).
 #
 # Runtime: FreeToken v0.1.2 (edge-native MoE serving engine).
 #   - Experts live in host RAM; an LRU cache of expert slots is resident
@@ -25,12 +25,12 @@
 # via `ft ctl cache --kv N --moe M` (grows KV by shrinking MoE; shrinking
 # KV requires a restart due to the swap-during-rebuild memory cost).
 #
-# Tunables come from frank-default-small.env unless FRANK_SMALL_ENV_FILE
+# Tunables come from frank-small.env unless FRANK_SMALL_ENV_FILE
 # overrides that path.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
-ENV_FILE="${FRANK_SMALL_ENV_FILE:-$SCRIPT_DIR/frank-default-small.env}"
+ENV_FILE="${FRANK_SMALL_ENV_FILE:-$SCRIPT_DIR/frank-small.env}"
 if [[ -f "$ENV_FILE" ]]; then
     set -a
     # shellcheck disable=SC1090
@@ -40,7 +40,7 @@ fi
 
 # --- defaults (used when the env file does not set them) -----------------
 : "${MODEL_DIR:=/home/dank/models/huihui-qwen36-35b-a3b-abliterated-fp8}"
-: "${ALIAS:=frank-default-small}"
+: "${ALIAS:=frank-small}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7770}"
 : "${FT_VENV:=/home/dank/freetoken/.venv}"

scripts/test-changed.sh

@@ -160,12 +160,12 @@ for path in "${CHANGED[@]}"; do
         scripts/mount-entropy.sh)
             add_test tests/mount_entropy.bats
             ;;
-        scripts/frank-default-large.env|scripts/serve-frank-large.sh)
+        scripts/frank-large.env|scripts/serve-frank-large.sh)
             add_test tests/llm_units.bats
             add_test tests/llm_secrets.bats
             add_test tests/scripts_syntax.bats
             ;;
-        scripts/frank-default-small.env|scripts/serve-frank-small.sh)
+        scripts/frank-small.env|scripts/serve-frank-small.sh)
             add_test tests/llm_units.bats
             add_test tests/llm_secrets.bats
             add_test tests/scripts_syntax.bats

tests/deployment_flow.bats

@@ -73,7 +73,7 @@ load helpers
 }
 
 @test "inference restarts are absent from the top-level dispatcher" {
-    ! grep -qE 'systemctl .*restart (frank-default-small|frank-default-large)' "$REPO_ROOT/scripts/deploy.sh"
+    ! grep -qE 'systemctl .*restart (frank-small|frank-large|frank-npu)' "$REPO_ROOT/scripts/deploy.sh"
 }
 
 @test "remote runner health-checks an inference endpoint" {

tests/deployment_scoping.bats

@@ -18,26 +18,26 @@ REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
 
 @test "deployment planner maps large-model changes to the large model only" {
     run python3 "$PLANNER" --target dankclaw --paths \
-        scripts/frank-default-large.env scripts/frank-default-large.service
+        scripts/frank-large.env scripts/frank-large.service
     [ "$status" -eq 0 ]
-    [ "$output" = "frank-default-large" ]
+    [ "$output" = "frank-large" ]
 }
 
 @test "shared chat-template changes map to the selected host's inference service" {
     run python3 "$PLANNER" --target dankclaw --paths scripts/chat-template.jinja
     [ "$status" -eq 0 ]
-    [ "$output" = "frank-default-large" ]
+    [ "$output" = "frank-large" ]
 
     run python3 "$PLANNER" --target dankserver --paths scripts/chat-template.jinja
     [ "$status" -eq 0 ]
-    [ "$output" = "frank-default-small" ]
+    [ "$output" = "frank-small" ]
 }
 
 @test "deployment planner maps small-model changes to the small model only" {
     run python3 "$PLANNER" --target dankserver --paths \
-        scripts/frank-default-small.service
+        scripts/frank-small.service
     [ "$status" -eq 0 ]
-    [ "$output" = "frank-default-small" ]
+    [ "$output" = "frank-small" ]
 }
 
 @test "documentation-only changes plan no runtime deployment" {
@@ -69,9 +69,9 @@ REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
     [ "$status" -eq 0 ]
     [ "$output" = "hermes" ]
 
-    run python3 "$PLANNER" --target dankclaw --paths scripts/serve-frank-default-npu.sh scripts/frank-default-npu.env
+    run python3 "$PLANNER" --target dankclaw --paths scripts/serve-frank-npu.sh scripts/frank-npu.env
     [ "$status" -eq 0 ]
-    [ "$output" = "frank-default-npu" ]
+    [ "$output" = "frank-npu" ]
 }
 
 @test "homepage is owned by Dankclaw's consolidated proxy" {
@@ -155,7 +155,7 @@ REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
     grep -q 'deploy_llm_large' "$REMOTE_DEPLOY"
     grep -q 'deploy_llm_small' "$REMOTE_DEPLOY"
     grep -q 'deploy_service' "$REMOTE_DEPLOY"
-    ! grep -qE 'for .*frank-default-(small|large)' "$REMOTE_DEPLOY"
+    ! grep -qE 'for .*frank-(small|large|npu)-?' "$REMOTE_DEPLOY"
 }
 
 @test "remote runner rejects services belonging to the other host" {

tests/llm_units.bats

@@ -1,6 +1,6 @@
 #!/usr/bin/env bash
 # Seam: LLM systemd unit integrity.
-# Every LLM unit (frank-default-*.service) must point at files that exist in
+# Every LLM unit (frank-*.service) must point at files that exist in
 # this repo. The homepage-status unit is a different pattern (it installs to
 # /usr/local/bin and runs from /srv at deploy time) and is not checked here.
 # The units reference absolute paths on the target checkout
@@ -50,7 +50,7 @@ unit_repo_path() {
             echo "$bad"
             return 1
         fi
-    done < <(find "$REPO_ROOT/scripts" -name 'frank-default-*.service' -type f | sort)
+    done < <(find "$REPO_ROOT/scripts" -name "frank-*.service" -type f | grep -v AGENTTRASH | sort)
     [ "$any" -eq 1 ] || skip "no LLM units yet"
 }
 
@@ -65,7 +65,7 @@ unit_repo_path() {
             echo "unit $(basename "$unit") env file $envfile not in repo"
             return 1
         }
-    done < <(find "$REPO_ROOT/scripts" -name 'frank-default-*.service' -type f | sort)
+    done < <(find "$REPO_ROOT/scripts" -name "frank-*.service" -type f | grep -v AGENTTRASH | sort)
 }
 
 @test "LLM serve scripts exist for every unit" {
@@ -78,5 +78,5 @@ unit_repo_path() {
             echo "unit $svc: ExecStart script $script not in repo"
             return 1
         }
-    done < <(find "$REPO_ROOT/scripts" -name 'frank-default-*.service' -type f | sort)
+    done < <(find "$REPO_ROOT/scripts" -name "frank-*.service" -type f | grep -v AGENTTRASH | sort)
 }

tests/open_webui_quadlet.bats

@@ -4,7 +4,7 @@
 # The old open-webui was a bare container on dankserver (port 3000) pointing at a
 # dead LLM backend (:9090). This unit stands one up on dankclaw on a free port
 # (3005), on the CPU image (dankclaw is CPU-only), wired to the live
-# llama.cpp backend (192.168.0.143:7770, model frank-default-large).
+# llama.cpp backend (192.168.0.143:7770, model frank-large).
 
 load helpers
 
@@ -63,7 +63,7 @@ QDIR="$REPO_ROOT/dankclaw/open-webui/quadlet"
     # gateway (10.89.3.1) lives in the rootless netns, NOT the host netns
     # where llama-server runs -- it refuses. The host's LAN IP reaches it
     # through the rootless NAT (verified from the container, 2026-08-22).
-    # 2026-08-22: frank-default-large moved from :52625 to :7770.
+    # 2026-08-22: frank-large moved from :52625 to :7770.
     grep -qE '^Environment=OPENAI_API_BASE_URL=http://192\.168\.0\.143:7770' \
         "$QDIR/open-webui.container" \
         || { echo "open-webui.container must set OPENAI_API_BASE_URL to the LLM at 192.168.0.143:7770"; return 1; }