frank-medium: serve the new R9700s, retire frank-small

The RTX 3090 left Dankserver; two AMD Radeon AI PRO R9700 cards (Navi 48,
gfx1201, 32,624 MiB each) replaced it. FreeToken/CUDA cannot run there at all,
so the `frank-small` service is retired and `frank-medium` takes the endpoint.

New service: charlie12345/ROCmFPX llama.cpp (built for gfx1201 against the
fork's self-contained ROCm 7.14 toolchain, so the host's stale /opt/rocm-6.3.3
never participates) serving kingjones777/Qwen3.8-27B-ROCmFPX-Q8_0-AGENT-GGUF --
a Q8_0_ROCMFPX_AGENT (ftype 115) checkpoint that stock llama.cpp cannot load.
Placeholder config: --split-mode tensor across both cards, 131072 context,
1 slot, f16 KV, MTP draft head on ROCm0.

deploy-remote.sh grows retire_root_llm_small(): the CUDA-era unit is stopped,
disabled and moved to ~/.AGENTTRASH/20260915-frank-small-retire/host-units
before frank-medium starts, because `systemctl disable` has been observed to
delete the unit file itself on this host (2026-08-26 incident).

The retired frank-small repo files (env, unit, serve script) move to
scripts/.AGENTTRASH/, and the planner, dispatcher, service allow-list and the
deployment test seams now name frank-medium.

scripts/deploy-plan.py

@@ -60,7 +60,7 @@ SERVICE_ORDER = (
     "lidarr",
     "readarr",
     "frank-large",
-    "frank-small",
+    "frank-medium",
 )
 
 DANKCLAW_SERVICES = {
@@ -107,7 +107,7 @@ DANKSERVER_SERVICES = {
     "sonarr",
     "lidarr",
     "readarr",
-    "frank-small",
+    "frank-medium",
 }
 
 # FrankBook-Pro runs the *arr stack + qBittorrent inside a podman machine on
@@ -368,12 +368,13 @@ def services_for_path(path: str, target: str) -> set[str]:
 
     if parts[0] == "scripts":
         name = p.name
-        if name in {"frank-small.env", "frank-small.service", "serve-frank-small.sh"}:
-            _add(services, "frank-small")
+        if name in {"frank-medium.env", "frank-medium.service", "serve-frank-medium.sh"}:
+            _add(services, "frank-medium")
         elif name == "chat-template.jinja":
-            # Only frank-small consumes this template now: frank-large runs
-            # halogen-flash-server, which owns its own chat handling.
-            _add(services, "frank-small")
+            # frank-medium reads this template only when its env file points
+            # at it (the GGUF's embedded template is the default); frank-large
+            # runs halogen-flash-server, which owns its own chat handling.
+            _add(services, "frank-medium")
         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