frank-primary: FreeToken (PR587 ROCm) cutover — trio, seam, deployer

Replaces the tcclaviger vLLM fork with FreeToken at PR #587 head 77a7201
built on dankserver into localhost/frank-primary-freetoken:pr587-77a7201
(scripts/docker/frank-primary-freetoken.Dockerfile: digest-pinned
rocm/pytorch rocm7.14 torch-2.11.0 base, libhiprtc dev symlink, curated
--no-deps install per docs/install_amd.md).

Shape (first-boot conservative): ONE R9700 (second card idle;
--tensor-parallel-size exists for future 2-card tuning), KV pool
--num-tokens 300000 (7.2 GiB at 24 KiB/token; clears the 177,356-token
harness worst case and one native 262,144 conversation), MoE LRU
--moe-cache-rate 0.10, --max-running-requests 2, --max-output-tokens
36864. Parsers AUTO: thinking -> reasoning_content natively (models.yml
flips reasoningContentField on the harness side). Experts + PLE pin
~170 GiB host RAM — root unit keeps LimitMEMLOCK=infinity.

Container identity renamed to the unit name (Frank's call): frank-primary;
vLLM-era frank-primary-qwen joins the legacy cleanup list. Deployer image
gate becomes podman image exists (a local build carries no RepoDigests;
the old digest grep refused exactly this shape). Rollback tag:
frank-primary-vllm-shapeG-20261003.

scripts/deploy-remote.sh

@@ -1250,24 +1250,25 @@ deploy_llm_small() {
     echo "frank-small: health answered by unit MainPID $main_pid"
 }
 
-# deploy_llm_primary — frank-primary is the tcclaviger RDNA4 vLLM fork
-# (digest-pinned image, gfx1201) serving the orcarouter
-# Qwen3.8-Flash-Next-Uncensored-FP8 payload (131 safetensors shards) with
-# MTP4 spec decode and q8/q8 KV on the two R9700s as a ROOT unit whose serve
-# script drives `podman run` directly (the image entrypoint execs
-# `vllm serve`). 2026-09-29 cutover from the R9V radiance fork, whose
-# launcher/shim/setup-state machinery is retired (state dirs stay on disk as
-# rollback; pre-cutover tag frank-primary-r9v-q8-20260929). Same port and
-# alias as the endpoints it replaced; the harness models.yml id is unchanged.
+# deploy_llm_primary — frank-primary is the FreeToken engine (PR #587 ROCm
+# build, gfx1201) serving the orcarouter Qwen3.8-Flash-Next-Uncensored-FP8
+# payload (131 safetensors shards) on ONE R9700 as a ROOT unit whose serve
+# script drives `podman run` directly (the image carries `ft serve`).
+# 2026-10-05 cutover from the tcclaviger vLLM fork (pre-cutover tag
+# frank-primary-vllm-shapeG-20261003); before that, 2026-09-29 cutover from
+# the R9V radiance fork, whose launcher/shim/setup-state machinery is
+# retired. Same port and alias as the endpoints it replaced; the harness
+# models.yml id is unchanged.
 #
-# Gates: the pinned runtime image must be loadable from dank's rootless
-# storage by its OCI manifest digest (the env file's FRANK_PRIMARY_IMAGE),
-# the payload dir must carry config.json and the expected shard count
-# (FRANK_PRIMARY_MODEL_SHARDS), and the unit env must be complete. Per-file
-# sha256 verification was the fetch script's job at download time, never
-# re-hashed here.
-LLM_PRIMARY_CONTAINER=frank-primary-qwen
-LLM_PRIMARY_LEGACY_CONTAINERS="frank-primary-r9v qwen-fp8 glm-probe"
+# Gates: the runtime image must exist in dank's rootless storage
+# (FRANK_PRIMARY_IMAGE — a LOCAL tag: the image is built on the host from
+# scripts/docker/frank-primary-freetoken.Dockerfile, which pins the
+# FreeToken PR-head SHA and the base image), the payload dir must carry
+# config.json and the expected shard count (FRANK_PRIMARY_MODEL_SHARDS),
+# and the unit env must be complete. Per-file sha256 verification was the
+# fetch script's job at download time, never re-hashed here.
+LLM_PRIMARY_CONTAINER=frank-primary
+LLM_PRIMARY_LEGACY_CONTAINERS="frank-primary-qwen frank-primary-r9v qwen-fp8 glm-probe"
 
 deploy_llm_primary() {
     # Refuse rather than restart-loop: a unit whose image or payload is
@@ -1286,15 +1287,16 @@ deploy_llm_primary() {
         echo "ERROR: frank-primary.env missing FRANK_PRIMARY_IMAGE/MODEL_DIR/MODEL_SHARDS" >&2
         return 1
     fi
-    # Capture podman's output BEFORE grepping: under set -o pipefail, the
-    # classic `podman images | grep -q` races (grep exits on match, podman
-    # dies SIGPIPE 141 writing the rest, pipefail calls it no-match — the
-    # 2026-09-30 deploy refusal).
-    local digests
-    digests="$(podman images --format '{{.RepoDigests}}')"
-    if ! grep -qF "${image#*@}" <<<"$digests"; then
-        echo "ERROR: pinned runtime image absent from rootless storage: $image" >&2
-        echo "frank-primary: fetch it (podman pull $image)" >&2
+    # The image gate is EXISTENCE IN STORAGE, not a registry digest: the
+    # FreeToken image is built ON THE HOST (a local tag carries NO
+    # RepoDigests entry — the old grep refused exactly this shape), and
+    # pinning lives in the Dockerfile (pinned PR-head SHA + digest-pinned
+    # base image). `podman image exists` accepts a local tag and a
+    # name@digest ref alike, in one command — no pipefail/grep race (the
+    # 2026-09-30 lesson) for either shape.
+    if ! podman image exists "$image"; then
+        echo "ERROR: runtime image absent from rootless storage: $image" >&2
+        echo "frank-primary: build it (scripts/docker/frank-primary-freetoken.Dockerfile) or pull it" >&2
         return 1
     fi
     if [[ ! -f "$model_dir/config.json" ]]; then

scripts/docker/frank-primary-freetoken.Dockerfile

@@ -31,8 +31,9 @@
 #     Triton kernels on ROCm.
 #
 # Base is digest-pinned (2026-10-05): sha256:a223aee1… is the manifest this
-# build was qualified against; a re-pushed tag cannot change the stack.
-FROM rocm/pytorch@sha256:a223aee17aef5d21c3b9f63436dd19d27d1c665ec8b2f40011c9546cabae2a80
+# build was qualified against; a re-pushed tag cannot change the stack. The
+# readable tag rides along for humans (podman verifies the digest matches).
+FROM rocm/pytorch:rocm7.14_ubuntu24.04_py3.12_pytorch_release_2.11.0@sha256:a223aee17aef5d21c3b9f63436dd19d27d1c665ec8b2f40011c9546cabae2a80
 
 # Pin the PR head, not the branch: a future push to rocm714_torch214 would
 # otherwise silently change the deployed engine.

scripts/frank-primary.env

@@ -1,362 +1,84 @@
-# frank-primary.env — tcclaviger RDNA4 vLLM production config (dankserver :7770).
+# frank-primary.env — FreeToken (PR #587 ROCm) serving the orcarouter
+# Qwen3.8-Flash-Next-Uncensored-FP8 payload on dankserver :7770.
 #
-# 2026-10-03 shape G (as shipped, after the 1.00 revert): the CUDA-graph plan
-# term dropped from the analytic 0.55 GiB to the measured 0.07 GiB (0 base +
-# 12 MiB/graph), and UTIL at the 0.982 law. MEASURED on the live deploy: arena
-# 17.77 GiB / 7,762 slots, KV 401,408 tokens / 2.00x concurrency (the first
-# shape holding two full-length conversations with real spare), driver used
-# 30.97 GiB of 31.86 — 0.89 GiB of real free VRAM per card, held through a
-# live 4,096-token generation. UTIL stays 0.982 ALWAYS: 1.00 is unbootable on
-# this fork (worker init refuses budget >= device total) and 0.13-GiB-margin
-# boots die under load.
-# `budget - non-expert - KV reserve - graphs - overhead` and the KV reserve is a
-# registry constant, so those two terms are the whole flag surface.
-# 2026-10-03 shape F (absorbed): MNBT 2048 + the graph term pinned. Measured on
-# the live deploy: arena 17.52 GiB / 7,653 slots, budget 31.29, graphs 0.32.
-# 2026-10-02 shape E: fp8 KV, MAXLEN 200704 x SEQS 3, pool 3.15e9/rank, and
-# --expert-precise-memory ON. The window shrink from the native 262144 and the
-# --max-num-seqs 3 lock both come from shape D (SEQS=2 CANNOT boot this model —
-# the measured 2x2 is below); shape E adds the precise-overhead plan, which
-# trades the default 7.60 GiB compile headroom for the fitted 5.25 GiB and puts
-# the 2.35 GiB difference into the expert arena: 6,496 -> 7,522 slots (+16%).
-# The pool is deliberately NOT cut (option A): the pool is not an arena lever
-# (measured), so 3.15e9 keeps shape D's 1.99x concurrency while the arena grows.
-# Same digest-pinned tcclaviger RDNA4 fork. Rollback for the fp8+MTP4 era is git
-# tag frank-primary-fp8-mtp-20261001.
+# 2026-10-05 cutover from the tcclaviger RDNA4 vLLM fork (git tag
+# frank-primary-vllm-shapeG-20261003 is the pre-cutover state; the 362-line
+# vLLM-era env is in that tag). The engine is FreeToken at PR head
+# 77a7201f98f00d93f618c6cf8b81ffe8360e0899 (branch rocm714_torch214), built
+# on the host into a local image by
+# scripts/docker/frank-primary-freetoken.Dockerfile — the PR's own
+# docs/install_amd.md stack (ROCm 7.14 base image, torch 2.11.0+rocm7.14,
+# triton 3.7) for gfx1201.
 #
-# HIP reads bare env vars TEMP, HOST, GPU_MAX_HEAP_SIZE — every key here is
-# prefixed FRANK_PRIMARY_ so none can leak. The one bare name we WANT inside the
-# container (GPU_MAX_HW_QUEUES) is held here under the prefix and passed on the
-# run line as `-e GPU_MAX_HW_QUEUES=…`.
+# WHY FREETOKEN: the vLLM fork's expert offload planned VRAM/host tiers per
+# boot from an estimator (util 0.982 law, arena 17.77 GiB / 7,762 slots,
+# ~40k-token GDN state faults) and 1.0 was unbootable. FreeToken keeps ALL
+# expert weights in pinned HOST RAM (~120 GiB) with an LRU GPU cache, sizes
+# KV from an explicit token pool, and serves on ONE R9700 (32 GB) with the
+# second card idle. RAM fit: 246 GiB total, service stopped frees the vLLM
+# container's ~170 GiB; weights ~120 GiB + PLE 47.7 GiB + overhead ≈ 190 GiB.
 #
+# PAYLOAD: unchanged — /home/dank/models/Qwen3.8-Flash-Next-Uncensored-FP8,
+# 131 safetensors shards. Quant is standard modelopt block-FP8: 75,264
+# weight_scale_inv tensors (block 128x128), zero input_scale (FreeToken #462
+# covers exactly this export shape), one weight_scale on the PLE ngram
+# embedding. FreeToken loads HF safetensors directly; no FTW conversion.
 #
-# --- runtime ----------------------------------------------------------------
-# Digest-pinned: the floating :latest tag moved once already. Local alias
-# qwen-fp8-runtime:tuned-20260929 (image ID 3322dbbbc96d) points at the same
-# bytes in rootless storage.
-FRANK_PRIMARY_IMAGE=docker.io/tcclaviger/vllm@sha256:da4029666668b90a0386c1ed23ea370c79916ad4e1a6ad1dd9db098b9fa069ea
+# SERVING FACTS (docs/cli.md, verified against main+PR587):
+# - `ft serve` loads the checkpoint directly; `--served-model-name` keeps the
+#   harness id; reasoning/tool parsers are AUTO (reasoning lands in
+#   reasoning_content — models.yml flips reasoningContentField to match).
+# - KV: --page-size must stay 1 for GDN/SWA models (default); --cache-type
+#   radix auto-picks the GDN-aware variant.
+# - MoE: --moe-strategy auto -> offload (fp8 experts CANNOT use
+#   --moe-cpu-layers; only bf16/nvfp4/mxfp4 have a CPU executor).
+#   --moe-cache-rate holds the GPU LRU fraction of all experts.
+# - `ft ctl cache --kv --moe` grows the pools LIVE on a running server
+#   (shrinking needs a restart); `ft ctl stats` reports pool occupancy.
+# - KV MATH: 12 full-attention layers x 2 KV heads x 256 head_dim x 2 (K+V)
+#   x 2 B = 24 KiB/token (f16 KV; the 36 GDN layers use fixed per-seq state,
+#   not per-token KV). FRANK_PRIMARY_FT_NUM_TOKENS=300000 -> ~7.2 GiB.
+#   Harness worst case = 140,492-token prompt + 36,864 max_tokens = 177,356
+#   < 300,000; one NATIVE 262,144-token conversation + full budget also fits.
+# - PLE: the ~47.7 GiB ngram-embedding table pins in HOST RAM by default
+#   (--ple-backend disk is the alternative); the unit's LimitMEMLOCK=infinity
+#   makes the pin legal. TENS of GiB of pinned pages are why this stays a
+#   ROOT unit — see frank-primary.service.
 
-# --- payload ----------------------------------------------------------------
+# --- Identity (deploy + serve contract) --------------------------------
+FRANK_PRIMARY_IMAGE=localhost/frank-primary-freetoken:pr587-77a7201
 FRANK_PRIMARY_MODEL_DIR=/home/dank/models/Qwen3.8-Flash-Next-Uncensored-FP8
 FRANK_PRIMARY_MODEL_SHARDS=131
-
-# --- identity ---------------------------------------------------------------
-# The harness models.yml id stays frank-primary (provider 192.168.0.235:7770).
-FRANK_PRIMARY_CONTAINER=frank-primary-qwen
+# Container identity is the SERVICE name (Frank's call, 2026-10-05): one
+# name across systemctl and podman ps. The vLLM-era name frank-primary-qwen
+# moved into the legacy list so every deploy cleans it up.
+FRANK_PRIMARY_CONTAINER=frank-primary
+FRANK_PRIMARY_LEGACY_CONTAINERS="frank-primary-qwen frank-primary-r9v qwen-fp8 glm-probe"
 FRANK_PRIMARY_SERVED_NAME=frank-primary
 FRANK_PRIMARY_PUBLISH=7770:7770
-# Containers removed before every start: the retired R9V identity and the ad
-# hoc experiment identity (both hold the GPUs / name registrations).
-FRANK_PRIMARY_LEGACY_CONTAINERS="frank-primary-r9v qwen-fp8"
 
-# --- qualified engine shape (2026-10-02, shape E) ---------------------------
-# WHAT THE SLOT COUNT DOES AND DOES NOT DO. The endpoint advertises 3 slots
-# (SEQS 3), but the POOL, not the slot count, decides how many full-length
-# conversations are resident. MEASURED LIVE 2026-10-02 at this shape:
-#   GPU KV cache size: 398,658 tokens,
-#   Maximum concurrency for 200,704 tokens per request: 1.99x
-# (3,146,129,408 B reserved — 7,892 B/token). The per-token price is
-# SHAPE-DEPENDENT, not a constant: the 262144 shape priced at 7,701 B/token
-# (6,100,000,000 B -> 792,069 tokens), ~2.5% cheaper, so never extrapolate a
-# concurrency figure across geometries. Shorter requests use the spare blocks,
-# and a third LONG request queues rather than being refused. Verified: three
-# concurrent 67-token requests answered in parallel, ~4.1 s each.
-#
-# WHY NOT --max-num-seqs 2 (measured 2026-10-02, single-variable boot probes
-# against the then-deployed known-good shape, production stopped for each):
-#   SEQS 2 + MNBT 1024 -> Engine core initialization failed
-#   SEQS 2 + MNBT 2048 -> Engine core initialization failed
-#   SEQS 3 + MNBT 1024 -> healthy (792,069 tokens, 3.02x, arena 6,248)
-#   SEQS 3 + MNBT 2048 -> healthy (the deployed incumbent)
-# The failure is torch.fx ConstraintViolationError: query_start_loc.size()[0]
-# "marked dynamic but your code specialized it to be a constant (3)", raised
-# from AOT build_guards(strict_error=True) during profile_run -> _dummy_run.
-# model_runner.py sizes that input buffer max_num_reqs + 1 and _dummy_run sets
-# num_reqs = min(max_num_batched_tokens, max_num_reqs), so the width is
-# SEQS + 1 for ANY MNBT >= SEQS: 3 at SEQS 2, 4 at SEQS 3. MNBT only moves the
-# compile RANGE ((1,1024) vs (1,2048)) and cannot dodge it — the 2x2 above is
-# why MNBT is not a lever here. --enforce-eager bypasses the path but loses
-# CUDA graphs. Same failure class killed the 2026-10-01 bf16 2 x 262144 shape.
-#
-# THE ARENA LEVER IS max_model_len, NOT KV_BYTES (measured 2026-10-02). The
-# planner sizes expert cache as budget - non-expert - KV reserve - graphs -
-# overhead, and the KV reserve is registry-priced at 9190 B/token x max_model_len:
-#   MAXLEN 262144 -> reserve 2.48 GiB -> arena 14.30 GiB / 6,248 slots
-#   MAXLEN 200704 -> reserve 1.91 GiB -> arena 14.87 GiB / 6,496 slots
-# d(reserve) 0.57 GiB = d(arena) 0.57 GiB = +248 slots. The 6.1e9 -> 3.15e9
-# pool cut buys ZERO arena; it buys runtime HEADROOM (the shape it replaced
-# died with 0 bytes free on a real 995-token request). To grow the arena,
-# lower MAXLEN — not KV_BYTES. The OTHER arena lever is the overhead term:
-# --expert-precise-memory (shape E) takes it from 7.60 to 5.25 GiB and lands
-# those 2.35 GiB in the arena — 14.87 -> 17.22 GiB / 6,496 -> 7,522 slots.
-#
-# GATHER 32x64 stays: R4D_LRU_GATHER_CHUNKS=32 / R4D_LRU_GATHER_LANES=64
-# measured +18.7% decode vs default geometry and the win grows with depth.
-# Do not drop it.
-# CHUNKED PREFILL: the fork exposes the standard scheduler flags. --max-num-batched-tokens
-# (MNBT) is the lever; --enable-chunked-prefill is an auto-flag (True in SchedulerConfig)
-# and --prefill-schedule-interval is the gap between iterations. The running shape carries
-# --max-num-batched-tokens 2048 with --max-model-len 200704, so chunked prefill is ON and
-# already active: a 200704-token prompt is prefilled in ~98 iterations of 2048 tokens.
-# MEASURED 2026-09-29 on the ad hoc qwen-fp8 container (same fork, same payload, TP=2):
-# MNBT 8192 vs the default 2048 is NEUTRAL on decode at every depth, and small values
-# re-chunk prefill only — they hurt TTFT and never touch decode, because a decode step is
-# max_num_seqs x (spec+1) tokens, independent of MNBT. There is NO --ubatch-size
-# equivalent in vLLM: that is a llama.cpp compute-buffer concept (the frank-small pair
-# doubled on 2026-10-05 has no counterpart here). MNBT is therefore NOT a lever on this
-# shape — the deployed 2048 is the fork's default — and every change re-enters the
-# compile RANGE path, so FRANK_PRIMARY_CACHE_DIR pays one recompilation.
-# MNBT 2048 (Frank's call, 2026-10-03; the lock was 1024). The measured law
-# still holds: MNBT 512 doubles TTFT at 4064 ctx (2.46 s vs 1.36 s), 1024-4096
-# are interchangeable on decode, 12288 costs 2.5% plus arena. 2048 is ARENA-FREE
-# by construction: the registry's overhead model is
-# base + 0.22 GiB x max(0, (nbt - 4096)/1024) with the anchor at nbt 4096, so
-# every rung up to and including 4096 prices the SAME 5.25 GiB overhead — and
-# the fitted 5.25 was fitted at nbt 4096, i.e. our 2048 sits UNDER the anchor,
-# so the activation term is covered by a figure measured at a bigger batch.
-# SEQS 3 boots at both 1024 and 2048 (measured 2026-10-02; the SEQS=2
-# ConstraintViolationError is a SEQS property, not an MNBT one). Costs exactly
-# one recompilation: the compile RANGE is part of the cache key, so
-# FRANK_PRIMARY_CACHE_DIR pays for whichever rung is chosen once.
-# PREFETCH IS ABSENT BY LAW: expert-cache telemetry measured the prefetcher at
-# 36% precision (36,720 slabs prefetched, 13,369 served) — roughly half the
-# gather traffic was waste. Never re-add --expert-prefetch without a fresh A/B.
-# TunableOp stays OFF: CLAV_TUNABLEOP_SWEEP silently skips under expert offload
-# unless CLAV_TUNABLEOP_WITH_OFFLOAD=1, and forcing it corrupts numerics.
-# --expert-precise-memory is ON (shape E). It selects the fitted overhead
-# (5.25 GiB) over the default (7.60 GiB = fitted + compile/graph-capture
-# headroom); the 2.35 GiB difference lands in the expert arena. MEASURED
-# 2026-10-02 by a boot probe on the shape-D base (production stopped, candidate
-# booted AS the service, plan read off the engine's own log):
-#   runtime overhead  7.60 -> 5.25 GiB   (registry Qwen4Exp…, precise
-#                                         gfx1201 TP2 nbt4096/seqs16/len262144)
-#   expert cache      14.87 -> 17.22 GiB
-#   slots             6,496 -> 7,522     (+1,026 = +16%, 2.344 MiB each)
-#   swap region                 13.7 GiB / 5,986 slots, 133-134 per layer
-#   boot                        healthy in 420 s, no OOM, no knife-edge
-# The flag was called a non-option after it crash-looped the 2 x 262144 bf16
-# boot (0.13 GiB free of 31.86 GiB, NRestarts=3 at ~6.7 min each) — that shape
-# was already at the ceiling, so precise-memory was the last 2.35 GiB over, not
-# the cause. At 200704 x 3 it fits with room; the run line also reports
-# 'expert_precise_memory': True in non-default args, so a silent argparse drop
-# would be visible in the boot log.
-FRANK_PRIMARY_PRECISE_MEMORY=1
-# GPU_MAX_HW_QUEUES caps the HSA hardware queues per GPU (AMD's own tuning
-# guide recommends 2 for this class of workload; the runtime default on Linux
-# is 4). Verified a REAL knob, not a no-op: the string is present in
-# /opt/rocm/core-10.0/lib/libhsa-runtime64.so. NOT A/B MEASURED — Frank's call,
-# shipped as a deliberate CPU-side tune alongside the 32x64 gather geometry.
-FRANK_PRIMARY_GPU_MAX_HW_QUEUES=2
-# Persistent compile cache. MEASURED 2026-10-02: the image ships NO
-# /root/.cache at all (`ls: cannot access '/root/.cache'` in a fresh
-# container), and after our boot it holds /root/.cache/vllm at 1,154,714,333 B
-# in 4,665 files plus /root/.cache/comgr at 229 MB — both inside the
-# container's ephemeral layer, so every `podman rm -f` (every deploy, restart
-# and reboot) throws them away and re-pays the build. The engine's own log
-# names the loss: `torch.compile took 181.20 s in total`, of which 'Compiling a
-# graph for compile range (1, 1024) takes 173.19 s', followed by 'saved AOT
-# compiled function to /root/.cache/vllm/torch_compile_cache/…'. Mounting a
-# host dir at /root/.cache persists the vLLM AOT/torch_compile tree AND the
-# comgr HIP-kernel JIT cache, and hides nothing (the image has no such dir).
-# PROVEN LIVE 2026-10-02, two boots of this exact shape:
-#   cold  `Compiling a graph for compile range (1, 1024) takes 179.24 s`
-#         `torch.compile took 188.26 s in total`
-#   warm  `Directly load the compiled graph(s) for compile range (1, 1024)
-#          from the cache, took 2.143 s`
-#         `torch.compile took 3.97 s in total`
-#         `init engine (profile, create kv cache, warmup model) took 41.13 s
-#          (compilation: 3.98 s)`
-# (Total time to /health is dominated by the 172.8 GiB payload load, not the
-# compile — the saving is the ~184 s of inductor/AOT build.)
-# Safe to grow/prune: entries are keyed by version + config hash, so a stale
-# entry is a miss, never a wrong answer.
-FRANK_PRIMARY_CACHE_DIR=/home/dank/.cache/frank-primary
-FRANK_PRIMARY_MAXLEN=200704
-FRANK_PRIMARY_SEQS=3
-# The POOL is deliberately kept at shape D's 3.15e9 (option A): because the pool
-# is not an arena lever, raising it back from a cut buys concurrency only, and
-# 3.15e9 preserves the measured 1.99x while precise-memory grows the arena. A
-# 2.2e9 pool was probed in the same window (277,686 tokens / 1.38x) and rejected
-# as the shipped value; it remains the conservative arm if free VRAM ever binds.
-# KV forced to 400,700 tokens (Frank, 2026-10-03). The engine prices this pool
-# at 7,891.8 B/token at this shape and loses ~3.87 MB to block alignment, so
-# 3,166,500,000 B is the ask that lands at/above 400,700 (verify the reported
-# "GPU KV cache size" line on every deploy; it is not a constant ratio across
-# geometries — 7,701 B/token at 262144).
-FRANK_PRIMARY_KV_BYTES=3166500000
-FRANK_PRIMARY_KV_DTYPE=fp8
-FRANK_PRIMARY_MNBT=2048
-FRANK_PRIMARY_GATHER_CHUNKS=32
-FRANK_PRIMARY_GATHER_LANES=64
-# PREFIX CACHING: ON. An OFF experiment ran 2026-10-05 (below) and FAILED
-# to stop the corruption, so the historical flag is back.
-# MEASURED 2026-10-04, 18:46:07 PDT (5.6 h into the live boot, one running
-# request, prefix hit rate 48.1%): 48 gdn_hip state faults in one 0.6 s
-# burst, then the process-lifetime silence cap:
-#   [gdn_hip] ERROR gdn_decode_r: state out of ssm-cache range: max|S|=0
-#   with non-finite values (slot=42 head=3 limit=3.40282e+38) fault #1-23
-#   [gdn_hip] ERROR gdn_decode_r: ... (slot=42 head=8 ...) fault #24-46
-#   [gdn_hip] ERROR: state fault report limit (32) reached; further faults
-#   are counted silently
-# One physical SSM slot, two heads, BOTH ranks (heads 3 and 8), 23 layers
-# each. The guard's own message in this build: "known Qwen3.8-Flash-Next
-# (QFN) flaw under prefix caching and is being actively worked; output
-# quality for this request may degrade. Mitigation:
-# --no-enable-prefix-caching".
-# MECHANISM: with prefix caching on, this fork puts QFN on
-# mamba_cache_mode 'align' (the default-for-this-arch branch in
-# config/vllm.py; 'all' is deprecated and 'none' is the no-prefix-cache
-# mode, so align is the only sound mode WITH the flag). Align mode
-# checkpoints each sequence's GDN (Gated DeltaNet) recurrent state into a
-# mamba page every block, where block = 3136 tokens (the attention block
-# size is raised to 3136 so the page sizes match exactly — the boot log's
-# "Padding mamba page size by 0.13% ..."), and RE-SEEDS the state from that
-# page whenever a request resumes from a cached prefix. The corrupt state
-# landed at the 13th boundary: 13 x 3136 = 40,768 tokens — the "~40k" mark
-# where the request's output turned repetitive/corrupted. The NaN stayed
-# in the mamba page, so every later turn of that conversation re-seeded the
-# same non-finite state for those two heads (silent: the fault-report cap
-# was already spent), while fresh short sessions looked fine.
-# RAM WAS "RULED OUT" THE SAME DAY — AND THAT WAS WRONG (RESOLVED below).
-# What the evidence actually supported: zero MCE/EDAC records is the
-# EXPECTED silence of consumer non-ECC memory (a silent flip raises no
-# machine check); an 8 GiB pattern check over 60 s covers ~0.5 % of
-# 246 GiB — no verdict on a speed setting; "4800 is the JEDEC floor on
-# 5600-rated DIMMs" is a rating, not a stability proof at four-DIMM
-# loading. Only the two-head NaN signature argument was load-bearing,
-# and the revert test outvoted it.
-# COST ACCEPTED: no prefix reuse, so each turn re-prefills the whole
-# history instead of at most 3135 tail tokens (a full 40k context costs
-# tens of seconds of TTFT per turn at this shape's prefill rate). A silently
-# corrupted conversation is worse than a slower first token.
-# RESULT (2026-10-05, later that day): THE MITIGATION DID NOT WORK. With
-# --no-enable-prefix-caching deployed and mechanically verified (zero
-# gdn_hip faults, a 40,771-token single-request boundary probe coherent),
-# live long conversations STILL degraded at ~40k on the running endpoint
-# (Frank, direct). The container serving that window logged ZERO faults
-# while the corruption reproduced, so the align-mode page re-seed is not
-# the (only) mechanism — see the runbook's RESULT note for the open
-# hypotheses (re-fed poisoned transcript vs a fault-free long-context
-# path such as fp8 KV at depth). Cost bought nothing: caching is back ON.
-# The knob stays commented for a future fork build with a fixed GDN state
-# path: set 1, redeploy, re-verify past 40,768 tokens (one conversation
-# coherent AND zero gdn_hip lines).
-# RESOLVED 2026-10-05 EVENING (Frank): IT WAS THE RAM. 4800 MT/s (in
-# effect since the 2026-10-04 17:17 boot) was marginal; 4600 MT/s (since
-# the 2026-10-05 12:21 boot) and the endpoint is clean — zero gdn_hip
-# ERROR lines, zero MCE, and the live agent session on it past 140k
-# context with no degradation. Both failure eras sit under the RAM: the
-# 2026-10-04 NaN burst (corrupted weight/activation traffic poisoning a
-# GDN state write — the guard-visible path) and the fault-free ~40k
-# degradation (silent flips in KV/expert data, which no guard covers on
-# non-ECC). CONSEQUENCE FOR THE KNOB: the OFF experiment was CONFOUNDED
-# — both arms ran on the marginal speed — so it neither proved nor
-# disproved the fork's align-mode flaw. Prefix caching stays ON (zero
-# gdn_hip lines under heavy re-send traffic since the speed drop); flip
-# the knob only if a fault recurs on stable RAM or the fork ships a fix.
-# FRANK_PRIMARY_NO_PREFIX_CACHING=1
-# UTIL is an ARENA lever: the fork plans `budget = device_total x util`, and at
-# 31.86 GiB/card every +0.01 is +0.32 GiB of expert cache (~+139 slots), and
-# 0.982 is Frank's standing law: NEVER 1.00. The 1.00 attempt (2026-10-03,
-# shape G v1) died in worker init BEFORE loading a byte of weights — the fork
-# refuses budget >= device total with
-#   ValueError: Free memory on device cuda:N (31.29/31.86 GiB ...)
-# on BOTH ranks at 09:53 and 09:54, NRestarts=2 — so 1.0 is not even a runtime
-# knife-edge here, it is unbootable. The two historical ceiling deaths (the
-# 2x262144 bf16 boot at 0.13 GiB free; the 5x262144 boot at "0 bytes free" on a
-# real 995-token request) remain the reason the margin exists. Rollback note
-# for the other direction: if a request ever dies with
-# `Tried to allocate ... 0 bytes free`, the first knob back is THIS number
-# down a notch, not the window.
-FRANK_PRIMARY_UTIL=0.982
-# CUDA-graph plan term, priced at the measured capture. expert_plan.py charges
-# estimate_cudagraph_memory() = BASE_MB + PER_GRAPH_MB x n_graphs (defaults
-# 256/52 = 0.55 GiB for our 6-graph plan), and the estimator's own docstring
-# says to tune these against the post-capture line. MEASURED twice on this
-# shape: shape E reported "Graph capturing finished ... took 0.31 GiB" (TP0) and
-# 0.17 GiB (TP1); shape F, with the 0.32 GiB we then charged, reported
-# "took -0.06 GiB" — a NEGATIVE delta, i.e. capture fits inside memory the
-# profiler had already counted. So the base pool (256 MiB) is the over-charge:
-# charge 0 base + 12 MiB/graph = 0.07 GiB for the shipped no-spec 6-graph plan,
-# which returns 0.25 GiB more to the arena while still paying per graph, so a
-# future spec-decode shape (18 graphs) is charged 0.21 GiB rather than zero.
-# Verify every deploy against the "Estimated CUDA graph memory" vs "Graph
-# capturing finished ... took X GiB" lines; if capture ever goes positive and
-# exceeds the charge, raise FRANK_PRIMARY_CUDAGRAPH_PER_GRAPH_MB back toward 52.
-# A THIRD env var exists and is the only way to state the graph term outright:
-# VLLM_CUDAGRAPH_MEM_ESTIMATE_MB pins the WHOLE term to an exact MiB total in
-# one knob — estimate_cudagraph_memory() checks it FIRST and returns base/
-# per-graph untouched when set (verified in the shipped image,
-# v1/worker/gpu/cudagraph_mem.py). We ship the BASE/PER_GRAPH pair instead so
-# a future spec-decode shape re-prices automatically; switch to ESTIMATE_MB
-# only if the drift check below ever shows the pair cannot track capture.
-FRANK_PRIMARY_CUDAGRAPH_BASE_MB=0
-FRANK_PRIMARY_CUDAGRAPH_PER_GRAPH_MB=12
-
-# HOST-region cap — the last arena-plan term that still autofit per boot. With
-# no cap the planner's host bound is MemAvailable AT BOOT minus PLE 47.68 -
-# 2 x 7.0 process - 5.0 api/engine - 5% margin (measured boot 2026-10-05:
-# MemAvailable 237.97 -> 159.39 GiB usable across 2 ranks; the demand is 105.48
-# = 52.74/rank x 2 ranks, 23,040 swap-target experts). The same host reads 75.4
-# GiB available while running — the bound tracks whatever the co-tenants hold at
-# boot, and a boot where that drops near the demand silently pins next-hottest
-# experts VRAM-only instead (smaller swap region; the pinned_extra warning is
-# the only trace). Pin 120 GiB: measured demand + 14% headroom, on a host with
-# 246.1 GiB total. If a boot ever logs "expert-offload-mem … exceeds
-# MemAvailable at plan time", THAT is the contract being broken — look at the
-# co-tenant RAM before touching this number. Plan semantics verified in the
-# shipped image (offloader/expert_plan.py): the cap binds as the bound, an
-# exceedance only warns.
-FRANK_PRIMARY_EXPERT_OFFLOAD_MEM=120
-
-# --- optional engine knobs (unset == the flag is absent) ---------------------
-# FRANK_PRIMARY_SPEC holds the WHOLE --speculative-config JSON; setting it adds
-# the flag. THE RETIREMENT VERDICT WAS INVALID: c1248d4 (2026-10-02) retired MTP
-# by comparing fp8+MTP4 (37.4-40.6 tok/s, 54% acceptance, 09-29) against the
-# bf16 no-spec boot (36.4-39.4) — and bf16 then proved unbootable, so fp8 came
-# back without MTP and fp8+spec was NEVER compared against fp8+no-spec on the
-# same shape. The no-spec incumbent measures ~30 tok/s single-stream (below the
-# fleet's 35 tok/s target); every vendor flash-next recipe ships MTP3; and our
-# MTP4 run used the fork's default GREEDY draft sampling, while the recipes pass
-# draft_sample_method=probabilistic (greedy drafts are rejected more often under
-# temp>0 — the plausible cause of the 54%). MTP also re-adds drafter workspace:
-# the old note says the 7.2 GiB/rank KV ceiling WAS the MTP4 workspace, and
-# --expert-precise-memory spends that same budget, so an MTP arm must be tested
-# with precise memory BOTH on and off.
-#   MTP3:  '{"method":"mtp","num_speculative_tokens":3,"draft_sample_method":"probabilistic"}'
-FRANK_PRIMARY_SPEC=
-# FRANK_PRIMARY_COMPCONFIG holds the whole --compilation-config JSON. The
-# capture-ladder law: the piecewise cudagraph ladder must contain
-# num_speculative_tokens + 1 (MTP3 -> 4 -> ladder 4,8,12; MTP4 -> 5,10,15;
-# MTP5 -> 6,12,18,24), because every draft step proposes n+1 tokens. The default
-# ladder is multiples of 1+4 up to 512 then powers of two, so an MTP3 shape can
-# miss its own step size. Pinning the ladder is ALSO the candidate fix for the
-# SEQS>3 wall: query_start_loc is specialised to SEQS+1 and that constant must
-# land on a captured graph size (3 is not in the default ladder, 4 is —
-# measured 2026-10-02, and the vendor runs SEQS 16 on this model/TP2).
-# combo_kernels false/true are BOTH in the shipped recipes, so it is not a law.
-#   MTP3 at SEQS 3:  '{"cudagraph_mode":"PIECEWISE","cudagraph_capture_sizes":[1,4,8,12],"max_cudagraph_capture_size":12}'
-FRANK_PRIMARY_COMPCONFIG=
-# FRANK_PRIMARY_GEN_CONFIG holds the whole --override-generation-config JSON.
-# The payload's HF generation_config.json sets temperature 1.0 / top_p 0.95 /
-# top_k 20 and the engine WARNS about it on every boot, so a client that sends
-# no sampling fields gets creativity it never asked for. This is the one knob
-# that changes ANSWERS, not speed.
-#   '{"max_tokens":65536,"temperature":0.7,"top_p":0.95,"top_k":20}'
-FRANK_PRIMARY_GEN_CONFIG=
-
-# --- client contract: reasoning split, tools, preserve_thinking ----------------
-# Without --reasoning-parser the engine leaves the thinking text INLINE in
-# `content` with a dangling `</think>` and a null `reasoning` field (measured
-# 2026-10-01: content = 'We need answer...Brief.\n\n391') — the
-# malformed thinking block clients choke on. The qwen3 parser splits it
-# properly. The GLM rollback (d91379d) had dropped all three of these; the
-# working values are the ones ecaad36 shipped for this model.
-FRANK_PRIMARY_REASONING_PARSER=qwen3
-# Tools: --enable-auto-tool-choice + the qwen3_xml parser is what makes
-# tool_calls work here (without it, tool_choice auto returns 400).
-FRANK_PRIMARY_TOOL_PARSER=qwen3_xml
-# preserve_thinking keeps prior thinking blocks in the rendered prompt across
-# turns; enable_thinking makes thinking the server-side default. Verified the
-# payload's tokenizer_config template consumes both keys.
-FRANK_PRIMARY_CHAT_TEMPLATE_KWARGS='{"enable_thinking": true, "preserve_thinking": true}'
+# --- FreeToken engine knobs (first-boot conservative, resize live) -----
+# Single GPU: the R9700 at index 0. HIP_VISIBLE_DEVICES=0 hides card 1 so
+# the in-container index 0 IS the right card; --gpu 0 selects it.
+FRANK_PRIMARY_FT_GPU=0
+# KV pool in TOKENS (not bytes — vLLM-era FRANK_PRIMARY_KV_BYTES is gone).
+# 300,000 tokens x 24 KiB = 7.2 GiB; clears the harness worst case 177,356.
+# Grows live with `ft ctl cache --kv <n>`; shrink needs a restart.
+FRANK_PRIMARY_FT_NUM_TOKENS=300000
+# Concurrent decode slots. 2 is the first-boot conservative value; the
+# radix pool admits ~2 full-length 200,704-token conversations. Raise with
+# --max-running-requests only after a real-traffic look at slot occupancy.
+FRANK_PRIMARY_FT_MAX_RUNNING=2
+# Per-request output budget ceiling: the harness's maxTokens (36,864).
+# Requests that omit max_tokens get this default instead of the engine's
+# 32,768.
+FRANK_PRIMARY_FT_MAX_OUTPUT_TOKENS=36864
+# GPU expert LRU cache as a FRACTION of all experts (~120 GiB fp8 total ->
+# ~12 GiB VRAM at 0.10). First-boot conservative; resize live with
+# `ft ctl cache --moe` after reading the boot ledger + ft ctl stats.
+FRANK_PRIMARY_FT_MOE_RATE=0.10
+# Escape hatch for boot-ladder experiments (YaRN, --max-prefill-length,
+# --moe-cpu-threads, --sampling-defaults none, ...). Unset -> no extra
+# argv. Keep multi-flag values as one string; the serve script expands it
+# unquoted on purpose.
+FRANK_PRIMARY_FT_EXTRA_ARGS=

scripts/frank-primary.service

@@ -1,29 +1,26 @@
-# frank-primary.service — tcclaviger RDNA4 vLLM endpoint (orcarouter
-# Qwen3.8-Flash-Next-Uncensored-FP8, fp8 KV, NO spec decode, 3 slots x 200704
-# context with the pool sized to ~2 full-length conversations, TP=2, tiered
-# experts, 131-shard payload) on the 2x R9700 pair, dankserver :7770.
-# 2026-09-29 cutover from the R9V radiance fork (git tag
-# frank-primary-r9v-q8-20260929 is the pre-cutover state; its
-# launcher/shim/setup-state machinery is retired and the state dirs stay on
-# disk as rollback).
+# frank-primary.service — FreeToken (PR #587 ROCm) endpoint (orcarouter
+# Qwen3.8-Flash-Next-Uncensored-FP8, 131-shard payload) on ONE R9700
+# (gfx1201), dankserver :7770. 2026-10-05 cutover from the tcclaviger vLLM
+# fork (git tag frank-primary-vllm-shapeG-20261003 is the pre-cutover
+# state; the retired unit/env/serve trio is in that tag).
 #
-# Same port, same served alias; the harness models.yml id is unchanged.
-# The serve script drives `podman run` directly (the image entrypoint execs
-# `vllm serve`) and then waits on the container. NOTE: that wait can return
-# 0 even when the engine died mid-request (vLLM's API server drains and
-# exits clean on a worker fault), which is why the restart policy is
-# `always` — see the [Service] note.
+# Same port, same served alias, same container identity as the unit name;
+# the harness models.yml id is unchanged. The serve script drives
+# `podman run` directly (the image carries `ft serve`) and then waits on
+# the container. The image is built ON THE HOST from
+# scripts/docker/frank-primary-freetoken.Dockerfile (FreeToken PR head
+# 77a7201 in the PR's own ROCm 7.14 base image).
 #
-# WHY A ROOT UNIT (not a rootless quadlet): the tiered-expert shape pins tens
-# of GiB of host RAM (the expert host slabs, ~20.5 GiB per rank of pinned
-# anonymous memory). Pinned pages are charged against RLIMIT_MEMLOCK; dank's
-# login session on this host carries 8 MiB and a user quadlet is capped by the
-# user manager's own hard limit — raising that means restarting
-# user@1000.service and bouncing every user container on the host. A root unit
-# grants LimitMEMLOCK=infinity to the dank process via PID1, and the image
-# stays in dank's rootless podman storage.
+# WHY A ROOT UNIT (not a rootless quadlet): FreeToken pins ~120 GiB of
+# expert weights plus the ~47.7 GiB PLE ngram table in HOST RAM. Pinned
+# pages are charged against RLIMIT_MEMLOCK; dank's login session on this
+# host carries 8 MiB and a user quadlet is capped by the user manager's own
+# hard limit — raising that means restarting user@1000.service and bouncing
+# every user container on the host. A root unit grants
+# LimitMEMLOCK=infinity to the dank process via PID1, and the image stays
+# in dank's rootless podman storage.
 [Unit]
-Description=frank-primary — tcclaviger vLLM Qwen3.8-Flash-Next-Uncensored-FP8 on 2x R9700
+Description=frank-primary — FreeToken (PR587) Qwen3.8-Flash-Next-Uncensored-FP8 on 1x R9700
 After=network-online.target
 Wants=network-online.target
 # Never let the start-rate limiter give up after a crash loop (a failed LLM
@@ -33,34 +30,35 @@ StartLimitIntervalSec=0
 [Service]
 User=dank
 Group=dank
-# The tiered-expert offloader pins host RAM; an RLIMIT_MEMLOCK smaller than
-# the pinned set fails the load mid-start. PID1 grants infinity here —
+# The expert LRU + PLE pin ~170 GiB of host RAM; an RLIMIT_MEMLOCK smaller
+# than the pinned set fails the load mid-start. PID1 grants infinity here —
 # parity with the fleet's other LLM units.
 LimitMEMLOCK=infinity
 Environment="FRANK_PRIMARY_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-primary.env"
 ExecStart=/home/dank/serverAppConfigs/scripts/serve-frank-primary.sh
 # systemd stop: wait alone cannot stop the container child; stop it
-# explicitly. vLLM 0.26 drains gracefully on SIGTERM.
-ExecStop=/usr/bin/podman stop -t 120 frank-primary-qwen
-# Boot cost: FP8 payload page-in plus torch compile/graph capture —
-# ~15 min cold (measured 2026-09-29), faster warm.
+# explicitly. ft serve drops connections on SIGTERM; no graceful drain
+# contract is claimed (the OpenAI front end holds no queue to drain —
+# in-flight decodes are lost, which a stop during a bench window accepts).
+ExecStop=/usr/bin/podman stop -t 120 frank-primary
+# Boot cost: 131-shard FP8 page-in + PLE pin + expert upload. vLLM-era
+# budget (1800 s) carried forward; the FreeToken first boot measured here
+# once it ran (see the runbook for the real number).
 TimeoutStartSec=1800
-# Restart=always, NOT on-failure (measured 2026-10-01): a runtime
-# torch.OutOfMemoryError kills the engine while vLLM's API server still
-# exits 0, so ExecStart returned clean, systemd logged "Deactivated
-# successfully", and on-failure NEVER fired — the endpoint stayed down until
-# a human noticed. `always` restarts on any container death; an explicit
-# `systemctl stop` still wins (systemd does not restart a unit the operator
-# stopped), so bench windows and deploys are unaffected.
+# Restart=always, NOT on-failure (the 2026-10-01 vLLM lesson carries over:
+# a clean API-server exit after a worker fault reads as success to
+# systemd). `always` restarts on any container death; an explicit
+# `systemctl stop` still wins, so bench windows and deploys are unaffected.
 Restart=always
 RestartSec=10
-# ExecStop allows the engine 120 s to drain (`podman stop -t 120`); without an
-# explicit TimeoutStopSec systemd's 90 s default cuts the stop short, kills it,
-# and records 'Failed with result timeout' (measured 2026-10-01 13:27:17).
-# Must exceed the podman grace with margin for the engine's own shutdown.
+# ExecStop allows the engine 120 s to drain (`podman stop -t 120`); without
+# an explicit TimeoutStopSec systemd's 90 s default cuts the stop short,
+# kills it, and records 'Failed with result timeout' (measured 2026-10-01
+# 13:27:17). Must exceed the podman grace with margin.
 TimeoutStopSec=180
-# The engine pins tens of GiB of host RAM (expert host slabs); it is the
-# last process on this host that should be chosen by the kernel OOM killer.
+# The engine pins tens of GiB of host RAM (expert rows + PLE table); it is
+# the last process on this host that should be chosen by the kernel OOM
+# killer.
 OOMScoreAdjust=-500
 
 [Install]

scripts/serve-frank-primary.sh

@@ -1,58 +1,31 @@
 #!/usr/bin/env bash
-# serve-frank-primary.sh — frank-primary endpoint (tcclaviger RDNA4 vLLM fork,
-# orcarouter Qwen3.8-Flash-Next-Uncensored-FP8, 2x R9700,
-# dankserver :7770; 2026-09-29 cutover from the R9V radiance fork — git tag
-# frank-primary-r9v-q8-20260929 is the pre-cutover state).
-#
-# The engine is driven by `podman run` DIRECTLY: the image's entrypoint execs
-# `vllm serve "$@"`, so the run line below IS the engine argv. This replaces
-# the R9V launcher/shim machinery (that fork needed a docker->podman shim and
-# a 104-key on-host setup state; this stack is fully expressed by flags, and
-# every flag here was qualified by boot probe on 2026-09-29 — see
-# frank-primary.env for the qualification record).
-#
-# Shape (2026-10-03 shape F, on the 2026-10-02 shape E base): MAXLEN 200704 x 3
-# slots, fp8 KV, KV_BYTES
-# 3,150,000,000 PER RANK — the POOL, not the slot count, caps resident
-# conversations at ~2 full-length (measured: 398,658 tokens = 1.99x);
-# shorter requests use the spare blocks. --max-num-seqs stays 3 because SEQS=2
-# CANNOT boot this model
-# (torch.fx ConstraintViolationError on query_start_loc, measured at both
-# MNBT 1024 and 2048 — the 2x2 lives in frank-primary.env). Speculative decode
-# is OFF today by ENV KNOB, not by measurement: FRANK_PRIMARY_SPEC / _COMPCONFIG
-# / _GEN_CONFIG hold the whole JSON value and unset means no flag. The 2026-10-02
-# retirement of MTP compared the wrong pair — see frank-primary.env.
-# --max-num-batched-tokens 2048 (Frank's call 2026-10-03; arena-free because the
-# registry prices overhead flat up to its nbt 4096 anchor), MoE gather geometry
-# R4D_LRU_GATHER_CHUNKS=32 / R4D_LRU_GATHER_LANES=64 (+18.7% decode, grows
-# with depth), prefix caching OFF 2026-10-05 (the fork's QFN align-mode GDN
-# state fault — the evidence block is in frank-primary.env), expert prefetch
-# OFF (36% precision measured),
-# TunableOp off. Shape E adds --expert-precise-memory (fitted 5.25 GiB overhead
-# instead of the 7.60 GiB default -> expert arena 17.22 GiB / 7,522 slots, +16%)
-# and GPU_MAX_HW_QUEUES=2; shape F pins the plan's CUDA-graph term to the
-# measured capture cost (VLLM_CUDAGRAPH_MEM_BASE_MB / _PER_GRAPH_MB, container
-# env — the analytic default charges 0.55 GiB where capture took 0.31 GiB, so
-# the 0.24 GiB difference goes to the arena) and raises util 0.98 -> 0.982,
-# Frank's cap. The native-262144 and fp8+MTP4 shapes are retired to
-# git tag frank-primary-fp8-mtp-20261001.
-#
-# THE COMPILE CACHE IS MOUNTED, and that is a boot-cost fix, not a tuning knob:
-# the image ships no /root/.cache at all, our first boot writes 1.1 GB of vLLM
-# AOT/torch_compile artifacts plus 229 MB of comgr JIT kernels into the
-# container's ephemeral layer, and `podman rm -f` deletes them — so every
-# deploy/restart/reboot re-pays `torch.compile took 181.20 s in total` (173.19 s
-# of it one graph). Mounting FRANK_PRIMARY_CACHE_DIR at /root/.cache makes all
-# later boots load the compiled artifact instead, and hides nothing. PROVEN
-# LIVE 2026-10-02 on consecutive boots of this shape: cold `torch.compile took
-# 188.26 s`, warm `Directly load the compiled graph(s) for compile range
-# (1, 1024) from the cache, took 2.143 s` / `torch.compile took 3.97 s in
-# total` / `init engine … took 41.13 s (compilation: 3.98 s)`.
+# serve-frank-primary.sh — frank-primary endpoint (FreeToken PR #587 ROCm
+# build, orcarouter Qwen3.8-Flash-Next-Uncensored-FP8, ONE R9700 gfx1201,
+# dankserver :7770; 2026-10-05 cutover from the tcclaviger vLLM fork — git
+# tag frank-primary-vllm-shapeG-20261003 is the pre-cutover state).
 #
+# The engine is driven by `podman run` DIRECTLY and the run line below IS
+# the engine argv: the image carries FreeToken installed at pinned PR head
+# 77a7201 (scripts/docker/frank-primary-freetoken.Dockerfile builds it from
+# the PR's own docs/install_amd.md stack). Unlike the vLLM fork there is no
+# per-boot planner: experts live in pinned host RAM with an LRU GPU cache,
+# KV is an explicit token pool, and the boot ledger in the log names
+# Shape: 1 GPU (first-boot conservative — the second R9700 sits idle;
+# --tensor-parallel-size EXISTS in FreeToken, so a 2-card TP shape is future
+# tuning once this single-card shape has a decode baseline), KV pool 300,000
+# tokens (24 KiB/token f16 across the 12 full-attention layers = 7.2 GiB;
+# clears the harness worst case of 177,356 tokens and admits one NATIVE
+# 262,144-token conversation), MoE LRU at 10% of all experts (~12 GiB),
+# 2 decode slots. First-boot conservative; `ft ctl cache --kv/--moe` grows
+# pools live, and the env comment block carries the resize law. Flag
+# surface verified against docs/cli.md of the pinned head AND against
+# `ft serve --help` inside the built image; every value here is env-driven
+# (frank-primary.env).
+
 # The root unit (scripts/frank-primary.service, User=dank,
-# LimitMEMLOCK=infinity) grants the pin budget for the tiered-expert host
-# slabs (~20.5 GiB/rank of pinned anonymous memory). A plain shell session
-# also works, but the unit is the fleet-parity boot-persistent shape.
+# LimitMEMLOCK=infinity) grants the pin budget: ~120 GiB of expert weights
+# plus the ~47.7 GiB PLE table pin in host RAM. A plain shell session also
+# works, but the unit is the fleet-parity boot-persistent shape.
 set -euo pipefail
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
@@ -67,27 +40,30 @@ set -a
 source "$ENV_FILE"
 set +a
 
-: "${FRANK_PRIMARY_IMAGE:?FRANK_PRIMARY_IMAGE must name the digest-pinned image}"
+: "${FRANK_PRIMARY_IMAGE:?FRANK_PRIMARY_IMAGE must name the FreeToken image}"
 : "${FRANK_PRIMARY_MODEL_DIR:?FRANK_PRIMARY_MODEL_DIR must name the FP8 payload}"
 : "${FRANK_PRIMARY_MODEL_SHARDS:?FRANK_PRIMARY_MODEL_SHARDS must give the shard count}"
 : "${FRANK_PRIMARY_CONTAINER:?FRANK_PRIMARY_CONTAINER must name the container}"
 : "${FRANK_PRIMARY_SERVED_NAME:?FRANK_PRIMARY_SERVED_NAME must name the alias}"
 : "${FRANK_PRIMARY_PUBLISH:?FRANK_PRIMARY_PUBLISH must be host:container}"
-: "${FRANK_PRIMARY_MAXLEN:?FRANK_PRIMARY_MAXLEN must be set}"
-: "${FRANK_PRIMARY_SEQS:?FRANK_PRIMARY_SEQS must be set}"
-: "${FRANK_PRIMARY_KV_BYTES:?FRANK_PRIMARY_KV_BYTES must be set (PER RANK)}"
-: "${FRANK_PRIMARY_KV_DTYPE:?FRANK_PRIMARY_KV_DTYPE must be set (auto = bf16 KV)}"
-: "${FRANK_PRIMARY_REASONING_PARSER:?FRANK_PRIMARY_REASONING_PARSER must be set (qwen3)}"
-: "${FRANK_PRIMARY_TOOL_PARSER:?FRANK_PRIMARY_TOOL_PARSER must be set (qwen3_xml)}"
-: "${FRANK_PRIMARY_CHAT_TEMPLATE_KWARGS:?FRANK_PRIMARY_CHAT_TEMPLATE_KWARGS must be set}"
-# Capture podman's output BEFORE grepping: under `set -o pipefail`, the
-# classic `podman images | grep -q` pattern races — grep exits on its first
-# match, podman dies SIGPIPE (141) writing the remaining lines, and pipefail
-# turns the 141 into "no match" (the 2026-09-30 deploy refusal).
-DIGESTS="$(podman images --format '{{.RepoDigests}}')"
-if ! grep -qF "${FRANK_PRIMARY_IMAGE#*@}" <<<"$DIGESTS"; then
-    echo "serve-frank-primary: pinned image absent from rootless storage: $FRANK_PRIMARY_IMAGE" >&2
-    echo "  fetch it: podman pull $FRANK_PRIMARY_IMAGE" >&2
+: "${FRANK_PRIMARY_FT_GPU:?FRANK_PRIMARY_FT_GPU must name the GPU index}"
+: "${FRANK_PRIMARY_FT_NUM_TOKENS:?FRANK_PRIMARY_FT_NUM_TOKENS must size the KV pool}"
+: "${FRANK_PRIMARY_FT_MAX_RUNNING:?FRANK_PRIMARY_FT_MAX_RUNNING must be set}"
+: "${FRANK_PRIMARY_FT_MAX_OUTPUT_TOKENS:?FRANK_PRIMARY_FT_MAX_OUTPUT_TOKENS must be set}"
+: "${FRANK_PRIMARY_FT_MOE_RATE:?FRANK_PRIMARY_FT_MOE_RATE must be set}"
+
+# The image gate is EXISTENCE IN STORAGE, not a registry digest: the tag is
+# built ON THE HOST (podman build from
+# scripts/docker/frank-primary-freetoken.Dockerfile) and local builds carry
+# no RepoDigests entry — the 362-line vLLM-era RepoDigests grep refused
+# exactly this shape. Pinning lives in the Dockerfile instead: the FreeToken
+# source is checked out at a hardcoded PR-head SHA and the base image is
+# digest-pinned there. `podman image exists` accepts both a local tag and a
+# name@digest ref, and it is one command — no pipefail/grep race (the
+# 2026-09-30 lesson) for either shape.
+if ! podman image exists "$FRANK_PRIMARY_IMAGE"; then
+    echo "serve-frank-primary: image absent from rootless storage: $FRANK_PRIMARY_IMAGE" >&2
+    echo "  build it: podman build -t $FRANK_PRIMARY_IMAGE -f scripts/docker/frank-primary-freetoken.Dockerfile scripts/docker/" >&2
     exit 1
 fi
 
@@ -114,8 +90,8 @@ fi
 
 # A crashed/killed unit can leave the container name registered (systemd
 # SIGKILLs conmon before cleanup runs). Clear OUR name plus the legacy
-# identities (the retired R9V container and the ad hoc experiment container
-# both hold these GPUs); all idempotent.
+# identities (the vLLM-era frank-primary-qwen, the retired R9V container and
+# the ad hoc experiment containers all hold this GPU); all idempotent.
 for CTR in $FRANK_PRIMARY_LEGACY_CONTAINERS "$FRANK_PRIMARY_CONTAINER"; do
     podman rm -f "$CTR" >/dev/null 2>&1 || true
 done
@@ -123,74 +99,34 @@ done
 LOG=/home/dank/logs/frank_primary.log
 mkdir -p "$(dirname "$LOG")"
 
-# Persistent compile cache (see the header). Create it before the mount so even
-# the first, cold boot has a target; unset -> no mount, exactly the old
-# ephemeral behaviour. It carries /root/.cache/vllm (AOT + torch_compile) and
-# /root/.cache/comgr (HIP kernel JIT).
-CACHE_DIR="${FRANK_PRIMARY_CACHE_DIR:-}"
-if [ -n "$CACHE_DIR" ]; then
-    mkdir -p "$CACHE_DIR"
-fi
-
 # --device /dev/dri is the WHOLE DIRECTORY (individual renderD nodes enumerate
-# without the card nodes and HIP refuses contexts — "No CUDA GPUs are
-# available" while device_count() says 2). --ipc=host for the engine's shared
-# memory; memlock unbounded for the pinned host slabs.
-# The entrypoint already execs `vllm serve "$@"`, so no `serve` here.
-# Prefix caching: ON — the shipped contract. FRANK_PRIMARY_NO_PREFIX_-
-# CACHING=1 flips to the fork-named mitigation (--no-enable-prefix-caching)
-# for the QFN align-mode GDN state fault; it was tried 2026-10-05 and
-# REVERTED the same day (live conversations still degraded at ~40k with
-# caching off and zero faults — see the evidence block in
-# frank-primary.env). NO comment lines inside the backslash chain below —
-# a comment there terminates the continuation and the next line runs as
-# its own command (the 2026-10-05 exit-127 crash loop).
-# The ${VAR:-word} / ${VAR:+word} double-expansion for the two directions is
-# AMBIGUOUS bash (${VAR:--flag} parses as a substring offset when set —
-# measured 2026-10-05: rendered "--no-enable-prefix-caching1"), so the flag
-# is branched explicitly: exactly one of the two reaches the engine.
-if [ -n "${FRANK_PRIMARY_NO_PREFIX_CACHING:-}" ]; then
-    FRANK_PRIMARY_PREFIX_CACHE_FLAG=--no-enable-prefix-caching
-else
-    FRANK_PRIMARY_PREFIX_CACHE_FLAG=--enable-prefix-caching
-fi
+# without the card nodes and HIP refuses contexts). --ipc=host for the
+# engine's shared memory; memlock unbounded for the ~120 GiB pinned expert
+# rows + the 47.7 GiB PLE pin (the unit's LimitMEMLOCK=infinity is the other
+# half of that law).
+# HIP_VISIBLE_DEVICES pins visibility to ONE card so in-container index 0 is
+# the right R9700; --gpu 0 selects it inside the visible set.
 podman run -d --name "$FRANK_PRIMARY_CONTAINER" \
   --publish "$FRANK_PRIMARY_PUBLISH" \
   --ipc=host --ulimit memlock=-1:-1 \
   --cap-add SYS_PTRACE \
   --device /dev/kfd --device /dev/dri --device /dev/mem \
-  -e HIP_VISIBLE_DEVICES=0,1 -e VLLM_ROCM_USE_AITER=0 \
-  ${FRANK_PRIMARY_GPU_MAX_HW_QUEUES:+-e GPU_MAX_HW_QUEUES="$FRANK_PRIMARY_GPU_MAX_HW_QUEUES"} \
-  ${FRANK_PRIMARY_GATHER_CHUNKS:+-e R4D_LRU_GATHER_CHUNKS="$FRANK_PRIMARY_GATHER_CHUNKS"} \
-  ${FRANK_PRIMARY_GATHER_LANES:+-e R4D_LRU_GATHER_LANES="$FRANK_PRIMARY_GATHER_LANES"} \
-  ${FRANK_PRIMARY_CUDAGRAPH_BASE_MB:+-e VLLM_CUDAGRAPH_MEM_BASE_MB="$FRANK_PRIMARY_CUDAGRAPH_BASE_MB"} \
-  ${FRANK_PRIMARY_CUDAGRAPH_PER_GRAPH_MB:+-e VLLM_CUDAGRAPH_MEM_PER_GRAPH_MB="$FRANK_PRIMARY_CUDAGRAPH_PER_GRAPH_MB"} \
-  ${CACHE_DIR:+-v "$CACHE_DIR":/root/.cache} \
+  -e HIP_VISIBLE_DEVICES="$FRANK_PRIMARY_FT_GPU" \
   -v "$FRANK_PRIMARY_MODEL_DIR":/models:ro \
-  "$FRANK_PRIMARY_IMAGE" /models \
-  --served-model-name "$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"} \
-  ${FRANK_PRIMARY_PRECISE_MEMORY:+--expert-precise-memory} \
-  ${FRANK_PRIMARY_EXPERT_OFFLOAD_MEM:+--expert-offload-mem "$FRANK_PRIMARY_EXPERT_OFFLOAD_MEM"} \
-  --gpu-memory-utilization "$FRANK_PRIMARY_UTIL" \
-  --kv-cache-memory-bytes "$FRANK_PRIMARY_KV_BYTES" \
-  --kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE" \
-  "$FRANK_PRIMARY_PREFIX_CACHE_FLAG" \
-  --enable-auto-tool-choice --tool-call-parser "$FRANK_PRIMARY_TOOL_PARSER" \
-  --reasoning-parser "$FRANK_PRIMARY_REASONING_PARSER" \
-  --default-chat-template-kwargs "$FRANK_PRIMARY_CHAT_TEMPLATE_KWARGS" \
-  ${FRANK_PRIMARY_SPEC:+--speculative-config "$FRANK_PRIMARY_SPEC"} \
-  ${FRANK_PRIMARY_COMPCONFIG:+--compilation-config "$FRANK_PRIMARY_COMPCONFIG"} \
-  ${FRANK_PRIMARY_GEN_CONFIG:+--override-generation-config "$FRANK_PRIMARY_GEN_CONFIG"} \
-  --trust-remote-code \
+  "$FRANK_PRIMARY_IMAGE" \
+  ft serve --model /models \
+    --served-model-name "$FRANK_PRIMARY_SERVED_NAME" \
+    --host 0.0.0.0 --port 7770 \
+    --gpu "$FRANK_PRIMARY_FT_GPU" \
+    --num-tokens "$FRANK_PRIMARY_FT_NUM_TOKENS" \
+    --max-running-requests "$FRANK_PRIMARY_FT_MAX_RUNNING" \
+    --max-output-tokens "$FRANK_PRIMARY_FT_MAX_OUTPUT_TOKENS" \
+    --moe-cache-rate "$FRANK_PRIMARY_FT_MOE_RATE" \
+    ${FRANK_PRIMARY_FT_EXTRA_ARGS:+$FRANK_PRIMARY_FT_EXTRA_ARGS} \
   > "$LOG" 2>&1
 
 # From here on, this script's lifetime IS the container's: wait returns the
 # container's exit code, so a crash is a nonzero ExecStart and the unit's
-# Restart=on-failure is real. (systemd stop goes through ExecStop in the
-# unit — podman wait alone cannot stop the container child.)
+# Restart=always is real. (systemd stop goes through ExecStop in the unit —
+# podman wait alone cannot stop the container child.)
 exec podman wait "$FRANK_PRIMARY_CONTAINER"

tests/frank_primary_unit.bats

@@ -1,26 +1,25 @@
 #!/usr/bin/env bats
 # Seam: frank-primary — the Dankserver LLM endpoint on :7770.
 #
-# This file asserts the tcclaviger RDNA4 vLLM ROOT-UNIT shape (the
-# 2026-10-01 BF16 cutover, the overnight redo campaign's verdict): the serve
-# script drives `podman run` DIRECTLY (the image entrypoint execs
-# `vllm serve`), with every engine flag qualified by boot probe and carried
-# in the repo env file. The seam pins what the flags alone do not say: the
-# KV qualification law (the night ladder: 262144/245760 OOM at graph
-# capture; 241664 boots at 732,359 tokens / 3.03x, util 0.98;
-# the bf16-KV trade (double the attention-KV bytes/token, ~14% decode cost,
-# clean cache + 262k windows), the automatic-offload law (the fork plans
-# the tiered-expert offload itself; no flag exists to set), the self-healing
-# law (the run returns before the engine is up, so the serve script must
-# wait on the container for Restart=on-failure to mean anything), the
-# memlock law that makes the pinned host rows legal, the deployer's
-# image/payload gates with the false-green MainPID check, and the measured
-# laws: expert prefetch ABSENT (36% precision), NO speculative decode (the
-# no-spec family measured fastest once the prefetch tax was removed; MTP
-# re-measures pending), gather geometry 32x64 PRESENT (+18.7% decode),
-# MNBT 2048, the CUDA-graph plan term pinned to the measured capture cost, and
-# the client contract (reasoning parser qwen3,
-# tool parser qwen3_xml, preserve_thinking on).
+# This file asserts the FreeToken (PR #587 ROCm) ROOT-UNIT shape (the
+# 2026-10-05 cutover from the tcclaviger RDNA4 vLLM fork, git tag
+# frank-primary-vllm-shapeG-20261003): the serve script drives `podman run`
+# DIRECTLY (the image carries `ft serve`, built on the host from
+# scripts/docker/frank-primary-freetoken.Dockerfile), one R9700, with every
+# engine value carried in the repo env file. The seam pins what flags alone
+# do not say: the KV-pool math (300k tokens at 24 KiB/token clears the
+# harness worst case of 177,356), the deployed single-GPU shape
+# (--tensor-parallel-size EXISTS in FreeToken — a 2-card TP shape is future
+# tuning; HIP_VISIBLE_DEVICES pins THIS shape to one card), the host-RAM
+# law (experts + PLE pin ~170 GiB — the memlock law that makes the pin
+# legal), the self-healing law (the run returns before the engine is up, so
+# the serve script must wait on the container for Restart=always to mean
+# anything), the image-existence gate (a local build carries no
+# RepoDigests — the old digest grep refused exactly this shape; pinning
+# lives in the Dockerfile), the deployer's payload gates with the
+# false-green MainPID check, and the client contract (parsers AUTO:
+# reasoning_content emission is the engine's native behavior — models.yml
+# maps reasoningContentField on the harness side, not here).
 
 load helpers
 
@@ -29,29 +28,30 @@ SERVE="$REPO_ROOT/scripts/serve-frank-primary.sh"
 ENV_FILE="$REPO_ROOT/scripts/frank-primary.env"
 REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
 DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"
+DOCKERFILE="$REPO_ROOT/scripts/docker/frank-primary-freetoken.Dockerfile"
 
-@test "frank-primary unit, serve script and env exist in scripts/" {
+@test "frank-primary unit, serve script, env and Dockerfile exist" {
     [ -f "$UNIT" ]
     [ -x "$SERVE" ]
     [ -f "$ENV_FILE" ]
+    [ -f "$DOCKERFILE" ]
 }
 
-@test "frank-primary is boot-persistent, self-healing and unprivileged" {
+@test "frank-primary unit is boot-persistent, self-healing and unprivileged" {
     # Root unit parity with frank-large/frank-small: enable is the [Install]
-    # section, the restart policy survives a crash, and the tiered-expert
-    # pin needs an unbounded memlock (a root unit grants it via PID1; the
-    # dank session's own hard limit is 8 MiB and cannot be raised without
-    # restarting user@1000.service).
+    # section, the restart policy survives a crash, and the pinned host RAM
+    # (expert rows + PLE table) needs an unbounded memlock (a root unit
+    # grants it via PID1; the dank session's own hard limit is 8 MiB).
     grep -q '^WantedBy=multi-user.target$' "$UNIT"
-    # Restart=always, not on-failure: a runtime worker OOM makes vLLM's API
-    # server exit CLEAN, so ExecStart returns 0 and on-failure never fires
-    # (measured 2026-10-01 — the endpoint stayed down until a human noticed).
+    # Restart=always, not on-failure: the vLLM-era lesson carries over — a
+    # clean front-end exit after a worker fault reads as success to systemd,
+    # so on-failure never fires.
     grep -q '^Restart=always$' "$UNIT"
     ! grep -q '^Restart=on-failure$' "$UNIT"
-    # Exiting the engine takes as long as vLLM's drain: ExecStop runs
-    # `podman stop -t 120`, so the stop timeout MUST exceed 120 s or systemd
-    # kills the stop and records 'Failed with result timeout' (measured
-    # 2026-10-01). Guard the relationship, not just the literal.
+    # ExecStop runs `podman stop -t 120`, so the stop timeout MUST exceed
+    # 120 s or systemd kills the stop and records 'Failed with result
+    # timeout' (measured 2026-10-01). Guard the relationship, not the
+    # literal.
     stop_t=$(awk -F= '/^TimeoutStopSec=/{print $2}' "$UNIT")
     [ -n "$stop_t" ] && [ "$stop_t" -gt 120 ]
     grep -q '^ExecStop=.*podman stop -t 120' "$UNIT"
@@ -69,320 +69,117 @@ DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"
     grep -q 'FRANK_PRIMARY_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-primary.env' "$UNIT"
 }
 
-@test "the unit stops the container child explicitly" {
+@test "the unit stops the container child explicitly — container identity is the unit name" {
     # The serve script blocks on podman wait, which cannot stop the
     # container child; systemd stop goes through ExecStop or the engine
-    # outlives the unit and holds both GPUs. The container name must match
-    # the env file's identity.
+    # outlives the unit and holds the GPU. Frank's 2026-10-05 call: the
+    # container name IS the service name (frank-primary), and the vLLM-era
+    # name frank-primary-qwen moved into the legacy cleanup list.
     grep -q '^ExecStop=/usr/bin/podman stop' "$UNIT"
-    grep -q 'frank-primary-qwen' "$UNIT"
-    grep -q '^FRANK_PRIMARY_CONTAINER=frank-primary-qwen$' "$ENV_FILE"
+    grep -q 'podman stop -t 120 frank-primary$' "$UNIT"
+    grep -q '^FRANK_PRIMARY_CONTAINER=frank-primary$' "$ENV_FILE"
+    grep -q 'frank-primary-qwen' "$ENV_FILE"
 }
 
-@test "the serve shape is direct podman run, not a launcher or shim" {
-    # The tcclaviger stack is fully expressed by flags; the R9V launcher,
-    # docker->podman shim and setup-state layering are the RETIRED shape.
+@test "the serve shape is direct podman run, not a launcher, shim, or the vLLM fork" {
     grep -q 'podman run' "$SERVE"
     ! grep -q 'launch.sh' "$SERVE"
     ! grep -q 'podman-shim' "$SERVE"
     ! grep -q 'R9V_STATE_FILE' "$SERVE"
-    ! grep -q -- '--model-draft' "$SERVE"
-    ! grep -q -- '--spec-type' "$SERVE"
+    # The tcclaviger vLLM fork is RETIRED — its image name and its
+    # fork-specific flags must not survive in the FreeToken run line
+    # (TP=2 is gone with the fork; FreeToken serves ONE GPU).
+    ! grep -q 'tcclaviger' "$SERVE"
+    ! grep -q 'tcclaviger' "$ENV_FILE"
+    ! grep -q -- '--tensor-parallel-size' "$SERVE"
+    ! grep -q -- '--kv-cache-dtype' "$SERVE"
+    ! grep -q -- '--max-num-seqs' "$SERVE"
 }
 
-@test "the qualified engine shape is in the env file" {
-    # 2026-10-02 shape D. History: the 2026-10-01 night ladder put SEQS=3
-    # bf16 at 241664 (KV 732,359 / 3.03x); SEQS=6 fp8 does NOT fit (6 x
-    # 241664 asked 10.70 GiB against 9.18 GiB free); SEQS=5 fp8 x 262144
-    # BOOTED (1,350,182 / 5.15x) but left ~0 bytes free and a real 995-token
-    # request killed the worker with `Tried to allocate 50.00 MiB ... 0 bytes
-    # free`. UTIL is a REAL arena lever (the fork plans budget = total x util)
-    # but a weak one, and Frank caps it at 0.982 — never 1.00 (see
-    # FRANK_PRIMARY_UTIL for the two ceiling deaths that justify the margin).
-    # SEQS=2 is IMPOSSIBLE on this model, measured 2026-10-02 by
-    # single-variable boot probe against the then-deployed shape: SEQS 2 fails
-    # at BOTH MNBT 1024 and 2048 with torch.fx ConstraintViolationError
-    # (query_start_loc.size()[0] marked dynamic but specialized to a constant
-    # (3)); SEQS 3 passes at both. model_runner sizes that buffer
-    # max_num_reqs + 1, so the width is SEQS + 1 and MNBT only moves the
-    # compile RANGE.
-    # So the shape is 3 slots with a pool that admits only ~2 full-length
-    # conversations: measured live, KV_BYTES 3.15e9/rank reports 398,658
-    # tokens = 1.99x for a 200704-token request (7,892 B/token at THIS shape;
-    # the per-token price is shape-dependent, 7,701 at 262144). Shorter
-    # requests use the spare blocks; a third LONG request queues.
-    # The arena is sized by max_model_len, NOT by KV_BYTES: the planner
-    # reserves registry 9190 B/token x max_model_len (2.48 GiB at 262144 ->
-    # arena 6,248 slots; 1.91 GiB at 200704 -> 6,496). The pool cut buys
-    # runtime headroom, not arena.
-    grep -q '^FRANK_PRIMARY_MAXLEN=200704$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_SEQS=3$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_UTIL=0.982$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_KV_BYTES=3166500000$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_MNBT=2048$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_KV_DTYPE=fp8$' "$ENV_FILE"
-    # --expert-precise-memory IS set (shape E, 2026-10-02). It was refused
-    # while the 2 x 262144 bf16 boot sat 0.13 GiB under the 31.86 GiB ceiling
-    # (arena 16.65 device-resident, NRestarts=3 at ~6.7 min each) — there it was
-    # the last 2.35 GiB over the line, not the cause. Probed on the shape-D base
-    # with production stopped: boots healthy in 420 s, plan reports runtime
-    # overhead 5.25 GiB (not 7.60), expert cache 17.22 GiB / 7,522 slots
-    # (+1,026 / +16% over 6,496). The pool is NOT cut with it (option A): the
-    # pool is not an arena lever, so 3.15e9 keeps the measured 1.99x.
-    grep -q '^FRANK_PRIMARY_PRECISE_MEMORY=1$' "$ENV_FILE"
-    # GPU_MAX_HW_QUEUES caps HSA hw queues per GPU; real knob (the literal is in
-    # libhsa-runtime64.so), passed inside the container as a bare name — the env
-    # file keeps only the prefixed form.
-    grep -q '^FRANK_PRIMARY_GPU_MAX_HW_QUEUES=2$' "$ENV_FILE"
-    # The compile cache is a BOOT-COST fix: the image ships no /root/.cache at
-    # all, our boot writes 1.1 GB of vLLM AOT artifacts (4,665 files) plus
-    # 229 MB of comgr JIT kernels into the ephemeral layer, and every
-    # `podman rm -f` throws them away — re-paying `torch.compile took 181.20 s`
-    # (173.19 s of it one graph) on every deploy, restart and reboot.
-    grep -q '^FRANK_PRIMARY_CACHE_DIR=/home/dank/.cache/frank-primary$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_GATHER_CHUNKS=32$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_GATHER_LANES=64$' "$ENV_FILE"
-    # Prefix caching is ON (reverted 2026-10-05 the same day it was
-    # disabled): the fork's QFN align-mode GDN state fault (48 gdn_hip
-    # state faults, slot 42 heads 3/8, at the 13th 3136-token boundary =
-    # 40,768 — the "~40k corruption" report) was mitigated with
-    # --no-enable-prefix-caching, but live long conversations STILL
-    # degraded at ~40k with caching off and zero faults logged — cost
-    # with no fix, so the historical flag returned. The knob stays
-    # commented in the env file for a future fixed fork build; flip it to
-    # 1 only together with a re-verification past 40,768 tokens.
-    grep -qE '^# FRANK_PRIMARY_NO_PREFIX_CACHING=1$' "$ENV_FILE"
+@test "the FreeToken engine shape is in the env file" {
+    # KV pool: TOKENS, not bytes. 24 KiB/token (12 full-attention layers x
+    # 2 KV heads x 256 head_dim x K+V x f16) — the 36 GDN layers use fixed
+    # per-seq state, not per-token KV. 300,000 tokens = 7.2 GiB and clears
+    # the harness worst case (140,492-token prompt + 36,864 max_tokens =
+    # 177,356); one NATIVE 262,144-token conversation + full budget also
+    # fits. The arithmetic guard keeps future resizes honest.
+    grep -q '^FRANK_PRIMARY_FT_NUM_TOKENS=300000$' "$ENV_FILE"
+    nt=$(awk -F= '/^FRANK_PRIMARY_FT_NUM_TOKENS=/{print $2}' "$ENV_FILE")
+    [ "$nt" -ge 177356 ]
+    # First-boot conservative shape: 2 decode slots, 10% expert LRU
+    # (~12 GiB of the ~120 GiB fp8 expert set), output ceiling = the
+    # harness maxTokens, single R9700 at index 0.
+    grep -q '^FRANK_PRIMARY_FT_MAX_RUNNING=2$' "$ENV_FILE"
+    grep -q '^FRANK_PRIMARY_FT_MOE_RATE=0.10$' "$ENV_FILE"
+    grep -q '^FRANK_PRIMARY_FT_MAX_OUTPUT_TOKENS=36864$' "$ENV_FILE"
+    grep -q '^FRANK_PRIMARY_FT_GPU=0$' "$ENV_FILE"
     grep -q '^FRANK_PRIMARY_MODEL_SHARDS=131$' "$ENV_FILE"
 }
 
 @test "the serve script wires the engine flags from the env" {
-    grep -q -- '--max-num-seqs "$FRANK_PRIMARY_SEQS"' "$SERVE"
-    grep -q -- '--max-model-len "$FRANK_PRIMARY_MAXLEN"' "$SERVE"
-    grep -q -- '--kv-cache-memory-bytes "$FRANK_PRIMARY_KV_BYTES"' "$SERVE"
-    grep -q -- '--kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE"' "$SERVE"
-    grep -q -- '--max-num-batched-tokens "$FRANK_PRIMARY_MNBT"' "$SERVE"
-    grep -q -- '-e R4D_LRU_GATHER_CHUNKS="$FRANK_PRIMARY_GATHER_CHUNKS"' "$SERVE"
-    grep -q -- '-e R4D_LRU_GATHER_LANES="$FRANK_PRIMARY_GATHER_LANES"' "$SERVE"
-    # Speculative decode, the cudagraph capture ladder and the sampling
-    # defaults are all ENV-DRIVEN knobs (unset -> the flag is absent, which is
-    # the shipped shape today). JSON values carry no shell-special characters
-    # that this quoting cannot carry.
-    grep -q -- '${FRANK_PRIMARY_SPEC:+--speculative-config "$FRANK_PRIMARY_SPEC"}' "$SERVE"
-    grep -q -- '${FRANK_PRIMARY_COMPCONFIG:+--compilation-config "$FRANK_PRIMARY_COMPCONFIG"}' "$SERVE"
-    grep -q -- '${FRANK_PRIMARY_GEN_CONFIG:+--override-generation-config "$FRANK_PRIMARY_GEN_CONFIG"}' "$SERVE"
-    grep -q -- '--tensor-parallel-size 2' "$SERVE"
-    # Prefix caching renders exactly ONE flag from the knob, branched
-    # explicitly in the serve script (the ${VAR:--flag} double-expansion is
-    # ambiguous bash — when set it parsed as a substring offset, measured
-    # 2026-10-05): set -> --no-enable-prefix-caching (the fork-named
-    # mitigation, tried and REVERTED the same day — live corruption
-    # persisted at ~40k with zero faults), unset -> the shipped
-    # --enable-prefix-caching. Both directions are spelled out so a fork
-    # default change cannot silently flip the contract.
-    grep -qF 'FRANK_PRIMARY_PREFIX_CACHE_FLAG=--no-enable-prefix-caching' "$SERVE"
-    grep -qF 'FRANK_PRIMARY_PREFIX_CACHE_FLAG=--enable-prefix-caching' "$SERVE"
-    grep -qF '"$FRANK_PRIMARY_PREFIX_CACHE_FLAG"' "$SERVE"
-    # The observable contract: the exact flag word the engine receives,
-    # rendered from the shipped env through the serve script's branch (the
-    # same render-assert pattern the spec knobs use above).
-    run bash -c '
-        set -a; . "$1" >/dev/null; set +a
-        if [ -n "${FRANK_PRIMARY_NO_PREFIX_CACHING:-}" ]; then
-            FRANK_PRIMARY_PREFIX_CACHE_FLAG=--no-enable-prefix-caching
-        else
-            FRANK_PRIMARY_PREFIX_CACHE_FLAG=--enable-prefix-caching
-        fi
-        printf %s "$FRANK_PRIMARY_PREFIX_CACHE_FLAG"' _ "$ENV_FILE"
-    [ "$output" = "--enable-prefix-caching" ]
-    grep -q -- '--trust-remote-code' "$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=' "$ENV_FILE"
-    # --expert-precise-memory selects the fitted overhead (5.25 GiB) over the
-    # default (7.60 GiB = fitted + compile/graph-capture headroom), which only
-    # moves the plan's `room` term and therefore the expert arena: ~1,025
-    # more slots at 2.344 MiB each.
-    grep -q -- '${FRANK_PRIMARY_PRECISE_MEMORY:+--expert-precise-memory}' "$SERVE"
-    # Shape E host/CPU wiring: the cache dir is created before it is mounted
-    # (a cold boot must have a target) and the mount lands on /root/.cache,
-    # whose vllm/ child is the path VLLM_CACHE_ROOT defaults to — the engine log
-    # names it as `Using cache directory: /root/.cache/vllm/torch_compile_cache/…`.
-    grep -q -- 'mkdir -p "$CACHE_DIR"' "$SERVE"
-    grep -q -- '${CACHE_DIR:+-v "$CACHE_DIR":/root/.cache}' "$SERVE"
-    grep -q -- '-e GPU_MAX_HW_QUEUES="$FRANK_PRIMARY_GPU_MAX_HW_QUEUES"' "$SERVE"
-    # Shape F/G: the CUDA-graph plan term is carried as CONTAINER env (the fork
-    # reads it at call time inside estimate_cudagraph_memory), and both must be
-    # present — the graph term and UTIL are the ONLY plan terms this repo can
-    # move, and shrinking them is what grows the arena. The base must be shipped
-    # explicitly: unset, the estimator would fall back to its 256 MiB default.
-    grep -q -- '-e VLLM_CUDAGRAPH_MEM_BASE_MB="$FRANK_PRIMARY_CUDAGRAPH_BASE_MB"' "$SERVE"
-    grep -q -- '-e VLLM_CUDAGRAPH_MEM_PER_GRAPH_MB="$FRANK_PRIMARY_CUDAGRAPH_PER_GRAPH_MB"' "$SERVE"
-    grep -q '^FRANK_PRIMARY_CUDAGRAPH_BASE_MB=0$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_CUDAGRAPH_PER_GRAPH_MB=12$' "$ENV_FILE"
-    # The host region is the ONE plan term that autofits per-boot: with no cap
-    # the bound is MemAvailable at that moment (boot 2026-10-05: 237.97 GiB ->
-    # 159.39 GiB usable, while the running host later reads 75.4 GiB available).
-    # An explicit --expert-offload-mem cap makes the plan deterministic whatever
-    # the co-tenant RAM state is at boot; 120 GiB covers the measured 105.48
-    # GiB of swappable experts (52.74/rank x 2) with 14% headroom.
-    grep -q -- '${FRANK_PRIMARY_EXPERT_OFFLOAD_MEM:+--expert-offload-mem "$FRANK_PRIMARY_EXPERT_OFFLOAD_MEM"}' "$SERVE"
-    grep -q '^FRANK_PRIMARY_EXPERT_OFFLOAD_MEM=120$' "$ENV_FILE"
+    grep -q 'ft serve --model /models' "$SERVE"
+    grep -q -- '--served-model-name "$FRANK_PRIMARY_SERVED_NAME"' "$SERVE"
+    grep -q -- '--host 0.0.0.0 --port 7770' "$SERVE"
+    grep -q -- '--gpu "$FRANK_PRIMARY_FT_GPU"' "$SERVE"
+    grep -q -- '--num-tokens "$FRANK_PRIMARY_FT_NUM_TOKENS"' "$SERVE"
+    grep -q -- '--max-running-requests "$FRANK_PRIMARY_FT_MAX_RUNNING"' "$SERVE"
+    grep -q -- '--max-output-tokens "$FRANK_PRIMARY_FT_MAX_OUTPUT_TOKENS"' "$SERVE"
+    grep -q -- '--moe-cache-rate "$FRANK_PRIMARY_FT_MOE_RATE"' "$SERVE"
+    # Single-GPU law: visibility is pinned to one card so in-container
+    # index 0 is the right R9700 (mirrors the env's FT_GPU).
+    grep -q -- '-e HIP_VISIBLE_DEVICES="$FRANK_PRIMARY_FT_GPU"' "$SERVE"
+    # The boot-ladder escape hatch is opt-in: unset renders NO extra argv.
+    grep -q -- '${FRANK_PRIMARY_FT_EXTRA_ARGS:+$FRANK_PRIMARY_FT_EXTRA_ARGS}' "$SERVE"
+    ! grep -q '^FRANK_PRIMARY_FT_EXTRA_ARGS=.' "$ENV_FILE"
 }
 
-@test "tools and reasoning are wired — the client contract is served" {
-    # 2026-10-01: the rollback-era trio served NO tool dialect and left
-    # thinking inline in `content` with a dangling `</think>` and a null
-    # `reasoning` field (measured: content 'We need answer...Brief.\n</think>
-    # \n\n391') — the malformed thinking block clients choke on. The working
-    # values are the ones ecaad36 shipped for this model and this fork's
-    # registries confirm: reasoning parser `qwen3`, tool parser `qwen3_xml`.
-    # preserve_thinking keeps prior thinking blocks across turns.
-    grep -q '^FRANK_PRIMARY_REASONING_PARSER=qwen3$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_TOOL_PARSER=qwen3_xml$' "$ENV_FILE"
-    grep -q -- '--reasoning-parser "$FRANK_PRIMARY_REASONING_PARSER"' "$SERVE"
-    grep -q -- '--enable-auto-tool-choice' "$SERVE"
-    grep -q -- '--tool-call-parser "$FRANK_PRIMARY_TOOL_PARSER"' "$SERVE"
-    grep -q -- '--default-chat-template-kwargs "$FRANK_PRIMARY_CHAT_TEMPLATE_KWARGS"' "$SERVE"
-    grep -q 'preserve_thinking' "$ENV_FILE"
-    grep -q 'enable_thinking' "$ENV_FILE"
+@test "parsers are AUTO — the engine infers them natively, the harness maps the field" {
+    # FreeToken infers the qwen3.8 reasoning/tool dialects from the model
+    # family and emits thinking in `reasoning_content` natively — NO
+    # --reasoning-parser/--tool-call-parser override flags. The vLLM-era
+    # client-contract wiring (qwen3 parser, qwen3_xml tool parser,
+    # default-chat-template-kwargs) is gone; models.yml's
+    # reasoningContentField flip is the harness-side contract and lives in
+    # the operator's home, not this repo.
+    ! grep -q -- '--reasoning-parser' "$SERVE"
+    ! grep -q -- '--tool-call-parser' "$SERVE"
+    ! grep -q -- '--enable-auto-tool-choice' "$SERVE"
+    ! grep -q -- '--default-chat-template-kwargs' "$SERVE"
+    ! grep -q 'FRANK_PRIMARY_REASONING_PARSER' "$ENV_FILE"
+    ! grep -q 'FRANK_PRIMARY_TOOL_PARSER' "$ENV_FILE"
 }
 
-@test "expert offload is AUTOMATIC — the payload cannot fit VRAM and no flag sets it" {
-    # ~86 GiB/rank of FP8 trunk against 32 GiB of VRAM: the fork's tiered-
-    # expert planner moves the overflow to pinned host rows by itself (the
-    # arena 6,574 slots x 2.344 MiB plus host rows). There is no
-    # --enable-expert-offload flag in this arm; the legality of the pin is
-    # the unit's unbounded LimitMEMLOCK.
-    ! grep -q -- '--enable-expert-offload' "$SERVE"
-    grep -q '^LimitMEMLOCK=infinity$' "$UNIT"
-    grep -q -- '--ipc=host --ulimit memlock=-1:-1' "$SERVE"
-}
-
-@test "speculative decode is an ENV KNOB — the old retirement verdict was invalid" {
-    # The 2026-10-02 c1248d4 retirement of MTP compared the WRONG PAIR:
-    # fp8+MTP4 (37.4-40.6 tok/s, 54% acceptance) against the bf16 no-spec boot
-    # (36.4-39.4), then bf16 proved unbootable and fp8 came back WITHOUT MTP —
-    # so fp8+spec was never compared against fp8+no-spec on the same shape. The
-    # no-spec incumbent runs ~30 tok/s, under the fleet's 35 tok/s target, while
-    # EVERY vendor flash-next recipe ships MTP3, and our MTP4 run used the
-    # default GREEDY draft sampling (probabilistic is the other fork option and
-    # is what the recipes use under temp>0). So spec is a knob, not a law: the
-    # shipped value is whatever a matched-pair re-measurement wins.
-    grep -q 'THE RETIREMENT VERDICT WAS INVALID' "$ENV_FILE"
-    # The knobs are empty in the shipped env, so the `${VAR:+…}` wiring renders
-    # NO spec/compilation flag — asserted by rendering, not by grepping the
-    # assignment (shape E today has neither flag in its argv).
-    run bash -c 'set -a; . "$1" >/dev/null; set +a
-        printf %s "${FRANK_PRIMARY_SPEC:+--speculative-config $FRANK_PRIMARY_SPEC}${FRANK_PRIMARY_COMPCONFIG:+--compilation-config $FRANK_PRIMARY_COMPCONFIG}"' _ "$ENV_FILE"
-    [ -z "$output" ]
-    # The capture-ladder law: the piecewise graph ladder must contain
-    # num_speculative_tokens + 1, so an MTP3 shape captures [4, 8, 12] and the
-    # 2026-10-02 SEQS=2 failure (query_start_loc specialized to the constant 3)
-    # is why SEQS stays a multiple-compatible value.
-    grep -q 'num_speculative_tokens + 1' "$ENV_FILE"
-}
-
-@test "KV dtype is fp8 — the incumbent, and the only one that boots" {
-    # fp8 costs ~7,701 B/token at 262144 (7,892 at 200704 — shape-dependent),
-    # decomposed as 6,138 attention + 1,563 mamba/side (dtype-independent);
-    # bf16 costs 13,839 (12,276 + 1,563).
-    # bf16 was abandoned 2026-10-01: its 2 x 262144 boot died with 0 bytes
-    # free on a real request, and the SEQS=2 slot count it was designed
-    # around cannot compile this model at all (see the shape test above).
-    grep -q '^FRANK_PRIMARY_KV_DTYPE=fp8$' "$ENV_FILE"
-    grep -q -- '--kv-cache-dtype "$FRANK_PRIMARY_KV_DTYPE"' "$SERVE"
-}
-
-@test "gather geometry 32x64 is PRESENT BY MEASUREMENT" {
-    # R4D_LRU_GATHER_CHUNKS=32 / R4D_LRU_GATHER_LANES=64: the overnight
-    # sweep's biggest lever, +18.7% decode vs default geometry, and the win
-    # GROWS with depth (39.5@166 -> 54.1@1087 -> 49.3@4064 in the fp8 era).
-    # g64x128 is past the peak; g8x16 mild. They are container ENV (the
-    # fork's knobs), not engine flags — passed through with -e.
-    grep -q '^FRANK_PRIMARY_GATHER_CHUNKS=32$' "$ENV_FILE"
-    grep -q '^FRANK_PRIMARY_GATHER_LANES=64$' "$ENV_FILE"
-    grep -q -- '-e R4D_LRU_GATHER_CHUNKS="$FRANK_PRIMARY_GATHER_CHUNKS"' "$SERVE"
-}
-
-@test "the arena sits just under the ceiling and the KV ask is honoured" {
-    # The planner sizes expert cache as budget - non-expert - KV reserve -
-    # graphs - overhead, and two of those five terms are reachable from a
-    # deploy: budget (= device_total x util) and graphs (VLLM_CUDAGRAPH_MEM_*).
-    # UTIL has a HARD LAW, not a field cap: 0.982, never 1.00. The 1.00 attempt
-    # is UNBOOTABLE on this fork — worker init raises
-    # `ValueError: Free memory on device cuda:N (31.29/31.86 GiB ...)`
-    # on both ranks because the worker demands free > budget and budget ==
-    # total — and even if it booted, 0.13-GiB-margin shapes have died under
-    # real load. So the arena tops out at 0.982 budget (31.29 GiB).
-    # Graphs: charge strictly below the fork's analytic 563 MiB default while
-    # still paying per graph (the measured post-capture delta is -0.06 GiB, i.e.
-    # the base pool is the over-charge, but a future spec-decode shape captures
-    # 18 graphs and must still be charged).
-    # MNBT stays 2048: 512 doubles TTFT at 4064 ctx, 1024-4096 are decode-
-    # interchangeable AND arena-identical (the registry prices overhead flat up
-    # to its nbt 4096 anchor), 12288 costs 2.5% plus arena.
-    # The KV ask: the pool is priced at the engine's measured 7,892 B/token at
-    # this shape, and a served conversation needs 200,704 tokens, so the pool
-    # must clear 400,700 tokens to keep two full-length resident.
-    grep -q '^FRANK_PRIMARY_MNBT=2048$' "$ENV_FILE"
-    grep -q -- '--max-num-batched-tokens "$FRANK_PRIMARY_MNBT"' "$SERVE"
-    grep -q '^FRANK_PRIMARY_UTIL=0.982$' "$ENV_FILE"
-    base=$(awk -F= '/^FRANK_PRIMARY_CUDAGRAPH_BASE_MB=/{print $2}' "$ENV_FILE")
-    per_graph=$(awk -F= '/^FRANK_PRIMARY_CUDAGRAPH_PER_GRAPH_MB=/{print $2}' "$ENV_FILE")
-    [ "$base" -eq 0 ] && [ "$per_graph" -gt 0 ]
-    [ $((base + 6 * per_graph)) -lt 563 ]
-    kv=$(awk -F= '/^FRANK_PRIMARY_KV_BYTES=/{print $2}' "$ENV_FILE")
-    [ $((kv / 7892)) -ge 400700 ]
-}
-
-@test "expert prefetch is absent BY LAW, not by omission" {
-    # Telemetry (2026-09-29): the prefetcher served 13,369 of 36,720
-    # prefetched slabs (36% precision) — roughly half the gather traffic was
-    # waste, and the "savings" would have been installs anyway. Deleting the
-    # flag moved decode 26.8 -> 40.6 tok/s. Any future flag must come with a
-    # fresh A/B, so the serve script must NOT wire it unconditionally.
-    ! grep -q -- '--expert-prefetch' "$SERVE"
-    ! grep -q 'expert_prefetch' "$ENV_FILE"
-    grep -q 'PREFETCH IS ABSENT BY LAW' "$ENV_FILE"
-}
-
-@test "TunableOp stays off" {
-    # CLAV_TUNABLEOP_SWEEP silently skips under expert offload unless
-    # CLAV_TUNABLEOP_WITH_OFFLOAD=1, and forcing it corrupts numerics
-    # (repetition loops, early halts, invalid measurements).
-    ! grep -q 'TUNABLEOP' "$ENV_FILE"
-    ! grep -q 'TUNABLEOP' "$SERVE"
-}
-
-@test "the serve script gates the digest-pinned image and the payload" {
-    # The image is pinned by OCI manifest digest (the floating :latest moved
-    # once already). The payload gate checks config.json and the exact shard
-    # count from the env — a missing shard means a guaranteed long-timeout
-    # boot instead of a fast failure.
+@test "the serve script gates the image, the payload and the GPU nodes" {
+    # The image gate is EXISTENCE (podman image exists): the FreeToken
+    # image is built ON THE HOST — a local tag carries no RepoDigests — and
+    # pinning lives in the Dockerfile (pinned PR-head SHA, base image).
+    # The payload gate checks config.json and the exact shard count from
+    # the env — a missing shard means a guaranteed long-timeout boot
+    # instead of a fast failure.
     grep -q 'FRANK_PRIMARY_IMAGE' "$SERVE"
-    grep -q 'RepoDigests' "$SERVE"
+    grep -q 'podman image exists' "$SERVE"
     grep -q 'FRANK_PRIMARY_MODEL_SHARDS' "$SERVE"
     grep -q 'config.json' "$SERVE"
+    grep -q 'model.safetensors.index.json' "$SERVE"
     grep -q '/dev/kfd' "$SERVE"
     grep -q -- '--device /dev/dri' "$SERVE"
-    ! grep -q 'tcclaviger/vllm:latest' "$ENV_FILE"
 }
 
 @test "the serve script clears stale containers and self-heals via podman wait" {
     # A crashed unit can leave the container name registered forever after;
-    # the legacy identities (the retired R9V container and the ad hoc
-    # experiment container) hold the same GPUs and die here too. Then block
-    # on the container so a crash is a nonzero ExecStart.
+    # the legacy identities (the vLLM-era frank-primary-qwen container, the
+    # retired R9V container and the ad hoc experiment containers) hold the
+    # same GPU and die here too. Then block on the container so a crash is
+    # a nonzero ExecStart.
     grep -q 'FRANK_PRIMARY_LEGACY_CONTAINERS' "$ENV_FILE"
+    grep -q 'frank-primary-qwen' "$ENV_FILE"
     grep -q 'frank-primary-r9v' "$ENV_FILE"
     grep -q 'qwen-fp8' "$ENV_FILE"
     grep -q 'exec podman wait "$FRANK_PRIMARY_CONTAINER"' "$SERVE"
 }
 
 @test "frank-primary holds the single fleet port under its own alias" {
-    # The scratch identity (qwen3.8-flash-next on :7773) must never leak
-    # into production: LAN publish of :7770, the harness's model id.
+    # LAN publish of :7770, the harness's model id.
     grep -q '^FRANK_PRIMARY_PUBLISH=7770:7770$' "$ENV_FILE"
     grep -q '^FRANK_PRIMARY_SERVED_NAME=frank-primary$' "$ENV_FILE"
 }
@@ -404,16 +201,38 @@ DOWNLOAD="$REPO_ROOT/scripts/download-frank-primary.sh"
     ! grep -qE '^(export )?(TEMP|HOST|GPU_MAX_HEAP_SIZE)=' "$SERVE"
 }
 
-@test "the deployer gates the image digest and payload, then health-checks" {
-    # The deployer refuses when the pinned image is absent from rootless
-    # storage or the payload is missing/wrong-sharded — then clears stale
-    # containers (including the legacy identities), waits out the port,
+@test "the Dockerfile pins the FreeToken source and follows the ROCm install law" {
+    # The engine is the PR #587 head, NOT a moving branch: a future push to
+    # rocm714_torch214 would otherwise silently change the deployed engine.
+    grep -q '77a7201f98f00d93f618c6cf8b81ffe8360e0899' "$DOCKERFILE"
+    grep -q 'pull/587/head' "$DOCKERFILE"
+    # docs/install_amd.md's build law: --no-build-isolation --no-deps (a
+    # plain `pip install -e .` on ROCm can REPLACE the ROCm torch with a
+    # CUDA build via its NVIDIA-authored dependency set), curated portable
+    # deps, flashlib --no-deps.
+    grep -q -- '--no-build-isolation --no-deps -e .' "$DOCKERFILE"
+    grep -q 'flashlib==0.3.0' "$DOCKERFILE"
+    # The CUDA-only backends have no ROCm builds and are intentionally
+    # absent (the PR's 12 pytest failures are exactly those backends;
+    # FreeToken falls back to its Triton kernels).
+    ! grep -q 'flashinfer' "$DOCKERFILE"
+    ! grep -q 'sgl_kernel' "$DOCKERFILE"
+    ! grep -q 'nvidia-cutlass-dsl' "$DOCKERFILE"
+    # The base image is digest-pinned (the registry tag is not trusted).
+    grep -qE '^FROM rocm/pytorch:.*@sha256:[0-9a-f]{64}$' "$DOCKERFILE"
+}
+
+@test "the deployer gates the image, payload and containers, then health-checks" {
+    # The deployer refuses when the image is absent from rootless storage
+    # or the payload is missing/wrong-sharded — then clears stale containers
+    # (including the legacy identities), waits out the port,
     # relinks/enables/restarts the root unit and health-gates it.
-    grep -q 'LLM_PRIMARY_CONTAINER=frank-primary-qwen' "$REMOTE_DEPLOY"
+    grep -q 'LLM_PRIMARY_CONTAINER=frank-primary$' "$REMOTE_DEPLOY"
     grep -q 'FRANK_PRIMARY_IMAGE' "$REMOTE_DEPLOY"
-    grep -q "podman images --format '{{.RepoDigests}}'" "$REMOTE_DEPLOY"
+    grep -q 'podman image exists' "$REMOTE_DEPLOY"
     grep -q 'FRANK_PRIMARY_MODEL_SHARDS' "$REMOTE_DEPLOY"
     grep -q 'config.json' "$REMOTE_DEPLOY"
+    grep -q 'frank-primary-qwen' "$REMOTE_DEPLOY"
     grep -q 'qwen-fp8' "$REMOTE_DEPLOY"
     grep -q 'glm-probe' "$REMOTE_DEPLOY"
     grep -q 'wait_port_free 7770' "$REMOTE_DEPLOY"