frank-zealot: sweep the live path — serve defaults, unit text, picker docs

- serve script: header + every fallback default re-keyed to the Bonsai-2 trio (vendor LLAMA_BIN, PQ2_0 MODEL_FILE, Q8_0 MMPROJ) and CACHE_TYPE_*:=q8_0 — a defaulted run must land on the shipped shape, never on the retired 9B/f16 pair (the trial window proved a silent default is how a swap goes wrong) - unit Description now names the payload + KV dtype that `systemctl status` will show during the next incident - OpenWebUI decoration-row description re-keyed, with the law that the row is live DB state a swap must follow into the database
docs(AGENTS): fleet topology + llama.cpp laws for the PQ2_0 zealot era
2026-10-17 19:42:13 -07:00 · 2026-10-17 19:41:11 -07:00 · 2026-10-17 19:41:11 -07:00 · 2026-10-17 19:40:56 -07:00 · 2026-10-17 19:40:56 -07:00 · 2026-10-17 19:40:56 -07:00
24 changed files with 1069 additions and 334 deletions
@@ -25,9 +25,9 @@ merge absorbed the former `vllmScripts` repo, history preserved).
 | Target | Service | Runtime | Model | Port |
 |--------|---------|---------|-------|------|
-| Dankserver | `frank-archon` | **radiance** (StillDeadcode, **pin 1.0.13** digest-pinned `stilldeadcode/radiance@sha256:4c3f484564…`, plain `podman run`, root systemd unit) | ukisai/Swift1.5-Qwen3.8-Flash-Next BF16 (335.3 GiB, 397/397 sha256-verified) converted by `scripts/convert-swift15-w4dn8.sh` to `qwen4exp-swift15-w4dn8-i8-hc8m.rad` (**116,416 MiB**): **all 49,152 experts GPTQ w4** (10M-token calibration on engine 1.2.0) + **24 whole bf16-protected experts/layer** (energy-share law), int8 trunk/lm_head, fp8 HC, PLE n-gram fp8 fixed-scale, on **BOTH R9700s TP=2** (`--tp-wire wht6`), experts in a **44 GiB/rank pinned host pool** + VRAM cache (`--placement expert_tiered`, explicit `--vram-weights-mib 25600 --vram-kv-mib 5120` = 30,720 of the **30,969 MiB** the engine's own budget table makes claimable: card 32,624 MiB, settle floor 209 MiB), **47.7 GiB n-gram copy pinned to host RAM** (`--ngram-placement ram`; root unit + `LimitMEMLOCK=infinity`), **fp8 KV** (pool 5,120 MiB = the 3-slot contract + 1.3 % — the only dtype that funds 3 × 200,000 without gutting the slab, since bf16 bills 13.8 KiB/token), **MTP spec decode depth 2**, `--max-num-seqs 3` (the capacity contract is 3 × 200,000; 3 × (1+2) = 9 all-reduce rows, inside the 25-row wht6 exactness bound), `--max-model-len 200000`, MNBT 2048, Froggeric v22.5 template. KLD-gated (mean KL 0.0131, top-1 97.92 % vs BF16); decode ~190 t/s live (gate bar 30.8); prefill is **slab-limited and pays for it** — 22,208 → 3,397, 24,000 → 3,290, 25,600 → **3,584** t/s at 43.5k single-stream, 3-way 197k aggregate 3,051 → **3,589** t/s, with a cliff at ~26 GiB (26,071 → 4,379). Cutover 2026-10-08 from fp8-native (payload on disk = rollback); 3-slot fp8-KV shape 2026-10-13, re-cut twice in the slab's favour (22208/6912 at 4 slots → 24000/5120 → 25600/5120); the 4-slot shape (22208/6912, `--max-num-seqs 4`) is the documented rollback. | 7770 |
+| Dankserver | `frank-archon` | **radiance** (StillDeadcode, **pin 1.0.13** digest-pinned `stilldeadcode/radiance@sha256:4c3f484564…`, plain `podman run`, root systemd unit) | **Publisher payload** (swap 2026-10-15, MODEL_FILE-only): `StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe` → **`qwen3.8-next-flash-fp8-iq4r-moe.rad`** (121,969,901,568 B = **116,322 MiB**, Hub-LFS sha256 `0af5e962…` verified at fetch by `scripts/download-frank-archon-iq4r.sh`) — the OFFICIAL Qwen3.8-Flash-Next bf16 checkpoint rad-converted by the engine's author: routed experts as **4-bit codes into a 16-level non-uniform codebook** (128-pt Walsh–Hadamard rotation, GPTQ on a 10M-token calibration + 3 coordinate-descent sweeps, E4M3 scales per 64 weights), **10 whole bf16-protected experts/layer**, int8 W8A8 trunk/lm_head, fp8 HC mixtures, fp8 fixed-scale PLE n-gram (47.7 GiB), **MTP head + bf16 vision tower in the container**; card KL 0.0789 mean all-tokens / top-1 92.85 % vs BF16. **Base-alignment (censored) model** — the abliterated family lives on frank-dragoon. Shape carried VERBATIM from the 2026-10-13 record: **3 × 200,000 fp8-KV** (`--max-num-seqs 3`), **25,600 MiB slab + 5,120 MiB pool = 30,720 of the 30,969 MiB claimable**, 44 GiB/rank pinned host pool, PLE pinned to RAM, MTP depth 2, MNBT 2048, Froggeric v22.5 template. Decode/prefill ladders in the runbook are the **w4dn8 record** (the bar to beat; new-payload probes pending). Rollback: revert the swap commit (w4dn8 `.rad` on disk); the fp8-native `.rad` + the raw Swift1.5 BF16 source were DELETED from disk 2026-10-15 (Frank's one-time rm, volume for this payload; rebuildable via the fetch/build scripts). | 7770 |
 | Dankclaw | `frank-dragoon` | **halogen-flash-server 0.16.2** (`ghcr.io/peonist-ai/halogen-flash-server@sha256:0c61bf84…`, digest-pinned, plain `podman run` via `scripts/serve-frank-dragoon.sh`, root systemd unit) | Quat3rnion/halogen-swift1.5-qwen3.8-flash-next-v2-abliterated **`qwen38-flash-next-v2-swift15-abliterated.hgn`** (66,687,678,464 B = compacted r2 of the card's 89,775,868,032 B original, ~62 GiB resident; the v2 `.hgn` format loads in NO other engine), **+ REQUIRED `qwen38-flash-next-ngram.hgn`** (51,200,246,144 B, peonist @5cc17cea — read beside the checkpoint) **+ vision tower** (897,916,416 B, @e053f488 — **vision ON**, `image_url` parts only, ≥256 px probes), **MTP spec decode ALWAYS-ON (`HALOGEN_SPEC_ADAPT=0` — the adaptive default disables the drafter per request and HALVES decode)**, MTP head INSIDE the checkpoint (`HALOGEN_MTP_HEAD` unset; no sidecar fetched), **2 slots × 262,144 ctx** (KV pool 524,288 positions ≈ 14.0 GiB at ~28 KiB/position; the 27B slots>1-disables-drafting law does NOT carry over — batching and speculation coexist, the card's quickstart ships 2 with the head), harness window 217,088 = ceiling − 45k estimate headroom, **server-side sampler 1.0/0.95/20** (card recipe; models.yml extraBody matches), coupled cap/timeout 65536/7200, prompt cache ON by default (warm 100k turn ≈ 2 s vs ≈ 88 s cold)|7770|
-| Dankclaw | `frank-zealot` | llama.cpp master (0.5.0-dev, commit `5fc4f3c`), CUDA sm_86 build (root systemd unit, relinked) | HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive **Q6_K** (7,359,259,008 B; dense `qwen35` hybrid: 32 layers, 8 full-attention + 24 Gated DeltaNet, 4 KV heads × 256 dim, vocab 248,320, native 262,144, **no MTP tensors in the file**) + the publisher's own **BF16 mmproj** (921,704,448 B) for **vision**, on the RTX 3090, **TWO 200,704-token slots** (`--ctx-size 401408 --parallel 2`), **exact f16 K + f16 V** under flash attention (32 KiB/token over the 8 full layers = 12.25 GiB pool), batch 4096 / **ubatch 2048** (measured CUDA optimum), `--log-verbosity 4`, **MTP OFF** (forced: no `nextn` tensors exist). Priced from the MiMo Q6_K boots (same geometry, same card, same shape): 21,276/2,849 at ubatch 1024, 21,846/2,279 at 2048. Cutover 2026-10-07 (late) from Gemma4-26B-A4B Q4_K_M 1×200,704. All three endpoints route harness **compaction** here. | 7771 |
+| Dankclaw | `frank-zealot` | **llama.cpp PrismML fork build** (vendor release `0.2.0-dev` build **10754**, commit `2459f68b5`; root systemd unit, relinked — the ONLY loader for this payload) | `prism-ml/Ternary-Bonsai-2-27B-gguf` **PQ2_0** (7,206,168,928 B, sha256 `3907dc16…`; `qwen35` hybrid: **64 blocks, 16 full-attention + 48 Gated DeltaNet**, 4 KV heads × 256 dim, vocab 248,320, native 262,144, **no MTP head in the file**; `general.file_type 141` = custom tensor type **142** + `prism.hadamard.*` dequant metadata, which is what locks the runtime) + the publisher's own **Q8_0 mmproj** (629,246,976 B; Qwen3-VL tower, 27 blocks, 768 px, `qwen3vl_merger`) for **vision**, on the RTX 3090, **TWO 200,704-token slots** (`--ctx-size 401408 --parallel 2`), **q8_0 K + q8_0 V** under flash attention (34 KiB/token over the 16 full layers = 13,328 MiB pool; **f16 KV needs 25,088 MiB and cannot boot this card**), batch 4096 / **ubatch 2048** (measured CUDA optimum), `--log-verbosity 4`, **MTP OFF** (no head in the file). Boot 22,664 used / 1,461 free; 76.6 t/s single-stream decode, 691.7 t/s prefill at 166k. Cutover 2026-10-17 from Qwen3.5-9B-Uncensored Q6_K (same shape; payload + master CUDA build on disk as rollback). |
 Retired endpoints (`frank-npu`, and every prior runtime) are in
 the [runbook index](#runbook-index). The full swap history lives in
@@ -226,13 +226,6 @@ archive.
 ## Benchmarking Policy (MANDATORY)
 **Benchmarking is NOT part of the model-swap procedure** (2026-10-15). A
 model change is verified by driving the live service — boot ledger,
 per-request `timings`/`Server-Timing`, one real request per harness role
 (`serverAppConfigs-docs/LLM/Model Swap and Rollback.md` §6/§8). No bench
 window is scheduled for a swap, ever. The rest of this policy governs
 *deliberate* bench windows (flag A/Bs, shape sweeps), which are separate
 operations on a live host:
 **STOP the production service BEFORE benchmarking** — these servers serve
 real users, and a bench beside a live service starves the GPU and corrupts
 results. Use the runtime's own harness: `llama-bench` for the llama.cpp
@@ -436,101 +429,122 @@ Rollback: revert the swap commit and redeploy — the 27B payload
 halogen 0.1.4 image digest all remain on disk; the ROCmFPX door behind
 that (`scripts/build-rocmfpx.sh`, pin `36e9acd`) is untouched.
-### frank-zealot — llama.cpp on the RTX 3090 (Dankclaw, ACTIVE)
+### frank-zealot — llama.cpp (PrismML fork) on the RTX 3090 (Dankclaw, ACTIVE)
-**llama.cpp master** (0.5.0-dev, commit `5fc4f3c`; CUDA sm_86 build
+**The PrismML fork build of llama.cpp** (vendor release, `--version` =
-`/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server`,
+`0.2.0-dev (build 10754, commit 2459f68b5)`;
-`GGML_CUDA_FA_ALL_QUANTS=ON`) as a **root systemd unit**
+`/home/dank/GitPackages/llama-prism/llama-server`) as a **root systemd unit**
 (`scripts/frank-zealot.service`, `relink_unit`ed into
-`/etc/systemd/system/`), serving
+`/etc/systemd/system/`), serving `prism-ml/Ternary-Bonsai-2-27B-gguf` at
-`HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive` at **Q6_K**
+**PQ2_0** (7,206,168,928 B, sha256 `3907dc16…` = the Hub LFS oid) **plus the
-(7,359,259,008 B, sha256 `c0ba7beb…` computed locally — the Hub carries no
+publisher's own Q8_0 mmproj** (629,246,976 B), both
-LFS oid) **plus the publisher's own BF16 mmproj** (921,704,448 B), both
+`/home/dank/models/Bonsai2-PQ2_0/`, on port 7771. Cutover 2026-10-17 from the
-`/home/dank/models/Qwen35-9B-HauhauCS-Q6K/`, on port 7771. Cutover
+Qwen3.5-9B-Uncensored Q6_K era (same shape).
 2026-10-07 (late) from the Gemma4-26B-A4B Q4_K_M 1×200,704 shape (same day).
-**Architecture: qwen35 dense hybrid** — read from the GGUF's own header, not
+**The runtime is part of the payload identity.** The file is
-the model card: 32 layers, `full_attention_interval = 4` ⇒ **8 full-attention
+`general.file_type 141` (PQ2_0, 2.13 bpw, group 128) with **402 tensors of the
-layers (3, 7, 11, …, 31) + 24 Gated DeltaNet linear layers**, 16 attention
+custom GGML type 142** plus `prism.hadamard.*` metadata (normalized
-heads / **4 KV heads** × 256 dim, `ssm` conv_kernel 4 / state_size 128 /
+Sylvester–Walsh transform, block 1024, 401 named weights, inverse on
-group_count 16 / time_step_rank 32 / inner_size 4096, native 262,144, vocab
+`token_embd`, `gdn_v_grouped`). Stock llama.cpp refuses type 142 at load, and a
-248,320. Tensor types are Q6_K × 250 + F32 × 177 — standard quants only, so
+loader that ignored the Hadamard metadata would dequant wrongly — same lock class
-the stock master build loads it (arch `qwen35` is registered in this build's
+as the ROCmFPX era. Retargeting the payload without the fork ships an endpoint
-`src/llama-arch.cpp`). **KV accounting:** the pool scales with the 8 full
+that cannot load, so the seam pins both paths.
 layers only — 8 × 4 × 256 = 8,192 elements/token per cache, so f16 K + f16 V
 bills **32 KiB/token** = 12.25 GiB at the 401,408 pool; the 24 DeltaNet
 layers bill a fixed recurrent state per SLOT, not per token, which is exactly
 why two 200k slots fit where the 26B MoE fit one.
-**The shape (2026-10-07):** `--ctx-size 401408 --parallel 2` = TWO
+**Architecture: qwen35 hybrid** — read from the GGUF's own header: **64
 blocks**, `full_attention_interval = 4` ⇒ **16 full-attention + 48 Gated
 DeltaNet layers**, 24 attention heads / **4 KV heads** × 256 dim, embedding
 5,120, ffn 17,408, `ssm` conv_kernel 4 / state_size 128 / group_count 16 /
 time_step_rank 48 / inner_size 6,144, native 262,144, vocab 248,320. **KV
 accounting:** the pool scales with the 16 full layers — 16 × 4 × 256 = 16,384
 elements/token per cache, so **q8_0 K + q8_0 V bills 34 KiB/token** = 13,328
 MiB at the 401,408 pool (ledger-confirmed to the MiB), while **f16 KV needs
 25,088 MiB and cannot boot on a 24,123 MiB card** (measured `cudaMalloc` OOM).
 The 48 DeltaNet layers bill a fixed recurrent state per SLOT — ~150 MiB each —
 so pool arithmetic alone under-prices the shape.
 **The shape (2026-10-17):** `--ctx-size 401408 --parallel 2` = TWO
 conversations of 200,704 (Frank's cap; the harness `contextWindow` quotes
-the per-slot number), `--flash-attn on`, **f16 K + f16 V** (exact KV),
+the per-slot number), `--flash-attn on`, **q8_0 K + q8_0 V**, batch 4096 /
-batch 4096 / **ubatch 2048** (the measured CUDA optimum: +4.6 % prefill,
+**ubatch 2048** (the measured CUDA optimum carried from the MiMo/Swift A/Bs on
-decode flat, 616 MiB — MiMo-era A/B on this card), `--log-verbosity 4`,
+this card), `--log-verbosity 4`, `--mmproj` for vision, **speculative decoding
-`--mmproj` for vision, **speculative decoding OFF** (`SPEC_TYPE=none`).
+OFF** (`SPEC_TYPE=none`). Boot: **22,664 MiB used / 1,461 free**; the
 projection (21,439) excludes the projector's 873.10 MiB worst-case, which
 lands AFTER the fit check — read settled `nvidia-smi`, never the projection.
 Measured: 76.6 t/s single-stream decode (the 9B ran 94.4), 1,258 t/s prefill
 at 35k, 691.7 t/s at 166k, 109.4 t/s aggregate across two concurrent streams.
 The **first request after boot is a warmup artifact** (2.6 t/s prefill / 37.7
 t/s decode measured) — never report it.
-**Why MTP is off**: it is not a choice — **this Q6_K file carries no
+**Why MTP is off**: the PQ2_0 export carries no MTP head (upstream ships a
-`nextn`/`mtp` tensors** (verified from the tensor-name list), and MTP is a
+separate `…-CRACK-MTP-GGUF`, +451 MB, for that), and MTP is a property of the
-property of the file, not of the flags. The publisher card advertises "MTP
+file, not of the flags.
 support" for the base architecture; the quantized export dropped the head.
-**Measured boots** (nvidia-smi, the referee): the deployed boot is
+**Vision**: the publisher's own Q8_0 mmproj via `--mmproj` (Qwen3-VL tower: 27
-**21,436 used / 2,689 free** (ubatch 2048) — the pricing boots were the
+blocks, 768 px, patch 16, merge 2, `qwen3vl_merger`, deepstack). Probe traps
 MiMo-V2.6-Distill-Qwen-9B pair at this exact geometry (**21,276 / 2,849** at
 ubatch 1024, **21,846 / 2,279** at 2048), so the 415 MiB lighter weights
 bought back what the projection predicted. The engine ledger confirms the KV
 law to the MiB: `CUDA0 KV buffer size = 12544.00 MiB` (`K (f16): 6272.00`,
 `V (f16): 6272.00`), compute buffers 1,136 MiB on CUDA0 + 848 MiB host, the
 mmproj 879 MiB + 248 MiB. Decode is ubatch-invariant (Swift-era 3090 law). The
 Q6_K rung costs ~10 % decode vs Q5_K_M (weight bandwidth; MiMo-measured 94.4
 vs 104.8 t/s).
 **Vision**: the publisher's own BF16 mmproj via `--mmproj` (the model is
 natively multimodal; the Q6_K file carries no vision tensors). Probe traps
 carry over: ≥256 px probe images or the model answers "video", and only the
-OpenAI `image_url` content part reaches the model.
+OpenAI `image_url` content part reaches the model. **New trap:** thinking
 tokens count against `max_tokens`, so a vision probe at 64 tokens returns
 EMPTY `content` with `finish_reason: "length"` — budget ≥512 or the endpoint
 looks blind while it is only mid-thought.
 **Base alignment**: Bonsai-2 is the censored BASE lineage (the 9B it replaced
 was uncensored). The CRACK re-export on disk
 (`/home/dank/models/Bonsai2-CRACK/`, header census proves byte-identical
 geometry) is a one-line `MODEL_FILE` swap if a refusal ever surfaces.
 **Compaction hub**: `models.yml` routes `compactionModel` for
 `frank-archon`, `frank-dragoon` and `frank-zealot` (the 3090 endpoint) here — 200,704 is the
 only window in the fleet that fits a worst-case compaction input (~170k
 tokens). With `--parallel 2` a compaction request no longer serializes behind
-a live generation (the Gemma4 era's `--parallel 1` law).
+a live generation (the Gemma4 era's `--parallel 1` law). Retrieval through a
 25,960-token prompt was verified exact after the swap.
 **Contract law learned at verbosity 4:** a raw `/completion` request prints
 `failed to parse reasoning content (… parse_reasoning=true)` whenever the
 model closes a bare prompt with `` — cosmetic
 (`probe_request.cpp:789`); the `/v1/chat/completions` path parses
 `reasoning_content` correctly, which is the only path consumers use. Do not
 lower `VERBOSITY` to silence it: the KV/buffer ledger is what VRAM forensics
 read.
 Runbook:
-`serverAppConfigs-docs/LLM/frank-zealot-llama-qwen35-9b-q6k-2x200704.md`.
+`serverAppConfigs-docs/LLM/frank-zealot-llama-prism-bonsai2-pq20.md`.
-Rollback: revert the swap commit — the Gemma4 payload
+Rollback: revert the swap commit — the Qwen3.5-9B Q6_K payload
 (`/home/dank/models/Qwen35-9B-HauhauCS-Q6K/`) with the master CUDA build
 (`~/GitPackages/llama-master/build-cuda/`), the Gemma4 payload
 (`/home/dank/models/Gemma4-26B-A4B/`), the MiMo Q6_K payload
 (`/home/dank/models/MiMo-Q6K/`), the Swift payload
 (`/home/dank/models/Swift15-UncIQ3XXS/`) and the Ornith Q8_0 payload
 (`/home/dank/models/Ornith-Q8/`) all remain on disk.
-### frank-archon — Radiance (StillDeadcode), Swift1.5-Qwen3.8-Flash-Next GPTQ w4, TP=2 (Dankserver, ACTIVE)
+### frank-archon — Radiance (StillDeadcode), publisher Qwen3.8-Flash-Next iq4r, TP=2 (Dankserver, ACTIVE)
 The **radiance engine** (StillDeadcode, Apache-2.0; image
 `stilldeadcode/radiance@sha256:4c3f484564…` digest-pinned, **pin 1.0.13**
-for serve/convert/KLD; `libr4d` gfx1201 kernels, plain `podman run`, root
+for serve; `libr4d` gfx1201 kernels, plain `podman run`, root
-systemd unit, container name = unit name) serving
+systemd unit, container name = unit name) serving the
-**ukisai/Swift1.5-Qwen3.8-Flash-Next (BF16, 335.3 GiB, 131 shards,
+**publisher's container of the official Qwen/Qwen3.8-Flash-Next**:
-397/397 sha256-verified)** converted by `scripts/convert-swift15-w4dn8.sh`
+`StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe` →
-with recipe `scripts/recipes/qwen4exp-swift15-w4dn8-i8-hc8m.recipe` to
+`qwen3.8-next-flash-fp8-iq4r-moe.rad` (116,322 MiB, Hub-LFS sha256
-`qwen4exp-swift15-w4dn8-i8-hc8m.rad` (~114 GiB): **all 49,152 experts GPTQ
+verified at fetch by `scripts/download-frank-archon-iq4r.sh`; recipe
-w4** (act-order, damp 0.05, 10,000,000-token calibration captured on engine
+`qwen4exp-w4nl64-i8-hc8m`): **routed experts as 4-bit codes into a
-**1.2.0** via `RADIANCE_CALIB_DIR`/`RADIANCE_CALIB_TOKENS` — the only pin
+16-level non-uniform codebook** after a 128-point Walsh–Hadamard rotation
-with the token knob; the RADGRAM2 grams are format-identical across pins and
+(E4M3 scale per 64 weights; codes by GPTQ on a 10M-token calibration with
-cross the boundary by design), **24 whole experts per layer cast bf16** (the
+per-expert down-proj Hessians, refined by 3 coordinate-descent sweeps),
-PROTECTED set, derived from the calibration grams' energy share),
+**10 whole bf16-protected experts/layer**, **int8 W8A8 trunk/lm_head**
-**int8 trunk/lm_head**, **fp8 HC mixtures** (`--hc-mix-dtype`), PLE n-gram
+(scale per 128 columns searched), **fp8 HC mixtures**, PLE n-gram table at
-table at fp8 fixed scale (47.7 GiB in the container, from 95.4 GiB bf16).
+fp8 fixed scale (47.7 GiB), **MTP head and bf16 vision tower in the
-The plugin's **one-table-one-encoding law** (measured at rad-convert
+container**. Card quality (full-vocab teacher-forced KL vs bf16, ~75K
-declare): one expert table takes ONE encoding; only whole bf16 experts are
+positions): mean 0.0789 all-tokens / 0.0239 assistant turns, top-1 92.85 %.
-legal beside it — no w4/fp8 split of the down/gate_up pair (24-value
+**MODEL_FILE is the only serving argument that moved** (2026-10-15); every
-`rad_arch_quant_desc` array, one per layer). KLD gate vs the BF16
+number of the 2026-10-13 shape below carries verbatim. The plugin's
-reference (recorded on the same 1.0.13 pin) is the precision referee;
+**one-table-one-encoding law** (fleet-measured at rad-convert declare):
-the throughput gate (decode ≥ 30.8 t/s) was passed at 4.5× the bar
+one expert table takes ONE encoding; only whole bf16 experts are legal
-(122–173 t/s at 44.5k depth). Measured decode/prefill in the runbook.
+beside it. Rollback: revert the swap commit — the in-house w4dn8 `.rad`
-Rollback: revert the swap commit — the fp8-native `.rad`
+(KLD-gated Swift1.5 conversion) stays on disk; the fp8-native `.rad` was
-(`qwen4exp-fp8-native.rad`) and every prior payload remain on disk.
+deleted 2026-10-15 (rebuild: `scripts/download-frank-archon.sh` +
 `scripts/build-frank-archon-rad.sh`).
 **Shape (both R9700s, TP=2)**: `--tp-wire wht6`, `--max-num-seqs 3`,
 `--max-model-len 200000` (the harness contextWindow must quote this),
@@ -582,7 +596,8 @@ accept 0.7246).
 **The KV dtype law (measured 2026-10-11, applied at 4 slots 2026-10-13)**:
 `--kv-cache-dtype` takes ONLY `bf16|fp8` — one dtype for the whole cache, so
-llama.cpp's exact-K/quantized-V pair (what frank-zealot runs) has NO radiance
+llama.cpp's exact-K/quantized-V pair (the 9B-era frank-zealot ran it; the
 Bonsai-2 swap runs q8_0/q8_0) has NO radiance
 equivalent; the rung under bf16 is fp8 on both halves. Measured per rank from
 the two boot ledgers: `kv_attn` (13 layers, 4-token blocks) pages 26.00 → 52.00
 KiB, while `kv_qsa_bkey` (13 layers) stays 3.25 KiB at BOTH dtypes (the QSA
@@ -637,8 +652,9 @@ chat format — no parser flags; vision native (the 27-layer Qwen-VL tower,
 `--mm-max-patches`); `/metrics` carries vLLM-compatible names +
 `radiance:*` families — the Dankclaw Prometheus scrape is re-added.
-Runbook: `serverAppConfigs-docs/LLM/frank-archon-radiance-swift15-w4dn8.md`.
+Runbook: `serverAppConfigs-docs/LLM/frank-archon-radiance-qwen38-iq4r.md`.
-Retired fp8-native era: `serverAppConfigs-docs/LLM/frank-archon-radiance-qwen38-native-fp8.md`.
+Retired Swift1.5 w4dn8 era (payload on disk = rollback): `serverAppConfigs-docs/LLM/frank-archon-radiance-swift15-w4dn8.md`.
 Retired fp8-native era (payload deleted 2026-10-15, rebuildable): `serverAppConfigs-docs/LLM/frank-archon-radiance-qwen38-native-fp8.md`.
 Retired FreeToken era: `serverAppConfigs-docs/LLM/frank-archon-freetoken-pr587.md`.
 Retired vLLM era: `serverAppConfigs-docs/LLM/dankserver-qwen38-fp8-expert-offload-tuning.md`.
 Retired GLM experiment: `serverAppConfigs-docs/LLM/frank-archon-glm53-flash-w4a16.md`.
@@ -1026,6 +1042,31 @@ linked runbooks.
  `Unexpected reasoning effort high` until `high: xhigh` was added on
  2026-09-16. Halogen accepts the wider set, so the two entries legitimately
  differ.
 - **The vision projector is NOT billed in llama.cpp's own fit check.** The
  engine prints `[mtmd] estimated worst-case memory usage of mmproj is
  873.10 MiB` and then fits WITHOUT it: frank-zealot's Bonsai-2 boot projected
  21,439 MiB and settled at 22,664 (2026-10-17). Price a 3090-class shape from
  settled `nvidia-smi` after a real boot, never from
  `model + context + compute` — the projector (and any drafter context) lands
  after `/health` would already have answered. Same failure class as the
  DSpark drafter OOM.
 - **The FIRST request after a boot is a warmup artifact.** Measured on
  Bonsai-2/3090: 2.6 t/s prefill and 37.7 t/s decode on request #1, then
  1,258 t/s prefill and 54.7 t/s (per stream, two concurrent) on the next — a
  3× spread on the same shape. Benchmark the second request or later, or the
  graph-capture cost reads as a model fault.
 - **Thinking tokens count against `max_tokens`, so a short-budget vision probe
  reads as blindness.** The Bonsai-2/`image_url` probe at `max_tokens: 64`
  returned `content: ""` with `finish_reason: "length"` and half a thought in
  `reasoning_content` — the image HAD reached the model (322 prompt tokens vs
  42 for the text alone). At 512 tokens the same image answers "Red". Budget
  ≥512 for any thinking model you probe for vision.
 - **Quantized KV is not the only dtype law a fork build can hide.** Vendor
  builds carry their own compile options: frank-zealot's PrismML prebuilt
  served `--cache-type-v q8_0` under flash attention at the exact 34,816
  B/token (the `GGML_CUDA_FA_ALL_QUANTS` door), so a build decision must be
  proven by the KV buffer line in the boot ledger, not by the build flags you
  remember passing.
 **Ops**
@@ -1097,8 +1138,8 @@ Active:
 | Service | Runbook |
 |---------|---------|
 | frank-dragoon (flash-server 0.16.2, abliterated Swift1.5 v2 .hgn + MTP always-on, 2×262,144, vision ON, Dankclaw) | `serverAppConfigs-docs/LLM/frank-dragoon-flash-server-v2-swift15.md` |
-| frank-zealot (llama.cpp CUDA, Qwen3.5-9B-Uncensored Q6_K, 2×200,704 exact f16 KV MTP-off, vision ON, Dankclaw) | `serverAppConfigs-docs/LLM/frank-zealot-llama-qwen35-9b-q6k-2x200704.md` |
+| frank-zealot (llama.cpp PrismML fork, Bonsai-2-27B PQ2_0, 2×200,704 q8_0 KV MTP-off, vision ON, Dankclaw) | `serverAppConfigs-docs/LLM/frank-zealot-llama-prism-bonsai2-pq20.md` |
-| frank-archon (radiance StillDeadcode, Qwen3.8-Flash-Next-FP8 native, 2×R9700 TP=2, Dankserver) | `serverAppConfigs-docs/LLM/frank-archon-radiance-qwen38-native-fp8.md` |
+| frank-archon (radiance StillDeadcode, publisher Qwen3.8-Flash-Next iq4r .rad, 2×R9700 TP=2, Dankserver) | `serverAppConfigs-docs/LLM/frank-archon-radiance-qwen38-iq4r.md` |
 | Dankclaw kernel posture (`amd_iommu=off`) | `serverAppConfigs-docs/LLM/dankclaw-iommu-translation-off.md` |
 | Deployment flow + incidents | `serverAppConfigs-docs/LLM/deployment.md` |
@@ -1106,6 +1147,8 @@ Retired (rollback targets and history):
 | Runtime | Host | Window | Runbook |
 |---------|------|--------|---------|
 | radiance Swift1.5-Qwen3.8-Flash-Next GPTQ w4dn8, 3×200,000 fp8-KV slab 25600 (`frank-archon`) | Dankserver | 2026-10-08 → 10-15 (rollback target — `.rad` on disk; owns the slab-slope ladder, KV dtype law, KLD campaign, and every shape law the iq4r swap carried verbatim) | `frank-archon-radiance-swift15-w4dn8.md` |
 | llama.cpp CUDA (master) Qwen3.5-9B-Uncensored Q6_K, 2×200,704 exact f16 KV MTP-off (`frank-zealot`) | Dankclaw | 2026-10-07 → 10-17 (rollback target — payload + master CUDA build on disk; owns the 32 KiB/token 8-full-layer KV law and the 2→3-slot reslice law) | `frank-zealot-llama-qwen35-9b-q6k-2x200704.md` |
 | llama.cpp CUDA Gemma4-26B-A4B QAT Q4_K_M, 1×200,704 f16-K/q8_0-V MTP-off (`frank-zealot`) | Dankclaw | 2026-10-07 → 10-07 (same-day swap; rollback target — payload on disk; owns the `attention_k_eq_v` pair-billing KV law and the gemma4-assistant drafter-cost boots) | `frank-zealot-llama-gemma4-q4km-200704.md` |
 | ROCmFPX llama.cpp fork Qwen3.8-27B Uncensored Q6_0_ROCMFPX_AGENT + MTP (`frank-dragoon`) | Dankclaw | 2026-10-03 → 10-05 (rollback target, payload + fork build on disk) | `frank-dragoon-rocmfpx-q6agent-uncensored-mtp.md` |
 | tcclaviger vLLM fork Qwen3.8-Flash-Next-Uncensored FP8, TP=2, shape G (`frank-archon`) | Dankserver | 2026-09-29 → 10-05 (rollback target — tag `frank-archon-vllm-shapeG-20261003`; trio + env lore in the tag, image in rootless storage) | `dankserver-qwen38-fp8-expert-offload-tuning.md` |
@@ -1164,7 +1207,7 @@ history.
 | Unstaged local changes | **Commit or discard** — check `git status` before starting work; ask if unsure. |
 | Deploying a committed change | **`scripts/deploy.sh <target>`** — pushes, pulls ff-only, plans, dispatches, health-checks. |
 | Container without a Quadlet unit | **Give it one** — boot-persistent, self-healing `.container` via git. |
-| Benchmarking | **Not part of a model swap** — swaps verify on the live service. A deliberate bench window: **stop and mask the service first**, bench, unmask, restart, verify health. |
+| Benchmarking | **Stop and mask the service first**, bench, unmask, restart, verify health. |
 | Deleting a file | **Move it to trash** — `.AGENTTRASH/` (in-repo) or `~/.AGENTTRASH/YYYYMMDD-topic`. Never `rm`. |
 | Tests exist | **Run them** — verify tests pass after every change. Do not commit failing tests. |
 | Real secrets | **Never commit** — host `.env` files; `.env.example` holds placeholders only. |
@@ -1,5 +1,16 @@
 # Server App Configs
 ### AI Disclosures:
 - Slop rating: 2/5 - Actively using, actively de-slopping, **repository mostly human owned**, lacks formal process.
 - Completeness: Unfinished, planning planned, no plan yet
 - Datacenter model/spend: Less than $20 of Deepseek 4.1 Flash and GLM-5.3-Flash
 - Local model: Qwen 3.8 Flash Next
 ### slop rating of 2 or lower indicates human reading is a worthwhile exercise, and that Frank has read the code and knows the architecture.
 ### slop rating of 2 indicates that while this project is human owned, no human contribution process exists and/or release is agentically driven.
 The single repository for the two homelab servers: the Podman container
 stacks **and** the LLM inference fleet. One repo, one checkout per host,
 one deploy script.
@@ -1222,23 +1222,26 @@ deploy_llm_dragoon() {
    wait_for_health frank-dragoon http://127.0.0.1:7770/health 1200
 }
-# deploy_llm_zealot — frank-zealot is llama.cpp (master build, CUDA sm_86) on
+# deploy_llm_zealot — frank-zealot is llama.cpp (PrismML fork build) on the
-# the RTX 3090 as a ROOT unit: the runtime is a native binary tree under
+# RTX 3090 as a ROOT unit: the runtime is a native binary tree under
-# ~/GitPackages/llama-master/build-cuda, so there is no container image and
+# ~/GitPackages/llama-prism (vendor release build 10754, commit 2459f68b5 —
-# no generated unit to avoid. relink_unit points
+# the ONLY loader that registers the payload's custom tensor type 142 and
 # reads its prism.hadamard.* metadata), so there is no container image and no
 # generated unit to avoid. relink_unit points
 # /etc/systemd/system/frank-zealot.service at the repo file and boot
 # persistence is that unit's [Install] section.
 #
 # It is a SEPARATE endpoint on port 7771; frank-dragoon keeps 7770. The 3090 is
 # not shared: frank-dragoon's engine runs on the gfx1151 iGPU.
-LLM_ZEALOT_MODEL_FILE="${LLM_ZEALOT_MODEL_FILE:-/home/dank/models/Qwen35-9B-HauhauCS-Q6K/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf}"
+LLM_ZEALOT_MODEL_FILE="${LLM_ZEALOT_MODEL_FILE:-/home/dank/models/Bonsai2-PQ2_0/Ternary-Bonsai-2-27B-PQ2_0.gguf}"
-LLM_ZEALOT_RUNTIME="${LLM_ZEALOT_RUNTIME:-/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
+LLM_ZEALOT_RUNTIME="${LLM_ZEALOT_RUNTIME:-/home/dank/GitPackages/llama-prism/llama-server}"
-# The projector IS the vision capability here: the model is natively
+# The projector IS the vision capability here: the Bonsai-2 text file carries
-# multimodal and the Q6_K file carries no vision tensors — the publisher ships
+# no vision tensors, so the publisher's own mmproj (Qwen3-VL tower, 27 blocks,
-# its own BF16 projector in the same repo, so a deploy that starts without
+# 768 px, qwen3vl_merger, 629,246,976 B) is the whole image path — a deploy
-# this file silently ships a text-only endpoint. Checked unconditionally, like
+# that starts without it silently ships a text-only endpoint. Checked
-# frank-dragoon's.
+# unconditionally, like frank-dragoon's. Its 873.10 MiB worst-case VRAM lands
-LLM_ZEALOT_MMPROJ="${LLM_ZEALOT_MMPROJ:-/home/dank/models/Qwen35-9B-HauhauCS-Q6K/mmproj-Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf}"
+# AFTER the engine's fit check, so it is not inside the q8_0 budget.
 LLM_ZEALOT_MMPROJ="${LLM_ZEALOT_MMPROJ:-/home/dank/models/Bonsai2-PQ2_0/Ternary-Bonsai-2-27B-mmproj-Q8_0.gguf}"
 deploy_llm_zealot() {
    # Refuse rather than restart-loop: a unit whose runtime or payload is
@@ -1246,15 +1249,15 @@ deploy_llm_zealot() {
    # endpoint dark with nothing in the log to say why.
    if [[ ! -x "$LLM_ZEALOT_RUNTIME" ]]; then
        echo "ERROR: llama.cpp runtime absent at $LLM_ZEALOT_RUNTIME" >&2
-        echo "frank-zealot: build it (cmake -B build-cuda -DGGML_CUDA=ON" >&2
+        echo "frank-zealot: fetch the PrismML fork release build (build 10754," >&2
-        echo "frank-zealot: -DCMAKE_CUDA_ARCHITECTURES=86 -DCMAKE_CUDA_HOST_COMPILER=/usr/bin/gcc-13" >&2
+        echo "frank-zealot: commit 2459f68b5) into ~/GitPackages/llama-prism first —" >&2
-        echo "frank-zealot: && cmake --build build-cuda --target llama-server) first." >&2
+        echo "frank-zealot: stock llama.cpp refuses the payload's custom tensor type 142." >&2
        return 1
    fi
    for f in "$LLM_ZEALOT_MODEL_FILE" "$LLM_ZEALOT_MMPROJ"; do
        if [[ ! -f "$f" ]]; then
            echo "ERROR: frank-zealot payload file absent at $f" >&2
-            echo "frank-zealot: run scripts/download-frank-zealot.sh first;" >&2
+            echo "frank-zealot: run scripts/download-frank-zealot-bonsai2.sh first;" >&2
            echo "frank-zealot: refusing to start a unit that cannot load." >&2
            return 1
        fi
@@ -1277,11 +1280,14 @@ deploy_llm_zealot() {
 }
 # deploy_llm_archon — frank-archon is the radiance engine (StillDeadcode,
-# digest-pinned stilldeadcode/radiance image) serving the OFFICIAL
+# digest-pinned stilldeadcode/radiance image) serving the PUBLISHER's
-# Qwen/Qwen3.8-Flash-Next-FP8 at native block-FP8 precision from the
+# 4-bit-codebook container of the official Qwen/Qwen3.8-Flash-Next
-# rad-convert container qwen4exp-fp8-native.rad, on BOTH R9700s (TP=2) as a
+# (qwen3.8-next-flash-fp8-iq4r-moe.rad, fetched by
 # scripts/download-frank-archon-iq4r.sh) on BOTH R9700s (TP=2) as a
 # ROOT unit whose serve script drives `podman run` directly (the engine is
 # the image entrypoint; the image lives in dank's rootless podman storage).
 # 2026-10-15 payload swap from the in-house w4dn8 (payload on disk =
 # rollback).
 # 2026-10-05 cutover from FreeToken (pre-cutover tag
 # frank-archon-freetoken-pr587-20261005); before that, the tcclaviger vLLM
 # fork (tag frank-archon-vllm-shapeG-20261003). Same port and alias; the
@@ -1290,7 +1296,7 @@ deploy_llm_zealot() {
 # Gates: the image must exist under its digest ref in dank's rootless
 # storage (FRANK_ARCHON_IMAGE), the .rad container file must exist at the
 # env's size floor (FRANK_ARCHON_MODEL_FILE >= FRANK_ARCHON_RAD_MIN_MIB —
-# a truncated convert is a guaranteed long-timeout boot), and the unit env
+# a truncated fetch is a guaranteed long-timeout boot), and the unit env
 # must be complete. Per-file sha256 verification is the fetch script's job
 # at download time and rad-convert/rad-info's job at build time, never
 # re-hashed here.
@@ -1325,13 +1331,13 @@ deploy_llm_archon() {
    fi
    if [[ ! -f "$model_dir/$model_file" ]]; then
        echo "ERROR: .rad container missing: $model_dir/$model_file" >&2
-        echo "frank-archon: run scripts/build-frank-archon-rad.sh" >&2
+        echo "frank-archon: run scripts/download-frank-archon-iq4r.sh --fetch" >&2
        return 1
    fi
    mib=$(( $(stat -c %s "$model_dir/$model_file") / 1048576 ))
    if [[ "$mib" -lt "$rad_min" ]]; then
        echo "ERROR: .rad container too small: $model_dir/$model_file is ${mib} MiB, want >= $rad_min" >&2
-        echo "frank-archon: rebuild it (scripts/build-frank-archon-rad.sh --force)" >&2
+        echo "frank-archon: re-fetch it (scripts/download-frank-archon-iq4r.sh --fetch; delete the staged file first if its sha256 failed)" >&2
        return 1
    fi
@@ -0,0 +1,83 @@
 #!/usr/bin/env bash
 # download-frank-archon-iq4r.sh — payload fetch/verify for the frank-archon
 # swap to the PUBLISHER's 4-bit-codebook container:
 # StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe — the official
 # Qwen/Qwen3.8-Flash-Next bf16 checkpoint rad-converted by the engine's own
 # author into ONE .rad: routed experts as 4-bit codes into a 16-level
 # non-uniform codebook (Walsh–Hadamard rotation, GPTQ + coordinate-descent,
 # 10M-token calibration), ten bf16-protected experts per layer, int8 trunk +
 # lm_head, fp8 HC mixtures, the PLE n-gram table at fp8 fixed scale, the MTP
 # head, and the bf16 vision tower. File:
 # qwen3.8-next-flash-fp8-iq4r-moe.rad — 121,969,901,568 B (113.6 GiB,
 # 116,322 MiB), card KL 0.0789 all-tokens / top-1 92.85 % vs bf16.
 # Repo is UNGATED — no token needed (never put one on the command line).
 #
 #   bash scripts/download-frank-archon-iq4r.sh --fetch         resume/complete
 #   bash scripts/download-frank-archon-iq4r.sh                 verify only
 #
 # Fetch uses the vendored scripts/hfget.sh (curl+jq only): per-file size
 # checks against the Hub listing, `-C -` resume, disk-fit gate. The side
 # files (LICENSE, README, the w4nl recipe) stay in the staging dir as
 # provenance; the serve gate mounts ONLY /home/dank/models/rad, so the
 # verified .rad alone moves into it.
 #
 # Verify (default) is the AGENTS.md law in two parts: the file lands at the
 # final path with the Hub's EXACT byte count, and its sha256 equals the
 # Hub's LFS oid. A truncated transfer is a guaranteed long-timeout boot
 # without this gate.
 set -euo pipefail
 REPO="StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe"
 RAD_NAME="qwen3.8-next-flash-fp8-iq4r-moe.rad"
 STAGE="/home/dank/models/StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe"
 DEST="/home/dank/models/rad/$RAD_NAME"
 SIZE=121969901568
 SHA256="0af5e96244e80c21ac8edca1719dae49b8a201b94a2f3994c3e24026ceaa4d20"
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 mode="verify"
 [[ "${1:-}" == "--fetch" ]] && mode="fetch"
 if [[ "$mode" == "fetch" ]]; then
    # HFGET_JOBS=4 is hfget's default (a few streams saturate the link).
    bash "$SCRIPT_DIR/hfget.sh" "$REPO" "$STAGE" main
    staged="$STAGE/$RAD_NAME"
    if [[ ! -f "$staged" ]]; then
        echo "FETCH FAILED: $staged absent after hfget" >&2
        exit 1
    fi
    got=$(stat -c %s "$staged")
    if [[ "$got" != "$SIZE" ]]; then
        echo "FETCH FAILED: staged .rad is $got B, want $SIZE B" >&2
        exit 1
    fi
    echo "staged .rad byte-exact ($SIZE B); hashing (one full read, minutes)"
    got_sha=$(sha256sum "$staged" | cut -d' ' -f1)
    if [[ "$got_sha" != "$SHA256" ]]; then
        echo "FETCH FAILED: sha256 $got_sha, want $SHA256 — DELETE the staged" \
             "file before re-fetching (curl -C - cannot repair a corrupt body)" >&2
        exit 1
    fi
    mkdir -p "$(dirname "$DEST")"
    mv "$staged" "$DEST"
    echo "payload placed: $DEST"
 fi
 echo "verifying deployed payload: $DEST"
 if [[ ! -f "$DEST" ]]; then
    echo "  BAD  payload absent: $DEST" >&2
    exit 1
 fi
 got=$(stat -c %s "$DEST")
 if [[ "$got" != "$SIZE" ]]; then
    echo "  BAD  payload is $got B, want $SIZE B" >&2
    exit 1
 fi
 echo "byte-exact ($SIZE B); hashing (one full read, minutes)"
 got_sha=$(sha256sum "$DEST" | cut -d' ' -f1)
 if [[ "$got_sha" != "$SHA256" ]]; then
    echo "  BAD  sha256 $got_sha, want $SHA256" >&2
    exit 1
 fi
 echo "payload verified: $RAD_NAME, size and sha256 match the Hub LFS oid"
@@ -0,0 +1,93 @@
 #!/usr/bin/env bash
 # Fetch candidate payload for frank-zealot: prism-ml/Ternary-Bonsai-2-27B-gguf
 # at **PQ2_0** (the ternary g128 pack stored 2 bits/trit + fp16 scale per 128)
 # plus the publisher's Q8_0 vision projector. Public repo — no auth header,
 # and never a token on the command line (world-readable in /proc/<pid>/cmdline).
 #
 # Why PQ2_0 and not PTQ1_0: measured on the same silicon family (community
 # 3090 Ti report, PrismML-Eng/Bonsai-demo) PTQ1_0 is ~17 % slower decode and
 # ~48 % slower prefill than PQ2_0 on Ampere; the model card says the same
 # (PTQ1_0 wins only on Ada/L4). The pack is consumed packed — 6.71 GiB
 # resident, never expanded to f16.
 #
 # Header facts (HTTP range parse, not the card): arch qwen35, 64 blocks,
 # full_attention_interval 4 => 16 full-attention + 48 Gated DeltaNet layers,
 # 4 KV heads x 256 dim, native 262,144, vocab 248,320, and NO nextn/mtp
 # tensors (block_count is 64 real layers) — so in-file MTP is impossible and
 # SPEC_TYPE=none is forced by the payload. 402 tensors carry the custom type
 # id 142 (GGML_TYPE_PQ2_0, group 128): STOCK llama.cpp refuses this file, and
 # loads the repo's F16 file silently with garbage output — only the
 # PrismML-Eng/llama.cpp fork applies the prism.hadamard.* activation
 # transform declared in this file's metadata.
 #
 # These ARE LFS files (unlike the HauhauCS payload): the Hub publishes the
 # oid, and both shas below are the Hub's LFS sha256. The mmproj sha has also
 # been recomputed locally against the copy in /home/dank/models/Bonsai2-CRACK/.
 #
 # NOT pinned by this script: /home/dank/models/Bonsai2-CRACK/
 # Bonsai-2-27B-PQ2_0-CRACK.gguf (7,206,168,928 B, sha256 5b24ea3eebc3e0bc...,
 # fetched 2026-10-06 by an undocumented ad-hoc path). Same size as the
 # official file, different bytes — a dealign/CRACK (uncensored) variant of the
 # same ternary pack. Provenance unverified; it is a candidate arm, not this
 # script's payload.
 #
 # Usage:
 #   scripts/download-frank-zealot-bonsai2.sh [DEST_DIR] [--verify-only]
 set -euo pipefail
 DEST=""
 VERIFY_ONLY=0
 for arg in "$@"; do
    case "$arg" in
        --verify-only) VERIFY_ONLY=1 ;;
        *) DEST="$arg" ;;
    esac
 done
 DEST="${DEST:-/home/dank/models/Bonsai2-PQ2_0}"
 # repo | hub-name | dest-name | bytes | sha256 (Hub LFS oid)
 FILES=(
  "prism-ml/Ternary-Bonsai-2-27B-gguf|Ternary-Bonsai-2-27B-PQ2_0.gguf|Ternary-Bonsai-2-27B-PQ2_0.gguf|7206168928|3907dc1658db1f78a9826bf8d5bcb8dc65db0d466388937af57f2294fae62ec1"
  "prism-ml/Ternary-Bonsai-2-27B-gguf|Ternary-Bonsai-2-27B-mmproj-Q8_0.gguf|Ternary-Bonsai-2-27B-mmproj-Q8_0.gguf|629246976|6807ede61d570bb86ba34b756a0fa109edc33668604de867c6ea6d8f1d631903"
 )
 mkdir -p "$DEST"
 status=0
 for entry in "${FILES[@]}"; do
  IFS='|' read -r repo hubname destname size sha <<<"$entry"
  url="https://huggingface.co/${repo}/resolve/main/${hubname}"
  f="$DEST/$destname"
  if [[ -f "$f" ]] && [[ "$(stat -c%s "$f")" == "$size" ]] \
     && sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
    echo "OK        $destname"
    continue
  fi
  if (( VERIFY_ONLY )); then
    echo "MISSING   $destname"
    status=1
    continue
  fi
  echo "FETCHING  $destname (from $repo)"
  tmp="$f.part"
  # No resume: `curl -C -` once produced an oversized file on a 31 GiB
  # payload. -f/--fail-with-body so an HTTP 401/403 body is never a success.
  curl -fsSL --fail-with-body --retry 3 --retry-delay 5 -o "$tmp" "$url"
  mv "$tmp" "$f"
  if [[ "$(stat -c%s "$f")" != "$size" ]]; then
    echo "SIZE FAIL $destname ($(stat -c%s "$f") != $size)"
    status=1
    continue
  fi
  if ! sha256sum -c --quiet <(printf '%s  %s\n' "$sha" "$f"); then
    echo "SHA FAIL  $destname"
    status=1
    continue
  fi
  echo "VERIFIED  $destname"
 done
 if (( status == 0 )); then
  echo "DOWNLOAD_DONE $DEST"
 else
  echo "DOWNLOAD_FAILED $DEST" >&2
 fi
 exit "$status"
@@ -1,7 +1,15 @@
-# frank-archon.env — radiance (StillDeadcode, Apache-2.0) serving
+# frank-archon.env — radiance (StillDeadcode, Apache-2.0) serving the
-# ukisai/Swift1.5-Qwen3.8-Flash-Next converted to GPTQ w4 (MODEL_FILE below,
+# PUBLISHER's 4-bit-codebook container of the official Qwen/Qwen3.8-Flash-Next
-# built by scripts/convert-swift15-w4dn8.sh) on BOTH R9700s (TP=2),
+# (MODEL_FILE below, fetched by scripts/download-frank-archon-iq4r.sh) on
-# dankserver :7770.
+# BOTH R9700s (TP=2), dankserver :7770.
 # 2026-10-15 PAYLOAD SWAP: the model moved from the in-house w4dn8 conversion
 # of the Swift1.5 finetune to the engine author's published container
 # qwen3.8-next-flash-fp8-iq4r-moe.rad (116,322 MiB, sha256-verified at fetch —
 # the w4dn8 measured 116,416 MiB, so this shape carries over with 94 MiB to
 # spare). NO argument changed: every number below is the 2026-10-13 shape,
 # kept verbatim. The swap commit is the rollback (the w4dn8 payload stays on
 # disk).
 #
 # SHAPE (2026-10-13): THREE decode slots x 200,000 tokens, fp8 (quantized) KV,
 # with the per-card budget spent on resident experts: 25,600 MiB of slab +
@@ -13,9 +21,11 @@
 # +25 % at the full window) while KV beyond the contract buys nothing.
 # Consequence, deliberate: a FOURTH full-height conversation does not fit this
 # pair, and the engine refuses it — it never truncates. See the KV block for the
-# arithmetic and the measured dtype law. The fp8-native payload this file was
+# arithmetic and the measured dtype law. The w4dn8 payload is the swap
-# written for is the rollback target and keeps its own trio under the
+# rollback and keeps its trio under the w4dn8 runbook; the fp8-native payload
-# fp8-native runbook.
+# that came before it was DELETED from disk 2026-10-15 (Frank's call, to free
 # the volume for this download — rebuildable via the fetch + build scripts
 # named in the fp8-native runbook).
 #
 # 2026-10-05 cutover from FreeToken (PR #587 ROCm, one card, experts in
 # pinned host RAM; git tag frank-archon-freetoken-pr587-20261005 is the
@@ -30,20 +40,30 @@
 # (`X.weight_scale_inv` is the scale plane — checkpoint.h). The PLE n-gram
 # table (51B params, 47.7 GiB) is served from pinned host RAM via io_uring
 # reads — Frank's call: "Native FP8. Experts from ram. Pin the PLE to ram."
-# The 4-bit-codebook publisher shape (qwen3.8-next-flash-fp8-iq4r-moe.rad,
+# THE 4-bit-codebook publisher shape is the DEPLOYED payload since
-# --host-pool-mib 12288) remains the documented fallback if the native
+# 2026-10-15. The card's own run line (--host-pool-mib 12288,
-# container proves unbootable.
+# --expert-vs-cache-ratio 0.82, seqs 8, spec 3) is the publisher's
 # suggestion on 32 GB cards; this file's shape is the fleet's measured one.
 #
-# PAYLOAD: /home/dank/models/rad/qwen4exp-fp8-native.rad — a rad-convert
+# PAYLOAD: /home/dank/models/rad/qwen3.8-next-flash-fp8-iq4r-moe.rad — the
-# NO-RECIPE pure copy of the official 131-shard checkpoint (every weight
+# official Qwen3.8-Flash-Next bf16 checkpoint rad-converted by the engine's
-# keeps its block-FP8 encoding; ~161 GiB). The convert runs against a
+# own author (recipe qwen4exp-w4nl64-i8-hc8m: experts as 4-bit codes into a
-# staging dir whose config.json drops `quantization_config`: the descriptor
+# 16-level non-uniform codebook after a 128-point Walsh–Hadamard rotation,
-# string is only the plugin SELECTION key (spec §2.4 — exact match, no
+# GPTQ + 3 coordinate-descent sweeps on a 10M-token calibration, ten
-# fallback), and no shipped plugin claims (qwen4exp, "fp8"); the shipped
+# bf16-protected experts per layer, int8 W8A8 trunk + lm_head, fp8 HC
-# qwen4exp plugin claims (qwen4exp, "") which is what recipe-built
+# mixtures, PLE n-gram fp8 fixed-scale, MTP head, bf16 vision tower; card KL
-# containers carry. Per-weight encodings are data, not the descriptor —
+# 0.0789 all-tokens / top-1 92.85 % vs bf16). Fetched byte-exact + sha256 by
-# removing the key changes nothing about what the weights hold. Built by
+# scripts/download-frank-archon-iq4r.sh; the recipe/LICENSE stay in the
-# scripts/build-frank-archon-rad.sh (staging + convert + rad-info).
+# staging dir beside it as provenance. ROLLBACK: revert the swap commit — the
 # in-house qwen4exp-swift15-w4dn8-i8-hc8m.rad (scripts/convert-swift15-w4dn8.sh,
 # KLD-gated) stays on disk. Behind it, the fp8-native
 # qwen4exp-fp8-native.rad was DELETED from disk 2026-10-15 (Frank's call,
 # one-time rm, to free the volume for this payload); rebuild =
 # scripts/download-frank-archon.sh + scripts/build-frank-archon-rad.sh — a
 # NO-RECIPE rad-convert copy of the official 131-shard checkpoint under the
 # descriptor law (no shipped plugin claims (qwen4exp, "fp8"), so the staging
 # config.json drops quantization_config; per-weight encodings are data, not
 # the descriptor).
 #
 # SERVING FACTS (docs/GUIDE.md, docs/DOCKER.md, compose/flashnext.yaml):
 # - The HTTP listener binds AFTER the full load (main.cpp: engine.start()
@@ -59,12 +79,12 @@
 #   enable_thinking, preserve_thinking (core/server/oai.cpp:194-205) —
 #   models.yml's extraBody set is fully inside it. Unknown params are
 #   refused (400), which is why nothing unverified rides the wire.
-# - MTP: the official checkpoint carries the mtp.* head (3,101 tensors,
+# - MTP: the .rad carries the model's mtp.* head (the publisher's recipe
-#   mtp_num_hidden_layers=1) and the plugin probes draft depth 3 — the
+#   names the mtp.fc_hidden/fc_embedding/draft_head rules; card default
-#   publisher's throughput peak for this model. Stated explicitly with
+#   depth 3). Served at the depth named by FRANK_ARCHON_SPEC_TOKENS below —
-#   --num-speculative-tokens 3.
+#   the depth this shape's decode ladder was measured at.
 # - The fused TP all-reduce is declared over max-num-seqs x
-#   (1 + --num-speculative-tokens) rows; 2 x 3 = 6 rows, under the 25-row
+#   (1 + --num-speculative-tokens) rows; 3 x (1+2) = 9 rows, under the 25-row
 #   exactness bound of the wht6 wire.
 # Engine pin: Codeberg tag v1.0.13 (commit 53282fa), Docker Hub tag 1.0.13,
 # index digest below. REJECTED UPGRADE: 1.2.0 (sha256:665775ed1d90de6dbb
@@ -88,7 +108,7 @@ FRANK_ARCHON_IMAGE=stilldeadcode/radiance@sha256:4c3f484564bb2872784e46b0a59cbd7
 # .rad files; the raw HF download and its staging dir live beside it and
 # are never mounted.
 FRANK_ARCHON_MODEL_DIR=/home/dank/models/rad
-FRANK_ARCHON_MODEL_FILE=qwen4exp-swift15-w4dn8-i8-hc8m.rad
+FRANK_ARCHON_MODEL_FILE=qwen3.8-next-flash-fp8-iq4r-moe.rad
 FRANK_ARCHON_STATE_DIR=/home/dank/radiance-state
 # The state dir's tune/ subdirectory holds rad-tune's kernel-selection
 # cache (the engine's selector reads $RADIANCE_HOME/tune/<machine>.tune
@@ -242,9 +262,10 @@ FRANK_ARCHON_VRAM_KV_MIB=5120
 # ledgers' `kv tier transfer` lines), so the host tier below parks twice as
 # many conversations as it did at bf16 — no re-size needed to park three slots.
 FRANK_ARCHON_KV_DTYPE=fp8
-# Spec decode: the checkpoint's own MTP head at the publisher's depth-3
+# Spec decode: the checkpoint's own MTP head, served at depth 2 — the
-# operating point (probe() returns 3 when mtp_num_hidden_layers > 0; the
+# publisher's card ships depth 3 as its peak; this fleet's ladder was
-# flag states it so the ledger records the intent).
+# measured at 2 and the swap keeps every argument, so 2 stays (rows
 # 3 x (1+2) = 9, inside the wht6 25-row exactness bound).
 FRANK_ARCHON_SPEC_TOKENS=2
 FRANK_ARCHON_MAX_BATCHED_TOKENS=2048
 # Prefix cache tiers (publisher pattern). The host tier is sized in ENTRIES,
@@ -278,9 +299,8 @@ FRANK_ARCHON_TTM_TARGET_MIB=204800
 # multi-flag values as one string; the serve script expands it unquoted on
 # purpose.
 FRANK_ARCHON_EXTRA_ARGS=
-# The .rad's minimum size in MiB (deployer gate; a truncated convert is a
+# The .rad's minimum size in MiB (deployer gate; a truncated fetch is a
-# guaranteed long-timeout boot instead of a fast failure). The converted
+# guaranteed long-timeout boot instead of a fast failure). The deployed
-# container measured 177,109 MiB (1,857,127,997,440 B = 173.0 GiB; the
+# publisher container measures 116,322 MiB (121,969,901,568 B); the
-# plan-only estimate 172.76 GiB covers the data planes but not the metadata
+# in-house w4dn8 rollback measured 116,416 MiB. Floor sits just under both.
 # tail) - floor sits just under the payload.
 FRANK_ARCHON_RAD_MIN_MIB=110000
@@ -1,9 +1,9 @@
 # frank-archon.service — radiance (StillDeadcode, Apache-2.0) endpoint
-# (OFFICIAL Qwen/Qwen3.8-Flash-Next-FP8 at NATIVE block-FP8 precision, the
+# (the publisher's 4-bit-codebook container of the official
-# rad-convert container qwen4exp-fp8-native.rad) on BOTH R9700s (TP=2,
+# Qwen/Qwen3.8-Flash-Next, qwen3.8-next-flash-fp8-iq4r-moe.rad, fetched by
-# wht6 wire), dankserver :7770. 2026-10-05 cutover from FreeToken (git tag
+# scripts/download-frank-archon-iq4r.sh) on BOTH R9700s (TP=2, wht6 wire),
-# frank-archon-freetoken-pr587-20261005 is the pre-cutover state; the
+# dankserver :7770. 2026-10-15 payload swap from the in-house w4dn8 (the
-# retired unit/env/serve trio and Dockerfile are in that tag).
+# swap commit is the revert; its .rad stays on disk).
 #
 # Same port, same served alias, same container identity as the unit name;
 # the harness models.yml id is unchanged. The serve script drives
@@ -19,7 +19,7 @@
 # unit grants LimitMEMLOCK=infinity to the dank process via PID1; the
 # engine still runs out of dank's rootless podman storage.
 [Unit]
-Description=frank-archon — radiance Qwen3.8-Flash-Next-FP8 (native) on 2x R9700 TP=2
+Description=frank-archon — radiance Qwen3.8-Flash-Next (publisher iq4r) on 2x R9700 TP=2
 After=network-online.target
 Wants=network-online.target
 # Never let the start-rate limiter give up after a crash loop (a failed LLM
@@ -1,59 +1,69 @@
-# frank-zealot — llama.cpp (master, CUDA sm_86) serving
+# frank-zealot — llama.cpp (PrismML fork build, CUDA) serving
-# HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive at Q6_K on the RTX 3090,
+# prism-ml/Ternary-Bonsai-2-27B-gguf at PQ2_0 on the RTX 3090, :7771.
 # :7771.
 #
-# 2026-10-07 (Frank): swap from Gemma4-26B-A4B QAT Q4_K_M (one 200,704 slot)
+# 2026-10-17 (Frank): swap from Qwen3.5-9B-Uncensored Q6_K to the Bonsai-2-27B
-# to Qwen3.5-9B Q6_K at TWO 200,704-token conversations, EXACT (f16) KV,
+# ternary checkpoint at the SAME shape Frank asked for — TWO 200,704-token
-# MTP disabled (SPEC_TYPE=none), log verbosity 4.
+# conversations — with q8_0 K + q8_0 V (f16 is arithmetically impossible here,
 # see the KV law), MTP off (the file carries no nextn/mtp tensors), verbosity 4.
 #
-# Architecture — read from the GGUF's own header (HTTP range read, not the
+# THE RUNTIME IS A LOCK, NOT A PREFERENCE. The file is general.file_type 141
-# model card): arch qwen35, 32 layers, dense 9B, full_attention_interval 4
+# with 402 tensors of the CUSTOM GGML type 142 (pq2_0) plus prism.hadamard.*
-# ⇒ 8 full-attention layers (3,7,11,...,31) + 24 Gated DeltaNet linear layers,
+# metadata (normalized-Sylvester-Walsh transform, block 1024, 401 named
-# 16 attention heads / 4 KV heads × 256 dim, ssm conv_kernel 4 / state_size
+# weights, inverse on token_embd, gdn_v_grouped). Stock llama.cpp refuses type
-# 128 / group_count 16 / time_step_rank 32 / inner_size 4096, native 262,144,
+# 142 at load; only the PrismML fork registers the type AND reads the Hadamard
-# vocab 248,320, file_type 18 (Q6_K). Tensor-type histogram: Q6_K×250 +
+# metadata. The vendor prebuilt build 10754 (commit 2459f68b5) is what every
-# F32×177 — standard types only, so the stock master build loads it (no
+# number in this file was measured on; sha256 12ae5baba033d8cd…
-# custom-quant lock-in like the ROCmFPX era). NO nextn/mtp tensors exist, so
+LLAMA_BIN=/home/dank/GitPackages/llama-prism/llama-server
-# in-file MTP is impossible here; SPEC_TYPE=none is forced by the payload.
+MODEL_FILE=/home/dank/models/Bonsai2-PQ2_0/Ternary-Bonsai-2-27B-PQ2_0.gguf
 MMPROJ_FILE=/home/dank/models/Bonsai2-PQ2_0/Ternary-Bonsai-2-27B-mmproj-Q8_0.gguf
 # The CRACK re-export (dealignai/Bonsai-2-27B-Ternary-CRACK-GGUF, uncensored,
 # already on disk at /home/dank/models/Bonsai2-CRACK/) is a ONE-LINE swap: the
 # header census proves byte-identical geometry (851 tensors, same
 # {pq2_0:402, f32:353, bf16:96} histogram, 64 blocks, vocab 248,320, same
 # 8,952-char chat template) and the official file's sha256 is the Hub LFS oid.
 # Bonsai-2 is the BASE (censored) Qwen3.8 family; if a compaction or subagent
 # request ever comes back with a refusal, point MODEL_FILE at the CRACK file
 # and restart — the VRAM ledger below does not move.
 #
-# KV rate law: 8 full layers × 4 KV heads × 256 dim = 8,192 elements per
+# Served model id — the harness/family name. The SERVICE, unit, scripts and
-# token per cache. f16 K + f16 V = 32,768 B/token = 32 KiB/token, so the
+# this env file keep the frank-zealot name; only the alias on the wire is the
-# 401,408-token pool is 12.25 GiB. The 24 DeltaNet layers cost a fixed
+# model id. Consumers that key on the served id: OpenWebUI (model row,
-# recurrent state per SLOT (not per token) — that is why two 200k slots fit
+# access_grant, api_configs model_ids) and the harness models.yml.
 # where the 26B MoE fit only one.
 #
 # Feasibility comes from the predecessor's MEASURED boots, not a formula:
 # MiMo-V2.6-Distill-Qwen-9B (identical qwen35 geometry, 7,793,710,624 B) at
 # 2×200,704 f16 K + f16 V measured 21,276 used / 2,849 free at ubatch 1024
 # and 21,846 / 2,279 at ubatch 2048. This file is 415 MiB lighter in weights,
 # its BF16 mmproj is 3 MiB heavier ⇒ projected ~21,430 used / ~2,700 free.
 # The verbosity-4 boot ledger is the referee.
 #
 # Ubatch 2048 is the measured CUDA optimum (measured on the MiMo predecessor
 # at this exact arch + shape: +4.6 % prefill at 8.9k depth, decode flat, cost
 # 616 MiB). 1024 is the fallback rung if the boot lands under the 2 GiB floor.
 LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server
 MODEL_FILE=/home/dank/models/Qwen35-9B-HauhauCS-Q6K/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf
 MMPROJ_FILE=/home/dank/models/Qwen35-9B-HauhauCS-Q6K/mmproj-Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf
 # Served model id — the harness/family name (Protoss rename completed to the
 # wire 2026-10-09: harness ids + homepage cards 2026-10-08, /v1/models aliases
 # this day). The SERVICE, unit, scripts and this env file keep the
 # frank-zealot name; only the alias on the wire changed. Consumers that
 # key on the served id: OpenWebUI (model row, access_grant, api_configs
 # model_ids) and the harness models.yml.
 ALIAS=frank-zealot
 BIND_ADDR=0.0.0.0
 LISTEN_PORT=7771
 # CTX_SIZE is the POOL llama.cpp divides across slots: 401,408 / 2 = 200,704
 # per conversation. MUST stay divisible by PARALLEL (the seam enforces it) and
 # the harness contextWindow quotes the PER-SLOT number — a longer prompt is
-# answered with a 400, never truncated.
+# answered with a 400, never truncated. The model's native window is 262,144;
 # 2 × 262,144 at q8_0 projects 25,758 MiB and does NOT fit this card (measured
 # f16 analogue: 41,118). One 262,144 slot fits with 5,995 MiB free but
 # serializes compaction, so the pair stays.
 CTX_SIZE=401408
 PARALLEL=2
 BATCH_SIZE=4096
 UBATCH_SIZE=2048
-CACHE_TYPE_K=f16
+# KV law (from the GGUF header, then confirmed by the boot ledger): 16
-CACHE_TYPE_V=f16
+# full-attention layers (full_attention_interval 4 over 64 blocks) × 4 KV heads
 # × 256 dim = 16,384 elements per token per cache. q8_0 bills 17,408 B per
 # cache ⇒ 34,816 B/token = 34 KiB, so the 401,408 pool is 13,328.00 MiB — the
 # ledger said exactly that. f16 would bill 25,088 MiB and the boot DIES:
 # `cudaMalloc failed: out of memory` on the 25,088.00 MiB request, engine fit
 # projection 33,198 vs 23,558 free. The 48 DeltaNet layers bill a fixed
 # recurrent state per SLOT — ~150 MiB each (context 13,627 − KV 13,328 = 299
 # for two slots), which is why pool arithmetic alone under-prices the shape.
 CACHE_TYPE_K=q8_0
 CACHE_TYPE_V=q8_0
 # Boot ledger (2026-10-17, this exact shape, nvidia-smi settled):
 #   22,664 MiB used / 1,461 MiB free of 24,123
 #   fit projection 21,439 = 6,539 model + 13,627 context + 1,272 compute
 #   the mtmd projector's 873.10 MiB worst-case is NOT inside that projection —
 #   it lands after the fit check, which is the whole difference between
 #   "2.6 GiB free on paper" and 1.4 GiB free in reality. Watch it.
 # Fallback rung if the margin is ever eaten (desktop, co-tenant): q4_0 KV
 # measured 16,392 used / 7,733 free at the same 2 × 200,704.
 # 1024 is the ubatch fallback (−616 MiB, measured on the 9B predecessor at
 # this card/arch; 2048 was the measured CUDA optimum, +4.6 % prefill).
 SPEC_TYPE=none
 NGL=99
 # Log verbosity threshold (llama.cpp -lv). 4 = debug: KV layout, buffer sizes
@@ -1,5 +1,5 @@
 [Unit]
-Description=llama.cpp Qwen3.5-9B-Uncensored-HauhauCS-Aggressive Q6_K GGUF (qwen35 hybrid, 2x200704 slots, f16 K+V, MTP off, mmproj vision) on the RTX 3090 (dankclaw, frank-zealot)
+Description=llama.cpp (PrismML build 10754) Ternary-Bonsai-2-27B PQ2_0 GGUF (qwen35 hybrid, 2x200704 slots, q8_0 K+V, MTP off, mmproj vision) on the RTX 3090 (dankclaw, frank-zealot)
 After=network-online.target
 Wants=network-online.target
@@ -1,11 +1,13 @@
 #!/usr/bin/env bash
 # serve-frank-archon.sh — frank-archon endpoint: radiance (StillDeadcode,
-# Apache-2.0) serving the OFFICIAL Qwen/Qwen3.8-Flash-Next-FP8 checkpoint at
+# Apache-2.0) serving the PUBLISHER's 4-bit-codebook container of the
-# NATIVE block-FP8 precision from a rad-convert container
+# official Qwen/Qwen3.8-Flash-Next (the engine author's own rad-convert of
-# (/home/dank/models/rad/qwen4exp-fp8-native.rad), on BOTH R9700s (TP=2,
+# the bf16 checkpoint: qwen3.8-next-flash-fp8-iq4r-moe.rad, fetched by
-# wht6 wire), dankserver :7770. 2026-10-05 cutover from FreeToken (PR #587,
+# scripts/download-frank-archon-iq4r.sh) on BOTH R9700s (TP=2, wht6 wire),
-# one card; git tag frank-archon-freetoken-pr587-20261005 is the
+# dankserver :7770. 2026-10-15 payload swap from the in-house w4dn8 of the
-# pre-cutover state).
+# Swift1.5 finetune (payload on disk = rollback; the swap commit is the
 # revert); 2026-10-05 radiance cutover from FreeToken (git tag
 # frank-archon-freetoken-pr587-20261005 is the pre-radiance state).
 #
 # The run line below IS the engine argv: the image's entrypoint is the
 # engine and its tools sit beside it on PATH. Unlike every predecessor
@@ -1,28 +1,30 @@
 #!/usr/bin/env bash
-# Serve HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive (Q6_K) as
+# Serve prism-ml/Ternary-Bonsai-2-27B (PQ2_0 ternary quant) as frank-zealot on
-# frank-zealot on Dankclaw's RTX 3090 via llama.cpp (master build, CUDA sm_86).
+# Dankclaw's RTX 3090 via llama.cpp (PrismML vendor build 10754, CUDA sm_86).
 #
-# 2026-10-07 (Frank): Qwen3.5-9B swap at TWO 200,704-token conversations
+# 2026-10-17 (Frank): Bonsai-2 PQ2_0 swap at TWO 200,704-token conversations
-# (--ctx-size 401408 --parallel 2) with EXACT f16 KV — the 9B rung frees the
+# (--ctx-size 401408 --parallel 2) with q8_0 K + q8_0 V — f16 KV does not fit
-# room the 26B MoE Gemma4 shape lacked, so quantized V retires. MTP stays off:
+# this geometry: the engine's own fit projected 33,198 MiB against 23,558 free
-# this GGUF carries no MTP tensors at all (verified from its tensor-name
+# and cudaMalloc failed on the 25,088 MiB pool. MTP stays off: this GGUF
-# list), so there is no in-file head to draft with. Verbosity 4 ships so the
+# carries no MTP tensors (verified from its tensor-name list). Verbosity 4
-# VRAM-fit forensics (KV layout, buffer sizes, graph capture) land in the journal.
+# ships so the VRAM-fit forensics (KV layout, buffer sizes, graph capture)
 # land in the journal.
 #
-# Architecture: qwen35 — dense 9B, 32 layers with full_attention_interval 4
+# Architecture: qwen35 — 27B, 64 blocks with full_attention_interval 4 (16
-# (8 full-attention layers at 3,7,...,31 + 24 Gated DeltaNet linear layers),
+# full-attention layers + 48 Gated DeltaNet linear layers), 24 heads / 4 KV
-# 16 heads / 4 KV heads × 256 dim, native 262,144, vocab 248,320. The KV pool
+# heads × 256 dim, native 262,144, vocab 248,320. The KV pool scales with the
-# scales with the 8 full layers: 32 KiB/token at f16 K + f16 V (12.25 GiB at
+# 16 full layers: 34 KiB/token at q8_0 K + q8_0 V (13,328 MiB at the 401,408
-# the 401,408 pool); the DeltaNet layers cost a fixed recurrent state per
+# pool); the DeltaNet layers cost a fixed recurrent state per SLOT (~150 MiB —
-# slot. Feasibility is priced from the MiMo-V2.6-Distill-Qwen-9B boots (same
+# boot-ledger context minus KV). Boot ledger: 22,664 used / 1,461 free, with
-# geometry, same card, same shape): 21,276/2,849 at ubatch 1024, 21,846/2,279
+# the Q8_0 projector's 873 MiB landing AFTER the engine's fit projection.
-# at ubatch 2048 — the boot ledger, not arithmetic, is the referee.
+# The runtime is a hard lock, not a preference: the file carries 402 tensors
-# Vision comes from the publisher's own BF16 projector (the model is natively
+# of custom GGML type 142 plus prism.hadamard.* metadata, which only the
-# multimodal), so --mmproj is what gives this endpoint eyes; MMPROJ_FILE="" is
+# vendor build registers — stock llama.cpp refuses it at load.
-# the documented text-only opt-out.
+# Vision comes from the publisher's Q8_0 projector, so --mmproj is what gives
 # this endpoint eyes; MMPROJ_FILE="" is the documented text-only opt-out.
 #
-# Sampling: llama.cpp takes it per request (the fleet harness sends the
+# Sampling: llama.cpp takes it per request (the fleet harness sends the file's
-# publisher recipe from models.yml: thinking temp 0.6 / top_p 0.95 / top_k 20).
+# own template defaults from models.yml: thinking temp 1.0 / top_p 0.95 / top_k 20).
 #
 # Tunables come from frank-zealot.env unless FRANK_ZEALOT_ENV_FILE overrides.
 set -euo pipefail
@@ -37,8 +39,8 @@ if [[ -f "$ENV_FILE" ]]; then
 fi
 # --- defaults (used when the env file does not set them) -------------------
-: "${LLAMA_BIN:=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server}"
+: "${LLAMA_BIN:=/home/dank/GitPackages/llama-prism/llama-server}"
-: "${MODEL_FILE:=/home/dank/models/Qwen35-9B-HauhauCS-Q6K/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-Q6_K.gguf}"
+: "${MODEL_FILE:=/home/dank/models/Bonsai2-PQ2_0/Ternary-Bonsai-2-27B-PQ2_0.gguf}"
 : "${ALIAS:=frank-zealot}"
 : "${BIND_ADDR:=0.0.0.0}"
 : "${LISTEN_PORT:=7771}"
@@ -54,19 +56,20 @@ fi
 # throughput-neutral at a fixed ubatch.
 : "${BATCH_SIZE:=4096}"
 : "${UBATCH_SIZE:=2048}"
-# Exact (unquantized) KV: f16 K + f16 V, restoring the MiMo-era contract that
+# Quantized KV: q8_0 K + q8_0 V — the only pair that funds 2 × 200,704 on this
-# the 26B Gemma4 shape could not afford. 32 KiB/token at this geometry
+# card. 34 KiB/token at this geometry (16 full-attention layers × 4 KV heads ×
-# (8 full-attention layers × 4 KV heads × 256 dim); 12.25 GiB at the 401,408
+# 256 dim); 13,328 MiB at the 401,408 pool. f16 measured OOM; q4_0 is the
-# pool. Explicit either way so the contract is visible in the argv, and
+# fallback rung (16,392 used / 7,733 free). Explicit either way so the contract
-# --flash-attn stays required for any quantized-V fallback (q8_0 = llama.cpp's
+# is visible in the argv, and --flash-attn stays required for quantized V
-# FP8 class; no true fp8 KV dtype exists in this build).
+# (no true fp8 KV dtype exists in this build).
-: "${CACHE_TYPE_K:=f16}"
+: "${CACHE_TYPE_K:=q8_0}"
-: "${CACHE_TYPE_V:=f16}"
+: "${CACHE_TYPE_V:=q8_0}"
-# Speculative decoding is OFF: this Q6_K file carries NO nextn/mtp tensors, so
+# Speculative decoding is OFF: this PQ2_0 file carries NO nextn/mtp tensors, so
 # there is no in-file head (the law: MTP is a property of the file, not of the
 # flags). SPEC_TYPE=none strips BOTH speculative flags (flags move as a set);
-# naming a drafter requires SPEC_DRAFT_FILE alongside SPEC_TYPE — the Gemma4
+# an MTP-bearing CRACK re-export exists upstream (ManniX-ITA, +451 MB) if
-# assistant on disk is arch gemma4-assistant and cannot drafter-match qwen35.
+# decode ever needs it — that is a new payload with its own VRAM bill, never a
 # flag flip on this file.
 : "${SPEC_TYPE:=none}"
 : "${SPEC_DRAFT_N_MAX:=3}"
 : "${SPEC_DRAFT_FILE:=}"
@@ -77,7 +80,7 @@ fi
 : "${VERBOSITY:=3}"
 # Vision projector. No colon on purpose: an explicitly empty value means
 # "text-only, on purpose" and must NOT be replaced by the default path.
-: "${MMPROJ_FILE=/home/dank/models/Qwen35-9B-HauhauCS-Q6K/mmproj-Qwen3.5-9B-Uncensored-HauhauCS-Aggressive-BF16.gguf}"
+: "${MMPROJ_FILE=/home/dank/models/Bonsai2-PQ2_0/Ternary-Bonsai-2-27B-mmproj-Q8_0.gguf}"
 # Fail loudly rather than half-loading: a missing file is a download that
 # has not finished, and Restart=always would turn it into a crash loop that
@@ -43,8 +43,10 @@ As of 2026-10-07 the picker exposes **exactly one model: `frank-zealot`**.
 | 2 | `http://host.containers.internal:7771/v1` | yes | `frank-zealot` | llama.cpp CUDA (RTX 3090, 2×200,704) | Dankclaw |
 The `model` table carries exactly one decoration row, `frank-zealot`
-(context length 200,704 = the per-slot window; description: Qwen3.5-9B
+(context length 200,704 = the per-slot window; description since 2026-10-17:
-Q6_K + BF16 vision mmproj).
+Ternary-Bonsai-2-27B PQ2_0 + Q8_0 vision mmproj — the row's `description` is
 live DB state, so a payload swap must re-key it in the database too, not only
 in the repo).
 A third gate sits *after* the table, and it is the one that bites family
 accounts (2026-10-07): a model row is only visible to a non-admin user when
@@ -452,7 +452,8 @@ access is decided entirely by GROUP MEMBERSHIP consumed downstream —
 - `Non-Admin Users` = the plain-user marker group (precedents: qa-e2e, and
  every human account).
 - **The human-user template** (ridley, kassie, alex, artem, kirby, ry, nic,
-  debo, freya — kirby/ry/nic/debo/freya (pk 17–21) created 2026-10-09, kassie
+  debo, freya, mitch, eric — mitch (pk 22) and eric (pk 23) created
  2026-10-15, kirby/ry/nic/debo/freya (pk 17–21) created 2026-10-09, kassie
  and alex created 2026-10-08, artem (pk 16) created 2026-10-07): `username` +
  `<user>@franksdank.cloud` + display name +
  `is_active=True` + the password set via `set_password`, membership in
@@ -3,7 +3,7 @@ type: reference
 title: Model Swap and Rollback
 description: The full model-swap discipline for the LLM fleet — fit preflight, fetch and payload verification, runtime build/flag checks, git-only config, live validation, systemd handoff, close-out, the three-pin revert law, and research-verification discipline.
 tags: [models, swap, gguf, huggingface, rollback, deployment, verification]
-timestamp: 2026-10-15T00:00:00-07:00
+timestamp: 2026-10-05T00:00:00-07:00
 ---
 # Model Swap and Rollback
@@ -12,15 +12,6 @@ Applies to every endpoint swap on the fleet (frank-zealot / frank-dragoon /
 frank-archon). Repo law: all config flows through git; the live models are
 host state under `/home/dank/models/<name>/`.
 **No bench step (law, 2026-10-15).** A model swap NEVER schedules a bench
 window. Performance evidence comes from the deployed service itself: the
 engine's boot ledger, per-request timings (`/completion` `timings`,
 `Server-Timing`), and one real request per harness role (§6, §8). A
 deliberate standalone bench (flag A/B, shape sweep) is OUT OF PROCEDURE —
 a separate operation that follows the AGENTS.md Benchmarking Policy
 (stop & mask). The env-file hook (§5) stays so those out-of-procedure
 arms remain possible.
 ## 1. Fit preflight — never deploy a swap without confirming it FITS
 1. Get the checkpoint's on-disk/weight size AND precision from the HF card
@@ -153,8 +144,7 @@ recoverable, drift is not.
 ## 8. Close-out (mandatory)
 1. Docs: active runbook updated (build recipe, profile, validation numbers
-   incl. real-workload prefill/decode measured on the LIVE service — no
+   incl. real-workload prefill/decode); superseded runbook gets a RETIRED
   bench window); superseded runbook gets a RETIRED
   banner and stays as the rollback record; `LLM/index.md` mermaid + active
   list; AGENTS.md fleet table + runtime section + history chain; work-log
   entry in `serverAppConfigs-docs/log.md`.
@@ -287,6 +277,5 @@ predecessor "stopped" (the port race above).
 - [[GGUF Compatibility]] — which runtime can load a payload at all
 - [[Llama Cpp Serving Sizing]] — pricing the shape once it loads
 - [[RDNA4 MoE Expert Offload VRAM Budget]] — vLLM-side fit arithmetic
- [[LLM Bench Windows and Measurement]] — out-of-procedure bench windows
+- [[LLM Bench Windows and Measurement]] — measuring the new deployment
  only; a new deployment is measured by §6 live validation, not by a bench
 - [[dankserver-qwen38-fp8-expert-offload-tuning]] — the current endpoint
@@ -0,0 +1,144 @@
 # frank-archon — Radiance (StillDeadcode), publisher Qwen3.8-Flash-Next iq4r, 2× R9700 TP=2
 **Status: LIVE — deployed 2026-10-15.** · **Host:** Dankserver (192.168.0.235) · **Port:** 7770 · **GPU:** 2× Radeon AI PRO R9700 (gfx1201), TP=2
 The in-house w4dn8 conversion of the Swift1.5 finetune
 ([[frank-archon-radiance-swift15-w4dn8]]) is replaced by the **engine
 author's published container**:
 [`StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe`](https://huggingface.co/StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe)
 — the official `Qwen/Qwen3.8-Flash-Next` bf16 checkpoint rad-converted by
 StillDeadcode. Same port, alias, container name, systemd unit, digest-pinned
 engine pin **1.0.13** (`stilldeadcode/radiance@sha256:4c3f484564…`), and
 **every serving argument carried verbatim** from the 2026-10-13 shape.
 Rollback: revert the swap commit — the w4dn8 `.rad` stays on disk.
 ## The payload
 `qwen3.8-next-flash-fp8-iq4r-moe.rad` — **121,969,901,568 B = 116,322 MiB**,
 sha256 `0af5e96244e80c21ac8edca1719dae49b8a201b94a2f3994c3e24026ceaa4d20`
 (Hub LFS oid), fetched byte-exact by `scripts/download-frank-archon-iq4r.sh`
 (hfget resume + size + sha256; staging dir
 `/home/dank/models/StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe/` keeps the
 card, LICENSE, and recipe `qwen4exp-w4nl64-i8-hc8m` as provenance).
 | Plane | Encoding (publisher recipe `qwen4exp-w4nl64-i8-hc8m`) |
 | --- | --- |
 | Routed experts | 4-bit codes into a 16-level **non-uniform** codebook after a 128-point Walsh–Hadamard rotation, one E4M3 scale per 64 weights; codes by GPTQ (10M-token calibration, per-expert down-proj Hessians) + 3 coordinate-descent sweeps |
 | Protected experts | **ten** per layer, whole-expert bf16 (down-projection energy) |
 | Trunk + lm_head | int8 W8A8, scale per 128 columns searched; HC mixtures E4M3 |
 | PLE n-gram | fp8 fixed-scale, in-container (served `--ngram-placement ram`, same 47.7 GiB pin law) |
 | Speculator | the model's own MTP head (card default depth 3; served at 2) |
 | Vision | bf16 vision tower, in-container |
 **Base model: the OFFICIAL (censored) Qwen3.8-Flash-Next** — the fleet's
 only frontier model at base alignment; the abliterated family lives on
 frank-dragoon. Card quality: full-vocab teacher-forced KL vs bf16 over
 ~75K positions — mean 0.0789 all-tokens / 0.0239 assistant turns, top-1
 agreement 92.85 %.
 ## Why this swap
 - **Publisher-graded precision**: the w4nl codebook + coordinate-descent
  refinement is the engine author's own quality ceiling for this
  checkpoint; the card's KL ladder (p99 1.65, p99.9 5.33) is published and
  reproducible, where our w4dn8 gate measured against our own reference.
 - **Formal parity**: the served file is the one the engine author supports
  — decode/prefill behavior on 1.0.13 is their tested path (the card's run
  line speaks the 1.0.13-era flags; the `--vram-weights-mib`/`--vram-kv-mib`
  pair we ship is accepted by pin 1.0.13 per the 2026-10-06 A/B, so the
  shape needed no translation).
 - **Cost**: the Swift1.5 finetune's refusal-bending behavior leaves this
  endpoint (it returns to the official base alignment); the 4-slot/200k
  economics and all shape laws carry over unchanged.
 ## Shape (unchanged from 2026-10-13)
 All of it, verbatim — the payload moved 116,416 → 116,322 MiB, inside the
 same budget:
 - `--tp 2 --tp-wire wht6`, `--max-num-seqs 3`, `--max-model-len 200000`
  (capacity contract 3 × 200,000), `--kv-cache-dtype fp8`
 - `--placement expert_tiered --host-pool-mib 44928` + explicit
  `--vram-weights-mib 25600 --vram-kv-mib 5120` (30,720 of the engine's
  30,969 MiB ceiling; pool = contract + 1.3 %)
 - `--num-speculative-tokens 2`, `--max-num-batched-tokens 2048`
  (MNBT 2048 law), prefix cache 8 GiB host + 64 GiB disk,
  `--ngram-placement ram`, froggeric v22.5 `--override-chat-template`
 - TTM preflight floor 150,000 / target 204,800 MiB; pinned ledger
  2 × 44 GiB pool + 47.7 GiB PLE + 8 GiB prefix ≈ 147 GiB (see
  [[frank-archon-radiance-swift15-w4dn8]] for the ledger arithmetic and
  the KV dtype law — both are engine properties, payload-independent)
 The publisher's card run line (`--host-pool-mib 12288`,
 `--expert-vs-cache-ratio 0.82`, seqs 8, spec 3, ~32 GB host RAM) is their
 shape on stock 32 GB cards; the fleet ships its own measured shape against
 the same file.
 ## Cutover record — 2026-10-15
 1. `rm` (Frank's one-time authorization): the raw
   `ukisai/Swift1.5-Qwen3.8-Flash-Next` BF16 checkpoint (336 GiB, spent
   conversion source) and `qwen4exp-fp8-native.rad` (173 GiB, two eras
   back) left `/home/dank/models` — 150 GB free → 658 GB free. The fp8-native
   payload is **no longer on disk**: rebuild =
   `scripts/download-frank-archon.sh` + `scripts/build-frank-archon-rad.sh`.
 2. Fetch: `scripts/download-frank-archon-iq4r.sh --fetch` as transient unit
   `iq4r-fetch` (detached-job protocol; log
   `/home/dank/logs/iq4r-fetch.log`, rc sentinel `…rc`).
 3. Deploy: `scripts/deploy.sh dankserver --service frank-archon` — launched
   detached (the swap restarts the very endpoint the operator session runs
   on; the harness timeout catches the session on return).
 4. **Boot ledger (2026-10-15, first boot, pin 1.0.13 — the w4nl codebook
   loaded, no pin bump)**: `kv_attn` fp8 page **26.00 KiB** at **607,740
   tokens** (151,935 blocks = 3.77 GiB) — byte-identical to the w4dn8 boot,
   the sizing law carries; `kv_qsa_bkey` 3.25 KiB at the same token count;
   `kv_gdn_state` 54 MiB × 6 slots, `kv_gdn_conv` 1.76 MiB × 3,
   `kv_qsa_tail` 19.5 KiB × 6; pool **5.00 GiB**, prefix checkpoints 8 ×
   56 MiB; the sizing line reads `kv cache 5.00 GiB … backs 3 sequences all
   at 200000 tokens at once, which is the worst case`; samplers print **9
   rows** per rank (3 × (1+2), inside the wht6 25-row bound);
   `speculation: 'mtp' drafts 2 token(s) a step in 2 serial pass(es)` +
   prompt-lookup fallback; slab **17,610 (rank0) / 17,658 (rank1) slots**
   (64 shadow) — above the w4dn8 record of 17,548 (ten bf16-protected
   experts per layer replace twenty-four, so more of the 4-bit table
   resides), pinned pool 7,532/7,484 slots; KV lending **4.22 GiB**
   (3,571/3,568 mover slots); arenas 896.02/988.17 MiB charged before the
   pair split; prefix cache RECOVERED 900,176 blocks + 126 checkpoint slots
   from the 64 GiB disk tier (same arch + tokenizer as w4dn8 — the tier
   survived the payload swap); froggeric template 28,234 B; vision encoder
   live (≤ 4,194,304 px, 16,384 patches/pass). Health gate passed in ~100 s
   (radiance binds the port after the full load).
 5. **Vision probe (2026-10-15)**: 300 px solid-red PNG via `image_url` —
   reasoning stream: "a solid fill of a deep, saturated red hue". Content
   came back EMPTY at `max_tokens 64`: the thinking budget consumed all 64
   (`reasoning_tokens: 64`, finish `length`) — fleet law, probe thinking
   models with ≥ a few hundred tokens.
 6. **e2e gate**: deploy exited DEPLOY INCOMPLETE — 30/33 Playwright green,
   3 red (`12-crawl`, `13-sso` search SSO, `16-marreta`) on DANKCLAW
   surfaces (vhosts intermittently returned `ERR_CONNECTION_RESET` from the
   workstation); frank-archon's own health gate passed. The swap touched no
   dankclaw runtime file (only homepage services.json text). Census of the
   Caddy/auth stack pending; see `log.md`.
 7. **Post-boot measurements (pending)**: decode ladder (99.0 t/s single
   @ 43.5k, 93.3 @ 197k, 3-way 113.9/43.3/10.9 = 18.4 t/s aggregate —
   these are the **w4dn8** numbers, the record to beat, not this file's),
   slab-limited prefill (22208/3,397 → 25600/3,584 t/s A-cold 43.5k), draft
   acceptance, and `scripts/probe-frank-archon-kv.py` leg D.
 ## Rollback
 Revert the swap commit (`scripts/frank-archon.env` MODEL_FILE line) +
 redeploy: `/home/dank/models/rad/qwen4exp-swift15-w4dn8-i8-hc8m.rad`
 (116,416 MiB) stays on disk, KLD-gated, same shape. The fp8-native era is
 rebuild-only (see the cutover record). The w4dn8 runbook keeps every shape
 law, the KV dtype table, the slab ladder, and the tuning levers:
 [[frank-archon-radiance-swift15-w4dn8]].
 ## Related
 - [[frank-archon-radiance-swift15-w4dn8]] — the replaced payload and the
  full shape-law library (slab slope, KV dtype arithmetic, TTM law)
 - [[frank-archon-radiance-qwen38-native-fp8]] — the fp8-native era
  (rebuild-only now; owns the descriptor-selection law)
 - [[Dual-R9700-Cooperation]] — the board swap that made TP=2 legal here
 - [[deployment]] — the service-scoped deploy this cutover rides
@@ -0,0 +1,174 @@
 ---
 type: reference
 title: "frank-zealot on Dankclaw — llama.cpp (PrismML fork), Bonsai-2-27B PQ2_0, 2 x 200704, q8_0 KV (ACTIVE)"
 description: "The ACTIVE frank-zealot runbook (since 2026-10-17) — the PrismML fork build of llama.cpp serving prism-ml/Ternary-Bonsai-2-27B-gguf at PQ2_0 on the RTX 3090: two conversations of 200,704 tokens with q8_0 K + q8_0 V (f16 KV does not fit this card at this window), vision through the publisher's Q8_0 Qwen3-VL projector, MTP impossible (no tensors in the file), and the measured four-arm VRAM census that priced the shape."
 tags:
  - llm
  - frank-zealot
  - dankclaw
  - llama-cpp
  - gguf
  - rtx3090
 timestamp: 2026-10-17
 ---
 # frank-zealot — llama.cpp (PrismML) Bonsai-2-27B PQ2_0, 2 × 200,704, q8_0 KV
 Live since 2026-10-17, replacing the
 [[frank-zealot-llama-qwen35-9b-q6k-2x200704]] era (Qwen3.5-9B Q6_K, exact f16
 KV, same 2 × 200,704 shape). The trade: the ternary 27B costs ~3.4× the weights
 of the 9B and buys a 3× larger, stronger base at the SAME window contract —
 paid for by quantizing KV (f16 KV is arithmetically impossible for this
 payload on this card, measured below).
 ## Identity
 | | |
 |---|---|
 | Host / device | Dankclaw (192.168.0.143), RTX 3090, 24,576 MiB (24,123 MiB visible to the engine) |
 | Endpoint | `http://192.168.0.143:7771` — served model id **`frank-zealot`** (`ALIAS`), `/v1` OpenAI surface |
 | Runtime | **PrismML fork build** `/home/dank/GitPackages/llama-prism/llama-server` — vendor release, `--version` = `0.2.0-dev (build 10754, commit 2459f68b5)`, sha256 `12ae5baba033d8cd…`. NOT a preference: see *Why the fork* |
 | Unit | root systemd `frank-zealot.service` ([`scripts/frank-zealot.service`](../../scripts/frank-zealot.service)), `User=dank`, `Restart=on-failure`, `LimitMEMLOCK=infinity` |
 | Serve script | [`scripts/serve-frank-zealot.sh`](../../scripts/serve-frank-zealot.sh), tunables [`scripts/frank-zealot.env`](../../scripts/frank-zealot.env) |
 | Weights | `/home/dank/models/Bonsai2-PQ2_0/Ternary-Bonsai-2-27B-PQ2_0.gguf` — 7,206,168,928 B, sha256 `3907dc1658db1f78a9826bf8d5bcb8dc65db0d466388937af57f2294fae62ec1` |
 | Projector | `Ternary-Bonsai-2-27B-mmproj-Q8_0.gguf` — 629,246,976 B (full sha256 pinned in the fetch script), Qwen3-VL tower; **873.10 MiB worst-case VRAM, loaded AFTER the engine's fit check** |
 | Fetch | [`scripts/download-frank-zealot-bonsai2.sh`](../../scripts/download-frank-zealot-bonsai2.sh) — `-f`, byte-count + sha256 verified, idempotent, `--verify-only`, no token on the command line |
 | Seam | `tests/frank_zealot_unit.bats` (argv assertions against a stub engine) |
 ## Why the fork — the format is the lock
 Read from the file's own metadata, not the model card:
 |Key|Value|
 |---|---|
 |`general.architecture`|`qwen35` (hybrid: Gated DeltaNet + softmax attention)|
 |`qwen35.block_count`|64, `full_attention_interval` 4 ⇒ **16 full-attention + 48 DeltaNet layers**|
 |Attention|24 heads / **4 KV heads** × key 256 / value 256; `rope.dimension_sections` [11,11,10,0], `freq_base` 1e7, partial rope `dimension_count` 64|
 |Widths|embedding 5,120, feed-forward 17,408|
 |`qwen35.ssm.*`|conv_kernel 4, state_size 128, group_count 16, **time_step_rank 48**, **inner_size 6,144**|
 |Window / vocab|`context_length` 262,144; vocab 248,320 (gpt2 BPE, pre `qwen35`), eos 248046|
 |`general.file_type`|**141 = PQ2_0 — 2.13 bpw (group 128)**|
 |Tensor histogram|851 tensors: **`pq2_0` ×402** (custom GGML type **142**), f32 ×353, bf16 ×96|
 |`prism.hadamard.*`|transform `normalized-sylvester-walsh-hadamard`, block_size 1024, axis `input-last-dimension`, sign_mode explicit, **401 named weights**, sign widths [5120, 6144, 17408], 28,672 sign values, inverse applied on `token_embd.weight`, `gdn_v_grouped` true|
 |Sampler metadata|`general.sampling.temp` 1.0 / `top_p` 0.95 / `top_k` 20|
 |Chat template|8,952 chars; reads `enable_thinking`, **`reasoning_effort` ∈ {`xhigh` (default), `medium`, `low` — anything else is `raise_exception`**, `preserve_thinking`, `tools`/`tool_call`, image + video content parts|
 Stock llama.cpp cannot load this file: type 142 is not in its enum (`gguf-py`'s
 stock `GGMLQuantizationType` raises `ValueError: 142 is not a valid…` on the
 same read), and even a loader that parsed it would ignore the
 `prism.hadamard.*` dequant transform the weights depend on. Same class of lock
 as the ROCmFPX custom-type era. The vendor build 10754 already carries the
 September upstream fixes (AVX-512 load segfault, and a `GGML_CUDA_FA_ALL_QUANTS`
 -capable CUDA backend — proven by q8_0 V serving under flash attention at the
 correct 34,816 B/token, below).
 ## VRAM census (2026-10-17, four arms, production stopped)
 The engine's own `common_memory_breakdown_print` ledger + settled `nvidia-smi`,
 all arms `--n-gpu-layers 99 --flash-attn on --batch-size 4096 --ubatch-size 2048`,
 mmproj attached:
 |Shape|KV|projected `model + context + compute`|settled used / free|verdict|
 |---|---|---|---|---|
 |**2 × 200,704 (pool 401,408)**|**q8_0 / q8_0**|21,439 = 6,539 + 13,627 + 1,272|**22,664 / 1,461**|**DEPLOYED**|
 |2 × 200,704|f16 / f16|33,198 = 6,539 + 25,387 + 1,272|—|`cudaMalloc failed: out of memory` on the **25,088.00 MiB** KV request|
 |1 × 262,144|q8_0 / q8_0|16,905 = 6,539 + 8,853 + 1,512|18,130 / 5,995|fits, but one slot serializes compaction|
 |2 × 262,144|q8_0 / q8_0|≈25,758 (arithmetic, same terms)|—|does not fit (f16 analogue measured 41,118)|
 |2 × 200,704|q4_0 / q4_0|15,167 = 6,539 + 7,355 + 1,272|16,392 / 7,733|the roomy fallback rung|
 **KV rate law (confirmed to the MiB):** 16 full layers × 4 KV heads × 256 dim =
 16,384 elements/token/cache; q8_0 bills 17,408 B per cache ⇒ **34,816 B/token**,
 so the 401,408 pool = **13,328.00 MiB** — the ledger printed exactly that
 (`CUDA0 KV buffer size = 13328.00 MiB`). f16 doubles it to 25,088 MiB, which is
 the wall. The 48 DeltaNet layers bill a fixed recurrent state per **slot**:
 context 13,627 − KV 13,328 = **299 MiB for two slots (~150 MiB each)** — pool
 arithmetic alone under-prices the shape by that much.
 **The projector is outside the fit check.** `[mtmd] estimated worst-case memory
 usage of mmproj is 873.10 MiB` is printed before fitting but not billed in it:
 settled used (22,664) − projection (21,439) ≈ 1.2 GiB is that projector plus the
 CUDA context. This is the difference between "2.6 GiB free on paper" and the
 real **1.4 GiB** — the same late-allocation failure class that killed the
 DSpark drafter boot in the llama.cpp eras. Any resize must re-read the settled
 `nvidia-smi`, never the projection.
 ## Measured rates (greedy, `Server-Timing`-free `/completion` `timings`)
 |Probe|Result|
 |---|---|
 |Short, warm, single stream (128 tok)|**76.6 t/s** decode (the 9B Q6_K predecessor ran 94.4 — the ternary 27B is ~19 % slower, weight bandwidth + Hadamard dequant)|
 |First request after boot|2.6 t/s prefill / 37.7 t/s decode — **warmup artifact; never report the first request** (measured twice on this payload)|
 |Prefill at ~35k depth|**1,258.4 t/s** (27.8 s)|
 |Prefill at 166,027-token depth|**691.7 t/s** (240.0 s), zero errors, slot intact|
 |Two concurrent streams, 256 tok each|**54.7 + 54.7 = 109.4 t/s aggregate** — `--parallel 2` really batches|
 |Long-context retrieval (25,960-token prompt, needle at position 180 of 300 passages)|exact: *"Frank keeps the fleet in git, only through it."*|
 ## Behavior contract (probes, not assumptions)
 - **Reasoning** lands in `reasoning_content` (`--reasoning-format deepseek`) ✓.
 - **Tool calls**: a `get_weather` request returns `finish_reason: tool_calls`
  with `arguments: {"city":"Seattle"}` — valid JSON, no loop, no HTTP 500. The
  fork's `KNOWN_ISSUES.md` warning about malformed/looping tool calls did not
  reproduce on build 10754 at this shape.
 - **Vision**: a 512 px solid-red PNG answers **"Red"** — but ONLY with a
  thinking budget ≥ ~512 tokens. At `max_tokens: 64` the request returns
  `finish_reason: "length"` with EMPTY `content` and half a thought in
  `reasoning_content`: thinking tokens count against the budget, so a
  short-budget vision probe reads as "the model is blind". Images do reach the
  model (a 512 px image bills ~280 prompt tokens: 322 total vs 42 for the text
  alone). Keep the ≥256 px probe rule from the earlier eras.
 - **Log noise law**: `/completion` (text context) at `VERBOSITY=4` prints
  `failed to parse reasoning content (response_format json_schema is currently
  only supported with parse_reasoning=true), content will be stored in
  'content' field` (`probe_request.cpp:789`) whenever the model closes a raw
  prompt with ``. It is **cosmetic** — the full chain of thought
  is in `content`. The OpenAI `/v1/chat/completions` path parses it into
  `reasoning_content` correctly, which is the path the harness and every
  consumer uses. Do not diagnose this as a fault, and do not drop verbosity
  below 4 — the KV/buffer ledger in the journal is what VRAM forensics read.
 - **Long raw-prompt completions can come back empty**: at ~26k+ tokens a bare
  `/completion` request generated 0–1 tokens with no error (the model emits an
  end-of-turn marker immediately, and a text context has no role frame to keep
  it talking). Chat traffic is unaffected; nothing in the harness posts raw
  `/completion` at depth.
 ## Ops notes
 - **Trial-window law (cost one boot window on 2026-10-17):** a scratch env file
  must use the serve script's OWN variable names — `CACHE_TYPE_K`/`CACHE_TYPE_V`,
  `BIND_ADDR`, `NGL`. An invented `KV_CACHE_TYPE` is silently swallowed by the
  script's `: "${CACHE_TYPE_K:=f16}"` default and the arm boots **f16**, which
  for this payload is an OOM that looks like a model problem.
 - **Base alignment:** Bonsai-2 is the BASE (censored) Qwen3.8-27B lineage, so a
  refusal is possible on a compaction or subagent request. The CRACK re-export
  (`dealignai/Bonsai-2-27B-Ternary-CRACK-GGUF`, already on disk at
  `/home/dank/models/Bonsai2-CRACK/Bonsai-2-27B-PQ2_0-CRACK.gguf`, sha256
  `5b24ea3e…`) is a **one-line `MODEL_FILE` swap**: the header census proves
  byte-identical geometry — 851 tensors, the same `{142:402, f32:353, bf16:96}`
  histogram, 64 blocks, vocab 248,320, the same 8,952-char template. The VRAM
  ledger does not move. If a refusal ever surfaces, that is the fix; there is
  also an MTP-bearing CRACK re-export upstream
  (`ManniX-ITA/…-CRACK-MTP-GGUF`, 7,657,489,920 B, +451 MB head) if decode ever
  needs the drafter — untested here.
 - **Compaction hub unchanged:** all three endpoints still route
  `compactionModel` here; 200,704 per slot is the fleet's only window that fits
  a worst-case compaction input, and `--parallel 2` keeps compaction off the
  critical path of a live generation.
 - **Harness side** (`~/.omp/agent/models.yml`): `contextWindow: 200704` and
  `maxTokens: 16384` unchanged; `extraBody` now quotes the payload's own
  1.0 / 0.95 / 20 with `preserve_thinking: true`. The `reasoningEffortMap` fold
  became **load-bearing** (the template raises on any level outside
  `xhigh|medium|low`) — an unmapped level is a hard 500 on the role's first
  request, naming Jinja rather than the model.
 - **Rollback:** revert the swap commit. The Qwen3.5-9B Q6_K payload, its mmproj
  and the master CUDA build all remain on disk
  (`/home/dank/models/Qwen35-9B-HauhauCS-Q6K/`,
  `~/GitPackages/llama-master/build-cuda/`), and the retired era keeps its own
  page: [[frank-zealot-llama-qwen35-9b-q6k-2x200704]].
 ## Related
 - [[frank-zealot-llama-qwen35-9b-q6k-2x200704]] — the replaced era (rollback target)
 - [[frank-dragoon-flash-server-v2-swift15]] — the abliterated sibling on the iGPU
 - [[frank-archon-radiance-qwen38-iq4r]] — the censored-base flagship this payload shares base alignment with
 - [[deployment]] — deploy flow and incidents
@@ -3,25 +3,30 @@
 **Dankserver runs the radiance engine (StillDeadcode) on frank-archon**
 (digest-pinned `stilldeadcode/radiance` image, engine as entrypoint,
 driving `podman run` directly, root systemd unit, :7770):
-`ukisai/Swift1.5-Qwen3.8-Flash-Next` converted to **GPTQ w4**
+the **publisher's** 4-bit-codebook container of the official
-(`qwen4exp-swift15-w4dn8-i8-hc8m.rad`, 116,416 MiB, KLD-gated), on BOTH R9700s
+`Qwen/Qwen3.8-Flash-Next` (`qwen3.8-next-flash-fp8-iq4r-moe.rad`, 116,322 MiB,
 sha256-verified at fetch — w4nl codebook experts + int8 trunk, PLE n-gram,
 MTP head and vision tower in-container), on BOTH R9700s
 TP=2 (`--tp-wire wht6`), experts in a 44 GiB/rank pinned host pool + VRAM cache
 (explicit `--vram-weights-mib 25600 --vram-kv-mib 5120` = 30,720 of the
 30,969 MiB the engine's own budget table makes claimable), the 47.7 GiB PLE
 table pinned to host RAM, **fp8 KV at 3 × 200,000**, MTP spec decode depth 2,
-froggeric v22.5 template. Rollback tags frank-archon-freetoken-pr587-20261005
+froggeric v22.5 template. Rollback: the in-house Swift1.5 w4dn8 `.rad` (on
-and frank-archon-vllm-shapeG-20261003),
+disk); tags frank-archon-freetoken-pr587-20261005 and
 frank-archon-vllm-shapeG-20261003),
 and Dankclaw runs two endpoints — **halogen-flash-server 0.16.2
 (frank-dragoon, port 7770: ghcr.io/peonist-ai/halogen-flash-server @ pinned
 digest serving the Quat3rnion ABLITERATED Swift1.5 finetune of
 Qwen3.8-Flash-Next v2, a ~62 GiB v2 .hgn that loads in no other engine,
 MTP spec decode always-on (HALOGEN_SPEC_ADAPT=0), TWO slots at 200,192
 ctx, vision ON)** and
-**llama.cpp CUDA (frank-zealot, port 7771: HauhauCS Gemma4-26B-A4B QAT
+**llama.cpp on the PrismML fork (frank-zealot, port 7771: prism-ml
-Uncensored Q4_K_M GGUF — 26B MoE hybrid (25 sliding-window + 5 full-attention
+Ternary-Bonsai-2-27B at **PQ2_0** — 27B qwen35 hybrid (16 full-attention + 48
-layers), ONE 200,704-token conversation, MTP disabled,
+Gated DeltaNet layers), TWO 200,704-token conversations, MTP disabled,
-q8_0 K + q8_0 V (FP8 class), vision via the publisher's own BF16
+q8_0 K + q8_0 V (f16 KV does not fit the RTX 3090 at this window), vision via
-mmproj, on the RTX 3090)**.
+the publisher's own Q8_0 Qwen3-VL mmproj, on the RTX 3090 — and the custom
 tensor type 142 + `prism.hadamard.*` metadata mean no other loader can open the
 file)**.
 > 2026-08-22: the former `vllmScripts` repository is merged into the
 > serverAppConfigs repository. This knowledge base moved from the old repo's
@@ -37,10 +42,10 @@ graph LR
 gfx1201, 32 GiB each]
        B2[radiance StillDeadcode, digest-pinned image
 podman run, frank-archon, port 7770]
-        C[Swift1.5-Qwen3.8-Flash-Next GPTQ w4 .rad
+        C[Publisher qwen3.8-next-flash-fp8-iq4r-moe .rad
 2x R9700 TP=2 wht6, experts 44 GiB/rank pinned pool + VRAM,
 PLE 47.7 GiB pinned RAM, fp8 KV 7.32 KiB/tok, MTP depth 2,
-4 x 200000, froggeric v22.5]
+3 x 200000, froggeric v22.5]
    end
    subgraph Dankclaw[AMD Strix Halo - Ubuntu 26.04]
@@ -103,13 +108,25 @@ frank-zealot, port 7771]
  (`slow`/`advisor` → frank-archon) carried forward. Superseded by the
  MODEL swap: the abliterated v2 .hgn loads only in flash-server, so the
  engine moved with the model
- [[frank-zealot-llama-qwen35-9b-q6k-2x200704]] — **ACTIVE since 2026-10-07**
+- [[frank-zealot-llama-prism-bonsai2-pq20]] — **ACTIVE since 2026-10-17**
-  (root systemd unit, port 7771): llama.cpp master (CUDA sm_86) serving
+  (root systemd unit, port 7771): the **PrismML fork** build of llama.cpp
-  HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive **Q6_K** on the RTX 3090
+  (vendor 10754, commit `2459f68b5` — the only loader for the payload's custom
-  — TWO 200,704-token conversations (`--ctx-size 401408 --parallel 2`), exact
+  tensor type 142 + `prism.hadamard.*` transform) serving
-  f16 K + f16 V, vision via the publisher's BF16 mmproj. MTP is OFF because
+  prism-ml/Ternary-Bonsai-2-27B-gguf **PQ2_0** (2.13 bpw) on the RTX 3090 —
-  the file has no MTP tensors at all. Priced from the MiMo Q6_K boots (same
+  TWO 200,704-token conversations (`--ctx-size 401408 --parallel 2`), **q8_0 K
-  qwen35 geometry, same card, same shape). Supersedes the Gemma4 era (below).
+  + q8_0 V** (34 KiB/token over the 16 full layers = 13,328 MiB; the f16 pair
  needs 25,088 MiB and dies), settled 22,664 used / 1,461 free, vision via the
  publisher's Q8_0 mmproj (+873 MiB, charged AFTER the engine's fit check), MTP
  OFF (no MTP tensors). 76.6 t/s single-stream decode, 691.7 t/s prefill at
  166k, 109.4 t/s aggregate at two streams. Supersedes the Qwen3.5-9B era below.
 - [[frank-zealot-llama-qwen35-9b-q6k-2x200704]] — **RETIRED 2026-10-07 →
  10-17** (payload + master CUDA build on disk as rollback): llama.cpp master
  (CUDA sm_86) serving HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive
  **Q6_K** on the RTX 3090 — TWO 200,704-token conversations
  (`--ctx-size 401408 --parallel 2`), exact f16 K + f16 V, vision via the
  publisher's BF16 mmproj. MTP is OFF because the file has no MTP tensors at
  all. Priced from the MiMo Q6_K boots (same qwen35 geometry, same card, same
  shape). Supersedes the Gemma4 era (below).
 - [[frank-zealot-llama-gemma4-q4km-200704]] — **RETIRED 2026-10-07** (same
  day; superseded by qwen35-9b-q6k; payload on disk as rollback): llama.cpp
  master (CUDA sm_86) serving HauhauCS/Gemma4-26B-A4B-QAT-Uncensored-
@@ -153,7 +170,22 @@ frank-zealot, port 7771]
  target; payload on disk; owns the measured boot-pair table)**: the same
  runtime and the same 2 x 200,704 + f16 KV shape one quant rung lower —
  104.8 tok/s, 3,571 MiB true free
- [[frank-archon-radiance-swift15-w4dn8]] — **ACTIVE since 2026-10-08**:
+- [[frank-archon-radiance-qwen38-iq4r]] — **ACTIVE since 2026-10-15**:
  the engine author's published container of the OFFICIAL (base-alignment)
  Qwen3.8-Flash-Next — `qwen3.8-next-flash-fp8-iq4r-moe.rad`, 116,322 MiB,
  Hub-sha256-verified at fetch: 4-bit codes into a 16-level non-uniform
  codebook after a Walsh–Hadamard rotation (GPTQ + 3 coordinate-descent
  sweeps, 10M-token calibration), ten bf16-protected experts per layer,
  int8 trunk/lm_head, fp8 HC + PLE, MTP head, bf16 vision tower; card KL
  0.0789 all-tokens / top-1 92.85 % vs bf16. **MODEL_FILE is the only line
  that moved** — the 2026-10-13 shape (25600/5120 pair, 44928 pool, fp8 KV
  3 × 200,000, MTP 2, wht6, MNBT 2048, froggeric v22.5) carries verbatim.
  Rollback: revert the swap commit (w4dn8 `.rad` stays on disk). The
  fp8-native `.rad` and the raw Swift1.5 BF16 source were DELETED from
  dankserver 2026-10-15 (Frank's one-time rm, volume for this payload;
  rebuild via the fetch + build scripts named in the fp8-native runbook)
 - [[frank-archon-radiance-swift15-w4dn8]] — **RETIRED 2026-10-08 → 10-15
  (superseded by the publisher iq4r swap; payload on disk as the rollback)**:
  Swift1.5 Qwen3.8-Flash-Next BF16 → GPTQ-calibrated W4Dn8 `.rad` on radiance
  1.0.13 (recipe + 10M-token calibration + KLD gate vs the BF16 container);
  the FP8-native payload remains the rollback. **2026-10-13: fp8 KV, and the
@@ -182,12 +182,20 @@ The LLM inference fleet on the two hosts. Full index:
 ### Deployment and Topology
 - [[deployment]] — unified deploy and update process for both servers
- [[frank-archon-radiance-swift15-w4dn8]] — STAGED frank-archon runbook:
+- [[frank-archon-radiance-qwen38-iq4r]] — **ACTIVE frank-archon runbook
  (2026-10-15)**: the PUBLISHER's container of the official
  Qwen3.8-Flash-Next (`qwen3.8-next-flash-fp8-iq4r-moe.rad`, 116,322 MiB,
  w4nl 4-bit-codebook experts + int8 trunk, Hub-sha256-verified at fetch)
  swapped in as a MODEL_FILE-only change — the 2026-10-13 shape (slab
  25600 / fp8-KV 5120, 3 × 200,000, host pool 44,928, MTP depth 2) carries
  verbatim; rollback = revert the swap commit (the w4dn8 `.rad` stays on
  disk; the fp8-native `.rad` was deleted 2026-10-15, rebuildable)
 - [[frank-archon-radiance-swift15-w4dn8]] — RETIRED 2026-10-08 → 10-15 frank-archon runbook:
  Swift1.5 Qwen3.8-Flash-Next BF16 → GPTQ-calibrated W4Dn8 `.rad` (radiance
  1.0.13), gated on KLD ≤ 0.03 vs the BF16 container and decode ≥ 30.8 t/s;
  activates by flipping `MODEL_FILE` in `scripts/frank-archon.env`, rollback
  = revert that line (the FP8-native `.rad` stays on disk)
- [[frank-archon-radiance-qwen38-native-fp8]] — the ACTIVE frank-archon
+- [[frank-archon-radiance-qwen38-native-fp8]] — the RETIRED 2026-10-05 → 10-08 frank-archon
  runbook (2026-10-05): the StillDeadcode radiance engine (digest-pinned
  287 MiB image, libr4d gfx1201 kernels) serving the OFFICIAL
  `Qwen/Qwen3.8-Flash-Next-FP8` at native block-FP8 (no-recipe convert
@@ -380,8 +388,15 @@ The LLM inference fleet on the two hosts. Full index:
 - [[ciru-activefpx-promptforge]] — the RETIRED v3 CIRU PromptForge runtime on Dankclaw (superseded 2026-08-24)
 - [[kingjones-strix-mtp]] — the kingjones Qwen3.8-27B ROCmFP4 STRIX MTP model on Dankclaw (active)
 - [[dealign-ornith-crack]] — the retired Ornith-1.5-35B-A3B CRACK model on Dankserver (retired 2026-09-02)
- [[frank-zealot-llama-qwen35-9b-q6k-2x200704]] — the **ACTIVE** frank-zealot
+- [[frank-zealot-llama-prism-bonsai2-pq20]] — the **ACTIVE** frank-zealot
-  runbook since 2026-10-07 (late): llama.cpp master (CUDA sm_86) serving
+  runbook since 2026-10-17: the PrismML vendor llama.cpp build 10754 (the only
  loader for GGML type 142 / `prism.hadamard.*`) serving
  prism-ml/Ternary-Bonsai-2-27B-gguf **PQ2_0** on the RTX 3090 — TWO
  200,704-token conversations, q8_0 K + q8_0 V (f16 OOMs at 2×200,704: 34 KiB
  vs 64 KiB per token over 16 full-attention layers), MTP **off** (no head in
  the file), vision through the Q8_0 mmproj; boot 22,664 used / 1,461 free
 - [[frank-zealot-llama-qwen35-9b-q6k-2x200704]] — RETIRED 2026-10-17 (rollback
  target, payload on disk): llama.cpp master (CUDA sm_86) serving
  HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive **Q6_K** on the RTX 3090 —
  TWO 200,704-token conversations, exact f16 K + f16 V, MTP **impossible**
  (the file carries no `nextn`/`mtp` tensors), vision through the publisher's
@@ -1745,22 +1745,110 @@ every restart since the cutover.
  [[frank-archon-radiance-swift15-w4dn8]], and the LLM index entry corrected
  (the w4dn8 entry said STAGED, the fp8-native one said ACTIVE).
 ## 2026-10-15 — frank-archon: publisher iq4r payload swap (MODEL_FILE-only)
-## 2026-10-15 — governance: bench removed from the model-change procedure
+- Ask: replace the served model with
  `StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe` — the engine author's
  published rad-convert of the OFFICIAL Qwen3.8-Flash-Next (w4nl codebook
  experts, ten bf16-protected/layer, int8 trunk, PLE/MTP/vision in-container,
  card KL 0.0789 / top-1 92.85 %) — **no other argument changes**, mindful
  the operator session runs on the endpoint being swapped.
 - Disk: Frank authorized one `rm` — the spent Swift1.5 BF16 source (336 GiB)
  and the two-era-old `qwen4exp-fp8-native.rad` (173 GiB) left
  `/home/dank/models`; 150 GB → 658 GB free. fp8-native is now rebuild-only
  (fetch + build scripts); rollback for THIS swap is the w4dn8 `.rad`
  (on disk) by reverting the commit.
 - Fetch: new `scripts/download-frank-archon-iq4r.sh` (hfget, exact bytes
  121,969,901,568 + Hub LFS sha256, `--verify-only` default) as transient
  unit `iq4r-fetch`; verified, staged sidecar files kept as provenance.
 - Shape carried VERBATIM (25600/5120 pair, 44928 pool, fp8 KV 3 × 200,000,
  MTP 2, wht6, MNBT 2048, froggeric v22.5). Tests re-keyed
  (`frank_archon_unit.bats` pins the new payload id + sha256, keeps the
  w4dn8 rollback provenance), homepage card + trio lore + both indexes
  updated; new runbook [[frank-archon-radiance-qwen38-iq4r]]. Commits
  `6dcf4a5` (swap) + `f44c398` + `c5ac072` (docs), full bats green.
 - Cutover self-severed by design (detached `deploy.sh` survived the session
  death when frank-archon restarted); engine healthy in ~100 s. First-boot
  ledger: w4nl loads on pin 1.0.13 (no pin bump); kv_attn 26.00 KiB fp8 @
  607,740 tokens (identical geometry); slab 17,610/17,658 slots per rank
  (> w4dn8's 17,548 — fewer bf16-protected experts pack more 4-bit table);
  sampler 9 rows; MTP 2/step; prefix tier RECOVERED 900,176 blocks across
  the swap (arch+tokenizer unchanged). Vision probe green (reasoning read
  the solid-red PNG; the 64-token budget went all to thinking — fleet law).
 - e2e gate went red on three dankclaw specs — NOT the swap: dankclaw rebooted
  01:41 and the gluetun boot-race dependency-failed `searxng`, `marreta`,
  and `marreta-browser` (jobs consumed while gluetun's start job retried;
  `Restart=always` never armed because the services never ran). Cascade
  restarted; skill codified (`gluetun-dependent-boot-race-recovery`).
  Gate rerunning against the repaired fleet; frank-archon's own health gate
  passed every deploy. Open: decode/prefill ladders vs the w4dn8 record,
  probe leg D — scheduled probe window.
- Frank's call: a model swap never carries a bench window. Codified as law:
+## 2026-10-15 — authentik: two more human accounts (Dankclaw)
-  - `AGENTS.md` Benchmarking Policy opens with "Benchmarking is NOT part of
+- **Live — mitch (pk 22) and eric (pk 23) provisioned via `ak shell` ORM, no
-    the model-swap procedure"; swap verification is the live service (boot
+  repo objects.** Each `<user>@franksdank.cloud` in the human-user template
-    ledger, `timings`/`Server-Timing`, one real request per harness role).
+  shape (`is_active=True`, display name, password via `set_password` on stdin
-    The stop-and-mask rule stays for DELIBERATE bench windows (flag A/Bs,
+  only — never argv, so nothing lands in `ps`), groups `Non-Admin Users` +
-    shape sweeps) — it is host protection (2026-09-16 hard-down precedent),
+  `jellyfin_users` + `openwebui_users`; no admin group granted. Verified
-    not a swap step. Summary-table row updated to match.
+  through the exact PasswordStage code path (`authenticate()` accepted each
-  - [[Model Swap and Rollback]]: "No bench step (law, 2026-10-15)" up top;
+  password and rejected a wrong one), `app_entitlements(open-webui)` →
-    §8 close-out numbers must be measured on the live service; the Related
+  `Open WebUI Users` for both (identical to the ridley precedent), and
-    link to [[LLM Bench Windows and Measurement]] rescoped to
+  `is_superuser=False` / `path=users`. Zero `proxysession` rows for either —
-    out-of-procedure windows only.
+  groups were set before any login, so no claim purge was due. Downstream:
- Untouched on purpose: the `FRANK_*_ENV_FILE` hook (staged/out-of-procedure
+  Jellyfin visibility rides the LDAP outpost cache (expect lag); OpenWebUI
-  arms), the Fleet Ops Playbook bench-window mechanics (deliberate windows
+  mints their accounts as role `pending` on first login.
-  still need the procedure), `deployment.md` (already says bench work is a
+- `/serverAppConfigs-docs/Infrastructure/Authentik.md` — human-user template
-  SEPARATE procedure). Managed skill `llamacpp-endpoint-model-swap` verifies
+  census extended with pk 22–23.
-  on the live engine — it never had a bench step.
+
 ## 2026-10-17 — frank-zealot: Bonsai-2-27B PQ2_0 trial + cutover (2 × 200,704, q8_0 KV)
 - Ask: evaluate `prism-ml/Ternary-Bonsai-2-27B-gguf` (PQ2_0) as frank-zealot's
  payload, and specifically measure **2 × 200,704 with q8_0 K + q8_0 V** on the
  RTX 3090. Fetch script `scripts/download-frank-zealot-bonsai2.sh` (exact
  bytes + sha256, `--verify-only`) landed first; payload verified at
  `/home/dank/models/Bonsai2-PQ2_0/` (7,206,168,928 B + 629,246,976 B mmproj).
 - Runtime door: the file is `file_type 141` with 402 tensors of custom GGML
  type **142** plus `prism.hadamard.*` metadata — stock llama.cpp refuses it,
  so the PrismML vendor build 10754 (`2459f68b5`) is forced, not chosen. A
  source build with `GGML_CUDA_FA_ALL_QUANTS=ON` was started and then
  cancelled as unnecessary: the vendor build already serves q8_0 V under flash
  attention at the exact 34,816 B/token (ledger-confirmed).
 - Trial-window law cost one boot: the scratch env invented `KV_CACHE_TYPE`
  where the serve script reads `CACHE_TYPE_K`/`CACHE_TYPE_V`, so the script's
  `:=f16` default silently won and every arm booted f16. That failed window is
  now the measured f16 wall: `cudaMalloc` OOM on a 25,088.00 MiB KV request,
  engine fit 33,198 vs 23,558 free.
 - Four-arm census (production stopped, trap-guarded restore, `bg_12`):
  **2 × 200,704 q8_0 = 22,664 used / 1,461 free (DEPLOYED)**; 1 × 262,144
  q8_0 = 18,130 / 5,995 (fits, but serializes compaction); 2 × 262,144 q8_0
  ≈ 25,758 projected (no fit); 2 × 200,704 q4_0 = 16,392 / 7,733 (fallback
  rung). Recurrent DeltaNet state bills ~150 MiB per SLOT (context 13,627 −
  KV 13,328 for two slots), which pool arithmetic alone misses.
 - Behavior probes green: exact-instruction chat, `reasoning_content` present,
  `tool_calls` with valid JSON arguments (no fork `KNOWN_ISSUES` loop/500),
  512 px solid-red PNG answered **"Red"**, needle retrieval exact through a
  25,960-token prompt, 166,027-token prefill clean in 240.0 s. Rates: 76.6 t/s
  single-stream (9B ran 94.4), 1,258 t/s at 35k, 691.7 t/s at 166k,
  **109.4 t/s aggregate** at two concurrent streams.
 - New fleet laws recorded (AGENTS.md + runbook): the mmproj's 873.10 MiB
  worst-case is NOT inside the engine's fit projection; the first request after
  a boot is a warmup artifact (2.6 / 37.7 t/s measured); a 64-token thinking
  budget makes a thinking model look blind; the Bonsai-2 template reads
  `reasoning_effort` (xhigh/medium/low, raises otherwise) so the harness fold
  became load-bearing on this endpoint, and it reads `preserve_thinking`.
 - Cutover: `scripts/frank-zealot.env` (payload + `CACHE_TYPE_*`=q8_0 + ledger
  lore), `scripts/deploy-remote.sh` (runtime/model/mmproj gates re-keyed, fork
  hint), `tests/frank_zealot_unit.bats` (payload pair pinned; KV assertions now
  env-derived instead of an f16 literal), harness `models.yml` (extraBody 1.0
  /0.95/20 + `preserve_thinking`, effort-map comment corrected —
  `contextWindow` 200704 and `maxTokens` 16384 unchanged), new runbook
  [[frank-zealot-llama-prism-bonsai2-pq20]], indexes re-keyed, 9B era retired
  in place. Full bats green (371).
 - Base alignment: **Frank chose the OFFICIAL censored payload** — publisher
  provenance over refusal-freedom. The 9B it replaces was uncensored, so the
  homepage card and its warning contract were re-keyed with it: zealot's card
  now carries the base-alignment notice, the shared legal warning belongs to
  dragoon alone, and the `homepage_config.bats` equality
  (`zealot.warn == dragoon.warn`) retired with the payload it described.
  The CRACK re-export (byte-identical geometry per header census) stays on
  disk as the one-line `MODEL_FILE` fallback if refusals bite.
@@ -90,14 +90,14 @@
  <h2>frank-zealot — the fast utility model</h2>
  <ul>
-    <li><strong>Model:</strong> <a href="https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive" target="_blank" rel="noopener">Qwen3.5-9B-Uncensored</a> (Q6_K) on the RTX&nbsp;3090 — roughly 95 tokens per second.</li>
+    <li><strong>Model:</strong> <a href="https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf" target="_blank" rel="noopener">Ternary-Bonsai-2-27B</a> (PQ2_0 ternary weights) on the RTX&nbsp;3090 — roughly 77 tokens per second.</li>
    <li><strong>Equivalent:</strong> last year's frontier level (2025).</li>
    <li><strong>Capacity:</strong> 200k-token context, two submissions at a time; sees images.</li>
    <li><strong>Inputs:</strong> text, image.</li>
    <li><strong>Best for:</strong> code editor autocomplete, agentic search, RAG, research subagents, translation, roleplay, and summarization — any small task that doesn't need much intelligence, and anything with a picture. This is the model Open&nbsp;WebUI offers to family accounts.</li>
    <li><strong>Compaction:</strong> if your agent harness supports setting a compaction model, set this one. A compaction job severely slows the bigger models for far longer than it slows this one.</li>
    <li><strong>Supervision:</strong> requires tight human supervision.</li>
-    <li><strong>Warning:</strong> <details class="key-warn"><summary>&#9888; uncensored model</summary><div class="warn-body">Uncensored model: output can include adult content, content that describes harmful, hateful, or illegal acts, content concerning &ldquo;sensitive offensive cybersecurity topics&rdquo;, and other output that may carry severe legal risk. Take this warning seriously &mdash; don&rsquo;t ruin this server for everybody.</div></details></li>
+    <li><strong>Warning:</strong> <details class="key-warn"><summary>&#9888; censored base model</summary><div class="warn-body">Base-alignment (censored) model: refusals are possible on sensitive topics, and any model can still be steered into risky output. Uncensored work belongs on frank-dragoon. Take this warning seriously &mdash; don&rsquo;t ruin this server for everybody.</div></details></li>
  </ul>
  <h2>frank-dragoon — deep reasoning</h2>
@@ -295,13 +295,13 @@
    "model": {
      "unit": "zealot",
      "role": "Frank's utility model",
-      "hf": "https://huggingface.co/HauhauCS/Qwen3.5-9B-Uncensored-HauhauCS-Aggressive",
+      "hf": "https://huggingface.co/prism-ml/Ternary-Bonsai-2-27B-gguf",
      "tagline": "HONOR GUIDE ME!",
      "sfx": [
        "zealot-honor.ogg"
      ],
      "equiv": "Equivalent to last year's frontier level (2025).",
-      "spec": "Qwen3.5-9B-Uncensored (Q6_K) on an NVIDIA RTX 3090 — ~95 tokens/s; 200k-token context, two submissions at a time; sees images.",
+      "spec": "Ternary-Bonsai-2-27B (PQ2_0 ternary weights) on an NVIDIA RTX 3090 — ~77 tokens/s; 200k-token context, two submissions at a time; sees images.",
      "inputs": [
        "text",
        "image"
@@ -314,7 +314,7 @@
        ]
      },
      "supervision": "Requires tight human supervision.",
-      "warn": "Uncensored model: output can include adult content, content that describes harmful, hateful, or illegal acts, content concerning “sensitive offensive cybersecurity topics”, and other output that may carry severe legal risk. Take this warning seriously — don’t ruin this server for everybody.",
+      "warn": "Base-alignment (censored) model: refusals are possible on sensitive topics, and any model can still be steered into risky output. Take this warning seriously — don’t ruin this server for everybody.",
      "compaction": "If your agent harness lets you set a compaction model, set this one: a compaction job on the bigger models blocks them for far longer."
    },
    "url": "",
@@ -366,13 +366,13 @@
    "model": {
      "unit": "archon",
      "role": "Frank's strongest and fastest model runtime",
-      "hf": "https://huggingface.co/frank8465/Swift-1.5-Qwen3.8-Flash-Next-GPTQ-W4A8-Radiance-AMD-R9700",
+      "hf": "https://huggingface.co/StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe",
      "tagline": "...Power Overwhelming...",
      "sfx": [
        "archon-power.ogg"
      ],
      "equiv": "Equivalent to Claude Opus 4.8 / OpenAI-Terra (Summer 2026 frontier intelligence).",
-      "spec": "Our own build: a GPTQ-w4 quant of Swift1.5-Qwen3.8-Flash-Next, quantized and tuned in-house (radiance, ~114 GiB) on twin AMD R9700s with more than 200 GB of system RAM — 200k-token context, three submissions at a time; sees images.",
+      "spec": "The engine author's published quant: 4-bit codebook experts + int8 trunk of Qwen3.8-Flash-Next (radiance, ~114 GiB) on twin AMD R9700s with more than 200 GB of system RAM — 200k-token context, three submissions at a time; sees images.",
      "inputs": [
        "text",
        "image"
@@ -3,8 +3,10 @@
 #
 # This file asserts the RADIANCE shape (StillDeadcode engine, digest-pinned
 # stilldeadcode/radiance image, BOTH R9700s TP=2 on the wht6 wire, serving
-# the Swift1.5 Qwen3.8-Flash-Next GPTQ-w4 .rad built by
+# the publisher's 4-bit-codebook .rad of the official Qwen3.8-Flash-Next
-# scripts/convert-swift15-w4dn8.sh). It replaces the FreeToken seam of
+# (fetched by scripts/download-frank-archon-iq4r.sh; the in-house
 # Swift1.5 w4dn8 .rad of scripts/convert-swift15-w4dn8.sh is the on-disk
 # rollback). It replaces the FreeToken seam of
 # 2026-10-05 (git tag frank-archon-freetoken-pr587-20261005) and pins what
 # flags alone do not say: the served window clears the harness worst case,
 # the KV pool backs seqs x max-model-len at the declared cache dtype (an
@@ -28,7 +30,7 @@ SERVE="$REPO_ROOT/scripts/serve-frank-archon.sh"
 TTM_LIB="$REPO_ROOT/scripts/ttm-preflight.sh"
 ENV_FILE="$REPO_ROOT/scripts/frank-archon.env"
 REMOTE_DEPLOY="$REPO_ROOT/scripts/deploy-remote.sh"
-DOWNLOAD="$REPO_ROOT/scripts/download-frank-archon-swift15.sh"
+DOWNLOAD="$REPO_ROOT/scripts/download-frank-archon-iq4r.sh"
 BUILD="$REPO_ROOT/scripts/convert-swift15-w4dn8.sh"
 HFGET="$REPO_ROOT/scripts/hfget.sh"
 TEMPLATE="$REPO_ROOT/scripts/qwen38-froggeric-v22.5.jinja"
@@ -381,18 +383,23 @@ nosudo_bin() {
    grep -q 'exec podman wait "$FRANK_ARCHON_CONTAINER"' "$SERVE"
 }
-@test "the model id matches the payload's build and fetch scripts" {
+@test "the model id matches the payload's fetch script (and the rollback's build script)" {
-    # The payload dir/file are the convert script's output layout; the fetch
+    # The deployed payload is the PUBLISHER's .rad: the fetch script names
-    # script must name the repo the convert stages from. (FP8-native era,
+    # the repo, the file, and the Hub's LFS sha256; nothing is converted on
-    # the rollback payload, keeps its own trio: build-frank-archon-rad.sh +
+    # the host for it. The in-house w4dn8 rollback keeps its own trio
-    # download-frank-archon.sh.)
+    # (convert-swift15-w4dn8.sh + download-frank-archon-swift15.sh, and the
    # fp8-native era keeps build-frank-archon-rad.sh +
    # download-frank-archon.sh).
    grep -q '^FRANK_ARCHON_MODEL_DIR=/home/dank/models/rad$' "$ENV_FILE"
-    grep -q '^FRANK_ARCHON_MODEL_FILE=qwen4exp-swift15-w4dn8-i8-hc8m.rad$' "$ENV_FILE"
+    grep -q '^FRANK_ARCHON_MODEL_FILE=qwen3.8-next-flash-fp8-iq4r-moe.rad$' "$ENV_FILE"
-    grep -q 'qwen4exp-swift15-w4dn8-i8-hc8m.rad' "$BUILD"
+    grep -q 'StillDeadcode/qwen3.8-next-flash-fp8-iq4r-moe' "$DOWNLOAD"
-    grep -q 'ukisai/Swift1.5-Qwen3.8-Flash-Next' "$DOWNLOAD"
+    grep -q 'qwen3.8-next-flash-fp8-iq4r-moe.rad' "$DOWNLOAD"
    grep -q '0af5e96244e80c21ac8edca1719dae49b8a201b94a2f3994c3e24026ceaa4d20' "$DOWNLOAD"
    grep -q 'hfget.sh' "$DOWNLOAD"
    # The repo is UNGATED — no token may be required on the fetch path.
    ! grep -q 'HF_TOKEN' "$DOWNLOAD"
    # Rollback provenance: the w4dn8 build script names its payload.
    grep -q 'qwen4exp-swift15-w4dn8-i8-hc8m.rad' "$BUILD"
 }
@test "no bare HIP-reserved env var is defined" {
@@ -1,13 +1,14 @@
 # Seam: the frank-zealot llama.cpp root unit on dankclaw.
-# frank-zealot is the RTX 3090 endpoint; since 2026-10-07 it serves
+# frank-zealot is the RTX 3090 endpoint; since 2026-10-17 it serves
-# HauhauCS's Qwen3.5-9B-Uncensored-HauhauCS-Aggressive (Q6_K, qwen35 hybrid:
+# prism-ml/Ternary-Bonsai-2-27B-gguf at PQ2_0 — the ternary Bonsai-2-27B, a
-# 32 layers, 8 full-attention + 24 Gated DeltaNet, no MTP tensors in the file)
+# qwen35 hybrid with 64 blocks (16 full-attention + 48 Gated DeltaNet, no
-# via the CUDA (sm_86) build of llama.cpp master: TWO 200,704-token
+# nextn/mtp tensors in the file) — via the PrismML fork build of llama.cpp
-# conversations (--ctx-size 401408 --parallel 2), exact f16 K + f16 V under
+# (vendor build 10754), the ONLY loader that registers the payload's custom
-# flash attention, the publisher's own BF16 vision projector, and MTP off —
+# tensor type 142 and honours its prism.hadamard.* metadata: TWO 200,704-token
-# the file carries no nextn/mtp tensors, so there is no in-file head to draft
+# conversations (--ctx-size 401408 --parallel 2), q8_0 K + q8_0 V under flash
-# with. Log verbosity 4 ships so the VRAM-fit forensics (KV layout, buffer
+# attention (f16 KV does not fit this card at this pool — the boot dies on a
-# sizes, graph capture) land in the journal.
+# 25,088 MiB cudaMalloc), the publisher's own Q8_0 vision projector, and MTP
 # off. Log verbosity 4 ships so the VRAM-fit forensics land in the journal.
 # This seam runs the serve script against a stub engine and asserts on the
 # argv it actually execs, so what is pinned is the command the operator gets.
@@ -95,10 +96,15 @@ run_stage() {
    grep -q 'FRANK_ZEALOT_ENV_FILE=/home/dank/serverAppConfigs/scripts/frank-zealot.env' "$UNIT"
 }
-@test "the shipped env points at the llama.cpp runtime and the Qwen3.5-9B Q6_K GGUF" {
+@test "the shipped env points at the fork runtime and the Bonsai-2 PQ2_0 pair" {
-    # The payload path IS the endpoint's identity.
+    # The payload path IS the endpoint's identity, and the runtime is part of
-    grep -qE '^LLAMA_BIN=/home/dank/GitPackages/llama-master/build-cuda/bin/llama-server$' "$ENV_FILE"
+    # it here: the file's custom tensor type 142 + prism.hadamard.* metadata
-    grep -qE '^MODEL_FILE=/home/dank/models/Qwen35-9B-HauhauCS-Q6K/Qwen3\.5-9B-Uncensored-HauhauCS-Aggressive-Q6_K\.gguf$' "$ENV_FILE"
+    # make the PrismML build the only loader, so a retarget that moves the
    # model but leaves the master build behind ships an endpoint that cannot
    # load at all.
    grep -qE '^LLAMA_BIN=/home/dank/GitPackages/llama-prism/llama-server$' "$ENV_FILE"
    grep -qE '^MODEL_FILE=/home/dank/models/Bonsai2-PQ2_0/Ternary-Bonsai-2-27B-PQ2_0\.gguf$' "$ENV_FILE"
    grep -qE '^MMPROJ_FILE=/home/dank/models/Bonsai2-PQ2_0/Ternary-Bonsai-2-27B-mmproj-Q8_0\.gguf$' "$ENV_FILE"
 }
@test "the deployer gates on exactly the payload paths the env file ships" {
@@ -135,19 +141,23 @@ run_stage() {
    [ $((pool / slots)) -eq 200704 ]
 }
-@test "the KV contract is exact f16 K + f16 V, flash-attn on" {
+@test "the KV dtype pair follows the env file and flash-attn stays pinned on" {
    # Asserted against the env rather than a literal so a retune moves one
    # file, not two. The shipped pair is q8_0/q8_0: this payload bills
    # 16 full-attention layers × 4 KV heads × 256 dim = 16,384 elements per
    # token per cache, so f16/f16 would need 25,088 MiB of the 24,123 MiB card
    # (measured: cudaMalloc OOM, engine fit 33,198 vs 23,558 free) while q8_0
    # bills 34,816 B/token = 13,328.00 MiB at the 401,408 pool. The boot
    # ledger, not this file, is the referee. flash-attn is not decoration:
    # quantized V is only legal with it, and it must stay explicit so a
    # future quant swap cannot silently fall back.
    local env_k env_v
    env_k="$(sed -nE 's/^CACHE_TYPE_K=(.+)$/\1/p' "$ENV_FILE")"
    env_v="$(sed -nE 's/^CACHE_TYPE_V=(.+)$/\1/p' "$ENV_FILE")"
    serve_argv
    [ "$status" -eq 0 ]
-    # Frank, 2026-10-07: the 9B rung funds unquantized KV (the 26B MoE era
+    [ "$(argv_value --cache-type-k)" = "$env_k" ]
-    # shipped q8_0 V because the card was full). qwen35 bills the pool on the
+    [ "$(argv_value --cache-type-v)" = "$env_v" ]
    # 8 full-attention layers only (8 × 4 KV heads × 256 dim = 8,192
    # elements/token ⇒ 32 KiB/token at f16/f16, 12.25 GiB at the 401,408
    # pool); the 24 DeltaNet layers cost a fixed recurrent state per slot.
    # The boot ledger, not this file, is the referee. flash-attn stays pinned:
    # any quantized-V fallback (q8_0 = this build's FP8 class) requires it, and
    # the build carries GGML_CUDA_FA_ALL_QUANTS=ON.
    [ "$(argv_value --cache-type-k)" = "f16" ]
    [ "$(argv_value --cache-type-v)" = "f16" ]
    [ "$(argv_value --flash-attn)" = "on" ]
 }
@@ -105,8 +105,10 @@ for s in fleet:
 assert [s["name"] for s in fleet] == ["frank-zealot", "frank-dragoon", "frank-archon"], \
    "card render order must be zealot, dragoon, archon: " + str([s["name"] for s in fleet])
 w = {s["name"]: s["model"].get("warn", "") for s in fleet}
-assert w["frank-zealot"] == w["frank-dragoon"] != "", "the legal warnings must be the common uncensored text"
+assert "legal risk" in w["frank-dragoon"].lower() and "everybody" in w["frank-dragoon"].lower(), \
-assert "legal risk" in w["frank-zealot"].lower() and "everybody" in w["frank-zealot"].lower()
+    "the abliterated endpoint must carry the common legal warning"
 assert "censored" in w["frank-zealot"].lower() and "uncensored" not in w["frank-zealot"].lower(), \
    "zealot ships the censored base since 2026-10-17: its card warning must not claim uncensored output"
 archon = next(s for s in fleet if s["name"] == "frank-archon")
 assert "permission" in archon["model"], "archon card needs the ask-Frank permission callout"
 PY
Author	SHA1	Message	Date
Frank	f48b45c1fa	frank-zealot: sweep the live path — serve defaults, unit text, picker docs - serve script: header + every fallback default re-keyed to the Bonsai-2 trio (vendor LLAMA_BIN, PQ2_0 MODEL_FILE, Q8_0 MMPROJ) and CACHE_TYPE_*:=q8_0 — a defaulted run must land on the shipped shape, never on the retired 9B/f16 pair (the trial window proved a silent default is how a swap goes wrong) - unit Description now names the payload + KV dtype that `systemctl status` will show during the next incident - OpenWebUI decoration-row description re-keyed, with the law that the row is live DB state a swap must follow into the database	2026-10-17 19:42:13 -07:00
Frank	322ebb1658	docs(AGENTS): fleet topology + llama.cpp laws for the PQ2_0 zealot era - topology row + zealot section: PrismML vendor build, Bonsai-2 PQ2_0, q8_0 KV, measured ledger; runbook index active/retired rows - new durable laws: custom-tensor-type runtime door (vendor build is forced), mmproj outside the engine fit projection, first-request warmup artifact, thinking-budget probe traps + load-bearing reasoning_effort fold	2026-10-17 19:41:11 -07:00
Frank	7706e06775	docs(frank-zealot): Prism Bonsai-2 PQ2_0 runbook; indexes and log re-keyed - new runbook: runtime lock (build 10754 / type 142 door), geometry census, four-arm VRAM table (f16 wall, q8_0 deployed, q4_0 rung, 2x262,144), measured rate ladder, behavior contract, ops notes - LLM/index.md + vault root index: new ACTIVE entry, 9B era retired in place - log.md: the trial+cutover wave record, incl. the env-var-name law	2026-10-17 19:41:11 -07:00
Frank	f383038437	homepage: zealot card -> Ternary-Bonsai-2 PQ2_0 (censored base) - card/docs: prism-ml payload link, PQ2_0 spec, ~77 t/s (measured single stream, replacing the 9B's ~95) - warning re-keyed: zealot is no longer an uncensored endpoint, so the card carries the base-alignment notice and points uncensored work at dragoon; the test's "common uncensored text" equality (zealot==dragoon) is retired with the payload it described — dragoon alone carries the legal warning	2026-10-17 19:40:56 -07:00
Frank	64185d63b9	frank-zealot: cutover to Ternary-Bonsai-2 PQ2_0 with q8_0 KV - env: Bonsai2 payload pair, CACHE_TYPE_K/V=q8_0 (f16 OOMs at 2x200,704: 34 KiB vs 64 KiB/token over the 16 full-attention layers), measured boot ledger 22,664 used / 1,461 free incl. the 873 MiB mmproj that lands AFTER the engine fit check, q4_0 fallback rung, CRACK one-line MODEL_FILE swap - deployer: runtime/model/mmproj gates re-keyed to the PrismML vendor build (the only loader for GGML tensor type 142 + prism.hadamard.* metadata) - seam: payload trio pinned; KV argv assertions now derived from CACHE_TYPE_* in the env file — the wrong-var-name f16 fallback that produced the first failed trial window can no longer pass silently	2026-10-17 19:40:56 -07:00
Frank	430c42ab18	frank-zealot: Bonsai2 PQ2_0 candidate fetch script (official LFS shas; CRACK variant documented, unpinned)	2026-10-17 19:40:56 -07:00
dank	3ccc1e554f	Update README.md	2026-10-15 18:22:22 -07:00
dank	7a69c31128	Update README.md	2026-10-15 18:14:53 -07:00
Frank	f96898d4c5	docs(authentik): pk 22-23 provisioned — mitch + eric in the human-user template	2026-10-15 15:20:15 -07:00
Frank	3e140cd077	docs(log): iq4r swap cutover record — e2e 33/33 after gluetun boot-race repair	2026-10-15 05:53:42 -07:00
Frank	c5ac0725f7	docs(frank-archon): iq4r first-boot ledger — pin 1.0.13 loads w4nl, geometry verbatim kv_attn 26.00 KiB fp8 pages at 607,740 tokens (identical to the w4dn8 boot), slab 17,610/17,658 slots per rank (above w4dn8's 17,548 — ten bf16-protected experts per layer pack more of the 4-bit table), sampler 9 rows, MTP 2/step, KV lending 4.22 GiB, prefix tier recovered 900,176 blocks across the payload swap. Vision probe green (reasoning read the solid-red PNG; empty content at 64 tokens = the thinking-budget law). e2e gate RED on three dankclaw specs: Marreta was down since the 01:41 dankclaw reboot (marreta-browser dependency-failed at boot beside gluetun, not re-armed); pair restarted manually, redeploy rerunning the gate.	2026-10-15 05:44:09 -07:00
Frank	f44c39812f	docs(frank-archon): iq4r era runbook + index/AGENTS re-key New runbook frank-archon-radiance-qwen38-iq4r.md (publisher container, payload chain, shape-verbatim cutover record with the boot-ledger and measurement slots left open for the first boot, rollback). LLM index, root vault index, and AGENTS.md (fleet table row, section, runbook index: iq4r ACTIVE, w4dn8 RETIRED/on-disk, fp8-native deleted). Full suite green.	2026-10-15 04:16:28 -07:00
Frank	6dcf4a5913	llm(frank-archon): swap payload to the publisher's iq4r .rad, shape verbatim Model swap on the radiance endpoint: MODEL_FILE moves from the in-house qwen4exp-swift15-w4dn8-i8-hc8m.rad (116,416 MiB) to the engine author's published qwen3.8-next-flash-fp8-iq4r-moe.rad (116,322 MiB, official Qwen3.8-Flash-Next bf16 -> 4-bit non-uniform codebook experts + int8 trunk, card KL 0.0789 / top-1 92.85 % vs bf16). NO argument changed: 25600/5120 vram pair, 44928 host pool, fp8 KV, 3 x 200000, MTP depth 2, wht6, MNBT 2048, froggeric v22.5 — the 2026-10-13 shape carries verbatim. New fetch script scripts/download-frank-archon-iq4r.sh (hfget + exact byte count 121,969,901,568 + LFS sha256, --verify-only default, ungated, no token on the command line). Unit/serve/deployer lore re-keyed; the seam pins the new payload id + sha256 and keeps the w4dn8 rollback provenance. Homepage card points at the publisher repo. Rollback: revert this commit (w4dn8 .rad stays on disk). The fp8-native rad was deleted from dankserver 2026-10-15 (Frank's one-time rm, volume for this payload); rebuild path documented.	2026-10-15 04:10:50 -07:00