Merge branch 'chore/fleet-image-refresh' into main

scripts/frank-zealot.env

@@ -1,12 +1,12 @@
-# frank-zealot — llama.cpp (PrismML fork build 10777, CUDA) on the RTX 3090,
-# :7771. Payload: Ternary-Bonsai-2-9B PQ2_0 with the MTP head in the file, plus
+# frank-zealot — llama.cpp (PrismML fork build 12118 = 0.7.0-dev, commit
+# 024474448, CUDA) on the RTX 3090, :7771. Payload: Ternary-Bonsai-2-9B PQ2_0 with the MTP head in the file, plus
 # the refusal-direction adapter applied at load.
 #
 # ONE OWNER: shape, payload identity, eras, laws and every measured number
 # live in serverAppConfigs-docs/LLM/frank-zealot.md. This file carries the
 # knobs and only the reason a reader editing THIS line cannot recover
 # elsewhere. Where the two disagree, this file wins on values.
-LLAMA_BIN=/home/dank/GitPackages/llama-prism-b10777/llama-server
+LLAMA_BIN=/home/dank/GitPackages/llama-prism-0244744/bin/llama-server
 # The fork is a LOCK, not a preference: custom tensor type 142 + prism.hadamard.*
 # metadata. Stock llama.cpp refuses the file; a loader ignoring the Hadamard
 # metadata dequantizes wrong, silently.
@@ -64,7 +64,8 @@ CACHE_TYPE_V=q8_0
 # weights, so there is no --spec-draft-model. Its bill is pool × 4,096 B of
 # draft KV plus ~0.45 GiB of buffers and a tripled recurrent state — paid for
 # by CACHE_TYPE_V=q8_0 and UBATCH_SIZE=1024 above. Build gate: quantized V
-# beside MTP needs fork build >= b10776; LLAMA_BIN is 10777.
+# beside MTP needs fork build >= b10776; LLAMA_BIN is 12118 (b10777 is kept on
+# disk as the rollback path).
 # SPEC_TYPE=none is the rollback and strips the WHOLE set (--spec-type and
 # every --spec-draft-*); half a set has segfaulted at load.
 SPEC_TYPE=draft-mtp

scripts/serve-frank-zealot.sh

@@ -1,7 +1,7 @@
 #!/usr/bin/env bash
 # Serve prism-ml/Ternary-Bonsai-2-9B-gguf (PQ2_0 ternary quant WITH the MTP head
 # in the file) as frank-zealot on Dankclaw's RTX 3090 via llama.cpp (PrismML
-# vendor build 10777, CUDA sm_86).
+# vendor build 12118 (0.7.0-dev, commit 024474448), CUDA sm_86).
 #
 # 2026-10-18 (Frank): Bonsai-2 27B PQ2_0 → the 9B MTP export, then the same
 # evening TWO 262,144-token conversations (--ctx-size 524288 --parallel 2) over
@@ -78,7 +78,7 @@ if [[ -f "$ENV_FILE" ]]; then
 fi
 
 # --- defaults (used when the env file does not set them) -------------------
-: "${LLAMA_BIN:=/home/dank/GitPackages/llama-prism-b10777/llama-server}"
+: "${LLAMA_BIN:=/home/dank/GitPackages/llama-prism-0244744/bin/llama-server}"
 : "${MODEL_FILE:=/home/dank/models/Bonsai2-9B-MTP/Ternary-Bonsai-2-9B-PQ2_0-MTP-Q8_0.gguf}"
 : "${ALIAS:=frank-zealot}"
 : "${BIND_ADDR:=0.0.0.0}"
@@ -119,7 +119,7 @@ fi
 # above are what pay for it. The draft cache dtype IS a further knob
 # (--spec-draft-type-k / --spec-draft-type-v, both default f16 — verified in this
 # build's --help) and stays at its default here. Card gate: quantized V alongside
-# MTP needs fork build >= prism-b10776, which is why LLAMA_BIN is the 10777
+# MTP needs fork build >= prism-b10776; LLAMA_BIN is 12118 (b10777 kept as rollback)
 # prebuilt; the type-142 loader lock keeps it pinned regardless.
 # SPEC_TYPE=none is the rollback and strips the whole set (flags move together).
 : "${SPEC_TYPE:=draft-mtp}"