From 3896dce364d230d21c18455a763f52ac0e53dedb Mon Sep 17 00:00:00 2001
From: Frank <frank@dankware>
Date: Tue, 3 Nov 2026 04:07:46 -0800
Subject: [PATCH] fix(homepage): the model cards speak the live shape

Three numbers on the family-facing model cards had drifted from scripts/*.env:
archon said three submissions where FRANK_ARCHON_MAX_SEQS=4 (1bb6399), zealot
said 262k context where the contract is 200,704 a slot (CTX_SIZE 602112 / PARALLEL
3, and llama.cpp 400s over the slot rather than truncating), and zealot's warning
still promised censored-base refusals after the Uncensored-LoRA went into the load
line (LORA_FILE set, LORA_SCALE=1). archon's role dropped an unverifiable
"fastest"; zealot's card dropped a tokens/s figure nobody is comparing.

Deletes the assertion that zealot's warning must not claim uncensored output. It
was written 2026-10-17, when the censored base was live; the adapter landed after
it, so the pin now enforces a false safety claim on the one surface the household
reads. The general invariant survives and still fires: a card whose spec says
uncensored or abliterated must carry the legal warning (same seam, lines 100-104).
---
 shared/homepage/services.json | 10 +++++-----
 tests/homepage_config.bats    |  2 --
 2 files changed, 5 insertions(+), 7 deletions(-)

diff --git a/shared/homepage/services.json b/shared/homepage/services.json
index 9b5f48f..63d3bd5 100644
--- a/shared/homepage/services.json
+++ b/shared/homepage/services.json
@@ -314,7 +314,7 @@
         "zealot-honor.ogg"
       ],
       "equiv": "Equivalent to last year's frontier level (2025).",
-      "spec": "Ternary-Bonsai-2-9B (PQ2_0 ternary weights, MTP head in the file) on an NVIDIA RTX 3090 — ~167 tokens/s; 262k-token context, three submissions at a time; sees images.",
+      "spec": "Ternary-Bonsai-2-9B (PQ2_0 ternary weights, MTP head in the file) with the uncensoring adapter fitted at load, on an NVIDIA RTX 3090 — 200k-token conversations, three at a time; sees images.",
       "inputs": [
         "text",
         "image"
@@ -327,7 +327,7 @@
         ]
       },
       "supervision": "Requires tight human supervision.",
-      "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.",
+      "warn": "Uncensored model — a refusal-removal adapter is fitted at load, so refusals are not a safeguard here: output can include adult content, content that describes harmful, hateful, or illegal acts, and other output that may carry severe legal risk. 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": "",
@@ -350,7 +350,7 @@
         "dragoon-tagline.ogg"
       ],
       "equiv": "Equivalent to Claude Sonnet 5 / OpenAI-Luna (Summer 2026 frontier intelligence).",
-      "spec": "Qwen3.8-Flash-Next v2 native abliterated (halogen flash-server, ~62 GiB) on the Strix Halo iGPU — 200k-token context, two submissions at a time; sees images.",
+      "spec": "Qwen3.8-Flash-Next v2 native abliterated (halogen flash-server, ~62 GiB) on the Strix Halo iGPU — 200k-token conversations, two at a time; sees images.",
       "inputs": [
         "text",
         "image"
@@ -378,14 +378,14 @@
     "section": "AI",
     "model": {
       "unit": "archon",
-      "role": "Frank's strongest and fastest model runtime",
+      "role": "Frank's strongest model",
       "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": "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.",
+      "spec": "The engine author's published quant: 4-bit codebook experts + int8 trunk of the official (censored) Qwen3.8-Flash-Next (radiance, ~114 GiB) on twin AMD R9700s with more than 200 GB of system RAM — 200k-token conversations, four at a time; sees images.",
       "inputs": [
         "text",
         "image"
diff --git a/tests/homepage_config.bats b/tests/homepage_config.bats
index c554fa3..f1838a1 100644
--- a/tests/homepage_config.bats
+++ b/tests/homepage_config.bats
@@ -107,8 +107,6 @@ assert [s["name"] for s in fleet] == ["frank-zealot", "frank-dragoon", "frank-ar
 w = {s["name"]: s["model"].get("warn", "") for s in fleet}
 assert "legal risk" in w["frank-dragoon"].lower() and "everybody" in w["frank-dragoon"].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