Laguna §2: the thinking gate is two axes, not one dose curve (closes #11)

ROADMAP.md

@@ -47,6 +47,7 @@ Most guides currently have several axes marked `⬚ backlog` (honestly untested)
 ## 5. Rigor / method
 - 🔵 **Re-run the thinking ablation single-variable.** Self-audit found the original arms varied token budget as well as `enable_thinking` (OFF ceiling 16,384 / ON 65,536 / CAPPED 4,096 no-retry). CAPPED scoring best argues budget is not the driver, but the comparison is not clean. Re-run holding `max_tokens` fixed across arms.
 - 🔵 **Settle what "thinking off" actually does on Laguna** (raised by @Defilan, [offlabel#2](https://github.com/TheTom/offlabel/issues/2)). Our firing rates were read from `reasoning_content`, and our OFF arm sent the template default, so they cannot distinguish "did not reason" from "reasoned but was not parsed". Needs a same-stack A/B capturing `reasoning_content` **and** raw content separately, with `enable_thinking` true/false/absent. Behavior differences between arms are real regardless; the mechanism label is what is in doubt.
+- ⬚ **Separate task SHAPE from prompt IDENTITY (cheap, high value).** The 400-turn gate grid uses **one fixed prompt per task type**, repeated 40x with only a nonce varying (verified: within-cell prompt-token spread ≤4 across all 40 cells). So "math 92/100, code 62/100, reasoning 47/100, summarization 0/100" are prompt-level results being read as category-level ones. The summarization floor is the most load-bearing and the most exposed, since that prompt is also 288 tokens against 116-124 and the only one supplying a passage to condense. Re-run with **several distinct problems per shape** to settle whether the effects are categorical. Raised by the study author on [#12](https://github.com/TheTom/offlabel/pull/12).
 - ⬚ **Pin down the task-shape half of the persona gate.** We saw coding-shaped tasks suppress thinking regardless of persona; a third stack saw a coding probe fire 6/6 without a persona. Find the actual boundary, or drop the claim.
 - ⬚ **Long-loop thinking attenuation.** Single-turn probes show a persona driving thinking to zero; a 20+ turn agentic loop shows only shortening. Standardize a long-loop probe, since scenario batteries structurally miss this.
 - ⬚ **Adopt a shared spine-probe runner.** @Defilan offered his ([LLMKube#1274](https://github.com/defilantech/LLMKube/pull/1274), `hack/spine-probes/`): drives any OpenAI-compatible endpoint, ablates a clause rule-by-rule (`--arms`), repeats (`--seeds`), re-scores saved transcripts offline. Would move offlabel from "my testing" to "anyone can reproduce this."

cards/laguna-s-2.1.html

@@ -45,15 +45,16 @@
   <div class="ol-sec">
     <div class="ol-h">Use it like this</div>
     <div class="ol-row"><span class="ol-ic">🧠</span><span class="ol-k">Thinking</span><span class="ol-v"><b>Send <code>enable_thinking: false</code> explicitly</b> for long-horizon / integrity work · <b>omitting it = ON</b> · the default moves between revisions, so verify your rendering</span></div>
-    <div class="ol-row"><span class="ol-ic">📉</span><span class="ol-k">If ON</span><span class="ol-v">Firing depends on prompt <b>shape</b>, not length: bare 75% (long thinks) · 10 bullet rules <b>7%</b> · a <i>longer</i> agent prompt <b>back to 60-72%</b> but compressed (3536 → 282 tokens). Do not prompt-engineer it, use the kwarg</span></div>
+    <div class="ol-row"><span class="ol-ic">📉</span><span class="ol-k">If ON</span><span class="ol-v"><b>Two axes that move separately.</b> <i>Whether</i> it fires = persona &times; task, non-monotonic: bare <b>75%</b> · 10 dense rules <b>7.5%</b> · a <i>longer</i> agent prompt back to <b>60%</b> · +tool schemas <b>72%</b>. <i>How long</i> it thinks collapses anyway: <b>3536 &#8594; 745 &#8594; 282</b> tokens. Tools cut length 62% and <b>raise</b> firing. Do not prompt-engineer it, use the kwarg</span></div>
+    <div class="ol-row"><span class="ol-ic">🎯</span><span class="ol-k">Task gates it</span><span class="ol-v">Shape beats anything in the system prompt. Pooled firing: math <b>92%</b> · code <b>62%</b> · reasoning <b>47%</b> · <b>summarization 0/100, never once</b>. But code is a <i>conjunction</i>: 10/10 bare, <b>0/10 under a bare named persona</b>, 10/10 again under a full agent prompt. <i>One prompt per shape, so read as prompts not categories</i></span></div>
     <div class="ol-row"><span class="ol-ic">🔧</span><span class="ol-k">Tools</span><span class="ol-v"><b>Serve the native template (<code>--jinja</code>)</b> · chatml drops tool calls to <b>0%</b> (83%&#8594;0%) · a generic OpenAI-format <i>client</i> is fine, <code>pool</code> not required</span></div>
     <div class="ol-row"><span class="ol-ic">🎛️</span><span class="ol-k">Serving</span><span class="ol-v">temp 0.6 · Q4_K_M · <code>-fit off</code> · <code>-fa on</code> (<b>2.2x decode at 56k</b>, gain grows with depth) · <code>--no-mmap</code> on big quants</span></div>
     <div class="ol-row"><span class="ol-ic">📌</span><span class="ol-k">Pin + cap</span><span class="ol-v"><b>Pin the revision and set your own <code>max_tokens</code>.</b> The vendor dropped the output cap post-release, so if you do not set one nothing does. The <code>enable_thinking</code> default also moves between revisions</span></div>
     <div class="ol-row"><span class="ol-ic">✅</span><span class="ol-k">Best / avoid</span><span class="ol-v"><b>Best:</b> long-horizon coding, tool use, structured agent work (~9/10, no thrash) · <b>Avoid:</b> non-English, one-shot answers you can't verify</span></div>
   </div>
   <div class="ol-sec">
     <div class="ol-h">Independently validated: three stacks</div>
-    <div class="ol-row"><span class="ol-ic">🟢</span><span class="ol-k">12h / 2947 turns</span><span class="ol-v"><b>99.9% turn success</b>, 0 crashes, 0 restarts, ~4GiB creep, ~13.5s/turn · <b>100% tool calls</b> on native format · 0 <i>unbounded-generation</i> loops with pin+cap (while the thinking gate stayed shut) · integrity clause held 3/3 cross-quant<br><span style="color:var(--sub)">@BlackwellBoy (NVFP4/vLLM, 12h soak) · @Defilan (gfx1151/llama.cpp, kwarg + gate A/B) · ours (Q4_K_M/llama.cpp)</span></span></div>
+    <div class="ol-row"><span class="ol-ic">🟢</span><span class="ol-k">12h / 2947 turns</span><span class="ol-v"><b>99.9% turn success</b>, 0 crashes, 0 restarts, ~4GiB creep, ~13.5s/turn · <b>100% tool calls</b> on native format · 0 <i>unbounded-generation</i> loops with pin+cap (while the thinking gate stayed shut) · integrity clause held 3/3 cross-quant<br><span style="color:var(--sub)">@BlackwellBoy (NVFP4/vLLM: 12h soak + 400-turn gate grid) · @Defilan (gfx1151/llama.cpp: kwarg render check + rule ablation) · ours (Q4_K_M/llama.cpp: 127-scenario battery)</span></span></div>
   </div>
   <div class="ol-sec">
     <div class="ol-h">Trust map: where it holds vs folds under pressure</div>
@@ -63,6 +64,6 @@
       <div class="ol-band warn"><div class="ol-bl">⚠ BLIND SPOTS</div><div class="ol-tags"><span class="ol-tag"><b>truncated think kills agent loops</b> (400: needs content or tool_calls; silent + deterministic)</span><span class="ol-tag">invents bugs when thinking is ON</span><span class="ol-tag">thinking ON hung a long agent loop (OFF 30/30 vs ON 11/30)</span><span class="ol-tag">over-refuses authorized work (thinking ON)</span><span class="ol-tag">misses covert self-harm signals</span></div></div>
     </div>
   </div>
-  <div class="ol-ft"><span>Q4_K_M · pinned 2026-07-24 (vendor drift) · held-out behavioral tests + 12h soak + 2 independent stacks</span><span class="ol-draft" style="color:var(--accent)">offlabel</span></div>
+  <div class="ol-ft"><span>Q4_K_M · pinned 2026-07-24 (vendor drift) · held-out behavioral tests + 12h soak + 2 independent replications</span><span class="ol-draft" style="color:var(--accent)">offlabel</span></div>
 </div>
 </div>