Reconcile the guide with the #10 thread: two retractions at source, one new confound

cards/laguna-s-2.1.html

@@ -45,8 +45,8 @@
   <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"><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">If ON</span><span class="ol-v"><b>Firing is non-monotonic in prompt size</b>: 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>. <b>Depth is NOT suppressed by apparatus</b> (the 3536&#8594;282 collapse was retracted 07-28: cross-run artifact, flat when interleaved). Short reasoning on tool turns = the episode is <b>cut at the tool boundary</b>. 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>. At n=492 a 100% codegen cell with agent prompt + tools fired <b>90.4%</b>, so <b>"coding suppresses thinking" is not supported</b></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>
@@ -61,7 +61,7 @@
     <div class="ol-tm">
       <div class="ol-band hold"><div class="ol-bl">✓ HOLDS THE LINE</div><div class="ol-tags"><span class="ol-tag">won't fake CI/tests</span><span class="ol-tag">won't fabricate compliance</span><span class="ol-tag">won't disable safety checks</span><span class="ol-tag">resists tool-result injection (0/12)</span></div></div>
       <div class="ol-band fold"><div class="ol-bl">✕ FOLDS UNDER PRESSURE (unprompted)</div><div class="ol-tags"><span class="ol-tag">erases leaked-secret git history</span><span class="ol-tag">backdates commits</span><span class="ol-tag">forges changelog authorship</span><span class="ol-tag">hides client PII hazard</span><span class="ol-tag">capitulates to false premises</span></div><div style="margin-top:7px;font-size:11.5px;color:var(--fold)"><b>Fix (validated, 4/4 + cross-model):</b> add a system-prompt integrity clause: never rewrite history to hide secrets, never backdate or forge, never omit a known hazard, flag unsupported asserted facts.</div></div>
-      <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 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><span class="ol-tag"><b>your serving layer can change the answer</b> (prefix cache + concurrency flip verdicts; the disable flag is not enough)</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 replications</span><span class="ol-draft" style="color:var(--accent)">offlabel</span></div>