README.md

@@ -165,12 +165,12 @@ Add your API keys in Settings (⌘,) → General tab:
 - **Max Tokens** - Set maximum response length
 - **Temperature** - Control response randomness (0.0 - 2.0)
 - **Reasoning** - Enable thinking tokens for supported models; set effort level (High/Medium/Low/Minimal); optionally hide reasoning content from chat
+- **Crash Recovery** - How often the in-progress conversation is mirrored to disk (Off/1s/10s/30s/60s), so a crash or force-quit doesn't lose it
 
 #### Advanced Tab
 - **Smart Context Selection** - Reduce token usage automatically
 - **Semantic Search** - Enable AI-powered conversation search
 - **Progressive Summarization** - Handle long conversations efficiently
-- **Crash Recovery** - How often the in-progress conversation is mirrored to disk (Off/1s/10s/30s/60s), so a crash or force-quit doesn't lose it
 
 #### Sync Tab
 - **Repository URL** - Git repository for conversation backup

oAI/Resources/oAI.help/Contents/Resources/en.lproj/index.html

@@ -525,7 +525,7 @@
                 </ul>
 
                 <div class="tip">
-                    <strong>💡 Crash Recovery:</strong> While you're chatting, oAI periodically mirrors the in-progress conversation to disk (every 10 seconds by default — adjustable or turned off in Settings → Advanced). If oAI crashes or is force-quit, the next launch offers to restore the conversation you were working on, including the model you had selected. This mirror is invisible and separate from your saved conversations — it's cleared automatically as soon as you save, discard, or restore it.
+                    <strong>💡 Crash Recovery:</strong> While you're chatting, oAI periodically mirrors the in-progress conversation to disk (every 10 seconds by default — adjustable or turned off in Settings → General). If oAI crashes or is force-quit, the next launch offers to restore the conversation you were working on, including the model you had selected. This mirror is invisible and separate from your saved conversations — it's cleared automatically as soon as you save, discard, or restore it.
                 </div>
 
                 <h3>Renaming Conversations</h3>
@@ -1590,6 +1590,7 @@ Whenever the user asks you to translate something, translate it to Norwegian Bok
                             <li><strong>Reasoning</strong> — enable thinking tokens, set effort level (High / Medium / Low / Minimal), optionally hide reasoning content from chat (see <a href="#reasoning">Reasoning / Thinking Tokens</a>)</li>
                         </ul>
                     </li>
+                    <li><strong>Crash Recovery</strong> — how often the in-progress conversation is mirrored to disk (Off, 1s, 10s, 30s, 60s); see <a href="#unsaved-changes">Unsaved Changes &amp; Crash Recovery</a></li>
                 </ul>
 
                 <h3>MCP Tab</h3>
@@ -1698,7 +1699,6 @@ Whenever the user asks you to translate something, translate it to Norwegian Bok
                     <li><strong>Smart Context Selection</strong> — Intelligently select relevant messages to reduce token usage</li>
                     <li><strong>Semantic Search</strong> — Enable AI-powered conversation search using embeddings</li>
                     <li><strong>Progressive Summarization</strong> — Automatically summarize old portions of long conversations</li>
-                    <li><strong>Crash Recovery</strong> — how often the in-progress conversation is mirrored to disk (Off, 1s, 10s, 30s, 60s); see <a href="#unsaved-changes">Unsaved Changes &amp; Crash Recovery</a></li>
                 </ul>
 
                 <h3>Backup Tab</h3>