Add Local AI system prompts documentation and known bugs section to docs page

src/pages/docs.astro

@@ -391,10 +391,116 @@ import BaseLayout from '../layouts/BaseLayout.astro';
       </div>
     </section>
 
+    <!-- Local AI System Prompts Section -->
+    <section id="local-ai-prompts" class="docs-section">
+      <div class="container">
+        <div class="section-label">[011] LOCAL_AI_SYSTEM_PROMPTS</div>
+        <h2 class="section-title">Custom System Prompts</h2>
+        
+        <div class="instructions-content">
+          <p class="instructions-intro">
+            When using Local AI models (Ollama or OpenAI-compatible), you can customize the system prompt for each model by creating a file with the exact model name.
+          </p>
+          
+          <div class="prompt-paths">
+            <div class="prompt-path-item">
+              <strong>Linux:</strong> <code class="inline-code">~/.config/zblade/prompts/[exact-model-name].md</code>
+            </div>
+            <div class="prompt-path-item">
+              <strong>Windows:</strong> <code class="inline-code">%APPDATA%\zblade\prompts\[exact-model-name].md</code>
+            </div>
+            <div class="prompt-path-item">
+              <strong>macOS:</strong> <code class="inline-code">~/Library/Application Support/zblade/prompts/[exact-model-name].md</code>
+            </div>
+          </div>
+          
+          <div class="code-block">
+            <div class="code-header">
+              <span class="code-filename">~/.config/zblade/prompts/glm-4.7-flash:Q4_K_M.md</span>
+              <span class="code-lang">markdown</span>
+            </div>
+            <pre><code>You are an AI coding assistant in Zaguán Blade. Help users write, understand, and improve code efficiently.
+
+# Core Rules
+
+- When asked who and what you are, you are "glm-4.7-flash, an AI coding assistant in Zaguán Blade."
+- Understand context before acting
+- Match existing code style and conventions
+- Verify libraries exist before using them (check imports, package.json, etc.)
+- Use absolute file paths
+- Read files before editing them
+- Add comments sparingly - focus on "why" not "what"
+- If unclear, ask for clarification
+
+# Communication
+
+- Be concise and direct
+- Use markdown for code blocks
+- No preamble ("Great!", "Certainly!")
+- Jump straight to the task
+
+# Available Tools
+
+**get_workspace_structure** - Get project directory tree
+**list_dir** - List files/directories in a path
+**read_file** - Read file contents  
+**write_file** - Create or overwrite a file
+**apply_patch** - Replace specific content in a file (for edits)
+**grep_search** - Search for patterns across files
+**run_command** - Execute shell commands
+**get_editor_state** - Get currently open file and cursor position</code></pre>
+          </div>
+          
+          <p class="instructions-note">
+            We encourage you to try Local AI and <a href="https://github.com/ZaguanLabs/ZaguanBlade/issues" target="_blank" rel="noopener">report any bugs or issues</a> you encounter!
+          </p>
+        </div>
+      </div>
+    </section>
+
+    <!-- Known Bugs Section -->
+    <section id="known-bugs" class="docs-section section-alt">
+      <div class="container">
+        <div class="section-label">[012] KNOWN_BUGS</div>
+        <h2 class="section-title">Known Issues</h2>
+        <p class="section-desc">As an alpha release, there are some known limitations and bugs we're actively working on:</p>
+        
+        <div class="bugs-grid">
+          <div class="bug-card">
+            <div class="bug-icon">⚠️</div>
+            <h3>Local AI Support</h3>
+            <p>Local AI support may not work consistently in all scenarios. We're actively improving reliability.</p>
+          </div>
+          
+          <div class="bug-card">
+            <div class="bug-icon">🔧</div>
+            <h3>Git Implementation</h3>
+            <p>The Git integration is incomplete. Some advanced Git operations may not be available yet.</p>
+          </div>
+          
+          <div class="bug-card">
+            <div class="bug-icon">📝</div>
+            <h3>Diff/Patch View</h3>
+            <p>The Diff/Patch view may not be 100% complete. Edge cases in code review might behave unexpectedly.</p>
+          </div>
+          
+          <div class="bug-card">
+            <div class="bug-icon">💾</div>
+            <h3>Local Storage Mode</h3>
+            <p>Local Storage Mode hasn't been extensively tested. Use with caution and report any issues.</p>
+          </div>
+        </div>
+        
+        <div class="bug-cta">
+          <p>Found a bug not listed here? Please <a href="https://github.com/ZaguanLabs/ZaguanBlade/issues" target="_blank" rel="noopener">report it on GitHub</a>.</p>
+        </div>
+      </div>
+    </section>
+
     <!-- Support Section -->
     <section id="support" class="docs-section">
       <div class="container">
-        <div class="section-label">[011] SUPPORT_&_FEEDBACK</div>
+        <div class="section-label">[013] SUPPORT_&_FEEDBACK</div>
         <div class="support-card">
           <div class="support-header">
             <h2>Alpha Release</h2>
@@ -1031,6 +1137,97 @@ import BaseLayout from '../layouts/BaseLayout.astro';
     font-style: italic;
   }
   
+  .instructions-note a {
+    color: var(--color-accent);
+    text-decoration: underline;
+  }
+  
+  .instructions-note a:hover {
+    color: var(--color-text);
+  }
+  
+  .prompt-paths {
+    display: grid;
+    gap: var(--space-md);
+    margin-bottom: var(--space-xl);
+    background: var(--color-bg-elevated);
+    border: 1px solid var(--color-border);
+    padding: var(--space-lg);
+  }
+  
+  .prompt-path-item {
+    font-size: 0.95rem;
+    color: var(--color-text-secondary);
+    line-height: 1.6;
+  }
+  
+  .prompt-path-item strong {
+    color: var(--color-text);
+    display: inline-block;
+    min-width: 80px;
+  }
+  
+  /* Known Bugs */
+  .bugs-grid {
+    display: grid;
+    grid-template-columns: repeat(auto-fit, minmax(280px, 1fr));
+    gap: var(--space-lg);
+    margin-bottom: var(--space-xl);
+  }
+  
+  .bug-card {
+    background: var(--color-bg);
+    border: 1px solid var(--color-border);
+    padding: var(--space-lg);
+    transition: all 0.3s ease;
+  }
+  
+  .bug-card:hover {
+    border-color: var(--color-accent-alt);
+    transform: translateY(-4px);
+  }
+  
+  .bug-icon {
+    font-size: 2rem;
+    margin-bottom: var(--space-sm);
+  }
+  
+  .bug-card h3 {
+    font-size: 1.125rem;
+    font-weight: 700;
+    margin-bottom: var(--space-sm);
+    text-transform: uppercase;
+  }
+  
+  .bug-card p {
+    color: var(--color-text-secondary);
+    font-size: 0.95rem;
+    line-height: 1.6;
+  }
+  
+  .bug-cta {
+    text-align: center;
+    padding: var(--space-lg);
+    background: var(--color-bg-elevated);
+    border: 1px solid var(--color-border);
+  }
+  
+  .bug-cta p {
+    font-size: 1.125rem;
+    color: var(--color-text-secondary);
+    margin: 0;
+  }
+  
+  .bug-cta a {
+    color: var(--color-accent);
+    text-decoration: underline;
+    font-weight: 600;
+  }
+  
+  .bug-cta a:hover {
+    color: var(--color-text);
+  }
+  
   /* Features List */
   .features-list {
     display: grid;

src/pages/index.astro

@@ -33,6 +33,7 @@ const version = pkg.version ?? "";
             The graphical frontend ("The Body") for the Zaguán AI system. 
             Built with Vite + React Router as recommended by Tauri developers.
             A lightweight, high-performance interface with deep AI integration through the Blade Protocol.
+            Supports Local AI via Ollama and OpenAI-compatible connections.
           </p>
           <div class="hero-actions">
             <a href="#download" class="action-primary">