diff --git a/src/pages/changelog.astro b/src/pages/changelog.astro index 61067e7..6e46078 100644 --- a/src/pages/changelog.astro +++ b/src/pages/changelog.astro @@ -54,6 +54,7 @@ import BaseLayout from '../layouts/BaseLayout.astro';
  • Zaguán Coder Daemon. Fixed a bug where it reconnected to the provider in a longer session.
  • Zaguán Coder Daemon. Wired up zlp_request. It was planned, but missing.
  • Zaguán Coder Daemon. Fixed loading the History in Zaguán Blade.
    • +
  • File Explorer. Fixed a bug where moving files was not possible using the mouse.
    • diff --git a/src/pages/docs.astro b/src/pages/docs.astro index cf7ef2d..0c4e691 100644 --- a/src/pages/docs.astro +++ b/src/pages/docs.astro @@ -66,15 +66,20 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    1
    -

    Get Your API Key

    -

    Visit ZaguanAI.com and subscribe to get your Zaguán API Key.

    -
    Without a valid API Key, Zaguán Blade functions as a standard, high-performance text editor.
    +

    Choose Your AI Path

    +

    Zaguán Blade supports both Local AI (private, no API key) and Cloud AI (faster hosted models). You can use either or both.

    +
    + Local AI + Cloud AI + Hybrid +
    2
    -

    Configure Account

    -

    Launch Zaguán Blade, click the Gear Icon (Settings) in the bottom-left corner, go to the Account tab, and paste your API Key.

    +

    Set Up Your AI Provider

    +

    For Local AI: Open Settings > Local AI and enable Ollama or an OpenAI-compatible server. No API key required.

    +

    For Cloud AI: Go to Settings > Account and add your Zaguán API key for hosted models.

    @@ -227,10 +232,14 @@ import BaseLayout from '../layouts/BaseLayout.astro';

    Context is Key

    -

    The AI automatically knows about the file you are currently looking at. You don't need to copy-paste code into the chat.

    +

    The AI automatically knows about your workspace context. You don't need to copy-paste code into the chat.

      -
    • Ask questions - "Explain this function", "Refactor this to be more performant", "Find the bug in this logic"
      • -
    • Tasking - "Create a new component for X", "Update the CSS to match this design", "Run the tests and fix the failure"
      • +
    • Active file - The file you are currently viewing
      • +
    • Open files - All open tabs in the editor
      • +
    • Cursor & selection - Your cursor position and any selected text
      • +
    • Mentioned paths - Files referenced via @path in chat
      • +
    • Diagnostics - Recent build errors and compiler warnings
      • +
    • Project structure - File tree and symbol index when needed
    @@ -248,23 +257,73 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    + +
    +
    +
    [007] CHAT_MODES
    +

    Chat Modes

    +

    Zaguán Blade supports two chat modes accessible from the Command Center:

    + +
    +
    +
    Code Mode
    +

    The default mode for implementing and executing. The AI can read files, edit code, run terminal commands, and make changes to your project.

    +
    +
    +
    Planning Mode
    +

    Investigate and build a plan before coding. The AI explores your codebase, researches approaches, and proposes architecture — no edits or commands are executed.

    +
    +
    +
    Implement Action
    +

    After reviewing a plan in Planning mode, use Implement to convert the plan into a code-mode request and start building.

    +
    +
    +
    +
    +
    -
    [007] SETTINGS
    +
    [008] SETTINGS

    Configuration

    +
    +
    + ⚙ +

    Configuration

    +
    +
      +
    • Theme - Zaguán Dark, Blade Coder, Blade Cream, Blade Robot
      • +
    • Language - UI language preference
      • +
    • Markdown View - Toggle edit/view mode for markdown files
      • +
    +
    +
    👤

    Account Tab

      -
    • API Key - Your Zaguán subscription key for AI features
      • +
    • API Key - Your Zaguán subscription key for cloud AI models
    • Manage Subscription - Link to your account dashboard
    + +
    +
    + 🤖 +

    Local AI Tab

    +
    +
      +
    • Ollama - Connect to a local Ollama instance
      • +
    • Ollama Cloud - Connect to Ollama via ngrok/remote
      • +
    • OpenAI-compatible - Any OpenAI-compatible server endpoint
      • +
    • Test Connection - Verify your local AI setup
      • +
    • Refresh Models - Reload available models from providers
      • +
    +
    @@ -291,6 +350,19 @@ import BaseLayout from '../layouts/BaseLayout.astro';
  • Allow .gitignored Files - Include gitignored files in AI context
    • + +
    +
    + ℹ +

    About Tab

    +
    +
      +
    • Version - Current Zaguán Blade version
      • +
    • Runtime - Tauri runtime information
      • +
    • Engine - WebView engine details
      • +
    • Local-First - Privacy and data control details
      • +
    +
    @@ -298,7 +370,7 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    -
    [008] PROJECT_INSTRUCTIONS
    +
    [009] PROJECT_INSTRUCTIONS

    Customize Your AI

    @@ -331,7 +403,7 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    -
    [009] EDITOR_FEATURES
    +
    [010] EDITOR_FEATURES

    Additional Features

    @@ -368,7 +440,7 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    -
    [010] SCREENSHOT_CAPTURE
    +
    [011] SCREENSHOT_CAPTURE

    Screenshot Capture

    Attach screenshots to your chat messages to give the AI visual context. Access capture options from the Feature Menu (grid icon) in the Command Center.

    @@ -383,6 +455,11 @@ import BaseLayout from '../layouts/BaseLayout.astro';

    Capture Region

    Select a window, then drag to crop a specific region from it.

    +
    +
    📤
    +

    Upload Image

    +

    Attach an existing image file to the chat conversation for visual context.

    +
    @@ -401,7 +478,7 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    -
    [011] PRIVACY_&_DATA
    +
    [012] PRIVACY_&_DATA

    Your Data, Your Control

    @@ -410,6 +487,11 @@ import BaseLayout from '../layouts/BaseLayout.astro';

    No Telemetry

    Zaguán Blade does not collect usage telemetry.

    +
    +
    🤖
    +

    Local AI Privacy

    +

    Local AI models run entirely on your machine. Prompts and code never leave your computer when using Ollama or local OpenAI-compatible servers.

    +
    🔒

    Local Storage Mode

    @@ -418,7 +500,7 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    🔐

    Server Storage Mode

    -

    Conversations are encrypted on Zaguán servers.

    +

    Conversations are encrypted on Zaguán servers. Cloud AI requests are processed on Zaguán infrastructure.

    @@ -427,25 +509,29 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    -
    [012] LOCAL_AI_SYSTEM_PROMPTS
    +
    [013] LOCAL_AI_SYSTEM_PROMPTS

    Custom System Prompts

    - 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. + When using Local AI models (Ollama or OpenAI-compatible), you can customize the system prompt for each model by creating a file with the model name or a compatible fallback name.

    - Linux: ~/.config/zblade/prompts/[exact-model-name].md + Linux: ~/.config/zblade/prompts/[model-name].md
    - Windows: %APPDATA%\zblade\prompts\[exact-model-name].md + Windows: %APPDATA%\zblade\prompts\[model-name].md
    - macOS: ~/Library/Application Support/zblade/prompts/[exact-model-name].md + macOS: ~/Library/Application Support/zblade/prompts/[model-name].md
    + +

    + Blade tries provider-qualified, stripped, lowercased, and base-model prompt filenames, so exact case and format is no longer required. +

    @@ -500,7 +586,7 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    -
    [013] TOOL_CALLS_REFERENCE
    +
    [014] TOOL_CALLS_REFERENCE

    Tool Calls Reference

    @@ -525,7 +611,7 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    -
    [014] KNOWN_BUGS
    +
    [015] KNOWN_BUGS

    Known Issues

    As an alpha release, there are some known limitations and bugs we're actively working on:

    @@ -564,7 +650,7 @@ import BaseLayout from '../layouts/BaseLayout.astro';
    -
    [015] SUPPORT_&_FEEDBACK
    +
    [016] SUPPORT_&_FEEDBACK

    Alpha Release

    @@ -817,6 +903,14 @@ import BaseLayout from '../layouts/BaseLayout.astro'; padding-top: var(--space-sm); border-top: 1px solid var(--color-border); } + + .step-or { + font-size: 0.85rem; + color: var(--color-text-secondary); + margin-top: var(--space-sm); + padding-top: var(--space-sm); + border-top: 1px dashed var(--color-border); + } .step-options { display: flex; diff --git a/src/pages/tools.astro b/src/pages/tools.astro index bd1989d..a6e1f47 100644 --- a/src/pages/tools.astro +++ b/src/pages/tools.astro @@ -38,6 +38,9 @@ import BaseLayout from '../layouts/BaseLayout.astro'; Directory & Search Editor Interaction Command Execution + Code Intelligence + Project Index + Composite Tools Result Handling Path Resolution System Prompt @@ -791,29 +794,53 @@ import BaseLayout from '../layouts/BaseLayout.astro'; run_command TERMINAL
    -

    Execute a shell command (requires user approval).

    +

    Execute a command in the workspace (requires user approval). Supports both legacy shell-line and structured program+args modes.

    -

    Parameters

    +

    Structured Mode (preferred)

    - - + + + +
    NameTypeDescription
    commandrequired stringShell command to execute
    cwdrequired stringWorking directory
    programrequired* stringExecutable path/name
    argsoptional arrayStructured arguments list
    shelloptional booleanForce shell execution (default: false in structured mode)
    cwdoptional stringWorking directory
    -
    -

    Example

    - 
    {
+              
    
+                
    Legacy Shell Mode
    
+                
+                  
+                  
+                    
+                    
+                    
+                    
+                  
+                
    NameTypeDescription
    commandrequired* stringShell command line to execute
    cwdoptional stringWorking directory
    blockingoptional booleanWait for completion (default: true)
    wait_ms_before_asyncoptional integerStartup wait when non-blocking
    
+              
    
+              
    
+                
    
+                  
    Structured (preferred)
    
+                  
    {
+  "program": "cargo",
+  "args": ["build", "--release"],
+  "cwd": "."
+}
    
+                
    
+                
    
+                  
    Legacy Shell
    
+                  
    {
   "command": "cargo build --release",
   "cwd": "."
 }
    
+                
    
               
    
               
    
                 ⚠️
-                
    This tool requires user confirmation before execution for safety.
    
+                
    This tool requires user confirmation before execution. Provide either command or program, not both.