add remaining v3 docs

Author: mythz

content/docs/extensions/ui.mdx

@@ -392,10 +392,10 @@ This makes a standard chat completion request that doesn't return until the full
 To start a new Chat Thread use:
 
 ```js
-await ctx.threads.startNewThread({ title, model })
+await ctx.threads.startNewThread({ title, model, redirect })
 ```
 
-Which creates and returns a new empty Thread in the Server then navigates the UI to the new thread page.
+Which creates and returns a new empty Thread in the Server, if `redirect:true` also navigates the UI to the new thread page.
 
 Then to begin processing an asynchronous chat completion request use:
 

content/docs/features/analytics.mdx

@@ -1,6 +1,6 @@
 ---
-title: Analytics & Monitoring
-description: Track costs, tokens, and usage across all providers
+title: Analytics
+description: Track costs, tokens, and monitor usage across all providers
 ---
 
 ## Overview

content/docs/features/calculator-ui.mdx

@@ -1,21 +1,37 @@
 ---
 title: Calculator UI
-description: Display mathematical expressions in your conversations using KaTeX.
+description: A powerful and safe mathematical expression evaluator with a rich web interface.
 ---
 
-The [katex](https://github.com/ServiceStack/llms/tree/main/llms/extensions/katex) extension enables beautiful rendering of LaTeX math expressions in AI responses using [KaTeX](https://katex.org/). It integrates automatically with the markdown parser to render math equations in both inline and block formats.
+A dedicated UI has been added for the `calc` tool with support for evaluating mathematical python expressions, including arithmetic, comparison, boolean operators, `math.*` functions & constants and python list comprehensions:
 
-### Features
+<Screenshot src="/img/run-calc.webp"/>
 
-- **Fast Rendering**: Uses KaTeX for high-performance rendering of math expressions.
-- **Inline Math**: Renders math within text using `$` or `$$` delimiters.
-- **Block Math**: Renders complex equations in their own block using `$` or `$$` delimiters across multiple lines.
-- **Auto-Integration**: Automatically extends the `marked` parser used in the application.
+## Features
 
-### Popular math expressions
+### 🖥️ UX Friendly Interface
+Experience a clean, modern interface designed for efficiency. The UI is fully responsive and supports dark mode, seamlessly integrating with the rest of the application.
 
-<Screenshot src="/img/rendering-katex.webp" />
+### 💾 Persistent History
+Never lose track of your calculations. The Calculator automatically saves your history to `localStorage`, ensuring your previous expressions and results are preserved between sessions.
 
-### Basic math expressions
+### ⚡ 1-Click Interaction
+Streamline your workflow with interactive history items:
+- **Load & Copy**: Click on any past expression or answer to instantly load it into the input field and copy it to your clipboard.
+- **Visual Feedback**: Temporary checkmarks confirm successful copy actions.
 
-<Screenshot src="/img/rendering-katex2.webp"/>
+### ⌨️ Keyboard-Free Access
+While full keyboard support is available, you can perform complex calculations entirely via the UI:
+- **Numbers & Constants**: Quick access to digits and mathematical constants like `pi`, `e`, `inf`.
+- **Operators**: Comprehensive set of buttons for arithmetic (`+`, `-`, `*`, `/`, `%`, `^`) and boolean logic (`and`, `or`, `not`).
+- **Functions**: One-click insertion or wrapping of selection for all supported math functions.
+
+### 🐍 Python Math Support
+Unlock the power of Python's math library:
+- **Math Functions**: Support for `sin`, `cos`, `tan`, `sqrt`, `log`, `factorial`, and many more.
+- **Statistics**: Built-in functions for `mean`, `median`, `stdev`, and `variance`.
+
+### 🛡️ Safe Evaluation
+Security is a priority. Instead of using Python's unsafe `eval()`, the Calculator uses a robust **AST (Abstract Syntax Tree) evaluator**.
+- **Restricted Environment**: Only allowed mathematical operations and functions are executed.
+- **No Side Effects**: Prevents arbitrary code execution, making it safe to evaluate expressions from untrusted sources.

content/docs/features/cli.mdx

@@ -27,7 +27,7 @@ llms --audio recording.mp3 "Transcribe this audio"
 llms --file document.pdf "Summarize this PDF"
 ```
 
-## 5. Configure Default Model
+## Configure Default Model
 
 Set your preferred default model:
 
@@ -51,6 +51,21 @@ llms -s "You are a quantum expert" "Explain quantum computing"
 llms "Hello" --raw
 ```
 
+### Tool Calling & Function Calling
+
+All registered tools are automatically available in CLI mode:
+
+```bash
+# Use all available tools (default)
+llms "Read the file data.txt and calculate the sum"
+
+# Use specific tools
+llms --tools calc,get_current_time "What time is it in Tokyo and what's 15% of 230?"
+
+# Disable all tools
+llms --tools none "Tell me a joke"
+```
+
 ### Image Analysis
 
 ```bash
@@ -84,6 +99,36 @@ llms --file report.pdf "Summarize the key points"
 llms -m gemini-flash-latest --file policy.pdf "Extract action items"
 ```
 
+### Image Generation
+
+Generate images directly from the CLI:
+
+```bash
+# Generate image with default model
+llms --out image "A serene mountain landscape at sunset"
+
+# Generate with specific model
+llms -m "gemini-2.5-flash-image" --out image "Logo for a tech startup"
+
+# All generated images are saved to ~/.llms/cache
+llms -m "Gemini 2.5 Flash Image" --out image "cat in a hat"
+```
+
+### Audio Generation
+
+Generate audio with Text-to-Speech models:
+
+```bash
+# Generate audio with default TTS model
+llms --out audio "Welcome to our podcast"
+
+# With specific TTS model
+llms -m gemini-2.5-pro-preview-tts --out audio "Merry Christmas"
+
+# All generated audio is saved to ~/.llms/cache
+llms -m gemini-2.5-flash-preview-tts --out audio "Hello world"
+```
+
 
 ## CLI Reference
 
@@ -135,6 +180,28 @@ llms --default grok-4-fast
 
 # Check provider status
 llms --check groq
+
+# Update provider definitions from models.dev
+llms --update-providers
+```
+
+### Extensions Management
+
+```bash
+# List available extensions
+llms --add
+
+# Install an extension
+llms --add duckduckgo
+
+# Install from GitHub
+llms --add github-user/repo-name
+
+# List installed extensions
+llms --remove
+
+# Uninstall an extension
+llms --remove duckduckgo
 ```
 
 ## Options Reference
@@ -317,6 +384,68 @@ llms --check groq
 llms --check groq kimi-k2 llama4:400b
 ```
 
+#### `--update-providers`
+
+Update provider definitions from models.dev:
+
+```bash
+llms --update-providers
+```
+
+#### `--tools TOOLS`
+
+Enable specific tools for function calling:
+
+```bash
+# Use all tools (default)
+llms --tools all "What time is it and calculate 15% of 230?"
+
+# Use specific tools
+llms --tools calc,get_current_time "What time is it in Tokyo?"
+
+# Disable all tools
+llms --tools none "Tell me a joke"
+```
+
+#### `--out OUTPUT_TYPE`
+
+Generate media output (image or audio):
+
+```bash
+# Generate images
+llms --out image "A serene mountain landscape"
+
+# Generate audio
+llms --out audio "Welcome message"
+```
+
+#### `--add [EXTENSION]`
+
+Install or list available extensions:
+
+```bash
+# List available extensions
+llms --add
+
+# Install an extension
+llms --add duckduckgo
+
+# Install from GitHub
+llms --add github-user/repo-name
+```
+
+#### `--remove [EXTENSION]`
+
+Uninstall or list installed extensions:
+
+```bash
+# List installed extensions
+llms --remove
+
+# Uninstall an extension
+llms --remove duckduckgo
+```
+
 ### Help
 
 #### `-h, --help`
@@ -443,6 +572,74 @@ llms --default grok-4-fast
 # Check provider status
 llms --check groq
 llms --check groq kimi-k2 llama4:400b gpt-oss:120b
+
+# Update provider definitions from models.dev (auto-updated daily)
+llms --update-providers
+```
+
+### Extensions Management
+
+```bash
+# List available extensions from github.com/llmspy
+llms --add
+
+# Install an extension
+llms --add duckduckgo
+
+# Install a 3rd-party extension from GitHub
+llms --add github-user/repo-name
+
+# List installed extensions
+llms --remove
+
+# Uninstall an extension
+llms --remove duckduckgo
+```
+
+### Tool Calling & Function Calling
+
+```bash
+# Use all available tools (default)
+llms "Read the file data.txt and calculate the sum"
+
+# Use specific tools
+llms --tools calc,get_current_time "What time is it in Tokyo and what's 15% of 230?"
+
+# Disable all tools
+llms --tools none "Tell me a joke"
+
+# Tools work with any model that supports function calling
+llms -m gpt-4o --tools calc "Calculate the area of a circle with radius 5"
+```
+
+### Image Generation
+
+```bash
+# Generate image with default model
+llms --out image "A serene mountain landscape at sunset"
+
+# Generate with specific model by ID
+llms -m "gemini-2.5-flash-image" --out image "Logo for a tech startup"
+
+# Generate with specific model by name
+llms -m "Gemini 2.5 Flash Image" --out image "cat in a hat"
+
+# Images are saved to ~/.llms/cache with local path and HTTP URL
+```
+
+### Audio Generation
+
+```bash
+# Generate audio with default TTS model
+llms --out audio "Welcome to our podcast"
+
+# With specific TTS model
+llms -m gemini-2.5-pro-preview-tts --out audio "Merry Christmas"
+
+# Generate with Flash TTS
+llms -m gemini-2.5-flash-preview-tts --out audio "Hello world"
+
+# Audio files are saved to ~/.llms/cache with local path and HTTP URL
 ```
 
 ## Environment Variables
@@ -466,6 +663,7 @@ DEEPSEEK_API_KEY       # DeepSeek
 CHUTES_API_KEY         # chutes.ai OSS LLM and Image Models
 HF_TOKEN               # Hugging Face
 FIREWORKS_API_KEY      # fireworks.ai OSS Models
+CODESTRAL_API_KEY      # Codestral (Mistral)
 LMSTUDIO_API_KEY       # Placeholder for local LM Studio
 ```
 

content/docs/features/core-tools.mdx

@@ -5,6 +5,8 @@ description: Built-in essential tools for memory persistence, file operations, m
 
 These tools defined in the [core_tools](https://github.com/ServiceStack/llms/blob/main/llms/extensions/core_tools/__init__.py) extension provide essential functionality for LLMs to interact with their environment, perform calculations, and manage persistent data.
 
+See [Tools Docs](/docs/extensions/tools) for details on registering and using your own tools.
+
 ## Memory Tools
 
 Functions for persistent key-value storage.

content/docs/features/meta.json

@@ -6,6 +6,8 @@
     "web-ui",
     "analytics",
     "core-tools",
+    "calculator-ui",
+    "run-code-ui",
     "katex",
     "model-selector",
     "system-prompts"