docs: sync CLI commands and provider list with current code

- cli-commands.md: remove non-existent 'auth' command; add missing
  subcommands (init, bridge, doctor, encrypt, mcp-server, session,
  cert) to overview, summary table, and examples to match the
  Commands enum in cli/mod.rs
- intro.md: add xAI, Vertex AI, Gemini CLI, Codex CLI to the
  multi-provider bullet and Supported Models table; refresh outdated
  model examples (claude-opus-4-5 -> claude-opus-4-6) and aliases
  (glm, grok, codex)
- configuration.md: extend alias comment with glm/grok/codex; fix
  codex_cli default model (gpt-4o -> o4-mini) to match the schema
  default

Author: yiwang

website/docs/cli-commands.md

@@ -18,19 +18,25 @@ Commands:
   gen         Launch world generation mode (Bevy renderer)
   daemon      Manage the background daemon
   memory      Memory management operations
-  search      Test web search provider
-  auth        Authenticate with providers
   config      Configuration management
   md          Manage LocalGPT.md standing instructions
-  sandbox     Shell sandbox diagnostics
   paths       Show resolved directory paths
-  desktop     Launch desktop GUI
+  sandbox     Shell sandbox diagnostics
+  search      Test and manage web search
+  init        Initialize configuration and keys
+  bridge      Manage bridges and credentials
+  doctor      Run diagnostics to validate setup
+  encrypt     Manage encryption at rest
+  tool        Manage MCP tool servers
+  plugin      Manage MCP tool servers (alias for 'tool')
   completion  Generate shell completion scripts
   cron        Manage cron jobs
   hooks       Manage lifecycle hooks
-  tool        Manage MCP tool servers
-  plugin      Manage MCP tool servers (alias for 'tool')
+  mcp-server  Run as MCP server (stdio) exposing memory tools
+  session     Manage sessions (list, branch, checkpoints)
   audit       View and verify compaction audit log
+  cert        Manage TLS certificates (info, regenerate)
+  desktop     Launch desktop GUI (feature-gated)
   help        Print help information
 ```
 
@@ -58,18 +64,24 @@ Options:
 | [`gen`](/docs/gen) | Launch world generation mode (Bevy renderer) |
 | [`daemon`](/docs/cli-daemon) | Start/stop/status of the background daemon |
 | [`memory`](/docs/cli-memory) | Search, reindex, and manage memory |
-| `search` | Test web search provider configuration |
-| `auth` | Authenticate with providers (Gemini, etc.) |
 | `config` | Init, show, get, and set configuration values |
 | [`md`](/docs/localgpt#quick-reference) | Sign, verify, and audit LocalGPT.md |
-| [`sandbox`](/docs/sandbox#cli-commands) | Inspect sandbox capabilities and run tests |
 | `paths` | Show resolved XDG directory paths |
+| [`sandbox`](/docs/sandbox#cli-commands) | Inspect sandbox capabilities and run tests |
+| `search` | Test and manage web search providers |
+| `init` | Initialize configuration and device keys |
+| `bridge` | Manage chat bridges and credentials |
+| `doctor` | Run diagnostics to validate setup (config, keys, providers) |
+| `encrypt` | Manage encryption at rest (sessions, config secrets) |
 | `desktop` | Launch the native desktop GUI (egui) |
 | `completion` | Generate shell completion scripts (bash, zsh, fish) |
 | `cron` | Manage cron jobs (list, add, remove) |
 | `hooks` | Manage lifecycle hooks |
 | `tool` / `plugin` | Manage MCP tool servers (list, add, remove, enable, disable) |
+| `mcp-server` | Run as an MCP server (stdio) exposing memory tools |
+| `session` | Manage sessions (list, branch, compaction checkpoints) |
 | `audit` | View and verify compaction audit log (show, verify, stats) |
+| `cert` | Manage TLS certificates (info, regenerate) |
 
 ## Examples
 
@@ -116,8 +128,11 @@ localgpt-gen "create a solar system with planets"
 # Test web search provider
 localgpt search test
 
-# Authenticate with Google Gemini
-localgpt auth gemini
+# Initialize config and device keys (first-time setup)
+localgpt init
+
+# Run setup diagnostics (config, keys, providers, MCP)
+localgpt doctor
 
 # Show resolved directory paths
 localgpt paths
@@ -149,6 +164,19 @@ localgpt audit show --limit 5     # Show last 5 events
 localgpt audit show --json        # JSON output
 localgpt audit verify             # Verify hash chain integrity
 localgpt audit stats              # Show compaction statistics
+
+# Session management and compaction checkpoints
+localgpt session list                          # List recent sessions
+localgpt session branch <session-id>           # Branch a session into a new one
+localgpt session checkpoints                   # List checkpoints for the latest session
+localgpt session restore 2                     # Restore latest session from checkpoint #2
+
+# Run as an MCP server (stdio) for external AI backends
+localgpt mcp-server
+
+# Manage TLS certificates for the HTTP server
+localgpt cert info                # Show certificate expiry, SANs, and paths
+localgpt cert regenerate          # Force certificate regeneration
 ```
 
 ## Built-in Chat Commands

website/docs/configuration.md

@@ -52,7 +52,7 @@ EOF
 #   xai/*              → xAI (Grok)
 #   glm/* or glm       → GLM (Z.AI)
 #   ollama/*           → Ollama
-#   Aliases: opus, sonnet, gpt, gpt-mini
+#   Aliases: opus, sonnet, gpt, gpt-mini, glm, grok, codex
 default_model = "claude-cli/opus"
 
 # Context window size (in tokens)
@@ -103,7 +103,7 @@ model = "gemini-3.1-pro-preview"
 
 [providers.codex_cli]
 command = "codex"
-model = "gpt-4o"
+model = "o4-mini"
 
 [providers.openai_compatible]
 # Generic OpenAI-compatible endpoint (OpenRouter, DeepSeek, etc.)

website/docs/intro.md

@@ -13,7 +13,7 @@ LocalGPT is a **local AI assistant with persistent memory, semantic search, and
 - **Hybrid Memory Search** - Markdown-based knowledge store with pluggable backends (SQLite FTS5, Markdown grep, or disabled). SQLite backend supports full-text search with AND matching and rank-based scoring plus local vector embeddings (fastembed) for semantic search
 - **Desktop App** - Optional native desktop GUI built with egui — chat, sessions, memory browser, and status dashboard. Disable with `--no-default-features` for headless/Docker deployments.
 - **Embedded Web UI** - Browser-based chat interface served directly from the binary
-- **Multi-Provider Support** - Works with Claude CLI, Anthropic API, OpenAI, Ollama, and GLM (Z.AI) — all with full tool calling support
+- **Multi-Provider Support** - Works with Claude CLI, Anthropic API, OpenAI, Ollama, GLM (Z.AI), xAI (Grok), Google Vertex AI, Gemini CLI, and Codex CLI — all with full tool calling support
 - **Telegram, Discord & WhatsApp** - Access LocalGPT from Telegram, Discord, or WhatsApp via bridge binaries with full chat, tool use, and memory support — secured with one-time pairing auth
 - **Autonomous Heartbeat** - Daemon mode with scheduled background tasks that run automatically
 - **Skills System** - Extensible skills for specialized tasks
@@ -92,9 +92,13 @@ LocalGPT automatically detects the provider based on model name prefix:
 | `openai/*` | LM Studio / OpenAI | openai/qwen/qwen3.5-35b-a3b, openai/gpt-4o |
 | Other | Ollama (local) | llama3, mistral, codellama |
 | `claude-cli/*` | Claude CLI | claude-cli/opus, claude-cli/sonnet |
-| `anthropic/*` | Anthropic API | anthropic/claude-opus-4-5, anthropic/claude-sonnet-4-5 |
+| `gemini-cli/*` | Gemini CLI | gemini-cli/gemini-2.5-pro |
+| `codex-cli/*` | Codex CLI | codex-cli/o4-mini |
+| `anthropic/*` | Anthropic API | anthropic/claude-opus-4-6, anthropic/claude-sonnet-4-6 |
+| `xai/*` | xAI (Grok) | xai/grok-3-mini |
+| `vertex/*` | Google Vertex AI | vertex/gemini-2.5-pro |
 | `glm/*` or `glm` | GLM (Z.AI) | glm/glm-4.7, glm |
-| Aliases | Any | opus, sonnet, gpt, gpt-mini |
+| Aliases | Any | opus, sonnet, gpt, gpt-mini, glm, grok, codex |
 
 ## Next Steps