@hansjm10/volt-coding-agent 0.0.0-bootstrap.0 → 0.1.0

package/README.md

@@ -1,5 +1,718 @@
-# @hansjm10/volt-coding-agent
+# Volt Coding Agent
 
-This package only reserves the npm name for [Volt](https://github.com/hansjm10/Volt).
+> New issues and PRs from new contributors are auto-closed by default. Maintainers review auto-closed issues daily. See [CONTRIBUTING.md](../../CONTRIBUTING.md).
 
-Installable releases begin at `0.1.0` and use the `beta` dist-tag.
+---
+
+Volt is a minimal terminal coding harness. Adapt volt to your workflows, not the other way around, without having to fork and modify volt internals. Extend it with TypeScript [Extensions](#extensions), [Skills](#skills), [Prompt Templates](#prompt-templates), and [Themes](#themes). Put your extensions, skills, prompt templates, and themes in [Volt Packages](#volt-packages) and share them with others via npm or git.
+
+Volt is maintained and distributed by [Jordan Hans](https://github.com/hansjm10).
+It is derived from [Mario Zechner's Pi project](https://github.com/badlogic/pi-mono)
+under the MIT License.
+
+Volt ships with powerful defaults but skips features like sub agents and plan mode. Instead, you can ask volt to build what you want or install a third party volt package that matches your workflow.
+
+Volt runs in four modes: interactive, print or JSON, RPC for process integration, and an SDK for embedding in your own apps.
+
+## Table of Contents
+
+- [Quick Start](#quick-start)
+- [Providers & Models](#providers--models)
+- [Interactive Mode](#interactive-mode)
+  - [Editor](#editor)
+  - [Commands](#commands)
+  - [Keyboard Shortcuts](#keyboard-shortcuts)
+  - [Message Queue](#message-queue)
+- [Sessions](#sessions)
+  - [Branching](#branching)
+  - [Compaction](#compaction)
+- [Settings](#settings)
+- [Context Files](#context-files)
+- [Customization](#customization)
+  - [Prompt Templates](#prompt-templates)
+  - [Skills](#skills)
+  - [Extensions](#extensions)
+  - [Themes](#themes)
+  - [Volt Packages](#volt-packages)
+- [Programmatic Usage](#programmatic-usage)
+- [Philosophy](#philosophy)
+- [CLI Reference](#cli-reference)
+
+---
+
+## Quick Start
+
+```bash
+npm install -g --ignore-scripts @hansjm10/volt-coding-agent@beta
+```
+
+`--ignore-scripts` disables dependency lifecycle scripts during install. Volt does not require install scripts for normal npm installs.
+
+Authenticate with an API key:
+
+```bash
+export ANTHROPIC_API_KEY=sk-ant-...
+volt
+```
+
+Or use your existing subscription:
+
+```bash
+volt
+/login  # Then select provider
+```
+
+Then just talk to volt. By default, volt gives the model four tools: `read`, `write`, `edit`, and `bash`. The model uses these to fulfill your requests. Add capabilities via [skills](#skills), [prompt templates](#prompt-templates), [extensions](#extensions), or [volt packages](#volt-packages).
+
+**Platform notes:** [Windows](docs/windows.md) | [Termux (Android)](docs/termux.md) | [tmux](docs/tmux.md) | [Terminal setup](docs/terminal-setup.md) | [Shell aliases](docs/shell-aliases.md)
+
+---
+
+## Providers & Models
+
+For each built-in provider, volt maintains a list of tool-capable models, updated with every release. Authenticate via subscription (`/login`) or API key, then select any model from that provider via `/model` (or Ctrl+L).
+
+**Subscriptions:**
+- Anthropic Claude Pro/Max
+- OpenAI ChatGPT Plus/Pro (Codex)
+- GitHub Copilot
+
+**API keys:**
+- Anthropic
+- Ant Ling
+- OpenAI
+- Azure OpenAI
+- DeepSeek
+- NVIDIA NIM
+- Google Gemini
+- Google Vertex
+- Amazon Bedrock
+- Mistral
+- Groq
+- Cerebras
+- Cloudflare AI Gateway
+- Cloudflare Workers AI
+- xAI
+- OpenRouter
+- Vercel AI Gateway
+- ZAI
+- ZAI Coding Plan (China)
+- OpenCode Zen
+- OpenCode Go
+- Hugging Face
+- Fireworks
+- Together AI
+- Kimi For Coding
+- MiniMax
+- Xiaomi MiMo
+- Xiaomi MiMo Token Plan (China)
+- Xiaomi MiMo Token Plan (Amsterdam)
+- Xiaomi MiMo Token Plan (Singapore)
+
+See [docs/providers.md](docs/providers.md) for detailed setup instructions.
+
+**Custom providers & models:** Add providers via `~/.volt/agent/models.json` if they speak a supported API (OpenAI, Anthropic, Google). For custom APIs or OAuth, use extensions. See [docs/models.md](docs/models.md) and [docs/custom-provider.md](docs/custom-provider.md).
+
+---
+
+## Interactive Mode
+
+<p align="center"><img src="docs/images/interactive-mode.png" alt="Interactive Mode" width="600"></p>
+
+The interface from top to bottom:
+
+- **Startup header** - Shows shortcuts (`/hotkeys` for all), loaded AGENTS.md files, prompt templates, skills, and extensions
+- **Messages** - Your messages, assistant responses, tool calls and results, notifications, errors, and extension UI
+- **Editor** - Where you type; border color indicates thinking level
+- **Footer** - Working directory, session name, total token/cache usage (`↑` input, `↓` output, `R` cache read, `W` cache write, `CH` latest cache hit rate), cost, context usage, current model
+
+The editor can be temporarily replaced by other UI, like built-in `/settings` or custom UI from extensions (e.g., a Q&A tool that lets the user answer model questions in a structured format). [Extensions](#extensions) can also replace the editor, add widgets above/below it, a status line, custom footer, or overlays.
+
+### Editor
+
+| Feature | How |
+|---------|-----|
+| File reference | Type `@` to fuzzy-search project files |
+| Path completion | Tab to complete paths |
+| Multi-line | Shift+Enter (or Ctrl+Enter on Windows Terminal) |
+| Images | Ctrl+V to paste (Alt+V on Windows), or drag onto terminal |
+| Bash commands | `!command` runs and sends output to LLM, `!!command` runs without sending |
+
+Standard editing keybindings for delete word, undo, etc. See [docs/keybindings.md](docs/keybindings.md).
+
+### Commands
+
+Type `/` in the editor to trigger commands. [Extensions](#extensions) can register custom commands, [skills](#skills) are available as `/skill:name`, and [prompt templates](#prompt-templates) expand via `/templatename`.
+
+| Command | Description |
+|---------|-------------|
+| `/login`, `/logout` | OAuth authentication |
+| `/model` | Switch models |
+| `/profile` | Show, switch, or create the active settings profile |
+| `/scoped-models` | Enable/disable models for Ctrl+P cycling |
+| `/settings` | Thinking level, theme, message delivery, transport |
+| `/resume` | Pick from previous sessions |
+| `/clear` | Start a new session |
+| `/name <name>` | Set session display name |
+| `/session` | Show session info (file, ID, messages, tokens, cost) |
+| `/tree` | Jump to any point in the session and continue from there |
+| `/subagents` | Inspect active or completed subagent conversations and tool flow |
+| `/trust` | Save project trust decision for future sessions (restart required) |
+| `/fork` | Create a new session from a previous user message |
+| `/clone` | Duplicate the current active branch into a new session |
+| `/compact [prompt]` | Manually compact context, optional custom instructions |
+| `/copy` | Copy last assistant message to clipboard |
+| `/export [file]` | Export session to HTML file |
+| `/share` | Upload as private GitHub gist with shareable HTML link |
+| `/reload` | Reload keybindings, extensions, skills, prompts, and context files (themes hot-reload automatically) |
+| `/hotkeys` | Show all keyboard shortcuts |
+| `/remote` | Manage daemon status, phone pairing, devices, workspaces, leases, and policy |
+| `/changelog` | Display version history |
+| `/quit` | Quit volt |
+
+### Keyboard Shortcuts
+
+See `/hotkeys` for the full list. Customize via `~/.volt/agent/keybindings.json`. See [docs/keybindings.md](docs/keybindings.md).
+
+**Commonly used:**
+
+| Key | Action |
+|-----|--------|
+| Ctrl+C | Clear editor |
+| Ctrl+C twice | Quit |
+| Escape | Cancel/abort |
+| Escape twice | Open `/tree` |
+| Ctrl+L | Open model selector |
+| Ctrl+P / Shift+Ctrl+P | Cycle scoped models forward/backward |
+| Shift+Tab | Cycle thinking level |
+| Ctrl+O | Collapse/expand tool output |
+| Ctrl+T | Collapse/expand thinking blocks |
+| Alt+A | Open the subagent inspector |
+
+### Message Queue
+
+Submit messages while the agent is working:
+
+- **Enter** queues a *steering* message, delivered after the current assistant turn finishes executing its tool calls
+- **Alt+Enter** queues a *follow-up* message, delivered only after the agent finishes all work
+- **Escape** aborts and restores queued messages to editor
+- **Alt+Up** retrieves queued messages back to editor
+
+On Windows Terminal, `Alt+Enter` is fullscreen by default. Remap it in [docs/terminal-setup.md](docs/terminal-setup.md) so volt can receive the follow-up shortcut.
+
+Configure delivery in [settings](docs/settings.md): `steeringMode` and `followUpMode` can be `"one-at-a-time"` (default, waits for response) or `"all"` (delivers all queued at once). `transport` selects provider transport preference (`"sse"`, `"websocket"`, or `"auto"`) for providers that support multiple transports.
+
+---
+
+## Sessions
+
+Sessions are stored as JSONL files with a tree structure. Each entry has an `id` and `parentId`, enabling in-place branching without creating new files. See [docs/session-format.md](docs/session-format.md) for file format.
+
+### Management
+
+Sessions auto-save to `~/.volt/agent/sessions/` organized by working directory.
+
+```bash
+volt -c                  # Continue most recent session
+volt -r                  # Browse and select from past sessions
+volt --no-session        # Ephemeral mode (don't save)
+volt --name "my task"    # Set session display name at startup
+volt --session <path|id> # Use specific session file or ID
+volt --fork <path|id>    # Fork specific session file or ID into a new session
+```
+
+Use `/session` in interactive mode to see the current session ID before reusing it with `--session <id>` or `--fork <id>`.
+
+### Branching
+
+**`/tree`** - Navigate the session tree in-place. Select any previous point, continue from there, and switch between branches. All history preserved in a single file.
+
+<p align="center"><img src="docs/images/tree-view.png" alt="Tree View" width="600"></p>
+
+- Search by typing, fold/unfold and jump between branches with Ctrl+←/Ctrl+→ or Alt+←/Alt+→, page with ←/→
+- Filter modes (Ctrl+O): default → no-tools → user-only → labeled-only → all
+- Press Shift+L to label entries as bookmarks and Shift+T to toggle label timestamps
+
+**`/fork`** - Create a new session file from a previous user message on the active branch. Opens a selector, copies the active path up to that point, and places the selected prompt in the editor for modification.
+
+**`/clone`** - Duplicate the current active branch into a new session file at the current position. The new session keeps the full active-path history and opens with an empty editor.
+
+**`--fork <path|id>`** - Fork an existing session file or partial session UUID directly from the CLI. This copies the full source session into a new session file in the current project.
+
+### Compaction
+
+Long sessions can exhaust context windows. Compaction summarizes older messages while keeping recent ones.
+
+**Manual:** `/compact` or `/compact <custom instructions>`
+
+**Automatic:** Enabled by default. Triggers on context overflow (recovers and retries) or when approaching the limit (proactive). Configure via `/settings` or `settings.json`.
+
+Compaction is lossy. The full history remains in the JSONL file; use `/tree` to revisit. Customize compaction behavior via [extensions](#extensions). See [docs/compaction.md](docs/compaction.md) for internals.
+
+---
+
+## Settings
+
+Use `/settings` to modify common options, or edit JSON files directly:
+
+| Location | Scope |
+|----------|-------|
+| `~/.volt/agent/settings.json` | Global (all projects) |
+| `.volt/settings.json` | Project (overrides global) |
+
+Settings can define named profiles for switching workflows. Select one with `volt --profile development`, `VOLT_PROFILE=work`, or `defaultProfile` in settings, or use `/profile` during an interactive session to show, switch, or create profiles. Profiles overlay normal settings and resources, but do not isolate auth or sessions yet.
+
+See [docs/settings.md](docs/settings.md) for all options.
+
+### Project Trust
+
+On interactive startup, volt asks before trusting a project folder that contains project-local settings, MCP server config, resources, or project `.agents/skills` and has no saved decision for the folder or a parent folder in `~/.volt/agent/trust.json`. Trusting a project allows volt to load `.volt/settings.json`, `.mcp.json`/`.volt/mcp.json`, and `.volt` resources, install missing project packages, and execute project extensions.
+
+Before the trust decision, volt loads only context files, user/global extensions, and CLI `-e` extensions so they can handle the `project_trust` event. Project-local extensions, project package-managed extensions, and project settings are loaded only after the project is trusted. This split also applies when switching to a session from a different cwd whose trust has not been resolved in the current process.
+
+Non-interactive modes (`-p`, `--mode json`, and `--mode rpc`) do not show a trust prompt. Without an applicable saved trust decision, they use `defaultProjectTrust` from global settings: `ask` (default) and `never` ignore those project resources, while `always` trusts them. Pass `--approve`/`-a` or `--no-approve`/`-na` to override project trust for one run.
+
+If no extension or saved decision applies, `defaultProjectTrust` controls the fallback behavior. Set it to `"ask"`, `"always"`, or `"never"` in `~/.volt/agent/settings.json`, or change it with `/settings`.
+
+`volt config` and package commands use the same project trust flow, except `volt update` never prompts. Pass `--approve` to trust project-local settings for one command or `--no-approve` to ignore them.
+
+Use `/trust` in interactive mode to save a project trust decision for future sessions, including trust for the immediate parent folder. It writes `~/.volt/agent/trust.json` only; the current session is not reloaded, so restart volt for changes to take effect.
+
+### Telemetry and update checks
+
+Volt has two optional startup features:
+
+- **Update check:** disabled unless `VOLT_LATEST_VERSION_URL` points to a JSON endpoint that returns the latest version metadata. Disable it with `VOLT_SKIP_VERSION_CHECK=1`.
+- **Install/update telemetry:** disabled unless `VOLT_REPORT_INSTALL_URL` points to an endpoint that accepts the version ping. This setting also controls optional provider attribution headers for OpenRouter, Cloudflare, and direct NVIDIA NIM requests. Opt out by setting `enableInstallTelemetry` to `false` in `settings.json`, or by setting `VOLT_TELEMETRY=0`.
+
+Use `--offline` or `VOLT_OFFLINE=1` to disable all startup network operations described here, including update checks, package update checks, and install/update telemetry.
+
+---
+
+## Context Files
+
+Volt loads `AGENTS.md` (or `CLAUDE.md`) at startup from:
+- `~/.volt/agent/AGENTS.md` (global)
+- Parent directories (walking up from cwd)
+- Current directory
+
+Use for project instructions (`AGENTS.md`/`CLAUDE.md`), conventions, common commands. All matching files are concatenated.
+
+Disable context file loading with `--no-context-files` (or `-nc`).
+
+### System Prompt
+
+Replace the default system prompt with `.volt/SYSTEM.md` (project) or `~/.volt/agent/SYSTEM.md` (global). Append without replacing via `APPEND_SYSTEM.md`.
+
+---
+
+## Customization
+
+### Prompt Templates
+
+Reusable prompts as Markdown files. Type `/name` to expand.
+
+```markdown
+<!-- ~/.volt/agent/prompts/review.md -->
+Review this code for bugs, security issues, and performance problems.
+Focus on: {{focus}}
+```
+
+Place in `~/.volt/agent/prompts/`, `.volt/prompts/`, or a [volt package](#volt-packages) to share with others. See [docs/prompt-templates.md](docs/prompt-templates.md).
+
+### Skills
+
+On-demand capability packages following the [Agent Skills standard](https://agentskills.io). Invoke via `/skill:name` or let the agent load them automatically.
+
+```markdown
+<!-- ~/.volt/agent/skills/my-skill/SKILL.md -->
+# My Skill
+Use this skill when the user asks about X.
+
+## Steps
+1. Do this
+2. Then that
+```
+
+Place in `~/.volt/agent/skills/`, `~/.agents/skills/`, `.volt/skills/`, or `.agents/skills/` (from `cwd` up through parent directories) or a [volt package](#volt-packages) to share with others. See [docs/skills.md](docs/skills.md).
+
+### Extensions
+
+TypeScript modules that extend volt with custom tools, commands, keyboard shortcuts, event handlers, and UI components.
+
+```typescript
+export default function (volt: ExtensionAPI) {
+  volt.registerTool({ name: "deploy", ... });
+  volt.registerCommand("stats", { ... });
+  volt.on("tool_call", async (event, ctx) => { ... });
+}
+```
+
+The default export can also be `async`. volt waits for async extension factories before startup continues, which is useful for one-time initialization such as fetching remote model lists before calling `volt.registerProvider()`.
+
+**What's possible:**
+- Custom tools (or replace built-in tools entirely)
+- Sub-agents and plan mode
+- Custom compaction and summarization
+- Permission gates and path protection
+- Custom editors and UI components
+- Status lines, headers, footers
+- Git checkpointing and auto-commit
+- SSH and sandbox execution
+- MCP server integration
+- Make volt look like Claude Code
+- Games while waiting (yes, Doom runs)
+- ...anything you can dream up
+
+Place in `~/.volt/agent/extensions/`, `.volt/extensions/`, or a [volt package](#volt-packages) to share with others. See [docs/extensions.md](docs/extensions.md) and [examples/extensions/](examples/extensions/).
+
+### MCP Servers
+
+Volt can connect to Model Context Protocol (MCP) servers using native config files at `~/.volt/agent/mcp.json`, shared `~/.config/mcp/mcp.json`, trusted project `.mcp.json`, or trusted project `.volt/mcp.json`. Configured servers are exposed to the model through one `mcp` gateway tool for status, discovery/search, tool calls, resources, prompts, and cached large-output reads.
+
+HTTP/SSE MCP servers with `auth: { "type": "oauth" }` can be authenticated with `volt mcp auth <server>` for browser PKCE or `volt mcp auth-device <server>` for device-code auth. Tokens stay on the host in MCP auth storage.
+
+See [docs/mcp.md](docs/mcp.md) for config format, trust rules, and current limitations.
+
+### Themes
+
+Built-in: `dark`, `light`. Themes hot-reload: modify the active theme file and volt immediately applies changes.
+
+Place in `~/.volt/agent/themes/`, `.volt/themes/`, or a [volt package](#volt-packages) to share with others. See [docs/themes.md](docs/themes.md).
+
+### Volt Packages
+
+Bundle and share extensions, skills, prompts, and themes via npm, git, or local paths.
+
+> **Security:** Volt packages run with full system access. Extensions execute arbitrary code, and skills can instruct the model to perform any action including running executables. Review source code before installing third-party packages.
+
+```bash
+volt install npm:@foo/volt-tools
+volt install npm:@foo/volt-tools@1.2.3      # pinned version
+volt install git:github.com/user/repo
+volt install git:github.com/user/repo@v1  # tag or commit
+volt install git:git@github.com:user/repo
+volt install git:git@github.com:user/repo@v1  # tag or commit
+volt install https://github.com/user/repo
+volt install https://github.com/user/repo@v1      # tag or commit
+volt install ssh://git@github.com/user/repo
+volt install ssh://git@github.com/user/repo@v1    # tag or commit
+volt remove npm:@foo/volt-tools
+volt uninstall npm:@foo/volt-tools          # alias for remove
+volt list
+volt update                               # update volt and packages (skips pinned packages)
+volt update --extensions                  # update packages only
+volt update --self                        # update volt only
+volt update --self --force                # reinstall volt even if current
+volt update npm:@foo/volt-tools             # update one package
+volt config                               # enable/disable extensions, skills, prompts, themes
+```
+
+Packages install to `~/.volt/agent/git/` (git) or `~/.volt/agent/npm/` (npm). Use `-l` for project-local installs (`.volt/git/`, `.volt/npm/`). Git `@ref` values are pinned tags or commits; pinned packages are skipped by `volt update`, so use `volt install git:host/user/repo@new-ref` to move an existing package to a new ref. Git packages install dependencies with `npm install --omit=dev` by default, so runtime deps must be listed under `dependencies`; when `npmCommand` is configured, git packages use plain `install` for compatibility with wrappers. If you use a Node version manager and want package installs to reuse a stable npm context, set `npmCommand` in `settings.json`, for example `["mise", "exec", "node@20", "--", "npm"]`.
+
+Create a package by adding a `volt` key to `package.json`:
+
+```json
+{
+  "name": "my-volt-package",
+  "keywords": ["volt-package"],
+  "volt": {
+    "extensions": ["./extensions"],
+    "skills": ["./skills"],
+    "prompts": ["./prompts"],
+    "themes": ["./themes"]
+  }
+}
+```
+
+Without a `volt` manifest, volt auto-discovers from conventional directories (`extensions/`, `skills/`, `prompts/`, `themes/`).
+
+See [docs/packages.md](docs/packages.md).
+
+---
+
+## Programmatic Usage
+
+### SDK
+
+```typescript
+import { AuthStorage, createAgentSession, ModelRegistry, SessionManager } from "@hansjm10/volt-coding-agent";
+
+const authStorage = AuthStorage.create();
+const modelRegistry = ModelRegistry.create(authStorage);
+const { session } = await createAgentSession({
+  sessionManager: SessionManager.inMemory(),
+  authStorage,
+  modelRegistry,
+});
+
+await session.prompt("What files are in the current directory?");
+```
+
+For advanced multi-session runtime replacement, use `createAgentSessionRuntime()` and `AgentSessionRuntime`.
+
+See [docs/sdk.md](docs/sdk.md) and [examples/sdk/](examples/sdk/).
+
+### RPC Mode
+
+For non-Node.js integrations, use RPC mode over stdin/stdout:
+
+```bash
+volt --mode rpc
+```
+
+RPC mode uses strict LF-delimited JSONL framing. Clients must split records on `\n` only. Do not use generic line readers like Node `readline`, which also split on Unicode separators inside JSON payloads.
+
+See [docs/rpc.md](docs/rpc.md) for the protocol.
+
+---
+
+## Philosophy
+
+Volt is aggressively extensible so it doesn't have to dictate your workflow. Features that other tools bake in can be built with [extensions](#extensions), [skills](#skills), or installed from third-party [volt packages](#volt-packages). This keeps the core minimal while letting you shape volt to fit how you work.
+
+**MCP stays explicit.** Native MCP support is available through `.mcp.json` or `.volt/mcp.json` and a single gateway tool; project MCP configs follow project trust and MCP server outputs are treated as untrusted data.
+
+**No sub-agents.** There's many ways to do this. Spawn volt instances via tmux, or build your own with [extensions](#extensions), or install a package that does it your way.
+
+**No permission popups.** Run in a container, or build your own confirmation flow with [extensions](#extensions) inline with your environment and security requirements.
+
+**No plan mode.** Write plans to files, or build it with [extensions](#extensions), or install a package.
+
+**No built-in to-dos.** They confuse models. Use a TODO.md file, or build your own with [extensions](#extensions).
+
+**No background bash.** Use tmux. Full observability, direct interaction.
+
+The project keeps the core small and relies on extensions for workflow-specific behavior.
+
+---
+
+## CLI Reference
+
+```bash
+volt [options] [@files...] [messages...]
+```
+
+### Package Commands
+
+```bash
+volt install <source> [-l]     # Install package, -l for project-local
+volt remove <source> [-l]      # Remove package
+volt uninstall <source> [-l]   # Alias for remove
+volt update [source|self|volt]   # Update volt and packages (skips pinned packages)
+volt update --extensions       # Update packages only
+volt update --self             # Update volt only
+volt update --self --force     # Reinstall volt even if current
+volt update --extension <src>  # Update one package
+volt list                      # List installed packages
+volt config                    # Enable/disable package resources
+```
+
+`volt config` and project package commands accept `--approve`/`--no-approve` to trust or ignore project-local settings for one command. `volt update` never prompts for project trust.
+
+### Modes
+
+| Flag | Description |
+|------|-------------|
+| (default) | Interactive mode |
+| `-p`, `--print` | Print response and exit |
+| `--mode json` | Output all events as JSON lines (see [docs/json.md](docs/json.md)) |
+| `--mode rpc` | RPC mode for process integration (see [docs/rpc.md](docs/rpc.md)) |
+| `--export <in> [out]` | Export session to HTML |
+
+### Remote Access over Iroh (Preview)
+
+Remote access is served by a background daemon (`voltd`). It is opt-in: nothing listens until you start the daemon. The host keeps provider credentials, files, tools, settings, sessions, state, and audit logs on the host machine, and the daemon's persistent Iroh identity means phones stay paired across restarts. In interactive Volt, `/remote` is the control center for daemon health, current-directory workspace registration, current lease ownership, attached phones, QR pairing and revocation, registered workspaces, and effective headless tool/retention policy. Its management connection is separate from the conversation lease.
+
+Copy-pastable happy path:
+
+```bash
+# Start the daemon and register a workspace.
+volt daemon start
+volt remote workspace add /path/to/repo --name volt
+
+# Create a short-lived one-time pairing ticket (QR when stderr is a TTY).
+volt remote pair --workspace volt
+
+# From a source checkout demo client, connect with the printed ticket.
+npm run iroh:poc:client -- "<ticket>" --get-state
+npm run iroh:poc:client -- "<ticket>" --message "List the top-level files."
+```
+
+Set `remote.background: true` in settings and interactive Volt manages the daemon automatically: a paired phone can then attach to the SAME live conversation your desktop TUI has open (the footer shows `📱 n`), keep the conversation when you quit the TUI, and hand it back at the next turn boundary when you reopen it.
+
+Use `/remote` for interactive management, including registering Volt's current directory, QR pairing, confirmed device revocation, and explicit approval before a revoked identity can re-pair. Equivalent shell commands are:
+
+```bash
+volt daemon status                        # daemon health, workspaces, clients, leases
+volt remote status                        # same status view
+volt remote clients                       # paired client JSON
+volt remote revoke <node-id>              # revoke one client and close its connections
+volt remote workspace add . --name volt
+volt remote workspace remove volt
+```
+
+Security defaults and limitations:
+
+- The default remote tool grant enables built-in `read,bash,edit,write,grep,find,ls,subagent` plus active tools registered by loaded extensions. A custom `remote.allowTools` list restricts daemon-owned headless runtimes; when a desktop TUI owns the conversation, phone prompts use the TUI session's full local tool set.
+- Granting `bash`, `edit`, or `write` can modify the host or run shell commands. Extension tools run code installed on the host and may do the same. Pair only devices you control.
+- Pairing tickets are short-lived, one-time credentials. `volt remote pair` talks to the running daemon; it does not generate offline tickets from persisted state.
+- Remote workspaces are selected by saved name, not arbitrary client-provided paths.
+- Remote sessions do not bypass project trust. Saved workspace trust is honored; otherwise project resources run untrusted.
+- Daemon files live under `~/.volt/agent/daemon/` (`state.json`, `audit.jsonl`, `voltd.log`); legacy `remote/iroh-host.json` state migrates automatically with pairings intact.
+- The daemon requires a Node.js npm package install or source checkout with optional `@number0/iroh` available for the platform. Standalone Node SEA builds reject `volt daemon` because the native Iroh adapter is intentionally not bundled.
+
+See [Background daemon](docs/daemon.md), [Iroh remote protocol v1](docs/iroh-remote-protocol.md), and [Security](docs/security.md#remote-access-over-iroh-preview).
+
+### Print Mode Stdin
+
+In print mode, volt also reads piped stdin and merges it into the initial prompt:
+
+```bash
+cat README.md | volt -p "Summarize this text"
+```
+
+### Model Options
+
+| Option | Description |
+|--------|-------------|
+| `--provider <name>` | Provider (anthropic, openai, google, etc.) |
+| `--model <pattern>` | Model pattern or ID (supports `provider/id` and optional `:<thinking>`) |
+| `--profile <name>` | Apply a named settings profile (or set `VOLT_PROFILE`) |
+| `--api-key <key>` | API key (overrides env vars) |
+| `--thinking <level>` | `off`, `minimal`, `low`, `medium`, `high`, `xhigh`, `max` |
+| `--models <patterns>` | Comma-separated patterns for Ctrl+P cycling |
+| `--list-models [search]` | List available models |
+
+### Session Options
+
+| Option | Description |
+|--------|-------------|
+| `-c`, `--continue` | Continue most recent session |
+| `-r`, `--resume` | Browse and select session |
+| `--session <path\|id>` | Use specific session file or partial UUID |
+| `--fork <path\|id>` | Fork specific session file or partial UUID into a new session |
+| `--session-dir <dir>` | Custom session storage directory |
+| `--no-session` | Ephemeral mode (don't save) |
+| `--name <name>`, `-n <name>` | Set session display name at startup |
+
+### Tool Options
+
+| Option | Description |
+|--------|-------------|
+| `--tools <list>`, `-t <list>` | Allowlist specific tool names across built-in, extension, and custom tools |
+| `--exclude-tools <list>`, `-xt <list>` | Disable specific tool names across built-in, extension, and custom tools |
+| `--no-builtin-tools`, `-nbt` | Disable built-in tools by default but keep extension/custom tools enabled |
+| `--no-tools`, `-nt` | Disable all tools by default |
+
+Available built-in tools: `read`, `bash`, `edit`, `write`, `web_search`, `grep`, `find`, `ls`, `lsp` (when enabled), `subagent` (when available), `mcp` (when MCP servers are configured)
+
+### Resource Options
+
+| Option | Description |
+|--------|-------------|
+| `-e`, `--extension <source>` | Load extension from path, npm, or git (repeatable) |
+| `--no-extensions` | Disable extension discovery |
+| `--skill <path>` | Load skill (repeatable) |
+| `--no-skills` | Disable skill discovery |
+| `--prompt-template <path>` | Load prompt template (repeatable) |
+| `--no-prompt-templates` | Disable prompt template discovery |
+| `--theme <path>` | Load theme (repeatable) |
+| `--no-themes` | Disable theme discovery |
+| `--no-context-files`, `-nc` | Disable AGENTS.md and CLAUDE.md context file discovery |
+
+Combine `--no-*` with explicit flags to load exactly what you need, ignoring settings.json (e.g., `--no-extensions -e ./my-ext.ts`).
+
+### Other Options
+
+| Option | Description |
+|--------|-------------|
+| `--system-prompt <text>` | Replace default prompt (context files and skills still appended) |
+| `--append-system-prompt <text>` | Append to system prompt |
+| `--verbose` | Force verbose startup |
+| `-a`, `--approve` | Trust project-local files for this run |
+| `-na`, `--no-approve` | Ignore project-local files for this run |
+| `-h`, `--help` | Show help |
+| `-v`, `--version` | Show version |
+
+### File Arguments
+
+Prefix files with `@` to include in the message:
+
+```bash
+volt @prompt.md "Answer this"
+volt -p @screenshot.png "What's in this image?"
+volt @code.ts @test.ts "Review these files"
+```
+
+### Examples
+
+```bash
+# Interactive with initial prompt
+volt "List all .ts files in src/"
+
+# Non-interactive
+volt -p "Summarize this codebase"
+
+# Non-interactive with piped stdin
+cat README.md | volt -p "Summarize this text"
+
+# Named one-shot session
+volt --name "release audit" -p "Audit this repository"
+
+# Different model
+volt --provider openai --model gpt-4o "Help me refactor"
+
+# Model with provider prefix (no --provider needed)
+volt --model openai/gpt-4o "Help me refactor"
+
+# Model with thinking level shorthand
+volt --model sonnet:high "Solve this complex problem"
+
+# Limit model cycling
+volt --models "claude-*,gpt-4o"
+
+# Read-only mode
+volt --tools read,grep,find,ls -p "Review the code"
+
+# Disable one extension or built-in tool while keeping the rest available
+volt --exclude-tools ask_question
+
+# High thinking level
+volt --thinking high "Solve this complex problem"
+```
+
+### Environment Variables
+
+| Variable | Description |
+|----------|-------------|
+| `VOLT_CODING_AGENT_DIR` | Override config directory (default: `~/.volt/agent`) |
+| `VOLT_CODING_AGENT_SESSION_DIR` | Override session storage directory (overridden by `--session-dir`) |
+| `VOLT_PACKAGE_DIR` | Override package directory (useful for Nix/Guix where store paths tokenize poorly) |
+| `VOLT_PROFILE` | Apply a named settings profile |
+| `VOLT_OFFLINE` | Disable startup network operations, including update checks, package update checks, and install/update telemetry |
+| `VOLT_SKIP_VERSION_CHECK` | Skip the Volt version update check at startup |
+| `VOLT_LATEST_VERSION_URL` | Enable hosted version checks against this JSON endpoint |
+| `VOLT_REPORT_INSTALL_URL` | Enable hosted install/update telemetry against this endpoint |
+| `VOLT_SHARE_VIEWER_URL` | Base URL for `/share` command viewer links |
+| `VOLT_TELEMETRY` | Override install/update telemetry and provider attribution headers. Use `1`/`true`/`yes` to enable or `0`/`false`/`no` to disable. This does not disable update checks |
+| `VOLT_CACHE_RETENTION` | Set to `long` for extended prompt cache (Anthropic: 1h, OpenAI: 24h) |
+| `VISUAL`, `EDITOR` | External editor for Ctrl+G |
+
+---
+
+## Contributing & Development
+
+See [CONTRIBUTING.md](../../CONTRIBUTING.md) for guidelines and [docs/development.md](docs/development.md) for setup, forking, and debugging.
+
+---
+
+## License
+
+MIT
+
+## See Also
+
+- [@hansjm10/volt-ai](../ai): Core LLM toolkit
+- [@hansjm10/volt-agent-core](../agent): Agent framework
+- [@hansjm10/volt-tui](../tui): Terminal UI components