threadwell 0.0.1 → 0.0.3

package/README.md

@@ -1,668 +1,402 @@
-<p align="center">
-  <a href="https://threadwell.local">
-    <picture>
-      <source media="(prefers-color-scheme: dark)" srcset="https://threadwell.local/logo.svg">
-      <source media="(prefers-color-scheme: light)" srcset="https://huggingface.co/buckets/julien-c/my-training-bucket/resolve/threadwell-logo-dark.svg">
-      <img alt="thread logo" src="https://threadwell.local/logo.svg" width="128">
-    </picture>
-  </a>
-</p>
-<p align="center">
-  <a href="https://discord.com/invite/3cU7Bz4UPx"><img alt="Discord" src="https://img.shields.io/badge/discord-community-5865F2?style=flat-square&logo=discord&logoColor=white" /></a>
-  <a href="https://www.npmjs.com/package/threadwell"><img alt="npm" src="https://img.shields.io/npm/v/threadwell?style=flat-square" /></a>
-  <a href="local Threadwell source/actions/workflows/ci.yml"><img alt="Build status" src="https://img.shields.io/github/actions/workflow/status/Threadwell source/ci.yml?style=flat-square&branch=main" /></a>
-</p>
-<p align="center">
-  <a href="https://threadwell.local">threadwell.dev</a> domain graciously donated by
-  <br /><br />
-  <a href="https://exe.dev"><img src="docs/images/exy.png" alt="Exy mascot" width="48" /><br />exe.dev</a>
-</p>
-
-> New issues and PRs from new contributors are auto-closed by default. Maintainers review auto-closed issues daily. See [CONTRIBUTING.md](../../CONTRIBUTING.md).
-
----
-
-Threadwell is a minimal terminal coding harness. Adapt Threadwell to your workflows, not the other way around, without having to fork and modify Threadwell 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 [Threadwell Packages](#threadwell-packages) and share them with others via npm or git.
-
-Threadwell ships with powerful defaults but skips features like sub agents and plan mode. Instead, you can ask Threadwell to build what you want or install a third party Threadwell package that matches your workflow.
-
-Threadwell runs in four modes: interactive, print or JSON, RPC for process integration, and an SDK for embedding in your own apps. See [openclaw/openclaw](https://github.com/openclaw/openclaw) for a real-world SDK integration.
-
-## Share your OSS coding agent sessions
-
-If you use Threadwell for open source work, please share your coding agent sessions.
-
-Public OSS session data helps improve models, prompts, tools, and evaluations using real development workflows.
-
-For the full explanation, see [this post on X](https://x.com/badlogicgames/status/2037811643774652911).
-
-To publish sessions, use [`badlogic/threadwell-share-hf`](https://github.com/badlogic/threadwell-share-hf). Read its README.md for setup instructions. All you need is a Hugging Face account, the Hugging Face CLI, and `threadwell-share-hf`.
-
-You can also watch [this video](https://x.com/badlogicgames/status/2041151967695634619), where I show how I publish my `thread` sessions.
-
-I regularly publish my own `thread` work sessions here:
-
-- [badlogicgames/threadwell on Hugging Face](https://huggingface.co/datasets/badlogicgames/threadwell)
-
-## 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)
-  - [Threadwell Packages](#threadwell-packages)
-- [Programmatic Usage](#programmatic-usage)
-- [Philosophy](#philosophy)
-- [CLI Reference](#cli-reference)
-
----
-
-## Quick Start
-
-```bash
-npm install -g threadwell
-```
-
-Authenticate with an API key:
-
-```bash
-export ANTHROPIC_API_KEY=sk-ant-...
-thread
-```
-
-Or use your existing subscription:
-
-```bash
-thread
-/login  # Then select provider
-```
-
-Then just talk to Threadwell. By default, Threadwell 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 [thread packages](#threadwell-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, Threadwell 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
-- OpenAI
-- Azure OpenAI
-- DeepSeek
-- Google Gemini
-- Google Vertex
-- Amazon Bedrock
-- Mistral
-- Groq
-- Cerebras
-- Cloudflare AI Gateway
-- Cloudflare Workers AI
-- xAI
-- OpenRouter
-- Vercel AI Gateway
-- ZAI
-- OpenCode Zen
-- OpenCode Go
-- Hugging Face
-- Fireworks
-- 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 `~/.threadwell/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, 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 |
-| `/scoped-models` | Enable/disable models for Ctrl+P cycling |
-| `/settings` | Thinking level, theme, message delivery, transport |
-| `/resume` | Pick from previous sessions |
-| `/new` | Start a new session |
-| `/name <name>` | Set session display name |
-| `/session` | Show session info (file, ID, messages, tokens, cost) |
-| `/memory ...` | Inspect/manage Threadwell memory: status, search, recent, why, doctor, export, forget, purge |
-| `/context ...` | Review and manage `CONTEXT.md` semantic candidates |
-| `/adr ...` | Review and manage architecture decision records |
-| `/review` | Open Threadwell review selector for context and ADR candidates |
-| `/feature ...` | Create and inspect Threadwell Feature Packets |
-| `/queue [long]` | Show active continuity queue tasks |
-| `/tree` | Jump to any point in the session and continue from there |
-| `/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 |
-| `/changelog` | Display version history |
-| `/quit` | Quit Threadwell |
-
-### Keyboard Shortcuts
-
-See `/hotkeys` for the full list. Customize via `~/.threadwell/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 |
-
-### 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 Threadwell 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 `~/.threadwell/agent/sessions/` organized by working directory.
-
-```bash
-thread -c                  # Continue most recent session
-thread -r                  # Browse and select from past sessions
-thread --no-session        # Ephemeral mode (don't save)
-thread --session <path|id> # Use specific session file or ID
-thread --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 |
-|----------|-------|
-| `~/.threadwell/agent/settings.json` | Global (all projects) |
-| `.threadwell/settings.json` | Project (primary Threadwell path) |
-| `.threadwell/settings.json` | Project compatibility fallback |
-
-Project settings are resolved relative to the directory where Threadwell is launched. See [docs/settings.md](docs/settings.md) for all options.
-
-### Telemetry and update checks
-
-Threadwell has two separate startup features:
-
-- **Update check:** fetches `https://threadwell.local/api/latest-version` to check whether a newer Threadwell version exists. Disable it with `THREADWELL_SKIP_VERSION_CHECK=1`. Disabling update checks only turns off this check.
-- **Install/update telemetry:** after first install or a changelog-detected update, sends an anonymous version ping to `https://threadwell.local/api/report-install`. Opt out by setting `enableInstallTelemetry` to `false` in `settings.json`, or by setting `THREADWELL_TELEMETRY=0`. This does not disable update checks; Threadwell may still contact `threadwell.dev` for the latest version unless update checks are disabled or offline mode is enabled.
-
-Use `--offline` or `THREADWELL_OFFLINE=1` to disable all startup network operations described here, including update checks, package update checks, and install/update telemetry.
-
----
-
-## Context Files
-
-Threadwell loads `AGENTS.md` (or `CLAUDE.md`) at startup from:
-- `~/.threadwell/agent/AGENTS.md` (global)
-- Parent directories (walking up from cwd)
-- Current directory
-
-Use for project instructions, 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 `.threadwell/SYSTEM.md` (project) or `~/.threadwell/agent/SYSTEM.md` (global). Append without replacing via `APPEND_SYSTEM.md`.
-
----
-
-## Customization
-
-### Prompt Templates
-
-Reusable prompts as Markdown files. Type `/name` to expand.
-
-```markdown
-<!-- ~/.threadwell/agent/prompts/review.md -->
-Review this code for bugs, security issues, and performance problems.
-Focus on: {{focus}}
-```
-
-Place in `~/.threadwell/agent/prompts/`, `.threadwell/prompts/`, or a [thread package](#threadwell-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
-<!-- ~/.threadwell/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 `~/.threadwell/agent/skills/`, `~/.agents/skills/`, `.threadwell/skills/`, or `.agents/skills/` (from `cwd` up through parent directories) or a [thread package](#threadwell-packages) to share with others. See [docs/skills.md](docs/skills.md).
-
-### Extensions
-
-<p align="center"><img src="docs/images/doom-extension.png" alt="Doom Extension" width="600"></p>
-
-TypeScript modules that extend Threadwell with custom tools, commands, keyboard shortcuts, event handlers, and UI components.
-
-```typescript
-export default function (thread: ExtensionAPI) {
-  Threadwell.registerTool({ name: "deploy", ... });
-  Threadwell.registerCommand("stats", { ... });
-  Threadwell.on("tool_call", async (event, ctx) => { ... });
-}
-```
-
-The default export can also be `async`. Threadwell waits for async extension factories before startup continues, which is useful for one-time initialization such as fetching remote model lists before calling `threadwell.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 Threadwell look like Claude Code
-- Games while waiting (yes, Doom runs)
-- ...anything you can dream up
-
-Place in `~/.threadwell/agent/extensions/`, `.threadwell/extensions/`, or a [thread package](#threadwell-packages) to share with others. See [docs/extensions.md](docs/extensions.md) and [examples/extensions/](examples/extensions/).
-
-### Themes
-
-Built-in: `dark`, `light`. Themes hot-reload: modify the active theme file and Threadwell immediately applies changes.
-
-Place in `~/.threadwell/agent/themes/`, `.threadwell/themes/`, or a [thread package](#threadwell-packages) to share with others. See [docs/themes.md](docs/themes.md).
-
-### Threadwell Packages
-
-Bundle and share extensions, skills, prompts, and themes via npm or git. Find packages on [npmjs.com](https://www.npmjs.com/search?q=keywords%3Athreadwell-package) or [Discord](https://discord.com/channels/1456806362351669492/1457744485428629628).
-
-> **Security:** Threadwell 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
-thread install npm:@foo/threadwell-tools
-thread install npm:@foo/threadwell-tools@1.2.3      # pinned version
-thread install git:github.com/user/repo
-thread install git:github.com/user/repo@v1  # tag or commit
-thread install git:git@github.com:user/repo
-thread install git:git@github.com:user/repo@v1  # tag or commit
-thread install https://github.com/user/repo
-thread install https://github.com/user/repo@v1      # tag or commit
-thread install ssh://git@github.com/user/repo
-thread install ssh://git@github.com/user/repo@v1    # tag or commit
-thread remove npm:@foo/threadwell-tools
-thread uninstall npm:@foo/threadwell-tools          # alias for remove
-thread list
-thread update                               # update Threadwell and packages (skips pinned packages)
-thread update --extensions                  # update packages only
-thread update --self                        # update Threadwell only
-thread update --self --force                # reinstall Threadwell even if current
-thread update npm:@foo/threadwell-tools             # update one package
-thread config                               # enable/disable extensions, skills, prompts, themes
-```
-
-Packages install to `~/.threadwell/agent/git/` (git) or global npm. Use `-l` for project-local installs (`.threadwell/git/`, `.threadwell/npm/`). 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 `thread` key to `package.json`:
-
-```json
-{
-  "name": "my-threadwell-package",
-  "keywords": ["threadwell-package"],
-  "threadwell": {
-    "extensions": ["./extensions"],
-    "skills": ["./skills"],
-    "prompts": ["./prompts"],
-    "themes": ["./themes"]
-  }
-}
-```
-
-Without a `thread` manifest, Threadwell 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 "threadwell";
-
-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
-thread --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
-
-Threadwell 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 [thread packages](#threadwell-packages). This keeps the core minimal while letting you shape Threadwell to fit how you work.
-
-**No MCP.** Build CLI tools with READMEs (see [Skills](#skills)), or build an extension that adds MCP support. [Why?](https://mariozechner.at/posts/2025-11-02-what-if-you-dont-need-mcp/)
-
-**No sub-agents.** There's many ways to do this. Spawn Threadwell 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.
-
-Read the [blog post](https://mariozechner.at/posts/2025-11-30-threadwell-coding-agent/) for the full rationale.
-
----
-
-## CLI Reference
-
-```bash
-thread [options] [@files...] [messages...]
-```
-
-### Package Commands
-
-```bash
-thread install <source> [-l]     # Install package, -l for project-local
-thread remove <source> [-l]      # Remove package
-thread uninstall <source> [-l]   # Alias for remove
-thread update [source|self]   # Update Threadwell and packages (skips pinned packages)
-thread update --extensions       # Update packages only
-thread update --self             # Update Threadwell only
-thread update --self --force     # Reinstall Threadwell even if current
-thread update --extension <src>  # Update one package
-thread list                      # List installed packages
-thread config                    # Enable/disable package resources
-```
-
-### 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 |
-
-In print mode, Threadwell also reads piped stdin and merges it into the initial prompt:
-
-```bash
-cat README.md | Threadwell -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>`) |
-| `--api-key <key>` | API key (overrides env vars) |
-| `--thinking <level>` | `off`, `minimal`, `low`, `medium`, `high`, `xhigh` |
-| `--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) |
-
-### Tool Options
-
-| Option | Description |
-|--------|-------------|
-| `--tools <list>`, `-t <list>` | Allowlist 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`, `grep`, `find`, `ls`
-
-### 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 |
-| `-h`, `--help` | Show help |
-| `-v`, `--version` | Show version |
-
-### File Arguments
-
-Prefix files with `@` to include in the message:
-
-```bash
-thread @prompt.md "Answer this"
-thread -p @screenshot.png "What's in this image?"
-thread @code.ts @test.ts "Review these files"
-```
-
-### Examples
-
-```bash
-# Interactive with initial prompt
-thread "List all .ts files in src/"
-
-# Non-interactive
-thread -p "Summarize this codebase"
-
-# Non-interactive with piped stdin
-cat README.md | Threadwell -p "Summarize this text"
-
-# Different model
-thread --provider openai --model gpt-4o "Help me refactor"
-
-# Model with provider prefix (no --provider needed)
-thread --model openai/gpt-4o "Help me refactor"
-
-# Model with thinking level shorthand
-thread --model sonnet:high "Solve this complex problem"
-
-# Limit model cycling
-thread --models "claude-*,gpt-4o"
-
-# Read-only mode
-thread --tools read,grep,find,ls -p "Review the code"
-
-# High thinking level
-thread --thinking high "Solve this complex problem"
-```
-
-### Environment Variables
-
-| Variable | Description |
-|----------|-------------|
-| `THREADWELL_CODING_AGENT_DIR` | Override config directory (default: `~/.threadwell/agent`) |
-| `THREADWELL_CODING_AGENT_SESSION_DIR` | Override session storage directory (overridden by `--session-dir`) |
-| `THREADWELL_PACKAGE_DIR` | Override package directory (useful for Nix/Guix where store paths tokenize poorly) |
-| `THREADWELL_OFFLINE` | Disable startup network operations, including update checks, package update checks, and install/update telemetry |
-| `THREADWELL_SKIP_VERSION_CHECK` | Skip the Threadwell version update check at startup. This prevents the `threadwell.dev` latest-version request |
-| `THREADWELL_TELEMETRY` | Override install/update telemetry. Use `1`/`true`/`yes` to enable or `0`/`false`/`no` to disable. This does not disable update checks |
-| `THREADWELL_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.
-
----
-
-## Repository and release policy
-
-Threadwell's target repository is `EngramResearch/threadwell`. The `threadwell` npm package was reserved with a `0.0.0` placeholder and should only be replaced by an explicitly approved real release.
-
-## License
-
-MIT. See the repository `LICENSE` and `NOTICE.md` files.
-
-## Attribution
-
-Threadwell is derived from Pi, originally developed by Mario Zechner and contributors. Pi is licensed under the MIT License; the original copyright and license notice are preserved in this repository.
-
-Original project: https://github.com/earendil-works/pi
-
-## See Also
-
-- [@threadwell/ai](https://www.npmjs.com/package/@threadwell/ai): Core LLM toolkit
-- [@threadwell/agent-core](https://www.npmjs.com/package/@threadwell/agent-core): Agent framework
-- [@threadwell/tui](https://www.npmjs.com/package/@threadwell/tui): Terminal UI components
+# Threadwell
+
+Threadwell is a standalone, terminal-native coding harness for long-running software work.
+It focuses on continuity, project memory, durable decisions, and low-friction coding workflows.
+
+```bash
+npm install -g threadwell
+thread
+```
+
+Package: [`threadwell`](https://www.npmjs.com/package/threadwell)  
+Repository: [`EngramResearch/threadwell`](https://github.com/EngramResearch/threadwell)  
+Command: `thread`
+
+## Status
+
+Threadwell is early. Version `0.0.x` is intended for real local use, but the public package and documentation are still being cleaned up after the fork and rebrand.
+
+The product identity is Threadwell:
+
+- CLI command: `thread`
+- npm package: `threadwell`
+- project config: `.threadwell/`
+- global config: `~/.threadwell/agent/`
+- env prefix: `THREADWELL_*`
+
+## What Threadwell does
+
+Threadwell gives an LLM a project-aware coding harness with:
+
+- terminal-native interactive TUI;
+- file tools: `read`, `write`, `edit`, `grep`, `find`, `ls`;
+- shell execution via `bash`;
+- persistent sessions with branching and compaction;
+- native continuity state;
+- semantic project memory;
+- `CONTEXT.md` project vocabulary and operating context;
+- architecture decision records via ADR support;
+- prompt templates, skills, themes, and TypeScript extensions;
+- JSON/RPC/SDK modes for automation and embedding.
+
+Threadwell is not a browser IDE. It is a local coding harness that keeps the terminal workflow while adding durable project context.
+
+## Quick start
+
+Install:
+
+```bash
+npm install -g threadwell
+```
+
+Run interactively:
+
+```bash
+thread
+```
+
+Run with an initial prompt:
+
+```bash
+thread "Review this repository and summarize the architecture"
+```
+
+Run non-interactively:
+
+```bash
+thread -p "List likely bugs in this file" @src/index.ts
+```
+
+Use a specific model:
+
+```bash
+thread --provider anthropic --model claude-sonnet-4-5
+thread --model openai/gpt-4o
+thread --model sonnet:high
+```
+
+## Authentication
+
+Threadwell supports API-key and OAuth/subscription login flows, depending on provider.
+
+API-key example:
+
+```bash
+export ANTHROPIC_API_KEY=sk-ant-...
+thread
+```
+
+Interactive login:
+
+```text
+/login
+```
+
+Auth is stored under:
+
+```text
+~/.threadwell/agent/auth.json
+```
+
+After the Threadwell rebrand, old Pi/Engram auth files are not silently migrated. Log in again if needed.
+
+## Providers and models
+
+Built-in provider support includes:
+
+- Anthropic
+- OpenAI
+- OpenAI Codex
+- GitHub Copilot
+- Google Gemini
+- Google Vertex
+- Azure OpenAI
+- Amazon Bedrock
+- Mistral
+- Groq
+- Cerebras
+- Cloudflare AI Gateway / Workers AI
+- xAI
+- OpenRouter
+- Vercel AI Gateway
+- Hugging Face
+- Fireworks
+- DeepSeek
+- Kimi / Moonshot
+- MiniMax
+- Xiaomi MiMo
+- OpenCode-compatible providers
+
+See [`docs/providers.md`](docs/providers.md) and [`docs/models.md`](docs/models.md).
+
+## Interactive mode
+
+The TUI includes:
+
+- transcript of user/assistant/tool messages;
+- multiline editor;
+- model and thinking controls;
+- session resume/fork/tree navigation;
+- tool output folding;
+- image paste support;
+- command palette via `/` commands;
+- status/footer with project and model state.
+
+Common commands:
+
+| Command | Description |
+| --- | --- |
+| `/login`, `/logout` | Manage provider auth |
+| `/model` | Switch model |
+| `/settings` | Edit runtime settings |
+| `/resume` | Resume previous session |
+| `/new` | Start a new session |
+| `/session` | Show session info |
+| `/tree` | Navigate/fork the session tree |
+| `/compact` | Compact long context |
+| `/memory ...` | Inspect/search/manage memory |
+| `/context ...` | Review `CONTEXT.md` candidates |
+| `/adr ...` | Manage architecture decision records |
+| `/review` | Review memory/context/ADR candidates |
+| `/feature ...` | Create Threadwell feature packets |
+| `/queue [long]` | Show continuity queue tasks |
+| `/copy` | Copy last assistant message |
+| `/export` | Export session to HTML |
+| `/hotkeys` | Show keybindings |
+| `/quit` | Exit |
+
+Common shortcuts:
+
+| Key | Action |
+| --- | --- |
+| Ctrl+C | Clear editor |
+| Ctrl+C twice | Quit |
+| Escape | Cancel/abort |
+| Ctrl+L | Model selector |
+| Ctrl+P / Shift+Ctrl+P | Cycle scoped models |
+| Shift+Tab | Cycle thinking level |
+| Ctrl+O | Collapse/expand tool output |
+| Ctrl+T | Collapse/expand thinking blocks |
+
+See [`docs/keybindings.md`](docs/keybindings.md) and [`docs/tui.md`](docs/tui.md).
+
+## Sessions and continuity
+
+Sessions are JSONL files stored under:
+
+```text
+~/.threadwell/agent/sessions/
+```
+
+Useful CLI flags:
+
+```bash
+thread -c                  # continue most recent session
+thread -r                  # select previous session
+thread --session <path|id> # use specific session
+thread --fork <path|id>    # fork from specific session
+thread --no-session        # ephemeral mode
+```
+
+Threadwell also maintains project continuity state under `.threadwell/` so work can be resumed across sessions without relying only on chat history.
+
+## Memory layer
+
+Threadwell includes a native memory layer for project work:
+
+- structured event storage;
+- redaction and ignore rules;
+- retrieval capsules injected into context;
+- `CONTEXT.md` semantic project vocabulary;
+- ADR files for durable decisions;
+- review flows for proposed memory/context/ADR updates.
+
+Primary commands:
+
+```text
+/memory status
+/memory search <query>
+/memory recent
+/memory why
+/memory doctor
+/context review
+/adr list
+/review
+```
+
+See [`docs/memory.md`](docs/memory.md), [`docs/settings.md`](docs/settings.md), and the [ADR guide](https://github.com/EngramResearch/threadwell/tree/main/docs/adr).
+
+## Configuration
+
+Global config:
+
+```text
+~/.threadwell/agent/settings.json
+```
+
+Project config:
+
+```text
+.threadwell/settings.json
+```
+
+Example:
+
+```json
+{
+  "continuity": true,
+  "memory": {
+    "enabled": true,
+    "inject": true,
+    "store": "sqlite"
+  }
+}
+```
+
+Important env vars:
+
+| Variable | Description |
+| --- | --- |
+| `THREADWELL_CODING_AGENT_DIR` | Override global config dir |
+| `THREADWELL_CODING_AGENT_SESSION_DIR` | Override session dir |
+| `THREADWELL_PACKAGE_DIR` | Override package install dir |
+| `THREADWELL_OFFLINE` | Disable startup network operations |
+| `THREADWELL_SKIP_VERSION_CHECK` | Skip version checks |
+| `THREADWELL_TELEMETRY` | Enable/disable install/update telemetry |
+| `THREADWELL_CACHE_RETENTION` | Set extended prompt cache behavior |
+| `VISUAL`, `EDITOR` | External editor |
+
+See [`docs/settings.md`](docs/settings.md).
+
+## Extensions, skills, prompts, themes
+
+Threadwell can be extended without changing core code.
+
+Resource locations:
+
+```text
+~/.threadwell/agent/extensions/
+~/.threadwell/agent/skills/
+~/.threadwell/agent/prompts/
+~/.threadwell/agent/themes/
+
+.threadwell/extensions/
+.threadwell/skills/
+.threadwell/prompts/
+.threadwell/themes/
+```
+
+Package commands:
+
+```bash
+thread install npm:@scope/threadwell-tools
+thread install git:github.com/user/repo
+thread remove npm:@scope/threadwell-tools
+thread list
+thread update
+thread config
+```
+
+Security note: extensions and third-party packages execute code locally. Review what you install.
+
+Docs:
+
+- [`docs/extensions.md`](docs/extensions.md)
+- [`docs/skills.md`](docs/skills.md)
+- [`docs/prompt-templates.md`](docs/prompt-templates.md)
+- [`docs/themes.md`](docs/themes.md)
+- [`docs/packages.md`](docs/packages.md)
+
+## Programmatic usage
+
+Threadwell can be embedded from Node.js:
+
+```typescript
+import { AuthStorage, createAgentSession, ModelRegistry, SessionManager } from "threadwell";
+
+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 non-Node integrations, use RPC mode:
+
+```bash
+thread --mode rpc
+```
+
+See [`docs/sdk.md`](docs/sdk.md), [`docs/rpc.md`](docs/rpc.md), and [`docs/json.md`](docs/json.md).
+
+## CLI reference
+
+```bash
+thread [options] [@files...] [messages...]
+```
+
+Selected options:
+
+| Option | Description |
+| --- | --- |
+| `-p`, `--print` | Print response and exit |
+| `--mode json` | JSON event output |
+| `--mode rpc` | RPC mode |
+| `--provider <name>` | Provider |
+| `--model <pattern>` | Model pattern/id |
+| `--api-key <key>` | Runtime API key |
+| `--thinking <level>` | `off`, `minimal`, `low`, `medium`, `high`, `xhigh` |
+| `--tools <list>` | Allowlist tools |
+| `--no-tools` | Disable all tools |
+| `--no-builtin-tools` | Disable built-in tools only |
+| `--extension <path>` | Load extension |
+| `--skill <path>` | Load skill |
+| `--theme <path>` | Load theme |
+| `--no-context-files` | Disable AGENTS.md/CLAUDE.md discovery |
+| `--export <file>` | Export session HTML |
+| `--list-models [search]` | List models |
+| `--offline` | Disable startup network operations |
+| `--help` | Show help |
+| `--version` | Show version |
+
+File arguments can be attached with `@`:
+
+```bash
+thread @README.md "Summarize this"
+thread @screenshot.png "What is shown here?"
+thread @src/index.ts @src/index.test.ts "Review these together"
+```
+
+## Development
+
+Repository:
+
+```text
+https://github.com/EngramResearch/threadwell
+```
+
+Useful commands:
+
+```bash
+npm install
+npm run check
+npm run build
+```
+
+## Related packages
+
+- [`@threadwell/ai`](https://www.npmjs.com/package/@threadwell/ai)
+- [`@threadwell/agent-core`](https://www.npmjs.com/package/@threadwell/agent-core)
+- [`@threadwell/tui`](https://www.npmjs.com/package/@threadwell/tui)
+
+## License and attribution
+
+MIT. See the repository [`LICENSE`](https://github.com/EngramResearch/threadwell/blob/main/LICENSE) and [`NOTICE.md`](https://github.com/EngramResearch/threadwell/blob/main/NOTICE.md).
+
+Threadwell is derived from Pi, originally developed by Mario Zechner and contributors. Pi is licensed under the MIT License; the original copyright and license notice are preserved in this repository.
+
+Original project: <https://github.com/earendil-works/pi>