@parallel-cli/parallel 0.4.1 → 0.4.3

package/CHANGELOG.md

@@ -0,0 +1,116 @@
+# Changelog
+
+All notable changes to Parallel are documented here.
+
+## 0.4.3 - 2026-06-23
+
+### 0.4.3 Added
+
+- Added a guided provider setup flow in both first-run wizard and settings: provider, model, endpoint review, API key, then save/default selection.
+- Added endpoint review and endpoint editing for provider presets and configured providers.
+- Added first-class local/no-key provider semantics for Ollama and vLLM/SGLang.
+- Added `/project` and `/folder` commands to reopen the project picker or switch project folder from inside the TUI.
+- Added `/wizard` and `/setup` commands to relaunch setup without restarting with `--first-run`.
+- Added keyboard selection for slash command and `@agent` suggestions.
+- Added viewport/windowing support for long wizard/settings lists.
+- Added Up/Down scrolling for long static views such as `/help`.
+- Added `CHANGELOG.md` to public release documentation.
+
+### 0.4.3 Changed
+
+- Refreshed the provider and model catalog across 29 presets.
+- Refreshed built-in pricing entries and made pricing lookup case-insensitive.
+- Reworked settings provider details to expose model changes, endpoint editing, key changes, key clearing, default selection, pricing, and removal.
+- Hid `/key` from visible help/autocomplete; provider keys are now guided through `/settings`.
+- Updated CLI help, TUI help, and README to document current commands and provider flows.
+- Updated the hardcoded TUI header version to `0.4.3`.
+- Corrected npm metadata to point at `Nil06/parallel-cli`.
+
+### 0.4.3 Fixed
+
+- Fixed preset providers skipping model selection and endpoint review before API key entry.
+- Fixed session settings accidentally behaving like global provider mutation in several flows.
+- Fixed bare model IDs containing `:` such as `qwen3-coder:480b`.
+- Fixed stale default provider normalization during config load and provider removal.
+- Fixed `DEEPSEEK_API_KEY` overriding whichever provider happened to be default; it now targets DeepSeek only.
+- Fixed local endpoints being blocked by missing API keys.
+- Fixed sensitive `/key ...` entries being stored in input history.
+- Fixed tiny pseudo-TTY dimensions causing negative string repeat values in the TUI header.
+
+## 0.4.2 - 2026-06-22
+
+### 0.4.2 Added
+
+- Expanded provider presets from 18 to 29.
+- Added new provider categories: Western, Chinese, Gateways, Inference, and Local.
+- Added MiniMax, Z.ai / GLM, Alibaba / Qwen, Moonshot / Kimi, Xiaomi / MiMo, StepFun, SiliconFlow, Atlas Cloud, Requesty, Vercel AI Gateway, and vLLM/SGLang presets.
+- Added provider category metadata for cleaner Wizard and Settings grouping.
+- Added a larger built-in model pricing catalog.
+
+### 0.4.2 Changed
+
+- Reworked the README provider section to be provider-agnostic instead of DeepSeek-centered.
+- Updated provider tables, endpoint documentation, and model catalog references.
+- Removed internal docs from remote tracking and kept them out of the public package.
+
+### 0.4.2 Fixed
+
+- Fixed Settings showing only configured providers instead of all presets in the Providers submenu.
+- Fixed README coherence around provider count, missing commands, approvals, repository metadata, and environment variables.
+
+## 0.4.1 - 2026-06-22
+
+### 0.4.1 Added
+
+- Added 10 new provider presets.
+- Added Ollama as a first-class local preset with automatic connectivity check and model detection.
+- Added custom provider setup for any OpenAI-compatible endpoint.
+- Added provider removal from Settings.
+
+### 0.4.1 Changed
+
+- Redesigned the provider wizard around grouped provider categories.
+- Reorganized Settings so provider keys, models, pricing, add/remove, and defaults are managed under a Providers submenu.
+- Reduced Settings root menu complexity.
+
+## 0.4.0 - 2026-06-22
+
+### 0.4.0 Added
+
+- Added explicit agent modes: `/ask`, `/task`, and `/plan`.
+- Added aliases `/a`, `/t`, and `/p`.
+- Added dedicated agent terminals through `parallel attach`.
+- Added automatic dedicated terminal opening with `/attach on`.
+- Added focus mode for routing plain input to one agent.
+- Added live telemetry in the hub and attached terminals.
+- Added structured timeline presentation for agent activity.
+- Added UI translations for English, French, Spanish, and Chinese.
+- Added color-coded system messages by severity.
+- Added safer test script behavior when local tests are absent.
+
+### 0.4.0 Changed
+
+- Redesigned the control room UI with a compact ASCII header and improved agent rows.
+- Reworked command grouping and alias resolution.
+- Reworked attached terminal command handling around modern agent modes.
+- Kept source tests local/internal instead of remote-tracked.
+
+### 0.4.0 Removed
+
+- Removed the visible `/spawn` command in favor of `/task`.
+
+### 0.4.0 Fixed
+
+- Fixed missing i18n strings in commands.
+- Fixed several TUI layout issues around headers, root height, arrow focus guards, and small terminals.
+- Fixed rapid repeated `/pause` behavior.
+
+## 0.3.3 - 2026-06-12
+
+### 0.3.3 Added
+
+- Initial public release.
+- Added the Parallel TUI control room for running multiple coding agents on one project.
+- Added OpenAI-compatible provider configuration.
+- Added session state, agent coordination, shared notes, file activity, diffs, approvals, and basic command dispatch.
+- Added npm binaries: `parallel` and `prl`.

package/README.md

@@ -2,41 +2,29 @@
 
 Real-time multi-agent coding from one terminal control room.
 
-Parallel lets you run several AI coding agents on the same repository at the same time. Each agent has its own task, mode, terminal, live activity timeline, and shared view of the session. The hub keeps you in control: what is running, what needs input, what changed, what it cost, and where to steer next.
+Parallel lets you run several AI coding agents on the same repository at the same time. Each agent has its own task, mode, live activity timeline, model, and shared session context. The TUI stays keyboard-first so you can launch work, inspect progress, answer approvals, steer agents, and review changes without leaving the terminal.
 
-> One hub. Many agents. Shared context. No silent overwrites.
+> One hub. Many agents. Shared context. Human in control.
 
 [![npm version](https://img.shields.io/npm/v/@parallel-cli/parallel?color=blue)](https://www.npmjs.com/package/@parallel-cli/parallel)
 ![node version](https://img.shields.io/node/v/@parallel-cli/parallel)
 ![license](https://img.shields.io/npm/l/@parallel-cli/parallel)
 ![platform](https://img.shields.io/badge/platform-linux%20%7C%20macos-lightgrey)
 
-## What Parallel Is
+## Highlights
 
-Parallel is built for active coding sessions where one agent is not enough:
-
-- ask one agent to audit while another implements
-- run a plan-first agent before allowing edits
-- keep a test-focused agent watching regressions
-- steer any agent live without stopping the others
-- open a dedicated terminal for deep scrollback on one agent
-
-The philosophy is simple: agents can move in parallel, but the human keeps the control room.
-
-## Features
-
-- Launch agents in three explicit modes: `/ask`, `/task`, and `/plan`.
+- Run multiple agents in parallel on one project.
+- Choose explicit modes: `/ask`, `/task`, and `/plan`.
 - Type plain text to launch a task agent immediately.
-- Run multiple agents at once on the same repository.
-- Open a dedicated terminal per agent with native scrollback and live steering.
-- See structured activity timelines instead of raw tool spam.
-- Share live context between agents: status, notes, claims, file activity, and diffs.
-- Avoid silent overwrites with adaptive merge-on-write for file edits.
-- Pause, resume, stop, focus, restore, and steer agents while they are running.
-- Review live diffs, notes, costs, sessions, skills, and specialists from built-in views.
-- Use any OpenAI-compatible provider — 18 pre-configured cloud providers (DeepSeek, xAI/Grok, Perplexity, Cohere, DeepInfra, Fireworks, Cerebras, Novita, Hyperbolic, SambaNova, and more), plus Ollama for local models, and any custom OpenAI-compatible endpoint.
-- Choose shell approval behavior: `ask`, `auto-safe`, or `yolo`.
-- Track token usage and estimated cost per agent and per session.
+- Steer one agent with `@a1 ...` or broadcast with `@all ...`.
+- Open dedicated agent terminals with native scrollback.
+- Review agents, notes, file activity, diffs, cost, skills, specialists, and saved sessions from the TUI.
+- Configure OpenAI-compatible providers through a guided wizard and settings panel.
+- Use 29 provider presets across Western, Chinese, Gateway, Inference, and Local categories.
+- Support local no-key endpoints such as Ollama and vLLM/SGLang.
+- Keep shell execution controlled with `ask`, `auto-safe`, or `yolo` approvals.
+- Save and restore project sessions.
+- Run headless multi-agent jobs for CI or scripts.
 
 ## Install
 
@@ -44,7 +32,7 @@ Requirements:
 
 - Node.js 18 or newer
 - Linux or macOS
-- An API key for an OpenAI-compatible provider
+- An API key for a cloud provider, or a local OpenAI-compatible endpoint
 
 Install from npm:
 
@@ -52,7 +40,7 @@ Install from npm:
 npm install -g @parallel-cli/parallel
 ```
 
-Run it inside a project:
+Run inside a project:
 
 ```bash
 parallel
@@ -66,7 +54,15 @@ prl
 
 ## Quick Start
 
-On first launch, Parallel opens a setup wizard for language, folder, session, provider, and model.
+On first launch, Parallel opens a setup wizard:
+
+1. Choose language.
+2. Choose the project folder.
+3. Restore a saved session or start a new one.
+4. Choose a provider.
+5. Choose the model.
+6. Review or edit the endpoint.
+7. Enter the provider API key if required.
 
 After setup, type a task and press Enter:
 
@@ -74,7 +70,7 @@ After setup, type a task and press Enter:
 > refactor the API client and update the tests
 ```
 
-Plain text launches a `/task` agent. Start another agent at any time, even while the first one is still working:
+Plain text launches a `/task` agent. You can launch another agent while the first is still working:
 
 ```text
 > add regression coverage for auth middleware
@@ -88,7 +84,7 @@ Use explicit modes when intent matters:
 /task builder implement the approved plan
 ```
 
-Send a live instruction to one agent:
+Steer a running agent:
 
 ```text
 @a1 also handle empty response bodies
@@ -106,7 +102,7 @@ Broadcast to every agent:
 | --- | --- | --- |
 | `/ask` | Questions, reviews, audits, tradeoffs | Answers and advises without editing files. |
 | `/task` | Implementation work | Executes, edits, validates, and summarizes. |
-| `/plan` | Risky or unclear work | Inspects first, asks for approval, then edits only after approval. |
+| `/plan` | Risky or unclear work | Inspects first, presents a plan, then edits only after approval. |
 
 Aliases:
 
@@ -118,28 +114,40 @@ Plain text is equivalent to `/task`.
 
 ## Control Room
 
-The main TUI is the Parallel hub. It is designed to answer four questions quickly:
+The main TUI is the Parallel hub. It is designed to answer:
 
-- What needs my input?
-- Which agents are working?
-- What did each agent just do?
-- What model, folder, shell mode, and cost am I currently running?
+- what needs your input
+- which agents are working
+- what each agent just did
+- what changed in the project
+- what model, provider, shell mode, and cost are active
 
-Useful hub commands:
+Common hub commands:
 
 ```text
 /agents              agent overview
 /focus a1            inspect and steer one agent
 /raw                 toggle raw detail in focus view
-/board               shared blackboard, claims, file activity
+/board               shared blackboard, claims, notes, file activity
 /diff                live diff history
 /cost                token and cost breakdown
 /sessions            saved sessions
 /settings            global settings
 /settings-session    session-only settings
+/project [folder]    change project folder
+/wizard              rerun setup wizard
 ```
 
-Best terminal size is around `120x34`. Parallel still adapts to smaller terminals, but the hub is most readable with enough width for model, folder, status, and agent summaries.
+Keyboard behavior:
+
+- `/` opens slash command suggestions.
+- Up/Down selects suggestions when a suggestion menu is open.
+- Enter accepts the selected suggestion.
+- Tab or Right accepts the best completion.
+- Up/Down scrolls long views such as `/help`.
+- Escape returns to the agents view or clears the input.
+
+Best terminal size is around `120x34`. Parallel adapts to smaller terminals, but the hub is most readable with enough width for model, folder, status, and agent summaries.
 
 ## Dedicated Agent Terminals
 
@@ -153,7 +161,7 @@ Attached terminals show:
 
 - the selected agent's live timeline
 - native terminal scrollback
-- model, elapsed time, steps, tokens, context percentage, and cost
+- model, elapsed time, context, and cost
 - other agents' current state
 - approval and question prompts for that agent
 - an input that steers that agent directly
@@ -176,40 +184,47 @@ Toggle automatic agent terminals from the hub:
 /attach off
 ```
 
-## Shell Approvals
+## Providers And Models
 
-Parallel separates agent modes from shell approval behavior.
+Parallel works with OpenAI-compatible chat completions and tool calling. It ships with 29 presets:
 
-```text
-/approvals ask
-/approvals auto-safe
-/approvals yolo
-```
+- Western: OpenAI, Anthropic, Google Gemini, xAI Grok, Mistral, Cohere, Perplexity
+- Chinese: DeepSeek, MiniMax, Z.ai / GLM, Alibaba / Qwen, Moonshot / Kimi, Xiaomi / MiMo, StepFun
+- Gateways: OpenRouter, SiliconFlow, Atlas Cloud, Requesty, Vercel AI Gateway
+- Inference: Groq, Cerebras, Together AI, Fireworks, DeepInfra, Novita, Hyperbolic, SambaNova
+- Local: Ollama, vLLM / SGLang
 
-| Mode | Behavior |
-| --- | --- |
-| `ask` | Ask before shell commands unless explicitly allowed. |
-| `auto-safe` | Auto-approve safe inspection/build/test commands; ask for risky commands. |
-| `yolo` | Auto-approve every shell command. Intended for trusted/headless usage only. |
+Provider setup is guided in both the first-run wizard and `/settings`:
 
-`auto` is accepted as a compatibility spelling for `auto-safe`.
+1. Pick a provider preset or custom provider.
+2. Pick the model.
+3. Review or edit the endpoint.
+4. Enter the provider API key if the provider requires one.
+5. Save globally or use the provider/model for the current session.
 
-## Headless Mode
+Local providers such as Ollama and vLLM/SGLang do not require an API key. You can still review and edit their endpoints.
 
-For CI and scripts, run without the TUI:
+Useful settings commands:
 
-```bash
-parallel --headless "fix lint failures" "update tests" --json
+```text
+/settings            global language, providers, keys, defaults, approvals
+/settings-session    temporary model, provider, approvals, sound
+/model               show current session model
+/model provider:id   switch model for this session
+/doctor              check provider/model/API key readiness
 ```
 
-Headless mode:
+Configuration is stored in `~/.parallel/config.json`.
 
-- runs one agent per task
-- uses the current folder as the project root
-- uses `yolo` shell approvals
-- auto-answers agent questions with the recommended option
-- saves the session
-- exits non-zero if any agent does not finish successfully
+Environment variables:
+
+| Variable | Purpose |
+| --- | --- |
+| `PARALLEL_API_KEY` | API key for the current default provider. |
+| `DEEPSEEK_API_KEY` | API key for the DeepSeek provider only. |
+| `PARALLEL_BASE_URL` | Override the default provider base URL. |
+| `PARALLEL_MODEL` | Override the session model. |
+| `PARALLEL_NO_ALT_SCREEN=1` | Disable the alternate terminal screen. |
 
 ## Commands
 
@@ -238,6 +253,8 @@ Headless mode:
 | `/resume <agent\|all>` | Resume paused agents. |
 | `/stop <agent\|all>` | Stop running agents. |
 | `/clear` | Remove finished agents from the current display. |
+| `/raw` | Toggle conversation-raw view. |
+| `/copy` | Copy the latest completed result to clipboard. |
 
 ### Git Safety
 
@@ -256,6 +273,7 @@ Headless mode:
 | `/notes` | Full notes history. |
 | `/diff` | Live diff history. |
 | `/cost` | Token and cost breakdown. |
+| `/status` | Session model, approval mode, agents, cost snapshot. |
 | `/skills` | Available skills. |
 | `/specialists` | Available specialists. |
 | `/save [name]` | Save the current session. |
@@ -263,62 +281,65 @@ Headless mode:
 | `/session <n\|latest>` | Restore a saved session. |
 | `/restore <agent>` | Relaunch a restored agent with its conversation history. |
 
-### Settings
+### Settings And Exit
 
 | Command | Description |
 | --- | --- |
 | `/model [[provider:]model]` | Show or switch the session model. |
-| `/key <api-key>` | Store the API key for the active provider. |
-| `/approvals <ask\|auto-safe\|yolo>` | Set shell approvals for this session. |
+| `/approvals <ask\|auto\|auto-safe\|yolo>` | Set shell approvals for this session. |
 | `/sound <on\|off>` | Toggle terminal bell notifications. |
 | `/settings` | Edit global language, providers, keys, defaults, and approvals. |
 | `/settings-session` | Edit session-only model, approvals, and sound. |
+| `/project [folder]` | Change project folder or reopen the folder picker. |
+| `/folder [folder]` | Alias for `/project`. |
+| `/wizard` | Relaunch the setup wizard. |
+| `/setup` | Alias for `/wizard`. |
 | `/doctor` | Check provider, key, and model configuration. |
 | `/help` | Full command reference. |
 | `/quit` | Save the session and exit. |
 
 When there is exactly one agent, commands such as `/undo`, `/focus`, `/pause`, `/resume`, `/stop`, and `/commit` can omit the agent name.
 
-## Providers
-
-Parallel ships with **18 pre-configured cloud providers** with verified endpoints and curated model lists, plus **Ollama** for local models with automatic model detection. All providers use OpenAI-compatible chat completions with tool calling. You can also add any custom OpenAI-compatible endpoint.
+## Shell Approvals
 
-The built-in DeepSeek preset works out of the box once an API key is configured. Additional providers like xAI/Grok, Perplexity, Cohere, DeepInfra, Fireworks, Cerebras, Novita, Hyperbolic, and SambaNova are available for selection during setup or from the Providers settings submenu.
+Parallel separates agent modes from shell approval behavior.
 
-Environment variables:
+```text
+/approvals ask
+/approvals auto-safe
+/approvals yolo
+```
 
-| Variable | Purpose |
+| Mode | Behavior |
 | --- | --- |
-| `DEEPSEEK_API_KEY` | API key for the built-in DeepSeek provider. |
-| `PARALLEL_API_KEY` | Generic fallback API key. |
-| `PARALLEL_BASE_URL` | Override the provider base URL. |
-| `PARALLEL_MODEL` | Override the session model. |
-| `PARALLEL_NO_ALT_SCREEN=1` | Disable the alternate terminal screen. |
+| `ask` | Ask before shell commands unless explicitly allowed. |
+| `auto-safe` | Auto-approve safe inspection/build/test commands and ask for risky commands. |
+| `yolo` | Auto-approve every shell command. Intended for trusted/headless usage only. |
 
-Configuration is stored in `~/.parallel/config.json`. Project state, sessions, skills, specialists, and memory are stored under `.parallel/` in the selected project.
+`auto` is accepted as a compatibility spelling for `auto-safe`.
+
+## Sessions, Skills, And Specialists
+
+Parallel stores project state under `.parallel/` in the selected project directory. That includes saved sessions, memory, skills, specialists, and session socket state.
 
-## Skills And Specialists
+Skills are markdown instruction files agents can load with the `load_skill` tool or that you can force-load with `#skill-name` in a task:
 
-Skills are markdown instruction files that agents can load with the `load_skill` tool or that you can force-load with `#skill-name` in a task.
+```text
+> add Redis-backed caching for expensive lookups #redis
+```
 
-Locations:
+Skill locations:
 
 - Global skills: `~/.parallel/skills/`
 - Project skills: `.parallel/skills/`
 
-Specialists are markdown personas with optional pinned models.
+Specialists are reusable personas with optional pinned models.
 
-Locations:
+Specialist locations:
 
 - Global specialists: `~/.parallel/specialists/`
 - Project specialists: `.parallel/specialists/`
 
-Example task with a forced skill:
-
-```text
-> add Redis-backed caching for expensive lookups #redis
-```
-
 ## How Parallel Avoids Lost Work
 
 Parallel does not lock files. Instead, each agent tracks the last version it read.
@@ -332,58 +353,42 @@ When an agent writes a file:
 
 This keeps agents moving without allowing silent overwrites.
 
-## Codebase Map
-
-The runtime is intentionally small:
+## Headless Mode
 
-- `src/index.tsx`: CLI entrypoint, TUI launch, attach mode, and headless mode.
-- `src/controller.ts`: session state, agents, approvals, questions, terminals, commits, and restores.
-- `src/coordination/blackboard.ts`: shared live state for agents, logs, notes, file activity, claims, and diffs.
-- `src/agents/agent.ts`: agent loop, mode instructions, live context injection, and completion.
-- `src/agents/tools.ts`: file, shell, note, skill, memory, and question tools.
-- `src/server.ts`: Unix socket bridge for dedicated agent terminals.
-- `src/ui/`: Ink components for the hub, timelines, settings, prompts, and attach UI.
-- `src/commands.ts`: hub command registry, hidden compatibility commands, aliases, and dispatch.
-- `src/config.ts` and `src/i18n.ts`: provider/session config and translations.
+For CI and scripts, run without the TUI:
 
-## Changelog
+```bash
+parallel --headless "fix lint failures" "update tests" --json
+```
 
-### 0.4.1
+Headless mode:
 
-- **18 pre-configured cloud providers** with verified endpoints and curated model lists (up from 8). Added: xAI/Grok, Perplexity, Cohere, DeepInfra, Fireworks, Cerebras, Novita, Hyperbolic, SambaNova.
-- **Ollama (local models)** as a first-class preset with automatic connectivity check and model detection.
-- **Wizard redesign** — provider selection now grouped by category (Configured, Cloud, Local, Custom) instead of a flat list.
-- **Settings reorganization** — all provider actions (keys, models, pricing, add/remove) consolidated under a "Providers" submenu; settings root reduced from 13 to 8 items.
-- **Provider removal** — can now remove configured providers from settings.
-- Custom provider option always available for any OpenAI-compatible endpoint.
+- runs one agent per task
+- uses the current folder as the project root
+- uses `yolo` shell approvals
+- auto-answers agent questions with the recommended option
+- saves the session
+- exits non-zero if any agent does not finish successfully
 
-### 0.4.0
+## Package Contents
 
-- **Removed `/spawn`** — use `/task` instead. The alias was redundant and its removal simplified the command registry.
-- **System messages color-coded by severity** — green for success, yellow for warnings, red for errors, gray for informational. Applied across all ~40 system messages in every command.
-- **UI fully internationalized** — all wizard screens, menus, and prompts now available in English, French, Spanish, and Chinese (zh).
-- **AgentHub header indicators** — the hub header now shows the active mode, model, and context usage at a glance.
-- **Fixed `/pause` double-call** — rapid consecutive `/pause` invocations no longer trigger the action twice.
+The npm package is intentionally small. It publishes the compiled runtime and public release docs only:
 
-## Development
+- `dist/`
+- `README.md`
+- `CHANGELOG.md`
+- `LICENSE`
 
-```bash
-npm install
-npm run build
-npm test
-```
+Internal development files such as source tests and design docs are not part of the npm package.
 
-Use a local global link while developing:
+## Changelog
 
-```bash
-npm link
-parallel --help
-```
+See [`CHANGELOG.md`](CHANGELOG.md).
 
-Published package:
+## Links
 
-- npm: https://www.npmjs.com/package/@parallel-cli/parallel
-- GitHub: https://github.com/Nil06/parallel-cli
+- npm: [@parallel-cli/parallel](https://www.npmjs.com/package/@parallel-cli/parallel)
+- GitHub: [Nil06/parallel-cli](https://github.com/Nil06/parallel-cli)
 
 ## License
 

package/dist/commands.js

@@ -1,5 +1,6 @@
 import { Controller, normalizeShellApprovalMode } from './controller.js';
 import { createSkillTemplate, createSpecialistTemplate } from './skills.js';
+import { providerReady } from './config.js';
 import { t } from './i18n.js';
 // Grouped by intent so /help reads as a story: create agents → steer them →
 // inspect the session → git safety net → session & config → exit.
@@ -41,11 +42,13 @@ export const COMMANDS = [
     { name: '/restore', args: '<agent>', descKey: 'cmd.restore', group: 'git' },
     // config
     { name: '/model', args: '[[provider:]model]', descKey: 'cmd.model', group: 'settings' },
-    { name: '/key', args: '<key>', descKey: 'cmd.key', group: 'settings' },
+    { name: '/key', args: '<key>', descKey: 'cmd.key', group: 'settings', hidden: true },
     { name: '/approvals', args: '<ask|auto|auto-safe|yolo>', descKey: 'cmd.approvals', group: 'settings' },
     { name: '/sound', args: '<on|off>', descKey: 'cmd.sound', group: 'settings' },
     { name: '/settings', args: '', descKey: 'cmd.settings', group: 'settings' },
     { name: '/settings-session', args: '', descKey: 'cmd.ssettings', group: 'settings', aliases: ['/ssettings'] },
+    { name: '/project', args: '[folder]', descKey: 'cmd.project', group: 'settings', aliases: ['/folder'] },
+    { name: '/wizard', args: '', descKey: 'cmd.wizard', group: 'settings', aliases: ['/setup'] },
     { name: '/doctor', args: '', descKey: 'cmd.doctor', group: 'settings' },
     // exit
     { name: '/help', args: '', descKey: 'cmd.help', group: 'other' },
@@ -75,7 +78,7 @@ function spawnFrom(arg, ctl, ui, images, specialist, mode = 'task') {
     const p = ctl.sessionProvider();
     if (!p)
         return ui.system(t('m.missingProvider'), 'error');
-    if (!p.apiKey)
+    if (!providerReady(p))
         return ui.system(t('m.missingKey', { name: p.name }), 'error');
     if (!ctl.session.model && !p.defaultModel && !p.models[0])
         return ui.system(t('m.missingModel', { name: p.name }), 'error');
@@ -155,7 +158,11 @@ export function executeInput(raw, ctl, ui, images) {
                     ? '/settings-session'
                     : rawCmd.toLowerCase() === '/exit'
                         ? '/quit'
-                        : rawCmd;
+                        : rawCmd.toLowerCase() === '/folder'
+                            ? '/project'
+                            : rawCmd.toLowerCase() === '/setup'
+                                ? '/wizard'
+                                : rawCmd;
     const arg = rest.join(' ').trim();
     switch (cmd.toLowerCase()) {
         case '/ask': {
@@ -311,7 +318,7 @@ export function executeInput(raw, ctl, ui, images) {
             const p = ctl.sessionProvider();
             if (!p)
                 return ui.system(t('m.missingProvider'), 'error');
-            if (!p.apiKey)
+            if (!providerReady(p))
                 return ui.system(t('m.missingKey', { name: p.name }), 'error');
             if (!ctl.session.model && !p.defaultModel && !p.models[0])
                 return ui.system(t('m.missingModel', { name: p.name }), 'error');
@@ -468,6 +475,12 @@ export function executeInput(raw, ctl, ui, images) {
         case '/settings-session':
             ui.setView('settings-session');
             return;
+        case '/project':
+            ui.openProject?.(arg || undefined);
+            return;
+        case '/wizard':
+            ui.openWizard?.();
+            return;
         // SESSION-only approvals & sound (global defaults editable in /settings).
         case '/approvals': {
             const mode = normalizeShellApprovalMode(arg);