gsd-pi 2.75.0-next.9c0ec0ba1 → 2.76.0

package/README.md

@@ -210,8 +210,8 @@ GSD v2 solves all of these because it's not a prompt framework anymore — it's
 | Roadmap reassessment | Manual                       | Automatic after each slice completes                    |
 | Skill discovery      | None                         | Auto-detect and install relevant skills during research |
 | Verification         | Manual                       | Automated verification commands with auto-fix retries   |
-| Reporting            | None                         | Self-contained HTML reports with metrics and dep graphs  |
-| Parallel execution   | None                         | Multi-worker parallel milestone orchestration            |
+| Reporting            | None                         | Self-contained HTML reports with metrics and dep graphs |
+| Parallel execution   | None                         | Multi-worker parallel milestone orchestration           |
 
 ### Migrating from v1
 
@@ -407,47 +407,47 @@ On first run, GSD launches a branded setup wizard that walks you through LLM pro
 
 ### Commands
 
-| Command                 | What it does                                                    |
-| ----------------------- | --------------------------------------------------------------- |
-| `/gsd`                  | Step mode — executes one unit at a time, pauses between each    |
-| `/gsd next`             | Explicit step mode (same as bare `/gsd`)                        |
-| `/gsd auto`             | Autonomous mode — researches, plans, executes, commits, repeats |
-| `/gsd quick`            | Execute a quick task with GSD guarantees, skip planning overhead |
-| `/gsd stop`             | Stop auto mode gracefully                                       |
-| `/gsd steer`            | Hard-steer plan documents during execution                      |
-| `/gsd discuss`          | Discuss architecture and decisions (works alongside auto mode)  |
-| `/gsd rethink`          | Conversational project reorganization                           |
-| `/gsd mcp`              | MCP server status and connectivity                              |
-| `/gsd status`           | Progress dashboard                                              |
-| `/gsd queue`            | Queue future milestones (safe during auto mode)                 |
-| `/gsd prefs`            | Model selection, timeouts, budget ceiling                       |
-| `/gsd migrate`          | Migrate a v1 `.planning` directory to `.gsd` format             |
-| `/gsd help`             | Categorized command reference for all GSD subcommands           |
-| `/gsd mode`             | Switch workflow mode (solo/team) with coordinated defaults      |
-| `/gsd workflow`         | Unified workflow plugins — list, run `<name>`, install, info, validate |
-| `/gsd start <template>` | Launch a bundled or custom workflow template (bugfix, release, etc.) |
-| `/gsd forensics`        | Full-access GSD debugger for auto-mode failure investigation    |
-| `/gsd cleanup`          | Archive phase directories from completed milestones             |
+| Command                 | What it does                                                                  |
+| ----------------------- | ----------------------------------------------------------------------------- |
+| `/gsd`                  | Step mode — executes one unit at a time, pauses between each                  |
+| `/gsd next`             | Explicit step mode (same as bare `/gsd`)                                      |
+| `/gsd auto`             | Autonomous mode — researches, plans, executes, commits, repeats               |
+| `/gsd quick`            | Execute a quick task with GSD guarantees, skip planning overhead              |
+| `/gsd stop`             | Stop auto mode gracefully                                                     |
+| `/gsd steer`            | Hard-steer plan documents during execution                                    |
+| `/gsd discuss`          | Discuss architecture and decisions (works alongside auto mode)                |
+| `/gsd rethink`          | Conversational project reorganization                                         |
+| `/gsd mcp`              | MCP server status and connectivity                                            |
+| `/gsd status`           | Progress dashboard                                                            |
+| `/gsd queue`            | Queue future milestones (safe during auto mode)                               |
+| `/gsd prefs`            | Model selection, timeouts, budget ceiling                                     |
+| `/gsd migrate`          | Migrate a v1 `.planning` directory to `.gsd` format                           |
+| `/gsd help`             | Categorized command reference for all GSD subcommands                         |
+| `/gsd mode`             | Switch workflow mode (solo/team) with coordinated defaults                    |
+| `/gsd workflow`         | Unified workflow plugins — list, run `<name>`, install, info, validate        |
+| `/gsd start <template>` | Launch a bundled or custom workflow template (bugfix, release, etc.)          |
+| `/gsd forensics`        | Full-access GSD debugger for auto-mode failure investigation                  |
+| `/gsd cleanup`          | Archive phase directories from completed milestones                           |
 | `/gsd doctor`           | Runtime health checks — issues surface across widget, visualizer, and reports |
-| `/gsd keys`             | API key manager — list, add, remove, test, rotate, doctor       |
-| `/gsd logs`             | Browse activity, debug, and metrics logs                        |
-| `/gsd export --html`    | Generate HTML report for current or completed milestone         |
-| `/worktree` (`/wt`)     | Git worktree lifecycle — create, switch, merge, remove          |
-| `/voice`                | Toggle real-time speech-to-text (macOS, Linux)                  |
-| `/exit`                 | Graceful shutdown — saves session state before exiting          |
-| `/kill`                 | Kill GSD process immediately                                    |
-| `/clear`                | Start a new session (alias for `/new`)                          |
-| `Ctrl+Alt+G`            | Toggle dashboard overlay                                        |
-| `Ctrl+Alt+V`            | Toggle voice transcription                                      |
-| `Ctrl+Alt+B`            | Show background shell processes                                 |
-| `Alt+V`                 | Paste clipboard image (macOS)                                   |
-| `gsd config`            | Re-run the setup wizard (LLM provider + tool keys)              |
-| `gsd update`            | Update GSD to the latest version                                |
-| `gsd headless [cmd]`    | Run `/gsd` commands without TUI (CI, cron, scripts)             |
-| `gsd headless query`    | Instant JSON snapshot — state, next dispatch, costs (no LLM)    |
-| `gsd --continue` (`-c`) | Resume the most recent session for the current directory        |
-| `gsd --worktree` (`-w`) | Launch an isolated worktree session for the active milestone    |
-| `gsd sessions`          | Interactive session picker — browse and resume any saved session |
+| `/gsd keys`             | API key manager — list, add, remove, test, rotate, doctor                     |
+| `/gsd logs`             | Browse activity, debug, and metrics logs                                      |
+| `/gsd export --html`    | Generate HTML report for current or completed milestone                       |
+| `/worktree` (`/wt`)     | Git worktree lifecycle — create, switch, merge, remove                        |
+| `/voice`                | Toggle real-time speech-to-text (macOS, Linux)                                |
+| `/exit`                 | Graceful shutdown — saves session state before exiting                        |
+| `/kill`                 | Kill GSD process immediately                                                  |
+| `/clear`                | Start a new session (alias for `/new`)                                        |
+| `Ctrl+Alt+G`            | Toggle dashboard overlay                                                      |
+| `Ctrl+Alt+V`            | Toggle voice transcription                                                    |
+| `Ctrl+Alt+B`            | Show background shell processes                                               |
+| `Alt+V`                 | Paste clipboard image (macOS)                                                 |
+| `gsd config`            | Re-run the setup wizard (LLM provider + tool keys)                            |
+| `gsd update`            | Update GSD to the latest version                                              |
+| `gsd headless [cmd]`    | Run `/gsd` commands without TUI (CI, cron, scripts)                           |
+| `gsd headless query`    | Instant JSON snapshot — state, next dispatch, costs (no LLM)                  |
+| `gsd --continue` (`-c`) | Resume the most recent session for the current directory                      |
+| `gsd --worktree` (`-w`) | Launch an isolated worktree session for the active milestone                  |
+| `gsd sessions`          | Interactive session picker — browse and resume any saved session              |
 
 ---
 
@@ -556,24 +556,24 @@ auto_report: true
 
 **Key settings:**
 
-| Setting                | What it controls                                                                                      |
-| ---------------------- | ----------------------------------------------------------------------------------------------------- |
-| `models.*`             | Per-phase model selection — string for a single model, or `{model, fallbacks}` for automatic failover |
-| `skill_discovery`      | `auto` / `suggest` / `off` — how GSD finds and applies skills                                         |
-| `auto_supervisor.*`    | Timeout thresholds for auto mode supervision                                                          |
-| `budget_ceiling`       | USD ceiling — auto mode pauses when reached                                                           |
-| `uat_dispatch`         | Enable automatic UAT runs after slice completion                                                      |
-| `always_use_skills`    | Skills to always load when relevant                                                                   |
-| `skill_rules`          | Situational rules for skill routing                                                                   |
-| `skill_staleness_days` | Skills unused for N days get deprioritized (default: 60, 0 = disabled)                                |
-| `unique_milestone_ids` | Uses unique milestone names to avoid clashes when working in teams of people                          |
-| `git.isolation`        | `none` (default), `worktree`, or `branch` — enable worktree or branch isolation for milestone work               |
-| `git.manage_gitignore` | Set `false` to prevent GSD from modifying `.gitignore`                                                           |
-| `verification_commands`| Array of shell commands to run after task execution (e.g., `["npm run lint", "npm run test"]`)        |
-| `verification_auto_fix`| Auto-retry on verification failures (default: true)                                                   |
-| `verification_max_retries` | Max retries for verification failures (default: 2)                                               |
-| `phases.require_slice_discussion` | Pause auto-mode before each slice for human discussion review                                    |
-| `auto_report`          | Auto-generate HTML reports after milestone completion (default: true)                                 |
+| Setting                           | What it controls                                                                                      |
+| --------------------------------- | ----------------------------------------------------------------------------------------------------- |
+| `models.*`                        | Per-phase model selection — string for a single model, or `{model, fallbacks}` for automatic failover |
+| `skill_discovery`                 | `auto` / `suggest` / `off` — how GSD finds and applies skills                                         |
+| `auto_supervisor.*`               | Timeout thresholds for auto mode supervision                                                          |
+| `budget_ceiling`                  | USD ceiling — auto mode pauses when reached                                                           |
+| `uat_dispatch`                    | Enable automatic UAT runs after slice completion                                                      |
+| `always_use_skills`               | Skills to always load when relevant                                                                   |
+| `skill_rules`                     | Situational rules for skill routing                                                                   |
+| `skill_staleness_days`            | Skills unused for N days get deprioritized (default: 60, 0 = disabled)                                |
+| `unique_milestone_ids`            | Uses unique milestone names to avoid clashes when working in teams of people                          |
+| `git.isolation`                   | `none` (default), `worktree`, or `branch` — enable worktree or branch isolation for milestone work    |
+| `git.manage_gitignore`            | Set `false` to prevent GSD from modifying `.gitignore`                                                |
+| `verification_commands`           | Array of shell commands to run after task execution (e.g., `["npm run lint", "npm run test"]`)        |
+| `verification_auto_fix`           | Auto-retry on verification failures (default: true)                                                   |
+| `verification_max_retries`        | Max retries for verification failures (default: 2)                                                    |
+| `phases.require_slice_discussion` | Pause auto-mode before each slice for human discussion review                                         |
+| `auto_report`                     | Auto-generate HTML reports after milestone completion (default: true)                                 |
 
 ### Agent Instructions
 
@@ -590,14 +590,14 @@ Start GSD with `gsd --debug` to enable structured JSONL diagnostic logging. Debu
 GSD includes a coordinated token optimization system that reduces usage by 40-60% on cost-sensitive workloads. Set a single preference to coordinate model selection, phase skipping, and context compression:
 
 ```yaml
-token_profile: budget      # or balanced (default), quality
+token_profile: budget # or balanced (default), quality
 ```
 
-| Profile | Savings | What It Does |
-|---------|---------|-------------|
-| `budget` | 40-60% | Cheap models, skip research/reassess, minimal context inlining |
-| `balanced` | 10-20% | Default models, skip slice research, standard context |
-| `quality` | 0% | All phases, all context, full model power |
+| Profile    | Savings | What It Does                                                   |
+| ---------- | ------- | -------------------------------------------------------------- |
+| `budget`   | 40-60%  | Cheap models, skip research/reassess, minimal context inlining |
+| `balanced` | 10-20%  | Default models, skip slice research, standard context          |
+| `quality`  | 0%      | All phases, all context, full model power                      |
 
 **Complexity-based routing** automatically classifies tasks as simple/standard/complex and routes to appropriate models. Simple docs tasks get Haiku; complex architectural work gets Opus. The classification is heuristic (sub-millisecond, no LLM calls) and learns from outcomes via a persistent routing history.
 
@@ -609,44 +609,44 @@ See the full [Token Optimization Guide](./docs/user-docs/token-optimization.md)
 
 GSD ships with 24 extensions, all loaded automatically:
 
-| Extension              | What it provides                                                                                                       |
-| ---------------------- | ---------------------------------------------------------------------------------------------------------------------- |
-| **GSD**                | Core workflow engine, auto mode, commands, dashboard                                                                   |
+| Extension              | What it provides                                                                                                                                                                                                                                                                     |
+| ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
+| **GSD**                | Core workflow engine, auto mode, commands, dashboard                                                                                                                                                                                                                                 |
 | **Browser Tools**      | Playwright-based browser with form intelligence, intent-ranked element finding, semantic actions, PDF export, session state persistence, network mocking, device emulation, structured extraction, visual diffing, region zoom, test code generation, and prompt injection detection |
-| **Search the Web**     | Brave Search, Tavily, or Jina page extraction                                                                          |
-| **Google Search**      | Gemini-powered web search with AI-synthesized answers                                                                  |
-| **Context7**           | Up-to-date library/framework documentation                                                                             |
-| **Background Shell**   | Long-running process management with readiness detection                                                               |
-| **Async Jobs**         | Background bash commands with job tracking and cancellation                                                            |
-| **Subagent**           | Delegated tasks with isolated context windows                                                                          |
-| **GitHub**             | Full-suite GitHub issues and PR management via `/gh` command                                                           |
-| **Mac Tools**          | macOS native app automation via Accessibility APIs                                                                     |
-| **MCP Client**         | Native MCP server integration via @modelcontextprotocol/sdk                                                            |
-| **Voice**              | Real-time speech-to-text transcription (macOS, Linux — Ubuntu 22.04+)                                                  |
-| **Slash Commands**     | Custom command creation                                                                                                |
-| **Ask User Questions** | Structured user input with single/multi-select                                                                         |
-| **Secure Env Collect** | Masked secret collection without manual .env editing                                                                   |
-| **Remote Questions**   | Route decisions to Slack/Discord when human input is needed in headless/CI mode                                         |
-| **Universal Config**   | Discover and import MCP servers and rules from other AI coding tools                                                    |
-| **AWS Auth**           | Automatic Bedrock credential refresh for AWS-hosted models                                                              |
-| **Ollama**             | First-class local LLM support via Ollama                                                                                |
-| **Claude Code CLI**    | External provider extension for Claude Code CLI                                                                         |
-| **cmux**               | Claude multiplexer integration — desktop notifications, sidebar metadata, visual subagent splits                        |
-| **GitHub Sync**        | Auto-sync milestones to GitHub Issues, PRs, and Milestones                                                              |
-| **LSP**                | Language Server Protocol — diagnostics, definitions, references, hover, rename                                          |
-| **TTSR**               | Tool-triggered system rules — conditional context injection based on tool usage                                         |
+| **Search the Web**     | Brave Search, Tavily, or Jina page extraction                                                                                                                                                                                                                                        |
+| **Google Search**      | Gemini-powered web search with AI-synthesized answers                                                                                                                                                                                                                                |
+| **Context7**           | Up-to-date library/framework documentation                                                                                                                                                                                                                                           |
+| **Background Shell**   | Long-running process management with readiness detection                                                                                                                                                                                                                             |
+| **Async Jobs**         | Background bash commands with job tracking and cancellation                                                                                                                                                                                                                          |
+| **Subagent**           | Delegated tasks with isolated context windows                                                                                                                                                                                                                                        |
+| **GitHub**             | Full-suite GitHub issues and PR management via `/gh` command                                                                                                                                                                                                                         |
+| **Mac Tools**          | macOS native app automation via Accessibility APIs                                                                                                                                                                                                                                   |
+| **MCP Client**         | Native MCP server integration via @modelcontextprotocol/sdk                                                                                                                                                                                                                          |
+| **Voice**              | Real-time speech-to-text transcription (macOS, Linux — Ubuntu 22.04+)                                                                                                                                                                                                                |
+| **Slash Commands**     | Custom command creation                                                                                                                                                                                                                                                              |
+| **Ask User Questions** | Structured user input with single/multi-select                                                                                                                                                                                                                                       |
+| **Secure Env Collect** | Masked secret collection without manual .env editing                                                                                                                                                                                                                                 |
+| **Remote Questions**   | Route decisions to Slack/Discord when human input is needed in headless/CI mode                                                                                                                                                                                                      |
+| **Universal Config**   | Discover and import MCP servers and rules from other AI coding tools                                                                                                                                                                                                                 |
+| **AWS Auth**           | Automatic Bedrock credential refresh for AWS-hosted models                                                                                                                                                                                                                           |
+| **Ollama**             | First-class local LLM support via Ollama                                                                                                                                                                                                                                             |
+| **Claude Code CLI**    | External provider extension for Claude Code CLI                                                                                                                                                                                                                                      |
+| **cmux**               | Claude multiplexer integration — desktop notifications, sidebar metadata, visual subagent splits                                                                                                                                                                                     |
+| **GitHub Sync**        | Auto-sync milestones to GitHub Issues, PRs, and Milestones                                                                                                                                                                                                                           |
+| **LSP**                | Language Server Protocol — diagnostics, definitions, references, hover, rename                                                                                                                                                                                                       |
+| **TTSR**               | Tool-triggered system rules — conditional context injection based on tool usage                                                                                                                                                                                                      |
 
 ### Bundled Agents
 
 Five specialized subagents for delegated work:
 
-| Agent               | Role                                                         |
-| ------------------- | ------------------------------------------------------------ |
-| **Scout**           | Fast codebase recon — returns compressed context for handoff |
-| **Researcher**      | Web research — finds and synthesizes current information     |
-| **Worker**          | General-purpose execution in an isolated context window      |
-| **JavaScript Pro**  | JavaScript-specialized execution and debugging               |
-| **TypeScript Pro**  | TypeScript-specialized execution and debugging               |
+| Agent              | Role                                                         |
+| ------------------ | ------------------------------------------------------------ |
+| **Scout**          | Fast codebase recon — returns compressed context for handoff |
+| **Researcher**     | Web research — finds and synthesizes current information     |
+| **Worker**         | General-purpose execution in an isolated context window      |
+| **JavaScript Pro** | JavaScript-specialized execution and debugging               |
+| **TypeScript Pro** | TypeScript-specialized execution and debugging               |
 
 ---
 
@@ -806,8 +806,8 @@ Use expensive models where quality matters (planning, complex execution) and che
 
 ## Ecosystem
 
-| Project | Description |
-| ------- | ----------- |
+| Project                                                         | Description                                                                         |
+| --------------------------------------------------------------- | ----------------------------------------------------------------------------------- |
 | [GSD2 Config Utility](https://github.com/jeremymcs/gsd2-config) | Standalone configuration tool for managing GSD preferences, providers, and API keys |
 
 ---

package/dist/claude-cli-check.d.ts

@@ -1,3 +1,13 @@
+/**
+ * Platform-correct binary name for the Claude Code CLI.
+ *
+ * On Windows, npm-global binaries are installed as `.cmd` shims and
+ * `execFileSync` does not auto-resolve the extension — calling bare
+ * `claude` would fail with ENOENT even when the CLI is installed and
+ * authenticated. Mirrors the `NPM_COMMAND` pattern in
+ * `src/resources/extensions/gsd/pre-execution-checks.ts`.
+ */
+export declare const CLAUDE_COMMAND: string;
 /**
  * Check if the `claude` binary is installed (regardless of auth state).
  */

package/dist/claude-cli-check.js

@@ -2,12 +2,22 @@
 // Lightweight check used at onboarding time (before extensions load).
 // The full readiness check with caching lives in the claude-code-cli extension.
 import { execFileSync } from 'node:child_process';
+/**
+ * Platform-correct binary name for the Claude Code CLI.
+ *
+ * On Windows, npm-global binaries are installed as `.cmd` shims and
+ * `execFileSync` does not auto-resolve the extension — calling bare
+ * `claude` would fail with ENOENT even when the CLI is installed and
+ * authenticated. Mirrors the `NPM_COMMAND` pattern in
+ * `src/resources/extensions/gsd/pre-execution-checks.ts`.
+ */
+export const CLAUDE_COMMAND = process.platform === 'win32' ? 'claude.cmd' : 'claude';
 /**
  * Check if the `claude` binary is installed (regardless of auth state).
  */
 export function isClaudeBinaryInstalled() {
     try {
-        execFileSync('claude', ['--version'], { timeout: 5_000, stdio: 'pipe' });
+        execFileSync(CLAUDE_COMMAND, ['--version'], { timeout: 5_000, stdio: 'pipe' });
         return true;
     }
     catch {
@@ -19,13 +29,13 @@ export function isClaudeBinaryInstalled() {
  */
 export function isClaudeCliReady() {
     try {
-        execFileSync('claude', ['--version'], { timeout: 5_000, stdio: 'pipe' });
+        execFileSync(CLAUDE_COMMAND, ['--version'], { timeout: 5_000, stdio: 'pipe' });
     }
     catch {
         return false;
     }
     try {
-        const output = execFileSync('claude', ['auth', 'status'], { timeout: 5_000, stdio: 'pipe' })
+        const output = execFileSync(CLAUDE_COMMAND, ['auth', 'status'], { timeout: 5_000, stdio: 'pipe' })
             .toString()
             .toLowerCase();
         return !(/not logged in|no credentials|unauthenticated|not authenticated/i.test(output));

package/dist/onboarding.d.ts

@@ -10,6 +10,20 @@
  * All steps are skippable. All errors are recoverable. Never crashes boot.
  */
 import type { AuthStorage } from '@gsd/pi-coding-agent';
+type ClackModule = typeof import('@clack/prompts');
+type PicoModule = {
+    cyan: (s: string) => string;
+    green: (s: string) => string;
+    yellow: (s: string) => string;
+    dim: (s: string) => string;
+    bold: (s: string) => string;
+    red: (s: string) => string;
+    reset: (s: string) => string;
+};
+interface RunOnboardingOptions {
+    /** Show logo + intro banner. Disable when onboarding is launched inside an active TUI session. */
+    showIntro?: boolean;
+}
 /**
  * Determine if the onboarding wizard should run.
  *
@@ -36,4 +50,9 @@ export declare function shouldRunOnboarding(authStorage: AuthStorage, settingsDe
  * All steps are skippable. All errors are recoverable.
  * Writes status to stderr during execution.
  */
-export declare function runOnboarding(authStorage: AuthStorage): Promise<void>;
+export declare function runOnboarding(authStorage: AuthStorage, opts?: RunOnboardingOptions): Promise<void>;
+export declare function runLlmStep(p: ClackModule, pc: PicoModule, authStorage: AuthStorage): Promise<boolean>;
+export declare function runWebSearchStep(p: ClackModule, pc: PicoModule, authStorage: AuthStorage, isAnthropicAuth: boolean): Promise<string | null>;
+export declare function runToolKeysStep(p: ClackModule, pc: PicoModule, authStorage: AuthStorage): Promise<number>;
+export declare function runRemoteQuestionsStep(p: ClackModule, pc: PicoModule, authStorage: AuthStorage): Promise<string | null>;
+export {};

package/dist/onboarding.js

@@ -15,6 +15,8 @@ import { dirname, join } from 'node:path';
 import { renderLogo } from './logo.js';
 import { agentDir } from './app-paths.js';
 import { isClaudeCliReady } from './claude-cli-check.js';
+import { markOnboardingComplete, markStepCompleted, markStepSkipped, isOnboardingComplete, } from './resources/extensions/gsd/onboarding-state.js';
+import { getLlmProviderIds } from './resources/extensions/gsd/setup-catalog.js';
 // ─── Constants ────────────────────────────────────────────────────────────────
 const TOOL_KEYS = [
     {
@@ -36,25 +38,17 @@ const TOOL_KEYS = [
         hint: 'voice transcription — free at console.groq.com',
     },
 ];
-/** Known LLM provider IDs that, if authed, mean the user doesn't need onboarding */
-const LLM_PROVIDER_IDS = [
-    'anthropic',
+/**
+ * Known LLM provider IDs that, if authed, mean the user doesn't need onboarding.
+ * Sourced from the shared setup-catalog so adding a provider lands in one place.
+ * 'anthropic-vertex' and 'ollama' aren't in PROVIDER_REGISTRY but are still
+ * treated as "authed = no onboarding needed" for back-compat.
+ */
+const LLM_PROVIDER_IDS = Array.from(new Set([
+    ...getLlmProviderIds(),
     'anthropic-vertex',
-    'claude-code',
-    'openai',
-    'github-copilot',
-    'openai-codex',
-    'google-gemini-cli',
-    'google-antigravity',
-    'google',
-    'groq',
-    'xai',
-    'openrouter',
-    'mistral',
     'ollama',
-    'ollama-cloud',
-    'custom-openai',
-];
+]));
 /** API key prefix validation — loose checks to catch obvious mistakes */
 const API_KEY_PREFIXES = {
     anthropic: ['sk-ant-'],
@@ -178,6 +172,10 @@ async function runStep(p, warnLabel, fn, opts = {}) {
 export function shouldRunOnboarding(authStorage, settingsDefaultProvider) {
     if (!process.stdin.isTTY)
         return false;
+    // Explicit completion record wins — user has already finished onboarding (and
+    // our flowVersion hasn't bumped since).
+    if (isOnboardingComplete())
+        return false;
     if (settingsDefaultProvider)
         return false;
     // Check if any LLM provider has credentials
@@ -196,7 +194,7 @@ export function shouldRunOnboarding(authStorage, settingsDefaultProvider) {
  * All steps are skippable. All errors are recoverable.
  * Writes status to stderr during execution.
  */
-export async function runOnboarding(authStorage) {
+export async function runOnboarding(authStorage, opts = {}) {
     let p;
     let pc;
     try {
@@ -209,31 +207,62 @@ export async function runOnboarding(authStorage) {
         return;
     }
     // ── Intro ─────────────────────────────────────────────────────────────────
-    process.stderr.write(renderLogo(pc.cyan));
-    p.intro(pc.bold('Welcome to GSD — let\'s get you set up'));
+    if (opts.showIntro !== false) {
+        process.stderr.write(renderLogo(pc.cyan));
+        p.intro(pc.bold('Welcome to GSD — let\'s get you set up'));
+    }
+    const completedSteps = [];
     // ── LLM Provider Selection ────────────────────────────────────────────────
     const llmResult = await runStep(p, 'LLM setup failed', () => runLlmStep(p, pc, authStorage), {
-        cancelMessage: 'Setup cancelled — you can run /login inside GSD later.',
+        cancelMessage: 'Setup cancelled — you can run /gsd onboarding --resume later.',
         errorInfo: 'You can configure your LLM provider later with /login inside GSD.',
     });
     if (llmResult === STEP_CANCELLED)
         return;
     const llmConfigured = llmResult ?? false;
+    if (llmConfigured) {
+        markStepCompleted('llm');
+        completedSteps.push('llm');
+    }
+    else {
+        markStepSkipped('llm');
+    }
     // ── Web Search Provider ──────────────────────────────────────────────────
     const searchResult = await runStep(p, 'Web search setup failed', () => runWebSearchStep(p, pc, authStorage, llmConfigured));
     if (searchResult === STEP_CANCELLED)
         return;
     const searchConfigured = searchResult;
+    if (searchConfigured) {
+        markStepCompleted('search');
+        completedSteps.push('search');
+    }
+    else {
+        markStepSkipped('search');
+    }
     // ── Remote Questions ─────────────────────────────────────────────────────
     const remoteResult = await runStep(p, 'Remote questions setup failed', () => runRemoteQuestionsStep(p, pc, authStorage));
     if (remoteResult === STEP_CANCELLED)
         return;
     const remoteConfigured = remoteResult;
+    if (remoteConfigured) {
+        markStepCompleted('remote');
+        completedSteps.push('remote');
+    }
+    else {
+        markStepSkipped('remote');
+    }
     // ── Tool API Keys ─────────────────────────────────────────────────────────
     const toolResult = await runStep(p, 'Tool key setup failed', () => runToolKeysStep(p, pc, authStorage));
     if (toolResult === STEP_CANCELLED)
         return;
     const toolKeyCount = toolResult ?? 0;
+    if (toolKeyCount > 0) {
+        markStepCompleted('tool-keys');
+        completedSteps.push('tool-keys');
+    }
+    else {
+        markStepSkipped('tool-keys');
+    }
     // ── Summary ───────────────────────────────────────────────────────────────
     const summaryLines = [];
     if (llmConfigured) {
@@ -268,11 +297,17 @@ export async function runOnboarding(authStorage) {
     else {
         summaryLines.push(`${pc.dim('↷')} Tool keys: none configured`);
     }
+    // Persist completion record so re-entry, web boot probe, and shouldRunOnboarding
+    // all agree the wizard finished. Required steps drive the "complete" semantics
+    // in onboarding-state.ts; here we mark wizard-level completion regardless.
+    markOnboardingComplete(completedSteps);
+    summaryLines.push('');
+    summaryLines.push(`${pc.dim('Tip:')} re-run anytime with ${pc.cyan('/gsd onboarding')}`);
     p.note(summaryLines.join('\n'), 'Setup complete');
     p.outro(pc.dim('Launching GSD...'));
 }
 // ─── LLM Authentication Step ──────────────────────────────────────────────────
-async function runLlmStep(p, pc, authStorage) {
+export async function runLlmStep(p, pc, authStorage) {
     // Build the OAuth provider list dynamically from what's registered
     const oauthProviders = authStorage.getOAuthProviders();
     const oauthMap = new Map(oauthProviders.map(op => [op.id, op]));
@@ -572,7 +607,7 @@ async function runCustomOpenAIFlow(p, pc, authStorage) {
     return true;
 }
 // ─── Web Search Provider Step ─────────────────────────────────────────────────
-async function runWebSearchStep(p, pc, authStorage, isAnthropicAuth) {
+export async function runWebSearchStep(p, pc, authStorage, isAnthropicAuth) {
     // Check which LLM provider was configured
     const authed = authStorage.list().filter(id => LLM_PROVIDER_IDS.includes(id));
     const isAnthropic = isAnthropicAuth && authed.includes('anthropic');
@@ -633,7 +668,7 @@ async function runWebSearchStep(p, pc, authStorage, isAnthropicAuth) {
     return null;
 }
 // ─── Tool API Keys Step ───────────────────────────────────────────────────────
-async function runToolKeysStep(p, pc, authStorage) {
+export async function runToolKeysStep(p, pc, authStorage) {
     // Filter to keys not already configured
     const missing = TOOL_KEYS.filter(tk => !authStorage.has(tk.provider) && !process.env[tk.envVar]);
     if (missing.length === 0)
@@ -668,7 +703,7 @@ async function runToolKeysStep(p, pc, authStorage) {
     return savedCount;
 }
 // ─── Remote Questions Step ────────────────────────────────────────────────────
-async function runRemoteQuestionsStep(p, pc, authStorage) {
+export async function runRemoteQuestionsStep(p, pc, authStorage) {
     // Check existing config — use getCredentialsForProvider to skip empty-key entries
     const hasValidKey = (provider) => authStorage
         .getCredentialsForProvider(provider)

package/dist/resources/extensions/ask-user-questions.js

@@ -316,10 +316,13 @@ export default function AskUserQuestions(pi) {
                             lines.push(`${theme.fg("accent", q.header)}: ${theme.fg("dim", "(no answer)")}`);
                             continue;
                         }
-                        const answerText = answer.answers.length > 0 ? answer.answers.join(", ") : "(custom)";
+                        const selected = answer.selected;
+                        const answerText = Array.isArray(selected)
+                            ? (selected.length > 0 ? selected.join(", ") : "(custom)")
+                            : (selected || "(custom)");
                         let line = `${theme.fg("success", "✓ ")}${theme.fg("accent", q.header)}: ${answerText}`;
-                        if (answer.user_note) {
-                            line += ` ${theme.fg("muted", `[note: ${answer.user_note}]`)}`;
+                        if (answer.notes) {
+                            line += ` ${theme.fg("muted", `[note: ${answer.notes}]`)}`;
                         }
                         lines.push(line);
                     }

package/dist/resources/extensions/claude-code-cli/readiness.js

@@ -9,6 +9,16 @@
  * and check the exit code + output for an authenticated session.
  */
 import { execFileSync } from "node:child_process";
+/**
+ * Platform-correct binary name for the Claude Code CLI.
+ *
+ * On Windows, npm-global binaries are installed as `.cmd` shims and
+ * `execFileSync` does not auto-resolve the extension — calling bare
+ * `claude` would fail with ENOENT even when the CLI is installed and
+ * authenticated. Mirrors the `NPM_COMMAND` pattern in
+ * `src/resources/extensions/gsd/pre-execution-checks.ts`.
+ */
+const CLAUDE_COMMAND = process.platform === "win32" ? "claude.cmd" : "claude";
 let cachedBinaryPresent = null;
 let cachedAuthed = null;
 let lastCheckMs = 0;
@@ -22,7 +32,7 @@ function refreshCache() {
     lastCheckMs = now;
     // Check binary presence
     try {
-        execFileSync("claude", ["--version"], { timeout: 5_000, stdio: "pipe" });
+        execFileSync(CLAUDE_COMMAND, ["--version"], { timeout: 5_000, stdio: "pipe" });
         cachedBinaryPresent = true;
     }
     catch {
@@ -32,7 +42,7 @@ function refreshCache() {
     }
     // Check auth status — exit code 0 with non-error output means authenticated
     try {
-        const output = execFileSync("claude", ["auth", "status"], { timeout: 5_000, stdio: "pipe" })
+        const output = execFileSync(CLAUDE_COMMAND, ["auth", "status"], { timeout: 5_000, stdio: "pipe" })
             .toString()
             .toLowerCase();
         // The CLI outputs "not logged in", "no credentials", or similar when unauthenticated