@covibes/zeroshot 4.2.0 → 5.0.0

package/CHANGELOG.md

@@ -1,3 +1,17 @@
+# [5.0.0](https://github.com/covibes/zeroshot/compare/v4.2.0...v5.0.0) (2026-01-07)
+
+
+* feat!: remove interactive setup wizard ([5438953](https://github.com/covibes/zeroshot/commit/54389536e478be1dce0ab707ac7ef8e4ef6ce26d))
+
+
+### BREAKING CHANGES
+
+* Interactive setup wizard removed. Configure via:
+  zeroshot settings set maxModel opus
+  zeroshot settings set dockerMounts '["gh","git","ssh"]'
+
+Closes: Setup wizard blocking non-interactive usage
+
 # [4.2.0](https://github.com/covibes/zeroshot/compare/v4.1.4...v4.2.0) (2026-01-06)
 
 

package/README.md

@@ -8,7 +8,24 @@
 
 > **2024** was the year of LLMs. **2025** was the year of agents. **2026** is the year of agent clusters.
 
-**Multi-agent coding CLI built on Claude Code.**
+**Autonomous engineering teams for Claude Code.**
+
+## Install
+
+**Platforms**: Linux, macOS
+
+```bash
+npm install -g @covibes/zeroshot
+```
+
+**Requires**: Node 18+, [Claude Code CLI](https://claude.com/product/claude-code), [GitHub CLI](https://cli.github.com/)
+
+```bash
+npm i -g @anthropic-ai/claude-code && claude auth login
+gh auth login
+```
+
+---
 
 You know the problem. Your AI agent:
 
@@ -44,7 +61,7 @@ with details of what conflicted. Handle the ABA problem where version goes A->B-
 <p align="center">
   <img src="./docs/assets/zeroshot-demo.gif" alt="Demo" width="700">
   <br>
-  <em>Sped up 100x — 90 minutes, $16, 5 iterations until validators approved</em>
+  <em>Sped up 100x — 90 minutes, 5 iterations until validators approved</em>
 </p>
 
 **The full fix cycle.** Initial implementation passed basic tests but validators caught edge cases: race conditions in concurrent updates, ABA problem not fully handled, retry backoff timing issues. Each rejection triggered fixes until all 48 tests passed with 91%+ coverage.
@@ -59,15 +76,15 @@ A single agent would say "done!" after the first implementation. Here, the adver
 
 **Zeroshot requires well-defined tasks with clear acceptance criteria.**
 
-| Scenario | Zeroshot? | Why |
-|----------|-----------|-----|
-| "Add rate limiting with sliding window, per-IP, 429 responses" | ✅ Yes | Clear requirements, validators can verify each one |
-| "Refactor auth to use JWT instead of sessions" | ✅ Yes | Known complexity, defined end state |
-| "Fix the bug where users can't login" | ✅ Yes | Known unknown - need to find cause, but success is clear |
-| "Fix all 2410 linting violations" | ✅ Yes | Long-running batch task, clear completion (0 violations) |
-| "Make the app faster" | ❌ No | Unknown unknowns - need exploration first |
-| "Improve the codebase" | ❌ No | No acceptance criteria to validate |
-| "Figure out why tests are flaky" | ❌ No | Exploratory - use single-agent Claude Code |
+| Scenario | Use? | Why |
+|----------|:----:|-----|
+| Add rate limiting (sliding window, per-IP, 429) | ✅ | Clear requirements |
+| Refactor auth to JWT | ✅ | Defined end state |
+| Fix login bug | ✅ | Success is measurable |
+| Fix 2410 lint violations | ✅ | Clear completion criteria |
+| Make the app faster | ❌ | Needs exploration first |
+| Improve the codebase | ❌ | No acceptance criteria |
+| Figure out flaky tests | ❌ | Exploratory |
 
 **Known unknowns** (implementation details unclear) → Zeroshot handles this. The planner figures it out.
 
@@ -84,23 +101,6 @@ Crash recovery (`zeroshot resume`) means multi-hour tasks survive interruptions.
 
 ---
 
-## Install
-
-**Platforms**: Linux, macOS
-
-```bash
-npm install -g @covibes/zeroshot
-```
-
-**Requires**: Node 18+, [Claude Code CLI](https://claude.com/product/claude-code), [GitHub CLI](https://cli.github.com/)
-
-```bash
-npm i -g @anthropic-ai/claude-code && claude auth login
-gh auth login
-```
-
----
-
 ## Commands
 
 ```bash
@@ -344,12 +344,14 @@ Full isolation in a fresh container. Your workspace stays untouched. Good for ri
 
 | Scenario | Recommended |
 | -------- | ----------- |
-| Quick trusted task | No isolation (default) |
+| Quick task, review changes yourself | No isolation (default) |
 | PR workflow, code review | `--worktree` or `--pr` |
 | Risky experiment, might break things | `--docker` |
 | Running multiple tasks in parallel | `--docker` |
 | Full automation, no review needed | `--ship` |
 
+**Default mode:** Agents are instructed to only modify files (no git commit/push). You review and commit yourself.
+
 <details>
 <summary><strong>Docker Credential Mounts</strong></summary>
 

package/cli/index.js

@@ -48,7 +48,7 @@ const {
 } = require('../lib/settings');
 const { MOUNT_PRESETS, resolveEnvs } = require('../lib/docker-config');
 const { requirePreflight } = require('../src/preflight');
-const { checkFirstRun } = require('./lib/first-run');
+// Setup wizard removed - use: zeroshot settings set <key> <value>
 const { checkForUpdates } = require('./lib/update-checker');
 const { StatusFooter, AGENT_STATE, ACTIVE_STATES } = require('../src/status-footer');
 
@@ -2771,7 +2771,7 @@ const settingsCmd = program.command('settings').description('Manage zeroshot set
 function formatSettingsList(settings, showUsage = false) {
   const DOCKER_KEYS = ['dockerMounts', 'dockerEnvPassthrough', 'dockerContainerHome'];
 
-  console.log(chalk.bold('\nCrew Settings:\n'));
+  console.log(chalk.bold('\nSettings:\n'));
 
   // Non-docker settings first
   for (const [key, value] of Object.entries(settings)) {
@@ -2861,6 +2861,13 @@ function formatSettingsList(settings, showUsage = false) {
     console.log(chalk.dim('  zeroshot settings get <key>'));
     console.log(chalk.dim('  zeroshot settings reset'));
     console.log('');
+    console.log(chalk.dim('Examples:'));
+    console.log(chalk.dim('  zeroshot settings set maxModel opus'));
+    console.log(chalk.dim('  zeroshot settings set dockerMounts \'["gh","git","ssh","aws"]\''));
+    console.log(chalk.dim('  zeroshot settings set dockerEnvPassthrough \'["AWS_*","TF_VAR_*"]\''));
+    console.log('');
+    console.log(chalk.dim('Available mount presets: gh, git, ssh, aws, azure, kube, terraform, gcloud'));
+    console.log('');
   }
 }
 
@@ -4480,10 +4487,7 @@ function printMessage(msg, showClusterId = false, watchMode = false, isActive =
 
 // Main async entry point
 async function main() {
-  // First-run setup wizard (blocks on first use only)
-  // CRITICAL: Auto-enable quiet mode in test environment to prevent stdin hangs
   const isQuiet = process.argv.includes('-q') || process.argv.includes('--quiet') || process.env.NODE_ENV === 'test';
-  await checkFirstRun({ quiet: isQuiet });
 
   // Check for updates (non-blocking if offline)
   await checkForUpdates({ quiet: isQuiet });

package/lib/settings.js

@@ -57,7 +57,7 @@ function validateModelAgainstMax(requestedModel, maxModel) {
 
 // Default settings
 const DEFAULT_SETTINGS = {
-  maxModel: 'sonnet', // Cost ceiling - agents cannot use models above this
+  maxModel: 'opus', // Cost ceiling - agents cannot use models above this
   defaultConfig: 'conductor-bootstrap',
   defaultDocker: false,
   strictSchema: true, // true = reliable json output (default), false = live streaming (may crash - see bold-meadow-11)
@@ -66,8 +66,6 @@ const DEFAULT_SETTINGS = {
   autoCheckUpdates: true, // Check npm registry for newer versions
   lastUpdateCheckAt: null, // Unix timestamp of last check (null = never checked)
   lastSeenVersion: null, // Don't re-prompt for same version
-  // First-run wizard
-  firstRunComplete: false, // Has user completed first-run setup?
   // Docker isolation mounts - preset names or {host, container, readonly?} objects
   // Valid presets: gh, git, ssh, aws, azure, kube, terraform, gcloud
   dockerMounts: ['gh', 'git', 'ssh'],

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@covibes/zeroshot",
-  "version": "4.2.0",
+  "version": "5.0.0",
   "description": "Multi-agent orchestration engine for Claude - cluster coordinator and CLI",
   "main": "src/orchestrator.js",
   "bin": {