helixevo 0.2.5 → 0.2.7

package/README.md

@@ -1,10 +1,10 @@
-# Helix
+# HelixEvo
 
 Self-evolving skill ecosystem for AI agents. Captures failures, evolves skills through multi-judge evaluation, and maintains a Pareto frontier of optimal skill configurations.
 
 ## How it works
 
-Helix builds on ideas from [EvoSkill](https://arxiv.org/abs/2603.02766) and [AutoResearch](https://github.com/karpathy/autoResearch) to create a three-directional evolution system:
+HelixEvo builds on ideas from [EvoSkill](https://arxiv.org/abs/2603.02766) and [AutoResearch](https://github.com/karpathy/autoResearch) to create a three-directional evolution system:
 
 - **Generalize ↑** — Detect cross-project patterns and promote them to abstract skills
 - **Specialize ↓** — Create project-specific skills from domain skills + project failures
@@ -21,7 +21,7 @@ Every proposed change goes through:
 - **[Bun](https://bun.sh)** — used for building (`curl -fsSL https://bun.sh/install | bash`)
 - **[Claude CLI](https://docs.anthropic.com/en/docs/claude-code)** — installed and authenticated
   - Requires a **Claude Max plan** subscription
-  - Helix uses `claude --print` for all LLM operations (no API key needed)
+  - HelixEvo uses `claude --print` for all LLM operations (no API key needed)
 
 Verify prerequisites:
 ```bash
@@ -160,7 +160,7 @@ cd dashboard && npm install
 
 ## Craft Agent Integration
 
-Helix includes a Craft Agent skill at `integrations/craft-agent/`:
+HelixEvo includes a Craft Agent skill at `integrations/craft-agent/`:
 
 ```bash
 # Copy to your skills directory

package/dashboard/app/guide/page.tsx

@@ -1,6 +1,6 @@
 'use client'
 
-import { useState } from 'react'
+import { useState, useEffect, useRef } from 'react'
 
 // ─── Table of Contents ──────────────────────────────────────────
 const TOC = [
@@ -195,6 +195,30 @@ function HierarchyDiagram() {
 // ─── Main Guide Page ────────────────────────────────────────────
 export default function GuidePage() {
   const [activeSection, setActiveSection] = useState('overview')
+  const contentRef = useRef<HTMLDivElement>(null)
+
+  useEffect(() => {
+    const sectionIds = TOC.map(t => t.id)
+    const observer = new IntersectionObserver(
+      (entries) => {
+        // Find the most visible section
+        const visible = entries
+          .filter(e => e.isIntersecting)
+          .sort((a, b) => b.intersectionRatio - a.intersectionRatio)
+        if (visible.length > 0) {
+          setActiveSection(visible[0].target.id)
+        }
+      },
+      { rootMargin: '-80px 0px -60% 0px', threshold: [0, 0.25, 0.5] }
+    )
+
+    for (const id of sectionIds) {
+      const el = document.getElementById(id)
+      if (el) observer.observe(el)
+    }
+
+    return () => observer.disconnect()
+  }, [])
 
   return (
     <div className="guide-layout">
@@ -202,7 +226,7 @@ export default function GuidePage() {
       <nav className="guide-toc">
         <div className="guide-toc-header">
           <div className="guide-toc-title">Documentation</div>
-          <div className="guide-toc-version">v0.2.0</div>
+          <div className="guide-toc-version">v0.2.6</div>
         </div>
         {TOC.map(item => (
           <a
@@ -222,7 +246,7 @@ export default function GuidePage() {
         {/* Hero */}
         <div className="guide-hero">
           <div className="guide-hero-badge">Documentation</div>
-          <h1 className="guide-hero-title">Helix Guide</h1>
+          <h1 className="guide-hero-title">HelixEvo Guide</h1>
           <p className="guide-hero-desc">
             A comprehensive guide to the self-evolving skill ecosystem for AI agents.
             Capture failures, evolve skills through multi-judge evaluation, and maintain
@@ -237,15 +261,15 @@ export default function GuidePage() {
         </div>
 
         {/* ─── Overview ─── */}
-        <Section id="overview" title="Overview" subtitle="What Helix does and why it exists.">
+        <Section id="overview" title="Overview" subtitle="What HelixEvo does and why it exists.">
           <p className="guide-text">
-            Helix is a self-improving system that manages SKILL.md files for AI agents. When an agent makes a mistake
-            and gets corrected, Helix captures that failure, clusters similar failures together, and proposes skill
+            HelixEvo is a self-improving system that manages SKILL.md files for AI agents. When an agent makes a mistake
+            and gets corrected, HelixEvo captures that failure, clusters similar failures together, and proposes skill
             improvements. Every proposed change goes through rigorous multi-judge evaluation and regression testing before
             being deployed with a 3-day canary period.
           </p>
           <p className="guide-text">
-            Built on ideas from <strong>EvoSkill</strong> and <strong>AutoResearch</strong>, Helix implements a
+            Built on ideas from <strong>EvoSkill</strong> and <strong>AutoResearch</strong>, HelixEvo implements a
             three-directional evolution model:
           </p>
           <div className="guide-directions">
@@ -280,9 +304,9 @@ export default function GuidePage() {
             and <a href="https://docs.anthropic.com/en/docs/claude-code">Claude CLI</a> with a Claude Max plan.
           </Callout>
 
-          <Step n={1} title="Install Helix">
+          <Step n={1} title="Install HelixEvo">
             <Code title="Terminal">{`# From npm (recommended)
-npm install -g helix
+npm install -g helixevo
 
 # Or from source
 git clone https://github.com/danielchen26/helixevo.git
@@ -292,7 +316,7 @@ cd helixevo && npm install && npm run build && npm link`}</Code>
           <Step n={2} title="Initialize your skill ecosystem">
             <Code title="Terminal">{`helixevo init`}</Code>
             <p className="guide-text-sm">
-              This scans your existing SKILL.md files (from <code>~/.agents/skills/</code>), imports them into Helix,
+              This scans your existing SKILL.md files (from <code>~/.agents/skills/</code>), imports them into HelixEvo,
               and generates golden test cases for each skill. It also creates the data directory at <code>~/.helix/</code>.
             </p>
           </Step>
@@ -326,7 +350,7 @@ helixevo status`}</Code>
         </Section>
 
         {/* ─── Commands ─── */}
-        <Section id="commands" title="Commands" subtitle="Complete CLI reference for every Helix command.">
+        <Section id="commands" title="Commands" subtitle="Complete CLI reference for every HelixEvo command.">
           <div className="guide-command-grid">
             {[
               {
@@ -336,7 +360,7 @@ helixevo status`}</Code>
               },
               {
                 cmd: 'helixevo metrics',
-                desc: 'Show correction rates per skill, trends over time, and whether each evolution actually reduced corrections. The proof that Helix works.',
+                desc: 'Show correction rates per skill, trends over time, and whether each evolution actually reduced corrections. The proof that HelixEvo works.',
                 flags: ['--verbose'],
               },
               {
@@ -346,7 +370,7 @@ helixevo status`}</Code>
               },
               {
                 cmd: 'helixevo init',
-                desc: 'Import existing skills and generate golden test cases. Scans ~/.agents/skills/ and creates the Helix data directory.',
+                desc: 'Import existing skills and generate golden test cases. Scans ~/.agents/skills/ and creates the HelixEvo data directory.',
                 flags: ['--verbose'],
               },
               {
@@ -431,7 +455,7 @@ helixevo status`}</Code>
         </Section>
 
         {/* ─── Always-On Learning ─── */}
-        <Section id="watch" title="Always-On Learning" subtitle="Helix watches your work, captures corrections automatically, and evolves without manual intervention.">
+        <Section id="watch" title="Always-On Learning" subtitle="HelixEvo watches your work, captures corrections automatically, and evolves without manual intervention.">
           <p className="guide-text">
             Instead of manually running <code>helixevo capture</code> after each session, <code>helixevo watch</code> runs
             continuously in the background. It monitors your conversation events in real-time, detects when you
@@ -477,7 +501,7 @@ helixevo watch --events path/to/events.jsonl --verbose`}</Code>
         {/* ─── Network Health ─── */}
         <Section id="networkhealth" title="Network Health" subtitle="The skill network is a co-evolving organism — its health determines project success.">
           <p className="guide-text">
-            Individual skill evolution is only part of the picture. Helix now treats the <strong>entire skill network</strong> as
+            Individual skill evolution is only part of the picture. HelixEvo now treats the <strong>entire skill network</strong> as
             a first-class entity that co-evolves with your projects. Network health is assessed across 4 dimensions after
             every evolution cycle.
           </p>
@@ -509,9 +533,9 @@ helixevo watch --events path/to/events.jsonl --verbose`}</Code>
         </Section>
 
         {/* ─── Auto-Generalization ─── */}
-        <Section id="autogen" title="Auto-Generalization" subtitle="When patterns recur across projects, Helix automatically creates abstract domain-level skills.">
+        <Section id="autogen" title="Auto-Generalization" subtitle="When patterns recur across projects, HelixEvo automatically creates abstract domain-level skills.">
           <p className="guide-text">
-            Instead of waiting for you to run <code>helixevo generalize</code>, Helix now detects cross-project patterns
+            Instead of waiting for you to run <code>helixevo generalize</code>, HelixEvo now detects cross-project patterns
             automatically during every evolution cycle. When the same type of correction appears in 2+ projects, it
             creates an abstract domain-level skill and sets up parent/child inheritance.
           </p>
@@ -530,9 +554,9 @@ Project B: "Use FlashList not FlatList" (React Native perf)
         </Section>
 
         {/* ─── Closed-Loop Metrics ─── */}
-        <Section id="metrics" title="Closed-Loop Metrics" subtitle="Proving that Helix actually makes the agent better — with data, not just LLM scores.">
+        <Section id="metrics" title="Closed-Loop Metrics" subtitle="Proving that HelixEvo actually makes the agent better — with data, not just LLM scores.">
           <p className="guide-text">
-            The <code>helixevo metrics</code> command answers the most important question: <strong>&ldquo;Is Helix actually
+            The <code>helixevo metrics</code> command answers the most important question: <strong>&ldquo;Is HelixEvo actually
             reducing corrections?&rdquo;</strong> It tracks correction rates per skill over time and measures the real
             impact of each evolution.
           </p>
@@ -685,7 +709,7 @@ Project B: "Use FlashList not FlatList" (React Native perf)
 
           <h3 className="guide-h3">Cross-Skill Regression</h3>
           <p className="guide-text">
-            When skill A is modified, Helix also tests golden cases from co-evolved, dependent, and enhancing
+            When skill A is modified, HelixEvo also tests golden cases from co-evolved, dependent, and enhancing
             partner skills. This catches silent incompatibilities where changing one skill breaks a related skill&apos;s behavior.
           </p>
           <Code title="How it works">{`Skill A evolves
@@ -888,9 +912,9 @@ generation: 3
         </Section>
 
         {/* ─── Craft Agent Integration ─── */}
-        <Section id="craft" title="Craft Agent Integration" subtitle="Use Helix from within Craft Agent.">
+        <Section id="craft" title="Craft Agent Integration" subtitle="Use HelixEvo from within Craft Agent.">
           <p className="guide-text">
-            Helix ships with a Craft Agent skill at <code>integrations/craft-agent/</code>.
+            HelixEvo ships with a Craft Agent skill at <code>integrations/craft-agent/</code>.
             Install it to trigger evolution directly from your Craft Agent sessions.
           </p>
           <Step n={1} title="Copy the skill">
@@ -911,26 +935,26 @@ generation: 3
             By default, 5 unresolved failures are required (<code>minFailuresForEvolution</code>).
             This ensures enough signal for meaningful pattern detection.
           </FAQItem>
-          <FAQItem q="What LLM model does Helix use?">
-            Helix uses <code>claude --print</code> with configurable models (default: <code>sonnet</code>).
+          <FAQItem q="What LLM model does HelixEvo use?">
+            HelixEvo uses <code>claude --print</code> with configurable models (default: <code>sonnet</code>).
             No API key is needed — it requires a Claude Max plan subscription. Judges and proposals can use different models.
           </FAQItem>
-          <FAQItem q="Can I use Helix with other AI agents?">
-            Yes. Helix manages standard SKILL.md files with YAML frontmatter. Any agent that reads SKILL.md
-            files can benefit from Helix&apos;s evolution pipeline.
+          <FAQItem q="Can I use HelixEvo with other AI agents?">
+            Yes. HelixEvo manages standard SKILL.md files with YAML frontmatter. Any agent that reads SKILL.md
+            files can benefit from HelixEvo&apos;s evolution pipeline.
           </FAQItem>
           <FAQItem q="What happens during canary rollback?">
             If the failure rate for a canary skill exceeds <code>autoRollbackThreshold</code> (default: 1.5x),
             the skill is automatically reverted from the backup. The failed evolution is recorded in history.
           </FAQItem>
           <FAQItem q="How does cross-skill regression work?">
-            When Skill A evolves, Helix checks the skill graph for co-evolved, dependent, and enhancing
+            When Skill A evolves, HelixEvo checks the skill graph for co-evolved, dependent, and enhancing
             partners. It tests their golden cases against Skill A&apos;s changes. If partner pass rate drops below 95%,
             the proposal is rejected.
           </FAQItem>
           <FAQItem q="How does the knowledge buffer work?">
             All research discoveries are saved, even if the resulting hypothesis fails. Failed experiments above
-            a minimum score are saved as drafts. When the same hypothesis appears again, Helix iterates on
+            a minimum score are saved as drafts. When the same hypothesis appears again, HelixEvo iterates on
             the draft rather than starting from scratch.
           </FAQItem>
           <FAQItem q="How does helixevo watch detect corrections?">
@@ -938,7 +962,7 @@ generation: 3
             (e.g., &quot;wrong&quot;, &quot;not like that&quot;, &quot;不对&quot;, &quot;改成&quot;). (2) If a signal is detected, an LLM analyzes
             the recent conversation window to extract structured failure records with confidence scores (&gt;0.7 required).
           </FAQItem>
-          <FAQItem q="How do I prove Helix is working?">
+          <FAQItem q="How do I prove HelixEvo is working?">
             Run <code>helixevo metrics</code>. It tracks correction rates per skill over 7-day rolling windows
             and compares before/after rates for each evolution. The verdict shows how many evolutions actually
             reduced corrections. This is closed-loop measurement — not LLM scores judging LLM output.
@@ -958,7 +982,7 @@ generation: 3
         {/* Footer */}
         <div className="guide-footer">
           <div className="guide-footer-content">
-            <div style={{ fontSize: 13, fontWeight: 600 }}>Helix v0.2.0</div>
+            <div style={{ fontSize: 13, fontWeight: 600 }}>HelixEvo v0.2.6</div>
             <div style={{ fontSize: 12, color: 'var(--text-dim)', marginTop: 4 }}>
               Self-evolving skill ecosystem for AI agents · MIT License
             </div>

package/dashboard/app/layout.tsx

@@ -3,8 +3,8 @@ import type { Metadata } from 'next'
 import Link from 'next/link'
 
 export const metadata: Metadata = {
-  title: 'Helix',
-  description: 'Self-evolving skill ecosystem for AI agents',
+  title: 'HelixEvo',
+  description: 'HelixEvo — Self-evolving skill ecosystem for AI agents',
 }
 
 const NAV = [
@@ -40,7 +40,7 @@ export default function RootLayout({ children }: { children: React.ReactNode })
                 </svg>
               </div>
               <div>
-                <div style={{ fontSize: 14, fontWeight: 700, color: 'var(--text)', letterSpacing: -0.3 }}>Helix</div>
+                <div style={{ fontSize: 14, fontWeight: 700, color: 'var(--text)', letterSpacing: -0.3 }}>HelixEvo</div>
                 <div style={{ fontSize: 10, color: 'var(--text-muted)', letterSpacing: 0.2 }}>Co-evolving AI Skills</div>
               </div>
             </div>

package/dashboard/package.json

@@ -1,5 +1,5 @@
 {
-  "name": "helix-dashboard",
+  "name": "helixevo-dashboard",
   "version": "0.1.0",
   "private": true,
   "scripts": {

package/dist/cli.js

@@ -9604,7 +9604,7 @@ Return JSON:
 
 // src/commands/init.ts
 async function initCommand(options) {
-  console.log(`\uD83E\uDDEC Initializing Helix...
+  console.log(`\uD83E\uDDEC Initializing HelixEvo...
 `);
   const sgDir = getHelixDir();
   const generalDir = getGeneralSkillsPath();
@@ -9680,7 +9680,7 @@ async function initCommand(options) {
     }
   }
   console.log(`
-✓ Helix initialized!`);
+✓ HelixEvo initialized!`);
   console.log(`  Data:   ${sgDir}`);
   console.log(`  Skills: ${generalDir}`);
   console.log(`
@@ -10350,7 +10350,7 @@ async function evolveCommand(options) {
   const dryRun = options.dryRun ?? false;
   const verbose = options.verbose ?? false;
   const maxProposals = parseInt(options.maxProposals ?? String(config.evolution.maxProposalsPerRun));
-  console.log(`\uD83E\uDDEC Helix Evolution Cycle
+  console.log(`\uD83E\uDDEC HelixEvo Evolution Cycle
 `);
   const allFailures = loadFailures();
   const failures = allFailures.filter((f) => !f.resolved);
@@ -10706,7 +10706,7 @@ async function statusCommand() {
   const goldenCases = loadGoldenCases();
   const stagnation = getStagnationCount();
   const recentIter = getRecentIterations(7);
-  console.log(`\uD83E\uDDEC Helix Status
+  console.log(`\uD83E\uDDEC HelixEvo Status
 `);
   console.log(`  Skills: ${skills.length}`);
   for (const s of skills) {
@@ -10767,7 +10767,7 @@ async function reportCommand(options) {
   const accepted = allProposals.filter((p) => p.outcome === "accepted");
   const rejected = allProposals.filter((p) => p.outcome === "rejected");
   const date = new Date().toISOString().slice(0, 10);
-  let report = `# Helix Report — ${date}
+  let report = `# HelixEvo Report — ${date}
 
 `;
   report += `## Overview
@@ -10851,7 +10851,7 @@ async function generalizeCommand(options) {
   const verbose = options.verbose ?? false;
   const dryRun = options.dryRun ?? false;
   const skills = loadAllGeneralSkills();
-  console.log(`\uD83D\uDD2C Helix Generalization Analysis
+  console.log(`\uD83D\uDD2C HelixEvo Generalization Analysis
 `);
   if (skills.length < 2) {
     console.log("  Need at least 2 skills to detect generalization candidates.");
@@ -11026,7 +11026,7 @@ async function specializeCommand(options) {
     console.error("  Error: --project <name> is required");
     process.exit(1);
   }
-  console.log(`\uD83C\uDFAF Helix Specialization for project "${projectName}"
+  console.log(`\uD83C\uDFAF HelixEvo Specialization for project "${projectName}"
 `);
   const failures = loadFailures().filter((f) => f.project === projectName && !f.resolved);
   const skills = loadAllGeneralSkills();
@@ -11556,7 +11556,7 @@ function syncToObsidian(vaultPath, verbose = false) {
       console.log(`  ✓ ${node.id}.md`);
   }
   const indexNote = generateIndexNote(graph);
-  writeFileSync7(join11(vaultPath, "Helix Index.md"), indexNote);
+  writeFileSync7(join11(vaultPath, "HelixEvo Index.md"), indexNote);
   const recent = getRecentIterations(7);
   if (recent.length > 0) {
     const report = generateEvolutionReport(recent);
@@ -11633,7 +11633,7 @@ ${skill.content.slice(0, 3000)}
   return note;
 }
 function generateIndexNote(graph) {
-  let note = `# Helix Index
+  let note = `# HelixEvo Index
 
 `;
   note += `*Updated: ${graph.updated}*
@@ -11744,7 +11744,7 @@ function openMermaidInBrowser(graph) {
   const html = `<!DOCTYPE html>
 <html><head>
 <meta charset="utf-8">
-<title>Helix Network</title>
+<title>HelixEvo Network</title>
 <style>
   * { box-sizing: border-box; margin: 0; padding: 0; }
   body {
@@ -11850,7 +11850,7 @@ function openMermaidInBrowser(graph) {
 </head><body>
 
 <div class="header">
-  <h1>Helix Network</h1>
+  <h1>HelixEvo Network</h1>
   <div class="stats">${graph.nodes.length} skills &middot; ${graph.edges.length} relationships &middot; ${graph.clusters.length} clusters</div>
 </div>
 
@@ -11928,7 +11928,7 @@ ${mermaidCode}
 function renderTerminalGraph(graph) {
   const w = Math.min(process.stdout.columns || 80, 100);
   console.log();
-  console.log(`${C.bold}  \uD83D\uDD78️  Helix Network${C.reset}`);
+  console.log(`${C.bold}  \uD83D\uDD78️  HelixEvo Network${C.reset}`);
   console.log(`  ${C.dim}${graph.nodes.length} skills · ${graph.edges.length} relationships · ${graph.clusters.length} clusters${C.reset}`);
   console.log();
   const layers = [
@@ -11991,7 +11991,7 @@ async function researchCommand(options) {
   const verbose = options.verbose ?? false;
   const dryRun = options.dryRun ?? false;
   const maxHypotheses = parseInt(options.maxHypotheses ?? "3");
-  console.log(`\uD83D\uDD2C Helix Proactive Research
+  console.log(`\uD83D\uDD2C HelixEvo Proactive Research
 `);
   const skills = loadAllGeneralSkills();
   console.log("  Step 1: Understanding project goals...");
@@ -12338,7 +12338,7 @@ async function dashboardCommand() {
       process.exit(1);
     }
   }
-  console.log(`  \uD83C\uDF10 Starting Helix Dashboard at http://localhost:3847
+  console.log(`  \uD83C\uDF10 Starting HelixEvo Dashboard at http://localhost:3847
 `);
   const child = spawn2("npx", ["next", "dev", "--port", "3847"], {
     cwd: dir,
@@ -12769,7 +12769,7 @@ async function watchCommand(options) {
   const autoEvolve = options.evolve !== false;
   const project = options.project ?? null;
   const eventsPath = options.events ?? join16(process.cwd(), "events.jsonl");
-  console.log(`\uD83E\uDDEC Helix Watch Mode — Always-On Learning
+  console.log(`\uD83E\uDDEC HelixEvo Watch Mode — Always-On Learning
 `);
   console.log(`  Events:      ${eventsPath}`);
   console.log(`  Project:     ${project ?? "(auto-detect)"}`);
@@ -12870,7 +12870,7 @@ async function watchCommand(options) {
 async function metricsCommand(options) {
   const verbose = options.verbose ?? false;
   const summary = getMetricsSummary();
-  console.log(`\uD83D\uDCCA Helix Metrics
+  console.log(`\uD83D\uDCCA HelixEvo Metrics
 `);
   console.log("  ── Correction Rate ──");
   console.log(`  Total failures:     ${summary.totalFailures}`);
@@ -12914,7 +12914,7 @@ async function metricsCommand(options) {
     console.log(`  ${effective}/${total} evolutions reduced corrections`);
     console.log(`  ${regressed}/${total} evolutions increased corrections`);
     if (effective > regressed) {
-      console.log("  ✓ Helix is making the agent better");
+      console.log("  ✓ HelixEvo is making the agent better");
     } else if (effective === 0 && total > 0) {
       console.log("  ⚠ Not enough data yet — keep working");
     }
@@ -12924,7 +12924,7 @@ async function metricsCommand(options) {
 
 // src/cli.ts
 var program2 = new Command;
-program2.name("helixevo").description("Self-evolving skill ecosystem for AI agents").version("0.2.5").addHelpText("after", `
+program2.name("helixevo").description("Self-evolving skill ecosystem for AI agents").version("0.2.7").addHelpText("after", `
 Examples:
   $ helixevo watch                         Always-on learning (auto-capture + auto-evolve)
   $ helixevo watch --project myapp         Watch with project context

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "helixevo",
-  "version": "0.2.5",
+  "version": "0.2.7",
   "description": "Self-evolving skill ecosystem for AI agents. Skills and projects co-evolve through multi-judge evaluation and a Pareto frontier.",
   "type": "module",
   "bin": {
@@ -40,7 +40,7 @@
     "claude",
     "claude-code",
     "helixevo",
-    "helix",
+    "helixevo",
     "co-evolution",
     "pareto-frontier",
     "llm"