argusqa-os 9.2.6 → 9.2.8

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "argusqa-os",
-  "version": "9.2.6",
+  "version": "9.2.8",
   "mcpName": "io.github.ironclawdevs27/argus",
   "description": "Argus — AI-powered automated dev-testing platform using Chrome DevTools MCP and Claude Code",
   "keywords": [

package/src/mcp-server.js

@@ -1,6 +1,6 @@
 #!/usr/bin/env node
 /**
- * Argus MCP Server (v9.2.6)
+ * Argus MCP Server (v9.2.8)
  *
  * Exposes Argus as an MCP server so Claude (or any MCP client) can call
  * argus_audit, argus_audit_full, argus_compare, and argus_last_report
@@ -28,6 +28,9 @@ import path from 'path';
 import { createMcpClient }                    from './utils/mcp-client.js';
 import { crawlRouteCheap, runCrawl }          from './orchestration/crawl-and-report.js';
 import { runComparison }                      from './orchestration/env-comparison.js';
+import { WatchSession }                       from './orchestration/watch-mode.js';
+import { CdpBrowserAdapter }                  from './adapters/browser.js';
+import { generateHtmlReport }                 from './utils/html-reporter.js';
 
 const REPORTS_DIR = path.resolve(process.cwd(), 'reports');
 
@@ -36,36 +39,51 @@ const REPORTS_DIR = path.resolve(process.cwd(), 'reports');
 const TOOLS = [
   {
     name: 'argus_audit',
-    description: 'Run a fast QA audit on a URL. Detects JavaScript errors, unhandled promise rejections, network failures (4xx/5xx), API frequency loops, CSS cascade issues, SEO problems, security vulnerabilities, content quality issues, and accessibility violations. Returns findings as JSON grouped by severity (critical/warning/info).',
+    description: 'Fast QA audit on a URL via Chrome DevTools Protocol. Runs 8 analyzers in one pass: JS errors, unhandled rejections, network failures (4xx/5xx), API frequency loops, CSS cascade issues, SEO violations, security header checks, and accessibility. Returns { findings: [{severity, type, message, url}], summary: {critical, warning, info} }. Use for CI smoke tests and pre-deploy gates. For Lighthouse scoring and memory leak detection, use argus_audit_full. Requires Chrome running with --remote-debugging-port=9222.',
     inputSchema: {
       type: 'object',
       properties: {
-        url:      { type: 'string',  description: 'Full URL to audit (e.g. http://localhost:3000/checkout)' },
-        critical: { type: 'boolean', description: 'Treat this route as critical — console errors become critical severity', default: false },
+        url:      { type: 'string',  description: 'Full URL to audit, including protocol and path (e.g. http://localhost:3000/checkout). Must be reachable by the running Chrome instance.' },
+        critical: { type: 'boolean', description: 'When true, console.error calls are escalated to critical severity. Set true for business-critical routes (login, checkout, dashboard) where any error is a blocker.', default: false },
       },
       required: ['url'],
     },
   },
   {
     name: 'argus_audit_full',
-    description: 'Run a deep QA pass on a URL using all analyzers — Lighthouse performance/accessibility scoring, responsive layout checks across mobile/tablet/desktop viewports, memory leak detection via heap snapshot, hover-state bug detection, and accessibility tree snapshot. Returns a full JSON report with findings grouped by severity.',
+    description: 'Deep QA audit — extends argus_audit with Lighthouse performance/accessibility scoring, responsive layout checks across 4 viewports (320/768/1280/1920px), memory leak detection via heap snapshot, hover-state regression detection, and accessibility tree snapshot. Returns full JSON report with findings by severity, Lighthouse scores, and layout overflow details. Use when argus_audit passes clean but visual or performance regressions are suspected. Requires Chrome running with --remote-debugging-port=9222.',
     inputSchema: {
       type: 'object',
       properties: {
-        url:      { type: 'string',  description: 'Full URL to audit (e.g. https://example.com/dashboard)' },
-        critical: { type: 'boolean', description: 'Mark this route as critical — console errors are escalated to critical severity', default: false },
+        url:      { type: 'string',  description: 'Full URL to audit, including protocol and path (e.g. https://example.com/dashboard). Must be reachable by the running Chrome instance.' },
+        critical: { type: 'boolean', description: 'When true, console.error calls are escalated to critical severity. Set true for business-critical routes (login, checkout, dashboard) where any error is a blocker.', default: false },
       },
       required: ['url'],
     },
   },
   {
     name: 'argus_compare',
-    description: 'Snapshot and diff two environments (dev vs staging) side-by-side. Navigates both URLs, captures screenshots, runs the full analyzer suite on each, then diffs the findings to surface regressions — things that appear in staging but not dev, or changed severity. Configure the two target URLs via TARGET_DEV_URL and TARGET_STAGING_URL environment variables before starting the server.',
+    description: 'Diffs dev vs staging environments side-by-side. Navigates both URLs, captures screenshots, and runs the full analyzer suite on each, then surfaces regressions — findings present in staging but not dev, or with changed severity. Returns { regressions: [{type, devSeverity, stagingSeverity}], screenshots, summary }. Run before promoting a build to staging to catch environment-specific bugs. Set TARGET_DEV_URL and TARGET_STAGING_URL env vars before starting the server; omit TARGET_STAGING_URL to run CSS-analysis-only mode.',
     inputSchema: { type: 'object', properties: {} },
   },
   {
     name: 'argus_last_report',
-    description: 'Return the most recent Argus JSON report from the reports/ directory.',
+    description: 'Returns the most recent Argus JSON report from the reports/ directory. Report includes a findings array and severity summary (critical/warning/info counts). Returns { "error": "No reports found in reports/" } when no audits have been run yet. Use to retrieve prior results without re-running a scan, or to pipe findings into another analysis tool.',
+    inputSchema: { type: 'object', properties: {} },
+  },
+  {
+    name: 'argus_watch_snapshot',
+    description: 'Snapshots the currently open Chrome tab without navigating — captures console errors, network failures (4xx/5xx), CORS blocks, and auth failures in one poll. Returns { findings: [{severity, type, message, url}], newConsole, newNetwork }. Use during active development to inspect what is happening on the current page without running a full audit. Requires Chrome on --remote-debugging-port=9222 with a page already open.',
+    inputSchema: {
+      type: 'object',
+      properties: {
+        url: { type: 'string', description: 'Optional base URL to attribute findings to (default: TARGET_DEV_URL env var). Does not navigate — reads the currently open Chrome tab.' },
+      },
+    },
+  },
+  {
+    name: 'argus_report_html',
+    description: 'Generates a self-contained reports/report.html from the most recent Argus JSON report. Inlines all screenshots and findings into a portable single-file HTML dashboard shareable with designers, PMs, or reviewable offline. Returns { path: "reports/report.html" }. Run after argus_audit or argus_audit_full. Returns an error if no JSON reports exist in the reports/ directory.',
     inputSchema: { type: 'object', properties: {} },
   },
 ];
@@ -111,6 +129,31 @@ async function handleCompare() {
   });
 }
 
+async function handleWatchSnapshot({ url } = {}) {
+  return withMcp(async (mcp) => {
+    const browser = new CdpBrowserAdapter(mcp);
+    const baseUrl = url ?? process.env.TARGET_DEV_URL ?? 'http://localhost:3000';
+    const session = new WatchSession(browser, baseUrl);
+    const result  = await session.poll();
+    return { content: [{ type: 'text', text: JSON.stringify(result, null, 2) }] };
+  });
+}
+
+async function handleReportHtml() {
+  if (!fs.existsSync(REPORTS_DIR)) {
+    return { content: [{ type: 'text', text: JSON.stringify({ error: 'No reports directory. Run argus_audit first.' }) }] };
+  }
+  const files = fs.readdirSync(REPORTS_DIR)
+    .filter(f => f.startsWith('error-report-') && f.endsWith('.json'))
+    .map(f => ({ f, mt: fs.statSync(path.join(REPORTS_DIR, f)).mtimeMs }))
+    .sort((a, b) => b.mt - a.mt);
+  if (files.length === 0) {
+    return { content: [{ type: 'text', text: JSON.stringify({ error: 'No reports found. Run argus_audit first.' }) }] };
+  }
+  const outPath = await generateHtmlReport(path.join(REPORTS_DIR, files[0].f));
+  return { content: [{ type: 'text', text: JSON.stringify({ path: outPath }) }] };
+}
+
 async function handleLastReport() {
   if (!fs.existsSync(REPORTS_DIR)) {
     return { content: [{ type: 'text', text: '{"error":"No reports found in reports/"}' }] };
@@ -129,7 +172,7 @@ async function handleLastReport() {
 // ── Server bootstrap ──────────────────────────────────────────────────────────
 
 const server = new Server(
-  { name: 'argus', version: '9.2.6' },
+  { name: 'argus', version: '9.2.8' },
   { capabilities: { tools: {} } },
 );
 
@@ -141,7 +184,9 @@ server.setRequestHandler(CallToolRequestSchema, async (req) => {
       case 'argus_audit':       return await handleAudit(req.params.arguments ?? {});
       case 'argus_audit_full':  return await handleAuditFull(req.params.arguments ?? {});
       case 'argus_compare':     return await handleCompare();
-      case 'argus_last_report': return await handleLastReport();
+      case 'argus_last_report':     return await handleLastReport();
+      case 'argus_watch_snapshot':  return await handleWatchSnapshot(req.params.arguments ?? {});
+      case 'argus_report_html':     return await handleReportHtml();
       default: throw new Error(`Unknown tool: ${req.params.name}`);
     }
   } catch (err) {