@tekyzinc/gsd-t 2.71.15 → 2.71.17

package/CHANGELOG.md

@@ -2,6 +2,21 @@
 
 All notable changes to GSD-T are documented here. Updated with each release.
 
+## [2.71.17] - 2026-04-08
+
+### Fixed (orchestrator — auto-review cycle limit)
+- **Bumped maxAutoReviewCycles from 2 to 4** — 2 cycles was too conservative for complex components (e.g., charts with multiple contract properties). 4 cycles gives the reviewer/fixer loop enough iterations to converge.
+
+## [2.71.16] - 2026-04-08
+
+### Added (orchestrator — automated AI review loop)
+- **Automated review before human review** — orchestrator now spawns an independent reviewer Claude (no builder context) that compares built components against design contracts. If issues found, spawns a fixer Claude, re-measures, and re-reviews (max 2 cycles). Only after automated review passes do items reach human review. This is the Term 2 equivalent, running deterministically in JavaScript.
+- **Review report persistence** — each auto-review cycle writes results to `.gsd-t/design-review/auto-review/`. Unresolved issues are written to `{phase}-unresolved.json` for human visibility.
+- **Structured review output** — reviewer uses `[REVIEW_ISSUES]` markers for reliable parsing. Fallback parser catches DEVIATION/FAIL/CRITICAL keywords.
+
+### Pipeline (updated)
+Build → Measure → **Automated AI Review** (reviewer → fixer → re-review loop) → Human Review → Next Tier
+
 ## [2.71.15] - 2026-04-08
 
 ### Changed (design-build command → orchestrator delegate)

package/bin/design-orchestrator.js

@@ -300,6 +300,91 @@ function buildFixPrompt(phase, needsWork) {
   return `Apply these specific fixes to ${phase} components:\n\n${fixes}\n\nApply the changes and EXIT. Do not rebuild anything else.`;
 }
 
+// ─── Automated AI Review (Term 2 equivalent) ───────────────────────────────
+
+function buildReviewPrompt(phase, items, measurements, projectDir, ports) {
+  const singular = PHASE_SINGULAR[phase];
+  const contractsDir = path.join(projectDir, CONTRACTS_DIR);
+
+  const componentList = items.map(c => {
+    const sourcePath = c.sourcePath || guessPaths(phase, c);
+    return `- **${c.componentName}** — contract: ${c.fullContractPath}, source: ${sourcePath}, selector: \`${c.selector || "." + c.id}\``;
+  }).join("\n");
+
+  // Include any measurement failures for context
+  const failedMeasurements = [];
+  for (const item of items) {
+    const m = measurements[item.id] || [];
+    const failures = m.filter(x => !x.pass);
+    if (failures.length > 0) {
+      failedMeasurements.push(`- ${item.componentName}: ${failures.map(f => `${f.property}: expected ${f.expected}, got ${f.actual}`).join("; ")}`);
+    }
+  }
+  const measurementContext = failedMeasurements.length > 0
+    ? `\n## Known Measurement Failures\nPlaywright already detected these — verify they are real issues:\n${failedMeasurements.join("\n")}\n`
+    : "";
+
+  return `You are an INDEPENDENT design reviewer. You have NO knowledge of how these components were built. Your job is to compare the built ${phase} against their design contracts and find deviations.
+
+## Components to Review
+${componentList}
+
+${measurementContext}
+## Review Process
+
+For EACH component:
+1. Read the design contract file (path given above) — note every specified property value
+2. Read the source file — check that specified values are implemented correctly
+3. Use Playwright to render the component at http://localhost:${ports.reviewPort}/ and measure:
+   - Does the component render and have correct dimensions?
+   - Do colors, fonts, spacing, border-radius match the contract?
+   - For charts: correct chart type, orientation, axis labels, legend position, data format?
+   - For layouts: correct grid columns, gap, padding, child count and arrangement?
+   - For interactive elements: correct states, hover effects, click behavior?
+4. Compare contract values against actual rendered values — be SPECIFIC (exact px, hex, counts)
+
+## Output Format
+
+Output your findings between these markers. Each issue must have component, severity (critical/high/medium/low), and description with SPECIFIC contract vs. actual values:
+
+[REVIEW_ISSUES]
+[
+  {"component": "ComponentName", "severity": "critical", "description": "Contract specifies donut chart but rendered as pie chart (no inner radius)"},
+  {"component": "ComponentName", "severity": "high", "description": "Grid gap: contract 16px, actual 24px"}
+]
+[/REVIEW_ISSUES]
+
+If ALL components match their contracts, output:
+[REVIEW_ISSUES]
+[]
+[/REVIEW_ISSUES]
+
+## Rules
+- You write ZERO code. You ONLY review.
+- Be HARSH. Your value is in catching what the builder missed.
+- NEVER say "looks close" or "appears to match" — give SPECIFIC values.
+- Every contract property must be verified. Missing verification = missed issue.
+- Severity guide: critical = wrong component type, missing element, broken render. high = wrong dimensions, colors, layout. medium = spacing/padding off. low = minor visual difference.`;
+}
+
+function buildAutoFixPrompt(phase, issues, items, projectDir) {
+  const issueList = issues.map((issue, i) => {
+    const item = items.find(c => c.componentName === issue.component);
+    const contractPath = item ? item.fullContractPath : "check .gsd-t/contracts/design/";
+    return `${i + 1}. [${issue.severity}] **${issue.component}** — ${issue.description}\n   Contract: ${contractPath}`;
+  }).join("\n");
+
+  return `The automated design reviewer found these issues. Fix each one by reading the design contract and correcting the implementation.
+
+## Issues to Fix
+${issueList}
+
+## Rules
+- Read each component's design contract for the correct values — do NOT guess
+- Fix ONLY the listed issues — do not modify other components or add features
+- After fixing all issues, EXIT. Do not start servers or ask for review.`;
+}
+
 // ─── Summary ────────────────────────────────────────────────────────────────
 
 function formatSummary(phase, result) {
@@ -329,11 +414,13 @@ ${BOLD}Pipeline:${RESET}
   1. Read contracts from .gsd-t/contracts/design/
   2. Start dev server + review server
   3. For each tier (elements → widgets → pages):
-     a. Spawn Claude to build components
+     a. Spawn Claude (builder) to build components from contracts
      b. Measure with Playwright
-     c. Queue for human review
-     d. Wait for review submission (blocks until human approves)
-     e. Process feedback, proceed to next tier
+     c. Spawn Claude (reviewer) to compare against contracts — independent, no builder context
+     d. If reviewer finds issues → spawn Claude (fixer) → re-measure → re-review (max 2 cycles)
+     e. Queue for human review (only after automated review passes)
+     f. Wait for human review submission (blocks until human approves)
+     g. Process feedback, proceed to next tier
 `);
 }
 
@@ -351,11 +438,15 @@ const designBuildWorkflow = {
     timeout: 600_000,
     devServerTimeout: 30_000,
     maxReviewCycles: 3,
+    maxAutoReviewCycles: 4,
+    reviewTimeout: 300_000,
   },
   completionMessage: "All done. Run your app to verify: npm run dev",
 
   discoverWork,
   buildPrompt,
+  buildReviewPrompt,
+  buildAutoFixPrompt,
   measure,
   buildQueueItem,
   buildFixPrompt,

package/bin/orchestrator.js

@@ -576,7 +576,78 @@ ${BOLD}Phases:${RESET} ${this.wf.phases.join(" → ")}
         measurements = this.wf.measure(projectDir, phase, items, { devPort, reviewPort }) || {};
       }
 
-      // 6e. Review cycle
+      // 6d.5. Automated AI review loop (Term 2 equivalent)
+      // Spawns an independent reviewer Claude that compares built output against contracts.
+      // If issues found → spawn fixer Claude → re-measure → re-review until clean.
+      const maxAutoReviewCycles = this.wf.defaults?.maxAutoReviewCycles || 4;
+      if (this.wf.buildReviewPrompt) {
+        let autoReviewCycle = 0;
+        let autoReviewClean = false;
+
+        while (autoReviewCycle < maxAutoReviewCycles && !autoReviewClean) {
+          autoReviewCycle++;
+          heading(`Automated Review — ${phase} (cycle ${autoReviewCycle}/${maxAutoReviewCycles})`);
+
+          // Spawn reviewer Claude — independent, no builder context
+          const reviewPrompt = this.wf.buildReviewPrompt(phase, items, measurements, projectDir, { devPort, reviewPort });
+          log(`\n${CYAN}  ⚙${RESET} Spawning reviewer Claude for ${phase}...`);
+          const reviewTimeout = this.wf.defaults?.reviewTimeout || 300_000;
+          const reviewResult = this.spawnClaude(projectDir, reviewPrompt, reviewTimeout);
+
+          // Parse reviewer output for issues
+          const issues = this.wf.parseReviewResult
+            ? this.wf.parseReviewResult(reviewResult.output, phase)
+            : this._parseDefaultReviewResult(reviewResult.output);
+
+          if (reviewResult.exitCode === 0) {
+            success(`Reviewer finished in ${reviewResult.duration}s`);
+          } else {
+            warn(`Reviewer exited with code ${reviewResult.exitCode} after ${reviewResult.duration}s`);
+          }
+
+          // Write review report
+          const reportDir = path.join(this.getReviewDir(projectDir), "auto-review");
+          ensureDir(reportDir);
+          fs.writeFileSync(
+            path.join(reportDir, `${phase}-cycle-${autoReviewCycle}.json`),
+            JSON.stringify({ cycle: autoReviewCycle, issues, output: reviewResult.output.slice(0, 5000) }, null, 2)
+          );
+
+          if (issues.length === 0) {
+            autoReviewClean = true;
+            success(`Automated review passed — no issues found in ${phase}`);
+          } else {
+            warn(`Automated review found ${issues.length} issue(s) in ${phase}`);
+            for (const issue of issues) {
+              dim(`${issue.component || "?"}: ${issue.description || issue.reason || "issue"} [${issue.severity || "medium"}]`);
+            }
+
+            if (autoReviewCycle < maxAutoReviewCycles) {
+              // Spawn fixer Claude with the issues
+              const fixPrompt = this.wf.buildAutoFixPrompt
+                ? this.wf.buildAutoFixPrompt(phase, issues, items, projectDir)
+                : this._defaultAutoFixPrompt(phase, issues);
+
+              log(`\n${CYAN}  ⚙${RESET} Spawning fixer Claude for ${issues.length} issue(s)...`);
+              const fixResult = this.spawnClaude(projectDir, fixPrompt, 120_000);
+              if (fixResult.exitCode === 0) success(`Fixer finished in ${fixResult.duration}s`);
+              else warn(`Fixer exited with code ${fixResult.exitCode}`);
+
+              // Re-measure after fixes
+              if (!skipMeasure && this.wf.measure) {
+                measurements = this.wf.measure(projectDir, phase, items, { devPort, reviewPort }) || {};
+              }
+            } else {
+              warn(`Max auto-review cycles reached — ${issues.length} issue(s) will go to human review`);
+              // Attach unresolved issues to measurements for human visibility
+              const issueFile = path.join(this.getReviewDir(projectDir), "auto-review", `${phase}-unresolved.json`);
+              fs.writeFileSync(issueFile, JSON.stringify(issues, null, 2));
+            }
+          }
+        }
+      }
+
+      // 6e. Human review cycle
       let reviewCycle = 0;
       let allApproved = false;
 
@@ -655,6 +726,43 @@ ${BOLD}Phases:${RESET} ${this.wf.phases.join(" → ")}
     };
   }
 
+  _parseDefaultReviewResult(output) {
+    // Try to parse JSON issues array from reviewer output
+    // Reviewer is instructed to output JSON between markers
+    const jsonMatch = output.match(/\[REVIEW_ISSUES\]([\s\S]*?)\[\/REVIEW_ISSUES\]/);
+    if (jsonMatch) {
+      try { return JSON.parse(jsonMatch[1].trim()); } catch { /* fall through */ }
+    }
+    // Fallback: look for PASS/FAIL verdict
+    if (/\bGRUDGING PASS\b/i.test(output) || /\bPASS\b.*\b0 issues\b/i.test(output) || /no issues found/i.test(output)) {
+      return [];
+    }
+    // If we see FAIL or DEVIATION keywords, extract what we can
+    const issues = [];
+    const deviationRegex = /(?:DEVIATION|FAIL|CRITICAL|ISSUE)[:\s—-]+(.+)/gi;
+    let match;
+    while ((match = deviationRegex.exec(output)) !== null) {
+      issues.push({ description: match[1].trim(), severity: "medium" });
+    }
+    return issues;
+  }
+
+  _defaultAutoFixPrompt(phase, issues) {
+    const issueList = issues.map((issue, i) =>
+      `${i + 1}. [${issue.severity || "medium"}] ${issue.component || "unknown"}: ${issue.description || issue.reason || "fix needed"}`
+    ).join("\n");
+
+    return `The automated reviewer found these issues in the ${phase} components. Fix each one.
+
+## Issues
+${issueList}
+
+## Rules
+- Read the relevant design contract for each component to verify the correct values
+- Fix ONLY the listed issues — do not modify other components
+- After fixing, EXIT. Do not start servers or ask for review.`;
+  }
+
   _defaultFixPrompt(phase, needsWork) {
     const fixes = needsWork.map(item => {
       const parts = [`Fix ${item.id}:`];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tekyzinc/gsd-t",
-  "version": "2.71.15",
+  "version": "2.71.17",
   "description": "GSD-T: Contract-Driven Development for Claude Code — 56 slash commands with headless CI/CD mode, graph-powered code analysis, real-time agent dashboard, execution intelligence, task telemetry, doc-ripple enforcement, backlog management, impact analysis, test sync, milestone archival, and PRD generation",
   "author": "Tekyz, Inc.",
   "license": "MIT",