feat: repo-agnostic refactor (BMad spec-test-build loop)

- NEW: repo-profiler.js — deterministic archetype detection (Infra, Frontend, Backend, etc.) - NEW: extract-dynamic.js — generic extractor replacing hardcoded Foxtrot patterns - NEW: eval-generator.js — dynamic ground-truth question generation from any repo graph - NEW: specs/bmad-agnostic-refactor-spec.md — full BMad spec with acceptance criteria - REFACTORED: prose.js — two-pass LLM synthesis with rich context (shared secrets, ports, service refs) - REFACTORED: sysdoc.js — wired repo-profiler + extract-dynamic, --legacy escape hatch - REFACTORED: wiggum-v2.sh — uses eval-generator before benchmarks - FIXED: graph.js — _edgeSet rebuilt on loadSnapshot() (edge dedup was broken) - FIXED: graph.js — recursive sortKeys() for deep equality in diffing - FIXED: prose.js — robust JSON array extraction from LLM output - FIXED: ratchet.js — syntax validation (node --check) before saving LLM mutations - FIXED: extract-dynamic.js — centralized state services regex, added console.warn for silent failures - TESTS: test-eval-generator, test-repo-profiler, test-synthesis-quality + mock fixtures Eval: 81.5% on Foxtrot (fully repo-agnostic, no hardcoded reference pages) BMad reviews: Architect B+, Dev Lead B-, TEA B-
2026-03-11 14:40:31 +00:00
parent 15fb1a753b
commit b8403be96c
26 changed files with 4653 additions and 1037 deletions
--- a/patch-sysdoc.js
+++ b/patch-sysdoc.js
@@ -1,56 +1,52 @@
 const fs = require('fs');
-let content = fs.readFileSync('/home/node/.openclaw/workspace/projects/dev-intel-v2/sysdoc.js', 'utf8');

-const oldStr = `const sysArchContent = \`# System Architecture
-\${archProse}
-## Summary Statistics
- **Subsystems:** \${subs.subsystems.length}
- **Helm Charts:** \${helmCharts.length}
- **Total Contracts:** \${contractsResult.contracts.length}
- **Cross-Cutting Concerns:** \${subs.crossCutting.join(', ') || 'none'}
+let content = fs.readFileSync('sysdoc.js', 'utf8');

-## Subsystems`;
+content = content.replace(
+  "const { extractDeep } = require('./extract-deep.js');",
+  "const { extractDeep } = require('./extract-deep.js');\nconst { profileRepo, ARCHETYPES } = require('./repo-profiler.js');\nconst { extractDynamic } = require('./extract-dynamic.js');"
+);

-const newStr = `const sysArchContent = \`# System Architecture
-\${archProse}
-## Summary Statistics
- **Subsystems:** \${subs.subsystems.length}
- **Helm Charts:** \${helmCharts.length}
- **Total Contracts:** \${contractsResult.contracts.length}
- **Cross-Cutting Concerns:** \${subs.crossCutting.join(', ') || 'none'}
+content = content.replace(
+  /const patterns = extractAllPatterns\(srcRoot\);\s*const deepData = extractDeep\(srcRoot\);/,
+  `let patterns = {
+    layers: [],
+    appsets: [],
+    regions: { aws: [], gcp: [], azure: [] },
+    cidrs: [],
+    naming: [],
+    techStack: { containerImages: [] },
+    syncWaves: []
+  };
+  let deepData = { addons: [], scriptParams: [], tfConfigs: [], helmValues: [], stateServices: [] };
+  let archetypeStr = ARCHETYPES ? ARCHETYPES.UNKNOWN : 'Unknown';

-## Platform Architecture Patterns
+  if (opts.legacyMode) {
+    patterns = extractAllPatterns(srcRoot);
+    deepData = extractDeep(srcRoot);
+    if (!archetypeStr || archetypeStr === 'Unknown') archetypeStr = 'Infrastructure';
+  } else {
+    const profile = profileRepo(srcRoot, graph);
+    archetypeStr = profile.archetype;
+    console.log(\`Detected Repo Archetype: \${archetypeStr} (confidence: \${profile.confidence})\`);
+    
+    const dynamicData = extractDynamic(graph, archetypeStr, srcRoot);
+    deepData = {
+      addons: [],
+      scriptParams: [],
+      tfConfigs: [],
+      helmValues: [],
+      stateServices: dynamicData.stateServices || [],
+      configs: dynamicData.configs || [],
+      deploymentPatterns: dynamicData.deploymentPatterns || [],
+      networkTopology: dynamicData.networkTopology || []
+    };
+  }`
+);

-### Layered Architecture
-The system is organized into the following logical layers (top to bottom):
-\${patterns.layers.map(l => \`- **\${l.layer}** (\${l.repos.join(', ')})\`).join('\\n')}
+content = content.replace(
+  /await proseMod\.synthesizeReferencePages\(agentKB, deepData, outDir, \{ confluenceCtx, model: process\.env\.LLM_MODEL \|\| 'claude-haiku-4\.5' \}\);/,
+  "await proseMod.synthesizeReferencePages(agentKB, deepData, outDir, archetypeStr, { confluenceCtx, model: process.env.LLM_MODEL || 'claude-haiku-4.5' });"
+);

-### Deployment Topology (Hub & Spoke)
-ArgoCD ApplicationSets define the following ownership model:
-**Hub (Infrastructure/Control Plane):**
-\${patterns.appsets.filter(a => a.location === 'hub').map(a => \`- \\\`\${a.name}\\\` manages \\\`\${a.repoName}\\\`\`).join('\\n')}
-**Spoke (Applications/Runtime):**
-\${patterns.appsets.filter(a => a.location === 'spoke').map(a => \`- \\\`\${a.name}\\\` manages \\\`\${a.repoName}\\\`\`).join('\\n')}
-
-### Cloud Regions Supported
- **AWS:** \${patterns.regions.aws.join(', ')}
- **GCP:** \${patterns.regions.gcp.join(', ')}
- **Azure:** \${patterns.regions.azure.join(', ')}
-
-### Network CIDR Allocations
-| CIDR Block | Context | File |
-|---|---|---|
-\${patterns.cidrs.slice(0, 15).map(c => \`| \\\`\${c.cidr}\\\` | \${c.refs[0].context} | \\\`\${c.refs[0].file}\\\` |\`).join('\\n')}
-
-### Naming Conventions
-The following resource naming patterns are enforced:
-\${patterns.naming.slice(0, 15).map(n => \`- \\\`\${n.pattern}\\\` (via \\\`\${n.file}\\\`)\`).join('\\n')}
-
-### Tech Stack & Dependencies
-**Core Images:**
-\${patterns.techStack.containerImages.slice(0, 20).map(i => \`- \\\`\${i}\\\`\`).join('\\n')}
-
-## Subsystems`;
-
-content = content.replace(oldStr, newStr);
-fs.writeFileSync('/home/node/.openclaw/workspace/projects/dev-intel-v2/sysdoc.js', content);
+fs.writeFileSync('sysdoc.js', content);