claude-flow-novice 1.5.17 → 1.5.19

package/CHANGELOG.md

@@ -7,6 +7,28 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.5.19] - 2025-10-01
+
+### ✨ Added
+- **Auto-enable Rust Strict Mode**: Automatically enables `--rust-strict` flag for `.rs` files
+  - Detects `.unwrap()`, `.expect()`, `panic!()`, `todo!()`, `unimplemented!()`
+  - Provides line numbers, code snippets, and actionable suggestions
+  - No manual flag required - activates automatically for all Rust files
+  - Populates `rustQuality` JSON field with comprehensive analysis
+- **Bypass Non-Code Files**: Skip validation for config/documentation files
+  - Bypassed extensions: `.toml`, `.md`, `.txt`, `.json`, `.yaml`, `.yml`
+  - Returns immediate success status without running formatters/linters
+  - Improves performance for Cargo.toml, README.md, package.json edits
+  - Agent-friendly: no wasted processing on configuration files
+
+### 🔧 Improved
+- **Post-Edit Pipeline**: Smarter file type detection and processing
+  - Console shows `🦀 Auto-enabled Rust strict mode` for visibility
+  - Bypass message: `⏭️ BYPASSED: .md files don't require validation`
+  - Structured JSON includes `bypassed: true` and reason field
+
+## [1.5.18] - Previous Release
+
 ### ✨ Added
 - **`/fullstack` Slash Command**: Launch coordinated full-stack development team with consensus validation
   - Automatic team composition (researcher, coder, tester, reviewer, architect)

package/config/hooks/post-edit-pipeline.js

@@ -1505,6 +1505,36 @@ class UnifiedPostEditPipeline {
 
     async run(filePath, options = {}) {
         const language = this.detectLanguage(filePath);
+
+        // Bypass non-code files (config/documentation)
+        const bypassExtensions = ['.toml', '.md', '.txt', '.json', '.yaml', '.yml'];
+        const ext = path.extname(filePath).toLowerCase();
+        if (bypassExtensions.includes(ext)) {
+            console.log(`\n⏭️  BYPASSED: ${ext} files don't require validation`);
+            return {
+                file: filePath,
+                language,
+                timestamp: new Date().toISOString(),
+                editId: `edit-${Date.now()}-${Math.random().toString(36).substr(2, 9)}`,
+                agentContext: this.extractAgentContext(options),
+                status: 'BYPASSED',
+                bypassed: true,
+                reason: `${ext} files are configuration/documentation and don't require validation`,
+                summary: {
+                    success: true,
+                    warnings: [],
+                    errors: [],
+                    suggestions: []
+                }
+            };
+        }
+
+        // Auto-enable Rust strict mode for .rs files
+        if (language === 'rust' && !this.rustStrict) {
+            this.rustStrict = true;
+            console.log('🦀 Auto-enabled Rust strict mode for .rs file');
+        }
+
         const results = {
             file: filePath,
             language,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "claude-flow-novice",
-  "version": "1.5.17",
+  "version": "1.5.19",
   "description": "Standalone Claude Flow for beginners - AI agent orchestration made easy with enhanced TDD testing pipeline. Enhanced init command creates complete agent system, MCP configuration with 30 essential tools, and automated hooks with single-file testing, real-time coverage analysis, and advanced validation. Fully standalone with zero external dependencies, complete project setup in one command.",
   "mcpName": "io.github.ruvnet/claude-flow",
   "main": ".claude-flow-novice/dist/index.js",
@@ -212,6 +212,7 @@
     "src/swarm-fullstack/",
     "src/npx/",
     "src/language/",
+    "src/hooks/",
     "examples/",
     "wiki/",
     "CLAUDE.md",

package/src/cli/simple-commands/init/templates/CLAUDE.md

@@ -299,14 +299,46 @@ claude mcp add claude-flow-novice npx claude-flow-novice mcp start
 - **Maximum iterations**: 3 attempts before escalation using next steps guidance
 
 ### Step 4: Verify - Consensus Swarm (2-4 validators REQUIRED)
+
+**⚠️ CRITICAL: Sequential Spawning to Prevent Premature Validation**
+
+Validators MUST spawn in **separate message** AFTER implementation completes:
+
 ```javascript
-// MANDATORY: Spawn consensus validation swarm
-[Single Message]:
-  Task("Validator 1", "Comprehensive quality review", "reviewer")
-  Task("Validator 2", "Security and performance audit", "security-specialist")
-  Task("Validator 3", "Architecture validation", "system-architect")
-  Task("Validator 4", "Integration testing", "tester")
+// MESSAGE 1: Implementation swarm only
+[Implementation Message]:
+  mcp__claude-flow-novice__swarm_init({
+    topology: "mesh",
+    maxAgents: 3,
+    strategy: "balanced"
+  })
+
+  Task("Coder 1", "Implement feature X", "coder")
+  Task("Coder 2", "Implement feature Y", "backend-dev")
+  Task("Coder 3", "Implement feature Z", "rust-expert")
+
+// [WAIT FOR ALL IMPLEMENTATION AGENTS TO COMPLETE]
+
+// MESSAGE 2: Validation swarm after completion
+[Validation Message]:
+  mcp__claude-flow-novice__swarm_init({
+    topology: "mesh",
+    maxAgents: 4,
+    strategy: "balanced"
+  })
+
+  Task("Validator 1", "Review completed work at [specific files]", "reviewer")
+  Task("Validator 2", "Security audit of completed implementation", "security-specialist")
+  Task("Validator 3", "Architecture validation of completed system", "system-architect")
+  Task("Validator 4", "Integration testing of completed features", "tester")
 ```
+
+**WHY SEQUENTIAL SPAWNING:**
+- ✅ Prevents validators from reviewing incomplete work-in-progress
+- ✅ Ensures all implementation is finished before validation begins
+- ✅ Avoids wasted validation cycles on partial code
+- ✅ Produces accurate consensus scores on completed deliverables
+
 - **Byzantine consensus voting** across all validators
 - **Multi-dimensional checks**: quality, security, performance, tests, docs