clavix 4.2.0 → 4.3.2

package/dist/templates/slash-commands/_canonical/deep.md

@@ -93,6 +93,7 @@ Deep mode provides **Clavix Intelligence™** with comprehensive analysis that g
    - **migration**: Version upgrades, porting code between frameworks
    - **security-review**: Security audits, vulnerability checks
    - **learning**: Conceptual understanding, tutorials, explanations
+   - **summarization**: Extracting requirements from conversations
 
 3. **Strategic Scope Detection** (before detailed analysis):
 
@@ -131,18 +132,12 @@ Deep mode provides **Clavix Intelligence™** with comprehensive analysis that g
 
    d. **Improvements Applied** (labeled with quality dimensions)
 
-   e. **Alternative Approaches**:
-      - 2-3 different ways to phrase the request
-      - Alternative structures (user story, job story, structured sections)
-      - When each approach is most appropriate
-      - Temperature/model recommendations
+   e. **Alternative Approaches** (generated by AlternativePhrasingGenerator pattern):
+      - 2-3 different ways to approach the request
+      - Each approach with title, description, and "best for" context
+      - Intent-specific alternatives (e.g., Functional Decomposition for code, Top-Down Design for planning)
 
-   f. **Alternative Structures**:
-      - **Step-by-step**: Break into sequential steps
-      - **Template-based**: Provide code/document template to fill
-      - **Example-driven**: Show concrete examples of desired output
-
-   g. **Validation Checklist**:
+   f. **Validation Checklist** (generated by ValidationChecklistCreator pattern):
       - Steps to verify accuracy
       - Requirements match checks
       - Edge case handling verification
@@ -150,7 +145,7 @@ Deep mode provides **Clavix Intelligence™** with comprehensive analysis that g
       - Output format validation
       - Performance considerations
 
-   h. **Edge Cases to Consider**:
+   g. **Edge Cases to Consider** (generated by EdgeCaseIdentifier pattern):
       - Intent-specific edge cases
       - Error conditions and recovery
       - Unexpected inputs or behavior
@@ -171,10 +166,9 @@ Deep mode provides **Clavix Intelligence™** with comprehensive analysis that g
 - **Intent Detection**: Automatic classification with confidence
 - **Quality Assessment**: All 6 dimensions with detailed analysis
 - **Advanced Optimization**: All applicable patterns
-- **Alternative Approaches**: Multiple phrasings and perspectives
-- **Alternative Structures**: Different organization approaches
-- **Validation Checklist**: Steps to verify completion
-- **Edge Case Analysis**: Potential issues and failure modes
+- **Alternative Approaches**: Multiple approaches (generated by AlternativePhrasingGenerator pattern)
+- **Validation Checklist**: Steps to verify completion (generated by ValidationChecklistCreator pattern)
+- **Edge Case Analysis**: Potential issues and failure modes (generated by EdgeCaseIdentifier pattern)
 - **Risk Assessment**: "What could go wrong" analysis
 
 **Do NOT include (these belong in `/clavix:prd`):**
@@ -290,66 +284,40 @@ Success Criteria:
 [Completeness] Added tech stack (React/TypeScript), API endpoint, accessibility standards, testing requirements
 [Actionability] Converted vague request into specific, measurable implementation requirements
 
-### Alternative Approaches:
+### Alternative Approaches
 
-1. **Functional Decomposition**: "Build a React login component that: (1) validates email/password inputs, (2) calls JWT auth API, (3) handles errors gracefully, (4) manages session persistence"
+**1. Functional Decomposition**
+   Break down into discrete functions with clear interfaces
    → Best for: Step-by-step implementation, clarity on sequence
 
-2. **User-Centric**: "As a user, I need to log into my account securely using email/password, with clear feedback if credentials are invalid"
-   → Best for: Emphasizing user experience and value
-
-3. **Example-Driven**: "Create a login page similar to [reference], with email/password fields, validation, and integration with our JWT API"
-   → Best for: When you have a reference implementation
-
-### Alternative Structures:
+**2. Test-Driven Approach**
+   Define expected behavior through tests first
+   → Best for: When requirements are clear and testable
 
-**Step-by-step approach:**
-1. Create form with email/password inputs and validation
-2. Implement API integration with JWT endpoint
-3. Add error handling and user feedback
-4. Implement "remember me" and "forgot password" features
-5. Add accessibility and responsive design
-6. Write tests and documentation
+**3. Example-Driven**
+   Provide concrete input/output examples
+   → Best for: When you have reference implementations
 
-**Template-based approach:**
-Provide a component template with:
-- Form structure with input fields
-- Validation logic placeholders
-- API call hooks
-- Error state management
-- Accessibility attributes
-
-**Example-driven approach:**
-Show concrete examples of:
-- Login form HTML structure
-- Validation error messages
-- Success/failure API responses
-- Loading and error states
-
-### Validation Checklist:
+### Validation Checklist
 
 Before considering this task complete, verify:
-☐ Email and password fields validate input correctly
-☐ Invalid credentials show appropriate, user-friendly error messages
-☐ Successful login redirects to correct page or updates auth state
-☐ "Remember me" persists session across browser sessions
-☐ "Forgot password" link navigates to password reset flow
-☐ Form is keyboard accessible (tab navigation, enter to submit)
-☐ Screen readers announce errors and state changes
-☐ Loading state prevents duplicate submissions
-☐ Component renders correctly on mobile and desktop
-☐ Unit tests cover success, failure, and edge cases (>80% coverage)
-
-### Edge Cases to Consider:
-
-• **Empty or invalid inputs**: How to handle blank email, malformed email, empty password?
-• **API failures**: What happens if auth API is down or times out?
-• **Slow network**: How to indicate loading state and prevent double-submission?
-• **Expired sessions**: How to handle JWT expiration during login attempt?
-• **Account locked**: What if user account is temporarily locked after failed attempts?
-• **Password reset in progress**: How to handle user who requested reset but tries to login?
-• **Browser autofill**: Does component work correctly with password managers?
-• **Concurrent logins**: What happens if user logs in on multiple devices?
+
+☐ Code compiles/runs without errors
+☐ All requirements from prompt are implemented
+☐ Edge cases are handled gracefully
+☐ UI renders correctly on different screen sizes
+☐ Keyboard navigation works correctly
+☐ Code follows project conventions/style guide
+☐ No console errors or warnings
+☐ Documentation updated if needed
+
+### Edge Cases to Consider
+
+• **Boundary conditions**: What happens at min/max values, empty collections, or single items?
+• **Empty or null inputs**: How should the system handle missing or undefined values?
+• **Invalid input types**: What happens if input is wrong type (string vs number)?
+• **Network failures**: How to handle timeouts, connection errors, and retries?
+• **Session expiration**: What happens when user session expires mid-operation?
 
 ### What Could Go Wrong:
 

package/dist/templates/slash-commands/_canonical/fast.md

@@ -91,6 +91,7 @@ Clavix provides **Clavix Intelligence™** that automatically detects intent and
    - **migration**: Version upgrades, porting code between frameworks
    - **security-review**: Security audits, vulnerability checks
    - **learning**: Conceptual understanding, tutorials, explanations
+   - **summarization**: Extracting requirements from conversations
 
 3. **Quality Assessment** - Evaluate across 6 dimensions:
 

package/dist/templates/slash-commands/_components/sections/pattern-visibility.md

@@ -75,6 +75,21 @@ Patterns: 7 applied (deep mode)
 | SuccessCriteriaEnforcer | 6 | Adds measurable success criteria |
 | DomainContextEnricher | 5 | Adds domain-specific best practices |
 
+**v4.3.2 PRD Mode Patterns (deep mode):**
+| Pattern | Priority | What It Does |
+|---------|----------|--------------|
+| RequirementPrioritizer | 7 | Separates must-have from nice-to-have requirements |
+| UserPersonaEnricher | 6 | Adds missing user context and personas |
+| SuccessMetricsEnforcer | 7 | Ensures measurable success criteria exist |
+| DependencyIdentifier | 5 | Identifies technical and external dependencies |
+
+**v4.3.2 Conversational Mode Patterns (deep mode):**
+| Pattern | Priority | What It Does |
+|---------|----------|--------------|
+| ConversationSummarizer | 8 | Extracts structured requirements from messages |
+| TopicCoherenceAnalyzer | 6 | Detects topic shifts and multi-topic conversations |
+| ImplicitRequirementExtractor | 7 | Surfaces requirements mentioned indirectly |
+
 ### Pattern Selection Logic
 
 Patterns are selected based on:
@@ -109,11 +124,20 @@ Deep mode only:
   AlternativePhrasingGenerator, EdgeCaseIdentifier, ValidationChecklistCreator,
   AssumptionExplicitizer, ScopeDefiner, PRDStructureEnforcer,
   ErrorToleranceEnhancer, PrerequisiteIdentifier
+
+v4.3.2 PRD mode (deep):
+  RequirementPrioritizer, UserPersonaEnricher, SuccessMetricsEnforcer,
+  DependencyIdentifier
+
+v4.3.2 Conversational mode (deep):
+  ConversationSummarizer, TopicCoherenceAnalyzer, ImplicitRequirementExtractor
 ```
 
 ### Pattern Count by Mode
 
 | Mode | Patterns Available | Typical Applied |
 |------|-------------------|-----------------|
-| Fast | 12 core patterns | 4-7 patterns |
-| Deep | 20 total patterns | 8-14 patterns |
+| Fast | 21 core patterns | 4-7 patterns |
+| Deep | 27 total patterns | 8-14 patterns |
+| PRD | 15 patterns | 10-15 patterns |
+| Conversational | 11 patterns | 6-11 patterns |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "clavix",
-  "version": "4.2.0",
+  "version": "4.3.2",
   "description": "Clavix Intelligence™ for AI coding. Automatically optimizes prompts with intent detection, quality assessment, and adaptive patterns—no framework to learn. Works with Claude Code, Cursor, Windsurf, and 19+ other AI coding tools.",
   "type": "module",
   "main": "dist/index.js",
@@ -17,7 +17,7 @@
     "prebuild": "npm run validate:consistency",
     "build": "tsc && npm run copy-templates",
     "build:prod": "npm run build && npm run remove-sourcemaps",
-    "copy-templates": "copyfiles -u 1 \"src/templates/**/*\" dist/",
+    "copy-templates": "rm -rf dist/templates && copyfiles -u 1 \"src/templates/**/*\" dist/",
     "remove-sourcemaps": "find dist -name '*.map' -type f -delete",
     "dev": "node --loader ts-node/esm src/index.ts",
     "test": "NODE_OPTIONS=\"--experimental-vm-modules --no-warnings\" jest",
@@ -54,7 +54,7 @@
     "requirements"
   ],
   "author": "ClavixDev",
-  "license": "MIT",
+  "license": "Apache-2.0",
   "bugs": {
     "url": "https://github.com/ClavixDev/Clavix/issues"
   },

package/dist/templates/instructions/README 2.md

@@ -1,311 +0,0 @@
-# Clavix Instructions Hierarchy
-
-This directory contains the complete instruction set for AI agents consuming Clavix workflows. Understanding this hierarchy is critical for maintaining consistent, high-quality agent behavior.
-
----
-
-## 📐 Documentation Architecture
-
-```
-Canonical Templates (SOURCE OF TRUTH)
-  src/templates/slash-commands/_canonical/
-  ├── fast.md, deep.md, prd.md
-  ├── start.md, summarize.md
-  ├── plan.md, implement.md, execute.md
-  └── archive.md, prompts.md
-    ↓ (copied during clavix init)
-Instruction Files (AUTO-GENERATED)
-  .clavix/instructions/
-  ├── workflows/         - Complete workflows (COPIED from canonical)
-  ├── core/             - Foundational concepts (static)
-  └── troubleshooting/  - Common issues (static)
-    ↓ (reference)
-Generic Connectors (THIN WRAPPERS)
-  src/templates/agents/
-  ├── agents.md          - Generic agents
-  ├── octo.md           - Octofriend-specific
-  ├── copilot-instructions.md - GitHub Copilot
-  └── warp.md           - Warp AI
-```
-
----
-
-## 🎯 Core Principles
-
-### 1. Single Source of Truth
-
-**Canonical templates** (`src/templates/slash-commands/_canonical/`) are the definitive reference:
-- Complete workflow descriptions
-- Official command behavior
-- Authoritative patterns and examples
-- NEVER modified for size/brevity - they define the standard
-
-**Rule:** When canonical and instruction files conflict, canonical wins.
-
-### 2. Agent-Optimized Instructions
-
-**Instruction files** (`src/templates/instructions/`) are derived from canonical templates but optimized for AI agent consumption:
-- Must match canonical workflows 100% in substance
-- Can reorganize for better agent comprehension
-- Add explicit checkpoints, self-correction checks, troubleshooting
-- Include "Common Mistakes" sections with wrong/right examples
-- Expand on ambiguous points from canonical
-
-**Rule:** Instruction files implement canonical, never contradict it.
-
-### 3. Thin Generic Connectors
-
-**Generic connector files** (`src/templates/agents/`) are minimal wrappers:
-- Reference instruction files, don't duplicate them
-- Platform-specific guidance ONLY (model switching, tool limitations, etc.)
-- Brief workflow overview + standard workflow (PRD → Plan → Implement → Archive)
-- Command quick reference table
-- Common mistakes specific to platform
-
-**Target sizes:**
-- agents.md: 4-7K (generic, no platform features)
-- octo.md: 7-10K (Octofriend has unique features)
-- copilot-instructions.md: 5-7K (GitHub Copilot integration)
-- warp.md: 5-7K (Warp AI-specific)
-
-**Rule:** If it's in an instruction file, don't duplicate it in a connector file.
-
----
-
-## 📂 Directory Structure
-
-### `/workflows/` - Step-by-Step Workflows
-
-Complete, executable workflows with explicit steps:
-
-| File | Purpose | Key Sections |
-|------|---------|--------------|
-| `start.md` | Conversational mode entry | Questions, complexity tracking, mode transitions |
-| `summarize.md` | Extract requirements from conversation | Pre-validation, extraction, file creation, optimization |
-| `fast.md` | Quick prompt optimization | Intent detection, quality assessment, smart triage |
-| `deep.md` | Comprehensive analysis | Strategic scope, alternatives, validation, edge cases, risks |
-| `prd.md` | PRD generation via Socratic questions | 5-question sequence, validation criteria, file-saving protocol |
-
-**Pattern:** Each workflow file includes:
-- CLAVIX PLANNING MODE block (clarifies planning vs implementation)
-- Complete workflow steps with checkpoints
-- Self-correction checks
-- Common mistakes (wrong/right examples)
-- Troubleshooting references
-- Integration with other workflows
-
-### `/core/` - Foundational Concepts
-
-Cross-workflow patterns and principles:
-
-| File | Purpose | Key Content |
-|------|---------|-------------|
-| `clavix-mode.md` | Planning vs implementation distinction | Mode table, standard workflow, command categorization |
-| `file-operations.md` | File creation patterns | Write tool usage, verification steps, error handling |
-| `verification.md` | Checkpoint patterns | Self-correction triggers, validation approaches |
-
-**Purpose:** Define concepts used across multiple workflows to avoid duplication.
-
-### `/troubleshooting/` - Common Issues
-
-Problem → Solution guides:
-
-| File | Purpose | Symptoms & Solutions |
-|------|---------|---------------------|
-| `jumped-to-implementation.md` | Agent implemented during planning | Detect, stop, apologize, return to planning |
-| `skipped-file-creation.md` | Files not created | Explicit Write tool steps, verification protocol |
-| `mode-confusion.md` | Unclear planning vs implementation | Ask user to clarify, explain mode boundaries |
-
-**Pattern:** Each troubleshooting file includes:
-- Symptoms (how to detect the problem)
-- Root cause (why it happened)
-- Solution (step-by-step fix)
-- Prevention (how to avoid in future)
-
----
-
-## 🔄 Maintenance Workflow
-
-### When Adding New Workflow
-
-1. **Create canonical template** in `src/templates/slash-commands/_canonical/`
-   - Complete workflow description
-   - All steps, examples, edge cases
-   - This is the official reference
-
-2. **NO NEED to create instruction file** - It's auto-copied during init
-   - During `clavix init`, canonical templates are automatically copied to `.clavix/instructions/workflows/`
-   - User projects get fresh copy on init/update
-   - **Single source of truth:** Only maintain canonical template
-
-3. **Update generic connectors** in `src/templates/agents/` (if needed)
-   - Add table reference to new workflow
-   - Update workflow detection keywords
-   - DO NOT duplicate workflow steps
-
-4. **Update this README** if new pattern/principle introduced
-
-### When Modifying Existing Workflow
-
-1. **Update canonical template** - This is source of truth
-2. **Users run `clavix update`** - Refreshes `.clavix/instructions/workflows/` from canonical
-3. **Test:** Verify `clavix update` propagates changes correctly
-4. **No manual duplication needed** - InstructionsGenerator copies from canonical automatically
-
-### When Reporting Verbosity Issues
-
-**Bloat checklist:**
-1. Is canonical template duplicated in instruction file? → Remove from instruction, reference canonical
-2. Is instruction file duplicated in connector file? → Remove from connector, reference instruction
-3. Is workflow description inline in connector? → Remove, add table reference to instruction file
-4. Are "Common Mistakes" duplicated across files? → Keep in instruction file only
-5. Is command reference table too detailed? → Condense to single-line purpose
-
-**Size targets:**
-- Canonical templates: 10-20K (complete reference, no size limit)
-- Instruction files: 10-18K (agent-optimized, comprehensive)
-- Generic connectors: 4-10K (thin wrappers)
-
----
-
-## 🧠 Design Philosophy
-
-### Why Three Layers?
-
-**Layer 1: Canonical Templates**
-- **Audience:** CLI implementation, human developers, official documentation
-- **Purpose:** Define authoritative behavior
-- **Constraint:** Complete and accurate, no brevity requirement
-
-**Layer 2: Instruction Files**
-- **Audience:** AI agents (all platforms)
-- **Purpose:** Executable guidance with self-correction
-- **Constraint:** Must match canonical, optimized for agent comprehension
-
-**Layer 3: Generic Connectors**
-- **Audience:** Platform-specific agents (Copilot, Octofriend, Warp, generic)
-- **Purpose:** Minimal platform-specific wrapper + references
-- **Constraint:** Keep thin, reference instruction files, platform-unique guidance only
-
-### Why Not Just One File?
-
-**Problems with single-file approach:**
-1. **Duplication:** Same workflow described 4+ times (canonical + 3 platforms)
-2. **Maintenance burden:** Update one workflow = edit 4+ files
-3. **Size bloat:** Each platform file becomes 15-20K
-4. **Inconsistency:** Descriptions drift apart over time
-5. **Confusion:** Agent sees multiple versions, unclear which is authoritative
-
-**Benefits of three-layer hierarchy:**
-1. **DRY principle:** Write workflow once (instruction file), reference everywhere
-2. **Single source of truth:** Canonical → Instruction → Connector flow
-3. **Platform focus:** Connector files focus on platform-specific value (model switching, tool limitations)
-4. **Maintainability:** Fix bug in one instruction file, all platforms benefit
-5. **Clarity:** Agent knows where to look - instruction file for workflow, connector for platform quirks
-
----
-
-## 📋 Quick Reference Tables
-
-### Standard Workflow
-
-All workflows follow this progression:
-
-```
-PRD Creation → Task Planning → Implementation → Archive
-```
-
-| Phase | Command | Output | Mode |
-|-------|---------|--------|------|
-| **Planning** | `clavix prd` or conversational | `full-prd.md` + `quick-prd.md` | PLANNING |
-| **Task Prep** | `clavix plan` | `tasks.md` | PLANNING (Pre-Implementation) |
-| **Implementation** | `clavix implement` | Executed code | IMPLEMENTATION |
-| **Completion** | `clavix archive` | Archived project | Management |
-
-### Mode Distinction
-
-| Command | Mode | Implement? |
-|---------|------|------------|
-| `/clavix:start` | Planning | ✗ NO |
-| `/clavix:summarize` | Planning | ✗ NO |
-| `/clavix:fast` | Planning | ✗ NO |
-| `/clavix:deep` | Planning | ✗ NO |
-| `/clavix:prd` | Planning | ✗ NO |
-| `/clavix:plan` | Planning (Pre-Implementation) | ✗ NO |
-| `/clavix:implement` | Implementation | ✓ YES |
-| `/clavix:execute` | Implementation | ✓ YES |
-| `/clavix:task-complete` | Implementation | ✓ YES |
-
-### File Size Expectations
-
-| File Type | Size Range | Line Range | Purpose |
-|-----------|-----------|------------|---------|
-| Canonical Template | 10-20K | 300-600 lines | Complete reference (no limit) |
-| Instruction File | 10-18K | 350-650 lines | Agent-executable workflows |
-| Generic Connector | 4-10K | 150-300 lines | Thin wrapper + platform-specific |
-
----
-
-## 🔧 Troubleshooting
-
-### "Agent jumped to implementation during planning"
-
-**Root cause:** Agent didn't recognize planning mode boundary
-
-**Fix:**
-1. Check instruction file has CLAVIX PLANNING MODE block at top
-2. Verify "DO NOT IMPLEMENT" warnings present and clear
-3. Add self-correction check: "Check 1: Am I Implementing?"
-4. Reference `troubleshooting/jumped-to-implementation.md`
-
-### "Agent skipped file creation"
-
-**Root cause:** File-saving protocol not explicit enough
-
-**Fix:**
-1. Add explicit step-by-step file creation section
-2. Include "Step N: Verify Files Were Created" with ls command
-3. Add common mistake: "Skipping file creation"
-4. Reference `troubleshooting/skipped-file-creation.md`
-
-### "Generic connector file too large (>10K)"
-
-**Root cause:** Duplicating instruction file content
-
-**Fix:**
-1. Identify duplicated workflow descriptions
-2. Replace with table reference to instruction file
-3. Keep only platform-specific guidance (model switching, tool limitations, etc.)
-4. Condense CLI reference table (one line per command)
-5. Remove detailed workflow explanations (link to instruction file instead)
-
-### "Instruction file doesn't match canonical"
-
-**Root cause:** Manual edit to instruction file without checking canonical
-
-**Fix:**
-1. Read canonical template: `src/templates/slash-commands/_canonical/<workflow>.md`
-2. Compare with instruction file: `src/templates/instructions/workflows/<workflow>.md`
-3. Ensure substance matches 100%
-4. Reorganization for agent clarity is OK, contradicting canonical is NOT
-
----
-
-## 📚 Additional Resources
-
-**Related documentation:**
-- `src/templates/slash-commands/_canonical/README.md` - Canonical template guidelines
-- `src/templates/agents/README.md` - Generic connector patterns (if exists)
-- `CONTRIBUTING.md` - General contribution guidelines
-- `ARCHITECTURE.md` - Overall Clavix architecture
-
-**Key files to read first:**
-- `core/clavix-mode.md` - Understand planning vs implementation
-- `workflows/fast.md` - See complete workflow pattern
-- `../agents/octo.md` - See thin connector example (post-v3.6.1)
-
----
-
-**Last updated:** v3.6.1 (November 2025)
-
-**Maintainers:** Ensure this README stays synchronized with actual instruction hierarchy.