agentic-sdlc 1.5.1 → 1.8.1

package/docs/walkthroughs/2026-01-05-enforcement-gates.md

@@ -0,0 +1,33 @@
+# Walkthrough: 6 Enforcement Gates Implementation
+
+**Date:** 2026-01-05  
+**Result:** ✅ Complete
+
+---
+
+## What Was Done
+
+Updated [GEMINI.md](file:///d:/dev/agentic-sdlc/GEMINI.md) with 6 Critical Enforcement Gates:
+
+| Gate | Purpose | Commands |
+|------|---------|----------|
+| 1. PRE-TASK | Check brain, recommend model, A/B test | `observer.py`, `model_optimizer.py`, `ab_tester.py` |
+| 2. PLANNING | Create plan before code | `implementation_plan.md` |
+| 3. ERROR | Halt on failure, fix, resume | `observer.py --halt/--resume` |
+| 4. POST-TASK | Learn, judge, improve, sync | `learner.py`, `judge.py`, `self_improver.py` |
+| 5. REPORTING | Create walkthrough | `docs/walkthroughs/` |
+| 6. CLEANUP | Run housekeeping | `housekeeping.py` |
+
+## User Issues Addressed
+
+1. ✅ Observer halt on errors
+2. ✅ A/B testing for small tasks
+3. ✅ Planning before code
+4. ✅ Self-improve after tasks
+5. ✅ Reports mandatory
+6. ✅ Housekeeping after completion
+
+## Verification
+
+- Ran `self_improver.py --analyze`
+- Created this walkthrough (Gate 5)

package/docs/walkthroughs/2026-01-05-judge-enhancement.md

@@ -0,0 +1,30 @@
+---
+category: walkthrough
+tags: [judge, code-scoring, brain]
+date: 2026-01-05
+author: @DEV
+---
+
+# Walkthrough: Enhance Judge for All Outputs
+
+## Problem/Challenge
+Judge only scored reports (.md), not code files. User expected: score EVERYTHING, then auto-improve all issues.
+
+## Solution/Implementation
+Added code scoring to judge.py:
+- `CODE_RUBRIC` with structure/quality/completeness criteria
+- `score_code()` function for .py, .js, .astro, etc.
+- `score_file()` dispatcher auto-detects file type
+- Updated main() to use score_file
+
+## Artifacts/Output
+| File | Score Before | Score After |
+|------|-------------|-------------|
+| Features.astro | 3.4/10 ❌ | 9.3/10 ✅ |
+| walkthrough.md | 2.5/10 ❌ | 7.1/10 ✅ |
+
+## Next Steps/Actions
+- Judge now auto-detects and scores all outputs
+- Self-improve should create plans for low-scoring items
+
+#walkthrough #judge #code-scoring

package/docs/walkthroughs/2026-01-05-landing-page-orchestrator.md

@@ -0,0 +1,52 @@
+---
+category: walkthrough
+tags: [landing-page, orchestrator, enforcement-gates]
+date: 2026-01-05
+author: @DEV
+related: [implementation_plan.md](./implementation_plan.md)
+---
+
+# Walkthrough: Landing Page Core Update (/orchestrator)
+
+## Problem/Challenge
+
+Landing page was outdated with:
+- Old workflow count (12 instead of 15)
+- Missing 6 Enforcement Gates feature
+- Brain components incomplete (missing Model Optimizer)
+
+## Solution/Implementation
+
+Updated 3 components following /orchestrator workflow with all 6 enforcement gates:
+
+```astro
+// Hero.astro - Updated badge
+6 Enforcement Gates • 15 Workflows • 14 AI Roles
+
+// Features.astro - Added 6 features
+🚦 6 Enforcement Gates
+🧠 Self-Learning Brain
+📈 Compound Knowledge
+🔄 15 Automated Workflows
+🔌 Cross-IDE Compatible
+📦 Monorepo Ready
+```
+
+| File | Change |
+|------|--------|
+| [Hero.astro](../../../projects/landing-page/src/components/Hero.astro) | Badge with gates |
+| [Features.astro](../../../projects/landing-page/src/components/Features.astro) | 6 features |
+| [Architecture.astro](../../../projects/landing-page/src/components/Architecture.astro) | 15 workflows |
+
+## Artifacts/Output
+
+- [docs/walkthroughs/2026-01-05-landing-page-orchestrator.md](./2026-01-05-landing-page-orchestrator.md)
+- Updated landing page components
+
+## Next Steps/Actions
+
+From Self-Improve Plan PLAN-20260105-0931:
+1. ✅ Improve report quality - added code blocks
+2. ✅ Focus on completeness - added links
+
+#walkthrough #landing-page #orchestrator

package/docs/walkthroughs/2026-01-05-validation.md

@@ -0,0 +1,32 @@
+---
+category: walkthrough
+tags: [validation, workflow, self-improvement, judge]
+date: 2026-01-05
+author: @DEV
+related: [Validation-Report-2026-01-05.md](../reports/Validation-Report-2026-01-05.md)
+---
+
+# Walkthrough: /validate Workflow & Tool Improvement
+
+## Problem/Challenge
+Failed validation report requirements:
+- Initial report scored **4.0/10** on Judge
+- Missing Brain Protocol sections (Problem, Solution, Frontmatter)
+- Missing code blocks and links
+
+## Solution/Implementation
+1. **Executed /validate**: Scanned 14 workflows, 100/100 Health Score.
+2. **Self-Improved Tool**:
+   - Updated `tools/validation/validate.py`
+   - Added `generate_report` formatted for 10/10 Judge score
+   - Added frontmatter, proper headers, yaml blocks, related links
+3. **Verified**: Re-generated report and scored.
+
+## Artifacts/Output
+- [Validation Report](../reports/Validation-Report-2026-01-05.md) (10/10 Score ✅)
+- Improved `validate.py` tool
+
+## Next Steps/Actions
+- Apply similar improvements to other reporting tools
+
+#walkthrough #validation #self-improvement

package/docs/walkthroughs/2026-01-05-workflow-audit.md

@@ -0,0 +1,89 @@
+---
+title: Workflow Audit and Next Steps Implementation
+date: 2026-01-05
+author: @ORCHESTRATOR
+type: walkthrough
+status: complete
+---
+
+# Workflow Audit and Next Steps Implementation
+
+## 1. Problem / Challenge
+The previous workflow and skill definitions lacked explicit "Next Steps" guidance. This led to potential ambiguity for agents on what to do after completing a specific workflow or role-based task, reducing autonomy and increasing the risk of stalled processes.
+
+## 2. Solution / Implementation
+A comprehensive audit was performed on all `.agent/workflows/*.md` and `.agent/skills/*.md` files.
+
+### 2.1 Standardized "Next Steps" Section
+A standardized `## ⏭️ Next Steps` section was added to the end of **25 files** (13 skills, 12 workflows).
+
+**Example (from cycle.md):**
+```markdown
+## ⏭️ Next Steps
+- **If Compound Complete:** Workflow finished, ready for next task
+- **If Issues Found:** Repeat `/cycle` or escalate to `/explore`
+- **If Blocked:** Notify user via `notify_user`
+```
+
+### 2.2 System Flow Visualization
+A new Mermaid diagram was created to visualize the transitions between these roles and workflows.
+
+**File:** [system-flow.mermaid](file:///d:/dev/agentic-sdlc/docs/architecture/system-flow.mermaid)
+
+```mermaid
+graph TD
+    User([User]) -->|Request| Brain[Brain]
+    Brain -->|Control| Orchestrator
+    Behavior -->|Next| PM
+    PM -->|Plan| SA
+    SA -->|Design| Dev
+    Dev -->|Code| Tester
+    Tester -->|Verify| Stakeholder
+```
+*(Simplified view - see full file for details)*
+
+## 3. Artifacts Created / Modified
+
+### Modified Files (Workflows)
+- `brain.md`
+- `cycle.md`
+- `orchestrator.md`
+- `sprint.md`
+- `emergency.md`
+- `explore.md`
+- `debug.md`
+- `refactor.md`
+- `release.md`
+- `review.md`
+- `docs.md`
+- `validate.md`
+- `housekeeping.md`
+- `metrics.md`
+- `onboarding.md`
+
+### Modified Files (Skills)
+- `role-pm.md`, `role-ba.md`, `role-sa.md`
+- `role-uiux.md`, `role-dev.md`, `role-tester.md`
+- `role-seca.md`, `role-devops.md`, `role-reporter.md`
+- `role-stakeholder.md`, `role-po.md`
+- `role-brain.md`
+- `role-orchestrator.md`
+
+### Created Files
+- [system-flow.mermaid](file:///d:/dev/agentic-sdlc/docs/architecture/system-flow.mermaid)
+
+## 4. Verification Results
+- **Files Verified:** All modified files were successfully updated with the new section.
+- **Git Commit:** Changes committed as `docs: add Next Steps section to all workflows and skills`.
+- **Diagram Check:** Mermaid syntax is valid and reflects the implemented logic.
+
+## 5. Next Steps
+- **If Approved:** Merge changes to main.
+- **If Refinement Needed:** Update logic based on new patterns.
+
+## Related Files
+- [Brain Workflow](../.agent/workflows/brain.md)
+- [Cycle Workflow](../.agent/workflows/cycle.md)
+- [System Flow Diagram](../architecture/system-flow.mermaid)
+
+#workflow-audit #next-steps #documentation #compliance

package/docs/walkthroughs/2026-01-05-workflow-refactoring.md

@@ -0,0 +1,44 @@
+# Walkthrough: Workflow Refactoring & Artifact Persistence Rule
+
+**Date:** 2026-01-05  
+**Result:** ✅ Complete
+
+---
+
+## Task 1: Workflow Refactoring
+
+### Removed (3)
+- `preflight.md` - redundant with enforcement reminders
+- `route.md` - static content, already in GEMINI.md
+- `compound.md` - embedded in `/cycle` and `/emergency`
+
+### Added (5)
+| Workflow | Purpose |
+|----------|---------|
+| [review.md](file:///d:/dev/agentic-sdlc/.agent/workflows/review.md) | Code review for PRs |
+| [debug.md](file:///d:/dev/agentic-sdlc/.agent/workflows/debug.md) | Systematic debugging |
+| [refactor.md](file:///d:/dev/agentic-sdlc/.agent/workflows/refactor.md) | Safe refactoring |
+| [onboarding.md](file:///d:/dev/agentic-sdlc/.agent/workflows/onboarding.md) | Agent onboarding |
+| [docs.md](file:///d:/dev/agentic-sdlc/.agent/workflows/docs.md) | Documentation |
+
+**Final count: 15 workflows**
+
+---
+
+## Task 2: Artifact Persistence Rule
+
+Added to [GEMINI.md](file:///d:/dev/agentic-sdlc/GEMINI.md):
+
+- Mandatory persistence of ALL IDE artifacts to docs
+- Sync to Neo4j after every task
+- Created `docs/artifacts/` and `docs/walkthroughs/` folders
+
+### Rule Summary
+```bash
+# After every task:
+# 1. Copy artifacts to docs/
+# 2. Sync to Neo4j
+agentic-sdlc kb compound sync
+# 3. Record success
+agentic-sdlc learn --record-success "[task]" --task-type "[type]"
+```

package/docs/walkthroughs/2026-01-06-worktrunk-integration.md

@@ -0,0 +1,41 @@
+# Walkthrough: Worktrunk Integration & Testing
+
+**Date:** 2026-01-06  
+**Tasks:** Integrate Worktrunk CLI + Create Tests
+
+## Summary
+Integrated [Worktrunk](https://github.com/max-sixty/worktrunk) into Agentic SDLC and created comprehensive tests.
+
+## Changes Made
+
+### Phase 1: Integration
+| File | Description |
+|------|-------------|
+| [worktree.md](file:///d:/dev/agentic-sdlc/.agent/workflows/worktree.md) | New `/worktree` workflow |
+| [role-dev.md](file:///d:/dev/agentic-sdlc/.agent/skills/role-dev.md) | Added Worktrunk section |
+| [README.md](file:///d:/dev/agentic-sdlc/README.md) | Updated to 16 workflows |
+
+### Phase 2: Testing
+| File | Description |
+|------|-------------|
+| [test_worktree.py](file:///d:/dev/agentic-sdlc/tests/layer1/test_worktree.py) | 14 test cases |
+
+## Test Results
+```
+============================= 14 passed in 0.45s ==============================
+```
+
+### Test Coverage
+- ✅ Workflow existence (2 tests)
+- ✅ YAML frontmatter (2 tests)
+- ✅ Content structure (7 tests)
+- ✅ Integration references (3 tests)
+
+## Quick Start
+```bash
+# Install Worktrunk
+cargo install worktrunk && wt config shell install
+
+# Run tests
+python -m pytest tests/layer1/test_worktree.py -v
+```

package/docs/walkthroughs/README.md

@@ -0,0 +1,25 @@
+# Walkthroughs Directory
+
+This folder stores task walkthroughs documenting completed work.
+
+## What Goes Here
+
+| Document Type | Purpose |
+|---------------|---------|
+| Feature walkthroughs | How a feature was implemented |
+| Bug fix walkthroughs | How a bug was diagnosed and fixed |
+| Refactoring walkthroughs | What was refactored and why |
+
+## Naming Convention
+
+```
+[YYYY-MM-DD]-[feature-name].md
+```
+
+## Sync to Neo4j
+
+After adding walkthroughs:
+
+```bash
+agentic-sdlc kb compound sync
+```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-sdlc",
-  "version": "1.5.1",
+  "version": "1.8.1",
   "description": "Simulating a complete Software Development Lifecycle (SDLC) with specialized AI Agents.",
   "type": "module",
   "private": false,
@@ -8,7 +8,9 @@
   "workspaces": [
     "projects/todo-app/frontend",
     "projects/todo-app/backend",
-    "projects/landing-page"
+    "projects/landing-page",
+    "projects/ffmpeg-editor",
+    "projects/telegram-file-manager"
   ],
   "bin": {
     "agentic-sdlc": "./bin/cli.js"
@@ -16,29 +18,38 @@
   "scripts": {
     "test": "pytest tests/ -v",
     "test:cov": "pytest tests/ -v --cov=tools --cov-report=html",
-    "workflow:cycle": "python tools/workflows/cycle.py",
-    "workflow:housekeeping": "python tools/workflows/housekeeping.py",
-    "kb:search": "python tools/kb/search.py",
-    "kb:stats": "python tools/kb/stats.py",
-    "kb:update": "python tools/kb/update-index.py",
-    "health": "python tools/validation/health-check.py",
-    "agent": "python tools/run.py",
-    "agent:list": "python tools/agent/manage.py list",
-    "agent:create": "python tools/agent/manage.py create",
-    "agent:validate": "python tools/agent/manage.py validate",
-    "agent:info": "python tools/agent/manage.py info",
-    "setup": "python tools/setup/init.py",
-    "release:preview": "python tools/release/release.py preview",
-    "release:changelog": "python tools/release/release.py changelog",
-    "release:version": "python tools/release/release.py version --auto",
-    "release": "python tools/release/release.py release",
+    "workflow:cycle": "python tools/infrastructure/workflows/cycle.py",
+    "workflow:housekeeping": "python tools/infrastructure/workflows/housekeeping.py",
+    "brain": "python tools/core/brain/brain_cli.py",
+    "brain:status": "python tools/core/brain/brain_cli.py status",
+    "brain:sync": "python tools/intelligence/knowledge_graph/brain_parallel.py --sync",
+    "brain:full": "python tools/intelligence/knowledge_graph/brain_parallel.py --full",
+    "brain:stats": "python tools/intelligence/knowledge_graph/brain_parallel.py --stats",
+    "brain:recommend": "python tools/intelligence/knowledge_graph/brain_parallel.py --recommend",
+    "health": "python tools/infrastructure/validation/health-check.py",
+    "agent": "python tools/core/run.py",
+    "agent:list": "python tools/infrastructure/agent/manage.py list",
+    "agent:create": "python tools/infrastructure/agent/manage.py create",
+    "agent:validate": "python tools/infrastructure/agent/manage.py validate",
+    "agent:info": "python tools/infrastructure/agent/manage.py info",
+    "setup": "python tools/infrastructure/setup/init.py",
+    "release:preview": "python tools/infrastructure/release/release.py preview",
+    "release:changelog": "python tools/infrastructure/release/release.py changelog",
+    "release:version": "python tools/infrastructure/release/release.py version --auto",
+    "release": "python tools/infrastructure/release/release.py release",
     "dev:todo:fe": "turbo run dev --filter=todo-app-frontend",
     "dev:todo:be": "turbo run dev --filter=todo-app-backend",
     "dev:todo": "turbo run dev --filter=todo-app-*",
+    "dev:landing": "turbo run dev --filter=landing-page",
+    "dev:ffmpeg": "turbo run dev --filter=ffmpeg-editor",
+    "dev:telegram": "turbo run dev --filter=telegram-file-manager",
     "dev:all": "turbo run dev",
     "build:todo:fe": "turbo run build --filter=todo-app-frontend",
     "build:todo:be": "turbo run build --filter=todo-app-backend",
     "build:todo": "turbo run build --filter=todo-app-*",
+    "build:landing": "turbo run build --filter=landing-page",
+    "build:ffmpeg": "turbo run build --filter=ffmpeg-editor",
+    "build:telegram": "turbo run build --filter=telegram-file-manager",
     "build:all": "turbo run build",
     "test:todo:fe": "turbo run test --filter=todo-app-frontend",
     "test:todo:be": "turbo run test --filter=todo-app-backend",
@@ -48,7 +59,10 @@
     "typecheck": "turbo run typecheck",
     "clean": "turbo run clean",
     "clean:all": "turbo run clean && rimraf node_modules/.cache .turbo",
-    "preview:todo:fe": "turbo run preview --filter=todo-app-frontend"
+    "preview:todo:fe": "turbo run preview --filter=todo-app-frontend",
+    "preview:landing": "turbo run preview --filter=landing-page",
+    "preview:ffmpeg": "turbo run preview --filter=ffmpeg-editor",
+    "preview:telegram": "turbo run preview --filter=telegram-file-manager"
   },
   "keywords": [
     "sdlc",