chati-dev 4.2.2 → 4.3.1

package/framework/tasks/orchestrator-handoff.md

@@ -77,7 +77,7 @@ Modify `.chati/session.yaml`:
 
 ### 7. Determine Next Agent
 Based on pipeline position and mode:
-- **DISCOVER → PLAN**: Follow sequence (wu → brief → detail → architect → ux → phases → tasks → qa-planning)
+- **DISCOVER → PLAN**: Follow sequence (wu → brief → [Planning Team: detail + architect + ux + qa-planning] → phases → tasks)
 - **BUILD**: dev → qa-implementation
 - **DEPLOY**: devops
 - Handle special transitions (e.g., qa-planning → dev requires mode switch)

package/framework/tasks/orchestrator-resume.md

@@ -50,7 +50,7 @@ Find the most recent agent with `status: completed`:
 
 ### 4. Determine Next Agent
 Based on pipeline position and last completed agent:
-- **DISCOVER → PLAN pipeline**: greenfield-wu → brief → detail → architect → ux → phases → tasks → qa-planning
+- **DISCOVER → PLAN pipeline**: greenfield-wu → brief → [Planning Team: detail + architect + ux + qa-planning] → phases → tasks
 - **BUILD pipeline**: dev → qa-implementation
 - **DEPLOY pipeline**: devops
 - Handle special cases (skipped, needs_revalidation)

package/framework/tasks/orchestrator-route.md

@@ -59,7 +59,7 @@ Check if the requested action is valid for current position:
 ### 5. Select Target Agent
 Based on intent and position, identify the appropriate agent:
 - **DISCOVER agents**: greenfield-wu, brownfield-wu, brief, detail
-- **PLAN agents**: architect, ux, phases, tasks, qa-planning
+- **PLAN agents**: architect, ux, phases, tasks (qa-planning runs inside the Planning Team after detail+architect+ux complete, not as a standalone sequential agent)
 - **BUILD agents**: dev, qa-implementation
 - **DEPLOY agents**: devops
 - **Orchestrator actions**: status, health, deviation

package/framework/tasks/orchestrator-status.md

@@ -46,7 +46,7 @@ For each agent in the pipeline, gather:
 
 ### 3. Calculate Pipeline Progress
 Determine overall completion for each mode:
-- **DISCOVER + PLAN**: 9 agents (greenfield-wu OR brownfield-wu, brief, detail, architect, ux, phases, tasks, qa-planning)
+- **DISCOVER + PLAN**: 8 agents (greenfield-wu OR brownfield-wu, brief, detail, architect, ux, phases, tasks) — qa-planning runs inside the Planning Team alongside detail+architect+ux, not as a separate sequential agent
 - **BUILD**: 2 agents (dev, qa-implementation)
 - **DEPLOY**: 1 agent (devops)
 - Calculate percentage: completed / total
@@ -166,7 +166,7 @@ status_report:
 
   pipeline_progress:
     planning:
-      total_agents: 8  # brownfield-wu counted, greenfield-wu skipped
+      total_agents: 7  # brownfield-wu counted, greenfield-wu skipped; qa-planning is inside Planning Team, not a standalone sequential agent
       completed: 3
       percentage: 37.5
       agents:
@@ -244,7 +244,7 @@ status_report:
     ╚════════════════════════════════════════════════════════════╝
 
     DISCOVER / PLAN Pipeline (37.5%)
-    ✓ brownfield-wu  ✓ brief  ✓ detail  ◐ architect  ○ ux  ○ phases  ○ tasks  ○ qa-planning
+    ✓ brownfield-wu  ✓ brief  ✓ detail  ◐ architect  ○ ux  [○ qa-planning — runs inside Planning Team]  ○ phases  ○ tasks
 
     BUILD Pipeline (0%)
     ○ dev  ○ qa-implementation

package/framework/tasks/qa-planning-gate-define.md

@@ -42,7 +42,7 @@ Define quality gates and enforcement thresholds for each stage of the chati.dev
    - **Bypass**: Not allowed (ensures baseline quality)
 
 3. **Define Planning Phase Gates**
-   - **Agent Completion**: All 8 planning agents must complete (greenfield-wu/brownfield-wu → brief → detail → architect → ux → phases → tasks → qa-planning)
+   - **Agent Completion**: All DISCOVER + PLAN agents must complete: WU → brief → [Planning Team: detail + architect + ux + qa-planning] → phases → tasks
    - **Specification Completeness**: 100% of required sections filled
    - **QA Planning Score**: >= 95% for autonomous transition to build phase
    - **Manual Override**: Available if score 90-94% with justification

package/framework/templates/brandbook-html-tmpl.md

@@ -11,7 +11,7 @@ sections must exist and what each must contain.
 - **CSS**: All styles in a single `<style>` tag (no external stylesheets)
 - **Fonts**: Google Fonts via `<link>` tags (only external dependency allowed)
 - **JavaScript**: Minimal (only for theme toggle and smooth scroll)
-- **Output path**: `chati.dev/artifacts/4-UX/brandbook.html`
+- **Output path**: `artifacts/4-UX/brandbook.html`
 
 ## Mandatory Sections (14)
 
@@ -103,5 +103,5 @@ sections must exist and what each must contain.
 
 ## Reference
 
-See `/Users/ogabrielalonso/code/focus-ai/ping/docs/brand/brandbook.html` for a production
+See `<your-project>/docs/brand/brandbook.html` for a production
 example with 14 sections, sticky nav, dark mode toggle, and complete token rendering.

package/framework/templates/brandbook-tmpl.yaml

@@ -10,7 +10,7 @@ template:
     typography rationale, color philosophy, spacing rhythm, and iconography
     style. Must be completed BEFORE design tokens.
 
-output_path: chati.dev/artifacts/4-UX/brandbook.md
+output_path: artifacts/4-UX/brandbook.md
 
 sections:
   - brand_voice

package/framework/templates/component-spec-tmpl.yaml

@@ -9,7 +9,7 @@ template:
     UI component specification document. Defines variants, states,
     anatomy, props, accessibility, and responsive behavior.
 
-output_path: chati.dev/artifacts/4-UX/components/
+output_path: artifacts/4-UX/components/
 
 fields:
   - name: id

package/framework/templates/design-token-tmpl.yaml

@@ -9,7 +9,7 @@ template:
     Structured design token system with 4 layers: primitive, semantic,
     component, and utility. Derived from brandbook decisions.
 
-output_path: chati.dev/artifacts/4-UX/design-tokens.md
+output_path: artifacts/4-UX/design-tokens.md
 
 layers:
   - primitive

package/framework/templates/icon-system-tmpl.yaml

@@ -9,7 +9,7 @@ template:
     Icon library selection, sizing scale, usage guidelines, and inventory.
     Aligned with brandbook iconography style.
 
-output_path: chati.dev/artifacts/4-UX/icon-system.md
+output_path: artifacts/4-UX/icon-system.md
 
 sections:
   library_selection:

package/framework/templates/team-planning-tasks.yaml

@@ -60,14 +60,15 @@ tasks:
       - brandbook.html
     threshold: 90
 
-  - id: TT-PLN-004
-    title: "Cross-validate alignment: PRD entities = DB tables = UI components"
-    assigned_to: null
+  - id: TT-PLN-005
+    title: "QA-Planning: Validate traceability, criteria quality, cross-artifact consistency"
+    assigned_to: qa-planning
     status: pending
     score: null
     blocker: null
     depends_on: [TT-PLN-001, TT-PLN-002, TT-PLN-003]
     cross_review: null
-    artifacts_produced: []
+    artifacts_produced:
+      - qa-planning-report.md
     threshold: 95
-    notes: "Assigned by Team Lead after individual tasks complete. All 3 members participate."
+    notes: "Activates after Detail, Architect, UX complete. Reviews PRD + Architecture + UX for traceability and consistency. Sends qa_review_finding via mailbox if ERRORs found. Team dissolves only when QA-Planning approves (score >= 95%)."

package/framework/workflows/brownfield-discovery.yaml

@@ -67,9 +67,9 @@ phases:
     sequence:
       - agent: brownfield-wu
         action: compile-report
-        creates: [chati.dev/artifacts/0-WU/wu-full-report.md]
+        creates: [artifacts/0-WU/wu-full-report.md]
         notes: "Consolidate all findings into comprehensive report"
 
 output:
-  primary: chati.dev/artifacts/0-WU/wu-full-report.md
+  primary: artifacts/0-WU/wu-full-report.md
   duration: "1-4 hours depending on codebase size"

package/framework/workflows/brownfield-fullstack.yaml

@@ -19,7 +19,7 @@ phases:
     sequence:
       - agent: brownfield-wu
         action: full-discovery
-        creates: [chati.dev/artifacts/0-WU/wu-full-report.md]
+        creates: [artifacts/0-WU/wu-full-report.md]
         notes: >
           Both axes (technical + operational). ALWAYS runs Deep Discovery
           with 3 scout calls: Architect, UX, QA in scout mode.
@@ -30,7 +30,7 @@ phases:
     sequence:
       - agent: brief
         action: problem-extraction
-        creates: [chati.dev/artifacts/1-Brief/brief-report.md]
+        creates: [artifacts/1-Brief/brief-report.md]
         notes: "Informed by existing codebase context from WU"
 
   - phase: 2
@@ -39,7 +39,7 @@ phases:
     sequence:
       - agent: architect
         action: assess-architecture
-        creates: [chati.dev/artifacts/3-Architecture/architecture.md]
+        creates: [artifacts/3-Architecture/architecture.md]
         template: fullstack-architecture-tmpl.yaml
         notes: >
           Architect comes BEFORE Detail in brownfield.
@@ -51,12 +51,12 @@ phases:
     sequence:
       - agent: detail
         action: create-prd
-        creates: [chati.dev/artifacts/2-PRD/prd.md]
+        creates: [artifacts/2-PRD/prd.md]
         template: brownfield-prd-tmpl.yaml
         notes: "PRD informed by architectural constraints"
       - agent: ux
         action: define-experience
-        creates: [chati.dev/artifacts/4-UX/ux-specification.md]
+        creates: [artifacts/4-UX/ux-specification.md]
         notes: "Includes Design System audit of existing code"
 
   - phase: 4
@@ -65,20 +65,24 @@ phases:
     sequence:
       - agent: phases
         action: create-roadmap
-        creates: [chati.dev/artifacts/5-Phases/phases.md]
+        creates: [artifacts/5-Phases/phases.md]
       - agent: tasks
         action: create-tasks
-        creates: [chati.dev/artifacts/6-Tasks/tasks.md]
+        creates: [artifacts/6-Tasks/tasks.md]
         template: task-tmpl.yaml
 
   - phase: 5
-    name: Planning Quality Gate
+    name: Planning Quality Gate (Planning Team)
     category: PLAN
     sequence:
       - agent: qa-planning
         action: validate-traceability
-        creates: [chati.dev/artifacts/7-QA-Planning/qa-planning-report.md]
+        creates: [artifacts/7-QA-Planning/qa-planning-report.md]
         template: qa-gate-tmpl.yaml
+        notes: >
+          Runs inside Planning Team (Article XXI), not as a standalone step.
+          Activates after Detail, Architect, and UX complete their tasks.
+          Score synced to session.yaml by orchestrator on team dissolution.
 
   - phase: 6
     name: Implementation
@@ -88,7 +92,7 @@ phases:
         action: implement-tasks
       - agent: qa-implementation
         action: validate-code
-        creates: [chati.dev/artifacts/9-QA-Implementation/qa-implementation-report.md]
+        creates: [artifacts/9-QA-Implementation/qa-implementation-report.md]
 
   - phase: 7
     name: Deployment
@@ -96,7 +100,7 @@ phases:
     sequence:
       - agent: devops
         action: deploy
-        creates: [chati.dev/artifacts/10-Deploy/deploy-report.md]
+        creates: [artifacts/10-Deploy/deploy-report.md]
 
 transitions:
   discover_to_plan:

package/framework/workflows/brownfield-service.yaml

@@ -20,7 +20,7 @@ phases:
     sequence:
       - agent: brownfield-wu
         action: full-discovery
-        creates: [chati.dev/artifacts/0-WU/wu-full-report.md]
+        creates: [artifacts/0-WU/wu-full-report.md]
 
   - phase: 1
     name: Problem Definition
@@ -28,7 +28,7 @@ phases:
     sequence:
       - agent: brief
         action: problem-extraction
-        creates: [chati.dev/artifacts/1-Brief/brief-report.md]
+        creates: [artifacts/1-Brief/brief-report.md]
 
   - phase: 2
     name: Architecture & Specification
@@ -36,11 +36,11 @@ phases:
     sequence:
       - agent: architect
         action: assess-architecture
-        creates: [chati.dev/artifacts/3-Architecture/architecture.md]
+        creates: [artifacts/3-Architecture/architecture.md]
         notes: "Focus on API design, data model, service patterns"
       - agent: detail
         action: create-prd
-        creates: [chati.dev/artifacts/2-PRD/prd.md]
+        creates: [artifacts/2-PRD/prd.md]
         template: brownfield-prd-tmpl.yaml
 
   - phase: 3
@@ -49,18 +49,22 @@ phases:
     sequence:
       - agent: phases
         action: create-roadmap
-        creates: [chati.dev/artifacts/5-Phases/phases.md]
+        creates: [artifacts/5-Phases/phases.md]
       - agent: tasks
         action: create-tasks
-        creates: [chati.dev/artifacts/6-Tasks/tasks.md]
+        creates: [artifacts/6-Tasks/tasks.md]
 
   - phase: 4
-    name: Planning Quality Gate
+    name: Planning Quality Gate (Planning Team)
     category: PLAN
     sequence:
       - agent: qa-planning
         action: validate-traceability
-        creates: [chati.dev/artifacts/7-QA-Planning/qa-planning-report.md]
+        creates: [artifacts/7-QA-Planning/qa-planning-report.md]
+        notes: >
+          Runs inside Planning Team (Article XXI), not as a standalone step.
+          Activates after Detail and Architect complete their tasks.
+          Score synced to session.yaml by orchestrator on team dissolution.
 
   - phase: 5
     name: Implementation
@@ -70,7 +74,7 @@ phases:
         action: implement-tasks
       - agent: qa-implementation
         action: validate-code
-        creates: [chati.dev/artifacts/9-QA-Implementation/qa-implementation-report.md]
+        creates: [artifacts/9-QA-Implementation/qa-implementation-report.md]
 
   - phase: 6
     name: Deployment
@@ -78,7 +82,7 @@ phases:
     sequence:
       - agent: devops
         action: deploy
-        creates: [chati.dev/artifacts/10-Deploy/deploy-report.md]
+        creates: [artifacts/10-Deploy/deploy-report.md]
 
 transitions:
   discover_to_plan:

package/framework/workflows/brownfield-ui.yaml

@@ -20,7 +20,7 @@ phases:
     sequence:
       - agent: brownfield-wu
         action: full-discovery
-        creates: [chati.dev/artifacts/0-WU/wu-full-report.md]
+        creates: [artifacts/0-WU/wu-full-report.md]
         notes: "UX scout call gets extra attention for component audit"
 
   - phase: 1
@@ -29,7 +29,7 @@ phases:
     sequence:
       - agent: brief
         action: problem-extraction
-        creates: [chati.dev/artifacts/1-Brief/brief-report.md]
+        creates: [artifacts/1-Brief/brief-report.md]
 
   - phase: 2
     name: Architecture & Experience
@@ -37,15 +37,15 @@ phases:
     sequence:
       - agent: architect
         action: assess-architecture
-        creates: [chati.dev/artifacts/3-Architecture/architecture.md]
+        creates: [artifacts/3-Architecture/architecture.md]
         notes: "Focus on frontend architecture, state management, component patterns"
       - agent: detail
         action: create-prd
-        creates: [chati.dev/artifacts/2-PRD/prd.md]
+        creates: [artifacts/2-PRD/prd.md]
         template: brownfield-prd-tmpl.yaml
       - agent: ux
         action: define-experience
-        creates: [chati.dev/artifacts/4-UX/ux-specification.md]
+        creates: [artifacts/4-UX/ux-specification.md]
         notes: "Full Design System audit + new token definitions"
 
   - phase: 3
@@ -54,18 +54,22 @@ phases:
     sequence:
       - agent: phases
         action: create-roadmap
-        creates: [chati.dev/artifacts/5-Phases/phases.md]
+        creates: [artifacts/5-Phases/phases.md]
       - agent: tasks
         action: create-tasks
-        creates: [chati.dev/artifacts/6-Tasks/tasks.md]
+        creates: [artifacts/6-Tasks/tasks.md]
 
   - phase: 4
-    name: Planning Quality Gate
+    name: Planning Quality Gate (Planning Team)
     category: PLAN
     sequence:
       - agent: qa-planning
         action: validate-traceability
-        creates: [chati.dev/artifacts/7-QA-Planning/qa-planning-report.md]
+        creates: [artifacts/7-QA-Planning/qa-planning-report.md]
+        notes: >
+          Runs inside Planning Team (Article XXI), not as a standalone step.
+          Activates after Architect, Detail, and UX complete their tasks.
+          Score synced to session.yaml by orchestrator on team dissolution.
 
   - phase: 5
     name: Implementation
@@ -76,7 +80,7 @@ phases:
         notes: "Design System token enforcement is critical for UI work"
       - agent: qa-implementation
         action: validate-code
-        creates: [chati.dev/artifacts/9-QA-Implementation/qa-implementation-report.md]
+        creates: [artifacts/9-QA-Implementation/qa-implementation-report.md]
 
   - phase: 6
     name: Deployment
@@ -84,7 +88,7 @@ phases:
     sequence:
       - agent: devops
         action: deploy
-        creates: [chati.dev/artifacts/10-Deploy/deploy-report.md]
+        creates: [artifacts/10-Deploy/deploy-report.md]
 
 transitions:
   discover_to_plan:

package/framework/workflows/greenfield-fullstack.yaml

@@ -20,7 +20,7 @@ phases:
     sequence:
       - agent: greenfield-wu
         action: operational-discovery
-        creates: [chati.dev/artifacts/0-WU/wu-operational-report.md]
+        creates: [artifacts/0-WU/wu-operational-report.md]
         notes: "Operational context only (no codebase to analyze)"
 
   - phase: 1
@@ -29,7 +29,7 @@ phases:
     sequence:
       - agent: brief
         action: problem-extraction
-        creates: [chati.dev/artifacts/1-Brief/brief-report.md]
+        creates: [artifacts/1-Brief/brief-report.md]
         notes: "5-phase extraction process"
 
   - phase: 2
@@ -38,7 +38,7 @@ phases:
     sequence:
       - agent: detail
         action: create-prd
-        creates: [chati.dev/artifacts/2-PRD/prd.md]
+        creates: [artifacts/2-PRD/prd.md]
         template: prd-tmpl.yaml
         notes: "Detail comes BEFORE Architect in greenfield"
 
@@ -48,16 +48,16 @@ phases:
     sequence:
       - agent: architect
         action: design-architecture
-        creates: [chati.dev/artifacts/3-Architecture/architecture.md]
+        creates: [artifacts/3-Architecture/architecture.md]
         template: fullstack-architecture-tmpl.yaml
         notes: "Tech stack selection, data model, deployment strategy"
       - agent: architect
         action: dep-audit
-        creates: [chati.dev/artifacts/3-Architecture/dep-audit.yaml]
+        creates: [artifacts/3-Architecture/dep-audit.yaml]
         notes: "Verify dependency versions, vulnerabilities, and compatibility before implementation"
       - agent: ux
         action: define-experience
-        creates: [chati.dev/artifacts/4-UX/ux-specification.md]
+        creates: [artifacts/4-UX/ux-specification.md]
         notes: "UX follows Architect (needs to know the stack)"
 
   - phase: 4
@@ -66,23 +66,26 @@ phases:
     sequence:
       - agent: phases
         action: create-roadmap
-        creates: [chati.dev/artifacts/5-Phases/phases.md]
+        creates: [artifacts/5-Phases/phases.md]
         notes: "MVP-first phase breakdown"
       - agent: tasks
         action: create-tasks
-        creates: [chati.dev/artifacts/6-Tasks/tasks.md]
+        creates: [artifacts/6-Tasks/tasks.md]
         template: task-tmpl.yaml
         notes: "Atomic tasks with Given-When-Then criteria"
 
   - phase: 5
-    name: Planning Quality Gate
+    name: Planning Quality Gate (Planning Team)
     category: PLAN
     sequence:
       - agent: qa-planning
         action: validate-traceability
-        creates: [chati.dev/artifacts/7-QA-Planning/qa-planning-report.md]
+        creates: [artifacts/7-QA-Planning/qa-planning-report.md]
         template: qa-gate-tmpl.yaml
-        notes: "Must score >= 95% to proceed to BUILD"
+        notes: >
+          Runs inside Planning Team (Article XXI), not as a standalone step.
+          Activates after Detail, Architect, and UX complete their tasks.
+          Must score >= 95% to proceed to BUILD. Score synced to session.yaml by orchestrator on team dissolution.
 
   - phase: 6
     name: Implementation
@@ -93,7 +96,7 @@ phases:
         notes: "Interactive or autonomous (Ralph Wiggum) mode"
       - agent: qa-implementation
         action: validate-code
-        creates: [chati.dev/artifacts/9-QA-Implementation/qa-implementation-report.md]
+        creates: [artifacts/9-QA-Implementation/qa-implementation-report.md]
         template: qa-gate-tmpl.yaml
         notes: "Tests + SAST + code review. Must pass to deploy"
 
@@ -103,7 +106,7 @@ phases:
     sequence:
       - agent: devops
         action: deploy
-        creates: [chati.dev/artifacts/10-Deploy/deploy-report.md]
+        creates: [artifacts/10-Deploy/deploy-report.md]
         notes: "Git operations, deployment, documentation"
 
 transitions:

package/framework/workflows/quick-flow.yaml

@@ -45,7 +45,7 @@ phases:
     sequence:
       - agent: brief
         action: quick-extraction
-        creates: [chati.dev/artifacts/1-Brief/quick-brief.md]
+        creates: [artifacts/1-Brief/quick-brief.md]
         notes: >
           Condensed extraction: single-pass, no 5-phase process.
           Capture: what, why, constraints, acceptance criteria.
@@ -72,7 +72,7 @@ phases:
     sequence:
       - agent: qa-implementation
         action: validate-code
-        creates: [chati.dev/artifacts/9-QA-Implementation/qa-implementation-report.md]
+        creates: [artifacts/9-QA-Implementation/qa-implementation-report.md]
         notes: >
           Full QA-Implementation validation still applies (no shortcuts on quality).
           Adversarial review still mandatory.
@@ -87,7 +87,7 @@ phases:
     sequence:
       - agent: devops
         action: deploy
-        creates: [chati.dev/artifacts/10-Deploy/deploy-report.md]
+        creates: [artifacts/10-Deploy/deploy-report.md]
         notes: "Standard deployment process"
 
 transitions:

package/framework/workflows/standard-flow.yaml

@@ -40,7 +40,7 @@ agents:
     - detail
     - architect
     - tasks
-    - qa-planning
+    - qa-planning # runs inside Planning Team; score synced via team dissolution
     - dev
     - qa-implementation
     - devops
@@ -57,7 +57,7 @@ phases:
     sequence:
       - agent: brief
         action: extract-requirements
-        creates: [chati.dev/artifacts/1-Brief/brief.md]
+        creates: [artifacts/1-Brief/brief.md]
         notes: >
           Full brief extraction (5 phases). Since no WU precedes it,
           Brief must also capture codebase context from user input.
@@ -71,27 +71,30 @@ phases:
     sequence:
       - agent: detail
         action: expand-requirements
-        creates: [chati.dev/artifacts/2-Detail/prd.md]
+        creates: [artifacts/2-Detail/prd.md]
         notes: "Full PRD from brief output"
         parallel_with: [architect]
 
       - agent: architect
         action: design-architecture
-        creates: [chati.dev/artifacts/3-Architecture/architecture.md]
+        creates: [artifacts/3-Architecture/architecture.md]
         notes: "Architecture decisions, no UX constraints needed"
         parallel_with: [detail]
 
       - agent: tasks
         action: create-tasks
-        creates: [chati.dev/artifacts/5-Tasks/tasks.md]
+        creates: [artifacts/5-Tasks/tasks.md]
         notes: >
           Tasks agent works directly from PRD + Architecture.
           No phases agent — tasks agent determines task breakdown directly.
 
       - agent: qa-planning
         action: validate-plan
-        creates: [chati.dev/artifacts/6-QA-Planning/qa-planning-report.md]
-        notes: "Full QA-Planning validation. Score >= 95% required to advance."
+        creates: [artifacts/6-QA-Planning/qa-planning-report.md]
+        notes: >
+          Runs inside Planning Team (Article XXI), not as a standalone step.
+          Activates after Detail, Architect complete. Score >= 95% required to advance.
+          Score synced to session.yaml by orchestrator on team dissolution.
         config:
           minimum_score: 95
 
@@ -105,7 +108,7 @@ phases:
 
       - agent: qa-implementation
         action: validate-code
-        creates: [chati.dev/artifacts/9-QA-Implementation/qa-implementation-report.md]
+        creates: [artifacts/9-QA-Implementation/qa-implementation-report.md]
         notes: >
           Full QA-Implementation validation. Score >= 95% required.
           Adversarial review mandatory.
@@ -120,7 +123,7 @@ phases:
     sequence:
       - agent: devops
         action: deploy
-        creates: [chati.dev/artifacts/10-Deploy/deploy-report.md]
+        creates: [artifacts/10-Deploy/deploy-report.md]
         notes: "Standard deployment process"
 
 transitions:

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "chati-dev",
-  "version": "4.2.2",
-  "description": "AI-Powered Multi-Agent Orchestration System — Structured vibe coding for Full Stack Development",
+  "version": "4.3.1",
+  "description": "AI-Powered Multi-Agent Orchestration System - Structured vibe coding for Full Stack Development",
   "type": "module",
   "bin": {
     "chati": "bin/chati.js",
@@ -18,19 +18,22 @@
   "files": [
     "bin/",
     "src/",
-    "assets/",
+    "assets/logo.txt",
     "framework/",
-    "scripts/",
     "LICENSE",
     "TERMS_OF_USE.md"
   ],
   "scripts": {
     "start": "node bin/chati.js",
     "bundle": "node scripts/bundle-framework.js",
-    "prepublishOnly": "node scripts/bundle-framework.js && node scripts/validate-package.js && node scripts/sign-manifest.js",
+    "sync": "node scripts/sync-framework.js",
+    "scan": "node scripts/scan-stale.js",
+    "install-to": "node scripts/install-to.js",
+    "prepublishOnly": "node scripts/sync-framework.js && node scripts/scan-stale.js && node scripts/validate-package.js && node scripts/sign-manifest.js",
     "test": "node --test test/**/*.test.js",
     "lint": "eslint src/ bin/",
-    "lint:fix": "eslint src/ bin/ --fix"
+    "lint:fix": "eslint src/ bin/ --fix",
+    "verify-v431": "npm test && node scripts/scan-stale.js && npm run sync && node scripts/validate-package.js && node test/fixtures/manual-smoke-v430-upgrade.mjs"
   },
   "keywords": [
     "ai",
@@ -68,6 +71,9 @@
   "engines": {
     "node": ">=20.0.0"
   },
+  "optionalDependencies": {
+    "playwright": "^1.50.0"
+  },
   "devDependencies": {
     "@eslint/js": "^10.0.1",
     "eslint": "^10.1.0",

package/src/autonomy/autonomous-gate.js

@@ -18,6 +18,7 @@ export const GATE_RESULTS = {
 const GATE_THRESHOLDS = {
   'qa-planning': 95,        // Highest — gates planning→build transition
   'qa-implementation': 95,  // Gates build→deploy transition
+  'qa-visual': 90,          // Visual quality gate
   'brief': 90,              // Requirements are critical
   'detail': 90,
   'architect': 90,