chati-dev 2.0.8 → 2.1.0

package/README.md

@@ -33,8 +33,8 @@ AI-assisted development today suffers from three critical issues:
 Chati.dev introduces **Agent-Driven Development**: a pipeline of 13 specialized agents where each agent owns a specific phase, produces validated artifacts, and hands off context to the next agent. An Intelligence Layer ensures context is never lost, knowledge persists across sessions, and the user never accidentally leaves the system.
 
 ```
-PLANNING (planning)  →  Quality Gate  →  BUILD  →  Quality Gate  →  DEPLOY
-  8 agents               QA-Planning     Dev        QA-Impl        DevOps
+DISCOVER  →  PLAN  →  Quality Gate  →  BUILD  →  Quality Gate  →  DEPLOY
+ 3 agents    5 agents   QA-Planning     Dev        QA-Impl        DevOps
 ```
 
 ### Key Innovations
@@ -55,17 +55,30 @@ PLANNING (planning)  →  Quality Gate  →  BUILD  →  Quality Gate  →  DEPL
 
 ---
 
+## Prerequisites
+
+- **Node.js** >= 20.0.0 ([download](https://nodejs.org/))
+- **Claude Code** — the CLI for Claude ([install guide](https://docs.anthropic.com/en/docs/claude-code/overview))
+
+Other supported IDEs: VS Code, Cursor, Gemini CLI, GitHub Copilot, AntiGravity (see [Supported IDEs](#supported-ides)).
+
+---
+
 ## Quick Start
 
-### Install
+### 1. Install in your project
+
+Open a terminal in your project directory:
 
 ```bash
 npx chati-dev init
 ```
 
-The wizard guides you through language and project type, then auto-configures Claude Code with the required MCPs.
+The wizard asks your language and project type, then auto-configures Claude Code with the required MCPs.
+
+### 2. Start Claude Code and activate
 
-### Activate
+Open Claude Code in the same project directory, then type:
 
 ```
 /chati
@@ -73,6 +86,10 @@ The wizard guides you through language and project type, then auto-configures Cl
 
 The orchestrator loads your session, detects where you left off, and routes you to the right agent. You stay inside the system until you explicitly exit.
 
+### 3. Build
+
+From here, the agents take over. You'll go through Planning (requirements, architecture, phases, tasks), Quality Gates, Build, and Deploy — all orchestrated automatically.
+
 ### Monitor
 
 ```bash
@@ -91,11 +108,12 @@ npx chati-dev status --watch  # Auto-refresh every 5s
 
 ## Architecture
 
-### 13 Agents, 4 Categories
+### 13 Agents, 5 Categories
 
 | Category | Agents | Purpose |
 |----------|--------|---------|
-| **PLANNING** | Greenfield WU, Brownfield WU, Brief, Detail (PRD), Architect, UX, Phases, Tasks | Planning & Requirements |
+| **DISCOVER** | Greenfield WU, Brownfield WU, Brief | User Interaction & Discovery |
+| **PLAN** | Detail (PRD), Architect, UX, Phases, Tasks | Autonomous Planning |
 | **Quality** | QA-Planning, QA-Implementation | Validation & Gates |
 | **BUILD** | Dev | Implementation |
 | **DEPLOY** | DevOps | Shipping |
@@ -114,13 +132,13 @@ User Request
     │
     ├── In-conversation ──┐
     │                     ▼
-    │   ┌─── PLANNING (interactive) ───┐
+    │   ┌─── DISCOVER (interactive) ──┐
     │   │  WU → Brief                 │
     │   └─────────────────────────────┘
     │
     ├── Spawns terminals ──────────────────────────┐
     │                                               ▼
-    │   ┌─── PLANNING (autonomous) ─── Parallel ───┐
+    │   ┌─── PLAN (autonomous) ─────── Parallel ───┐
     │   │  Detail (opus) ──┐                       │
     │   │  Architect (opus)├── run simultaneously  │
     │   │  UX (sonnet) ────┘                       │
@@ -267,13 +285,14 @@ your-project/
 ├── chati.dev/
 │   ├── orchestrator/             # Main orchestrator
 │   ├── agents/                   # 13 agent definitions
-│   │   ├── planning/              # 8 planning agents
+│   │   ├── discover/              # 3 discover agents (WU, Brief)
+│   │   ├── plan/                  # 5 plan agents (Detail, Architect, UX, Phases, Tasks)
 │   │   ├── quality/              # 2 quality gate agents
 │   │   ├── build/                # Dev agent
 │   │   └── deploy/               # DevOps agent
 │   ├── tasks/                    # 72 task definitions (YAML frontmatter)
-│   ├── workflows/                # 5 workflow blueprints
-│   ├── templates/                # 5 artifact templates
+│   ├── workflows/                # 6 workflow blueprints
+│   ├── templates/                # 6 artifact templates
 │   ├── schemas/                  # 5 JSON schemas for validation
 │   ├── intelligence/             # Context Engine, Memory Layer, Decision Engine
 │   ├── domains/                  # Domain loading configs (per-agent, per-workflow)
@@ -282,7 +301,7 @@ your-project/
 │   ├── frameworks/               # Decision heuristics, quality dims
 │   ├── quality-gates/            # Planning & implementation gates
 │   ├── patterns/                 # Elicitation patterns
-│   ├── data/                     # Entity registry (48 artifacts)
+│   ├── data/                     # Entity registry (50 artifacts)
 │   ├── i18n/                     # EN, PT, ES, FR translations
 │   ├── migrations/               # Version migration scripts
 │   ├── constitution.md           # 17 Articles + Preamble
@@ -332,14 +351,6 @@ Upgrades include automatic backup, migrations, validation, and config merging. R
 
 ---
 
-## Prerequisites
-
-- **Node.js** >= 20.0.0
-- **npm** >= 9.0.0
-- A supported IDE with AI assistant capabilities
-
----
-
 ## Contributing
 
 We welcome contributions from agents, templates, workflows, intelligence data, translations, and CLI improvements. Please see [CONTRIBUTING.md](.github/CONTRIBUTING.md) for guidelines.

package/assets/logo - co/314/201pia.svg"

@@ -0,0 +1,42 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 620 200">
+  <defs>
+    <clipPath id="c">
+      <path d="M100,8 C155,8 190,40 190,90 C190,140 155,172 100,172 C82,172 66,167 52,159 L22,192 L34,155 C18,140 10,118 10,90 C10,40 45,8 100,8 Z"/>
+    </clipPath>
+    <radialGradient id="g" cx="38%" cy="30%" r="68%">
+      <stop offset="0%" stop-color="#8EC5F5"/>
+      <stop offset="40%" stop-color="#5DA2E2"/>
+      <stop offset="75%" stop-color="#4A90D9"/>
+      <stop offset="100%" stop-color="#2D6BAF"/>
+    </radialGradient>
+    <linearGradient id="r" x1="0" y1="0" x2="0" y2="1">
+      <stop offset="0%" stop-color="rgba(255,255,255,0.5)"/>
+      <stop offset="30%" stop-color="rgba(255,255,255,0.15)"/>
+      <stop offset="100%" stop-color="rgba(0,0,0,0)"/>
+    </linearGradient>
+    <linearGradient id="bs" x1="0" y1="0" x2="0" y2="1">
+      <stop offset="0%" stop-color="rgba(0,0,0,0)"/>
+      <stop offset="65%" stop-color="rgba(0,0,0,0)"/>
+      <stop offset="100%" stop-color="rgba(15,30,60,0.25)"/>
+    </linearGradient>
+  </defs>
+
+  <!-- Chat bubble -->
+  <path d="M100,8 C155,8 190,40 190,90 C190,140 155,172 100,172 C82,172 66,167 52,159 L22,192 L34,155 C18,140 10,118 10,90 C10,40 45,8 100,8 Z" fill="url(#g)"/>
+  <ellipse cx="82" cy="38" rx="52" ry="25" fill="rgba(255,255,255,0.18)" clip-path="url(#c)"/>
+  <path d="M100,8 C155,8 190,40 190,90 C190,140 155,172 100,172 C82,172 66,167 52,159 L22,192 L34,155 C18,140 10,118 10,90 C10,40 45,8 100,8 Z" fill="url(#bs)" clip-path="url(#c)"/>
+  <path d="M100,8 C155,8 190,40 190,90 C190,140 155,172 100,172 C82,172 66,167 52,159 L22,192 L34,155 C18,140 10,118 10,90 C10,40 45,8 100,8 Z" fill="none" stroke="url(#r)" stroke-width="1.5"/>
+
+  <!-- Eyes -->
+  <ellipse cx="72" cy="95" rx="18" ry="20" fill="#1a1a2e"/>
+  <ellipse cx="128" cy="95" rx="18" ry="20" fill="#1a1a2e"/>
+  <ellipse cx="65" cy="86" rx="7" ry="5" fill="rgba(255,255,255,0.55)"/>
+  <ellipse cx="121" cy="86" rx="7" ry="5" fill="rgba(255,255,255,0.55)"/>
+  <ellipse cx="77" cy="100" rx="3.5" ry="2.5" fill="rgba(255,255,255,0.3)"/>
+  <ellipse cx="133" cy="100" rx="3.5" ry="2.5" fill="rgba(255,255,255,0.3)"/>
+
+  <!-- "Chati.dev" text inline -->
+  <text x="210" y="122" font-family="ui-monospace,'SF Mono','Menlo','Consolas','Liberation Mono',monospace" font-weight="700" font-size="68" letter-spacing="-1">
+    <tspan fill="#e6edf3">Chati</tspan><tspan fill="#4A90D9">.</tspan><tspan fill="#e6edf3">dev</tspan>
+  </text>
+</svg>

package/bin/chati.js

@@ -253,9 +253,9 @@ async function main() {
       console.log();
       console.log('v1.0.0 - Initial Release');
       console.log('  - 13 agents (orchestrator + 12 specialized)');
-      console.log('  - 5 workflow blueprints');
-      console.log('  - 5 templates');
-      console.log('  - Constitution (10 Articles + Preamble)');
+      console.log('  - 6 workflow blueprints');
+      console.log('  - 6 templates');
+      console.log('  - Constitution (17 Articles + Preamble)');
       console.log('  - Dashboard TUI');
       console.log('  - Upgrade system with migrations');
       console.log('  - 6 IDE support');

package/framework/agents/{planning → discover}/brief.md

@@ -8,7 +8,7 @@ You are the **Brief Agent**, responsible for extracting and structuring the core
 
 - **Role**: Problem Extraction Specialist
 - **Pipeline Position**: 2nd agent (after WU)
-- **Category**: PLANNING
+- **Category**: DISCOVER
 - **Question Answered**: WHAT is the problem?
 - **Duration**: 30-60 min
 - **Ratio**: 90% Human / 10% AI
@@ -42,6 +42,28 @@ Extract, analyze, and document the core problems, desired outcomes, target users
 
 ## Execution: 5 Phases
 
+### Elicitation Method Selection
+
+Before starting extraction, select elicitation methods from the library:
+
+```
+Reference: chati.dev/patterns/elicitation-library.yaml
+
+Auto-selection based on context:
+  IF greenfield + vibecoder -> brain-dump, moscow, persona-building, playback
+  IF greenfield + power_user -> constraint-mapping, decision-matrix, pre-mortem
+  IF brownfield -> gap-analysis, constraint-mapping, event-storming-lite
+  IF many requirements (>20) -> add moscow, impact-effort-matrix
+  IF multiple stakeholders (>3) -> add stakeholder-map, six-thinking-hats
+
+Primary methods for Brief: brain-dump, five-whys, moscow, stakeholder-map, playback
+Secondary methods (use when needed): scamper, competitor-teardown, persona-building
+
+Adapt method depth to user level:
+  Vibecoder: More open-discovery, explain why each question matters, use examples
+  Power User: More constraint-check, be concise, accept technical shorthand
+```
+
 ### Phase 1: Extraction (Brain Dump)
 ```
 Purpose: Get everything out of the user's head without filtering
@@ -52,7 +74,7 @@ Prompts:
 - "What happens if we don't build this?"
 - "Any references, competitors, or inspirations?"
 
-Technique: Open Discovery
+Technique: Open Discovery (see elicitation-library.yaml -> brain-dump)
 Duration: 10-15 min
 Output: Raw, unfiltered user input captured
 ```

package/framework/agents/{planning → discover}/brownfield-wu.md

@@ -8,7 +8,7 @@ You are the **Brownfield WU Agent**, responsible for comprehensive discovery of
 
 - **Role**: Technical + Operational Discovery Agent
 - **Pipeline Position**: 1st agent (brownfield projects)
-- **Category**: PLANNING
+- **Category**: DISCOVER
 - **Question Answered**: HOW does it work today? (both code and operations)
 - **Duration**: 1-4h depending on codebase size
 - **Ratio**: 40% Human / 60% AI

package/framework/agents/{planning → discover}/greenfield-wu.md

@@ -8,7 +8,7 @@ You are the **Greenfield WU Agent**, responsible for understanding HOW the user
 
 - **Role**: Operational Discovery Agent
 - **Pipeline Position**: 1st agent (greenfield projects)
-- **Category**: PLANNING
+- **Category**: DISCOVER
 - **Question Answered**: HOW does it work today?
 - **Duration**: 15-30 min
 - **Ratio**: 70% Human / 30% AI

package/framework/agents/{planning → plan}/architect.md

@@ -8,7 +8,7 @@ You are the **Architect Agent**, responsible for defining HOW the system will be
 
 - **Role**: Technical Design & Data Architecture Specialist
 - **Pipeline Position**: 4th (greenfield, after Detail) or 3rd (brownfield, after Brief)
-- **Category**: PLANNING
+- **Category**: PLAN
 - **Question Answered**: HOW will we build it?
 - **Duration**: 45-90 min
 - **Ratio**: 50% Human / 50% AI

package/framework/agents/{planning → plan}/detail.md

@@ -8,7 +8,7 @@ You are the **Detail Agent**, responsible for transforming the Brief into a form
 
 - **Role**: Product Specification & Requirements Analyst
 - **Pipeline Position**: 3rd (greenfield) or 4th (brownfield, after Architect)
-- **Category**: PLANNING
+- **Category**: PLAN
 - **Question Answered**: WHAT will we build?
 - **Duration**: 45-90 min
 - **Ratio**: 70% Human / 30% AI

package/framework/agents/{planning → plan}/phases.md

@@ -8,7 +8,7 @@ You are the **Phases Agent**, responsible for breaking the PRD into development
 
 - **Role**: Roadmap & Execution Planning Specialist
 - **Pipeline Position**: 6th (after UX)
-- **Category**: PLANNING
+- **Category**: PLAN
 - **Question Answered**: WHEN will we build it?
 - **Duration**: 20-40 min
 - **Ratio**: 60% Human / 40% AI

package/framework/agents/{planning → plan}/tasks.md

@@ -8,7 +8,7 @@ You are the **Tasks Agent**, responsible for breaking phases into atomic, execut
 
 - **Role**: Work Breakdown & Task Definition Specialist
 - **Pipeline Position**: 7th (after Phases)
-- **Category**: PLANNING
+- **Category**: PLAN
 - **Question Answered**: WHO does WHAT specifically?
 - **Duration**: 30-60 min
 - **Ratio**: 50% Human / 50% AI

package/framework/agents/{planning → plan}/ux.md

@@ -8,7 +8,7 @@ You are the **UX Agent**, responsible for defining HOW the product will look and
 
 - **Role**: User Experience & Design System Specialist
 - **Pipeline Position**: 5th (after Architect in both flows)
-- **Category**: PLANNING
+- **Category**: PLAN
 - **Question Answered**: HOW will it look/feel?
 - **Duration**: 30-60 min
 - **Ratio**: 60% Human / 40% AI

package/framework/agents/quality/qa-implementation.md

@@ -119,18 +119,56 @@ For each completed task:
 Flag unverified criteria for manual review
 ```
 
-### Phase 5: Score & Decide
+### Phase 5: Adversarial Review (Mandatory)
+```
+RULE: Every QA pass MUST identify minimum 3 findings.
+Zero findings = suspiciously clean -> mandatory re-review.
+
+Process:
+1. After Phases 1-4, count total findings across all categories
+2. IF findings < 3:
+   - Log: "Adversarial trigger: only {N} findings detected"
+   - Re-run Phases 2-4 with DEEPER analysis:
+     * Lower severity threshold (include INFO-level observations)
+     * Check for implicit issues (poor naming, missing edge cases, weak error messages)
+     * Look for "things that work but could fail under load/scale"
+   - Findings now include: improvements, suggestions, best-practice deviations
+3. IF findings still < 3 after deep re-review:
+   - Document explicitly WHY the code is genuinely clean
+   - This documentation itself counts as a finding (type: attestation)
+
+Devil's Advocate Pass:
+  After initial review concludes APPROVED:
+  1. Assume the opposite: "This code has a hidden flaw"
+  2. Spend one focused pass actively seeking:
+     - Race conditions, memory leaks, unhandled edge cases
+     - Security assumptions that could be wrong
+     - Performance bottlenecks under 10x load
+     - Integration failures with external services
+  3. Document what you looked for and why it held up (or didn't)
+  4. This analysis is ALWAYS included in the report, even if no new issues found
+
+Findings Classification:
+  - ERROR: Must be fixed before APPROVED
+  - WARNING: Should be fixed, can proceed with documentation
+  - SUGGESTION: Improvement opportunity, does not block
+  - ATTESTATION: Explicit documentation of why something is clean
+```
+
+### Phase 6: Score & Decide
 ```
 Calculate overall quality score:
-  Tests: weight 0.30
-  Coverage: weight 0.20
+  Tests: weight 0.25
+  Coverage: weight 0.15
   Security: weight 0.25
   Code Quality: weight 0.15
   Acceptance Criteria: weight 0.10
+  Adversarial Review: weight 0.10
 
 Result:
-  - All checks pass -> APPROVED -> proceed to DevOps
+  - All checks pass AND adversarial review complete -> APPROVED -> proceed to DevOps
   - Any check fails -> enter silent correction loop
+  - Adversarial review incomplete -> CANNOT approve (re-run Phase 5)
 ```
 
 ---
@@ -233,6 +271,17 @@ Save to: `chati.dev/artifacts/8-Validation/qa-implementation-report.md`
 |------|----------|----------|--------|
 | T1.1 | {criterion} | Yes/No | {OK/FAIL} |
 
+## Adversarial Review
+| # | Type | Category | Description | Severity |
+|---|------|----------|-------------|----------|
+| 1 | {finding/attestation} | {security/performance/quality} | {desc} | {error/warning/suggestion/attestation} |
+
+### Devil's Advocate Analysis
+**Initial conclusion**: {APPROVED/NEEDS CORRECTION}
+**Adversarial hypothesis**: "This code has a hidden flaw in {area}"
+**Investigation**: {what was checked and why}
+**Result**: {held up / new issue found: {desc}}
+
 ## Correction History
 | Loop | Issue | Resolution |
 |------|-------|------------|

package/framework/agents/quality/qa-planning.md

@@ -121,7 +121,44 @@ For each agent that completed PLANNING:
      - Example: Brief said "Brief is well-written" (subjective, not binary)
 ```
 
-### Step 4: Calculate Score & Decide
+### Step 4: Adversarial Review (Mandatory)
+
+```
+RULE: Every planning validation MUST identify minimum 3 findings.
+Zero findings = suspiciously clean -> mandatory re-review.
+
+Process:
+1. After Steps 1-3, count total findings (flags, penalties, observations)
+2. IF findings < 3:
+   - Log: "Adversarial trigger: only {N} findings detected"
+   - Re-analyze with DEEPER scrutiny:
+     * Check for implicit assumptions not documented
+     * Look for missing non-functional requirements (performance, security, a11y)
+     * Verify edge cases are covered in acceptance criteria
+     * Challenge requirement prioritization
+   - Findings now include: suggestions, missing considerations, best-practice gaps
+3. IF findings still < 3 after deep re-review:
+   - Document explicitly WHY the planning is genuinely complete
+   - This documentation itself counts as a finding (type: attestation)
+
+Devil's Advocate Pass:
+  After traceability validation concludes APPROVED:
+  1. Assume the plan has a hidden flaw
+  2. Challenge:
+     - "What requirement is missing that will surface during BUILD?"
+     - "Which acceptance criterion is too vague to test objectively?"
+     - "What stakeholder need was mentioned but not traced to a task?"
+     - "Which architectural decision might not scale?"
+  3. Document the adversarial analysis in the report
+
+Findings Classification:
+  - GAP: Missing traceability link (blocks approval)
+  - WEAK: Subjective or vague criterion (should be fixed)
+  - SUGGESTION: Improvement opportunity (does not block)
+  - ATTESTATION: Explicit justification of completeness
+```
+
+### Step 5: Calculate Score & Decide
 
 ```
 Starting score: 100
@@ -134,10 +171,12 @@ Scoring:
 - Critical gap: -20 points
 - Placeholder: -5 points each
 - Agent defined weak criteria: -10 points
+- Adversarial review incomplete: -15 points
 
 Result:
-- Score >= 95: APPROVED -> GO to BUILD
+- Score >= 95 AND adversarial review complete: APPROVED -> GO to BUILD
 - Score < 95: Enter silent correction loop
+- Adversarial review incomplete: CANNOT approve (re-run Step 4)
 ```
 
 ---
@@ -208,6 +247,18 @@ Save to: `chati.dev/artifacts/7-QA-Planning/qa-planning-report.md`
 |------|------|------|
 | {file} | {placeholder} | {line} |
 
+## Adversarial Review
+| # | Type | Area | Description | Severity |
+|---|------|------|-------------|----------|
+| 1 | {gap/weak/suggestion/attestation} | {traceability/criteria/scope} | {desc} | {blocks/should-fix/info} |
+
+### Devil's Advocate Analysis
+**Initial conclusion**: {APPROVED/NEEDS CORRECTION}
+**Adversarial challenges**:
+1. "What requirement is missing?" → {finding or "None — all Brief problems traced to tasks"}
+2. "Which criterion is too vague?" → {finding or "None — all GWT criteria are binary"}
+3. "What will surface during BUILD?" → {finding or "None — edge cases covered"}
+
 ## Correction History
 | Loop | Agent | Issue | Resolution |
 |------|-------|-------|------------|

package/framework/config.yaml

@@ -1,8 +1,8 @@
 # chati.dev Configuration
-version: "2.0.1"
+version: "2.1.0"
 installed_at: "2026-02-07T10:00:00Z"
-updated_at: "2026-02-13T00:00:00Z"
-installer_version: "2.0.1"
+updated_at: "2026-02-17T00:00:00Z"
+installer_version: "2.1.0"
 project_type: greenfield
 language: en
 ides: [claude-code]

package/framework/constitution.md

@@ -6,7 +6,7 @@ Chati.dev is a planning-first AI-assisted orchestration system that coordinates
 
 ### 4 Core Principles
 
-1. **Planning Before Code**: Never write code without understanding the problem, the users, and the constraints. The PLANNING phase exists because assumptions are the root cause of failed projects.
+1. **Planning Before Code**: Never write code without understanding the problem, the users, and the constraints. The DISCOVER and PLAN phases exist because assumptions are the root cause of failed projects.
 
 2. **Short Iterations**: Deliver value in small, verifiable increments. Every agent validates its own output before passing forward. Every quality gate catches issues early.
 
@@ -242,7 +242,7 @@ The pipeline operates in three execution modes that control agent permissions. M
 
 | Mode | States | Read Scope | Write Scope |
 |------|--------|------------|-------------|
-| **planning** | planning | Entire project (codebase + chati.dev/) | `chati.dev/` and `.chati/` only |
+| **planning** | discover, plan | Entire project (codebase + chati.dev/) | `chati.dev/` and `.chati/` only |
 | **build** | build, validate | Entire project | Entire project |
 | **deploy** | deploy | Entire project | Entire project + infra/CI operations |
 
@@ -390,7 +390,7 @@ The system SHALL support two execution modes that govern the degree of human inv
 
 4. Certain agents are ALWAYS human-in-the-loop regardless of mode:
    - **brief**: Requirements extraction requires human validation
-   - **deviation-handler**: Deviations from the plan always need human approval
+   - **orchestrator (deviation protocol)**: Deviations from the plan always need human approval
 
 5. Safety net triggers SHALL pause autonomous execution when dangerous conditions are detected: consecutive failures, circular approaches, resource limits, or destructive operations.
 
@@ -402,5 +402,5 @@ The system SHALL support two execution modes that govern the degree of human inv
 
 ---
 
-*Chati.dev Constitution v2.0.0 — 17 Articles + Preamble*
+*Chati.dev Constitution v2.1.0 — 17 Articles + Preamble*
 *All agents are bound by this Constitution. Violations are enforced per article.*

package/framework/context/quality.md

@@ -11,7 +11,7 @@
 Scores within 5 points below threshold trigger REVIEW (human confirmation required even in autonomous mode).
 
 ## 5 Pipeline Gates
-1. **Planning Complete** — All PLANNING agents finished
+1. **Planning Complete** — All DISCOVER + PLAN agents finished
 2. **QA Planning** — QA-Planning agent validates plan coherence (95% threshold)
 3. **Implementation** — Dev agent completes all tasks
 4. **QA Implementation** — Tests pass, SAST clean, coverage adequate (95% threshold)

package/framework/context/root.md

@@ -1,7 +1,7 @@
 # Chati.dev System Context
 
 ## Framework
-- **Version**: 2.0.1
+- **Version**: 2.1.0
 - **Agents**: 13 (12 specialized + orchestrator)
 - **Constitution**: 17 Articles + Preamble
 - **Quality**: 5 pipeline gates + 4-tier validation
@@ -15,9 +15,10 @@
 
 ## Pipeline
 ```
-PLANNING: WU -> Brief -> Detail -> Architect -> UX -> Phases -> Tasks -> QA-Planning
-BUILD:   Dev -> QA-Implementation
-DEPLOY:  DevOps
+DISCOVER: WU -> Brief
+PLAN:     Detail -> Architect -> UX -> Phases -> Tasks -> QA-Planning
+BUILD:    Dev -> QA-Implementation
+DEPLOY:   DevOps
 ```
 
 ## How to Use