chati-dev 2.0.1 → 2.0.2

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/README.md CHANGED
@@ -3,13 +3,13 @@
3
3
  <img src="packages/chati-dev/assets/logo.svg" alt="chati.dev" width="380">
4
4
  <br><br>
5
5
  <strong>AI-Powered Multi-Agent Orchestration System</strong><br>
6
- <em>13 agents. 16 articles. 6 IDEs. 4 languages. Structured vibe coding.</em>
6
+ <em>13 agents. 17 articles. 6 IDEs. 4 languages. 849 tests. Structured vibe coding.</em>
7
7
  </div>
8
8
 
9
9
  <p align="center">
10
10
  <a href="https://www.npmjs.com/package/chati-dev"><img src="https://img.shields.io/npm/v/chati-dev?color=blue&label=npm" alt="npm"></a>
11
11
  <a href="LICENSE"><img src="https://img.shields.io/badge/License-MIT-yellow.svg" alt="License: MIT"></a>
12
- <a href="https://nodejs.org/"><img src="https://img.shields.io/badge/node-%3E%3D18.0.0-brightgreen.svg" alt="Node.js"></a>
12
+ <a href="https://nodejs.org/"><img src="https://img.shields.io/badge/node-%3E%3D20.0.0-brightgreen.svg" alt="Node.js"></a>
13
13
  <a href="#architecture"><img src="https://img.shields.io/badge/agents-13-purple.svg" alt="Agents"></a>
14
14
  <a href="#supported-ides"><img src="https://img.shields.io/badge/IDEs-6-orange.svg" alt="IDEs"></a>
15
15
  <a href="#internationalization"><img src="https://img.shields.io/badge/i18n-EN%20%7C%20PT%20%7C%20ES%20%7C%20FR-informational.svg" alt="i18n"></a>
@@ -44,11 +44,14 @@ CLARITY (planning) → Quality Gate → BUILD → Quality Gate → DEPLO
44
44
  | Innovation | Description |
45
45
  |------------|-------------|
46
46
  | **Structured Agent Pipeline** | 13 agents with defined missions, validated outputs, and handoff protocols |
47
- | **Self-Validating Agents** | Binary pass/fail criteria per agent. Quality gates at planning and implementation |
48
- | **Context Engine** | 4 context brackets (FRESH → CRITICAL) with 5 injection layers. Autonomous recovery |
49
- | **Memory Layer** | 4 cognitive sectors. Persistent knowledge across sessions with attention scoring |
50
- | **Framework Registry** | Entity catalog with decision engine (REUSE/ADAPT/CREATE) for brownfield analysis |
47
+ | **Self-Validating Agents** | Binary pass/fail criteria per agent. 5 quality gates with circuit breaker |
48
+ | **Context Engine PRISM** | 5-layer injection pipeline with bracket tracking (FRESH → CRITICAL). Autonomous recovery |
49
+ | **Memory System RECALL** | 4 cognitive sectors. Persistent knowledge across sessions with attention scoring and natural decay |
50
+ | **Decision Engine COMPASS** | Entity catalog with Jaccard similarity for REUSE/ADAPT/CREATE decisions. Self-healing registry |
51
51
  | **Session Lock** | Once activated, user stays in system until explicit exit. Zero accidental leakage |
52
+ | **Hooks System** | 5 Claude Code hooks — constitution guard, mode governance, model governance, context injection, session digest |
53
+ | **Execution Modes** | Autonomous and human-in-the-loop modes with safety net (5 triggers) and circuit breaker |
54
+ | **Multi-Terminal** | Parallel agent execution with write-scope isolation (Detail + Architect + UX simultaneously) |
52
55
  | **IDE-Agnostic** | Works with 6 IDEs through a thin router pattern |
53
56
 
54
57
  ---
@@ -139,15 +142,15 @@ User Request
139
142
  └──────────────────────────────────────────────────┘
140
143
  ```
141
144
 
142
- ### Intelligence Layer (V7.1)
145
+ ### Intelligence Layer
143
146
 
144
147
  The Intelligence Layer operates transparently behind the pipeline:
145
148
 
146
149
  | System | What it does |
147
150
  |--------|-------------|
148
- | **Context Engine** | Detects context depletion across 4 brackets. Reduces injection layers as context fills. Autonomous recovery via Smart Continuation or Session Spawn. |
149
- | **Memory Layer** | Captures decisions, patterns, and lessons learned. Persists across sessions. 4 cognitive sectors (Episodic, Semantic, Procedural, Reflective). Attention scoring with natural decay. |
150
- | **Framework Registry** | Catalogs all 48 system artifacts. Decision engine for brownfield analysis: REUSE existing artifacts, ADAPT with modifications, or CREATE new. |
151
+ | **Context Engine PRISM** | 5-layer injection pipeline (Constitution Global Agent Workflow Task). 4 brackets (FRESH/MODERATE/DEPLETED/CRITICAL). Domain loading with graceful degradation. |
152
+ | **Memory System RECALL** | Gotchas auto-capture with 3x/24h promotion. Per-agent memory CRUD. Session digests. Unified search across 4 cognitive sectors (Episodic, Semantic, Procedural, Reflective). |
153
+ | **Decision Engine COMPASS** | Jaccard similarity for REUSE/ADAPT/CREATE decisions. BFS dependency analysis. Entity registry auto-update. 6 self-healing rules. |
151
154
  | **Session Lock** | Locks the session on `/chati` activation. All messages routed through orchestrator. Exit only via `/chati exit`. Prevents accidental context leakage. |
152
155
 
153
156
  ### Universal Protocols
@@ -167,7 +170,7 @@ Every agent follows 8 universal protocols:
167
170
 
168
171
  ### Constitution
169
172
 
170
- The system is governed by a **16-article Constitution** that enforces agent behavior, quality standards, security, and system integrity. Key articles:
173
+ The system is governed by a **17-article Constitution** that enforces agent behavior, quality standards, security, and system integrity. Key articles:
171
174
 
172
175
  | Article | Governance |
173
176
  |---------|-----------|
@@ -178,6 +181,7 @@ The system is governed by a **16-article Constitution** that enforces agent beha
178
181
  | XII-XIV | Context bracket governance, memory governance, framework registry |
179
182
  | XV | Session lock governance — mandatory lock, explicit exit only |
180
183
  | XVI | Model governance — opus/sonnet/haiku per agent, no downgrade rule |
184
+ | XVII | Execution mode governance — autonomous vs human-in-the-loop, safety net triggers |
181
185
 
182
186
  ---
183
187
 
@@ -233,13 +237,21 @@ The system is governed by a **16-article Constitution** that enforces agent beha
233
237
  ```
234
238
  your-project/
235
239
  ├── .chati/
236
- │ ├── session.yaml # Session state (auto-managed)
237
- ├── memories/ # Memory Layer storage (gitignored)
238
- │ └── continuation/ # Context recovery files
240
+ │ ├── session.yaml # Session state (auto-managed, gitignored)
241
+ └── memories/ # Memory Layer storage (gitignored)
239
242
  ├── .claude/
240
- └── commands/
241
- └── chati.md # Thin router → orchestrator
242
- ├── CLAUDE.md # IDE entry point (auto-updated)
243
+ ├── commands/
244
+ └── chati.md # Thin router → orchestrator
245
+ │ └── rules/
246
+ │ └── chati/ # Framework context (auto-loaded by Claude Code)
247
+ │ ├── root.md # System overview + key references
248
+ │ ├── governance.md # Constitution key rules
249
+ │ ├── protocols.md # 8 universal protocols
250
+ │ └── quality.md # Quality standards
251
+ ├── CLAUDE.md # Minimal project context (auto-generated)
252
+ ├── CLAUDE.local.md # Runtime state — session lock, current agent (gitignored)
253
+ ├── docs/
254
+ │ └── CHANGELOG.md # Version history
243
255
  ├── chati.dev/
244
256
  │ ├── orchestrator/ # Main orchestrator
245
257
  │ ├── agents/ # 13 agent definitions
@@ -247,17 +259,21 @@ your-project/
247
259
  │ │ ├── quality/ # 2 quality gate agents
248
260
  │ │ ├── build/ # Dev agent
249
261
  │ │ └── deploy/ # DevOps agent
262
+ │ ├── tasks/ # 72 task definitions (YAML frontmatter)
250
263
  │ ├── workflows/ # 5 workflow blueprints
251
264
  │ ├── templates/ # 5 artifact templates
252
- │ ├── schemas/ # JSON schemas for validation
265
+ │ ├── schemas/ # 5 JSON schemas for validation
253
266
  │ ├── intelligence/ # Context Engine, Memory Layer, Decision Engine
267
+ │ ├── domains/ # Domain loading configs (per-agent, per-workflow)
268
+ │ ├── hooks/ # 5 Claude Code hooks (enforcement)
269
+ │ ├── context/ # Context source files (deployed to .claude/rules/)
254
270
  │ ├── frameworks/ # Decision heuristics, quality dims
255
271
  │ ├── quality-gates/ # Planning & implementation gates
256
272
  │ ├── patterns/ # Elicitation patterns
257
- │ ├── data/ # Entity registry
273
+ │ ├── data/ # Entity registry (48 artifacts)
258
274
  │ ├── i18n/ # EN, PT, ES, FR translations
259
275
  │ ├── migrations/ # Version migration scripts
260
- │ ├── constitution.md # 16 Articles + Preamble
276
+ │ ├── constitution.md # 17 Articles + Preamble
261
277
  │ └── config.yaml # System configuration
262
278
  ├── chati.dev/artifacts/ # Generated during pipeline
263
279
  │ ├── 0-WU/
@@ -305,7 +321,7 @@ Upgrades include automatic backup, migrations, validation, and config merging. R
305
321
 
306
322
  ## Prerequisites
307
323
 
308
- - **Node.js** >= 18.0.0
324
+ - **Node.js** >= 20.0.0
309
325
  - **npm** >= 9.0.0
310
326
  - A supported IDE with AI assistant capabilities
311
327
 
@@ -241,7 +241,7 @@ entities:
241
241
  constitution:
242
242
  path: chati.dev/constitution.md
243
243
  type: governance
244
- purpose: "16 Articles + Preamble governing all agent behavior"
244
+ purpose: "17 Articles + Preamble governing all agent behavior"
245
245
  keywords: [constitution, governance, rules, articles, enforcement]
246
246
  dependencies: []
247
247
  adaptability: 0.1
@@ -1,5 +1,5 @@
1
1
  # Constitution Domain — Extracted governance rules for PRISM L0
2
- # Source: chati.dev/constitution.md (16 Articles + Preamble)
2
+ # Source: chati.dev/constitution.md (17 Articles + Preamble)
3
3
 
4
4
  summary: >
5
5
  Constitution governance: self-validation required (loop until quality >= 95%),
@@ -21,7 +21,7 @@ installer:
21
21
  agents_count: "13 agent definitions (CLARITY, BUILD, DEPLOY phases)"
22
22
  workflows_count: "5 workflow blueprints"
23
23
  templates_count: "5 templates (PRD, Brownfield PRD, Architecture, Task, QA Gate)"
24
- constitution: "Constitution (16 Articles + Preamble)"
24
+ constitution: "Constitution (17 Articles + Preamble)"
25
25
  session_mgmt: "Session management system"
26
26
  quality_gates: "Quality gates (4-tier validation)"
27
27
  proceed: "Proceed with installation?"
@@ -29,7 +29,7 @@ installer:
29
29
  created_chati: "Created .chati/ session directory"
30
30
  created_framework: "Created chati.dev/ system directory (agents, templates, workflows)"
31
31
  created_commands: "Created .claude/commands/ (thin router)"
32
- installed_constitution: "Installed Constitution (Articles I-XVI)"
32
+ installed_constitution: "Installed Constitution (Articles I-XVII)"
33
33
  created_session: "Created session.yaml schema"
34
34
  created_claude_md: "Created CLAUDE.md"
35
35
  configured_mcps: "Configured MCPs:"
@@ -37,7 +37,7 @@ installer:
37
37
  agents_valid: "All 13 agents implement 8 protocols"
38
38
  handoff_ok: "Handoff protocol: OK"
39
39
  validation_ok: "Self-validation criteria: OK"
40
- constitution_ok: "Constitution: 16 articles verified"
40
+ constitution_ok: "Constitution: 17 articles verified"
41
41
  created_memories: "Created .chati/memories/ (Memory Layer)"
42
42
  installed_intelligence: "Installed Intelligence Layer (Context Engine, Memory, Registry)"
43
43
  intelligence_valid: "Intelligence: 6 spec files verified"
@@ -21,7 +21,7 @@ installer:
21
21
  agents_count: "13 definiciones de agentes (fases CLARITY, BUILD, DEPLOY)"
22
22
  workflows_count: "5 blueprints de workflow"
23
23
  templates_count: "5 templates (PRD, PRD Brownfield, Arquitectura, Task, QA Gate)"
24
- constitution: "Constitucion (16 Articulos + Preambulo)"
24
+ constitution: "Constitucion (17 Articulos + Preambulo)"
25
25
  session_mgmt: "Sistema de gestion de sesion"
26
26
  quality_gates: "Quality gates (validacion en 4 capas)"
27
27
  proceed: "Proceder con la instalacion?"
@@ -29,7 +29,7 @@ installer:
29
29
  created_chati: "Creado directorio de sesion .chati/"
30
30
  created_framework: "Creado directorio del sistema chati.dev/ (agentes, templates, workflows)"
31
31
  created_commands: "Creado .claude/commands/ (enrutador)"
32
- installed_constitution: "Instalada Constitucion (Articulos I-XVI)"
32
+ installed_constitution: "Instalada Constitucion (Articulos I-XVII)"
33
33
  created_session: "Creado schema session.yaml"
34
34
  created_claude_md: "Creado CLAUDE.md"
35
35
  configured_mcps: "MCPs configurados:"
@@ -37,7 +37,7 @@ installer:
37
37
  agents_valid: "Los 13 agentes implementan 8 protocolos"
38
38
  handoff_ok: "Protocolo de handoff: OK"
39
39
  validation_ok: "Criterios de auto-validacion: OK"
40
- constitution_ok: "Constitucion: 16 articulos verificados"
40
+ constitution_ok: "Constitucion: 17 articulos verificados"
41
41
  created_memories: "Creado .chati/memories/ (Memory Layer)"
42
42
  installed_intelligence: "Instalada Intelligence Layer (Context Engine, Memory, Registry)"
43
43
  intelligence_valid: "Intelligence: 6 archivos de spec verificados"
@@ -21,7 +21,7 @@ installer:
21
21
  agents_count: "13 definitions d'agents (phases CLARITY, BUILD, DEPLOY)"
22
22
  workflows_count: "5 blueprints de workflow"
23
23
  templates_count: "5 templates (PRD, PRD Brownfield, Architecture, Task, QA Gate)"
24
- constitution: "Constitution (16 Articles + Preambule)"
24
+ constitution: "Constitution (17 Articles + Preambule)"
25
25
  session_mgmt: "Systeme de gestion de session"
26
26
  quality_gates: "Quality gates (validation en 4 couches)"
27
27
  proceed: "Proceder a l'installation?"
@@ -29,7 +29,7 @@ installer:
29
29
  created_chati: "Cree le repertoire de session .chati/"
30
30
  created_framework: "Cree le repertoire du systeme chati.dev/ (agents, templates, workflows)"
31
31
  created_commands: "Cree .claude/commands/ (routeur)"
32
- installed_constitution: "Installee la Constitution (Articles I-XVI)"
32
+ installed_constitution: "Installee la Constitution (Articles I-XVII)"
33
33
  created_session: "Cree le schema session.yaml"
34
34
  created_claude_md: "Cree CLAUDE.md"
35
35
  configured_mcps: "MCPs configures:"
@@ -37,7 +37,7 @@ installer:
37
37
  agents_valid: "Les 13 agents implementent 8 protocoles"
38
38
  handoff_ok: "Protocole de passation: OK"
39
39
  validation_ok: "Criteres d'auto-validation: OK"
40
- constitution_ok: "Constitution: 16 articles verifies"
40
+ constitution_ok: "Constitution: 17 articles verifies"
41
41
  created_memories: "Cree .chati/memories/ (Memory Layer)"
42
42
  installed_intelligence: "Installee Intelligence Layer (Context Engine, Memory, Registry)"
43
43
  intelligence_valid: "Intelligence: 6 fichiers de spec verifies"
@@ -21,7 +21,7 @@ installer:
21
21
  agents_count: "13 definicoes de agentes (fases CLARITY, BUILD, DEPLOY)"
22
22
  workflows_count: "5 blueprints de workflow"
23
23
  templates_count: "5 templates (PRD, PRD Brownfield, Arquitetura, Task, QA Gate)"
24
- constitution: "Constituicao (16 Artigos + Preambulo)"
24
+ constitution: "Constituicao (17 Artigos + Preambulo)"
25
25
  session_mgmt: "Sistema de gerenciamento de sessao"
26
26
  quality_gates: "Quality gates (validacao em 4 camadas)"
27
27
  proceed: "Prosseguir com a instalacao?"
@@ -29,7 +29,7 @@ installer:
29
29
  created_chati: "Criado diretorio de sessao .chati/"
30
30
  created_framework: "Criado diretorio do sistema chati.dev/ (agentes, templates, workflows)"
31
31
  created_commands: "Criado .claude/commands/ (roteador)"
32
- installed_constitution: "Instalada Constituicao (Artigos I-XVI)"
32
+ installed_constitution: "Instalada Constituicao (Artigos I-XVII)"
33
33
  created_session: "Criado schema session.yaml"
34
34
  created_claude_md: "Criado CLAUDE.md"
35
35
  configured_mcps: "MCPs configurados:"
@@ -37,7 +37,7 @@ installer:
37
37
  agents_valid: "Todos os 13 agentes implementam 8 protocolos"
38
38
  handoff_ok: "Protocolo de handoff: OK"
39
39
  validation_ok: "Criterios de auto-validacao: OK"
40
- constitution_ok: "Constituicao: 16 artigos verificados"
40
+ constitution_ok: "Constituicao: 17 artigos verificados"
41
41
  created_memories: "Criado .chati/memories/ (Memory Layer)"
42
42
  installed_intelligence: "Instalada Intelligence Layer (Context Engine, Memory, Registry)"
43
43
  intelligence_valid: "Intelligence: 6 arquivos de spec verificados"
@@ -96,7 +96,7 @@ npx chati-dev health
96
96
  Checks:
97
97
  1. All registered entities exist on disk
98
98
  2. Schema files are valid JSON
99
- 3. Constitution has >= 16 articles
99
+ 3. Constitution has >= 17 articles
100
100
  4. Agents contain required protocol references
101
101
  5. Entity count matches actual file count
102
102
  6. Checksums match (if calculated)
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "chati-dev",
3
- "version": "2.0.1",
3
+ "version": "2.0.2",
4
4
  "description": "AI-Powered Multi-Agent Orchestration System — 13 agents, 6 IDEs, 4 languages",
5
5
  "type": "module",
6
6
  "bin": {
@@ -60,7 +60,7 @@
60
60
  "semver": "^7.6.0"
61
61
  },
62
62
  "engines": {
63
- "node": ">=18.0.0"
63
+ "node": ">=20.0.0"
64
64
  },
65
65
  "devDependencies": {
66
66
  "@eslint/js": "^10.0.1",
@@ -235,18 +235,37 @@ async function configureIDE(targetDir, ideKey, selectedMCPs) {
235
235
 
236
236
  if (ideKey === 'claude-code') {
237
237
  // Thin router
238
- const routerContent = `---
239
- # chati.dev Thin Router
240
- # This file delegates to the full orchestrator at chati.dev/orchestrator/chati.md
241
- # DO NOT add logic here -- pure delegation only
238
+ const routerContent = `# /chati — Thin Router
239
+
240
+ ## CRITICAL Language Override
241
+
242
+ Read \`.chati/session.yaml\` field \`language\` BEFORE anything else.
243
+ ALL responses MUST be in this language. This overrides any global IDE language setting.
244
+
245
+ | Value | Language |
246
+ |-------|----------|
247
+ | \`en\` | English |
248
+ | \`pt\` | Portugues |
249
+ | \`es\` | Espanol |
250
+ | \`fr\` | Francais |
251
+
252
+ If session.yaml does not exist or has no language field, default to English.
253
+
242
254
  ---
243
255
 
244
- Read and execute the orchestrator at \`chati.dev/orchestrator/chati.md\`.
256
+ ## Load
257
+
258
+ Read and execute the full orchestrator at \`chati.dev/orchestrator/chati.md\`.
259
+
260
+ Pass through all context: session state, handoffs, artifacts, and user input.
245
261
 
246
- Pass through all context: session (.chati/session.yaml), handoffs (chati.dev/artifacts/handoffs/),
247
- artifacts (chati.dev/artifacts/), constitution (chati.dev/constitution.md).
262
+ **Context to pass:**
263
+ - \`.chati/session.yaml\` (session state — includes language)
264
+ - \`CLAUDE.local.md\` (runtime state — session lock, current agent)
265
+ - \`chati.dev/artifacts/handoffs/\` (latest handoff)
266
+ - \`chati.dev/config.yaml\` (version info)
248
267
 
249
- This is a thin router. All logic lives in the orchestrator.
268
+ **User input:** $ARGUMENTS
250
269
  `;
251
270
  writeFileSync(join(targetDir, '.claude', 'commands', 'chati.md'), routerContent, 'utf-8');
252
271
 
@@ -131,8 +131,8 @@ export function runHealthCheck(targetDir) {
131
131
  if (existsSync(constitutionPath)) {
132
132
  const content = readFileSync(constitutionPath, 'utf-8');
133
133
  const articleCount = (content.match(/^## Article/gm) || []).length;
134
- checks.constitution.pass = articleCount >= 16;
135
- checks.constitution.details = `${articleCount}/16 articles`;
134
+ checks.constitution.pass = articleCount >= 17;
135
+ checks.constitution.details = `${articleCount}/17 articles`;
136
136
  } else {
137
137
  checks.constitution.details = 'Not found';
138
138
  }
@@ -26,7 +26,7 @@ const FALLBACK_EN = {
26
26
  agents_count: '13 agent definitions (CLARITY, BUILD, DEPLOY phases)',
27
27
  workflows_count: '5 workflow blueprints',
28
28
  templates_count: '5 templates (PRD, Brownfield PRD, Architecture, Task, QA Gate)',
29
- constitution: 'Constitution (16 Articles + Preamble)',
29
+ constitution: 'Constitution (17 Articles + Preamble)',
30
30
  session_mgmt: 'Session management system',
31
31
  quality_gates: 'Quality gates (4-tier validation)',
32
32
  proceed: 'Proceed with installation?',
@@ -34,7 +34,7 @@ const FALLBACK_EN = {
34
34
  created_chati: 'Created .chati/ session directory',
35
35
  created_framework: 'Created chati.dev/ system directory (agents, templates, workflows)',
36
36
  created_commands: 'Created .claude/commands/ (thin router)',
37
- installed_constitution: 'Installed Constitution (Articles I-XVI)',
37
+ installed_constitution: 'Installed Constitution (Articles I-XVII)',
38
38
  created_session: 'Created session.yaml schema',
39
39
  created_claude_md: 'Created CLAUDE.md',
40
40
  configured_mcps: 'Configured MCPs:',
@@ -42,7 +42,7 @@ const FALLBACK_EN = {
42
42
  agents_valid: 'All 13 agents implement 8 protocols',
43
43
  handoff_ok: 'Handoff protocol: OK',
44
44
  validation_ok: 'Self-validation criteria: OK',
45
- constitution_ok: 'Constitution: 16 articles verified',
45
+ constitution_ok: 'Constitution: 17 articles verified',
46
46
  created_memories: 'Created .chati/memories/ (Memory Layer)',
47
47
  installed_intelligence: 'Installed Intelligence Layer (Context Engine, Memory, Registry)',
48
48
  intelligence_valid: 'Intelligence: 6 spec files verified',