@christianmaf80/agentic-workflow 1.19.1 → 1.19.2-beta.1

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.
Files changed (118) hide show
  1. package/README.es.md +84 -13
  2. package/README.md +83 -12
  3. package/RELEASE_PROCESS.md +4 -3
  4. package/bin/cli.js +39 -18
  5. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/acceptance.md +6 -0
  6. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/agent-scores.md +6 -0
  7. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/agent-tasks/1-dev-agent-scaffold.md +6 -0
  8. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/agent-tasks/2-dev-agent-manifest-command.md +6 -0
  9. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/agent-tasks/3-dev-agent-marketplace-evidence.md +6 -0
  10. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/agent-tasks/4-qa-agent-verify-build.md +6 -0
  11. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/analysis.md +6 -0
  12. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/architect/review.md +6 -0
  13. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/metrics.md +6 -0
  14. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/plan.md +6 -0
  15. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/researcher/research.md +6 -0
  16. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/results-acceptance.md +6 -0
  17. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/task.md +6 -0
  18. package/dist/agent/artifacts/1-scaffold-extension-vscode-agentinc/verification.md +6 -0
  19. package/dist/agent/artifacts/2-scaffold-vscode-chat-ai-panel/acceptance.md +6 -0
  20. package/dist/agent/artifacts/2-scaffold-vscode-chat-ai-panel/task.md +6 -0
  21. package/dist/agent/artifacts/3-new-vscode-agentic-activitybar-chat/acceptance.md +6 -0
  22. package/dist/agent/artifacts/3-new-vscode-agentic-activitybar-chat/task.md +6 -0
  23. package/dist/agent/artifacts/4-copiar-estructura-agentic-cliente/acceptance.md +6 -0
  24. package/dist/agent/artifacts/4-copiar-estructura-agentic-cliente/architect/implementation.md +6 -0
  25. package/dist/agent/artifacts/5-reestructurar-src-para-extension-vscode/acceptance.md +6 -0
  26. package/dist/agent/artifacts/5-reestructurar-src-para-extension-vscode/agent-tasks/1-dev-agent-reestructurar-carpetas.md +1 -1
  27. package/dist/agent/artifacts/5-reestructurar-src-para-extension-vscode/task.md +6 -0
  28. package/dist/agent/artifacts/6-release-beta-11/task.md +6 -0
  29. package/dist/agent/artifacts/candidate/init.md +8 -4
  30. package/dist/agent/artifacts/candidate/task.md +6 -0
  31. package/dist/agent/artifacts/task-20260128-reorganize-structure/acceptance.md +6 -0
  32. package/dist/agent/artifacts/task-20260128-reorganize-structure/brief.md +1 -1
  33. package/dist/agent/artifacts/task-20260128-reorganize-structure/closure.md +3 -3
  34. package/dist/agent/artifacts/task-20260128-reorganize-structure/implementation.md +2 -2
  35. package/dist/agent/artifacts/task-20260128-reorganize-structure/task.md +6 -0
  36. package/dist/agent/index.md +3 -0
  37. package/dist/agent/rules/constitution/agents-behavior.md +0 -1
  38. package/dist/agent/rules/constitution/clean-code.md +6 -0
  39. package/dist/agent/rules/constitution/index.md +1 -1
  40. package/dist/agent/rules/constitution/runtime-integration.md +101 -0
  41. package/dist/agent/rules/index.md +0 -1
  42. package/dist/agent/rules/roles/architect.md +2 -1
  43. package/dist/agent/templates/acceptance.md +6 -0
  44. package/dist/agent/templates/init.md +18 -0
  45. package/dist/agent/templates/supplemental-report.md +6 -0
  46. package/dist/agent/templates/task.md +7 -0
  47. package/dist/agent/workflows/init.md +29 -10
  48. package/dist/agent/workflows/tasklifecycle-long/index.md +27 -27
  49. package/dist/agent/workflows/tasklifecycle-long/phase-0-acceptance-criteria.md +13 -3
  50. package/dist/agent/workflows/tasklifecycle-long/phase-1-research.md +6 -4
  51. package/dist/agent/workflows/tasklifecycle-long/phase-2-analysis.md +4 -4
  52. package/dist/agent/workflows/tasklifecycle-long/phase-3-planning.md +4 -4
  53. package/dist/agent/workflows/tasklifecycle-long/phase-4-implementation.md +4 -4
  54. package/dist/agent/workflows/tasklifecycle-long/phase-5-verification.md +4 -4
  55. package/dist/agent/workflows/tasklifecycle-long/phase-6-results-acceptance.md +4 -4
  56. package/dist/agent/workflows/tasklifecycle-long/phase-7-evaluation.md +4 -4
  57. package/dist/agent/workflows/tasklifecycle-long/phase-8-commit-push.md +2 -2
  58. package/dist/agent/workflows/tasklifecycle-short/index.md +12 -9
  59. package/dist/agent/workflows/tasklifecycle-short/short-phase-1-brief.md +2 -0
  60. package/dist/cli/commands/create.js +30 -5
  61. package/dist/cli/commands/create.js.map +1 -1
  62. package/dist/cli/commands/init.js +9 -3
  63. package/dist/cli/commands/init.js.map +1 -1
  64. package/dist/cli/commands/mcp.js +11 -0
  65. package/dist/cli/commands/mcp.js.map +1 -0
  66. package/dist/cli/commands/register-mcp.js +116 -0
  67. package/dist/cli/commands/register-mcp.js.map +1 -0
  68. package/dist/cli/index.js +1 -0
  69. package/dist/cli/index.js.map +1 -1
  70. package/dist/infrastructure/context/index.js +2 -0
  71. package/dist/infrastructure/context/index.js.map +1 -0
  72. package/dist/{core → infrastructure}/context/manager.js +0 -1
  73. package/dist/infrastructure/context/manager.js.map +1 -0
  74. package/dist/infrastructure/index.js +7 -0
  75. package/dist/infrastructure/index.js.map +1 -0
  76. package/dist/infrastructure/logger/index.js +41 -0
  77. package/dist/infrastructure/logger/index.js.map +1 -0
  78. package/dist/infrastructure/mapping/index.js +2 -0
  79. package/dist/infrastructure/mapping/index.js.map +1 -0
  80. package/dist/{core → infrastructure}/mapping/resolver.js +5 -5
  81. package/dist/infrastructure/mapping/resolver.js.map +1 -0
  82. package/dist/infrastructure/migration/backup.js.map +1 -0
  83. package/dist/infrastructure/migration/detector.js.map +1 -0
  84. package/dist/infrastructure/migration/index.js +4 -0
  85. package/dist/infrastructure/migration/index.js.map +1 -0
  86. package/dist/infrastructure/migration/transformer.js.map +1 -0
  87. package/dist/infrastructure/utils/backup.js.map +1 -0
  88. package/dist/infrastructure/utils/index.js +2 -0
  89. package/dist/infrastructure/utils/index.js.map +1 -0
  90. package/dist/runtime/index.js +4 -0
  91. package/dist/runtime/index.js.map +1 -0
  92. package/dist/runtime/runtime.js +254 -0
  93. package/dist/runtime/runtime.js.map +1 -0
  94. package/dist/runtime/task-loader.js +32 -0
  95. package/dist/runtime/task-loader.js.map +1 -0
  96. package/dist/runtime/task-resolver.js +201 -0
  97. package/dist/runtime/task-resolver.js.map +1 -0
  98. package/package.json +16 -9
  99. package/dist/agent/rules/constitution/GEMINI.location.md +0 -32
  100. package/dist/core/context/manager.js.map +0 -1
  101. package/dist/core/index.js +0 -2
  102. package/dist/core/index.js.map +0 -1
  103. package/dist/core/mapping/resolver.js.map +0 -1
  104. package/dist/core/migration/backup.js.map +0 -1
  105. package/dist/core/migration/detector.js.map +0 -1
  106. package/dist/core/migration/transformer.js.map +0 -1
  107. package/dist/core/utils/backup.js.map +0 -1
  108. package/dist/extension/extension.js +0 -6
  109. package/dist/extension/extension.js.map +0 -1
  110. package/dist/extension/views/index.js +0 -2
  111. package/dist/extension/views/index.js.map +0 -1
  112. package/dist/extension/views/main-view.js +0 -53
  113. package/dist/extension/views/main-view.js.map +0 -1
  114. package/media/agent-chat.svg +0 -20
  115. /package/dist/{core → infrastructure}/migration/backup.js +0 -0
  116. /package/dist/{core → infrastructure}/migration/detector.js +0 -0
  117. /package/dist/{core → infrastructure}/migration/transformer.js +0 -0
  118. /package/dist/{core → infrastructure}/utils/backup.js +0 -0
package/README.es.md CHANGED
@@ -11,8 +11,9 @@
11
11
  ## ✨ Características Principales
12
12
 
13
13
  - **Protocolo AHRP (Agentic Handover & Reasoning Protocol)**: Impone un flujo estricto de Triple-Puerta para cada tarea (Activación, Aprobación de Razonamiento y Aceptación de Resultados).
14
+ - **Gobernanza de Runtime y MCP**: Integración profunda con un servidor MCP para seguimiento de ciclos de vida, validación de puertas y logs a prueba de manipulaciones.
15
+ - **Skills Agénticos**: Capacidades modulares para los agentes, incluyendo habilidades de gobernanza localizadas (ej: `skill.runtime-governance`).
14
16
  - **Arquitectura local**: Copia las reglas y workflows del core dentro de `.agent/` para evitar dependencias de acceso continuado a `node_modules`.
15
- - **Gobernanza de Tolerancia Cero**: Penalizaciones automáticas de rendimiento por violaciones del protocolo.
16
17
  - **Independiente y Portátil**: Funciona en cualquier proyecto, siempre que el agente del IDE pueda leer archivos Markdown.
17
18
 
18
19
  ## 📦 Instalación
@@ -40,28 +41,96 @@ Inicializa el sistema agéntico en el directorio actual.
40
41
  npx agentic-workflow init
41
42
  ```
42
43
 
43
- ### `create <role|workflow> <name>`
44
- Genera el andamiaje (scaffolding) para un nuevo componente personalizado.
44
+ ### `create <role|workflow|skill> <name>`
45
+ Genera el andamiaje (scaffolding) para un nuevo componente específico del proyecto.
45
46
  - **role**: Crea un nuevo rol de agente con reglas de identificación obligatorias.
46
47
  - **workflow**: Crea una plantilla de ciclo de trabajo personalizado.
48
+ - **skill**: Crea una nueva habilidad modular con su propia plantilla `SKILL.md`.
47
49
  ```bash
48
50
  npx agentic-workflow create role neo
49
51
  ```
50
52
 
51
53
  ### `restore`
52
- Recupera la configuración de `.agent/` desde una copia de seguridad previa.
53
- - Los backups se almacenan como `.agent.backup_<timestamp>` en la raíz del proyecto.
54
- - Permite seleccionar versiones antes de un cambio destructivo.
54
+ Recuepra la configuración de `.agent/` desde una copia de seguridad previa.
55
55
  ```bash
56
56
  npx agentic-workflow restore
57
57
  ```
58
58
 
59
+ ### `clean`
60
+ Elimina archivos de configuración temporales o heredados (ej: configuraciones MCP obsoletas).
61
+ ```bash
62
+ npx agentic-workflow clean
63
+ ```
64
+
65
+ ### `mcp`
66
+ Inicia el servidor local del Runtime MCP (modo stdio).
67
+ ```bash
68
+ npx agentic-workflow mcp
69
+ ```
70
+
71
+ ### `register-mcp`
72
+ Registra automáticamente el servidor local en la configuración de Antigravity/Gemini.
73
+ ```bash
74
+ npx agentic-workflow register-mcp
75
+ ```
76
+
77
+ ## 📦 Instalación y Registro MCP
78
+
79
+ ### Instalar y Ejecutar
80
+ Instalación global:
81
+ ```bash
82
+ npm install -g @christianmaf80/agentic-workflow
83
+ agentic-workflow mcp
84
+ ```
85
+
86
+ Con `npx` (sin instalación global):
87
+ ```bash
88
+ npx agentic-workflow mcp
89
+ ```
90
+
91
+ ### Registrar o Actualizar Cliente MCP
92
+ Registrar (Antigravity/Gemini o Codex CLI si está presente):
93
+ ```bash
94
+ npx agentic-workflow register-mcp
95
+ ```
96
+
97
+ Si necesitas actualizar el registro en Codex, elimina el bloque
98
+ `[mcp_servers.agentic-workflow]` de `~/.codex/config.toml` y vuelve
99
+ a ejecutar `register-mcp`. En Antigravity se actualiza en el lugar.
100
+
101
+ ### Parar y Logs
102
+ Detén el servidor MCP con `Ctrl+C`. Los logs del runtime se escriben en `agentic-runtime.log`.
103
+
104
+ ## ⚙️ Configuración Avanzada
105
+
106
+ ### Integración de Runtime MCP
107
+ El sistema utiliza un servidor MCP para rastrear el estado del flujo. Para conectarlo con tu asistente de IDE:
108
+ 1. Ejecuta `npx agentic-workflow register-mcp`.
109
+ 2. Asegúrate de que `mcp_config.json` apunte al binario local del CLI.
110
+ 3. Los logs de ejecución se guardan en `agentic-runtime.log` para auditoría y depuración.
111
+
59
112
  ## 🧠 Conceptos Core
60
113
 
61
114
  ### Ciclos de Vida
62
115
  El framework soporta dos flujos principales según la complejidad de la tarea:
63
- 1. **Ciclo de Vida Largo (9 Fases)**: Para funcionalidades complejas que requieren Investigación, Análisis, Planificación y Revisión Arquitectónica formal.
64
- 2. **Ciclo de Vida Corto (3 Fases)**: Para correcciones rápidas o actualizaciones simples, fusionando Aceptación, Implementación y Cierre.
116
+
117
+ #### 1. Ciclo de Vida Largo (9 Fases)
118
+ Diseñado para funcionalidades complejas, cambios arquitectónicos o tareas con alto riesgo. Garantiza el máximo razonamiento antes de escribir una sola línea de código.
119
+ - **Fase 0: Criterios de Aceptación**: Elimina la ambigüedad definiendo exactamente qué significa el éxito.
120
+ - **Fase 1: Investigación**: Recopilación de contexto. Necesaria para entender el código existente o APIs externas.
121
+ - **Fase 2: Análisis**: Evaluación de impacto. Identifica riesgos y restricciones arquitectónicas.
122
+ - **Fase 3: Planificación**: Plan de implementación detallado. Crucial para la alineación con el desarrollador.
123
+ - **Fase 4: Implementación**: El proceso de codificación propiamente dicho.
124
+ - **Fase 5: Verificación**: Pruebas rigurosas y validación de los cambios realizados.
125
+ - **Fase 6: Aceptación de Resultados**: Firma final del desarrollador sobre el valor entregado.
126
+ - **Fase 7: Evaluación**: Retrospectiva sobre el desempeño del agente y eficiencia del proceso.
127
+ - **Fase 8: Commit & Push**: Persistencia segura de los cambios en el repositorio.
128
+
129
+ #### 2. Ciclo de Vida Corto (3 Fases)
130
+ Optimizado para correcciones rápidas, actualizaciones simples de documentación o cambios de bajo riesgo.
131
+ - **Fase 1: Brief**: Fusiona Aceptación, Análisis y Planificación en un solo paso para mayor agilidad.
132
+ - **Fase 2: Implementación**: Codificación y verificación combinadas.
133
+ - **Fase 3: Cierre**: Aceptación de resultados y limpieza final.
65
134
 
66
135
  ### Protocolo AHRP
67
136
  Cada tarea de un agente sigue el **Protocolo de Traspaso y Razonamiento Agéntico**:
@@ -72,12 +141,14 @@ Cada tarea de un agente sigue el **Protocolo de Traspaso y Razonamiento Agéntic
72
141
  ### Arquitectura por Instalación
73
142
  Para garantizar la estabilidad, la lógica central del framework (reglas y workflows) se instala dentro de la carpeta `.agent` del proyecto. Esto ofrece una copia local limpia que se puede extender sin tocar el paquete publicado.
74
143
 
75
- ## ⚖️ Gobernanza
144
+ ### Sistema de Indexación por Dominios
145
+ El sistema utiliza una **Arquitectura de Indexación en Cascada** para una trazabilidad absoluta:
146
+ 1. **Root Index** (`.agent/index.md`): Declara los puntos de entrada para todos los dominios del sistema (reglas, workflows, templates, skills, artefactos).
147
+ 2. **Índices de Dominio**: Cada carpeta contiene su propio `index.md` donde se asignan **alias** a los archivos.
148
+ 3. **Modelo de Referencia**: Los agentes nunca utilizan rutas absolutas. Resuelven las referencias a través del sistema de alias (ej: `skill.runtime-governance` → `.agent/skills/runtime-governance/SKILL.md`), lo que garantiza que la lógica se pueda mover o actualizar sin romper los flujos de trabajo.
76
149
 
77
- Este framework se basa en el principio de **Máxima Disciplina**. Los agentes deben:
78
- 1. Identificarse con un prefijo obligatorio.
79
- 2. Enviar un plan de razonamiento antes de cualquier modificación.
80
- 3. Obtener la aprobación explícita del desarrollador (`SI`) para cada transición.
150
+ ### Responsabilidad en Runtime
151
+ Todas las transiciones de ciclo de vida se registran a través de un Runtime MCP dedicado. Las acciones realizadas sin una "Huella de Gobernanza" correspondiente (logs de MCP) se consideran inválidas y están sujetas a reversión.
81
152
 
82
153
  ## 📄 Licencia
83
154
 
package/README.md CHANGED
@@ -11,8 +11,9 @@
11
11
  ## ✨ Key Features
12
12
 
13
13
  - **AHRP (Agentic Handover & Reasoning Protocol)**: Enforces a strict Triple-Gate flow for every task (Activation, Reasoning Approval, and Results Acceptance).
14
+ - **Runtime Governance & MCP**: Deep integration with an MCP server for lifecycle tracking, gate validation, and tamper-proof logging.
15
+ - **Agentic Skills**: Modular capabilities for agents, including localized and specialized governance skills (e.g., `skill.runtime-governance`).
14
16
  - **Local Core Snapshot**: Copies core rules and workflows into `.agent/` so runtime no longer depends on `node_modules` access.
15
- - **Zero-Tolerance Governance**: Automatic performance penalties for protocol violations.
16
17
  - **Standalone & Portable**: Works in any project provided the IDE agent can read Markdown files.
17
18
 
18
19
  ## 📦 Installation
@@ -40,28 +41,96 @@ Initializes the agentic system in the current directory.
40
41
  npx agentic-workflow init
41
42
  ```
42
43
 
43
- ### `create <role|workflow> <name>`
44
- Scaffolds a new custom component.
44
+ ### `create <role|workflow|skill> <name>`
45
+ Scaffolds a new project-specific component.
45
46
  - **role**: Creates a new agent role with mandatory identification rules.
46
47
  - **workflow**: Creates a custom work cycle template.
48
+ - **skill**: Creates a new modular skill with its own `SKILL.md` template.
47
49
  ```bash
48
50
  npx agentic-workflow create role neo
49
51
  ```
50
52
 
51
53
  ### `restore`
52
54
  Recovers the `.agent/` configuration from a previous backup.
53
- - Backups are stored as `.agent.backup_<timestamp>` in the project root.
54
- - Allows selecting versions before a destructive change.
55
55
  ```bash
56
56
  npx agentic-workflow restore
57
57
  ```
58
58
 
59
+ ### `clean`
60
+ Removes legacy or temporary configuration files (e.g., outdated MCP setups).
61
+ ```bash
62
+ npx agentic-workflow clean
63
+ ```
64
+
65
+ ### `mcp`
66
+ Starts the local MCP Runtime server (stdio mode).
67
+ ```bash
68
+ npx agentic-workflow mcp
69
+ ```
70
+
71
+ ### `register-mcp`
72
+ Automatically registers the local server in the Antigravity/Gemini config.
73
+ ```bash
74
+ npx agentic-workflow register-mcp
75
+ ```
76
+
77
+ ## 📦 Install and MCP Registration
78
+
79
+ ### Install and Run
80
+ Global install:
81
+ ```bash
82
+ npm install -g @christianmaf80/agentic-workflow
83
+ agentic-workflow mcp
84
+ ```
85
+
86
+ With `npx` (no global install):
87
+ ```bash
88
+ npx agentic-workflow mcp
89
+ ```
90
+
91
+ ### Register or Update MCP Client
92
+ Register (Antigravity/Gemini or Codex CLI if present):
93
+ ```bash
94
+ npx agentic-workflow register-mcp
95
+ ```
96
+
97
+ If you need to update a Codex registration, remove the existing
98
+ `[mcp_servers.agentic-workflow]` block from `~/.codex/config.toml`,
99
+ then run `register-mcp` again. Antigravity updates in place.
100
+
101
+ ### Stop and Logs
102
+ Stop the MCP server with `Ctrl+C`. Runtime logs are written to `agentic-runtime.log`.
103
+
104
+ ## ⚙️ Advanced Configuration
105
+
106
+ ### MCP Runtime Integration
107
+ The system relies on an MCP server to track the workflow state. To connect it with your IDE assistant (like Antigravity):
108
+ 1. Run `npx agentic-workflow register-mcp`.
109
+ 2. Ensure `mcp_config.json` (or equivalent) points to the local CLI binary.
110
+ 3. The Runtime logs are stored in `agentic-runtime.log` for debugging.
111
+
59
112
  ## 🧠 Core Concepts
60
113
 
61
114
  ### Lifecycles
62
115
  The framework supports two main workflows depending on task complexity:
63
- 1. **Long Lifecycle (9 Phases)**: For complex features requiring Research, Analysis, Planning, and formal Architectural Review.
64
- 2. **Short Lifecycle (3 Phases)**: For quick fixes or simple updates, merging Acceptance, Implementation, and Closure.
116
+
117
+ #### 1. Long Lifecycle (9 Phases)
118
+ Designed for complex features, architectural changes, or tasks with high risk. It ensures maximum reasoning before a single line of code is written.
119
+ - **Phase 0: Acceptance Criteria**: Eliminates ambiguity by defining exactly what success looks like.
120
+ - **Phase 1: Research**: Context gathering. Necessary to understand existing code or external APIs.
121
+ - **Phase 2: Analysis**: Impact evaluation. Identifies risks and architectural constraints.
122
+ - **Phase 3: Planning**: Detailed implementation plan. Crucial for developer alignment before execution.
123
+ - **Phase 4: Implementation**: The actual coding process.
124
+ - **Phase 5: Verification**: Rigorous testing and validation of the implemented changes.
125
+ - **Phase 6: Results Acceptance**: Final developer sign-off on the delivered value.
126
+ - **Phase 7: Evaluation**: Retrospective on the agent's performance and process efficiency.
127
+ - **Phase 8: Commit & Push**: Safely persisting the changes to the repository.
128
+
129
+ #### 2. Short Lifecycle (3 Phases)
130
+ Optimized for quick fixes, simple documentation updates, or low-risk changes.
131
+ - **Phase 1: Brief**: Merges Acceptance, Analysis, and Planning into a single step for speed.
132
+ - **Phase 2: Implementation**: Combined coding and verification.
133
+ - **Phase 3: Closure**: Results acceptance and final cleanup.
65
134
 
66
135
  ### AHRP Protocol
67
136
  Every agent task follows the **Agentic Handover & Reasoning Protocol**:
@@ -72,12 +141,14 @@ Every agent task follows the **Agentic Handover & Reasoning Protocol**:
72
141
  ### Architecture by Install
73
142
  To ensure stability, the framework's core logic (rules and workflows) is installed into your project's `.agent` folder. This provides a clean, local copy that can be extended without touching the published package.
74
143
 
75
- ## ⚖️ Governance
144
+ ### Domain Indexing System
145
+ The system uses a **Cascading Indexing Architecture** for absolute traceability:
146
+ 1. **Root Index** (`.agent/index.md`): Declares the entry points for all system domains (rules, workflows, templates, skills, artifacts).
147
+ 2. **Domain Indexes**: Each folder contains its own `index.md` where files are assigned **aliases**.
148
+ 3. **Reference Model**: Agents never use absolute paths. They resolve references through the alias system (e.g., `skill.runtime-governance` → `.agent/skills/runtime-governance/SKILL.md`), ensuring that logic can be moved or updated without breaking workflows.
76
149
 
77
- This framework is built on the principle of **Maximum Discipline**. Agents are required to:
78
- 1. Identify themselves with a mandatory prefix.
79
- 2. Submit a reasoning plan before any modification.
80
- 3. Obtain explicit developer approval (`YES`) for every transition.
150
+ ### Runtime Accountability
151
+ All lifecycle transitions are recorded through a dedicated MCP Runtime. Actions performed without a corresponding "Governance Trace" (MCP logs) are considered invalid and subject to reversal.
81
152
 
82
153
  ## 📄 License
83
154
 
@@ -22,6 +22,7 @@ The project uses GitHub Actions for automated releases to npm.
22
22
  ### Manual Steps for Release
23
23
  1. Update version: `npm version prerelease --preid=beta` (or appropriate semver command).
24
24
  2. Update `CHANGELOG.md`.
25
- 3. (Optional) Generate local package: `npm run package`. The `.tgz` file will be moved to `.backups/npm-packages/`.
26
- 4. Create a branch: `git checkout -b ci/publish-beta-x.x.x`.
27
- 5. Push and create PR.
25
+ 3. Build the distributable: `npm run build` (generates `dist/`).
26
+ 4. (Optional) Generate local package: `npm run package`. The `.tgz` file will be moved to `.backups/npm-packages/`.
27
+ 5. Create a branch: `git checkout -b ci/publish-beta-x.x.x`.
28
+ 6. Push and create PR.
package/bin/cli.js CHANGED
@@ -1,38 +1,59 @@
1
1
  #!/usr/bin/env node
2
2
  import { Command } from 'commander';
3
+ import { readFileSync } from 'fs';
4
+ import { fileURLToPath } from 'url';
5
+ import { dirname, join } from 'path';
3
6
  import { initCommand } from '../dist/cli/commands/init.js';
4
7
  import { createCommand } from '../dist/cli/commands/create.js';
5
8
  import { restoreCommand } from '../dist/cli/commands/restore.js';
6
9
  import { cleanCommand } from '../dist/cli/commands/clean.js';
10
+ import { mcpCommand } from '../dist/cli/commands/mcp.js';
11
+ import { registerMcpCommand } from '../dist/cli/commands/register-mcp.js';
12
+
13
+ const __filename = fileURLToPath(import.meta.url);
14
+ const __dirname = dirname(__filename);
15
+ const pkg = JSON.parse(readFileSync(join(__dirname, '..', 'package.json'), 'utf-8'));
7
16
 
8
17
  const program = new Command();
9
18
 
10
19
  program
11
- .name('agentic-workflow')
12
- .description('Portable agentic orchestration system')
13
- .version('1.0.0');
20
+ .name('agentic-workflow')
21
+ .description('Portable agentic orchestration system')
22
+ .version(pkg.version);
23
+
24
+ program
25
+ .command('init')
26
+ .description('Initialize the agentic system in the current directory')
27
+ .option('--non-interactive', 'Run without prompts (assume YES)')
28
+ .option('--start-mcp', 'Start MCP server after initialization (foreground)')
29
+ .action((options) => initCommand(options));
14
30
 
15
31
  program
16
- .command('init')
17
- .description('Initialize the agentic system in the current directory')
18
- .option('--non-interactive', 'Run without prompts (assume YES)')
19
- .action((options) => initCommand(options));
32
+ .command('create')
33
+ .argument('<type>', 'The type of element to create (role, workflow, skill)')
34
+ .argument('<name>', 'The name for the new element')
35
+ .description('Scaffold a new project-specific element')
36
+ .action(createCommand);
20
37
 
21
38
  program
22
- .command('create')
23
- .argument('<type>', 'The type of element to create (role, workflow)')
24
- .argument('<name>', 'The name for the new element')
25
- .description('Scaffold a new project-specific element')
26
- .action(createCommand);
39
+ .command('restore')
40
+ .description('Restore the agentic system from a backup')
41
+ .action(restoreCommand);
27
42
 
28
43
  program
29
- .command('restore')
30
- .description('Restore the agentic system from a backup')
31
- .action(restoreCommand);
44
+ .command('clean')
45
+ .description('Remove legacy configuration files (e.g. MCP)')
46
+ .action(cleanCommand);
32
47
 
33
48
  program
34
- .command('clean')
35
- .description('Remove legacy configuration files (e.g. MCP)')
36
- .action(cleanCommand);
49
+ .command('mcp')
50
+ .description('Start MCP runtime server (stdio)')
51
+ .action(() => mcpCommand());
52
+
53
+ program
54
+ .command('register-mcp')
55
+ .description('Register MCP server in Gemini CLI (Antigravity) and/or Codex CLI')
56
+ .action(() => registerMcpCommand());
37
57
 
38
58
  program.parse();
59
+
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: acceptance
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🏛️ **architect-agent**: Acceptance criteria definidos para scaffold vscode-agentinc.
2
8
 
3
9
  # Acceptance Criteria — 1-scaffold-extension-vscode-agentinc
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: agent-scores
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🏛️ **architect-agent**: Actualizacion de puntuaciones por agente.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: 1-dev-agent-scaffold
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🧑‍💻 **dev-agent**: Tarea asignada para generar scaffold oficial.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: 2-dev-agent-manifest-command
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🧑‍💻 **dev-agent**: Tarea asignada para revisar manifesto y comando minimo.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: 3-dev-agent-marketplace-evidence
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🧑‍💻 **dev-agent**: Tarea asignada para documentar evidencia de Marketplace.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: 4-qa-agent-verify-build
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🛡️ **qa-agent**: Tarea asignada para verificacion de build y comando.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: analysis
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🏛️ **architect-agent**: Analisis inicial para scaffold de extension VS Code.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: review
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🏛️ **architect-agent**: Revision de implementacion de fase 4.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: metrics
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🏛️ **architect-agent**: Metricas de evaluacion de agentes.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: plan
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🏛️ **architect-agent**: Plan de implementacion para scaffold VS Code.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: research
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🔍 **researcher-agent**: Informe de investigacion preparado para la fase 1.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: results-acceptance
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🏛️ **architect-agent**: Informe final de resultados preparado.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: task
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  # Task (Template)
2
8
 
3
9
  ## Identificacion
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: verification
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🛡️ **qa-agent**: Informe de verificacion de scaffold VS Code.
2
8
 
3
9
  ---
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: acceptance
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🏛️ **architect-agent**: Acceptance criteria definidos para el scaffolding del chat AI en la extension de VS Code.
2
8
 
3
9
  # Acceptance Criteria — 2-scaffold-vscode-chat-ai-panel
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: task
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  # Task (Template)
2
8
 
3
9
  ## Identificación
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: acceptance
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  🏛️ **architect-agent**: Acceptance criteria definidos para nuevo proyecto vscode-agentic.
2
8
 
3
9
  # Acceptance Criteria — 3-new-vscode-agentic-activitybar-chat
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: task
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  # Task (Template)
2
8
 
3
9
  ## Identificación
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: acceptance
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  # Acceptance Criteria — 4-copiar-estructura-agentic-cliente
2
8
 
3
9
  🏛️ **architect-agent**: Consolidando criterios de aceptacion para copia completa de `.agent` en cliente.
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: implementation
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  # Informe de Implementacion — 4-copiar-estructura-agentic-cliente
2
8
 
3
9
  🏛️ **architect-agent**: Implementacion verificada para copia completa de `.agent` en cliente.
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: acceptance
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  # Acceptance Criteria — 5-reestructurar-src-para-extension-vscode
2
8
 
3
9
  🏛️ **architect-agent**: Definición de criterios de aceptación para la reestructuración de src y scaffolding de extensión VSCode.
@@ -64,7 +64,7 @@ execution:
64
64
 
65
65
  ### Cambios realizados
66
66
  - Creado directorio `src/agentic-system-structure`.
67
- - Movido `src/cli`, `src/core`, `src/rules`, `src/templates`, `src/workflows`, `src/artifacts`, `src/index.md` a la nueva ubicación.
67
+ - Movido `src/cli`, `src/infrastructure`, `src/rules`, `src/templates`, `src/workflows`, `src/artifacts`, `src/index.md` a la nueva ubicación.
68
68
 
69
69
  ### Decisiones técnicas
70
70
  - Uso de `mv` con múltiples argumentos para atomizar la operación.
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: task
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  # Task: Reestructurar src para Extensión VSCode
2
8
 
3
9
  ## Identificación
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: task
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  # Task: Release Beta 1.18.0-beta.11
2
8
 
3
9
  ## Identificación
@@ -1,3 +1,9 @@
1
+ ---
2
+ kind: artifact
3
+ name: init
4
+ source: agentic-system-structure
5
+ ---
6
+
1
7
  # init bootstrap
2
8
 
3
9
  - command: init
@@ -5,9 +11,8 @@
5
11
  - constitution.loaded.in_context: true
6
12
 
7
13
  ## Constitution (load order)
8
- 1. .agent/rules/constitution/GEMINI.location.md
9
- 2. .agent/rules/constitution/clean-code.md
10
- 3. .agent/rules/constitution/agents-behavior.md
14
+ 1. .agent/rules/constitution/clean-code.md
15
+ 2. .agent/rules/constitution/agents-behavior.md
11
16
 
12
17
  ```yaml
13
18
  bootstrap:
@@ -16,7 +21,6 @@ roles:
16
21
  architect: architect-agent
17
22
  constitution:
18
23
  loaded:
19
- - .agent/rules/constitution/GEMINI.location.md
20
24
  - .agent/rules/constitution/clean-code.md
21
25
  - .agent/rules/constitution/agents-behavior.md
22
26
  language: