@christianmaf80/agentic-workflow 1.24.0-beta.3 → 1.25.0-beta.3

package/dist/agent/templates/review.md

@@ -9,101 +9,101 @@ related_plan: .agent/artifacts/<taskId>-<taskTitle>/plan.md
 
 # Architectural Implementation Review — <taskId>-<taskTitle>
 
-## Identificacion del agente (OBLIGATORIA)
-Primera linea del documento:
-`<icono> **<nombre-agente>**: <mensaje>`
+## Agent Identification (MANDATORY)
+First line of the document:
+`<icon> **<agent-name>**: <message>`
 
-## 1. Resumen de la revisión
-- **Objetivo del review**  
-  Verificar que la implementación ejecutada cumple el **plan de implementación aprobado** sin desviaciones no autorizadas.
+## 1. Review Summary
+- **Review objective**  
+  Verify that the executed implementation meets the **approved implementation plan** without unauthorized deviations.
 
-- **Resultado global**  
-  - Estado: ☐ APROBADO ☐ RECHAZADO
-  - Fecha de revisión:
-  - Arquitecto responsable:
+- **Overall result**  
+  - Status: ☐ APPROVED ☐ REJECTED
+  - Review date:
+  - Responsible architect:
 
 ---
 
-## 2. Verificación contra el plan de implementación
-Revisión directa y trazable **plan → implementación**.
+## 2. Verification Against the Implementation Plan
+Direct and traceable review **plan → implementation**.
 
-### 2.1 Pasos del plan
-Para **cada paso definido en `plan.md`**:
+### 2.1 Plan Steps
+For **each step defined in `plan.md`**:
 
-| Paso del plan | Estado | Evidencia | Observaciones |
-|---------------|--------|-----------|---------------|
-| Paso 1 | ☐ OK ☐ NO OK | refs / commits / artefactos | |
-| Paso 2 | ☐ OK ☐ NO OK | | |
+| Plan Step | Status | Evidence | Observations |
+|-----------|--------|----------|-------------|
+| Step 1 | ☐ OK ☐ NOT OK | refs / commits / artifacts | |
+| Step 2 | ☐ OK ☐ NOT OK | | |
 
-> Todos los pasos **DEBEN** estar en estado **OK** para aprobar la fase.
+> All steps **MUST** be in **OK** status to approve the phase.
 
 ---
 
-## 3. Subtareas por agente
-Revisión de las implementaciones individuales.
+## 3. Subtasks by Agent
+Review of individual implementations.
 
-### Agente: `<agent-name>`
+### Agent: `<agent-name>`
 - **Subtask document**:
   - `.agent/artifacts/<taskId>-<taskTitle>/<agent>/subtask-implementation.md`
-- **Evaluación**:
-  - ☐ Cumple el plan
-  - ☐ Desviaciones detectadas (detallar abajo)
+- **Evaluation**:
+  - ☐ Meets the plan
+  - ☐ Deviations detected (detail below)
 
-**Notas del arquitecto**
-- Cambios realizados:
-- Decisiones técnicas:
-- Coherencia con el resto del sistema:
+**Architect's Notes**
+- Changes made:
+- Technical decisions:
+- Coherence with the rest of the system:
 
-(Repetir sección por cada agente participante)
+(Repeat section for each participating agent)
 
 ---
 
-## 4. Acceptance Criteria (impacto)
-Verificación de que la implementación **no rompe** los acceptance criteria definidos.
+## 4. Acceptance Criteria (impact)
+Verification that the implementation **does not break** the defined acceptance criteria.
 
-- ☐ Todos los AC siguen siendo válidos
-- ☐ Algún AC requiere revisión (detallar)
+- ☐ All ACs remain valid
+- ☐ Some AC requires review (detail)
 
-**Observaciones**
-- AC afectados:
-- Motivo:
+**Observations**
+- Affected ACs:
+- Reason:
 
 ---
 
-## 5. Coherencia arquitectónica
-Evaluación global del sistema tras la implementación.
+## 5. Architectural Coherence
+Overall system evaluation after implementation.
 
-- ☐ Respeta arquitectura del proyecto
-- ☐ Respeta clean code
-- ☐ No introduce deuda técnica significativa
-- ☐ Mantiene compatibilidad esperada (multi-browser si aplica)
+- ☐ Respects project architecture
+- ☐ Respects clean code
+- ☐ Does not introduce significant technical debt
+- ☐ Maintains expected compatibility (multi-browser if applicable)
 
-**Observaciones arquitectónicas**
-- Impacto en estructura:
-- Impacto en componentes:
-- Riesgos introducidos:
+**Architectural Observations**
+- Structural impact:
+- Component impact:
+- Introduced risks:
 
 ---
 
-## 6. Desviaciones del plan
-Registro explícito de desviaciones (si existen).
+## 6. Plan Deviations
+Explicit record of deviations (if any).
 
-- **Desviación**
-  - Descripción:
-  - Justificación:
-  - ¿Estaba prevista en el plan? ☐ Sí ☐ No
-  - ¿Requiere replanificación? ☐ Sí ☐ No
+- **Deviation**
+  - Description:
+  - Justification:
+  - Was it planned? ☐ Yes ☐ No
+  - Does it require replanning? ☐ Yes ☐ No
 
-(Si no hay desviaciones, indicar explícitamente: “Sin desviaciones detectadas”).
+(If no deviations, indicate explicitly: "No deviations detected.")
 
 ---
 
-## 7. Decisión final del arquitecto
-Decisión **severa y binaria**.
+## 7. Architect's Final Decision
+**Strict and binary** decision.
 
 ```yaml
 decision:
   architect:
-    result: APROBADO | RECHAZADO
+    result: APPROVED | REJECTED
     date: <ISO-8601>
-    comments: <opcional>
+    comments: <optional>

package/dist/agent/templates/subtask-implementation.md

@@ -9,54 +9,54 @@ subtask_id: <id>
 ---
 
 > [!WARNING]
-> **@deprecated**: Este template está obsoleto. Usar `templates.agent_task` para nuevas tareas.
+> **@deprecated**: This template is obsolete. Use `templates.agent_task` for new tasks.
 
 # Subtask Implementation Report — <taskId>-<taskTitle> — <agent> — <subtask_id>
 
-## 1. Contexto y alcance
-- Descripcion precisa de la subtask
-- Objetivo especifico
-- Relacion con el plan (referencia a paso exacto)
+## 1. Context and Scope
+- Precise description of the subtask
+- Specific objective
+- Relationship with the plan (reference to exact step)
 
 ---
 
-## 2. Cambios realizados (detallado)
-- Archivos tocados (lista completa)
-- Cambios por archivo (resumen por archivo)
-- APIs/contratos afectados
-- Nuevas funciones/clases/constantes
+## 2. Changes Made (detailed)
+- Files touched (complete list)
+- Changes per file (summary per file)
+- APIs/contracts affected
+- New functions/classes/constants
 
 ---
 
-## 3. Decisiones tecnicas
-- Decisiones clave y su justificacion
-- Alternativas consideradas y por que se descartaron
-- Impacto en otros componentes (si aplica)
+## 3. Technical Decisions
+- Key decisions and their justification
+- Alternatives considered and why they were discarded
+- Impact on other components (if applicable)
 
 ---
 
-## 4. Testing y evidencia
-- Tests ejecutados (comando y alcance)
-- Resultados (pass/fail)
-- Evidencias (logs, capturas, reportes)
+## 4. Testing and Evidence
+- Tests executed (command and scope)
+- Results (pass/fail)
+- Evidence (logs, screenshots, reports)
 
 ---
 
-## 5. Desviaciones del plan
-- Desviaciones detectadas
-- Motivo
-- Accion correctiva o deuda registrada
+## 5. Plan Deviations
+- Detected deviations
+- Reason
+- Corrective action or registered debt
 
 ---
 
-## 6. Riesgos y validaciones pendientes
-- Riesgos abiertos
-- Validaciones pendientes
+## 6. Risks and Pending Validations
+- Open risks
+- Pending validations
 
 ---
 
 ## 7. Checklist
-- [ ] Subtask completada
-- [ ] Cambios documentados
-- [ ] Testing documentado
-- [ ] Lista para revision de arquitecto
+- [ ] Subtask completed
+- [ ] Changes documented
+- [ ] Testing documented
+- [ ] Ready for architect review

package/dist/agent/templates/supplemental-report.md

@@ -1,9 +1,3 @@
----
-kind: template
-name: supplemental-report
-source: agentic-system-structure
----
-
 # Supplemental Report (Template)
 
 ## Identificacion

package/dist/agent/templates/task-metrics.md

@@ -8,31 +8,31 @@ related_task: <taskId>-<taskTitle>
 
 # Task Metrics — <taskId>-<taskTitle>
 
-## Identificacion del agente (OBLIGATORIA)
-Primera linea del documento:
-`<icono> **<nombre-agente>**: <mensaje>`
+## Agent Identification (MANDATORY)
+First line of the document:
+`<icon> **<agent-name>**: <message>`
 
-## 1. Agentes evaluados
+## 1. Evaluated Agents
 - Agent A
 - Agent B
 
 ---
 
-## 2. Puntuacion por agente (0-10)
+## 2. Score per Agent (0-10)
 - **Agent A**: score
-  - Justificacion
+  - Justification
 - **Agent B**: score
-  - Justificacion
+  - Justification
 
 ---
 
-## 3. Puntuacion global de la tarea
-- Promedio ponderado: score
-- Observaciones
+## 3. Overall Task Score
+- Weighted average: score
+- Observations
 
 ---
 
-## 4. Validación del Desarrollador
-- Aprobado: [SI/NO]
-- Puntuación del desarrollador (0-5): 
-- Comentarios: 
+## 4. Developer Validation
+- Approved: [SI/NO]
+- Developer score (0-5): 
+- Comments: 

package/dist/agent/templates/task.md

@@ -7,25 +7,25 @@ strategy: {{task.strategy}}
 
 # Task (Template)
 
-## Identificación
+## Identification
 - id: {{task.id}}
 - title: {{task.title}}
 - scope: candidate | current
 - owner: architect-agent
 
-## Origen
+## Origin
 - created_from:
   - workflow: tasklifecycle
   - source: init / tasklifecycle
   - candidate_path: artifacts.candidate.task
 
-## Descripción de la tarea
+## Task Description
 {{task.description}}
 
-## Objetivo
+## Objective
 {{task.goal}}
 
-## Estado del ciclo de vida (FUENTE ÚNICA DE VERDAD)
+## Lifecycle State (SINGLE SOURCE OF TRUTH)
 
 ```yaml
 task:
@@ -109,18 +109,18 @@ task:
 
 ---
 
-## 2. Definición y Alcance (Contrato)
+## 2. Definition and Scope (Contract)
 - **Acceptance Criteria**: [acceptance.md](file:///{{task.acceptance_path}})
 - **Alias**: `task.acceptance`
 
 ---
 
-## Reglas contractuales
-- Este fichero es la **fuente única de verdad** del estado de la tarea.
-- El campo `task.phase.current` **SOLO puede ser modificado por `architect-agent`**.
-- El campo `task.lifecycle.phases.*` **SOLO puede ser marcado como completed por `architect-agent`**.
-- Una fase **NO puede marcarse como completed** si no es la fase actual.
-- El avance de fase requiere:
-  1. Marcar la fase actual como `completed: true`
-  2. Validación explícita del architect
-  3. Actualización de `task.phase.current` a la siguiente fase
+## Contractual Rules
+- This file is the **single source of truth** of the task state.
+- The `task.phase.current` field can **ONLY be modified by `architect-agent`**.
+- The `task.lifecycle.phases.*` field can **ONLY be marked as completed by `architect-agent`**.
+- A phase **CANNOT be marked as completed** if it is not the current phase.
+- Phase advancement requires:
+  1. Marking the current phase as `completed: true`
+  2. Explicit architect validation
+  3. Updating `task.phase.current` to the next phase

package/dist/agent/templates/todo-item.md

@@ -2,44 +2,44 @@
 artifact: todo_item
 owner: architect-agent
 status: open | in-progress | done | cancelled
-priority: alta | media | baja
+priority: high | medium | low
 ---
 
-# TODO: <título breve>
+# TODO: <short title>
 
-## Origen
-- **Detectado en tarea**: <taskId>-<taskTitle>
-- **Fase**: <phase donde se detectó>
-- **Fecha**: <ISO-8601>
-- **Agente**: <agente que lo detectó>
+## Origin
+- **Detected in task**: <taskId>-<taskTitle>
+- **Phase**: <phase where detected>
+- **Date**: <ISO-8601>
+- **Agent**: <agent that detected it>
 
-## Descripción
-<Descripción clara de la mejora propuesta>
+## Description
+<Clear description of the proposed improvement>
 
-## Justificación
-<Por qué es importante hacer este cambio>
+## Justification
+<Why it is important to make this change>
 
-## Impacto estimado
-- **Complejidad**: baja | media | alta
-- **Áreas afectadas**: <componentes/workflows/templates>
+## Estimated Impact
+- **Complexity**: low | medium | high
+- **Affected areas**: <components/workflows/templates>
 
-## Criterio de aceptación
-- [ ] <Condición verificable 1>
-- [ ] <Condición verificable 2>
+## Acceptance Criterion
+- [ ] <Verifiable condition 1>
+- [ ] <Verifiable condition 2>
 
-## Notas
-<Información adicional relevante>
+## Notes
+<Additional relevant information>
 
 ---
 
-## Historial
+## History
 ```yaml
 history:
   - action: created
     date: <ISO-8601>
-    by: <agente>
+    by: <agent>
   # - action: started | completed | cancelled
   #   date: <ISO-8601>
-  #   by: <agente>
-  #   task: <taskId donde se implementó>
+  #   by: <agent>
+  #   task: <taskId where implemented>
 ```

package/dist/agent/workflows/coding/coding-backend.md

@@ -0,0 +1,147 @@
+---
+id: workflow.coding.backend
+description: On-demand coding workflow for the Backend layer. Invoked by architect-agent during Phase 4 implementation.
+owner: backend
+version: 1.0.0
+severity: PERMANENT
+trigger:
+  commands: ["coding-backend"]
+blocking: true
+---
+
+# WORKFLOW: coding.backend
+
+## Input (REQUIRED)
+- Agent task file assigned by architect:
+  - `.agent/artifacts/<taskId>-<taskTitle>/agent-tasks/<N>-backend-<taskName>.md`
+- Constitution loaded:
+  - `constitution.backend` (MANDATORY)
+  - `constitution.clean_code` (MANDATORY)
+- Role activated:
+  - `roles.backend`
+
+> [!IMPORTANT]
+> **This is an on-demand workflow.** It is invoked by `architect-agent` during Phase 4 as part of the implementation plan. The architect defines the execution order of coding workflows.
+
+## Output (REQUIRED)
+- Implementation report using `templates.coding.layer_report`:
+  - Embedded in the agent task file under "Implementation Report"
+- All code changes passing compilation
+
+---
+
+## Objective (ONLY)
+- Implement the **backend layer** of the assigned task following `constitution.backend`.
+- Generate a detailed implementation report.
+- Present to developer for Gate approval.
+
+> This workflow **ONLY** implements backend logic.
+> This workflow **NEVER** imports `vscode` or DOM APIs.
+> This workflow **NEVER** communicates directly with View.
+
+---
+
+## Mandatory Steps
+
+### 0. Activate role
+- Activate `roles.backend` and use mandatory agent prefix in all messages.
+
+### 1. Verify inputs
+- Agent task file exists and has Input section completed by architect.
+- Constitution `constitution.backend` loaded.
+- Constitution `constitution.clean_code` loaded.
+- If missing → **FAIL**.
+
+### 2. Analyze the task
+- Read the agent task Input (objective, scope, dependencies).
+- Complete the "Reasoning" section of the agent task:
+  - Analyze objective
+  - Consider options
+  - Document decision and justification
+
+### 3. Implement
+- Write code following `constitution.backend`:
+  - **Extend AbstractServer** from `core/backend`.
+  - **No vscode imports** — logic must be IDE-decoupled.
+  - **Transport agnostic** — use abstract adapters.
+  - **Error handling** — return `{ error, code }`, no raw exceptions.
+  - **Response format** — strictly typed JSON.
+- Write code following `constitution.clean_code`.
+
+### 4. Self-validate
+- Verify all constitution rules are satisfied:
+  - [ ] Extends `AbstractServer` (if applicable)
+  - [ ] No `vscode` or `dom` imports
+  - [ ] Error handling via structured responses
+  - [ ] No direct View communication
+  - [ ] Clean code principles applied
+- Run compilation: `npm run compile`
+- If compilation fails → fix before proceeding.
+
+### 5. Generate implementation report
+- Complete the "Implementation Report" section using `templates.coding.layer_report`:
+  - **Who**: Agent identity and role
+  - **How**: Technical details, specifications, diagrams if needed
+  - **Why**: Justification and reasoning
+  - **Results**: What was achieved, compilation status
+  - **E2E Test Indications**: Scenarios for e2e testing
+
+### 6. Present to developer (Gate)
+- Present completed task with report to developer.
+- Request approval: **SI / NO**
+
+### 7. Register Gate
+```yaml
+approval:
+  developer:
+    decision: SI | NO
+    date: <ISO-8601>
+    comments: <optional>
+```
+
+### 8. Evaluate Gate
+- If `decision == SI` → go to **Step 9 (PASS)**.
+- If `decision == NO`:
+  - Mark task as `failed`.
+  - Define corrective actions.
+  - **Do NOT advance** until resolved.
+  - Go to **Step 10 (FAIL)**.
+
+### 9. PASS (only if Gate approved)
+- Mark agent task as `completed`.
+- Update agent task file:
+  ```yaml
+  execution:
+    status: completed
+    completed_at: <ISO-8601>
+  ```
+- Update the coding layer report with final status.
+- Return control to `architect-agent` for next workflow in the sequence.
+
+---
+
+## FAIL (MANDATORY)
+
+### 10. Declare workflow as NOT completed
+Cases:
+- Missing inputs or constitution.
+- Compilation failure not resolved.
+- Constitution violation detected.
+- Gate = NO without resolution.
+
+Actions:
+- Identify the failure point.
+- Define corrective actions.
+- Iterate until Gate PASS.
+
+---
+
+## Gate (REQUIRED)
+
+Requirements (all mandatory):
+1. Code compiles without errors.
+2. All `constitution.backend` rules are satisfied.
+3. All `constitution.clean_code` rules are satisfied.
+4. Implementation report is complete (all 5 sections).
+5. Developer Gate PASS (`decision == SI`).
+6. Agent task file starts with backend agent prefix.