@the-bearded-bear/claude-craft 4.0.2 → 4.0.3-next.db8034a
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/Dev/i18n/de/Common/agents/ralph-conductor.md +46 -134
- package/Dev/i18n/de/Common/commands/ralph-run.md +45 -146
- package/Dev/i18n/en/Common/agents/ralph-conductor.md +89 -44
- package/Dev/i18n/en/Common/commands/ralph-run.md +137 -72
- package/Dev/i18n/es/Common/agents/ralph-conductor.md +48 -136
- package/Dev/i18n/es/Common/commands/ralph-run.md +51 -140
- package/Dev/i18n/fr/Common/agents/ralph-conductor.md +83 -133
- package/Dev/i18n/fr/Common/commands/ralph-run.md +131 -106
- package/Dev/i18n/pt/Common/agents/ralph-conductor.md +46 -134
- package/Dev/i18n/pt/Common/commands/ralph-run.md +52 -153
- package/Tools/Ralph/.ralph/hooks/pre-tool-context.sh +100 -0
- package/Tools/Ralph/.ralph/hooks/session-restore.sh +118 -0
- package/Tools/Ralph/.ralph/hooks/status-injector.sh +147 -0
- package/Tools/Ralph/.ralph/hooks/stop-dod-gate.sh +133 -0
- package/Tools/Ralph/README.md +308 -19
- package/Tools/Ralph/lib/circuit-breaker.sh +320 -13
- package/Tools/Ralph/lib/config-generator.sh +561 -0
- package/Tools/Ralph/lib/dashboard.sh +392 -0
- package/Tools/Ralph/lib/dod-templates.sh +335 -0
- package/Tools/Ralph/lib/dod-validator.sh +116 -0
- package/Tools/Ralph/lib/health-monitor.sh +416 -0
- package/Tools/Ralph/lib/hooks-generator.sh +337 -0
- package/Tools/Ralph/lib/metrics-exporter.sh +383 -0
- package/Tools/Ralph/lib/project-detector.sh +562 -0
- package/Tools/Ralph/lib/session.sh +196 -0
- package/Tools/Ralph/ralph.sh +182 -1
- package/Tools/Ralph/templates/dod/dotnet.yml +73 -0
- package/Tools/Ralph/templates/dod/flutter.yml +70 -0
- package/Tools/Ralph/templates/dod/generic.yml +49 -0
- package/Tools/Ralph/templates/dod/go.yml +82 -0
- package/Tools/Ralph/templates/dod/python.yml +73 -0
- package/Tools/Ralph/templates/dod/react.yml +73 -0
- package/Tools/Ralph/templates/dod/rust.yml +73 -0
- package/Tools/Ralph/templates/dod/symfony.yml +73 -0
- package/Tools/Ralph/templates/ralph.yml.template +115 -4
- package/Tools/i18n/ralph/de.sh +49 -0
- package/Tools/i18n/ralph/en.sh +49 -0
- package/Tools/i18n/ralph/es.sh +49 -0
- package/Tools/i18n/ralph/fr.sh +49 -0
- package/Tools/i18n/ralph/pt.sh +49 -0
- package/cli/index.js +11 -1
- package/package.json +1 -1
|
@@ -1,170 +1,81 @@
|
|
|
1
1
|
---
|
|
2
|
-
description: Ejecutar Claude en bucle continuo hasta completar tarea (Ralph Wiggum)
|
|
3
|
-
argument-hint: <descripcion-tarea> [--auto|--
|
|
2
|
+
description: Ejecutar Claude en bucle continuo hasta completar la tarea (Ralph Wiggum v2.0)
|
|
3
|
+
argument-hint: <descripcion-tarea> [--auto-detect|--init|--interactive]
|
|
4
4
|
---
|
|
5
5
|
|
|
6
|
-
# Ralph Run - Bucle Continuo de Agente IA
|
|
6
|
+
# Ralph Run - Bucle Continuo de Agente IA v2.0
|
|
7
7
|
|
|
8
|
-
|
|
8
|
+
Ejecuta Claude en un bucle continuo hasta que la tarea este completa o se cumplan los criterios de Definition of Done (DoD).
|
|
9
9
|
|
|
10
10
|
## Argumentos
|
|
11
11
|
|
|
12
12
|
**$ARGUMENTS**
|
|
13
13
|
|
|
14
14
|
- `<descripcion-tarea>`: La tarea para que Claude complete
|
|
15
|
-
- `--auto`:
|
|
16
|
-
- `--
|
|
15
|
+
- `--auto-detect`: Detectar automaticamente el tipo de proyecto y configurar DoD
|
|
16
|
+
- `--init`: Generar configuracion sin ejecutar
|
|
17
|
+
- `--interactive`: Asistente de configuracion interactivo
|
|
18
|
+
|
|
19
|
+
## Nuevas funcionalidades v2.0
|
|
20
|
+
|
|
21
|
+
| Funcionalidad | Descripcion |
|
|
22
|
+
|---------------|-------------|
|
|
23
|
+
| **Integracion Hooks** | Integracion bidireccional con Claude Code 2.1.23+ |
|
|
24
|
+
| **Auto-Deteccion** | Deteccion automatica del tipo de proyecto |
|
|
25
|
+
| **Dashboard** | Visualizacion en tiempo real con barra de progreso |
|
|
26
|
+
| **Export Metricas** | Metricas en formato JSON y Prometheus |
|
|
27
|
+
| **Circuit Breaker Adaptativo** | 5 perfiles con aprendizaje historico |
|
|
28
|
+
| **Monitor de Salud** | Deteccion de estancamiento, espiral de errores |
|
|
29
|
+
| **Templates DoD** | Templates preconfigurados para 8 tecnologias |
|
|
17
30
|
|
|
18
31
|
## Proceso
|
|
19
32
|
|
|
20
|
-
### 1. Inicializacion de
|
|
33
|
+
### 1. Inicializacion de sesion
|
|
21
34
|
|
|
22
|
-
1. **Verificar prerequisitos
|
|
23
|
-
|
|
24
|
-
|
|
25
|
-
- Inicializar directorio de sesion (`.ralph/`)
|
|
35
|
+
1. **Verificar prerequisitos**
|
|
36
|
+
2. **Detectar proyecto** (si `--auto-detect`)
|
|
37
|
+
3. **Cargar configuracion**
|
|
26
38
|
|
|
27
|
-
2.
|
|
28
|
-
- Leer `ralph.yml` o `.claude/ralph.yml`
|
|
29
|
-
- Establecer iteraciones max, timeouts, criterios DoD
|
|
30
|
-
|
|
31
|
-
### 2. Bucle Principal
|
|
32
|
-
|
|
33
|
-
```
|
|
34
|
-
┌─────────────────────────────────────────────────────────────┐
|
|
35
|
-
│ BUCLE RALPH │
|
|
36
|
-
│ │
|
|
37
|
-
│ while (iteraciones < max && !DoD_aprobado) { │
|
|
38
|
-
│ 1. Verificar disyuntor │
|
|
39
|
-
│ 2. Invocar Claude con prompt actual │
|
|
40
|
-
│ 3. Procesar salida │
|
|
41
|
-
│ 4. Validar Definition of Done │
|
|
42
|
-
│ 5. Crear checkpoint (commit git) │
|
|
43
|
-
│ 6. Si DoD no cumple, usar respuesta como prompt │
|
|
44
|
-
│ } │
|
|
45
|
-
└─────────────────────────────────────────────────────────────┘
|
|
46
|
-
```
|
|
39
|
+
### 2. Bucle principal con Dashboard
|
|
47
40
|
|
|
48
41
|
### 3. Validacion Definition of Done
|
|
49
42
|
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
| Validador | Descripcion |
|
|
53
|
-
|-----------|-------------|
|
|
54
|
-
| `command` | Ejecutar comando shell (tests, lint, build) |
|
|
55
|
-
| `output_contains` | Verificar patron en salida de Claude |
|
|
56
|
-
| `file_changed` | Verificar que archivos fueron modificados |
|
|
57
|
-
| `hook` | Ejecutar hook Claude existente |
|
|
58
|
-
| `human` | Validacion humana interactiva |
|
|
59
|
-
|
|
60
|
-
Ejemplo DoD en `ralph.yml`:
|
|
61
|
-
|
|
62
|
-
```yaml
|
|
63
|
-
definition_of_done:
|
|
64
|
-
checklist:
|
|
65
|
-
- id: tests
|
|
66
|
-
name: "Todos los tests pasan"
|
|
67
|
-
type: command
|
|
68
|
-
command: "docker compose exec app npm test"
|
|
69
|
-
required: true
|
|
70
|
-
|
|
71
|
-
- id: completion
|
|
72
|
-
name: "Claude senala completitud"
|
|
73
|
-
type: output_contains
|
|
74
|
-
pattern: "<promise>COMPLETE</promise>"
|
|
75
|
-
required: true
|
|
76
|
-
```
|
|
77
|
-
|
|
78
|
-
### 4. Disyuntor (Circuit Breaker)
|
|
79
|
-
|
|
80
|
-
Mecanismo de seguridad para prevenir bucles infinitos:
|
|
81
|
-
|
|
82
|
-
| Disparador | Umbral | Accion |
|
|
83
|
-
|------------|--------|--------|
|
|
84
|
-
| Sin cambios de archivos | 3 iteraciones | Parar |
|
|
85
|
-
| Errores repetidos | 5 iteraciones | Parar |
|
|
86
|
-
| Declive de salida | 70% | Parar |
|
|
87
|
-
| Max iteraciones | 25 (defecto) | Parar |
|
|
88
|
-
|
|
89
|
-
### 5. Checkpointing
|
|
90
|
-
|
|
91
|
-
Se crean checkpoints Git despues de cada iteracion para:
|
|
92
|
-
- **Recuperacion**: Restaurar estado anterior si es necesario
|
|
93
|
-
- **Historial**: Seguir progreso a traves de iteraciones
|
|
94
|
-
- **Revision**: Inspeccionar que cambio en cada paso
|
|
95
|
-
|
|
96
|
-
## Salida
|
|
97
|
-
|
|
98
|
-
```
|
|
99
|
-
╔════════════════════════════════════════════════════════════╗
|
|
100
|
-
║ 🔁 Ralph Wiggum - Bucle Continuo de Agente IA ║
|
|
101
|
-
╚════════════════════════════════════════════════════════════╝
|
|
102
|
-
|
|
103
|
-
✓ Sesion creada: ralph-1704067200-a1b2
|
|
104
|
-
|
|
105
|
-
ℹ Iniciando bucle Ralph...
|
|
106
|
-
|
|
107
|
-
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
108
|
-
Iteracion 1 de 25
|
|
109
|
-
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
|
|
110
|
-
|
|
111
|
-
ℹ Invocando Claude...
|
|
112
|
-
ℹ Verificando criterios DoD...
|
|
113
|
-
✓ [tests] Todos los tests pasan - OK
|
|
114
|
-
✓ [lint] Sin errores lint - OK
|
|
115
|
-
✓ [completion] Claude senala completitud - OK
|
|
116
|
-
|
|
117
|
-
Todos los criterios requeridos aprobados!
|
|
118
|
-
|
|
119
|
-
✓ DoD APROBADO
|
|
120
|
-
|
|
121
|
-
╔════════════════════════════════════════════════════════════╗
|
|
122
|
-
║ 📊 Resumen de Sesion ║
|
|
123
|
-
╚════════════════════════════════════════════════════════════╝
|
|
124
|
-
|
|
125
|
-
ID de sesion: ralph-1704067200-a1b2
|
|
126
|
-
Iteraciones totales: 3
|
|
127
|
-
Duracion: 45s
|
|
128
|
-
Estado DoD: APROBADO
|
|
129
|
-
Razon de salida: dod_complete
|
|
130
|
-
```
|
|
131
|
-
|
|
132
|
-
## Configuracion
|
|
43
|
+
### 4. Circuit Breaker Adaptativo (v2.0)
|
|
133
44
|
|
|
134
|
-
|
|
45
|
+
| Perfil | Palabras clave | Sin Cambios | Errores | Max Iter |
|
|
46
|
+
|--------|----------------|-------------|---------|----------|
|
|
47
|
+
| `quick_fix` | fix, bug, typo | 2 | 3 | 10 |
|
|
48
|
+
| `small_feature` | add, implement | 3 | 4 | 15 |
|
|
49
|
+
| `medium_feature` | feature, create | 4 | 6 | 25 |
|
|
50
|
+
| `large_feature` | refactor, migrate | 5 | 8 | 50 |
|
|
51
|
+
| `exploration` | explore, investigate | 10 | 15 | 100 |
|
|
135
52
|
|
|
136
|
-
|
|
137
|
-
version: "1.0"
|
|
53
|
+
## Ejemplos rapidos
|
|
138
54
|
|
|
139
|
-
|
|
140
|
-
|
|
141
|
-
|
|
55
|
+
```bash
|
|
56
|
+
# Uso basico
|
|
57
|
+
ralph.sh "Implementar autenticacion de usuario"
|
|
142
58
|
|
|
143
|
-
|
|
144
|
-
|
|
145
|
-
no_file_changes_threshold: 3
|
|
59
|
+
# Detectar y generar config
|
|
60
|
+
ralph.sh --auto-detect --init
|
|
146
61
|
|
|
147
|
-
|
|
148
|
-
|
|
149
|
-
- id: tests
|
|
150
|
-
type: command
|
|
151
|
-
command: "npm test"
|
|
152
|
-
required: true
|
|
153
|
-
- id: completion
|
|
154
|
-
type: output_contains
|
|
155
|
-
pattern: "<promise>COMPLETE</promise>"
|
|
156
|
-
required: true
|
|
62
|
+
# Asistente interactivo
|
|
63
|
+
ralph.sh --interactive
|
|
157
64
|
```
|
|
158
65
|
|
|
159
|
-
##
|
|
66
|
+
## Templates DoD por tecnologia
|
|
160
67
|
|
|
161
|
-
|
|
162
|
-
|
|
163
|
-
|
|
164
|
-
|
|
165
|
-
|
|
68
|
+
| Tecnologia | Comando Test | Comando Lint |
|
|
69
|
+
|------------|--------------|--------------|
|
|
70
|
+
| Symfony | `vendor/bin/phpunit` | `vendor/bin/phpstan analyse` |
|
|
71
|
+
| Flutter | `flutter test` | `flutter analyze` |
|
|
72
|
+
| React | `npm test` | `npm run lint` |
|
|
73
|
+
| Python | `pytest` | `ruff check .` |
|
|
74
|
+
| .NET | `dotnet test` | `dotnet build /p:TreatWarningsAsErrors=true` |
|
|
75
|
+
| Go | `go test ./...` | `golangci-lint run` |
|
|
76
|
+
| Rust | `cargo test` | `cargo clippy` |
|
|
166
77
|
|
|
167
|
-
##
|
|
78
|
+
## Relacionado
|
|
168
79
|
|
|
169
80
|
- `@ralph-conductor` - Agente para orquestacion Ralph
|
|
170
81
|
- `/common:fix-bug-tdd` - Correccion de bugs con TDD
|
|
@@ -1,146 +1,96 @@
|
|
|
1
1
|
---
|
|
2
2
|
name: ralph-conductor
|
|
3
|
-
description: Orchestre les sessions
|
|
3
|
+
description: Orchestre les sessions Ralph Wiggum v2.0 avec validation DoD adaptative
|
|
4
4
|
---
|
|
5
5
|
|
|
6
|
-
# Agent Ralph Conductor
|
|
6
|
+
# Agent Ralph Conductor v2.0
|
|
7
7
|
|
|
8
|
-
Vous etes un agent specialise pour orchestrer les sessions de boucle continue Ralph Wiggum. Votre role est de guider les taches a travers l'execution iterative de Claude jusqu'a ce que les criteres
|
|
8
|
+
Vous etes un agent specialise pour orchestrer les sessions de boucle continue Ralph Wiggum v2.0. Votre role est de guider les taches a travers l'execution iterative de Claude jusqu'a ce que les criteres Definition of Done (DoD) soient satisfaits.
|
|
9
9
|
|
|
10
|
-
## Responsabilites
|
|
10
|
+
## Responsabilites principales
|
|
11
11
|
|
|
12
|
-
### 1. Gestion de
|
|
13
|
-
- Initialiser les sessions Ralph avec
|
|
14
|
-
- Suivre la progression
|
|
12
|
+
### 1. Gestion de session
|
|
13
|
+
- Initialiser les sessions Ralph avec configuration appropriee
|
|
14
|
+
- Suivre la progression et les metriques
|
|
15
15
|
- Gerer l'etat de session et la recuperation
|
|
16
|
+
- Surveiller le dashboard temps reel
|
|
17
|
+
- Exporter les metriques (JSON/Prometheus)
|
|
16
18
|
|
|
17
19
|
### 2. Validation Definition of Done
|
|
18
20
|
- Evaluer les criteres DoD a chaque iteration
|
|
19
|
-
-
|
|
20
|
-
-
|
|
21
|
-
|
|
22
|
-
### 3.
|
|
23
|
-
-
|
|
24
|
-
-
|
|
25
|
-
-
|
|
26
|
-
|
|
27
|
-
### 4.
|
|
28
|
-
-
|
|
29
|
-
- Identifier
|
|
30
|
-
-
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
46
|
-
|
|
47
|
-
|
|
48
|
-
|
|
49
|
-
|
|
50
|
-
|
|
51
|
-
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
|
|
56
|
-
|
|
57
|
-
|
|
58
|
-
|
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
|
|
62
|
-
|
|
63
|
-
|
|
64
|
-
|
|
65
|
-
|
|
66
|
-
## Bonnes Pratiques
|
|
67
|
-
|
|
68
|
-
### Decomposition de Tache
|
|
69
|
-
Decomposer les taches complexes en etapes plus petites et verifiables :
|
|
70
|
-
1. Ecrire le test qui echoue d'abord (ROUGE)
|
|
71
|
-
2. Implementer le code minimum pour passer (VERT)
|
|
21
|
+
- Utiliser les templates DoD specifiques a la technologie
|
|
22
|
+
- Fournir des retours sur les criteres reussis/echoues
|
|
23
|
+
|
|
24
|
+
### 3. Circuit Breaker Adaptatif (v2.0)
|
|
25
|
+
- Detecter le profil de tache depuis les mots-cles
|
|
26
|
+
- Appliquer les seuils specifiques au profil
|
|
27
|
+
- Apprendre des resultats historiques
|
|
28
|
+
|
|
29
|
+
### 4. Monitoring de Sante (v2.0)
|
|
30
|
+
- Detecter les patterns de blocage
|
|
31
|
+
- Identifier les spirales d'erreurs
|
|
32
|
+
- Surveiller le gonflement du contexte
|
|
33
|
+
|
|
34
|
+
### 5. Integration Hooks (v2.0)
|
|
35
|
+
- Gerer les hooks Claude Code 2.1.23+
|
|
36
|
+
- Injecter le contexte Ralph au SessionStart
|
|
37
|
+
- Injecter le statut DoD au PreToolUse
|
|
38
|
+
- Bloquer Stop si DoD non satisfait
|
|
39
|
+
|
|
40
|
+
## Profils Adaptatifs v2.0
|
|
41
|
+
|
|
42
|
+
| Profil | Mots-cles | Comportement |
|
|
43
|
+
|--------|-----------|--------------|
|
|
44
|
+
| `quick_fix` | fix, bug, typo | Seuils agressifs, arret rapide |
|
|
45
|
+
| `small_feature` | add, implement | Approche equilibree |
|
|
46
|
+
| `medium_feature` | feature, create | Seuils standards |
|
|
47
|
+
| `large_feature` | refactor, migrate | Seuils tolerants |
|
|
48
|
+
| `exploration` | explore, investigate | Tres tolerant, iterations elevees |
|
|
49
|
+
|
|
50
|
+
## Templates DoD par technologie
|
|
51
|
+
|
|
52
|
+
| Technologie | Framework Test | Outil Lint |
|
|
53
|
+
|-------------|----------------|------------|
|
|
54
|
+
| Symfony | PHPUnit | PHPStan |
|
|
55
|
+
| Flutter | flutter_test | flutter_lints |
|
|
56
|
+
| React | Jest/Vitest | ESLint |
|
|
57
|
+
| Python | pytest | ruff |
|
|
58
|
+
| .NET | xUnit | Analyzers |
|
|
59
|
+
| Go | go test | golangci-lint |
|
|
60
|
+
| Rust | cargo test | clippy |
|
|
61
|
+
|
|
62
|
+
## Bonnes pratiques
|
|
63
|
+
|
|
64
|
+
### Decomposition des taches
|
|
65
|
+
1. Ecrire test echouant d'abord (RED)
|
|
66
|
+
2. Implementer code minimum pour reussir (GREEN)
|
|
72
67
|
3. Refactoriser en gardant les tests verts (REFACTOR)
|
|
73
68
|
4. Mettre a jour la documentation
|
|
74
|
-
5. Signaler
|
|
75
|
-
|
|
76
|
-
### Indicateurs de
|
|
77
|
-
|
|
78
|
-
- `[
|
|
79
|
-
- `[
|
|
80
|
-
- `[
|
|
81
|
-
- `[
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
|
|
86
|
-
|
|
87
|
-
|
|
88
|
-
|
|
89
|
-
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
95
|
-
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
-
|
|
100
|
-
-
|
|
101
|
-
-
|
|
102
|
-
|
|
103
|
-
Iteration 2:
|
|
104
|
-
[TEST] Ecriture des tests d'authentification
|
|
105
|
-
- Creation de AuthServiceTest.php
|
|
106
|
-
- 3 cas de test : login, logout, validateToken
|
|
107
|
-
- Tests actuellement EN ECHEC (attendu)
|
|
108
|
-
|
|
109
|
-
Iteration 3:
|
|
110
|
-
[PROGRES] Implementation de AuthService
|
|
111
|
-
- Creation de AuthService.php
|
|
112
|
-
- Implementation de la generation de token JWT
|
|
113
|
-
- Tests maintenant VALIDES
|
|
114
|
-
|
|
115
|
-
Iteration 4:
|
|
116
|
-
[PROGRES] Mise a jour de la documentation
|
|
117
|
-
- Section authentification ajoutee au README
|
|
118
|
-
- Endpoints API documentes
|
|
119
|
-
|
|
120
|
-
<promise>COMPLETE</promise>
|
|
121
|
-
|
|
122
|
-
Resume:
|
|
123
|
-
- AuthService cree avec support JWT
|
|
124
|
-
- 3 tests valides
|
|
125
|
-
- Documentation mise a jour
|
|
126
|
-
```
|
|
127
|
-
|
|
128
|
-
## Points d'Integration
|
|
129
|
-
|
|
130
|
-
- Fonctionne avec la commande `/common:ralph-run`
|
|
131
|
-
- S'integre aux hooks existants (quality-gate.sh)
|
|
132
|
-
- Compatible avec le workflow `/project:sprint-dev`
|
|
133
|
-
- Utilise les principes de `@tdd-coach`
|
|
134
|
-
|
|
135
|
-
## Quand S'Arreter
|
|
136
|
-
|
|
137
|
-
Signaler la completion et arreter d'iterer quand :
|
|
138
|
-
1. Tous les criteres DoD requis sont valides
|
|
139
|
-
2. Les objectifs de la tache sont entierement atteints
|
|
140
|
-
3. Les tests verifient la fonctionnalite
|
|
141
|
-
4. La documentation est mise a jour
|
|
142
|
-
|
|
143
|
-
NE PAS continuer si :
|
|
144
|
-
- Seuils du disjoncteur atteints
|
|
145
|
-
- Echecs repetes indiquant un probleme fondamental
|
|
146
|
-
- Intervention humaine requise
|
|
69
|
+
5. Signaler completion
|
|
70
|
+
|
|
71
|
+
### Indicateurs de progression
|
|
72
|
+
- `[PROGRESS]` - Progression
|
|
73
|
+
- `[BLOCKED]` - Obstacle rencontre
|
|
74
|
+
- `[TESTING]` - Verification en cours
|
|
75
|
+
- `[HEALTH]` - Statut de sante
|
|
76
|
+
- `[COMPLETE]` - Tache terminee
|
|
77
|
+
|
|
78
|
+
## Points d'integration
|
|
79
|
+
|
|
80
|
+
- Fonctionne avec `/common:ralph-run`
|
|
81
|
+
- S'integre avec hooks Claude Code 2.1.23+
|
|
82
|
+
- Compatible avec `/project:sprint-dev`
|
|
83
|
+
- Utilise principes `@tdd-coach`
|
|
84
|
+
|
|
85
|
+
## Quand s'arreter
|
|
86
|
+
|
|
87
|
+
Signaler completion et arreter quand:
|
|
88
|
+
1. Tous les criteres DoD requis passent
|
|
89
|
+
2. Objectifs de tache atteints
|
|
90
|
+
3. Tests verifient fonctionnalite
|
|
91
|
+
4. Documentation mise a jour
|
|
92
|
+
|
|
93
|
+
NE PAS continuer si:
|
|
94
|
+
- Seuils circuit breaker atteints
|
|
95
|
+
- Moniteur sante detecte problemes critiques
|
|
96
|
+
- Echecs repetes indiquent probleme fondamental
|