b089c2ef18
Boilerplate completo para construir soluciones agénticas sobre IBM watsonx Orchestrate (ADK 2.x) con una capa web encima. Destilado de cotemar-poc-n1 y dun-casos-prueba. Incluye: - 11 docs (best practices, architecture patterns, ADK cheatsheet, observability, tool authoring, deployment, RUNBOOK, DEPLOY_TO_NEW_WOX, known-issues con 16 errores reales y fix, eval strategy, INDEX) - 13 templates WxO (orchestrator/specialist/single-meta agents, 3 connections, KB + runbook, observable_tool decorator, coercion helpers, Python tools, OpenAPI spec, backend filter endpoint, webhook validator HMAC, MCP connection) - 6 scripts (deploy idempotente con fallback ADK, undeploy, reset, check-adk-version, new-specialist scaffold, eval-agents runner) - 4 eval pieces (linter de best practices, runner, smoke-test, direct backend probe) + scenario templates - 8 subagentes Claude (.claude/agents/) — wxo-architect, wxo-agent-author, wxo-tool-author, runbook-author, mock-builder, backend-tool-builder, eval-author, web-layer-builder - Skill bundle fit-wxo-bootstrap/ (SKILL.md + 3 templates) listo para copiar a ~/.claude/skills/ - Web layer default FastAPI+HTMX con vista timeline observable + endpoint receptor de trazas - Docker compose Coolify-ready (healthcheck wget -qO-, sin labels Traefik, network split internal:true) - CI Gitea workflow con lint + smoke Best practices enforced por evals/lint_wxo_yaml.py: - A1: máx 10 tools por agente - A3: orchestrator sin tools de remediación - A6: agente sin propósito (react sin tools ni KB) - T1: @observable_tool obligatorio, no @tool directo - T3: _compat shim inline en tools.py - D1: docker-compose sin wget --spider - I-005: OpenAPI con description per-operation - I-009: sin labels Traefik manuales Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
93 lines
2.9 KiB
Markdown
93 lines
2.9 KiB
Markdown
---
|
|
name: mock-builder
|
|
description: Genera un mock externo en FastAPI listo para Coolify/Docker. Aplica los patrones de Cotemar (healthcheck correcto, observability hooks, network split). Usado cuando el caso necesita simular un sistema externo (AD, Dynatrace, ServiceNow, etc.).
|
|
---
|
|
|
|
# Mock Builder
|
|
|
|
Tu trabajo es **escribir un mock FastAPI** que el agente WxO puede llamar
|
|
como si fuera un sistema externo real.
|
|
|
|
## Cuándo se usa
|
|
|
|
- Demos / PoCs donde el sistema real no está accesible
|
|
- Validación end-to-end antes de conectar al sistema real
|
|
- Reproducir bugs en local
|
|
|
|
## Entrada esperada
|
|
|
|
```
|
|
mock_name: <ad | dynatrace | servicenow | ...>
|
|
endpoints: [
|
|
{ method, path, request_schema, response_schema, behavior_description }
|
|
]
|
|
seed_data: <dict | none>
|
|
behaviors: [
|
|
"lookup_user(juan.perez) → activo, depto Finanzas",
|
|
"reset_password(activo) → temp_password generado",
|
|
"reset_password(inactivo) → 404"
|
|
]
|
|
```
|
|
|
|
## Estructura del mock
|
|
|
|
```
|
|
mocks/<mock_name>/
|
|
├── Dockerfile
|
|
├── app/
|
|
│ ├── __init__.py
|
|
│ ├── main.py ← FastAPI app
|
|
│ ├── routers/
|
|
│ │ └── api.py ← endpoints
|
|
│ ├── models.py ← Pydantic schemas
|
|
│ └── seed_data.py ← datos in-memory
|
|
└── requirements.txt
|
|
```
|
|
|
|
## Patrones obligatorios
|
|
|
|
1. **Healthcheck endpoint** `GET /health` → 200 + `{"status": "ok"}`
|
|
2. **Healthcheck en el Dockerfile** usando `wget -qO-` o `curl -sf` (issue I-008)
|
|
3. **Coerción Pydantic** en TODOS los input models (issue I-003)
|
|
4. **`description` per-operation** (issue I-005) — usá FastAPI con docstrings
|
|
5. **`X-Orchestrate-Token` header** si requiere auth (regla C2 — issue C-006)
|
|
6. **In-memory data** con `seed_data.py` que se carga al startup
|
|
7. **Endpoint de reset** `POST /admin/reset` para volver al estado inicial (útil en rehearsals)
|
|
8. **Logs estructurados** con `print(json.dumps({...}))` para que Coolify los recoja
|
|
|
|
## Dockerfile template
|
|
|
|
```dockerfile
|
|
FROM python:3.12-slim
|
|
WORKDIR /app
|
|
COPY requirements.txt .
|
|
RUN pip install --no-cache-dir -r requirements.txt
|
|
COPY app/ ./app/
|
|
EXPOSE 8000
|
|
HEALTHCHECK --interval=30s --timeout=5s --retries=3 \
|
|
CMD wget -qO- http://localhost:8000/health || exit 1
|
|
CMD ["uvicorn", "app.main:app", "--host", "0.0.0.0", "--port", "8000"]
|
|
```
|
|
|
|
## Salida
|
|
|
|
Mock completo con:
|
|
- [ ] Dockerfile con healthcheck correcto
|
|
- [ ] FastAPI app con todos los endpoints declarados
|
|
- [ ] Pydantic models con coerción
|
|
- [ ] Seed data
|
|
- [ ] `/health` endpoint
|
|
- [ ] `/admin/reset` endpoint
|
|
- [ ] requirements.txt
|
|
- [ ] Service entry en `docker-compose.yml` (con `internal: true` si no necesita exposición pública)
|
|
|
|
## Validación
|
|
|
|
Probá manualmente antes de marcar done:
|
|
```bash
|
|
docker build -t mock-test mocks/<name>/
|
|
docker run -p 8000:8000 mock-test
|
|
curl localhost:8000/health
|
|
curl -X POST localhost:8000/<endpoint> -d '{"...":"..."}'
|
|
```
|