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>
36 lines
1.4 KiB
Markdown
36 lines
1.4 KiB
Markdown
# Index — Doc de docs
|
|
|
|
Mapa de toda la documentación del boilerplate. Si no sabés por dónde empezar, leé en este orden.
|
|
|
|
## Para empezar (lectura obligatoria, 15 min)
|
|
|
|
1. [`../README.md`](../README.md) — Filosofía del template, qué hay acá
|
|
2. [`../INSTRUCCIONES.md`](../INSTRUCCIONES.md) — Quickstart de 5 pasos
|
|
3. [`wxo-best-practices.md`](wxo-best-practices.md) — Las 30+ reglas que el linter enforcea
|
|
|
|
## Para diseñar (al arrancar un caso nuevo)
|
|
|
|
4. [`architecture-patterns.md`](architecture-patterns.md) — Árbol de decisión del `wxo-architect`
|
|
5. [`tool-authoring-guide.md`](tool-authoring-guide.md) — Python vs OpenAPI vs MCP
|
|
6. [`eval-strategy.md`](eval-strategy.md) — Qué validar y cómo
|
|
|
|
## Para implementar
|
|
|
|
7. [`adk-2x-cheatsheet.md`](adk-2x-cheatsheet.md) — Comandos ADK, YAML schemas, gotchas
|
|
8. [`observability-pattern.md`](observability-pattern.md) — Contrato `@observable_tool` + `write_audit`
|
|
|
|
## Para desplegar
|
|
|
|
9. [`deployment-guide.md`](deployment-guide.md) — Deploy genérico parametrizable
|
|
10. [`DEPLOY_TO_NEW_WOX.md`](DEPLOY_TO_NEW_WOX.md) — Cold start playbook
|
|
|
|
## Para operar
|
|
|
|
11. [`RUNBOOK.md`](RUNBOOK.md) — URLs, monitoring, recovery, rotation
|
|
12. [`known-issues.md`](known-issues.md) — Errores con su fix
|
|
|
|
## Apéndices
|
|
|
|
- [`../skill/fit-wxo-bootstrap/SKILL.md`](../skill/fit-wxo-bootstrap/SKILL.md) — Cómo funciona la skill
|
|
- [`../.claude/agents/`](../.claude/agents/) — Los 7 subagentes Claude del template
|