feat: v1 — boilerplate WxO + web

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>

evals/smoke-test.sh

@@ -0,0 +1,55 @@
+#!/usr/bin/env bash
+# Smoke test mínimo: end-to-end del flujo principal.
+#
+# Sirve como:
+#   - Validación post-deploy
+#   - Health check nightly (cron en CI)
+#   - Reproducible bug report
+#
+# Pasos:
+#   1. Healthcheck del backend público
+#   2. Llamar al endpoint principal con un input válido
+#   3. Pollear hasta done
+#   4. Assert sobre el estado final
+
+set -euo pipefail
+
+PUBLIC_HOST="${PUBLIC_HOST:-mi-cliente.fitlabs.dev}"
+BASE="https://${PUBLIC_HOST}"
+
+echo "→ [1/4] Healthcheck"
+curl -sf "${BASE}/health" > /dev/null && echo "  ✓ 200 OK" || { echo "  ✗ FAIL"; exit 1; }
+
+echo "→ [2/4] Create case (smoke input)"
+# REPLACE: ajustar al endpoint y payload de tu solución
+RESULT=$(curl -sf -X POST "${BASE}/api/v1/cases/run" \
+  -H "Content-Type: application/json" \
+  -H "X-Orchestrate-Token: ${WXO_BACKEND_TOKEN:-smoke-test-token}" \
+  -d '{"case_id":"smoke-001","target_id":1}' \
+  2>&1) || { echo "  ✗ FAIL: $RESULT"; exit 1; }
+echo "  ✓ accepted: $RESULT"
+
+echo "→ [3/4] Poll until done (max 60s)"
+for i in $(seq 1 60); do
+  STATUS=$(curl -sf "${BASE}/api/v1/cases/smoke-001" | python3 -c "import sys,json; print(json.load(sys.stdin).get('status','?'))" 2>/dev/null || echo "?")
+  [ "$STATUS" = "done" ] && { echo "  ✓ done after ${i}s"; break; }
+  [ "$STATUS" = "failed" ] && { echo "  ✗ failed"; exit 1; }
+  sleep 1
+done
+[ "$STATUS" = "done" ] || { echo "  ✗ timeout (last status: $STATUS)"; exit 1; }
+
+echo "→ [4/4] Assert final state"
+# REPLACE: ajustar al assert de tu solución
+RESULT=$(curl -sf "${BASE}/api/v1/cases/smoke-001")
+echo "$RESULT" | python3 -c "
+import sys, json
+data = json.load(sys.stdin)
+assert data['status'] == 'done', f'status={data[\"status\"]}'
+assert data.get('package_url'), 'no package_url'
+print('  ✓ assertions OK')
+"
+
+echo ""
+echo "════════════════════════════════════════"
+echo "  ✓ Smoke test passed"
+echo "════════════════════════════════════════"