Guía para publicar un agente ADK o A2A en Gemini Enterprise, gestionar el Agent Registry y usar el comando `agents-cli publish gemini-enterprise`.
en todo el repo
0–100, la ruta de este skill
último commit aquí
últimos 90 días
163 tok en reposo
10 KB
Funciona con cualquier agente que lea SKILL.md
npx -y skills add google/agents-cli --skill google-agents-cli-publish --agent claude-codeSe instala solo en este repositorio.
Este skill makes network requests, reads environment config.
Di cualquiera de estas frases y el agente debería cargar este skill.
Requires: A deployed agent. For Agent Runtime,
deployment_metadata.json(created byagents-cli deploy) enables auto-detection. For Cloud Run or GKE, provide the agent card URL and flags directly.
deployment_metadata.json (Agent Runtime only) — Created automatically by agents-cli deploy; contains the agent runtime ID, deployment target, the A2A flag, and the agent directoryroles/run.servicesInvoker granted to the Discovery Engine service account (service-<PROJECT_NUMBER>@gcp-sa-discoveryengine.iam.gserviceaccount.com) on the Cloud Run service.Every scaffolded agent serves the Agent-to-Agent protocol. A2A is the default — and only — registration type on Cloud Run and GKE, which have no reasoning engine, so Gemini Enterprise registers them over A2A. Pass the agent card URL and the command fetches the card and registers it; display name and description default to the card's name/description.
# A2A on Cloud Run / GKE
agents-cli publish gemini-enterprise \
--agent-card-url https://my-service-abc123.us-east1.run.app/a2a/app/.well-known/agent-card.json \
--gemini-enterprise-app-id projects/123456/locations/global/collections/default_collection/engines/my-app
Pass --display-name / --description to override the card defaults. For Agent Runtime, use ADK registration (below).
This is the default and recommended registration for Agent Runtime deployments: Gemini Enterprise invokes the agent natively via :streamQuery on its reasoning engine resource, authenticating end-to-end. Under the hood, :streamQuery dispatches to the AdkApp's streaming_agent_run_with_events method — when debugging an ADK invocation, search the runtime's reasoning_engine_stderr logs for that method name to trace the failure. It's also the path to use when the agent needs an OAuth authorization (--authorization-id). The agent is registered directly via its reasoning engine resource name; no agent card URL is needed.
agents-cli publish gemini-enterprise \
--registration-type adk \
--agent-runtime-id projects/123456/locations/us-east1/reasoningEngines/789 \
--gemini-enterprise-app-id projects/123456/locations/global/collections/default_collection/engines/my-app \
--display-name "My Agent" \
--description "Handles customer queries" \
--tool-description "Answers questions about products"
The command is non-interactive by default — pass all required values via flags or environment variables. This makes it safe for CI/CD pipelines.
agents-cli publish gemini-enterprise \
--agent-runtime-id "$AGENT_RUNTIME_ID" \
--gemini-enterprise-app-id "$GEMINI_ENTERPRISE_APP_ID" \
--display-name "Production Agent" \
--registration-type adk
Most flags have an env var alternative (--metadata-file, --interactive, and --list do not):
export AGENT_RUNTIME_ID="projects/123456/locations/us-east1/reasoningEngines/789"
export GEMINI_ENTERPRISE_APP_ID="projects/123456/locations/global/collections/default_collection/engines/my-app"
export GEMINI_DISPLAY_NAME="Production Agent"
export GEMINI_DESCRIPTION="Handles customer queries"
agents-cli publish gemini-enterprise
--interactive)Pass --interactive (or -i) to be guided through any missing values with interactive prompts. The command will list available Gemini Enterprise apps, offer to auto-detect the agent runtime ID from metadata, and prompt for display name and description.
agents-cli publish gemini-enterprise --interactive
| Flag | Env Var | Description |
|---|---|---|
--agent-runtime-id |
AGENT_RUNTIME_ID |
Agent Runtime resource name (auto-detected from deployment_metadata.json) |
--gemini-enterprise-app-id |
ID or GEMINI_ENTERPRISE_APP_ID |
Gemini Enterprise app full resource name |
--display-name |
GEMINI_DISPLAY_NAME |
Display name in Gemini Enterprise |
--description |
GEMINI_DESCRIPTION |
Agent description |
--tool-description |
GEMINI_TOOL_DESCRIPTION |
Tool description (ADK mode only, defaults to description) |
--registration-type |
REGISTRATION_TYPE |
adk or a2a (defaults to adk on Agent Runtime, a2a on Cloud Run / GKE) |
--agent-card-url |
AGENT_CARD_URL |
Agent card URL for A2A registration |
--deployment-target |
DEPLOYMENT_TARGET |
agent_runtime, cloud_run, or gke (sets the default registration type — ADK on Agent Runtime, A2A on Cloud Run / GKE — and the A2A auth method) |
--project-id |
GOOGLE_CLOUD_PROJECT |
GCP project ID for billing |
--project-number |
PROJECT_NUMBER |
GCP project number (used for Gemini Enterprise lookup) |
--authorization-id |
GEMINI_AUTHORIZATION_ID |
OAuth authorization resource name |
--metadata-file |
— | Path to deployment metadata (default: deployment_metadata.json) |
--interactive / -i |
— | Enable interactive prompts |
--list |
— | List Gemini Enterprise apps in the current project and exit |
When deployment_metadata.json exists, the command automatically:
remote_agent_runtime_id):streamQuery) on Agent Runtime, and A2A on Cloud Run / GKE (which have no reasoning engine). Override with --registration-type.This means that for the simplest case (an agent on Agent Runtime, registered as ADK), you only need to provide the Gemini Enterprise app ID:
agents-cli publish gemini-enterprise \
--gemini-enterprise-app-id projects/123456/locations/global/collections/default_collection/engines/my-app
Agent Runtime deployments may encounter "Session not found" errors with google-cloud-aiplatform versions <= 1.128.0. In interactive mode (--interactive), the command checks the SDK version from uv.lock and offers to upgrade. In programmatic mode, ensure your SDK is up to date before registering.
Agent Registry (Preview) is the Google Cloud fleet-wide record of your agents.
Agents deployed to a managed runtime (Agent Runtime on Gemini Enterprise
Agent Platform) are auto-registered — no extra step after agents-cli deploy.
Manage them with gcloud (requires roles/agentregistry.editor):
# List / filter
gcloud alpha agent-registry agents list --project PROJECT --location LOCATION
gcloud alpha agent-registry agents list --filter="displayName:my-agent"
# Inspect
gcloud alpha agent-registry agents describe AGENT_NAME
# Update endpoint/metadata — edit the Service resource, not the Agent
gcloud alpha agent-registry services update AGENT_NAME \
--display-name "..." --description "..." \
--interfaces "url=ENDPOINT_URL,protocol=HTTP_JSON"
# Remove: delete the underlying runtime agent (auto-registered) OR, for
# manually registered agents, delete the Service resource
gcloud alpha agent-registry services delete AGENT_NAME
Docs: https://docs.cloud.google.com/agent-registry/manage-agents
| Issue | Solution |
|---|---|
| "Session not found" after registration | SDK version issue — upgrade google-cloud-aiplatform (see SDK Compatibility above), redeploy, then re-register |
--registration-type is required |
Non-interactive mode needs --registration-type when no deployment_metadata.json exists |
| "Gemini Enterprise App ID is required" | Provide --gemini-enterprise-app-id or set the ID / GEMINI_ENTERPRISE_APP_ID env var |
| Re-publishing the same agent | Registration is idempotent — re-running updates the existing registration in place instead of creating a duplicate |
| HTTP 403 on registration | Check that your account has Discovery Engine Editor permissions on the Gemini Enterprise project |
| Debugging ADK invocation failures on Agent Runtime | Gemini Enterprise calls the agent via the AdkApp's streaming_agent_run_with_events method (the native :streamQuery contract). Grep the runtime's reasoning_engine_stderr logs for streaming_agent_run_with_events to find the underlying error |
| "Could not fetch agent card" | Verify the agent is running and the URL is correct; for Cloud Run, ensure gcloud auth login is done |
/google-agents-cli-deploy — Deployment targets, CI/CD pipelines, and production workflows (also covers Agent Gateway governed ingress/egress and Semantic Governance awareness)/google-agents-cli-workflow — Development workflow, coding guidelines, and operational rules/google-agents-cli-scaffold — Project creation and enhancement with agents-cli scaffold create / scaffold enhanceReproducido de google/agents-cli bajo licencia Apache-2.0. Leer esta página en markdown.
1 archivo en el paquete. Solo se lee SKILL.md al activarse — las referencias se cargan si el skill decide que las necesita.
Requiere un agente ya desplegado y una app de Gemini Enterprise existente; `agents-cli` se instala con `uv tool install google-agents-cli`.
Necesita en el PATH:gcloud
Variables de entorno:AGENT_RUNTIME_IDGEMINI_ENTERPRISE_APP_ID
Este repo incluye 7 skills. Si instalas uno, normalmente ya tienes los demás.
Guía para desplegar un agente ADK, configurar CI/CD, gestionar secretos o solucionar despliegues en Agent Runtime, Cloud Run o GKE, incluyendo Agent Gateway.
Guía sobre la metodología de evaluación de Agent Platform y el Quality Flywheel: métricas, esquema de dataset, scoring LLM-as-judge y causas comunes de fallo.
Referencia rápida de patrones de la API Python de ADK: tipos de agente, definición de tools, orquestación, callbacks, manejo de estado y recetas de referencia para estudiar.
Guía activa siempre para el ciclo de vida completo de desarrollo con ADK: scaffolding, construcción, evaluación, despliegue, publicación y observación de agentes, con reglas de preservación de código y selección de modelo.
Úsalo para 'crear un proyecto de agente', 'iniciar un proyecto ADK nuevo', 'añadir CI/CD' o 'mejorar/actualizar mi proyecto'. Cubre `scaffold create`, `scaffold enhance` y `scaffold upgrade`, plantillas y targets de deployment.
Úsalo para configurar tracing, monitorizar agentes ADK, configurar logging o depurar tráfico en producción; cubre Cloud Trace, prompt-response logging, BigQuery Agent Analytics e integraciones de terceros.
Responde preguntas sobre la AI SDK y ayuda a construir funciones con IA: agentes, chatbots, RAG, streaming, tool calling, salida estructurada, embeddings y hooks como useChat.
Configura Turborepo para builds de monorepo eficientes con caché local y remota. Útil al configurar Turborepo, optimizar pipelines de build o implementar caching distribuido.
Implementa observabilidad integral para service meshes, incluyendo tracing distribuido, métricas y visualización. Útil para monitoreo de mesh, depuración de latencia y SLOs.
