google-agents-cli-publish

作者: google

當使用者想要「發布代理程式」、「發布我的ADK代理程式」、「向Gemini Enterprise註冊代理程式」、「發布到Gemini Enterprise」,或需要關於agents-cli publish gemini-enterprise指令的指引時,應使用此技能。涵蓋ADK與A2A註冊模式、程式化與互動式使用方式、旗標參考、從部署中繼資料自動偵測,以及疑難排解。屬於Google ADK(代理程式開發套件)技能套件的一部分。請勿用於部署(請使用...

npx skills add https://github.com/google/agents-cli --skill google-agents-cli-publish

Gemini Enterprise Registration

Requires: A deployed agent. For Agent Runtime, deployment_metadata.json (created by agents-cli deploy) enables auto-detection. For Cloud Run or GKE, provide the agent card URL and flags directly.

Prerequisites

  1. Agent must be deployed — the agent must be running and reachable
  2. Gemini Enterprise app must exist — Create one in Google Cloud Console → Gemini Enterprise → Apps before registering
  3. 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 directory

Required Permissions for A2A on Cloud Run

  • roles/run.servicesInvoker granted to the Discovery Engine service account (service-<PROJECT_NUMBER>@gcp-sa-discoveryengine.iam.gserviceaccount.com) on the Cloud Run service.

Registration Modes

A2A Registration (Cloud Run / GKE)

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).

ADK Registration (default on Agent Runtime)

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"

Programmatic Mode (CI/CD)

The command is non-interactive by default — pass all required values via flags or environment variables. This makes it safe for CI/CD pipelines.

Via flags

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

Via environment variables

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 Mode (--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

Complete Flag Reference

FlagEnv VarDescription
--agent-runtime-idAGENT_RUNTIME_IDAgent Runtime resource name (auto-detected from deployment_metadata.json)
--gemini-enterprise-app-idID or GEMINI_ENTERPRISE_APP_IDGemini Enterprise app full resource name
--display-nameGEMINI_DISPLAY_NAMEDisplay name in Gemini Enterprise
--descriptionGEMINI_DESCRIPTIONAgent description
--tool-descriptionGEMINI_TOOL_DESCRIPTIONTool description (ADK mode only, defaults to description)
--registration-typeREGISTRATION_TYPEadk or a2a (defaults to adk on Agent Runtime, a2a on Cloud Run / GKE)
--agent-card-urlAGENT_CARD_URLAgent card URL for A2A registration
--deployment-targetDEPLOYMENT_TARGETagent_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-idGOOGLE_CLOUD_PROJECTGCP project ID for billing
--project-numberPROJECT_NUMBERGCP project number (used for Gemini Enterprise lookup)
--authorization-idGEMINI_AUTHORIZATION_IDOAuth authorization resource name
--metadata-filePath to deployment metadata (default: deployment_metadata.json)
--interactive / -iEnable interactive prompts
--listList Gemini Enterprise apps in the current project and exit

Auto-Detection from Metadata

When deployment_metadata.json exists, the command automatically:

  • Reads the agent runtime ID (remote_agent_runtime_id)
  • Determines the registration type: defaults to ADK (native :streamQuery) on Agent Runtime, and A2A on Cloud Run / GKE (which have no reasoning engine). Override with --registration-type.
  • Determines the deployment target for authentication

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

SDK Compatibility

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.


Managing Agents in Agent Registry

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


Troubleshooting

IssueSolution
"Session not found" after registrationSDK version issue — upgrade google-cloud-aiplatform (see SDK Compatibility above), redeploy, then re-register
--registration-type is requiredNon-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 agentRegistration is idempotent — re-running updates the existing registration in place instead of creating a duplicate
HTTP 403 on registrationCheck that your account has Discovery Engine Editor permissions on the Gemini Enterprise project
Debugging ADK invocation failures on Agent RuntimeGemini 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

Related Skills

  • /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 enhance

來自 google 的更多技能

google-agents-cli-adk-code
google
當使用者想要「撰寫代理程式碼」、「使用 ADK 建置代理程式」、「新增工具」、「建立回呼」、「定義代理程式」、「使用狀態管理」,或需要 ADK(代理程式開發套件)Python API 模式與程式碼範例時,應使用此技能。屬於 Google ADK 技能套件的一部分。提供代理程式類型、工具定義、編排模式、回呼與狀態管理的快速參考。請勿用於建立新專案(請使用 google-agents-cli-scaffold)或部署...
developmentapicode-review
google-agents-cli-eval
google
當使用者想要「執行評估」、「評估我的 ADK 代理」、「撰寫評估資料集」、「分析評估失敗原因」、「比較評估結果」、「優化代理」,或需要 Agent Platform 評估方法論與品質飛輪的指引時,應使用此技能。涵蓋評估指標、資料集結構、LLM 作為評審的評分方式,以及常見的失敗原因。請勿用於 API 程式碼模式(請使用 google-agents-cli-adk-code)、部署(請使用 google-agents-cli-deploy)或專案架構生成(請使用...
developmenttestingdata-analysis
google-agents-cli-workflow
google
此技能應在使用者想要「開發代理」、「使用 ADK 建置代理」、「在本機執行代理」、「除錯代理程式碼」、「測試代理」、「部署代理」、「發布代理」、「監控代理」,或需要 ADK(代理開發套件)開發生命週期與編碼指南時使用。為建置 ADK 代理的進入點。始終啟用 — 提供完整工作流程(建立框架、建置、評估、部署、發布、監控)、程式碼保留規則、模型選擇指引,以及...
developmentdevopstesting
google-agents-cli-deploy
google
當使用者想要「部署代理程式」、「部署我的ADK代理程式」、「設定CI/CD」、「設定機密」、「疑難排解部署」,或需要關於Agent Runtime、Cloud Run或GKE部署目標的指引時,應使用此技能。涵蓋部署工作流程、服務帳戶、回滾及生產基礎架構。屬於Google ADK(代理程式開發套件)技能套件的一部分。請勿用於API程式碼模式(請使用google-agents-cli-adk-code)、評估(請使用google-agents-cli-eval)或...
developmentdevops
google-agents-cli-scaffold
google
We need to translate the given text from English to Traditional Chinese. The text is a description of a skill for an agent. We must preserve the name "google-agents-cli-scaffold" but it's not in the text, so we don't include it. We also preserve product names, protocol names, URLs, numbers, technical terms. The text includes "Google ADK", "Agent Development Kit", "agents-cli scaffold create", "scaffold enhance", "scaffold upgrade". These should be kept as is. Also "prototype-first workflow" is a technical term. The translation should be in Traditional Chinese. No extra commentary, no labels. Just the translated text. Let's translate: "This skill should be used when the user wants to..." -> "此技能應在使用者想要...時使用" "create an agent project" -> "建立代理專案" "start a new ADK project" -> "啟動新的ADK專案" "build me a new agent" -> "為我建立新的代理" "add CI/CD to my
developmentdevops
google-agents-cli-observability
google
此技能應在使用者想要「設定追蹤」、「監控我的 ADK 代理程式」、「設定記錄」、「加入可觀測性」、「偵錯正式環境流量」,或需要關於監控已部署 ADK(代理程式開發套件)代理程式的指引時使用。涵蓋 Cloud Trace、提示-回應記錄、BigQuery 代理程式分析、第三方整合(AgentOps、Phoenix、MLflow 等)以及疑難排解。屬於 Google ADK(代理程式開發套件)技能套件的一部分。請勿用於部署設定(請使用...
developmentdevopsapi