OpenParable
Skip to content
← Back to skills

Migration Config Skill

Others
migration-config-skill

Migration Config Skill is an Agent Skill for general use published in the GoogleCloudPlatform/generative-ai repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Holds canonical source and target environment parameters and verified DataStore mappings.

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/GoogleCloudPlatform/generative-ai/blob/HEAD/search/gemini-enterprise/ge-migration-agent/skills/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/migration-config-skill, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

ADK Administration Setup & Migration Instructions

This file serves as the single source of truth for Gemini Enterprise migrations. Administrators can fully configure source-to-target resource pairings by updating the YAML metadata frontmatter above.

Administrative Setup Guide

1. Environments Configuration

Set your official canonical source and target project definitions under environments:

  • project_number: The numeric Google Cloud Project Number (e.g., 404109417257).
  • engine_id: The fully qualified Discovery Engine app/engine ID.

2. DataStore Grounding Mappings (datastores_mapping)

Map underlying knowledge search collections and grounding data stores (assigned under dataStoreSpecs) using their exact resource ID suffix:

datastores_mapping:
  # Source ID -> Target ID
  example-mcp-source_12345_mcp_data: example-mcp-target_67890_mcp_data
  example-drive-source_12345_google_drive: example-drive-target_67890_google_drive

Note: Always use the fully qualified ID suffix (e.g., _google_drive, _mcp_data) to prevent substring truncation.

3. Visual Connector & Tool Mappings (connectors_mapping)

Map display aliases and frontend extension tool chips (assigned under selectedTools) to ensure visual rendering parity in the Agent Designer UI canvas:

connectors_mapping:
  # Source UI Badge -> Canonical Target UI Token
  "Example Source Connector": custom_mcp
  "example-drive": Drive

Operational Execution

Once configured, run live migrations or offline GCS imports directly:

# 1. Execute live cross-environment migration
uv run ./migrate.py migrate-agent "Quarterly Business Review Generator" --force

# 2. Import agent definition from GCS offline backup
uv run ./migrate.py import-agent-gcs quarterly_business_review_export.json --target-engine <TARGET_ENGINE_ID>