Upgrade Guide

Use this checklist whenever you bump the GL AIP or deploy a new version of the AIP backend.

circle-check

ℹ️ Current versions

  • AIP SDK: 0.0.5

  • AIP Platform backend: 0.1.53

Latest platform release notes live at https://github.com/GDP-ADMIN/ai-agent-platform/releasesarrow-up-right. SDK release notes are tracked in the Changelogarrow-up-right.


Quick Checklist

1

Read the changelog

Capture breaking changes or behavioural updates.

2

Export state

Back up agents, tools, and MCP configs as JSON/YAML if you manage them manually.

3

Update the SDK/CLI

On each machine or runner execute:

Update CLI
aip update
# Use flags as needed:
# aip update --check-only   # verify availability
# aip update --force        # reinstall
4

Smoke test

Run the following checks:

  • aip status

  • representative CLI commands such as aip agents run or aip tools get

  • client.ping() from a Python shell

Example Python check:

Python ping
from aip import Client
client = Client()
print(client.ping())
5

Deploy backend changes (if applicable)

Pull the corresponding AIP release and restart services for the platform backend.

6

Verify MCP and tool integrations

Run one workflow that exercises each connector you depend on.

7

Communicate

Note the versions installed and any follow-up tasks (e.g., feature flag toggles, configuration updates).


Tips

  • Keep a copy of exported agent/tool JSON in version control; it simplifies rollback and lets you diff changes across upgrades.

  • Automate aip update via CI jobs so runners stay in sync with PyPI releases.

  • When the REST API introduces new endpoints or payloads, the REST API Referencearrow-up-right is updated automatically and should be consulted for schema details.

Future breaking changes will re-use this page—add concise “Before / After” code snippets when they land so the checklist stays actionable.

Last updated