ideogram-prod-checklist

name	ideogram-prod-checklist
description	Execute Ideogram production deployment checklist and rollback procedures. Use when deploying Ideogram integrations to production, preparing for launch, or implementing go-live procedures. Trigger with phrases like "ideogram production", "deploy ideogram", "ideogram go-live", "ideogram launch checklist", "ideogram production ready".
allowed-tools	Read, Bash(curl:*), Bash(kubectl:*), Grep
version	1.10.0
license	MIT
author	Jeremy Longshore <[e-mail]>
tags	["saas","ideogram","deployment","production"]
compatibility	Designed for Claude Code

Ideogram Production Checklist

Overview

Complete pre-flight checklist for deploying Ideogram image generation to production. Covers API key management, timeout configuration, image persistence, error handling, monitoring, and rollback procedures.

Prerequisites

• Staging environment tested
• Production API key created (separate from dev)
• Image storage configured (S3, GCS, or R2)
• Monitoring stack ready

Pre-Deployment Checklist

API Configuration

• Production API key stored in secret manager (not .env file)
• Key is separate from dev/staging keys
• Auto top-up billing configured with appropriate limits
• Base URL is https://api.ideogram.ai (no trailing slash)

Request Handling

• Api-Key header used (not Authorization: Bearer)
• Request timeout set to 60s+ (generation takes 5-15s, complex prompts longer)
• Retry logic with exponential backoff on 429 and 5xx
• Concurrency limited to 8 (below the 10 in-flight limit)
• Prompt length validated (max 10,000 chars)

Image Persistence

• Images downloaded immediately after generation (URLs expire ~1 hour)
• Downloaded to durable storage (S3/GCS/R2), not local filesystem
• Filenames include seed for reproducibility tracking
• Generation metadata (prompt, seed, model, style) stored in database

Error Handling

• 401 triggers key rotation alert
• 422 (safety filter) logged with sanitized prompt for review
• 429 handled with retry, not user-facing error