The Morning a Preview Image Model Went Dark — Migrating to GA Gemini Image Models and Building a Deprecation-Resilient Pipeline
With gemini-3.1-flash-image-preview and gemini-3-pro-image-preview retired, here is how to migrate to the GA models and design an image pipeline that no longer gets caught off guard by deprecation dates — with code and cost math, plus video-to-image thumbnail automation.
Structured Product Image Analysis with the Gemini API — A Production Pipeline Built on Thousands of Photos
Turn a one-off image analysis script into a production pipeline that auto-generates tags, descriptions, and categories at scale — covering structured output, resumable batches, measured cost, and model routing learned from real indie-developer operation.
Gemini API Implicit Caching Not Working — Troubleshooting Guide by Root Cause
Troubleshoot Gemini API implicit caching issues: cache not hitting, unexpectedly high costs, or low cache hit rates. Covers token thresholds, prompt structure, model version consistency, TTL expiry, and multimodal caching with code examples.
When Gemini's Maps Grounding Quietly Fails in Production — Field Notes on Attribution, Billing Boundaries, and Fallbacks
An operations-focused look at the pitfalls that surface after you ship Grounding with Google Maps on Gemini: detecting silent grounding misses, meeting the attribution requirement, knowing which responses are billed, and building fallbacks for latency and staleness.
Track Gemini API Costs in Production with usageMetadata — A Per-Request Logging Pattern That Reconciles With Your Bill
A production pattern for capturing Gemini API's usageMetadata per request to attribute spend by endpoint, user, and model — hardened for the 3.5 Flash GA era where the default model can shift under you. Covers pricing keyed on resp.model_version and a nightly audit that flags model drift and unknown models before the invoice does.
Moving My Automation Off the Gemini CLI Before the June 18 Shutdown
On June 18, the Gemini CLI stops responding for hosted plans. Here is how I moved unattended scripts that called gemini from the shell over to the google-genai SDK, with structured output, retries, and cost measurement built in.
Defending Against Prompt Injection When You Pass External Text to the Gemini API
User reviews, scraped articles, and other untrusted text are the entry point for indirect prompt injection when you feed them to the Gemini API. Here is a prioritized, code-backed defense you can drop into a production pipeline: trust-boundary isolation, schema constraints, a two-stage screening pass, and output sanitization.
Switching Image Models Quietly Degrades Quality — A Gate That Catches It Without Manual Review
When you move image generation from preview to GA models, the API keeps returning 200 and quality slips silently. This is the three-layer gate I built to detect that drift without staring at every image: deterministic property checks, multimodal embedding similarity, and a Gemini judge, wired together in Python with thresholds and a cutover procedure.
When Gemini API Cuts Your Response Off Mid-Sentence — Detecting finish_reason: MAX_TOKENS and Stitching the Continuation
Long-form generation that ends mid-sentence is usually finish_reason: MAX_TOKENS. This failure arrives as a quiet HTTP 200, no exception. Here is how to detect it, stitch a continuation to recover the full text, and avoid the thinking-token trap that makes it worse on 3.x models.
Retiring the Midnight Polling Loop — Rebuilding My Gemini Batch Monitoring Around Webhooks
A working log of migrating Gemini Batch API completion monitoring from 60-second polling to event-driven webhooks: static vs dynamic, signature verification, and real numbers.
Gemini's Preview Image Models Shut Down on June 25 — Code Diffs and Checks From an Actual GA Migration
How I moved my image pipeline off Gemini's preview image models before the June 25 shutdown — confirming GA model IDs, Python code diffs, regression checks, and a safe cutover order.
Reverse-Engineering Empty Gemini API Responses with finish_reason — Triage, Retry Classification, and Monitoring
An empty response.text has three distinct failure layers — candidates, prompt_feedback, and finish_reason. Production code for detecting thinking-token starvation, classifying what is worth retrying, and monitoring your empty-response rate.