All Articles
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.
Gemini Interactions API: Fixing What Broke When the Legacy outputs Schema Was Removed on June 6
Google removed the Gemini Interactions API legacy outputs schema on June 6, 2026. A symptom-based walkthrough of migrating to steps and the new response_format.
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.
Designing a Nightly Batch That Survives a Gemini API Outage — Three Layers of Defense
This week's widespread Gemini outage cost my nightly batch three hours of work. Here is how I rebuilt it with three layers of defense: classified retries, a model fallback chain, graceful degradation, plus idempotency keys and a catch-up queue.
Gemini 3.2 API Developer Guide — Correct Model IDs, Migration from 3.1, and Production Checklist
A practical guide to calling Gemini 3.2 via the API: correct model IDs, what changed from Gemini 3.1, Python and TypeScript code examples, and a production migration checklist.
Don't make Gemini judge your AdMob report — confine structured output to extraction
When deciding AdMob floors (eCPM thresholds), letting Gemini make the decision itself is dangerous. Confine structured output to 'extracting a messy report into typed data,' and keep the threshold judgment in deterministic code — here is the reasoning and implementation, with the actual decision rules from running 42 groups.
Gemini Live API Audio Sounds Sped Up — Fixing the Sample Rate Mismatch
When Gemini Live API responses sound high-pitched and sped up, or come back full of noise, the cause is almost always that the 24kHz output is being played at a different sample rate. Here are the concrete fixes for both the browser and iOS.
Reconciling Orphaned Gemini Files API Uploads Across a Fleet of Apps
Files API uploads quietly expire after 48 hours. Here's how I keep orphaned files and quota under control across six apps, using reconciliation against my own database and a scheduled cleanup job — written up as production notes from running wallpaper apps.
Recording Provenance for Gemini Output — Designing for Reproducibility and Audit
Before you lose track of which model and prompt produced an output months later: how to stamp provenance metadata onto Gemini generations so quality investigations and model migrations stay reproducible.
Why Firebase AI Logic Returns 403 When Calling Gemini from iOS — And How to Fix It
Firebase AI Logic (formerly Vertex AI in Firebase) often returns 403 PERMISSION_DENIED when calling Gemini from an iOS app. Here is how to isolate the three real causes — App Check enforcement, disabled APIs, and missing Blaze billing — based on hands-on device testing.
A Month of Refreshing App Store Promotional Text Weekly with Gemini
Notes from one month of rewriting App Store promotional text (the 170-character line above the description) weekly with the Gemini API. How I reused a slot that ships without review, what I handed to AI, what I always touched by hand, and whether it moved anything.
Stopping Gemini API Config Drift — Codifying Model IDs and Safety Settings to Catch Cross-Environment Gaps
Most of those puzzling per-app bugs come from drift in model IDs and safety settings between environments. This guide shows how to codify your Gemini config and snapshot the effective settings to detect cross-environment gaps.