GEMINI LABJP
API — The Interactions API is now generally available and is the default for Google AI Studio, the Gemini API, and the docs, with a toggle back to the legacy formatAGENTS — With GA, the Interactions API schema is stable and adds Managed Agents and background execution — a good moment to revisit how you run long batchesTRANSLATE — Near-real-time speech-to-speech translation across 70+ auto-detected languages is rolling out in the Live API, AI Studio, and the Google Translate appNOTEBOOK — NotebookLM has been renamed Gemini Notebook, now used by over 30 million people and 600,000+ organizationsMODEL — Gemini 3.5 Flash is the newest broadly available release. The flagship Gemini 3.5 Pro is running months behind while its coding ability is improvedSIRI — Apple picked a custom 1.2-trillion-parameter Gemini model to power the rebuilt Siri, shipping with iOS 27 later this yearAPI — The Interactions API is now generally available and is the default for Google AI Studio, the Gemini API, and the docs, with a toggle back to the legacy formatAGENTS — With GA, the Interactions API schema is stable and adds Managed Agents and background execution — a good moment to revisit how you run long batchesTRANSLATE — Near-real-time speech-to-speech translation across 70+ auto-detected languages is rolling out in the Live API, AI Studio, and the Google Translate appNOTEBOOK — NotebookLM has been renamed Gemini Notebook, now used by over 30 million people and 600,000+ organizationsMODEL — Gemini 3.5 Flash is the newest broadly available release. The flagship Gemini 3.5 Pro is running months behind while its coding ability is improvedSIRI — Apple picked a custom 1.2-trillion-parameter Gemini model to power the rebuilt Siri, shipping with iOS 27 later this year
ARTICLES

All Articles

All (733) Gemini Basics (57) Dev Tools (106) API & SDK (405) Advanced (110) Workspace (37) Updates (18)
API & SDK/2026-06-14Intermediate

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.

API & SDK/2026-06-13Advanced

Rebuilding a Three-Layer RAG Cache After Migrating to Gemini 3.5 Flash

When Gemini 2.0 Flash was retired, I rebuilt my RAG caching stack around 3.5 Flash. Here are the working implementations for response, semantic, and embedding caches, measured hit rates from production, and how self-managed caching divides the work with the API's Context Caching.

API & SDK/2026-06-13Advanced

Where to Adopt Gemini 3.5 Flash GA First — Per-Workload Evaluation and a Staged Rollout with a Model Router

How I migrated production workloads to Gemini 3.5 Flash GA in stages: a per-workload evaluation harness, measured results, an env-based model router, and rollback design.

API & SDK/2026-06-13Advanced

The Morning Gemini Generated Fine but the Publish Crashed — A 'Generation Outbox' So Expensive Output Is Never Lost

Generation succeeds, then the process dies right before publishing. The expensive output is gone, and you pay for the same generation again. Here is a 'generation outbox' that persists the output first and turns publishing into an idempotent follow-up, plus what it did for me during the June outage.

API & SDK/2026-06-13Intermediate

Reading a Night of Logs in Three Minutes — Building My Own Daily Brief for Ops With the Gemini API

Inspired by Gemini's Daily Brief, I built a pipeline that turns overnight operations logs into one morning email: collect, summarize with response_schema, render, deliver — with measured token counts and a fallback that kept working through the June outage.

API & SDK/2026-06-12Intermediate

Letting File Search's Multimodal Mode Find Wallpapers I Couldn't: A Field Report

I tested whether File Search's new multimodal retrieval (gemini-embedding-2) could replace category tags for finding one wallpaper among thousands. A 300-image trial, the walls I hit, and where semantic search actually fits — with working code.

API & SDK/2026-06-12Intermediate

Building an App Store Rejection Workflow with the Gemini API — From Structured Notices to Resolution Center Replies

How I use the Gemini API to parse App Store rejection notices into structured JSON, cross-check guidelines, draft Resolution Center replies, and run pre-submission checks as an indie developer.

API & SDK/2026-06-12Intermediate

Is Anyone Actually Using Your Gemini Feature? Measuring Acceptance, Regeneration, and Edit Distance

Token charts will not tell you whether users embrace a Gemini-powered feature. A practical design for measuring acceptance rate, regeneration rate, and edit distance with Swift and BigQuery, with two weeks of real numbers.

API & SDK/2026-06-12Advanced

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.

API & SDK/2026-06-12Intermediate

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.

API & SDK/2026-06-12Intermediate

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.

API & SDK/2026-06-12Intermediate

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.