Designing Batch Image Costs with Nano Banana 2 Lite: Decide by Measuring
How to fold the fastest, cheapest image model, Nano Banana 2 Lite, into high-volume generation: measuring per-image cost, a two-tier setup with a quality model, and retry handling grounded in real numbers.
Splitting Bulk Image Generation Cost in Two with Nano Banana 2 Lite: A Draft-and-Render Design
A two-tier cost design that routes first-pass generation to Nano Banana 2 Lite and final renders to the standard Nano Banana 2, with a minimal Python router you can adapt.
Gemini 3 Multi-Tool Agents: Function Calling + Built-in Tools + Context Circulation in Production
A hands-on look at Gemini 3 multi-tool agents: combining Built-in Tools with Function Calling, Context Circulation, and parallel tool IDs, with measured latency numbers and the pitfalls I hit in production.
When Two Managed Agents Fight Over the Same Repo: External Leases and Fencing for Isolated Sandboxes
Every Managed Agents run gets its own isolated sandbox, so a local lock cannot stop two runs from touching the same repo or record. Here is how I serialize them safely with an external lease and a fencing token.
Before the August 17 Gemini Image Model Shutdown: Inventory Where You Actually Call Them First
Some Gemini image generation models retire on August 17. Before choosing a replacement, here is how to inventory which models are actually being called, and from where, using your request logs.
Your Tool Results Are Quietly Eating the Conversation — Handle Passing to Keep Gemini Function Calling Contexts Lean
Tool results linger in Function Calling history and compound your input tokens every turn. Two implementations — a token-budgeted compactor and handle passing — cut my measured input by roughly 8x, with the pitfalls I hit along the way.
Your Night Batch Is Causing the Morning 429s — Priority Admission Control for a Shared Gemini Quota
When bulk jobs and interactive features share one project's RPM/TPM, the bulk lane wins by default. A priority token bucket design with measurements: 429 rate 3.2% down to 0.03%.
Stop Making Listeners Wait for the Whole File — Wiring Gemini TTS Streaming into Your Delivery Path
gemini-3.1-flash-tts-preview now streams audio via streamGenerateContent. A delivery path with 1.8s to first sound, covering PCM boundary handling, sentence-level resume, and a fallback for preview shutdown.
A Webhook Is a Claim, Not a Fact — Three Layers of Defense for Your Gemini Webhooks Endpoint
Your Gemini Webhooks receiver is a public URL, which means forged events, replays, and duplicate deliveries are all on the table. This walkthrough builds a three-layer defense — reachability checks, dedupe, and a lightweight handler that re-fetches truth from the API — with working FastAPI and SQLite code.
Deleting the Source Isn't Enough — A Ledger Design for Propagating Deletes Through Gemini-Derived Data
When a user deletes their data, the embeddings, caches, and File Search documents you generated from it live on. A provenance ledger written at generation time, per-sink propagation workers, and a verification sweep make deletion actually reach your derived data.
url_context Still Answers When the Fetch Fails — Gating on Retrieval Status Before You Trust It
The url_context tool returns a confident answer even when it failed to fetch the target page. This walks through reading url_retrieval_status from url_context_metadata to build a verification gate, plus a fallback that only finalizes an answer when the source URL was truly read.
Locking Down a Gemini API Key on Servers Whose IP Keeps Changing — Restrictions for Headless Automation
After unrestricted keys started getting blocked, headless server automation whose egress IP changes every run can't cleanly use HTTP referrer, app restrictions, or an IP allowlist. Do you get by with API restrictions alone, funnel egress through a fixed IP, or move server workloads off API keys onto Vertex service-account auth? A decision framework and working code, without taking your pipelines down.