All Articles
After generated_images Disappeared: Three Branches Between the Response and a Saved File
Once you switch to generate_content, the line that breaks is usually the save. Here are the three branches on the response side - zero image parts, a shifting image count, and picking the extension - plus a receiver function you can drop in.
Moving to the Batch Tier Cancels Out the Gemini 3.7 Flash Price Increase Exactly
Introductory pricing for Gemini 3.7 Flash ends on December 31, 2026, and the rate doubles the next day. Here is which models are affected, which are not, and how to project your January bill from the usage you already have.
generate_images Survives Until 2027. Your Image Generation Still Stops on August 17
google-genai 2.18.1 still ships generate_images, and the SDK deprecation notice points at 2027. The imagen-4.0 models, meanwhile, shut down on August 17. Here is what those two deadlines actually mean, measured on my own machine.
Rewriting generate_images as generate_content, where the arguments actually go
Ahead of the August 17 Imagen shutdown, I checked the SDK directly: of the 17 arguments in GenerateImagesConfig, only 5 move across unchanged. Here is the mapping, a compatibility layer that keeps callers working, and a way to verify the request shape without an API key.
A Timeout Was Never Evidence of Failure — Designing Around Blocking Function Calls
When a tool call cannot return until the real-world effect finishes, two habits reverse on you: parallel dispatch and generous timeouts. Measured numbers from a sandbox harness, plus the design that replaces retries with observation.
When Streaming Responses Quietly Lose Non-ASCII Text: Measuring the Byte Boundary and the Event Boundary Separately
I measured why Japanese text disappears from streaming Gemini responses using a local mock SSE server. Two separate layers were broken, one of them silently, and an English-only test suite caught neither.
Retrying a Retired Model Never Showed Up in Success Latency
With the image generation models shutting down soon, I rebuilt a mock server to see what my retry layer actually does when it hits a retired model ID. The damage landed in wall time and queue wait, and never touched the metric I was watching.
Measuring Update Policies for Memory Profiles: The Guard That Cost Me 16 Points of Accuracy
Memory profiles went GA in Memory Bank, making structured memory available to downstream code. I built three update policies and compared them under identical conditions. The one that looked obviously correct turned out to be the worst. Full harness code and the path to per-field TTLs.
Measuring a Guard in environment hooks: 46 Microseconds to Decide, 23 Milliseconds to Start
A record of building a destructive-command guard for Managed Agents environment hooks. A regex denylist let 9 of 20 dangerous commands through; argv parsing reached 100 percent detection. The startup cost turned out to be 500 times the decision cost.
When Sampling Parameters Were Deprecated, Diversity Broke Before Determinism Did
Deprecating temperature, top_p and top_k hurt the diversity-generating side of my pipeline, not the deterministic side. Counting real call sites, moving diversity to the input layer, and measuring effective diversity.
What Decided Our Cascade's Economics Wasn't the Escalation Rate
Putting Flash-Lite in front of 3.6 Flash and escalating only the hard items looks like an easy win. Estimating it from the escalation rate alone will mislead you. Here is the break-even solved with the escalated subset's output length in the equation.
A 17% Drop in Output Tokens Sounded Big. Then I Decomposed the Bill
Output pricing fell 16.67% and output tokens fell about 17%. Adding those numbers does not give you the savings. Here is an exact price/volume/cross-term decomposition, plus a loop measurement where the savings rate went down instead of up.