GEMINI LABJP
ROBOTICS — The ER 1.6 preview that shut down on August 31 does have a successor. Gemini Robotics ER 2 is in public preview, in both standard and streaming variantsVIDEO — ER 2 judges success and failure from live video rather than still snapshots, which is what lets it catch spills, slips, and misalignments while a task is still runningDEADLINE — Next up is September 30, when gemini-omni-flash-preview is retired. The target is gemini-omni-1.1-flash, GA since August 27, and there are now under four weeks leftAPIKEY — Every remaining standard API key, restricted ones included, stops working during September. The replacement is an auth key bound to a Google Cloud service accountPRICE — Gemini 3.7 Flash keeps its introductory $0.75/$3.75 per 1M through December 31, then moves to $1.50/$7.50 on January 1, 2027. Any estimate crossing the year needs both figuresAUDIO — Gemini 3.5 Transcribe handles language detection across 85+ languages, speaker diarization, word-level timestamps, and custom vocabulary biasing of up to 1,000 termsROBOTICS — The ER 1.6 preview that shut down on August 31 does have a successor. Gemini Robotics ER 2 is in public preview, in both standard and streaming variantsVIDEO — ER 2 judges success and failure from live video rather than still snapshots, which is what lets it catch spills, slips, and misalignments while a task is still runningDEADLINE — Next up is September 30, when gemini-omni-flash-preview is retired. The target is gemini-omni-1.1-flash, GA since August 27, and there are now under four weeks leftAPIKEY — Every remaining standard API key, restricted ones included, stops working during September. The replacement is an auth key bound to a Google Cloud service accountPRICE — Gemini 3.7 Flash keeps its introductory $0.75/$3.75 per 1M through December 31, then moves to $1.50/$7.50 on January 1, 2027. Any estimate crossing the year needs both figuresAUDIO — Gemini 3.5 Transcribe handles language detection across 85+ languages, speaker diarization, word-level timestamps, and custom vocabulary biasing of up to 1,000 terms
TAG

idempotency

8 articles
Back to all tags
Related:
Gemini API5gemini-api2batch-api2production2Function Calling1Agent Design1Timeouts1Managed Agents1Architecture1Operations1streaming1cost design1
Gemini API/2026-08-08Advanced

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.

Gemini API/2026-07-18Advanced

Keeping a Long-Running Managed Agent Alive Across Sandbox Recycling — Durable Checkpoints and Idempotent Resume

A Managed Agents sandbox can be recycled out from under you. Before 40 minutes of work resets to zero, we design a durable checkpoint that pushes progress outside the sandbox and an idempotent resume that never runs a side effect twice. With working SQLite code.

Gemini API/2026-07-17Advanced

A Gemini stream drops halfway — restart it, or have the model continue?

Most apps silently restart a dropped stream. Here is the arithmetic behind continuing from the partial output instead, and where to put the threshold.

Gemini API/2026-07-04Advanced

Catching the Rows That Quietly Failed Overnight: A Per-Row Retry Ledger for the Gemini Batch API

A SUCCEEDED batch job is not the same as all-rows-succeeded. From running nightly batches as a solo developer, here is a per-row result ledger, a transient-vs-permanent failure classifier, selective retries, and a guard against retrying permanent failures forever, with a working SQLite state machine.

Gemini API/2026-07-03Advanced

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.

Gemini API/2026-06-30Advanced

Fire-and-Forget on a Cron That Never Loses a Result: Reclaiming Gemini Background Executions with a Submission Ledger

A design for running the Interactions API's background execution safely from a cron-driven runner. We reserve a row in a ledger by idempotency key before submitting, then reclaim only outstanding handles on the next tick — shown with working code.

Gemini Advanced/2026-06-27Advanced

Your Gemini Completion Event Will Arrive Twice — An Idempotent Sink That Makes Webhook + Reconciliation Effectively Once-Only

Once you receive Gemini long-running operations over a Webhook and back it up with a reconciliation poller, the same completion arrives twice and publishing or billing runs twice. Build an idempotent sink with a normalized key and a claim-run-commit pattern that keeps side effects effectively once-only.

Gemini API/2026-05-23Advanced

Idempotency Key Design for the Gemini API: Patterns I Use to Prevent Duplicate Generation Across Six Sites

After five months of running six AI-driven sites in parallel, I built an idempotency layer in front of the Gemini API to neutralize retry storms. This deep dive shares the SHA-256 + Cloudflare Workers KV design, the operational numbers behind it, and the four gotchas that only surface in production.