I stopped storing every generation log — three retention tiers and a prompt fingerprint that keeps traceability
I was storing every Gemini API request and response body for debugging. Here is how I moved to three retention tiers plus a prompt fingerprint, and kept the ability to diagnose issues without keeping the text.
When a Batch Job Sat in RUNNING for Half a Day: Field Notes on Catching Stalls Early with Per-State Dwell Budgets and Record Reconciliation
When a Gemini Batch job stalls quietly under the shadow of the 24-hour SLA, per-state dwell-time budgets and submitted-vs-completed record reconciliation let you name the stall early. Field notes with real operational numbers.
When Context Caching Didn't Lower My Gemini Bill — Field Notes on Measuring the Real Hit Rate
When Context Caching is enabled but the Gemini API bill barely drops, this field note measures the real hit rate from usage_metadata, separates TTL churn from fragmentation, and walks through a staged recovery.
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.
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 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%.
When the Gemini Review Bot in Your CI Quietly Stops Earning Its Keep — Rebuilding Trust with Coverage and Actioned-Rate Metrics
A Gemini-powered PR review bot in GitHub Actions degrades without ever throwing an error. Field notes on catching diff truncation, model alias drift, and swallowed parse failures with one-line JSON logs and an actioned-rate metric.
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.
After You Improve the Prompt, How Far Back Do You Regenerate? — Designing a Budget-Bounded Backfill
A prompt improvement only helps future output — thousands of old artifacts stay on the previous generation. This piece covers a budget-bounded backfill: selection scoring, edit-detection hashes, a pre-replacement gate, and a resumable cursor, with working code.
Keeping Unattended Jobs From Failing Silently: A Preflight Gate for Gemini's Platform Changes
Unrestricted API keys are now rejected, the old CLI reached end of life, and the Interactions API is becoming the default entry point. These 2026 platform shifts stop working automation without raising an error. Here is a preflight gate, with runnable code, that catches the failure before the batch runs.
Stopping Runaway Costs Twice: Project Spend Caps Plus an App-Side Soft Limit
Pairing Gemini API Project Spend Caps (a monthly USD ceiling) with an app-side soft circuit breaker that trips before the hard cap. Includes a working Python and sqlite daily cost ledger.
Finding Every Reference to the Image Preview Models Before They Stop on June 25
gemini-3.1-flash-image-preview and gemini-3-pro-image-preview stop on June 25. Here is a dependency audit for surfacing references buried in rarely-run branches and batches before the cutoff.