Mixing Text and Images in One File Search Skewed My Results Toward Images — Rebalancing by Modality After Retrieval
When you put text and images in a single File Search store with gemini-embedding-2, results can quietly skew toward one modality. Here is how to measure that skew and even it out after retrieval, using per-modality normalization and quota-based merging — with working code.
A Promotion Gate So gemini-flash-latest Flipping to 3.5 Flash Doesn't Break Your Pipeline at 3 AM
Floating aliases like gemini-flash-latest swap their target on every GA, quietly shifting the assumptions your unattended automation depends on. Here is a role-to-pinned-ID indirection layer, an acceptance harness that measures four metrics against your own golden set, and threshold-driven promotion and automatic rollback — with working code.
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.
Don't Retry Every Gemini 429 — Telling Rate Limits Apart From Spend Cap Exhaustion
A 429 RESOURCE_EXHAUSTED can mean 'wait a second and it clears' or 'you're out of budget for the month.' Now that Project Spend Caps is generally available, the second case is real in production. Here's how to classify the two and build a retry layer plus a circuit breaker around them.
When Gemini Computer Use Acts on a Stale Screen and Fails Quietly — Field Notes on Guarding the Loop
A Computer Use agent will click based on a screenshot taken moments ago, miss the real target, and throw no error. These are field notes on measuring those silent misclicks and stopping them with an observe-act-verify loop.
When Gemini's Safety Filter Silently Drops Legitimate Output — Field Notes on Catching False Positives Without Turning Everything Off
Field notes on handling Gemini API false positives in production without disabling every category. Separating input blocks from output blocks, instrumenting per-category false-positive rates, and recovering by relaxing only the offending category.
When your Gemini API spend cap trips, paying users go down too — isolating the blast radius with per-tier projects
A Project Spend Cap stops the entire project at once. To keep a runaway free tier from taking paying users down with it, this is a design note on isolating the cap's blast radius across per-tier projects and closing the ~10-minute delay with an application-side soft budget gate.
Gemini API × TypeScript Type-Safe AI Application Architecture — Integrating Zod Schemas, Structured Output, and Streaming
Type-safe AI applications with the Gemini API and TypeScript: Zod validation, Structured Output, streaming pipelines, and error handling that holds up in production.
When Gemini's Structured Output Quietly Drifts From Your Schema — Field Notes on Measuring Validation and Retries
Even with response_schema set, Gemini's structured output occasionally drifts in production. Stop swallowing failures, measure them, split causes by finish_reason, and feed errors back for a corrected retry. Field notes from stabilizing a validation pipeline.
The Morning a Preview Image Model Went Dark — Migrating to GA Gemini Image Models and Building a Deprecation-Resilient Pipeline
With gemini-3.1-flash-image-preview and gemini-3-pro-image-preview retired, here is how to migrate to the GA models and design an image pipeline that no longer gets caught off guard by deprecation dates — with code and cost math, plus video-to-image thumbnail automation.
Gemini API × Cloudflare D1: A Zero-Cold-Start AI Backend Under $10/Month — Implementation Notes
Build a zero-cold-start, globally distributed AI backend with Cloudflare Workers + D1 (edge SQLite) and Gemini API — conversation history, rate limiting, post-stream write latency, and a real $8.50/month cost breakdown, from a deployment I actually operate.
Your File Search Store Goes Stale in Production — Catalog Sync and Drift Detection That Actually Hold
Load a catalog into File Search once and forget it, and within weeks it starts confidently pointing users at assets you already pulled. Here is the sync pipeline I run: hash-based incremental import, a blue/green rebuild that swallows deletions, and a nightly drift audit.