Bulk Processing Without the 429s: Adaptive Concurrency for the Gemini API
Pushing tens of thousands of requests through the Gemini API with a fixed concurrency almost always produces 429s and dropped items. Here is an AIMD design that auto-tunes concurrency from the 429 feedback, with a bounded worker pool, a dead-letter queue, and resumable checkpoints.
The Day You Switch Gemini Embedding Models: Designing a Zero-Downtime Reindex
Upgrade your embedding model and every vector you ever stored becomes incompatible. Here is a dual-index design for re-embedding hundreds of thousands of vectors without downtime, complete with a resumable reindex job and a query-side abstraction layer.
Preserving Gemini 3 Thought Signatures So Multi-Turn Function Calling Doesn't Degrade
When you build function calling on Gemini 3 thinking models, reasoning quality often drops from the second turn onward. The cause is usually a dropped thought signature. Here is how to keep it and verify the effect.
Propagating a Time Budget Through a Multi-Stage Gemini Pipeline
A field memo on killing DEADLINE_EXCEEDED errors in an in-app help search by carrying a single request-wide deadline through the embed, search, and generate stages — sizing maxOutputTokens from the remaining budget and reserving a fallback budget so a breach returns a partial answer instead of an error.
Running an SLO and Error Budget for the Gemini API as an Indie Developer — Guarding Four Sites with Burn-Rate Monitoring
Notes from running the Gemini API inside four production sites as an indie developer. A practical SLO and Error Budget design that fits a single-person operation: Cloudflare Workers and KV for burn-rate calculation, simplified multi-window alerts, and decision rules for what to freeze when the budget runs out.
Coalescing Gemini API Requests with SSE Fan-out: Collapsing 100 Simultaneous Hits into a Single Call
How I rebuilt the post-push-notification thundering herd on a 50M-download wallpaper app into a Cloudflare Durable Objects coalescer with SSE fan-out, cutting Gemini API costs by 92% with 14 days of production telemetry.
Designing a Semantic Cache for the Gemini API — Embedding-based Answer Caching That Actually Pays for Itself
A practical design for a semantic cache that sits in front of the Gemini API. Combines text-embedding-004, cosine similarity thresholds, versioned cache keys, and TTL design to balance hit rate and answer quality, with Python and Cloudflare Vectorize code that runs in production.
Running Streamlit + Gemini as a Production BI Dashboard — Auth, Cost, Caching, Rate Limits, Observability
A design memo for promoting a Streamlit + Gemini data analysis app into a real multi-user internal BI dashboard — authentication, cost optimization, result caching, per-user rate limits, and observability, all from production experience.
Taming Gemini API Tail Latency with Request Hedging: A p99 Design Notebook
A four-month operational journal of taming Gemini API tail latency with hedged requests across a production indie app portfolio. Includes measured p50/p95/p99 numbers, a working Swift and TypeScript implementation, and the cost-control parameters that kept monthly billing growth under 18%.
Why Your Gemini File API Uploads Vanish After 48 Hours — and How to Code Around It
Gemini File API resources are auto-deleted 48 hours after upload. Here is how to recognize the failure, why it happens, and concrete patterns for re-uploading, falling back to inline data, and managing expiration safely.
Gemini API × Sentry: A Production Pipeline for LLM Error Tracking and Prompt Failure Observability
Pair Sentry's error tracking with Gemini-specific failure modes so you can catch safety filter blocks, recitation rejections, empty completions, and quiet latency drift in production.
When Gemini API Streaming Cuts Off Mid-Response in Production: The Diagnosis Order I Run
How I diagnose mid-response cutoffs in Gemini API streaming - the order I check network, SDK, and server-side suspects, with real cases from indie production.