◉GEMINI LABJP
●NANOLITE — Nano Banana 2 Lite is here: Google's fastest and most cost-efficient Gemini Image model, made for running lightweight image generation cheaply●OMNIFLASH — Gemini Omni Flash is in public preview, a natively multimodal model that lets enterprises and developers build custom, dynamic video workflows●AGENTS — Managed Agents expand with background: true for async server-side runs and polling, remote MCP server integration, and refreshing credentials across interactions●MEMORY — The Memory Bank IngestEvents API is generally available, decoupling event ingestion from memory generation so you can stream content continuously●THROUGHPUT — Provisioned Throughput now lets you submit up to seven pending orders for the same model and region●DEPRECATE — Image generation models shut down on August 17, and the Grok 4.1 family on the Gemini Enterprise Agent Platform on August 20●NANOLITE — Nano Banana 2 Lite is here: Google's fastest and most cost-efficient Gemini Image model, made for running lightweight image generation cheaply●OMNIFLASH — Gemini Omni Flash is in public preview, a natively multimodal model that lets enterprises and developers build custom, dynamic video workflows●AGENTS — Managed Agents expand with background: true for async server-side runs and polling, remote MCP server integration, and refreshing credentials across interactions●MEMORY — The Memory Bank IngestEvents API is generally available, decoupling event ingestion from memory generation so you can stream content continuously●THROUGHPUT — Provisioned Throughput now lets you submit up to seven pending orders for the same model and region●DEPRECATE — Image generation models shut down on August 17, and the Grok 4.1 family on the Gemini Enterprise Agent Platform on August 20
TAG

finish-reason

3 articles
← Back to all tags
Related:
gemini-api3troubleshooting3python2typescript2error-handling2max-tokens1recitation1
◈ Gemini API/2026-06-14Intermediate

When Gemini API Cuts Your Response Off Mid-Sentence — Detecting finish_reason: MAX_TOKENS and Stitching the Continuation

Long-form generation that ends mid-sentence is usually finish_reason: MAX_TOKENS. This failure arrives as a quiet HTTP 200, no exception. Here is how to detect it, stitch a continuation to recover the full text, and avoid the thinking-token trap that makes it worse on 3.x models.

◈ Gemini API/2026-06-12Intermediate

Reverse-Engineering Empty Gemini API Responses with finish_reason — Triage, Retry Classification, and Monitoring

An empty response.text has three distinct failure layers — candidates, prompt_feedback, and finish_reason. Production code for detecting thinking-token starvation, classifying what is worth retrying, and monitoring your empty-response rate.

◈ Gemini API/2026-05-03Intermediate

Why Gemini API Returns RECITATION as finish_reason — and How to Fix It

When Gemini API silently truncates responses with finish_reason RECITATION, the request technically succeeds with HTTP 200 — but the output is gone. Here's what actually triggers it and how to recover.