<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Timeouts on Jamal Yusuf</title><link>https://jamal.dev/tags/timeouts/</link><description>Recent content in Timeouts on Jamal Yusuf</description><generator>Hugo</generator><language>en-us</language><lastBuildDate>Wed, 10 Jun 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://jamal.dev/tags/timeouts/index.xml" rel="self" type="application/rss+xml"/><item><title>Context Is the Kill Switch: Go, Cancellation, and LLM Timeouts</title><link>https://jamal.dev/writing/go-context-llm-timeouts/</link><pubDate>Wed, 10 Jun 2026 00:00:00 +0000</pubDate><guid>https://jamal.dev/writing/go-context-llm-timeouts/</guid><description>&lt;p&gt;The first time I watched an agent runaway eat a month&amp;rsquo;s inference budget in an afternoon, nobody blamed the model. They should have blamed &lt;strong&gt;the missing kill switch&lt;/strong&gt;.&lt;/p&gt;
&lt;p&gt;The model kept going because nothing told it to stop. Tool calls chained. Retries compounded. Goroutines — or their equivalent — waited politely for a provider that had already left the building.&lt;/p&gt;
&lt;p&gt;In Go, the kill switch has a name: &lt;code&gt;context.Context&lt;/code&gt;. And I think it is the most underrated tool in production LLM orchestration.&lt;/p&gt;</description></item></channel></rss>