Author Archives: setevoy

Kubernetes: a “Detective Work” with the OOM Killer, Linux cgroups, and cAdvisor container_memory
0 (0)

29 October 2026

We ran into a pretty standard OOM Killer issue in Kubernetes. I thought I would take a quick look – but somehow it “suddenly” turned into a pretty decent post. What made it even better is that I hadn’t dug into things like Linux OOM Killer, cgroups, memory types and Kubernetes limits myself for quite… Read More: Kubernetes: a “Detective Work” with the OOM Killer, Linux cgroups,… »

Starlink: Installation, Activation, Registration, and Connecting to Wi-Fi
0 (0)

27 October 2026

In the post Preparing for Winter 2026-2027: “And So It Begins” – Getting Ready for Winter and Blackouts (in Ukrainian only, as it’s too specific), I wrote that I’d ordered myself a Starlink – it finally arrived, and I finally got it connected. I thought there wouldn’t be much to write about – but there… Read More: Starlink: Installation, Activation, Registration, and Connecting to Wi-Fi0 (0) »

PHP: PHP2Shell – CVE-2026-109618 and CVE-2026-109619, Temporary Fix
0 (0)

21 October 2026

UPD: The official patch is already out, see PHP 8.5.12 Release Announcement. But it’s not available in the Amazon Linux repositories yet. I barely had time to recover from the issue with Updraft and the RTFM hack the day before yesterday – and here we go again. But this time, I’d really like to avoid… Read More: PHP: PHP2Shell – CVE-2026-109618 and CVE-2026-109619, Temporary Fix0 (0) »

RTFM: TeamUpdraft (UpdraftPlus) and WordPress Hack on the RTFM Blog
5 (1)

20 October 2026

The morning of October 19 didn’t start with coffee – but there was plenty of adrenaline. The first thing I saw when I woke up was Telegram alerts telling me that something had gone wrong with RTFM: At first, I didn’t pay much attention. PHP error alerts do happen occasionally, so I made myself some… Read More: RTFM: TeamUpdraft (UpdraftPlus) and WordPress Hack on the RTFM Blog5… »

LiteLLM: PostgreSQL Failed Requests, AWS RDS, and “Manual Debugging”
0 (0)

7 October 2026

This one turned out to be a bit unusual 🙂 Unusual in the sense that it’s actually quite “usual” – usual in the way posts like this were written back in the old days, in the age of mammoths – before LLMs and AI agents: today I was debugging an issue, and decided to do… Read More: LiteLLM: PostgreSQL Failed Requests, AWS RDS, and “Manual Debugging”0 (0) »

AI: LLMs, Agents, Work, and Us – Engineers. Personal Thoughts.
0 (0)

30 September 2026

A very random text. Wasn’t planned at all, and there aren’t that many posts like this on this blog, but sometimes something “clicks in my head” (while there’s still something there to click) – and a thought takes shape that I want to express in a text like this, to save it. “Agentic development is… Read More: AI: LLMs, Agents, Work, and Us – Engineers. Personal Thoughts.0… »

AI: LLM Spend Control with LiteLLM Budgets and OpenAI Limits
0 (0)

24 September 2026

The main goal we had when introducing LiteLLM AI Gateway on the project (see LiteLLM: AI Gateway for LLMs – features overview) was access and cost control, because right now we can’t enable auto-recharge for our OpenAI or OpenRouter account: our startup is still in the development and experimentation stage, developers actively use AI agents… Read More: AI: LLM Spend Control with LiteLLM Budgets and OpenAI Limits0… »

LiteLLM: Debugging AI Cost Monitoring with VictoriaMetrics
5 (1)

16 September 2026

Had a pretty interesting case with monitoring LLM costs through LiteLLM when using multiple providers. What we have: LiteLLM: AI Gateway, all our services work through it, it proxies requests to providers, generates metrics and traces, controls access, spending, etc. OpenAI and OpenRouter: currently the two main providers LiteLLM sends requests to some clients (our… Read More: LiteLLM: Debugging AI Cost Monitoring with VictoriaMetrics5 (1) »

LiteLLM: Custom Callbacks and LLM Evaluations with Judge LLM
0 (0)

11 September 2026

A quick recap of what we are doing on the project right now: we have a separate hardware server (hostname == “Matrix”), where we run our own self-hosted models with llama.cpp. In our Kubernetes cluster we have a LiteLLM AI Gateway for our clients – Backend API and other project services. Clients send their OpenAI/Anthropic/OpenRouter… Read More: LiteLLM: Custom Callbacks and LLM Evaluations with Judge LLM0 (0) »

LiteLLM: Custom Callback for Traffic Mirroring and OTel Tracing to VictoriaTraces
0 (0)

9 September 2026

We’re currently setting up our own hardware server where we want to run self-hosted models. But we can’t just switch client traffic to them right away – first we need to see how these self-hosted LLMs will actually perform. So the general idea for now is to keep sending traffic to the primary provider, OpenAI… Read More: LiteLLM: Custom Callback for Traffic Mirroring and OTel Tracing to… »