标签：#EV

Every developer building on AWS eventually runs into the same frustrations: waiting for deployments just to verify a small change, needing an internet connection for local development, watching cloud costs grow during testing, and discovering issues in CI that could have been caught earlier. That's exactly why we built LocalEmu. LocalEmu is an open-source AWS emulator that lets you build and test against AWS APIs entirely on your own machine. It supports 132 AWS services and works with the tools you already use every day—AWS CLI, boto3, Terraform, AWS CDK, and Pulumi. Instead of changing your workflow, you simply point your tools to localhost:4566 and continue developing. Unlike many local emulators that only mock API responses, LocalEmu focuses on realistic behavior where it matters most. Lambda functions execute using the official AWS runtime images. EC2 instances run as real containers connected through a virtual network with enforced security groups. RDS uses real PostgreSQL and MySQL engines, and optional IAM policy enforcement allows you to validate authorization rules before deploying to AWS. Getting started takes only a couple of commands: pip install localemu [runtime] localemu start Once running, you can use the included awsemu CLI or simply point your existing AWS CLI, boto3, Terraform, CDK, or Pulumi configuration to localemu. No new SDKs or complex setup are required. LocalEmu also includes a built-in dashboard that launches automatically. It provides a live overview of running services, resource exploration, an S3 object browser, a DynamoDB viewer, CloudTrail event history, and a real-time activity feed so you can inspect what's happening inside your local cloud environment. The biggest advantage is speed. You can iterate in seconds instead of minutes, experiment freely, reset your environment whenever you want, and develop without an AWS account, credentials, or cloud costs for local testing. We're actively improving LocalEmu and would love feedback f

The Quest Begins (The "Why") I still remember the first time I tried to track down a bug that only showed up after midnight. I opened my terminal, typed git log , and was greeted by a wall of commits that read like a toddler’s grocery list: * 7a9c3f1 (HEAD -> main ) fix stuff * 4b2e8a1 update * f1d9c6b wip * 9e3b7d2 more changes * … I spent three hours chasing a regression that turned out to be a one‑line typo in a file I hadn’t touched in weeks. The commit messages gave me zero clues, and the diff was a tangled mess of unrelated changes. I felt like I was wandering through a dungeon without a map, hoping the next room would hold the answer. That night I realized the real monster wasn’t the bug—it was the way I was committing code. My commits were large, vague, and scattered , making every subsequent step (review, revert, bisect) a gamble. If I wanted to keep my sanity (and maybe even enjoy coding again), I needed a better system. The Revelation (The Insight) The turning point came when I read about Conventional Commits —a lightweight convention that gives each commit a clear type ( feat , fix , docs , refactor , test , chore , etc.) and a short, descriptive message. It sounded simple, but the impact was massive: Atomicity – each commit does one thing. Clarity – the message tells you why the change exists, not just what changed. Automation – tools can generate changelogs, version bumps, and even release notes straight from the log. Adopting this felt like discovering a hidden shortcut in a Zelda dungeon—suddenly the whole map made sense, and I could sprint to the boss room with confidence. Wielding the Power (Code & Examples) Before – The Chaos Imagine we’re building a tiny API for user profiles. Here’s what a typical day of committing looked like (messages only, but the diffs were just as messy): $ git log --oneline -5 7a9c3f1 ( HEAD -> main ) fix stuff 4b2e8a1 update profile handler f1d9c6b wip 9e3b7d2 added auth middleware c5d4e3f refactor utils If I needed to ro

Headline: Tailwind v4 is the most significant rewrite since the framework launched — CSS-first config, Lightning CSS under the hood, container queries built-in, and no more tailwind.config.js . I migrated two production projects and here's what actually broke and what the upgrade tool misses. Tailwind CSS v4 arrived with a steeper upgrade curve than most version bumps in the JS ecosystem. The configuration story changed completely. The build engine changed. Several features that previously required plugins are now built-in. The headline change: no more tailwind.config.js In v3, configuration lived in a JavaScript file — theme extensions, plugins, content paths. In v4, it moves into your CSS: @import "tailwindcss" ; @theme { --color-brand : #6366f1 ; --spacing-18 : 4.5rem ; } Theme tokens become CSS custom properties under @theme , and Tailwind generates utility classes automatically. The content array is gone — v4 detects source files automatically. The new engine: Lightning CSS Tailwind v4 ships with Lightning CSS replacing PostCSS as the default: Build times drop significantly (cold rebuild went from ~8s to under 3s on the dashboard) CSS nesting works natively without a plugin Modern CSS features like color-mix() , @starting-style , oklch are transpiled automatically autoprefixer is no longer needed New features built-in Container queries — native in v4, no plugin needed: <div class= "@container" > <div class= "grid grid-cols-1 @sm:grid-cols-2" > ... </div> </div> 3D transforms — rotate-x-45 , rotate-y-12 , perspective-1000 for card flip effects without inline styles. Dynamic spacing — p-13 , mt-22 work without explicit definition. Migration: the upgrade tool and what it misses npx @tailwindcss/upgrade@next The codemod handles the mechanical parts. What it missed: Custom plugins — the JS plugin API changed; non-trivial v3 plugins need a rewrite to the new @plugin / @utility API theme() calls in CSS — replace theme('colors.zinc.900') with var(--color-zinc-900) ; gr

Local LLM inference has an expensive habit: It recomputes prefixes it has already seen. A system prompt. A reused RAG document. A few-shot block. A long static context. If the prefix is identical, why pay the prefill cost again? That's the problem I explored with EdgeSync-LLM. The idea The mechanism is simple: Prompt = shared prefix + new suffix On the first request, EdgeSync prefills the prefix and captures its KV cache state. On the next request sharing that exact prefix, it restores the state and decodes only the new suffix. No llama.cpp fork. No patch. The current validated path uses the public: llama_state_seq_get_data and llama_state_seq_set_data APIs. Measured on a real Android ARM64 phone Model: Qwen2.5-0.5B-Instruct Q4_K_M Shared prefix: 123 tokens 40 requests. 4 threads. Release build. Path Mean TTFT p50 p95 Cold 4828 ms 4752 ms 5297 ms KV state reuse 486 ms 476 ms 569 ms 9.9× lower TTFT on cache hits. The warm path was approximately: 363 ms to decode the 10-token suffix 123 ms to restore the state blob Fragment size: 1.64 MB I also measured the same mechanism on x86-64. Cold mean TTFT: 1395 ms Warm mean TTFT: 185 ms That's 7.5× on cache hits. But I almost published a fake 8.8× speedup This was the most important part of the project. My first implementation directly copied raw K/V tensors. It was fast. Very fast. The benchmark reported an 8.8× speedup. There was one problem. It was wrong. llama.cpp tracks more than the K/V tensor values. Cache cells also have position and sequence metadata used to construct the attention mask. Copying tensor values without restoring that bookkeeping produced an inert fragment. The model skipped prefix computation... ...but attention could not actually see the restored prefix. 14 of 24 cache hits reproduced, token for token, the output of a generation with no prefix at all. The “speedup” was dropped context. So I discarded it. Timing is not enough A broken cache can be fast. That's why EdgeSync now runs two correctness chec

I've been building apps with IndexedDB for years. The local part works fine — store data, query it, show it on screen. The hard part is keeping that data in sync with a server when the network comes and goes. Most tutorials show you how to build an offline app with a framework. Firebase, RxDB, WatermelonDB. Those work, but they bring their own abstractions, their own sync protocols, their own opinions. I wanted something simpler. A database with a sync API that doesn't dictate how my backend works. Here's the setup I landed on. npm: npm install ctrodb Docs: ctrodb.vercel.app/docs/sync/overview What We're Building A notes app that works offline. Create and edit notes on the train, in a tunnel, on a plane. When the network comes back, everything syncs automatically. The database is ctrodb (zero-dependency, browser-based). The backend is anything that speaks HTTP. Step 1: Database Setup import { Database , syncPlugin , HttpTransport } from " ctrodb " const db = new Database ({ name : " notes-app " , schema : { version : 1 , collections : { notes : { fields : { title : { type : " string " , required : true }, body : { type : " string " }, updatedAt : { type : " string " , default : () => new Date (). toISOString () }, }, indexes : [{ field : " updatedAt " }], }, }, }, }) await db . connect () Every collection you want to sync needs a timestamp field. The sync engine uses it to order changes and detect conflicts. Plugins are passed in the Database constructor via plugins array: const transport = new HttpTransport ({ url : " https://api.myapp.com/sync " , }) const db = new Database ({ name : " notes-app " , schema : { ... }, plugins : [ syncPlugin ({ transport })], }) await db . connect () The transport takes a single base URL and appends /push and /pull automatically. The sync plugin hooks into every write operation and records it in the change log. The plugin exposes devtools that take the database instance as their first argument: import { inspectSyncQueue , retryFaile

If you've ever bid on a public sector contract, you know the PQQ drill. Someone sends you a Word document with 47 questions spread across 6 sections. Company info. Technical capability. Financial standing. Health & safety. References. Maybe something about modern slavery or carbon reporting because it's 2026 and everything has to check everything. You have to: Read every question Figure out what category it falls under Decide which ones are easy and which will take a week Dig up the right evidence for each one Track word limits And you're doing this at 10pm because the submission deadline is Friday. I got tired of doing this manually, so I built a free tool that does it in one click. What it does PQQCheck takes any PQQ document — pasted raw, formatting and all — and runs it through an LLM that understands procurement documents. It returns: Every question extracted — no more re-reading the document to check you didn't miss one Category tags — Technical, Financial, H&S, Insurance, etc. Difficulty ratings — Easy / Medium / Hard at a glance so you know where to start Suggested evidence — what to prepare for each question Word limits — pulled straight from the document Here's what the output looks like: | Question | Category | Difficulty | Suggested Evidence | Limit | |-----------------------------------|-------------|------------|----------------------------|-------| | Provide your registered name & no | Company | Easy | Certificate of Incorporation | 50 | | Describe IT managed services exp | Technical | Hard | 3 case studies + CVs | 500 | | Provide H&S policy | H&S | Easy | Current policy document | — | | ISO 27001 certification details | Technical | Medium | Certificate + scope doc | 200 | Why this matters for procurement teams Most PQQ response planning is reactive. You read the document, start answering, and discover mid-way that a question needs a certificate you don't have or a reference you can't get in time. PQQCheck flips that. You know before you start writing

Ever wondered what would happen if the world's leading Large Language Models settled their benchmark disputes in a 2D cybercity arena? It's easy to look at model performance on standardized benchmarks (like MMLU, MATH, or HumanEval). It is much more fun to visualize their underlying architectures, parameter scales, and hardware constraints as a retro-cyber fighting game. So, we built Model Kombat (Mixture of Experts Edition)! 🕹️ Play Directly Here 🎮 Launch Game in Full Screen 🧬 Playable ML Concepts Explained This isn't just a basic stick-figure fighting game. Every mechanic—from rendering complexity to the speed at which characters recover—is a direct, playable representation of real-world Large Language Model engineering. 1. 📐 Parameter Scaling vs. Render Tiers A model's representation capacity (intelligence) scales with its parameter count. In Model Kombat, a fighter's visual complexity, joint detail, and rendering fidelity directly reflect its real-world parameter size: Tier 1 (< 5B Parameters - Gemma 2B, Llama 3.2 3B) - Primitive Capsules : Drawn as simple, single-color flat limbs with low joint segmentation. This visualizes the limited representation capacity and coarse output resolution of small edge models. Tier 2 (7B - 14B Parameters - Mistral 7B, Claude Haiku) - Simple Vectors : Structured as thin skeletal wireframe vectors. Tier 3 (14B - 35B Parameters - Gemini Flash, Mixtral) - Two-Tone Vectors : Rendered as dual-color, layered vector limbs. Tier 4 (35B - 100B Parameters - Llama 8B, Claude Sonnet) - Cyborg Shading : Rendered as detailed vector cylinders with dynamic code particle streams flowing along their limbs. Tier 5 (> 100B Parameters - o3, GPT-4o, Claude Opus) - Quantum Vectors : Rendered as glowing vector limbs with digital matrix code particles, soft drop-shadow depth buffers, and real-time afterimage motion trails. 2. ⚡ Reasoning Tokens & KV-Cache Overcharging Instead of arbitrary "mana" or "stamina," fighters charge a Ki bar representing interna

Hey DEV community! 👋 If you maintain open-source projects on GitHub, you probably love checking your repository's "Insights" tab. Seeing people clone, view, and star your project is an amazing feeling. But there are two catches that have always frustrated me: The Tedious Click-Fest: To see how your projects are doing, you have to manually open GitHub in your browser, navigate to each repository individually, click "Insights", and then click "Traffic". If you maintain 5+ repos, this becomes a chore real quick. The 14-Day Limit: Even worse, GitHub only keeps your traffic data for exactly 14 days. If you don't check your stats within that window, that data is gone forever. If you want a unified view and historical data, you either have to manually scrape it yourself, write a cron job, or pay a monthly subscription for a third-party SaaS tool. I didn't want to do any of those. So, I built my own solution. 🌟 Enter: Repo-rter Repo-rter is a completely free, 100% open-source desktop application available for Windows, macOS, and Linux. It fetches your GitHub traffic data and caches it locally on your machine, meaning you never lose your historical stats again. TIP Privacy First: Unlike SaaS alternatives, Repo-rter doesn't store your Personal Access Token (PAT) on any server. Everything runs locally on your machine, so your data remains strictly yours. ✨ Key Features Infinite History: Automatically merges new traffic data with your local cache. Say goodbye to the 14-day limit! Release Downloads Tracker: Wondering how many people downloaded your .exe or .dmg? Repo-rter tracks total and individual asset downloads across all your releases. Neo-Brutalist UI: I wanted the app to be fun to use, so it features a vibrant, gamified Neo-Brutalist design. Export to Markdown: Need to show off your stats? Generate and download a beautiful Markdown report of your repo's health and traffic with one click. Cross-Platform: Built with Tauri, it's incredibly lightweight and runs natively on Wi

Week 5 of my Google Summer of Code journey with CircuitVerse ( June 22nd to June 28th ) is officially in the books. After dealing with a rough sickness last week, I’m happy to say this week was incredibly positive . 🔄 Reconnecting with the Community Since I had to miss last week's sync because I was under the weather, I had to attend the CircuitVerse GSoC Contributors' Meeting this week. It felt so good to reconnect with everyone ! I shared the progress I'd managed to scrape together over the last couple of weeks, and the mentors were incredibly understanding and kind about my slower pace due to being sick. The CircuitVerse community is genuinely unmatched! Everyone is so encouraging, and having that layer of support makes a world of difference. It was also super motivating to hear what the other contributors have been up to. Seeing how much progress everyone has made gave me a massive burst of inspiration to jump right back into development! 🛠️ importCanonical.ts is Completed! Once the meeting was over, I officially finished implementing the entire import pipeline in importCanonical.ts! 🥳 This file does the heavy lifting of taking our clean, deterministic canonical JSON and reconstructing the circuit right back onto the user's canvas. Here is what's packed inside: 🔀 Full Multi-Circuit Support: The import pipeline seamlessly handles projects containing multiple individual circuits. 📐 Smart Subcircuit Dependency Resolution: Just like the export pipeline, the import engine now uses Kahn's Algorithm to figure out the exact sequence the circuits need to be loaded in so that nested dependencies never break. 🛑 What's Missing? (For Now): The import pipeline doesn't validate the incoming JSON file . I am waiting until the canonical format is finalised. Once that's locked in, I will add JSON schema validation in the file. 🚀 The PR Status On the GitHub side of things, the three foundational Pull Requests I opened earlier are still actively under review . One of my mentors gav

I built Luxury Hotel Offers , a fully static site with 3,400+ listings that generates 4,400 HTML pages at build time. No SSR, no database at runtime. Here are the four hardest scaling problems I hit. 1. Googlebot's 2 MB HTML Limit With 3,400 hotels on one listing page, the naive approach (render all cards in HTML) produced a 9 MB page. Googlebot truncates at 2 MB and ignores the rest. The fix: cap the initial HTML at 400 cards. The remaining 2,500+ cards are generated as a separate HTML fragment file at a predictable URL ( /data/cards/{slug}-remaining/ ). A "Load More" button injects 48 cards at a time from the fragment. The first search or filter interaction loads the entire fragment so all cards are available for client-side filtering. This keeps every page under 2 MB for crawlers while giving users access to everything. 2. Content-Aware Lastmod with Cascading A site with 4,400 pages can't update every lastmod on every build. Search engines treat that as spam, and IndexNow has rate implications. Instead, the build hashes each hotel's SEO-relevant fields and compares against a persisted store. Only pages with actual content changes get their lastmod bumped. The interesting part is cascading: when a hotel in Paris changes, the Paris city page, France country page, and Europe region page all get their dates updated too, since their content changed (they list that hotel). Changed URLs feed into IndexNow so only genuinely modified pages get pushed to search engines. 3. DOM Filtering Breaks on Mobile at Scale The site started with pure DOM filtering: every card has data-* attributes for region, country, brand, and perks. JavaScript reads attributes and toggles visibility. Zero network requests, instant results. Great on desktop. On a mid-range phone with 2,500+ cards in the DOM, filtering took 2-3 seconds per interaction. textContent traversal across 20-40 nodes per card means ~60,000 DOM visits per keystroke. Layout thrashing with 10,000+ nodes made every show/hide cyc

At my workplace, I worked on an ERP platform used by fashion businesses to manage customers, body measurements, products, orders, invoices, inventory, staff, and other day-to-day operations. Each business also had a public storefront where customers could browse products and check out. The storefront started as a simple sharing feature. Businesses could publish products, copy a link, and send it to customers outside the main workspace. That worked well because the storefront was mostly a product catalogue, and most of the sales process still happened after the customer contacted the business. As the platform evolved, the storefront became much more than a catalogue. Customers were discovering businesses through shared links, browsing products, placing an order, and tracking orders directly from the storefront. That introduced new technical requirements around branded storefronts, SEO, server-rendered metadata, public checkout, pricing, and analytics. This article explores how I designed the storefront around wildcard subdomains, immutable shop identities, server-side shop resolution, and a scalable analytics pipeline. Table of Contents Giving the Storefront Its Own Identity Business Names, Reserved Names, and Subdomains Resolving a Storefront Active and Inactive Storefronts Location and Currency Product Pages and Share Previews Storefront Event Ingestion Processing Raw Events Counting Unique Visitors With HyperLogLog Domain Routing and Local DNS 1. Giving the Storefront Its Own Identity The original storefront was fairly simple. It was a React application that fetched a business and rendered its products. Beyond that, there wasn't much to it. There were no branded storefronts, analytics, subdomains, or even a separate identity beyond the business itself. Introducing those capabilities meant the storefront needed its own data model. I introduced a dedicated shop entity to represent the public storefront. The business remained the source of operational data such as cu

Image generation is where a seemingly simple API client starts to accumulate production bugs. A request may finish inline for one model, return a task for another, or take a longer path when the input includes edits and uploaded files. Treating every successful HTTP response as a completed image is the fastest way to ship broken retry logic and incorrect user-facing status. This post adapts the TokenLab article TokenLab Async Image Generation Tasks for Production Apps . The canonical article contains the full implementation discussion; this version focuses on the contract decisions that matter when building an integration. The response is a delivery decision, not just a payload An image endpoint can return either a completed representation or an asynchronous task. The client should inspect the response envelope and normalize the delivery mode before it touches application state: type Delivery = | { mode : " sync " ; terminal : true } | { mode : " async " ; task_id : string ; status : string ; terminal : false }; The important invariant is that mode and terminal state come from the API contract. Do not infer completion from a missing progress field, a truthy data property, or a fast response time. Progress is useful when present, but it is not the completion signal. Poll by task identity, not by the original request When the server returns an async task, persist the task ID and the provider-neutral status. A worker can then poll the task endpoint with bounded backoff: async function waitForTask ( id : string ) { for ( let attempt = 0 ; attempt < 60 ; attempt += 1 ) { const task = await getTaskStatus ( id ); if ( task . status === " succeeded " ) return task . result ; if ([ " failed " , " cancelled " , " expired " ]. includes ( task . status )) { throw new Error ( `Media task ${ id } ended as ${ task . status } ` ); } await sleep ( Math . min ( 1000 * 2 ** Math . min ( attempt , 5 ), 30 _000 )); } throw new Error ( `Media task ${ id } exceeded the polling budget` );

A while back I set myself a slightly unhinged goal: build a web browser from scratch in Node.js and Electron no external HTML/CSS/layout libraries, everything hand-rolled. URL parser, TCP/TLS socket, HTTP pipeline, HTML tokenizer, DOM builder, CSS tokenizer, CSS parser, style matcher, layout engine, canvas renderer. All of it, from zero. so,I called it Courage Browser . This week, after dozens of daily sessions, I hit a milestone that felt disproportionately satisfying: Courage now renders info.cern.ch the very first website ever put on the internet almost pixel-for-pixel identical to real Chrome. It sounds small. It is not small. Getting there meant chasing down bugs across nearly every layer of the browser. Why info.cern.ch If you haven't seen it, info.cern.ch is CERN's preserved copy of Tim Berners-Lee's original website. It's about as simple as HTML gets — one heading, a paragraph, a bulleted list of links. No CSS file, no JavaScript, no styling of any kind beyond what a browser applies by default. Which is exactly why it's a great test case. If your browser can't get a page with zero author CSS to look right, it has no business trying to render anything more complex. Default styling headings being bold, links being blue and underlined, bullets showing up in the right place has to work before anything else does. The bugs I found by just... comparing screenshots I put a screenshot of Courage's render side-by-side with Chrome's and started listing differences. Two jumped out immediately: The <h1> wasn't bold in Courage, even though it clearly should be. The links had underlines but weren't blue , they were rendering in the default text color. Neither of these had anything to do with what I was originally working on that day (CSS attribute selectors, for an upcoming GitHub-rendering push). But they were visible, they were wrong, and they were small enough to fix in one sitting. So I did. Bug #1: styles computed before they were applied Courage has a defaultRules ar

Imagine a hotel where every room key is cut from a master template. When a guest checks in, the front desk hands them a key that opens only their room. Simple enough. Now imagine a guest who, during check-in, sneaks a tiny modification into the key-cutting machine itself — changing the template so that every new key cut from that moment on also opens the manager's office, the safe, and the server room. The guest didn't break a lock. They didn't clone anyone's key. They changed the factory that makes all keys. That factory is JavaScript's Object.prototype . And the attack is called Prototype Pollution .

This is a submission for Weekend Challenge: Passion Edition What I Built As a QA engineer, I spend a lot of time reading requirements, questioning unclear business rules, and thinking about what could break before a feature reaches users. That part of quality engineering is something I genuinely enjoy, and it inspired me to build PassionQA . PassionQA is an AI-powered quality intelligence platform that turns product requirements into practical QA insights and executable test cases. The workflow is simple: Upload or paste a BRD (Excel or text) Run AI-assisted quality analysis Review the complete QA output in one dashboard: Requirement health and release readiness Missing rules and ambiguous requirements Positive, negative, boundary, security, and accessibility test cases Bug-risk insights and heatmap Requirements Traceability Matrix (RTM) Excel and PDF exports My goal was to reduce the repetitive part of requirement analysis so testers can spend more time thinking critically about product risk and quality. Demo Try it quickly Live app: https://passion-qa.vercel.app Click Explore Demo Preset to analyze the built-in insurance example. The application uses Gemini when available and automatically falls back to the local analysis engine if Gemini is unavailable. Or click Launch Platform (Free) , upload your own BRD, and select Run Quality Analysis . For my demo, I used an insurance Policy BRD. PassionQA analyzed the requirements, highlighted quality gaps, and generated executable positive, negative, boundary, security, and accessibility test scenarios across the policy workflow. Video Demo The demo shows the complete flow from Policy BRD upload to AI analysis, test-case generation, risk insights, RTM, and report export. Demo video: https://drive.google.com/file/d/1sAoOauTGCk66xAzY46zF8_lWBQbVM8Gr/view?usp=sharing Code GitHub repository: https://github.com/DhanashriQAEngineer/PassionQA/ Some of the key parts of the project are: src/lib/gemini.ts --- Gemini analysis and loc

The glasses are targeted at people who might be constantly in meetings, giving presentations, and traveling to countries where different languages are spoken.

If you've ever tried to duplicate a Keycloak realm on the same server — say, to spin up a myrealm-dev realm alongside your existing myrealm — you've probably hit this wall: Export the realm from the Admin Console ( Realm settings → Action → Partial export , with clients and groups/roles included). Rename it in a text editor, or in the import dialog's "realm name" field. Import it back into the same Keycloak instance. Watch it fail with: ERROR: duplicate key value violates unique constraint "constraint_a" Detail: Key (id)=(51e1a26d-c24f-4454-9a34-708f1fc14917) already exists. Why this happens A realm export isn't just configuration — it's a snapshot of database rows. Every role, client, user, protocol mapper, component, and authentication flow in the export carries the same internal UUID it has in the live database. Renaming the realm field changes what the realm is called , but it does nothing to the dozens (often hundreds) of UUIDs referenced throughout the file. Import that JSON into the instance it came from, and Keycloak tries to insert rows whose primary keys already exist. Every single one collides. This is a known limitation, tracked upstream as keycloak/keycloak#24770 . Keycloak's exporter was never designed to produce an import-anywhere-including-here artifact — it assumes you're moving the realm to a different instance (dev → staging → prod), where the UUID space is independent. The manual fix (and why it doesn't scale) In principle you can fix this by hand: open the export JSON, find every UUID, and replace it with a fresh one, while keeping track of which old UUID maps to which new UUID so that references between objects (a role's containerId , a client's serviceAccountClientId , a flow's execution list) still point at the right thing after the rewrite. For a small realm with a handful of clients this is tedious but doable in an editor with careful find-and-replace. For a realm with custom roles, several clients, an identity provider, and a full set of a

Learning how to add evals to an LLM feature is the difference between shipping a demo and shipping a reliable product. When you embed an LLM into a real feature — a chatbot, a voice agent, a document summarizer — you’re not just calling a model. You’re betting your user’s experience on a non‑deterministic system that can silently break with every prompt tweak, model update, or edge case. That’s why we instrument every LLM feature we build with a purpose‑built eval suite. Here’s how we did it for an outbound AI calling agent and how you can do the same. Why Evals Are Not Optional LLMs are non‑deterministic: give them the same input twice, and you’ll get two different responses. That means unit tests that check for exact string matches are useless. As Pragmatic Engineer notes , you need evals to verify that the solution works well enough — because there’s no guarantee it will. When you’re building a feature that speaks to real customers, like the AI Calling Agent dashboard we built, a regression in tone or missed booking intent can cost revenue immediately. Evals turn that uncertainty into signal. How to Add Evals to an LLM Feature: A 4‑Step Workflow We’ll walk through the exact process we followed, from defining success to automating checks in CI, using the DeepEval framework as an example. You can swap in Evidently AI or build your own, but the pattern is the same. Step 1: Define Success for Your Feature Takeaway: Before you pick a metric, write down the one thing that makes the feature “done” — usually a business outcome, not a technical measure. For the AI Calling Agent, the core feature was an outbound call that books a meeting. The success criterion wasn’t “the LLM replied politely.” It was “the agent scheduled a meeting with the right time and date.” This is a reference‑based evaluation: you compare the output to a known ground truth. Evidently AI’s guide calls this pattern out as essential for regression testing and experimentation. From that criterion, we der

I’m currently relearning the Core Three — HTML, CSS, and JavaScript — as I work toward becoming a full-stack JavaScript developer. Before I came back to learning software, I spent 22 years working industrial turnarounds. One lesson from that world has followed me into software engineering: Never trust a single point of failure. In industrial maintenance, there’s a safety practice called double block-and-bleed . Instead of trusting one isolation valve, you use two independent valves with a bleed point between them. If one valve leaks, you know immediately. The entire system assumes individual components can fail. Safety doesn’t come from perfect parts. It comes from independent layers of protection. That idea completely changed how I think about CI pipelines. When I first started relearning web development, my mindset was simple: Run Lighthouse. Everything green? Great. 100 across the board locally? Even better. Ship it. Different results after deployment? Uh-oh. Now I see Lighthouse as one checkpoint — not the finish line. A fast website can still have accessibility issues. An accessible site can still have broken metadata. Good SEO won’t catch rendering bugs. Passing unit tests won’t tell you if the generated HTML is malformed. Every tool has blind spots. No single tool should get the final vote. So instead of asking: “Did my tests pass?” I ask: “What kinds of failures could still slip through?” That question naturally leads to layered validation. Formatting Linting Type checking Accessibility checks Performance audits HTML validation SEO analysis Manual review None of these tools is perfect. Together, they’re much stronger than any one of them alone. The more I learn about software, the more I find myself applying lessons from heavy industry. Different environment. Different risks. The same engineering mindset. Assume components will fail. Design systems that fail safely. That’s becoming the philosophy behind every test matrix and CI pipeline I’m designing. What’s

A roundup of recent reviews published by Engadget.