Hunting JavaScript memory leaks with V8 mechanics and Chrome DevTools
How V8 decides what stays alive, seven common leak patterns, and how to find the retaining path with Performance and heap snapshots.
Stuzhuk Lab — Chemistry of Code
Chemistry of Code
← All posts
Tag
DevTools
All blog posts with this tag.
Semantic context for LLMs: how LSP helps a model understand code
Part 4 of a completion series: Language Server Protocol supplies types, definitions, and references — a layer on top of repository text search.
Spec-Driven Development in 2026: the spec as source of truth for AI-assisted coding
Make the specification the primary artifact: spec → plan → agent code → verify, 2026 tools, vs TDD/BDD, and where SDD breaks.
How Cursor and other AI IDEs work with code: from autocomplete to agents
Evolution of IDEs and AI tool internals: LSP, repo indexing, context assembly, Tab/Chat/Agent modes, MCP, and comparison of Cursor, Copilot, JetBrains, CLI agents — what happens to code under the hood in 2026.
Agentic Engineering in 2026: How to Manage AI Agents Without Sacrificing Quality
A practical model for agentic development: context, task decomposition, verification loops, multi-agent orchestration, security, DORA metrics, and the engineer's role in the 2026 SDLC.
Where Code Generation Ends and Engineering Begins
AI already writes working functions, but a product is architecture, context, risk, and accountability. The boundary between code and engineering, a 15-year legacy case study, and developer skills in 2026.
Can AI Understand a Codebase With 15 Years of History?
Millions of lines, hundreds of tables, dozens of integrations: what AI grasps in hours, where it fails, how teams deploy RAG and repo indexing, and why expert + model beats either alone.
How to Turn a Diagram Image into an Editable Diagram: Full Technology Survey from OCR to AI
Flowcharts, UML, BPMN, network topologies, and CAD drawings: why PNG ≠ diagram, what OCR, vectorization, CAD, computer vision, and VLMs deliver in 2025–2026, and which pipeline actually works.
Biome vs Oxlint in 2026: Replacing ESLint
Rust-powered linters run 50–100× faster than ESLint, but choosing Biome or Oxlint depends on custom plugins, type-checking, and whether you want one tool instead of ESLint plus Prettier.
The new SDLC: vibe coding vs agentic engineering
A senior dev's honest take: Agent = Model + Scaffold, context engineering, the factory model, and why vibe coding does not scale past prototypes.
Smart document registry: free Google Drive OCR and Gemini quota tricks
Google Apps Script, hidden Drive OCR, Gemini key rotation, and LockService — a Habr pipeline for cataloging huge archives.
Beyond the hype: how top engineering teams actually use AI
Platform9, Monday.com, and PlayStation on restructuring the SDLC around AI, orchestration engineers, and review bottlenecks.
Why JSON is becoming a bottleneck for AI agents — and ULMEN
Million-token context windows still move JSON between planner, tools, and memory. ULMEN LLM claims 44% fewer tokens in the author's tests.
Governed evolution of agent runtimes: code as durable operational memory
Preprint on HarnessMutation—how multi-agent systems can adapt runtime artifacts with validation, tracing, and rollback instead of chaotic self-modification.
Open WebUI on Ubuntu: Docker Compose and HTTPS with Traefik
Your own ChatGPT-style UI for Ollama and OpenAI-compatible APIs — a step-by-step deploy with Let's Encrypt.
Antigravity 2.0: a $1000 OS built by 93 AI agents in 12 hours
Google I/O Writing Challenge: multi-agent orchestration assembled an OS core with no hand-written code — and shifts the developer role.
Docker as a safety net for AI-generated frontend code
Copilot/Cursor code compiles but breaks in the browser — why to run the app and Playwright/Cypress in one compose stack.