The LGTM (Page 14)

The LGTM

Sign in Subscribe

OpenClaw’s sessions.reset Race Shows Why Agent Session Identity Has to Be More Than a Key String

OpenClaw’s sessions.reset Race Shows Why Agent Session Identity Has to Be More Than a Key String

The most dangerous session bugs are the ones that look like a healthy system. Slack is connected. The gateway is alive. The UI says there is no active run. Then the fresh OpenClaw session row is marked running, or worse, failed, by an error from a dead run that should

Replit and Visa Are Turning Agent Identity Into Payment Infrastructure

Replit and Visa Are Turning Agent Identity Into Payment Infrastructure

Agentic commerce sounds like a keynote phrase until you strip it down to the systems problem: a piece of software is going to spend money on behalf of a user. That instantly turns an AI agent from a helpful interface into an actor with external side effects. Replit and Visa’

AI Commits Make Git Hygiene a Production Control, Not a Style Preference

AI Commits Make Git Hygiene a Production Control, Not a Style Preference

AI did not invent bad commits. It made them cheap. That is why the HackerNoon piece on AI agents committing to repositories lands harder than its modest premise suggests. The visible artifact of agentic engineering maturity may not be your prompt library, model router, or eval dashboard. It may be

Slack Is Becoming the Agent Runtime Surface, Which Means Context Is Now a Product Decision

Slack Is Becoming the Agent Runtime Surface, Which Means Context Is Now a Product Decision

The least interesting version of “AI in Slack” is a chatbot that answers questions where coworkers happen to be talking. The interesting version is a runtime boundary: a place where product context, incident context, customer context, repo permissions, agent identity, and audit trails collide. Kilo for Slack is worth covering

Copilot’s Usage Billing Turns Agentic Coding Into a FinOps Problem, Not an IDE Feature

Copilot’s Usage Billing Turns Agentic Coding Into a FinOps Problem, Not an IDE Feature

GitHub Copilot’s pricing change is being argued about like a subscription plan got worse. That misses the more useful diagnosis: agentic coding has stopped behaving like an IDE feature and started behaving like metered infrastructure. Once a single developer action can trigger a long context load, multiple model calls,

OpenCode Adds Session Metadata, and Suddenly Agent Runs Look More Like Workflows Than Chats

OpenCode Adds Session Metadata, and Suddenly Agent Runs Look More Like Workflows Than Chats

OpenCode v1.15.13 looks like a small release if you read it as a changelog. Read it as an operating signal and it says something more useful: coding-agent sessions are becoming workflow objects, not chat logs with better autocomplete. The release, published May 30 at 23:40 UTC, adds

A Tiny HN Launch Accidentally Captures the Real Agentic-Coding Standard: Harness First, Model Second

A Tiny HN Launch Accidentally Captures the Real Agentic-Coding Standard: Harness First, Model Second

The most useful agentic-coding release this morning is not a model launch, benchmark graph, or IDE demo. It is a tiny GitHub repository with two stars at collection time saying the part teams keep learning the expensive way: production agents are mostly harness, not magic. AlexDuchDev/agentic-product-standard was created on

Codex’s Windows Computer Use Update Turns Agent UX Into an Ops Surface

Codex’s Windows Computer Use Update Turns Agent UX Into an Ops Surface

Codex’s latest update looks, at first glance, like a Windows checkbox. That undersells it. OpenAI is not merely letting Codex click around another operating system; it is moving the coding agent from “chat window with tools” toward something closer to a managed desktop worker: host-bound execution, remote steering, app

Claude Code Proxy Is a Cost-Control Hack With a Big Architecture Lesson

Claude Code Proxy Is a Cost-Control Hack With a Big Architecture Lesson

claude-code-proxy looks like a cost hack because that is the obvious reason people will install it. Point Claude Code at a local Anthropic-compatible server, route requests to ChatGPT Plus/Pro Codex models or Kimi Code, and suddenly the expensive part of a coding-agent workflow is negotiable. But the more important

Lite-Harness Turns Coding Agents Into Team Infrastructure — and Makes the Harness the Product

Lite-Harness Turns Coding Agents Into Team Infrastructure — and Makes the Harness the Product

Lite-Harness is not interesting because the world needed another chat box for coding agents. It is interesting because it treats Claude Code, OpenCode, Codex, and GitHub Copilot-style agents as interchangeable workers behind a team control plane. That is the architectural line the agent market keeps trying to avoid drawing: the