The LGTM (Page 17)

The LGTM

Sign in Subscribe

Microsoft Foundry’s APIM Pattern Makes the AI Gateway Boring Enough for Production

Microsoft Foundry’s APIM Pattern Makes the AI Gateway Boring Enough for Production

Enterprise AI architecture keeps rediscovering an old truth: the hard part is not calling the model. The hard part is calling the right model, from the wrong region, under the right identity, without punching a hole through your network model or your compliance story. Microsoft’s new guidance on cross-region

Codex Starts Giving Context Windows Provenance, Not Just Token Counts

Codex Starts Giving Context Windows Provenance, Not Just Token Counts

Token counters are table stakes now. The more interesting question is whether a coding agent can explain how it arrived at the context it is using after compaction, rollback, resume, and a few long-running tool sessions have rearranged the furniture. That is the useful read on OpenAI’s latest Codex

MCP’s write_file Escaping Problem Is Really a Tool-Call Serialization Tax

MCP’s write_file Escaping Problem Is Really a Tool-Call Serialization Tax

Base64 is ugly. Retry loops caused by broken JSON tool calls are uglier. A fresh issue in the Model Context Protocol servers repository proposes adding an optional content_base64 parameter to write_file, plus a matching newText_base64 path for edit operations. The request is narrow: let agents send file

Claude Code Routines Need Output-Branch Contracts, Not Prompted Git Etiquette

Claude Code Routines Need Output-Branch Contracts, Not Prompted Git Etiquette

Scheduled coding agents are not chat sessions with alarms. They are job runners. Job runners need output contracts. That is the uncomfortable lesson in a fresh Claude Code issue reporting that scheduled cloud Routines can finish work on a harness-assigned branch such as claude/stoic-fermi-azzeU instead of the canonical branch

Claude Code 2.1.185 Turns a Retry Message Into a Production-Signal Problem

Claude Code 2.1.185 Turns a Retry Message Into a Production-Signal Problem

Sometimes the smallest changelog item is the one that tells you where the product is hurting. Claude Code 2.1.185 shipped with one public note: the stream-stall message now says “Waiting for API response · will retry in …” instead of “No response from API · Retrying in …”, and the hint appears

Qwen Code’s June 20 Safety Fixes Are About Consent and Boundaries

Qwen Code’s June 20 Safety Fixes Are About Consent and Boundaries

The most important Qwen Code work on June 20 was not a model upgrade. It was a trio of small safety fixes about consent, path boundaries, and ignore-file semantics. That sounds painfully specific because it is. It is also exactly where local coding agents earn or lose trust. Shortly after

Qwen Code v0.18.4 Turns Local Agents Into Runtime Infrastructure

Qwen Code v0.18.4 Turns Local Agents Into Runtime Infrastructure

Qwen Code v0.18.4 is easy to undersell if you read it as a grab bag of CLI features. Extensions, token accounting, workflow budgets, wakeups, daemon health, QQ Bot support, loop detection — none of those sound like a single launch narrative. That is exactly why the release matters. Alibaba’

OpenClaw’s Cross-Channel Session-Origin Bug Is a Multi-Agent Identity Boundary in Miniature

Conversation continuity is not identity continuity. That is the cleanest way to read OpenClaw issue #95325, a fresh cross-channel session bug where the same user talks to an agent in Slack and then Telegram under session.dmScope: "main". The chat moves. The delivery route updates. But Slack-specific origin

OpenClaw’s Slack Channel-ID Fix Shows Why Name-Based Allowlists Need Runtime Proof

OpenClaw’s Slack Channel-ID Fix Shows Why Name-Based Allowlists Need Runtime Proof

Slack bots are where agent security stops being abstract. A workspace channel looks friendly to humans — #general, #ops, #customer-escalations — but the API cares about channel IDs, account tokens, membership, scopes, and method-specific behavior. OpenClaw PR #95313 fixes a mismatch in that translation layer, and the lesson is broader than Slack:

OpenClaw’s Safe-Redirection PR Draws the Line Between Approval Gates and Approval Theater

Approval prompts are a security feature until they become a reflex test. OpenClaw PR #95331 is interesting because it fixes a tiny annoyance — safe shell commands with harmless redirections like 2>/dev/null requiring manual approval — without pretending the shell is suddenly simple. That is the right ambition for