Posts tagged “developer-tools”

• Claude Projects Can Fan Out. The Hard Part Is Accepting the Work

  Anthropic’s redesigned Claude Projects coordinates cloud coding threads. The real test is accepted delivery, policy, memory, and quota.

• Gemini 3.8 Live Extended Thinking Makes “Done” a Three-Clock Problem

  Google’s new Gemini Live models make background work first-class. Builders now need separate speech, interaction, and transaction states.

• Mistral Patched Six Vibe Shell Bypasses. The Approval Prompt Saw the Wrong Action

  Mistral Vibe 2.25.4 fixes six shell-permission CVEs. The deeper lesson is how coding agents must bind approvals to actual runtime effects.

• Fugu Max Turns Model Orchestration Into a Spending Policy

  Sakana’s Fugu Max and Ultra v2 turn learned routing into an API product. Builders should measure accepted-task cost, drift, and opacity.

• OpenAI’s Agents API Rents You the Codex Harness. Keep Your Own Ledger.

  OpenAI’s Agents API turns the Codex harness into managed infrastructure. Here is what it owns, what builders retain, and how to pilot it safely.

• GitHub Let Copilot Approve Pull Requests. Treat It Like a New Privileged Identity

  GitHub Copilot can now satisfy pull request approval rules. Here is how to pilot AI approvals without weakening code governance.

• Alibaba’s Qoder Agent Desktop Puts the Harness Above the Model

  Alibaba’s Qoder Agent Desktop turns coding agents into a task control plane. See why the harness, permissions and review layer matter.

• Claude Code’s New Weekly Limit Has an 83.3% Warning Line

  Anthropic will reset Claude Code weekly limits to 125% of the old baseline on September 14. Here is the 83.3% threshold teams need to plan around.

• DeepSeek V4 Pro 0813: GA Benchmarks, Pricing, and API Guide

  DeepSeek V4 Pro 0813 is live. See GA benchmarks, peak/off-peak API pricing, Codex setup, the Flash comparison, and open-weight details.

• Agent Plugins 1.0 Makes Agent Tools Portable. Trust Still Does Not Travel.

  GitHub brings Agent Plugins 1.0 to Copilot clients, making skills and MCP packages portable while trust, policy, and runtime parity stay local.

• OpenAI’s Agents SDK Turns a Package Upgrade Into a Runtime Migration

  OpenAI’s Agents SDK defaults to GPT-5.6 Luna, negotiates MCP v2, and hardens durable runs. Here’s the production migration builders need.

• SGLang 0.5.17 Gives Agent Sessions a Vote in GPU Memory

  SGLang 0.5.17 adds session-aware KV caching, faster recovery, Rust ingress, and frontier-model paths—shifting serving toward agent runtime policy.

← Back to blog