Fetching from the wire…
01
02
03
04
05
06
07
08
Infra2026-09-25 · source-backed
PR #58613 adds thinking to /v1/messages, which had been silently dropped through Pydantic's extra='ignore'. The PR explains the concrete failure: Claude Code's client-side auto-mode classifier sends thinking disabled with max_tokens 64 and expects <severity>N immediately, but on a reasoning model it spent the whole budget thinking and never returned a verdict. Anyone running Claude Code against a local vLLM backend wants this merge.
Each link below shares sources, entities, or timing with this story.
Anthropic's new permanent level indexes to 125 against a 100 baseline, but subscribers have been running at 150 since a temporary 50% boost announced May 13 was extended past July 13, July 19, August 31 and September 13. Both "25% up" and "17% down" are true from different ref...
This is the paper of the week. arXiv 2607.28871 introduces BSG-VA, which replays every validation command an agent runs across three code states: the original buggy code (B), the candidate patch (S), and the gold developer fix (G). If a test passes in all three states, it neve...
If a gateway closed the stream cleanly partway through a response, Claude Code displayed it as complete with no warning. Duplicated stream events could run a tool call twice (GitHub). Both fixed, plus partial output is kept when a proxy drops an event rather than failing with...
Blaizzy/nativ (1,163 stars, Swift, MIT, macOS 26+) comes from the mlx-vlm author and bundles that server into a SwiftUI app that discovers MLX models already in your HF cache. It exposes OpenAI-compatible chat, Responses, image, audio and model endpoints plus Anthropic Message...
The June 15 release of Claude Code (v2.1.178) is small on the changelog and large in practice. Two changes matter for anyone running agentic workflows daily. First, permission rules now match on parameters, not just tool names. You can write Agent(model:opus) to block Opus sub...
For a month, Claude Code users were convinced the model had been "nerfed." Forums lit up. Conspiracy theories multiplied. People switched tools. Then on April 23, Anthropic did something unusual: they published a detailed post-mortem that named three specific bugs with exact d...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.