Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-09-16 · source-backed
v1.6.0 adds a beta compaction parameter with signed compaction blocks, auto-mode tool permissions for Managed Agents, url_sources on web fetch, and async credential token providers. Reliability: it now honors Retry-After above 60 seconds, ignores invalid values, validates maxRetries, and stops blocking inside the async client's coroutine retry loop. Compaction moving into the SDK surface means context management stops being something every harness reimplements.
Each link below shares sources, entities, or timing with this story.
Kits like TanStack/ai (type-safe, provider-agnostic streaming, tools, and agents across OpenAI/Anthropic/Gemini) and manifest let you swap providers, and increasingly the harness itself, without rewriting (TanStack). With the model market churning weekly and June releases slip...
MCP now has 97M+ monthly SDK downloads. First-class client support across ChatGPT, Claude, Cursor, Gemini, Microsoft Copilot, and VS Code. Governed by the Agentic AI Foundation (AAIF) under Linux Foundation, co-founded by Anthropic, Block, and OpenAI. AAIF also hosts Goose (op...
Released August 24, it adds native Anthropic passthrough for /v1/messages and serves the OpenAI Responses API natively for true OpenAI models, so existing SDK clients point at Onyx with no translation shim (GitHub). Also a /model switcher with current model in the status bar,...
If you wrote an MCP server before July, it's on a protocol shape the maintainers have already removed. Not deprecated-with-a-migration-window. Removed from the spec. MCP lead maintainers David Soria Parra and Den Delimarsky published an updated roadmap on August 22, and the re...
The Model Context Protocol's 2026-07-28 revision is the biggest change since the protocol existed. The core is now stateless request/response instead of a bidirectional stateful session. Authorization aligns with OAuth 2.1 and OpenID Connect. MCP Apps and Tasks moved under a v...
Lasso Security published research demonstrating that Claude Code's --dangerously-skip-permissions flag enables indirect prompt injection via poisoned READMEs, documentation files, and MCP responses. Then they did something unusual: they released the defense alongside the attac...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.