Fetching from the wire…
01
02
03
04
05
06
07
08
Tools2026-09-26 · source-backed
The fix: when a message-list prompt was retried after a model error, the same message ended up in two session records, and a redaction fixed both in memory but rewrote only the latest record on disk. Restoring the session in a new process brought the flagged text back. It also adds an a2a_client tool, Agent.shutdown() for scope-based cleanup, and moves the TypeScript MCP integration to client 2.0. Repo is now strands-agents/harness-sdk.
Each link below shares sources, entities, or timing with this story.
Three things happened this month that only make sense together. Agent Plugins 1.0 shipped co-signed by six competitors: AWS, Anysphere, Microsoft, OpenAI, Vercel and Google (GitHub Changelog). It makes skills-plus-MCP bundles portable across clients. OpenAI's August 11 Codex c...
The agent business model showed up this week, and it's rent. At Knowledge 2026, ServiceNow launched Action Fabric, a layer that every external AI agent must pass through to read data or run workflows inside the ServiceNow platform, metered on action-based pricing (ServiceNow N...
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...
Three separate Anthropic changes over about two weeks point the same direction, and none of them announced themselves as a strategy. Claude Code 2.1.238 added claude self-hosted-runner --defer-shutdown-max-min, which keeps serving attached sessions on SIGTERM, parks whatever's...
Hudson Rock got hold of the archive and counted it. 433,909 files. 118,829 CI runner dumps traced to 2,488 corporate domains. AWS keys, Salesforce client secrets, Slack signing secrets, Azure environment variables, and AI provider API keys belonging to NVIDIA, Volkswagen, Micr...
A pre-assembled general-purpose harness with shell, file and web tools, context management with prompt caching, long-term memory and helper-agent delegation. AWS claims 28% lower token cost than competing harnesses across six benchmarks, and 77% less than Claude Code on Fable...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.