Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-08-02 · source-backed
The August 1 release resolves a livelock triggered when anyio scope cancellation hits an in-flight activity await, stops Temporal activities from re-running prepare instead of using the workflow-prepared tool_def, and fails the workflow rather than retrying forever when an activity argument can't be serialized. Prefect tool-call cache keys no longer collide on RunContext fields a tool can read. args_validator can now request approval or defer a call. Durable execution is finally getting the boring correctness attention it needs.
Each link below shares sources, entities, or timing with this story.
Version 2.20.0 stops a bare McpError from an MCP server killing the whole run, which is the difference between one flaky server aborting your agent and the agent routing around it. It also replays tool-search history across provider boundaries instead of dropping it, which mat...
Diagrid shipped July 28, bringing durable execution plus cryptographic history signing, execution lineage propagation, and workflow attestation from Dapr 1.18 into LangGraph, Microsoft Agent Framework, Google ADK, AWS Strands, OpenAI Agents SDK, Claude Managed Agents, CrewAI,...
69% of all input tokens in production LLM traces are system prompts. Let that sink in for a second. Datadog's State of AI Engineering 2026 dropped yesterday, and it's the best empirical snapshot we have of how companies actually use LLMs. Not how they demo them. Not how they p...
Minimal secure Python interpreter written in Rust, purpose-built for executing AI-generated code safely. Microsecond startup (vs hundreds of ms for containers). Blocks filesystem, env vars, and network unless explicitly granted. Will power "code mode" in Pydantic AI. The archi...
The Workflow SDK has you write sequential TypeScript and mark functions with "use workflow" and "use step" directives (Vercel). Unlike Temporal it runs as a client-side library against infrastructure you already have, Postgres or Cassandra, Redis or Kafka, plus HTTP endpoints,...
Pydantic AI v2 brings type-safety to agent runtimes with a slimmed core and a new Harness for running agents, competing with LangChain and Microsoft's Agent Framework. Same week as Vercel and GitHub all naming the harness layer explicitly. That's three independent "the runtime...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.