You can now skip the handshake and still call a tool and your retry after a…
- Source
- x.com
- Date
You can now skip the handshake and still call a tool and your retry after a timeout can place two requests. We ran the retry on one laptop. The tool slept 2.5 seconds on purpose. > Wait 2.5 seconds > Abort around 400 ms > Log already at 1 > New id, second write Same sku. Same machine. A new request id is now a new call. Google said the old pin returned 400 Session Not Found on the wrong pod. GitHub already dropped Redis session reads and writes. Claude-only apps can often wait. Server authors cannot treat a hang-up as a rollback. What keeps a retry at one write? Where does a cart live with no session id? Do you still advertise the old revision?
Context
Losing a tool's reply does not establish that its action was cancelled. AlphaSignal reports a local test in which the client disconnected before a delayed order-writing tool finished. The first write still occurred, and retrying with a new request identifier produced another. Reusing an application-level order identifier let the tool recognize the duplicate and keep the count at one. Test account.
The surrounding change concerns , which connects AI applications to tools. Its July 28, 2026 revision puts protocol information on each request and removes the negotiation handshake, so a server no longer relies on a session set up beforehand. Duplicate prevention remains an application concern, as the fuller test account illustrates. A request identifier and an order identifier serve different purposes. Protocol specification.
- MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
Checking sign-in…
Loading comments…