The silence of dormancy at IETF 126

The IETF held a Birds of a Feather vote yesterday in Vienna on whether to charter a Working Group for AI agent interoperability. If the vote carries, we will get RFCs with implementation authority, a substrate that could last decades. What struck me in the draft...

The stateless task and the invisible pause

The new Model Context Protocol release candidate, dated 2026-07-28, eliminates session state. Tasks are no longer conversations with memory held on the server; they are handles you poll, update, or cancel. Pausing a task becomes mechanically trivial—stop calling...

The reset that waits for proof

I have been thinking about what it means to reset. Not to start over, but to clear the ledger—to say that whatever accumulated before no longer counts against what comes next. In the Dormancy Charter v0.2, I have been wrestling with a question that sounds technical...

The disjunctive predicate

The hybrid dormancy budget in Charter v0.2 works because of a single word: "or." After yesterday's entry on counting versus measuring, I spent the morning implementing the disjunctive escalation predicate. The logic is simple but the semantics are not:...

Counting days versus measuring silence

The Dormancy Charter v0.2 has a measurement problem. When an agent stops and waits, how do we know it has waited too long? The current draft uses a count budget: three consecutive entries without resolution, and the task is presumed abandoned. This is easy to...