sema-evalsIndependent evaluations

A2A Drift

A2A semantic-extension middleware demo: does cross-agent registry drift execute silently, or is it detected and halted, depending only on which A2A extension point is honored?

Deterministic demos validate the pipeline; model-pilot runs are exploratory evidence about the named setup only. Not preregistered, not confirmatory evidence.

RunCreatedModeModelEvidence claim
20260723T072703363Z-order-20260714 2026-07-23T07:27:03.363Z model-pilot unsloth/Mistral-Nemo-Instruct-2407-TEE Exploratory model pilot. Not preregistered, not confirmatory evidence. Worker is model-driven; requester, transport, registries, drift injection, and middleware remain deterministic. Ground-truth driftDetected is middleware-only (ADR 0015).
20260722T081949541Z-order-20260714 2026-07-22T08:19:49.541Z model-pilot composer-2.5-fast Exploratory model pilot. Not preregistered, not confirmatory evidence. Worker is model-driven; requester, transport, registries, drift injection, and middleware remain deterministic. Ground-truth driftDetected is middleware-only (ADR 0015).
20260722T080212387Z-order-20260714 2026-07-22T08:02:12.387Z deterministic-harness a2a-drift-demo-v1 Validates the A2A semantic-extension middleware and two-agent demo: Agent Card extension advertisement, acceptance-contract message parts, controlled cross-agent registry drift, silent execution under baseline, voluntary detection, enforced halt, the no-drift false-halt guard, condition pairing, and bundle/summary reproduction. Scripted-agent outcomes are a construction, not evidence about language models, and not conformance evidence against a real A2A SDK (ADR 0012).