Live capability snapshot of the responder's GPU sidecar — extensions[] (e.g. gpu, clay-v1.5, prithvi-eo2), cuda_available, models_loaded[], healthy, last_polled_unix_s. Refreshed every 30 s by a background poller; reads are constant-time.
When to use: Call before scheduling a GPU-heavy plan (Clay / Prithvi / Galileo embeddings, foundation-anchored algorithms) so the agent knows whether the GPU tier is up *right now* without per-request /health round-trips. Pair with `emem_topics` (its `algorithm_availability` map says which algorithm keys can run given the current capabilities) and `emem_explain_algorithm` (full inference-tier metadata per algorithm). When `extensions[]` is empty the sidecar is unreachable — only CPU/scalar/cached tiers will produce facts; foundation-anchored materializers will sign Absence with `gpu_unavailable` reason.
Connector