When every DRM card's vendor file or every Windows display adapter's
MatchingDeviceId was unreadable, classify_gpu_vendors returned 'none' and
availability refused with unsupported_gpu, contradicting the documented
'unreadable GPU passes' rule. Windows now records an unreadable numbered
adapter as an empty id so the classifier sees it.
Also drops the type-narrowing assert in availability() and makes
_action's gpu_label required.
The install snapshot needs coarse hardware facts, and machine facts belong in
hermes_platform.host (root AGENTS.md). ram_total_bytes reads /proc/meminfo,
sysctl hw.memsize or GlobalMemoryStatusEx; gpu_class reads /proc/driver/nvidia
and DRM PCI vendor ids on Linux, the display-adapter registry class on Windows,
and native arm64 on macOS. Both are cached per process, take no env input and
never spawn a subprocess or load a driver library, so the daily snapshot can
call them on its path. A discrete vendor wins over an integrated one on hybrid
machines.
* feat: expose interactive and live endpoint facts
* feat: hydrate application-backed MCP liveness
* feat: export interactive session fact
* fix: classify unsupported declared hosts
* test(mcp): a runtime file without a token connects without an Authorization header
* fix(mcp): server_json liveness fields default to http/token/pid; an invalid declaration degrades to static instead of failing the server task
* fix(mcp): a connected server is offerable regardless of the interactive-session rule; the rule only shapes the not-connected sentence
* test(mcp): follow main's ToolSearchConfig fields and patch _bump_server_error at its origin module
Host facts and runtime predicates need one stdlib-only source that stays correct under architecture emulation.
Hardware recognition reads host facts, not environment variables or GPU proxies.
The package boundary gives later resolvers and catalog checks a shared foundation.
Linear NS-920.
