correx

T

kami 7b1df95627 feat: correx-managed model lifecycle slice 4 — resource telemetry

Vendor-agnostic ResourceProbe (commons): NvidiaResourceProbe reads nvidia-smi
(injectable runner) for whole-device VRAM/util and /proc/<pid>/status for the
managed llama-server RSS, both fail-soft to null; UnavailableProbe for non-GPU
hosts / the static path. DefaultModelManager.currentPid() + LlamaProcess.pid
expose the managed pid. ServerMessage.ResourceStatus (resource.status,
NonEventMessage, all-nullable) pushed every 2.5s on the global stream plus one
in the initial snapshot. Live gauge only — never event-sourced (feeds no core
decision), so invariants #8/#9 hold. Main wires the NVIDIA probe on the managed
path when nvidia-smi is present, else UnavailableProbe.

Tests: csv parsing (single/multi/malformed), gpu+rss combine, fallbacks.

Plan: docs/plans/2026-05-31-model-lifecycle-management.md (slice 4 of 5).

2026-06-01 12:36:38 +04:00

apps

feat: correx-managed model lifecycle slice 4 — resource telemetry

2026-06-01 12:36:38 +04:00

core

feat: correx-managed model lifecycle slice 2 — per-stage model selection

2026-06-01 11:35:51 +04:00

docs

feat: correx-managed model lifecycle slice 1 — config + manager factory + boot/shutdown

2026-06-01 11:03:05 +04:00

examples/workflows

fix(apps): send workflowId not path from CLI; wire sandboxRoot and systemPromptPath in server; update prompts and fixtures