hypr - My "local" LLM setup with Hyperstack.

Age	Commit message (Collapse)	Author
2026-05-25	fix(inference_tester): add bounded-retry guard around vLLM chat inference	Paul Buetow
	Retry up to 3 times with 15/30/45s backoff on Net::ReadTimeout, Net::OpenTimeout, connection errors, non-200 HTTP, and JSON parse failures. Prevents a single transient timeout from failing the whole test run. Task referenced Manager#vllm_chat which no longer exists after refactor; applied guard to InferenceTester#chat where the call actually lives.
2026-05-25	refactor(manager): extract focused collaborators from Manager God Class	Paul Buetow
	Extract VM lifecycle, SSH execution, WireGuard setup, model switching, end-to-end inference tests, and provisioning orchestration into separate collaborator classes. Manager becomes a thin facade (~80 lines). Also fixes CLI edge-cases: status/model-list when no VMs are active, and threads --vllm/--ollama flags through the provisioning pipeline.