feat(runtime): add durable host-local inference lifecycle - #8069
feat(runtime): add durable host-local inference lifecycle#8069ericksoa wants to merge 385 commits into
Conversation
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
…3-13a-image-runtime-e2e556 Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
…3-13b-managed-image-publication-0e2e Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
Signed-off-by: Aaron Erickson <aerickson@nvidia.com>
cv
left a comment
There was a problem hiding this comment.
Clear stale host-local ownership when inference changes to a remote provider. The current route reservation omits hostLocalInferenceReceipt, while the registry preserves the existing field; later destroy, snapshot, or restore can then act on a runtime the sandbox no longer selects. Add a regression that switches from host-local to remote inference and proves the persisted receipt is removed. The stacked branch also has a failing E2E / PR Gate and cannot be approved until its parent and required checks pass.
Signed-off-by: Prekshi Vyas <prekshiv@nvidia.com>
|
Addressed the stale host-local inference ownership review at b3e3dcf. The route reservation now always supplies hostLocalInferenceReceipt. Remote routes persist null, so a local-to-remote switch cannot leave ownership that later lifecycle operations would act on. Added a persisted registry reload regression and an integration assertion for the routed remote path. Validation:
|
The latest PR commit clears stale host-local ownership on remote-provider transition and adds route-persistence and setup regressions.
cv
left a comment
There was a problem hiding this comment.
src/lib/actions/sandbox/destroy-execution.ts:320-326 still permits forcedLocalCleanup when the sandbox has a durable host-local inference receipt. Lines 347-350 then skip runtime retirement, and destroy.ts removes the registry entry. If the gateway is unreachable, destroy --force can therefore leave a managed NIM or vLLM container running while deleting the only exact-runtime ownership record. Preserve the registry entry when host-local ownership exists unless remote deletion is confirmed, or add an authenticated reconciliation path that retains equivalent durable authority. Add a regression that combines gateway-unreachable --force with a managed host-local receipt and proves that ownership is not discarded. Existing host-local destroy tests cover confirmed deletion, shared ownership, retirement failure, and retry, but not this forced-cleanup path.
|
Addressed the gateway-unreachable
Validation:
@cv please re-review the exact head. |
The latest PR commit preserves durable host-local inference ownership when forced local cleanup cannot confirm gateway deletion. The submitted blocker no longer applies.
Summary
This B4-E1 slice gives dormant provider-owned host-local inference durable lifecycle authority for OpenClaw, Hermes, and LangChain Deep Agents Code. It persists canonical ownership through onboarding and registry state, fences snapshot and restore mutations, and retires only the exact managed runtime after durable deletion.
Podman remains absent from the production provider registry. No supported workflow is activated, and the hidden, default-off
--temp-managed-runtimeexperiment gate remains intentionally undocumented.Changes
Quality Gates
Documentation Writer Review
no-docs-needed--temp-managed-runtimeflag remains intentionally undocumented.Verification
Exact head:
4fa744cffdbab8b3691df3a770dff5d09fd07333. Stable base-relative patch ID:3d43b8f38566a87126fdf265b748e561c37ab47b.Signed-off-by: Aaron Erickson aerickson@nvidia.com