Skip to content

docs(changelog): add v0.0.109 release entry #9014

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
cv merged 1 commit into from
Aug 13, 2026
+59 −0
Merged

docs(changelog): add v0.0.109 release entry #9014

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 59 additions & 0 deletions docs/changelog/2026-08-13.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,59 @@
{/*
* SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
* SPDX-License-Identifier: Apache-2.0
*/}

## v0.0.109

NemoClaw v0.0.109 adds credential-free launch-readiness leases, a distinct OpenAI-compatible API port for each Hermes sandbox, and selectable Hermes WhatsApp reply modes.
It improves inference health reporting, local inference discovery, onboarding recovery, sandbox startup, messaging status, and uninstall behavior.
It also strengthens managed images, Deep Agents Code login probes, Shields transitions, gateway lifecycle authority, and release qualification.

- On Linux, `nemoclaw launch <sandbox>` can reuse a credential-free launch-readiness lease with a fixed 24-hour lifetime after it validates the sandbox, policy, inference route, forwards, and agent health.
For missing, expired, changed, or unavailable evidence, NemoClaw fences any prior acceptable evidence before it runs the complete preflight.
If prior authority might remain and NemoClaw cannot durably rotate it, `launch` stops before preflight or recovery.
On macOS, `launch` runs the complete preflight every time and does not publish a launch-readiness lease.
Sandbox startup now waits for OpenShell readiness before process recovery, probe-only recovery starts a stopped container, and status reports stopped sandboxes without implying that their gateways are serving.
For more information, refer to the [NemoClaw CLI Commands Reference](/user-guide/openclaw/reference/commands), [Run Sandboxes](/user-guide/openclaw/manage-sandboxes/operate-sandboxes/run-sandboxes), and [Recover and Rebuild Sandboxes](/user-guide/openclaw/manage-sandboxes/operate-sandboxes/recover-and-rebuild-sandboxes).
Related changes: [PR #8951](https://github.com/NVIDIA/NemoClaw/pull/8951), [PR #8990](https://github.com/NVIDIA/NemoClaw/pull/8990), [PR #8977](https://github.com/NVIDIA/NemoClaw/pull/8977), [PR #8848](https://github.com/NVIDIA/NemoClaw/pull/8848), and [PR #8895](https://github.com/NVIDIA/NemoClaw/pull/8895).
- Sandbox status and `start` now send one bounded inference request after the route responds, so rejected credentials report `unauthorized` instead of route reachability alone.
Ollama model switching waits for the selected model to load before recording its served context window, and local Ollama validation bypasses ambient host proxy variables.
GPU discovery now finds `nvidia-smi` on WSL and requires bounded CUDA evidence before accepting a plausible ARM64 GPU name that lacks trusted host identity.
DGX Spark cluster discovery recognizes dual-controller QSFP topology, Ollama proxy credentials remain consistent across gateway ports, and Model Router shutdown verifies process convergence.
For more information, refer to [Verify the Inference Route](/user-guide/openclaw/inference/validate-inference/verify-inference-route), [Use Ollama](/user-guide/openclaw/inference/local-inference/set-up-ollama), and [Troubleshooting](/user-guide/openclaw/reference/troubleshooting).
Related changes: [PR #8731](https://github.com/NVIDIA/NemoClaw/pull/8731), [PR #8988](https://github.com/NVIDIA/NemoClaw/pull/8988), [PR #9004](https://github.com/NVIDIA/NemoClaw/pull/9004), [PR #9008](https://github.com/NVIDIA/NemoClaw/pull/9008), [PR #8904](https://github.com/NVIDIA/NemoClaw/pull/8904), [PR #8645](https://github.com/NVIDIA/NemoClaw/pull/8645), [PR #8736](https://github.com/NVIDIA/NemoClaw/pull/8736), [PR #8869](https://github.com/NVIDIA/NemoClaw/pull/8869), [PR #8809](https://github.com/NVIDIA/NemoClaw/pull/8809), and [PR #7663](https://github.com/NVIDIA/NemoClaw/pull/7663).
- On macOS, the official Homebrew formula remains the gateway lifecycle authority through a checksum-verified, formula-scoped temporary trust boundary.
Installation uses a standalone gateway only when Homebrew and its OpenShell formula or keg cannot retain authority, and a known unavailable `systemd` user manager follows a similarly bounded fallback on Linux.
Onboarding abort now stops and deletes a NemoClaw-managed gateway when no retained lifecycle authority owns it, reports incompatible gateway database recovery without discarding state, preserves a requested sandbox name during resume, and prints portable recovery commands instead of an unsupported `--resume` hint.
Portable onboarding avoids overlapping Personal-tier presets and preserves an explicit `NEMOCLAW_POLICY_PRESETS` selection, while `nemoclaw host probe` distinguishes remediable Docker storage from an unresolvable host failure.
For more information, refer to [Gateway Lifecycle Authority](/user-guide/openclaw/deployment/gateway-lifecycle-authority), [System Readiness](/user-guide/openclaw/reference/system-readiness), and [Network Policies Reference](/user-guide/openclaw/reference/network-policies).
Related changes: [PR #7739](https://github.com/NVIDIA/NemoClaw/pull/7739), [PR #8949](https://github.com/NVIDIA/NemoClaw/pull/8949), [PR #8993](https://github.com/NVIDIA/NemoClaw/pull/8993), [PR #8995](https://github.com/NVIDIA/NemoClaw/pull/8995), [PR #8958](https://github.com/NVIDIA/NemoClaw/pull/8958), [PR #8897](https://github.com/NVIDIA/NemoClaw/pull/8897), [PR #8994](https://github.com/NVIDIA/NemoClaw/pull/8994), [PR #9003](https://github.com/NVIDIA/NemoClaw/pull/9003), [PR #8922](https://github.com/NVIDIA/NemoClaw/pull/8922), and [PR #8867](https://github.com/NVIDIA/NemoClaw/pull/8867).
- Each Hermes sandbox now receives its own recorded OpenAI-compatible API port, including forward recovery and snapshot-clone restoration.
Hermes WhatsApp setup lets the operator select `self-chat` or `bot` reply behavior, and status checks use the configured durable session path.
`channels status` again accepts documented calls without `--wait`, and the Hermes forward watcher now reports bounded redacted diagnostics without stopping a forward that it does not own.
Hermes can also install its pinned Hindsight client into durable sandbox-owned state with the opt-in `local-memory` network policy.
For more information, refer to the [Hermes Quickstart](/user-guide/hermes/get-started/quickstart), [Set Up WhatsApp](/user-guide/hermes/manage-sandboxes/messaging-channels/set-up-whatsapp), and [Install Hermes Plugins](/user-guide/hermes/manage-sandboxes/install-hermes-plugins).
Related changes: [PR #8577](https://github.com/NVIDIA/NemoClaw/pull/8577), [PR #8423](https://github.com/NVIDIA/NemoClaw/pull/8423), [PR #8727](https://github.com/NVIDIA/NemoClaw/pull/8727), [PR #8900](https://github.com/NVIDIA/NemoClaw/pull/8900), [PR #8956](https://github.com/NVIDIA/NemoClaw/pull/8956), and [PR #8844](https://github.com/NVIDIA/NemoClaw/pull/8844).
- Backup credential scanning now excludes dependency trees while retaining scans of user and runtime state.
An equivalent repeated `shields down` request succeeds only with matching live auto-restore authority, and an unsafe Hermes configuration path leaves Shields up or restores the restrictive policy.
Seven policy presets now match the installed Python interpreter without retaining a nonexistent `python3.11` path.
For more information, refer to [Create and Restore Snapshots](/user-guide/openclaw/manage-sandboxes/state-and-backups/create-and-restore-snapshots), [Understand Runtime Changes](/user-guide/openclaw/manage-sandboxes/configure-sandboxes/understand-runtime-changes), and [Create Custom Policy Presets](/user-guide/openclaw/network-policy/configure-policies/create-custom-policy-presets).
Related changes: [PR #8807](https://github.com/NVIDIA/NemoClaw/pull/8807), [PR #8821](https://github.com/NVIDIA/NemoClaw/pull/8821), [PR #8830](https://github.com/NVIDIA/NemoClaw/pull/8830), and [PR #8960](https://github.com/NVIDIA/NemoClaw/pull/8960).
- Managed Deep Agents Code images now protect the root-owned login profile used by managed probes and reject a reusable base image without executable `dos2unix`.
Managed OpenClaw, Hermes, and Deep Agents Code images include checksum-pinned Vim fixes and the NemoClaw libssh2 revision containing two reviewed public-key fixes.
For more information, refer to [Run LangChain Deep Agents Code](/user-guide/deepagents/manage-sandboxes/operate-sandboxes/run-deep-agents-code), [Process Controls](/user-guide/openclaw/security/security-controls/process-controls), and [Trusted Computing Base](/user-guide/openclaw/security/trusted-computing-base).
Related changes: [PR #8670](https://github.com/NVIDIA/NemoClaw/pull/8670), [PR #8937](https://github.com/NVIDIA/NemoClaw/pull/8937), [PR #8940](https://github.com/NVIDIA/NemoClaw/pull/8940), [PR #8941](https://github.com/NVIDIA/NemoClaw/pull/8941), and [PR #8959](https://github.com/NVIDIA/NemoClaw/pull/8959).
- `nemoclaw uninstall --delete-models` now removes every model in the validated loopback Ollama inventory and non-credential Hugging Face cache data after managed runtimes stop.
The operation preserves authentication files and model stores used by sibling gateways, returns nonzero when inventory or deletion fails, and limits broad Docker cleanup to parsed owned container and image fields.
Selected-port uninstall also highlights retained sibling gateway environments and their cleanup commands.
For more information, refer to [Uninstall NemoClaw](/user-guide/openclaw/manage-sandboxes/operate-sandboxes/uninstall-nemoclaw).
Related changes: [PR #8919](https://github.com/NVIDIA/NemoClaw/pull/8919), [PR #8976](https://github.com/NVIDIA/NemoClaw/pull/8976), and [PR #8876](https://github.com/NVIDIA/NemoClaw/pull/8876).
- Contributor tooling now uses Oxlint and Oxfmt, enforces LF checkout for tracked text files, and reports the required Node.js heap limit when setup type checks exhaust memory.
Issue-planning and implementation skills now support configured GitHub access, while stale-issue verification adds stricter reproduction, evidence, and cost controls.
GitHub Actions dependencies also include the reviewed CodeQL Action and path-filter updates.
Related changes: [PR #8930](https://github.com/NVIDIA/NemoClaw/pull/8930), [PR #8657](https://github.com/NVIDIA/NemoClaw/pull/8657), [PR #8865](https://github.com/NVIDIA/NemoClaw/pull/8865), [PR #8968](https://github.com/NVIDIA/NemoClaw/pull/8968), [PR #8838](https://github.com/NVIDIA/NemoClaw/pull/8838), [PR #8309](https://github.com/NVIDIA/NemoClaw/pull/8309), [PR #8933](https://github.com/NVIDIA/NemoClaw/pull/8933), and [PR #8934](https://github.com/NVIDIA/NemoClaw/pull/8934).
- Release engineering now derives relevant main-push and full release qualification jobs from one runner-aware end-to-end (E2E) target catalogue and renders the selected execution plan.
The workflow keeps exact candidate and risk-signal identities, runs the Jetson GPU proof on main pushes, and adds coverage for interactive policy ordering, Hermes routing, image contracts, WSL connection behavior, and state-lock recovery.
CI corrections restore the affected workflow, source-architecture, timeout, and abort-cleanup checks without changing the shipped runtime contracts.
PR #7853 preserves contributor history through a no-diff merge after PR #8859 supplied the messaging credential-drift implementation, so it adds no separate release behavior.
Related changes: [PR #7853](https://github.com/NVIDIA/NemoClaw/pull/7853), [PR #8618](https://github.com/NVIDIA/NemoClaw/pull/8618), [PR #8896](https://github.com/NVIDIA/NemoClaw/pull/8896), [PR #8902](https://github.com/NVIDIA/NemoClaw/pull/8902), [PR #8912](https://github.com/NVIDIA/NemoClaw/pull/8912), [PR #8915](https://github.com/NVIDIA/NemoClaw/pull/8915), [PR #8946](https://github.com/NVIDIA/NemoClaw/pull/8946), [PR #8948](https://github.com/NVIDIA/NemoClaw/pull/8948), [PR #8950](https://github.com/NVIDIA/NemoClaw/pull/8950), [PR #8954](https://github.com/NVIDIA/NemoClaw/pull/8954), [PR #8957](https://github.com/NVIDIA/NemoClaw/pull/8957), [PR #8961](https://github.com/NVIDIA/NemoClaw/pull/8961), [PR #8963](https://github.com/NVIDIA/NemoClaw/pull/8963), [PR #8966](https://github.com/NVIDIA/NemoClaw/pull/8966), [PR #8984](https://github.com/NVIDIA/NemoClaw/pull/8984), [PR #8986](https://github.com/NVIDIA/NemoClaw/pull/8986), [PR #8989](https://github.com/NVIDIA/NemoClaw/pull/8989), [PR #8997](https://github.com/NVIDIA/NemoClaw/pull/8997), and [PR #9001](https://github.com/NVIDIA/NemoClaw/pull/9001).
Loading