|
| 1 | +{/* |
| 2 | + * SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. |
| 3 | + * SPDX-License-Identifier: Apache-2.0 |
| 4 | + */} |
| 5 | + |
| 6 | +## v0.0.110 |
| 7 | + |
| 8 | +NemoClaw v0.0.110 adds an Experimental managed llama.cpp profile for Meta Muse Glimmer 30B on one DGX Spark and requires native tool-use evidence from custom Anthropic-compatible endpoints. |
| 9 | +It strengthens the explicit experimental Portable OpenClaw path with rootless Podman lifecycle authority, CPU-delegation preflight, and receipt-bound uninstall. |
| 10 | +It also improves onboarding recovery, local inference diagnostics, messaging and policy cleanup, backup and uninstall safety, and release qualification. |
| 11 | + |
| 12 | +- Managed llama.cpp onboarding now recommends the compatible Meta Muse Glimmer 30B profile on one DGX Spark while retaining NVIDIA Nemotron as a lower-priority choice. |
| 13 | + Profile selection is deterministic, exact recipe selection remains available for automation, and typed recipe contracts constrain templates and reasoning settings. |
| 14 | + The Experimental managed vLLM Muse Glimmer profile now uses its qualified pinned runtime, and `onboard --profile` selects the provider required by the requested serving profile instead of falling through to the provider menu. |
| 15 | + Local inference setup also distinguishes a probe-image pull failure from a networking failure, reuses a positively identified Windows-host Ollama daemon under WSL mirrored networking, and completes a required Ollama upgrade before continuing. |
| 16 | + For more information, refer to [Set Up llama.cpp](/user-guide/openclaw/inference/local-inference/set-up-llama-cpp), [Set Up vLLM](/user-guide/openclaw/inference/local-inference/set-up-vllm), and [Use Ollama](/user-guide/openclaw/inference/local-inference/set-up-ollama). |
| 17 | + Related changes: [PR #8711](https://github.com/NVIDIA/NemoClaw/pull/8711), [PR #9099](https://github.com/NVIDIA/NemoClaw/pull/9099), [PR #9319](https://github.com/NVIDIA/NemoClaw/pull/9319), [PR #9311](https://github.com/NVIDIA/NemoClaw/pull/9311), [PR #9345](https://github.com/NVIDIA/NemoClaw/pull/9345), and [PR #9284](https://github.com/NVIDIA/NemoClaw/pull/9284). |
| 18 | +- Custom endpoint onboarding, `inference set`, and rebuild recovery now reject unsafe URL characters and unsupported URL components before network or state mutation. |
| 19 | + OpenClaw onboarding for a custom Anthropic-compatible endpoint requires a native streaming `tool_use` block and matching stop reason instead of accepting JSON-shaped assistant text. |
| 20 | + Google Gemini diagnostics distinguish a Chat Completions route `404` from native model-catalog validation, while sandbox status preserves the recorded API family when only the model drifts. |
| 21 | + Hermes route changes fail when the in-sandbox configuration cannot synchronize, and Model Router setup and teardown serialize lifecycle work across the current user's gateways so destroy cannot stop a replacement router or overwrite a concurrent onboarding session. |
| 22 | + For more information, refer to [Custom Endpoint Security](/user-guide/openclaw/inference/custom-endpoints/custom-endpoint-security), [Set Up an Anthropic-Compatible Endpoint](/user-guide/openclaw/inference/custom-endpoints/set-up-anthropic-compatible-endpoint), [Use Google Gemini](/user-guide/openclaw/inference/hosted-inference/use-google-gemini), [Verify the Inference Route](/user-guide/openclaw/inference/validate-inference/verify-inference-route), and [Set Up Model Router](/user-guide/openclaw/inference/hosted-inference/set-up-model-router). |
| 23 | + Related changes: [PR #9320](https://github.com/NVIDIA/NemoClaw/pull/9320), [PR #9119](https://github.com/NVIDIA/NemoClaw/pull/9119), [PR #9236](https://github.com/NVIDIA/NemoClaw/pull/9236), [PR #9347](https://github.com/NVIDIA/NemoClaw/pull/9347), [PR #9307](https://github.com/NVIDIA/NemoClaw/pull/9307), [PR #9233](https://github.com/NVIDIA/NemoClaw/pull/9233), [PR #9185](https://github.com/NVIDIA/NemoClaw/pull/9185), and [PR #9112](https://github.com/NVIDIA/NemoClaw/pull/9112). |
| 24 | +- Fresh OpenClaw and Hermes onboarding now waits for a durable sandbox ID and a successful no-op command after OpenShell reports `Ready`. |
| 25 | + Deployment verification also probes a separate agent API host forward before reporting the sandbox ready, and names the exact forward recovery command when that endpoint is unavailable. |
| 26 | + An explicit `--recreate-sandbox` request bypasses stale saved build or policy fingerprints, and managed OpenClaw registration records its validated agent identity for later rebuild and restore authority. |
| 27 | + Readiness observations now age from collection completion, so slow probes do not immediately invalidate their own results, and rebuild recovery can defer an unanswered route query to authoritative onboarding while still rejecting a confirmed route mismatch. |
| 28 | + Reused onboarding passes the selected messaging dependencies, session reporting recognizes proxied `connect` processes, and recovery can use probe-only convergence without failing solely because platform evidence is absent. |
| 29 | + Legacy gateway upgrades preserve a proven gateway identity and scope cleanup to the exact selected gateway, while sandbox destroy removes only an identity-bound Docker orphan and preserves recovery state on any mismatch. |
| 30 | + The deprecated global `nemoclaw start` command exits successfully with migration guidance instead of starting a tunnel, leaving sandbox startup to `nemoclaw <sandbox> start` and tunnel startup to `nemoclaw tunnel start`. |
| 31 | + For more information, refer to [Recover and Rebuild Sandboxes](/user-guide/openclaw/manage-sandboxes/operate-sandboxes/recover-and-rebuild-sandboxes), the [NemoClaw CLI Commands Reference](/user-guide/openclaw/reference/commands), and [Troubleshooting](/user-guide/openclaw/reference/troubleshooting). |
| 32 | + Related changes: [PR #9229](https://github.com/NVIDIA/NemoClaw/pull/9229), [PR #9299](https://github.com/NVIDIA/NemoClaw/pull/9299), [PR #9318](https://github.com/NVIDIA/NemoClaw/pull/9318), [PR #9325](https://github.com/NVIDIA/NemoClaw/pull/9325), [PR #9352](https://github.com/NVIDIA/NemoClaw/pull/9352), [PR #9370](https://github.com/NVIDIA/NemoClaw/pull/9370), [PR #9366](https://github.com/NVIDIA/NemoClaw/pull/9366), [PR #9321](https://github.com/NVIDIA/NemoClaw/pull/9321), [PR #9285](https://github.com/NVIDIA/NemoClaw/pull/9285), [PR #9282](https://github.com/NVIDIA/NemoClaw/pull/9282), [PR #8920](https://github.com/NVIDIA/NemoClaw/pull/8920), [PR #9198](https://github.com/NVIDIA/NemoClaw/pull/9198), and [PR #9201](https://github.com/NVIDIA/NemoClaw/pull/9201). |
| 33 | +- The explicit experimental Portable OpenClaw profile now keeps sandbox lifecycle operations under the selected current-user rootless Podman socket and exact container identity, uses native OpenShell GPU injection, and preserves a sandbox whose identity cannot be verified. |
| 34 | + Portable onboarding verifies the cgroups v2 CPU controller at the root hierarchy, per-user slice, user manager, and `app.slice` before mutation, with documented administrator-owned Ubuntu 22.04 preparation and rollback. |
| 35 | + Portable OpenClaw onboarding publishes readiness only after paired-device and active-operator scopes settle against the current lifecycle receipt; connect, recovery, and launch preflight perform at most one bounded repair or report incomplete onboarding. |
| 36 | + Fresh Portable onboarding defaults to the narrower `weather`, `public-reference`, and `github` policy presets, retains explicit model intent, and reconciles a timed-out stop only after the exact receipt-owned container reaches `Running=false`. |
| 37 | + Portable uninstall removes only receipt-owned Podman resources and NemoClaw-owned selectors, preserves ambiguous state for retry, and leaves ordinary Docker, model stores, and unrelated user resources unchanged. |
| 38 | + For more information, refer to [Platform Support](/user-guide/openclaw/reference/platform-support), [Network Policies Reference](/user-guide/openclaw/reference/network-policies), [Uninstall NemoClaw](/user-guide/openclaw/manage-sandboxes/operate-sandboxes/uninstall-nemoclaw), and [Troubleshooting](/user-guide/openclaw/reference/troubleshooting). |
| 39 | + Related changes: [PR #9176](https://github.com/NVIDIA/NemoClaw/pull/9176), [PR #9197](https://github.com/NVIDIA/NemoClaw/pull/9197), [PR #9289](https://github.com/NVIDIA/NemoClaw/pull/9289), [PR #9270](https://github.com/NVIDIA/NemoClaw/pull/9270), [PR #9339](https://github.com/NVIDIA/NemoClaw/pull/9339), [PR #9209](https://github.com/NVIDIA/NemoClaw/pull/9209), [PR #9186](https://github.com/NVIDIA/NemoClaw/pull/9186), and [PR #9376](https://github.com/NVIDIA/NemoClaw/pull/9376). |
| 40 | +- Later onboarding runs now record when the host stops configuring a messaging channel, remove its stale egress preset, and preserve in-sandbox QR-paired channels whose state the host cannot determine. |
| 41 | + Managed startup validation accepts schema-owned messaging package pins and approved credential placeholder assignments while continuing to reject raw credentials, mismatched keys, and malformed or misplaced values. |
| 42 | + `policy remove` can remove a preset enforced by the live gateway even when the local registry lacks it, and reports an unavailable gateway separately from a gateway that does not hold the preset. |
| 43 | + Experimental Google Chat pairing approval becomes active for the next message after direct approval, with managed restart recovery when activation partially commits. |
| 44 | + For more information, refer to [Enable Channels During Onboarding](/user-guide/openclaw/manage-sandboxes/messaging-channels/enable-channels-during-onboarding), [Set Up Google Chat](/user-guide/openclaw/manage-sandboxes/messaging-channels/set-up-google-chat), and [Apply Policy Presets](/user-guide/openclaw/network-policy/configure-policies/apply-policy-presets). |
| 45 | + Related changes: [PR #9296](https://github.com/NVIDIA/NemoClaw/pull/9296), [PR #9327](https://github.com/NVIDIA/NemoClaw/pull/9327), [PR #9306](https://github.com/NVIDIA/NemoClaw/pull/9306), [PR #9248](https://github.com/NVIDIA/NemoClaw/pull/9248), and [PR #9374](https://github.com/NVIDIA/NemoClaw/pull/9374). |
| 46 | +- Snapshot backup now accepts multiply linked regular package files in a Hermes sandbox while continuing to reject unsafe symbolic links and special files. |
| 47 | + `uninstall --destroy-user-data` removes installer-managed user-local CLI shims when sibling evidence does not require the shared package, and full Portable uninstall follows its separate receipt-bound cleanup contract. |
| 48 | + The experimental voice gateway reads startup credentials from fixed inherited file descriptors instead of accepting credential paths in process arguments, and Shields accepts only bounded native OpenClaw device-store modes while restoring mutable state. |
| 49 | + OpenClaw startup guard output now stays in a root-only child directory while the shared runtime directory remains traversable, preserving access to the root-owned managed CA bundle without exposing guard diagnostics to sandbox processes. |
| 50 | + For more information, refer to [Create and Restore Snapshots](/user-guide/openclaw/manage-sandboxes/state-and-backups/create-and-restore-snapshots), [Uninstall NemoClaw](/user-guide/openclaw/manage-sandboxes/operate-sandboxes/uninstall-nemoclaw), [Filesystem Controls](/user-guide/openclaw/security/security-controls/filesystem-controls), and the [NemoClaw CLI Commands Reference](/user-guide/openclaw/reference/commands). |
| 51 | + Related changes: [PR #9317](https://github.com/NVIDIA/NemoClaw/pull/9317), [PR #9288](https://github.com/NVIDIA/NemoClaw/pull/9288), [PR #9239](https://github.com/NVIDIA/NemoClaw/pull/9239), [PR #9269](https://github.com/NVIDIA/NemoClaw/pull/9269), and [PR #9371](https://github.com/NVIDIA/NemoClaw/pull/9371). |
| 52 | +- Release qualification again treats the trusted staging Launchable deployment as required evidence and retains bounded, secret-safe readiness diagnostics and transient collaborator-permission retries. |
| 53 | + The E2E workflow reports same-commit first-pass and retry reliability, retries only transient reads of the exact trusted contract artifact, executes the credential-free native-runtime qualification matrix without enabling production Podman selection, and documents canonical target selection and retry rules. |
| 54 | + Post-merge documentation catch-up now runs after merges through separated author, reviewer, and publisher boundaries, while release prep continues to require the dated changelog entry on `main` before tag planning. |
| 55 | + Related changes: [PR #9351](https://github.com/NVIDIA/NemoClaw/pull/9351), [PR #9350](https://github.com/NVIDIA/NemoClaw/pull/9350), [PR #9353](https://github.com/NVIDIA/NemoClaw/pull/9353), [PR #9226](https://github.com/NVIDIA/NemoClaw/pull/9226), [PR #9237](https://github.com/NVIDIA/NemoClaw/pull/9237), [PR #9232](https://github.com/NVIDIA/NemoClaw/pull/9232), [PR #9275](https://github.com/NVIDIA/NemoClaw/pull/9275), [PR #9234](https://github.com/NVIDIA/NemoClaw/pull/9234), and [PR #9365](https://github.com/NVIDIA/NemoClaw/pull/9365). |
0 commit comments