rsliter · Oct 20, 2026 · Oct 16, 2026 · Oct 16, 2026 · Oct 16, 2026 · Oct 19, 2026
diff --git a/docs/changelog/2026-10-12.mdx b/docs/changelog/2026-10-12.mdx
@@ -45,4 +45,4 @@ It also makes policy removal, provider verification, and configuration export mo
   Collection and delivery share a five-second total limit, and `NEMOCLAW_DISABLE_TELEMETRY=1` suppresses both.
   Production delivery is not enabled.
   Related change: [PR #12859](https://github.com/NVIDIA/NemoClaw/pull/12859).
-  Refer to [QA Operation Telemetry](/user-guide/openclaw/security/best-practices#qa-operation-telemetry).
+  Refer to [Operation Telemetry](/user-guide/openclaw/security/best-practices#operation-telemetry).
diff --git a/docs/changelog/2026-10-19.mdx b/docs/changelog/2026-10-19.mdx
@@ -0,0 +1,43 @@
+{/*
+ * SPDX-FileCopyrightText: Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+ * SPDX-License-Identifier: Apache-2.0
+ */}
+
+## v0.0.136
+
+NemoClaw v0.0.136 expands sandbox-attached inference and adds hosted image input and an experimental local profile for Super VL.
+It repairs onboarding and DGX Station Express recovery and strengthens provider ownership checks.
+Ordinary operation telemetry now uses the fixed TEST receiver.
+
+- Fresh custom hosted endpoint selections bind the validated endpoint, API, and credential source to a provider attached to the selected sandbox.
+  Inference status, health checks, switching, and rebuilds use that recorded route.
+  Existing shared-route selections remain on their recorded path.
+  Related change: [PR #13201](https://github.com/NVIDIA/NemoClaw/pull/13201).
+- New Deep Agents Code, OpenClaw, and Pi local selections use sandbox-attached providers for qualified local endpoints.
+  Hermes native-local startup, switching, and rebuild refresh supervisor-issued credential references while preserving the selected route and unrelated settings.
+  Related changes: [PR #13203](https://github.com/NVIDIA/NemoClaw/pull/13203), [PR #13293](https://github.com/NVIDIA/NemoClaw/pull/13293), [PR #13007](https://github.com/NVIDIA/NemoClaw/pull/13007), and [PR #13292](https://github.com/NVIDIA/NemoClaw/pull/13292).
+- For OpenClaw native-local routes, `status`, `connect`, and `start` now send health requests to the provider recorded for the sandbox.
+  They no longer probe an unconfigured shared route for those selections.
+  Related change: [PR #13447](https://github.com/NVIDIA/NemoClaw/pull/13447).
+- An explicit Experimental Nemotron 3.5 Super VL profile serves one 128 GB DGX Spark with native five-token MTP.
+  It rejects 64 GB or unknown-memory systems before installation and retains the Spark Qwen default.
+  Physical serving and managed-installer smoke tests passed; complete agent onboarding and sustained-load qualification remain pending.
+  Related change: [PR #13357](https://github.com/NVIDIA/NemoClaw/pull/13357).
+- The NVIDIA Endpoints model picker includes hosted `nvidia/nemotron-3.5-super-vl-120b-a12b` for OpenClaw.
+  Interactive and unattended onboarding enable text and image input for that selection unless an explicit valid input override is set.
+  Related change: [PR #13371](https://github.com/NVIDIA/NemoClaw/pull/13371).
+- Fresh Model Router onboarding waits for the selected OpenClaw gateway to accept connections before requesting its native restart.
+  If startup does not settle within the existing bound or the sandbox identity changes, setup stops before restart.
+  Related change: [PR #13481](https://github.com/NVIDIA/NemoClaw/pull/13481).
+- DGX Station Express keeps automatic model selection under the serving catalog.
+  Installation and resume now retain the selected GPU and model, accept the catalog's automatic receipt, verify an owned vLLM server before reuse, and preserve an unchanged sandbox route.
+  Related changes: [PR #13305](https://github.com/NVIDIA/NemoClaw/pull/13305) and [PR #13480](https://github.com/NVIDIA/NemoClaw/pull/13480).
+- Credential registration inspects existing operator profiles before changing provider state.
+  Sandbox creation verifies NemoClaw-owned extra profiles, and messaging setup rejects a fallback to a provider profile it does not own.
+  Related changes: [PR #13353](https://github.com/NVIDIA/NemoClaw/pull/13353), [PR #13356](https://github.com/NVIDIA/NemoClaw/pull/13356), and [PR #13351](https://github.com/NVIDIA/NemoClaw/pull/13351).
+- OpenClaw rebuild keeps the recorded dashboard origin when it restores a sandbox.
+  The `nemoclaw sandbox mcp` usage message now lists the existing `update` action.
+  Related changes: [PR #13198](https://github.com/NVIDIA/NemoClaw/pull/13198) and [PR #12384](https://github.com/NVIDIA/NemoClaw/pull/12384).
+- The installer and supported CLI operations now attempt anonymous completion telemetry by default through NVIDIA's fixed TEST receiver.
+  QA runs can still add a valid test label; `NEMOCLAW_DISABLE_TELEMETRY=1` suppresses collection and delivery, and Production delivery remains disabled.
+  Related change: [PR #13494](https://github.com/NVIDIA/NemoClaw/pull/13494).
diff --git a/docs/get-started/quickstart-hermes.mdx b/docs/get-started/quickstart-hermes.mdx
@@ -36,6 +36,11 @@ Review the [Prerequisites](prerequisites) before you begin.
 
 <Steps>
   <Step title="Install NemoClaw for Hermes">
+    The installer and supported CLI operations attempt anonymous completion telemetry to NVIDIA's fixed TEST receiver by default.
+    Run `export NEMOCLAW_DISABLE_TELEMETRY=1` in this shell before installation to suppress collection and delivery.
+    Repeat it in any new shell used for NemoClaw CLI commands.
+    Refer to [Operation Telemetry](/user-guide/hermes/security/best-practices#operation-telemetry) for details.
+
     Run the hosted installer.
 
     ```bash

diff --git a/docs/get-started/quickstart-langchain-deepagents-code.mdx b/docs/get-started/quickstart-langchain-deepagents-code.mdx
@@ -40,6 +40,11 @@ If you use the coding-agent prompt in the preceding section, you can skip this p
 
 <Steps>
   <Step title="Install NemoClaw for Deep Agents">
+    The installer and supported CLI operations attempt anonymous completion telemetry to NVIDIA's fixed TEST receiver by default.
+    Run `export NEMOCLAW_DISABLE_TELEMETRY=1` in this shell before installation to suppress collection and delivery.
+    Repeat it in any new shell used for NemoClaw CLI commands.
+    Refer to [Operation Telemetry](/user-guide/deepagents/security/best-practices#operation-telemetry) for details.
+
     Run the hosted installer.
 
     ```bash
@@ -274,7 +279,12 @@ If you upgrade from a release that persisted LangSmith environment values, rebui
 
 `status` reports the selected harness as a terminal runtime and prints the interactive/headless command shape. If `status` reports `Runtime health: degraded` with an OOM kill count, rebuild the sandbox to restore the terminal runtime. Proxy launchers and startup scripts are baked into the sandbox image. After upgrading from a release that used `inference.local` for NVIDIA Endpoints, recreate each NVIDIA sandbox during onboarding. NemoClaw does not add the required native provider attachment to an existing beta sandbox. NemoClaw v0.0.78 and newer clients fail closed when a pre-v0.0.78 sandbox image lacks the trusted `/usr/local/lib/nemoclaw/dcode-managed-exec` route-probe helper, even when the installed Deep Agents Code version still matches the managed manifest. Rebuild the sandbox to install that image-owned helper before retrying `status`, `doctor`, `connect`, or onboarding recovery. There is no dashboard port or long-running gateway process for this harness.
 
-Older Deep Agents Code sandboxes with a standalone local shared route have no native provider attachment. Back up the sandbox before upgrading OpenShell, then recreate it with `nemo-deepagents onboard --fresh --name <sandbox-name> --recreate-sandbox`. Expect downtime while the replacement is created. Resume and rebuild stop if the old standalone local route has no native attachment; NemoClaw does not migrate it automatically. Owned Local NVIDIA NIM keeps its shared route and can resume without a native attachment.
+Older Deep Agents Code sandboxes with a standalone local shared route have no native provider attachment.
+Back up the sandbox before upgrading OpenShell, then recreate it with `nemo-deepagents onboard --fresh --name <sandbox-name> --recreate-sandbox`.
+Expect downtime while the replacement is created.
+Resume and rebuild stop if the old standalone local route has no native attachment; NemoClaw does not migrate it automatically.
+This requirement applies to Ollama, standalone vLLM, llama.cpp, and qualifying local compatible endpoints.
+Owned Local NVIDIA NIM keeps its shared route and can resume without a native attachment.
 
 ## Next Steps
 

diff --git a/docs/get-started/quickstart-pi.mdx b/docs/get-started/quickstart-pi.mdx
@@ -35,6 +35,10 @@ Native Podman, macOS, Windows, WSL, messaging channels, dashboards, host mounts,
 ## Install and Onboard
 
 After Pi activation is available in the selected NemoClaw release, install NemoClaw and select Pi explicitly.
+The installer and supported CLI operations attempt anonymous completion telemetry to NVIDIA's fixed TEST receiver by default.
+Run `export NEMOCLAW_DISABLE_TELEMETRY=1` in this shell before installation to suppress collection and delivery.
+Repeat it in any new shell used for NemoClaw CLI commands.
+Refer to [Operation Telemetry](/user-guide/openclaw/security/best-practices#operation-telemetry) for details.
 
 ```bash
 curl -fsSL https://www.nvidia.com/nemoclaw.sh | \

diff --git a/docs/get-started/quickstart.mdx b/docs/get-started/quickstart.mdx
@@ -35,6 +35,11 @@ Review the [Prerequisites](prerequisites) before you begin.
 
 <Steps>
   <Step title="Install NemoClaw">
+    The installer and supported CLI operations attempt anonymous completion telemetry to NVIDIA's fixed TEST receiver by default.
+    Run `export NEMOCLAW_DISABLE_TELEMETRY=1` in this shell before installation to suppress collection and delivery.
+    Repeat it in any new shell used for NemoClaw CLI commands.
+    Refer to [Operation Telemetry](/user-guide/openclaw/security/best-practices#operation-telemetry) for details.
+
     Run the hosted installer in a terminal.
 
     ```bash
@@ -337,6 +342,10 @@ Use these details when your first-run path needs more control.
     | Local Ollama | You want a host-local Ollama model. | None |
     | Model Router | You want NemoClaw to start the host-side model router. | `NVIDIA_INFERENCE_API_KEY` |
 
+    The NVIDIA Endpoints model picker includes hosted `nvidia/nemotron-3.5-super-vl-120b-a12b`.
+    Selecting it enables text and image input unless you provide an explicit valid override.
+    Refer to [Configure OpenClaw Model Capabilities](/user-guide/openclaw/inference/manage-inference/configure-model-capabilities) for input settings.
+
     For an OpenAI-compatible HTTP endpoint on `localhost`, `127.0.0.1`, or `[::1]`, press Enter to select no authentication when the endpoint uses the port selected by `NEMOCLAW_VLLM_PORT` (`8000` by default) or port `11434`.
     Port `11435` is reserved for the proxy and is unavailable for new no-authentication endpoints.
     Recovery can retain an existing no-authentication route on `11435` only when the proxy has moved and no other protected service owns that port.

diff --git a/docs/get-started/windows-preparation.mdx b/docs/get-started/windows-preparation.mdx
@@ -81,6 +81,10 @@ The default distro is `Ubuntu-24.04`.
 To reuse an existing distro named `Ubuntu`, pass `-DistroName Ubuntu`.
 
 The bootstrap script does not install NemoClaw itself.
+The installer and supported CLI operations attempt anonymous completion telemetry to NVIDIA's fixed TEST receiver by default.
+Run `export NEMOCLAW_DISABLE_TELEMETRY=1` in the Ubuntu shell before installation to suppress collection and delivery.
+Repeat it in any new shell used for NemoClaw CLI commands.
+Refer to [Operation Telemetry](/user-guide/openclaw/security/best-practices#operation-telemetry) for details.
 When Windows preparation is complete, it opens Ubuntu and prints the standard installer command to run inside Ubuntu:
 
 ```bash

diff --git a/docs/index.mdx b/docs/index.mdx
@@ -50,6 +50,10 @@ It helps you choose an agent to run in an OpenShell sandbox, asks one question a
 
 ### From Your Terminal
 
+The installer and supported CLI operations attempt anonymous completion telemetry to NVIDIA's fixed TEST receiver by default.
+Run `export NEMOCLAW_DISABLE_TELEMETRY=1` in this shell before installation to suppress collection and delivery.
+Repeat it in any new shell used for NemoClaw CLI commands.
+Refer to [Operation Telemetry](/user-guide/openclaw/security/best-practices#operation-telemetry) for details.
 Paste this command into your terminal for the default installation process.
 
 <llms-ignore>

diff --git a/docs/inference/choose-local-inference-server.mdx b/docs/inference/choose-local-inference-server.mdx
@@ -102,6 +102,11 @@ It runs the remaining onboarding steps non-interactively and can recreate the na
 The runtime stores an owner-only bearer API key and model artifacts on the host.
 </Warning>
 
+The installer and supported CLI operations also attempt anonymous completion telemetry to NVIDIA's fixed TEST receiver by default.
+Run `export NEMOCLAW_DISABLE_TELEMETRY=1` in this shell before installation to suppress collection and delivery.
+Repeat it in any new shell used for NemoClaw CLI commands.
+Refer to [Operation Telemetry](/user-guide/openclaw/security/best-practices#operation-telemetry) for details.
+
 ```bash
 curl -fsSL https://www.nvidia.com/nemoclaw.sh | \
 <AgentOnly variant="openclaw">

diff --git a/docs/inference/set-up-model-router.mdx b/docs/inference/set-up-model-router.mdx
@@ -19,6 +19,8 @@ During onboarding, NemoClaw starts the router proxy on host port `4000`, waits f
 The sandbox does not call port `4000` directly.
 On a host without cached routing-model files, Model Router downloads and loads its routing model before the health endpoint responds.
 NemoClaw gives a running router up to 10 minutes to pass its health check and stops onboarding sooner if the process exits.
+Routed OpenClaw setup then waits for the selected sandbox gateway to accept connections before requesting its native restart.
+If the gateway does not become ready within the startup bound, or the sandbox identity changes while waiting, setup stops before restart.
 NemoClaw tries to append router process output to `~/.nemoclaw/state/model-router.log`.
 A nondefault gateway port uses `~/.nemoclaw/gateways/<port>/state/model-router.log`.
 NemoClaw creates or reopens the log with owner-only permissions.

diff --git a/docs/inference/set-up-vllm-on-two-dgx-sparks.mdx b/docs/inference/set-up-vllm-on-two-dgx-sparks.mdx
@@ -128,6 +128,10 @@ Do not interpret two qualified `200,000 Mbps` rails as measured aggregate servin
 ## Run Automatic Express Installation
 
 Run the interactive installer on the system that should become the head.
+The installer and supported CLI operations attempt anonymous completion telemetry to NVIDIA's fixed TEST receiver by default.
+Run `export NEMOCLAW_DISABLE_TELEMETRY=1` in this shell before installation to suppress collection and delivery.
+Repeat it in any new shell used for NemoClaw CLI commands.
+Refer to [Operation Telemetry](/user-guide/openclaw/security/best-practices#operation-telemetry) for details.
 
 ```bash
 curl -fsSL https://www.nvidia.com/nemoclaw.sh | \

diff --git a/docs/inference/set-up-vllm-on-two-dgx-stations.mdx b/docs/inference/set-up-vllm-on-two-dgx-stations.mdx
@@ -67,6 +67,10 @@ A missing, malformed, or mismatched ownership field remains foreign state and st
 For the first non-interactive setup, pass the managed provider and peer to the shell installer.
 The installer qualifies the pair and creates the peer binding that managed vLLM requires.
 Do not set `NEMOCLAW_DGX_STATION_SSH_BINDING` yourself or run `$$nemoclaw onboard` directly for the first pair setup.
+The installer and supported CLI operations attempt anonymous completion telemetry to NVIDIA's fixed TEST receiver by default.
+Run `export NEMOCLAW_DISABLE_TELEMETRY=1` in this shell before installation to suppress collection and delivery.
+Repeat it in any new shell used for NemoClaw CLI commands.
+Refer to [Operation Telemetry](/user-guide/openclaw/security/best-practices#operation-telemetry) for details.
 
 ```bash
 curl -fsSL https://www.nvidia.com/nemoclaw.sh | \