docs: use ~/nemoclaw instead of hardcoded /home/ubuntu (#1319)

.agents/skills/nemoclaw-user-deploy-remote/SKILL.md

@@ -71,7 +71,7 @@ $ nemoclaw deploy <instance-name>
 SSH to the instance and run the OpenShell TUI to monitor activity and approve network requests:
 
 ```console
-$ ssh <instance-name> 'cd /home/ubuntu/nemoclaw && set -a && . .env && set +a && openshell term'
+$ ssh <instance-name> 'cd ~/nemoclaw && set -a && . .env && set +a && openshell term'
 ```
 
 ## Step 5: Verify Inference

.agents/skills/nemoclaw-user-manage-policy/SKILL.md

@@ -30,7 +30,7 @@ $ openshell term
 For a remote sandbox, pass the instance name:
 
 ```console
-$ ssh my-gpu-box 'cd /home/ubuntu/nemoclaw && . .env && openshell term'
+$ ssh my-gpu-box 'cd ~/nemoclaw && . .env && openshell term'
 ```
 
 The TUI displays the sandbox state, active inference provider, and a live feed of network activity.

.agents/skills/nemoclaw-user-reference/references/troubleshooting.md

@@ -350,6 +350,18 @@ The status command detects the sandbox context and reports "active (inside sandb
 
 Run `openshell sandbox list` on the host to check the underlying sandbox state.
 
+### `openclaw update` hangs or times out inside the sandbox
+
+This is expected for the current NemoClaw deployment model.
+NemoClaw installs `openclaw` into the sandbox image at build time, so the CLI is image-pinned rather than updated in place inside a running sandbox.
+
+Do not run `openclaw update` inside the sandbox.
+Instead:
+
+1. Upgrade to a NemoClaw release that includes the newer `openclaw` version.
+2. If you build NemoClaw from source, bump the pinned `openclaw` version in `Dockerfile.base` and rebuild the sandbox base image.
+3. Back up any workspace files you need, then recreate the sandbox so it uses the rebuilt image.
+
 ### Inference requests time out
 
 Verify that the inference provider endpoint is reachable from the host.

docs/deployment/deploy-to-remote-gpu.md

@@ -83,7 +83,7 @@ $ nemoclaw deploy <instance-name>
 SSH to the instance and run the OpenShell TUI to monitor activity and approve network requests:
 
 ```console
-$ ssh <instance-name> 'cd /home/ubuntu/nemoclaw && set -a && . .env && set +a && openshell term'
+$ ssh <instance-name> 'cd ~/nemoclaw && set -a && . .env && set +a && openshell term'
 ```
 
 ## Verify Inference

docs/network-policy/approve-network-requests.md

@@ -41,7 +41,7 @@ $ openshell term
 For a remote sandbox, pass the instance name:
 
 ```console
-$ ssh my-gpu-box 'cd /home/ubuntu/nemoclaw && . .env && openshell term'
+$ ssh my-gpu-box 'cd ~/nemoclaw && . .env && openshell term'
 ```
 
 The TUI displays the sandbox state, active inference provider, and a live feed of network activity.