docs: expand messaging channels and reorganize sandbox guides#2850
Merged
Conversation
Co-authored-by: Cursor <cursoragent@cursor.com>
Contributor
📝 WalkthroughWalkthroughDocumentation reorganized to add a consolidated manage-sandboxes/ section (lifecycle, messaging channels, workspace, backup), update cross-references and generated skill mappings, add several skill-priority frontmatter entries, and remove the standalone Telegram bridge doc in favor of a unified messaging-channels guide. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant User as User
participant Provider as Messaging Provider\n(Telegram/Discord/Slack)
participant Gateway as OpenShell Gateway\n(host)
participant CLI as nemoclaw CLI
participant Sandbox as Sandbox Agent
Note over CLI,Gateway: Onboarding / channel registration
User->>CLI: nemoclaw onboard (provide token / env)
CLI->>Gateway: register bridge / store token
Gateway->>Sandbox: trigger rebuild (if needed)
Sandbox-->>Gateway: confirm bridge config persisted
Note over User,Provider: Message flow
User->>Provider: send message
Provider->>Gateway: deliver webhook/event
Gateway->>Sandbox: forward message to agent
Sandbox->>Gateway: agent response/log
Gateway->>Provider: (optional) send outbound reply
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
|
Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually. Contributors can view more details about this message here. |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (2)
docs/manage-sandboxes/messaging-channels.md (1)
169-174: ⚡ Quick winRename the bottom section to “Next Steps” for doc consistency.
The new page ends with “Related Topics”; the style guide expects a “Next Steps” section at the bottom with related links.
As per coding guidelines, new pages must include "A 'Next Steps' section at the bottom links to related pages."
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/manage-sandboxes/messaging-channels.md` around lines 169 - 174, Rename the trailing section header "Related Topics" to "Next Steps" to follow the style guide and leave the existing list of links intact; update the heading text in the markdown where the "Related Topics" H2 appears so it reads "Next Steps" (preserving the same markdown heading level and the three bulleted links to deployment, architecture, and commands).docs/manage-sandboxes/lifecycle.md (1)
220-226: ⚡ Quick winUse “Next Steps” as the closing section title.
The page closes with “Related Topics”; the docs structure standard expects “Next Steps.”
As per coding guidelines, new pages must include "A 'Next Steps' section at the bottom links to related pages."
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/manage-sandboxes/lifecycle.md` around lines 220 - 226, Replace the closing section heading "Related Topics" with "Next Steps" and keep the existing list of links intact; specifically update the heading text that currently reads "Related Topics" to "Next Steps" so the page includes the required "A 'Next Steps' section at the bottom links to related pages." Ensure the link list under the heading (entries like "Set Up Messaging Channels", "Workspace Files", "Backup and Restore", "Monitor Sandbox Activity") remains unchanged.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@docs/get-started/quickstart.md`:
- Around line 301-313: The CLI examples use ```bash blocks without shell
prompts; change both examples to use ```console fenced code blocks and add a
leading "$ " prompt to the commands (replace the "nemoclaw my-assistant connect"
and "openclaw agent --agent main --local -m \"hello\" --session-id test" lines
so they appear as "$ nemoclaw my-assistant connect" and "$ openclaw agent
--agent main --local -m \"hello\" --session-id test"). Ensure both fence
openings read "```console" and the commands include the dollar prompt to comply
with the CLI code block guideline.
In `@docs/manage-sandboxes/lifecycle.md`:
- Around line 76-90: Update the CLI examples in
docs/manage-sandboxes/lifecycle.md to use the required `console` code block tag
and include a `$` prompt prefix for each command: replace the three ```bash
blocks containing "nemoclaw my-assistant connect", "openclaw tui", and "openclaw
agent --agent main --local -m \"hello\" --session-id test" with ```console
blocks and prepend `$ ` to the command lines; do the same for the later examples
"nemoclaw uninstall" and `curl -fsSL
https://raw.githubusercontent.com/NVIDIA/NemoClaw/refs/heads/main/uninstall.sh |
bash`; apply the same transformation to the additional examples mentioned in the
200-216 range.
---
Nitpick comments:
In `@docs/manage-sandboxes/lifecycle.md`:
- Around line 220-226: Replace the closing section heading "Related Topics" with
"Next Steps" and keep the existing list of links intact; specifically update the
heading text that currently reads "Related Topics" to "Next Steps" so the page
includes the required "A 'Next Steps' section at the bottom links to related
pages." Ensure the link list under the heading (entries like "Set Up Messaging
Channels", "Workspace Files", "Backup and Restore", "Monitor Sandbox Activity")
remains unchanged.
In `@docs/manage-sandboxes/messaging-channels.md`:
- Around line 169-174: Rename the trailing section header "Related Topics" to
"Next Steps" to follow the style guide and leave the existing list of links
intact; update the heading text in the markdown where the "Related Topics" H2
appears so it reads "Next Steps" (preserving the same markdown heading level and
the three bulleted links to deployment, architecture, and commands).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: c8720d50-eb5e-4469-8e72-0911ca1bfb41
📒 Files selected for processing (14)
docs/CONTRIBUTING.mddocs/conf.pydocs/deployment/deploy-to-remote-gpu.mddocs/deployment/set-up-telegram-bridge.mddocs/get-started/quickstart-hermes.mddocs/get-started/quickstart.mddocs/index.mddocs/inference/set-up-sub-agent.mddocs/manage-sandboxes/backup-restore.mddocs/manage-sandboxes/lifecycle.mddocs/manage-sandboxes/messaging-channels.mddocs/manage-sandboxes/workspace-files.mddocs/reference/commands.mddocs/reference/troubleshooting.md
💤 Files with no reviewable changes (1)
- docs/deployment/set-up-telegram-bridge.md
miyoungc
changed the title
Contributor
There was a problem hiding this comment.
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (3)
docs/inference/set-up-sub-agent.md (3)
24-113:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winApply required capitalization:
SandboxandGateway.There are multiple instances of the words
sandboxandgatewayin prose that should be capitalized per the project word list (e.g., “inside the sandbox.” around Line 30, “OpenShell sandbox” around Line 34, “/tmp/gateway.log … gateway …” around Line 43, “confirm the gateway …” around Line 90, and “OpenClaw gateway runs …” around Line 111). As per coding guidelines, “Word List: sandbox → Sandbox (unless starting a sentence)” and “gateway → Gateway (unless starting a sentence).”🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/inference/set-up-sub-agent.md` around lines 24 - 113, Multiple prose instances use lowercase "sandbox" and "gateway" but the project word list mandates "Sandbox" and "Gateway" (unless at sentence start); update each occurrence in this doc — specifically the phrases "inside the sandbox", "OpenShell sandbox", the path token "/sandbox/.openclaw", "/tmp/gateway.log", the phrase "confirm the gateway hot-reloaded", and "OpenClaw gateway runs" — to use "Sandbox" and "Gateway" respectively while preserving sentence-start capitalization rules and paths exactly as-is.
48-52:⚠️ Potential issue | 🟠 Major | ⚡ Quick winRemove/replace third-party GitHub repo links.
You link to a GitHub repository (
brevdev/nemoclaw-demos) in both the Omni example section (Line 50) and the Demo Assets section (Line 129). The docs style rules prohibit links to third-party code repositories/unofficial resources; you should link only to official tool documentation (or internal docs that are part of this site). As per coding guidelines, “docs/**/*.md: Do not add links to third-party code repositories, community collections, or unofficial resources in documentation; only link to official tool documentation (Node.js, Python, uv).”Also applies to: 127-134
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/inference/set-up-sub-agent.md` around lines 48 - 52, The docs contain a disallowed third-party GitHub link (`vlm-demo` -> brevdev/nemoclaw-demos) in the "Omni Vision Sub-Agent Example" section and again in the "Demo Assets" section; remove or replace those links with approved alternatives (either link to official tool documentation or an internal documentation page/example). Specifically, update the "Omni Vision Sub-Agent Example" paragraph (the `vlm-demo` reference) and the "Demo Assets" section to remove the external GitHub URL and instead point to an internal example page or the official Omni/vision model docs, or simply remove the link and keep the descriptive text.
2-27:⚠️ Potential issue | 🟡 Minor | ⚡ Quick winFix H1 to match
title.pagefrontmatter exactly.The page H1 (
# Set Up Task-Specific Sub-Agents, Line 25) doesn’t exactly match thetitle.pagefrontmatter value (Set up a Task-Specific Sub-Agent, Line 3), including singular/plural and capitalization. This breaks the doc “page structure” consistency checks. As per coding guidelines, “H1 heading matches thetitle.pagefrontmatter value.”🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/inference/set-up-sub-agent.md` around lines 2 - 27, The H1 in the document ("# Set Up Task-Specific Sub-Agents") does not exactly match the title.page frontmatter value ("Set up a Task-Specific Sub-Agent"); update the H1 to exactly match the title.page string (including capitalization and singular/plural) so the H1 equals "Set up a Task-Specific Sub-Agent" to satisfy the page-structure rule that H1 matches title.page; verify no extra whitespace or punctuation differences remain.
🧹 Nitpick comments (1)
docs/inference/set-up-sub-agent.md (1)
136-143: 💤 Low valueAvoid repeated “Refer to …” lead-in in consecutive bullets (LLM pattern).
In “Next Steps”, consecutive bullets start with the same phrase (“Refer to …”, Lines 140-142). Static analysis flagged this repetition; vary the lead-in wording to reduce LLM-pattern feel. As per coding guidelines, “LLM-Generated Patterns … Flag every occurrence: … Excessive em dashes, superlatives, hedge words,” and the static analysis hint “Three successive sentences begin with the same word.”
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@docs/inference/set-up-sub-agent.md` around lines 136 - 143, In the "Next Steps" section replace the three consecutive bullets that all start with "Refer to ..." with varied lead-ins to avoid repetition; update the bullets referencing OpenClaw Sub-Agents, Switch Inference Providers, and Workspace Files so they use distinct phrasing (for example: "See OpenClaw Sub-Agents for ...", "To change the primary orchestration model, consult Switch Inference Providers", "Learn about per-agent workspace directories in Workspace Files") while preserving the existing links and descriptions.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Outside diff comments:
In `@docs/inference/set-up-sub-agent.md`:
- Around line 24-113: Multiple prose instances use lowercase "sandbox" and
"gateway" but the project word list mandates "Sandbox" and "Gateway" (unless at
sentence start); update each occurrence in this doc — specifically the phrases
"inside the sandbox", "OpenShell sandbox", the path token "/sandbox/.openclaw",
"/tmp/gateway.log", the phrase "confirm the gateway hot-reloaded", and "OpenClaw
gateway runs" — to use "Sandbox" and "Gateway" respectively while preserving
sentence-start capitalization rules and paths exactly as-is.
- Around line 48-52: The docs contain a disallowed third-party GitHub link
(`vlm-demo` -> brevdev/nemoclaw-demos) in the "Omni Vision Sub-Agent Example"
section and again in the "Demo Assets" section; remove or replace those links
with approved alternatives (either link to official tool documentation or an
internal documentation page/example). Specifically, update the "Omni Vision
Sub-Agent Example" paragraph (the `vlm-demo` reference) and the "Demo Assets"
section to remove the external GitHub URL and instead point to an internal
example page or the official Omni/vision model docs, or simply remove the link
and keep the descriptive text.
- Around line 2-27: The H1 in the document ("# Set Up Task-Specific Sub-Agents")
does not exactly match the title.page frontmatter value ("Set up a Task-Specific
Sub-Agent"); update the H1 to exactly match the title.page string (including
capitalization and singular/plural) so the H1 equals "Set up a Task-Specific
Sub-Agent" to satisfy the page-structure rule that H1 matches title.page; verify
no extra whitespace or punctuation differences remain.
---
Nitpick comments:
In `@docs/inference/set-up-sub-agent.md`:
- Around line 136-143: In the "Next Steps" section replace the three consecutive
bullets that all start with "Refer to ..." with varied lead-ins to avoid
repetition; update the bullets referencing OpenClaw Sub-Agents, Switch Inference
Providers, and Workspace Files so they use distinct phrasing (for example: "See
OpenClaw Sub-Agents for ...", "To change the primary orchestration model,
consult Switch Inference Providers", "Learn about per-agent workspace
directories in Workspace Files") while preserving the existing links and
descriptions.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Enterprise
Run ID: 0e4979d4-ffd9-4c82-93ae-a17cd3cc46eb
📒 Files selected for processing (11)
docs/deployment/deploy-to-remote-gpu.mddocs/deployment/install-openclaw-plugins.mddocs/inference/set-up-sub-agent.mddocs/inference/switch-inference-providers.mddocs/inference/use-local-inference.mddocs/manage-sandboxes/backup-restore.mddocs/manage-sandboxes/lifecycle.mddocs/manage-sandboxes/messaging-channels.mddocs/monitoring/monitor-sandbox-activity.mddocs/network-policy/approve-network-requests.mddocs/network-policy/customize-network-policy.md
✅ Files skipped from review due to trivial changes (10)
- docs/monitoring/monitor-sandbox-activity.md
- docs/inference/use-local-inference.md
- docs/inference/switch-inference-providers.md
- docs/deployment/install-openclaw-plugins.md
- docs/network-policy/customize-network-policy.md
- docs/manage-sandboxes/backup-restore.md
- docs/deployment/deploy-to-remote-gpu.md
- docs/network-policy/approve-network-requests.md
- docs/manage-sandboxes/messaging-channels.md
- docs/manage-sandboxes/lifecycle.md
cv
approved these changes
May 1, 2026
wscurran
added
area: docs
This was referenced Jul 4, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Expands the messaging channels documentation into a full Telegram, Discord, and Slack guide, including onboarding-time setup, post-onboarding
channels add, credential rotation, pause/resume, and delivery verification. The remaining changes reorganize sandbox lifecycle and workspace docs under a dedicated Manage Sandboxes section while preserving old URLs with redirects.Changes
docs/manage-sandboxes/and updated the docs navigation.Type of Change
Verification
npx prek run --all-filespassesnpm testpassesmake docsbuilds without warnings (doc changes only)AI Disclosure
Signed-off-by: Miyoung Choi miyoungc@nvidia.com
Summary by CodeRabbit