docs(tools): add Related sections and unify See also to Related

This commit is contained in:
Vincent Koc
2026-04-23 15:41:49 -07:00
parent 1daa552d5f
commit 6667f66fd8
22 changed files with 108 additions and 5 deletions

View File

@@ -800,3 +800,9 @@ Restart the gateway after changing these values.
| `AcpRuntimeError: Permission prompt unavailable in non-interactive mode` | `permissionMode` blocks writes/exec in non-interactive ACP session. | Set `plugins.entries.acpx.config.permissionMode` to `approve-all` and restart gateway. See [Permission configuration](#permission-configuration). |
| ACP session fails early with little output | Permission prompts are blocked by `permissionMode`/`nonInteractivePermissions`. | Check gateway logs for `AcpRuntimeError`. For full permissions, set `permissionMode=approve-all`; for graceful degradation, set `nonInteractivePermissions=deny`. |
| ACP session stalls indefinitely after completing work | Harness process finished but ACP session did not report completion. | Monitor with `ps aux \| grep acpx`; kill stale processes manually. |
## Related
- [Sub-agents](/tools/subagents)
- [Multi-agent sandbox tools](/tools/multi-agent-sandbox-tools)
- [Agent send](/tools/agent-send)

View File

@@ -48,3 +48,9 @@ The tool accepts a single `input` string that wraps one or more file operations:
"input": "*** Begin Patch\n*** Update File: src/index.ts\n@@\n-const foo = 1\n+const foo = 2\n*** End Patch"
}
```
## Related
- [Diffs](/tools/diffs)
- [Exec tool](/tools/exec)
- [Code execution](/tools/code-execution)

View File

@@ -143,3 +143,9 @@ Notes:
- Remote CDP profiles accept `http://`, `https://`, `ws://`, and `wss://`.
Use HTTP(S) for `/json/version` discovery, or WS(S) when your browser
service gives you a direct DevTools socket URL.
## Related
- [Browser](/tools/browser)
- [Browser login](/tools/browser-login)
- [Browser WSL2 troubleshooting](/tools/browser-wsl2-windows-remote-cdp-troubleshooting)

View File

@@ -71,3 +71,9 @@ openclaw browser open https://x.com --browser-profile openclaw --target host
```
Or disable sandboxing for the agent that posts updates.
## Related
- [Browser](/tools/browser)
- [Browser Linux troubleshooting](/tools/browser-linux-troubleshooting)
- [Browser WSL2 troubleshooting](/tools/browser-wsl2-windows-remote-cdp-troubleshooting)

View File

@@ -217,3 +217,9 @@ When in doubt:
- verify the Windows Chrome endpoint locally first
- verify the same endpoint from WSL2 second
- only then debug OpenClaw config or Control UI auth
## Related
- [Browser](/tools/browser)
- [Browser login](/tools/browser-login)
- [Browser Linux troubleshooting](/tools/browser-linux-troubleshooting)

View File

@@ -115,3 +115,9 @@ Before shipping a new capability, verify:
If a PR skips the capability layer and hardcodes vendor behavior into a
channel/tool, send it back and define the contract first.
## Related
- [Plugin](/tools/plugin)
- [Creating skills](/tools/creating-skills)
- [Tools and plugins](/tools)

View File

@@ -350,3 +350,9 @@ export CLAWHUB_DISABLE_TELEMETRY=1
- `CLAWHUB_CONFIG_PATH`: Override where the CLI stores the token/config.
- `CLAWHUB_WORKDIR`: Override the default workdir.
- `CLAWHUB_DISABLE_TELEMETRY=1`: Disable telemetry on `sync`.
## Related
- [Plugin](/tools/plugin)
- [Skills](/tools/skills)
- [Community plugins](/plugins/community)

View File

@@ -86,3 +86,9 @@ the full analysis request and any inline data in one prompt.
- [Web tools](/tools/web)
- [Exec](/tools/exec)
- [xAI](/providers/xai)
## Related
- [Exec tool](/tools/exec)
- [Exec approvals](/tools/exec-approvals)
- [apply_patch tool](/tools/apply-patch)

View File

@@ -115,3 +115,9 @@ openclaw.invoke --tool llm-task --action json --args-json '{
- No tools are exposed to the model for this run.
- Treat output as untrusted unless you validate with `schema`.
- Put approvals before any side-effecting step (send, post, exec).
## Related
- [Thinking levels](/tools/thinking)
- [Sub-agents](/tools/subagents)
- [Slash commands](/tools/slash-commands)

View File

@@ -96,3 +96,9 @@ This protects users from runaway token spend and lockups while preserving normal
- `tools.loopDetection` is merged with agent-level overrides.
- Per-agent config fully overrides or extends global values.
- If no config exists, guardrails stay off.
## Related
- [Exec approvals](/tools/exec-approvals)
- [Thinking levels](/tools/thinking)
- [Sub-agents](/tools/subagents)

View File

@@ -72,3 +72,10 @@ voice contract can represent it.
- [Music Generation](/tools/music-generation) -- creating music and audio tracks
- [Text-to-Speech](/tools/tts) -- converting replies to spoken audio
- [Media Understanding](/nodes/media-understanding) -- understanding inbound images, audio, and video
## Related
- [Image generation](/tools/image-generation)
- [Video generation](/tools/video-generation)
- [Music generation](/tools/music-generation)
- [Text-to-speech](/tools/tts)

View File

@@ -363,7 +363,7 @@ After configuring multi-agent sandbox and tools:
---
## See also
## Related
- [Sandboxing](/gateway/sandboxing) -- full sandbox reference (modes, scopes, backends, images)
- [Sandbox vs Tool Policy vs Elevated](/gateway/sandbox-vs-tool-policy-vs-elevated) -- debugging "why is this blocked?"

View File

@@ -129,3 +129,9 @@ Use one of:
- bake the env into your custom sandbox image or remote sandbox environment
Global `env` and `skills.entries.<skill>.env/apiKey` apply to **host** runs only.
## Related
- [Skills](/tools/skills)
- [Creating skills](/tools/creating-skills)
- [Slash commands](/tools/slash-commands)

View File

@@ -384,3 +384,9 @@ Example:
See [BTW Side Questions](/tools/btw) for the full behavior and client UX
details.
## Related
- [Skills](/tools/skills)
- [Skills config](/tools/skills-config)
- [Creating skills](/tools/creating-skills)

View File

@@ -343,3 +343,9 @@ Sub-agents use a dedicated in-process queue lane:
- Sub-agent context only injects `AGENTS.md` + `TOOLS.md` (no `SOUL.md`, `IDENTITY.md`, `USER.md`, `HEARTBEAT.md`, or `BOOTSTRAP.md`).
- Maximum nesting depth is 5 (`maxSpawnDepth` range: 15). Depth 2 is recommended for most use cases.
- `maxChildrenPerAgent` caps active children per session (default: 5, range: 120).
## Related
- [ACP agents](/tools/acp-agents)
- [Multi-agent sandbox tools](/tools/multi-agent-sandbox-tools)
- [Agent send](/tools/agent-send)

View File

@@ -72,3 +72,9 @@ Or:
```bash
openclaw plugins disable tokenjuice
```
## Related
- [Exec tool](/tools/exec)
- [Thinking levels](/tools/thinking)
- [Context engine](/concepts/context-engine)

View File

@@ -180,3 +180,9 @@ If the command rejects the output path:
If the export fails with a size error, the session or sidecar exceeded the
export safety limits. Start a new session or export a smaller reproduction.
## Related
- [Diffs](/tools/diffs)
- [Session management](/concepts/session)
- [Exec tool](/tools/exec)

View File

@@ -520,3 +520,9 @@ Gateway methods:
- `tts.convert`
- `tts.setProvider`
- `tts.providers`
## Related
- [Media overview](/tools/media-overview)
- [Music generation](/tools/music-generation)
- [Video generation](/tools/video-generation)