Update Learning Hub for Copilot CLI v1.0.76-v1.0.78 features

- Add /permissions command for switching approval modes
- Document autopilot stayInAutopilot setting
- Add /limits predict for AI credit estimation
- Add experimental Sessions sidebar for multi-session CLI management
- Document enterprise managed sandbox policy enforcement
- Add allowDevToolCaches sandbox setting
- Document /plugins enable/disable controls for plugin components

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

website/src/content/docs/learning-hub/installing-and-using-plugins.md

@@ -3,7 +3,7 @@ title: 'Installing and Using Plugins'
 description: 'Learn how to find, install, and manage plugins that extend GitHub Copilot CLI with reusable agents, skills, hooks, and integrations.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-28
+lastUpdated: 2026-08-01
 estimatedReadingTime: '8 minutes'
 tags:
   - plugins
@@ -248,6 +248,18 @@ When you install a plugin, its components become available to Copilot CLI automa
 
 You don't need to do any additional configuration after installing — the plugin's components integrate seamlessly into your workflow. Plugins take effect immediately after installation without requiring a Copilot CLI restart.
 
+### Enabling and Disabling Plugin Components
+
+You can enable or disable individual components of an installed plugin without uninstalling it. Open the `/plugins` panel in an interactive Copilot CLI session to see all installed plugins and toggle their agents, instructions, skills, LSP servers, and hooks independently:
+
+```
+/plugins
+```
+
+This is useful when you want to temporarily disable a hook or agent from a plugin without removing the entire plugin, or when debugging which plugin component is affecting your session.
+
+> **Tip**: Changes made in `/plugins` take effect immediately in the current session and are remembered for future sessions.
+
 ## Plugins from This Repository
 
 This repository (`awesome-copilot`) serves as both a collection of individual resources _and_ a plugin marketplace. You can use it in two ways:

website/src/content/docs/learning-hub/using-copilot-coding-agent.md

@@ -3,7 +3,7 @@ title: 'Using the Copilot Coding Agent'
 description: 'Learn how to use GitHub Copilot coding agent to autonomously work on issues, generate pull requests, and automate development tasks.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-05-13
+lastUpdated: 2026-08-01
 estimatedReadingTime: '12 minutes'
 tags:
   - coding-agent
@@ -334,6 +334,36 @@ This repository provides a curated collection of agents, skills, and hooks desig
 
 > **Example workflow**: Combine a `test-specialist` agent with a `database-migrations` skill and a linting hook. Assign an issue to the coding agent using the test-specialist agent — it will automatically pick up the migrations skill when relevant, and the hook ensures all code is formatted before completion.
 
+## Controlling Approval Modes
+
+By default, Copilot CLI asks for your approval before executing tools like shell commands and file writes. You can change this behavior with the `/permissions` command:
+
+```
+/permissions
+```
+
+This opens a dialog where you can switch between approval modes:
+
+| Mode | Behavior |
+|------|----------|
+| **Interactive** | Asks for approval before each sensitive action (default) |
+| **Autopilot** | Executes actions autonomously without per-action prompts |
+| **Plan** | Produces a plan for your review before taking any actions |
+
+Switching to **autopilot** mode lets the agent work without interruption — useful for well-defined tasks where you trust the agent's judgment. Autopilot mode now stays active after a task completes; if you prefer to return to interactive mode after each task, set `stayInAutopilot: false` in your Copilot settings.
+
+> **Note**: When unconditional autopilot approval is enabled and sandbox bypass is allowed, the sandbox is disabled for the current session.
+
+### Estimating AI Credit Usage
+
+Before running a long task, you can ask Copilot to predict how many AI credits the session might consume based on similar past sessions:
+
+```
+/limits predict
+```
+
+This helps avoid unexpected credit exhaustion on long autonomous tasks.
+
 ## Remote Control
 
 You can connect to and steer a running coding agent session from a local Copilot CLI terminal using **remote control**. This lets you observe the agent's progress, send follow-up prompts, and redirect its work in real time — without waiting for it to open a PR first.
@@ -377,6 +407,16 @@ Since v1.0.47, `--resume` also surfaces **cloud agent sessions that haven't yet
 
 > **Note**: Remote control replaces the earlier "steering" feature. If you see references to steering in older documentation, remote control is the updated equivalent.
 
+### Managing Multiple Concurrent Sessions (Experimental)
+
+If you regularly run several coding agent tasks in parallel from the CLI, you can enable the **Sessions sidebar** to manage them all from one terminal window:
+
+```
+/experimental on
+```
+
+Once enabled, the sidebar lets you switch between active sessions, spawn new ones, and see each session's status at a glance — without opening separate terminal windows. This is an experimental feature and the interface may change in future releases.
+
 ## Hooks and the Coding Agent
 
 Hooks are especially valuable with the coding agent because they provide deterministic guardrails for autonomous work:
@@ -422,6 +462,28 @@ It's less suited for:
 - Use hooks to enforce security scanning on every commit
 - Scope repository permissions appropriately
 
+#### Enterprise Sandbox Enforcement
+
+Enterprise administrators can enforce a **managed sandbox policy** using macOS and Windows native MDM (Mobile Device Management) settings. When a managed policy is in effect:
+
+- The managed settings **tighten** (but never loosen) the user's sandbox policy
+- The `/sandbox` dialog shows the org-configured managed values with locked fields
+- Managed filesystem paths are clearly identified as admin-controlled
+
+This lets organizations ensure that all Copilot CLI sessions on managed machines operate within approved sandbox boundaries, regardless of individual user settings.
+
+#### Sandbox Toolchain Cache Access
+
+The `allowDevToolCaches` sandbox setting (on by default) grants sandboxed builds access to toolchain caches, package manager registries, and local installs — so builds work without extra configuration in most cases. Set it to `false` in your Copilot settings to opt out if you need stricter isolation:
+
+```json
+{
+  "sandbox": {
+    "allowDevToolCaches": false
+  }
+}
+```
+
 ## Common Questions
 
 **Q: How long does the coding agent take?**