Update Learning Hub for Copilot CLI v1.0.71-v1.0.72 features

- copilot-configuration-basics.md: Split /worktree and /move into separate
  commands with distinct behaviors (worktree leaves changes, move carries them);
  document plan mode workspace-modification hard-block (v1.0.71+)
- agents-and-subagents.md: Document multi-turn subagents always enabled (v1.0.72);
  note default max subagent depth lowered from 6 to 4 (v1.0.71)
- working-with-canvas-extensions.md: Document canvas support in CLI (v1.0.71)

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

website/src/content/docs/learning-hub/agents-and-subagents.md

@@ -3,7 +3,7 @@ title: 'Agents and Subagents'
 description: 'Learn how delegated subagents differ from primary agents, when to use them, and how to launch them in VS Code and Copilot CLI.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-01
+lastUpdated: 2026-07-18
 estimatedReadingTime: '9 minutes'
 tags:
   - agents
@@ -210,7 +210,11 @@ No. They can run sequentially when one step depends on another, or in parallel w
 
 **Can I control how many subagents run simultaneously?**
 
-Yes. In v1.0.66+, usage-based billing users can configure **subagent concurrency and depth limits** directly from `/settings`. The concurrency limit controls how many subagents run in parallel; the depth limit controls how many levels deep delegation can chain (preventing runaway recursive subagent trees). These settings give you predictable control over resource consumption during complex orchestrated tasks.
+Yes. In v1.0.66+, usage-based billing users can configure **subagent concurrency and depth limits** directly from `/settings`. The concurrency limit controls how many subagents run in parallel; the depth limit controls how many levels deep delegation can chain (preventing runaway recursive subagent trees). As of v1.0.71, the default maximum nesting depth was lowered from 6 to 4 — usage-based billing users can still raise it up to 128 via `subagents.maxDepth`. These settings give you predictable control over resource consumption during complex orchestrated tasks.
+
+**Can I send follow-up messages to a running subagent?**
+
+Yes, as of v1.0.72 **multi-turn subagents are always enabled**. You can send follow-up messages to a subagent that is still running — for example to correct its course, provide missing context, or ask for an intermediate status — without waiting for it to finish. This makes subagents genuinely interactive rather than fire-and-forget.
 
 ## Next steps
 

website/src/content/docs/learning-hub/copilot-configuration-basics.md

@@ -3,7 +3,7 @@ title: 'Copilot Configuration Basics'
 description: 'Learn how to configure GitHub Copilot at user, workspace, and repository levels to optimize your AI-assisted development experience.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-07-13
+lastUpdated: 2026-07-18
 estimatedReadingTime: '10 minutes'
 tags:
   - configuration
@@ -541,7 +541,7 @@ The `/cd` command changes the working directory for the current session. Since v
 
 This is useful when you have multiple backgrounded sessions each focused on a different project directory.
 
-The `/worktree` command (v1.0.61+, also aliased `/move`) creates a new git worktree and switches into it, moving any uncommitted changes along. This lets you start working on a parallel branch without leaving your current terminal session:
+The `/worktree` command (v1.0.61+) creates a new git worktree and switches into it, **leaving your uncommitted changes in the current branch**. Use this when you want a clean slate in the new worktree and intend to stash or discard your in-progress changes separately:
 
 ```
 /worktree my-feature-branch
@@ -555,7 +555,15 @@ In v1.0.66+, you can pass a task description to `/worktree` to name the branch f
 
 This creates a branch named from your task description and begins working on it immediately, making it easy to spin up parallel work without stopping to think of a branch name.
 
-After the command runs, the session is inside the new worktree. Use this when you want to work on a second task in parallel without stashing changes or opening a new terminal. In v1.0.64+ you can also use the experimental `--worktree` flag at startup (`copilot -w [name]`) to create or reuse a worktree under `<repo>.worktrees/` before the session begins.
+The `/move` command (v1.0.71+) is the companion to `/worktree` and **carries your uncommitted changes into the new worktree**. Use `/move` when you have in-progress work that you want to continue on a new branch:
+
+```
+/move my-feature-branch
+```
+
+Before v1.0.71, `/move` was an alias for `/worktree` and always moved uncommitted changes. The split gives you deliberate control: `/worktree` to leave changes behind, `/move` to take them with you.
+
+After either command runs, the session is inside the new worktree. Use these when you want to work on a second task in parallel without opening a new terminal. In v1.0.64+ you can also use the experimental `--worktree` flag at startup (`copilot -w [name]`) to create or reuse a worktree under `<repo>.worktrees/` before the session begins.
 
 The `/every` command (also available as `/loop` since v1.0.64) schedules a recurring prompt to run automatically at a specified interval. The companion `/after` command runs a prompt once after a specified delay. Both are useful for self-paced automation — polling for results, periodically summarizing progress, or triggering other slash commands on a timer:
 
@@ -744,6 +752,8 @@ copilot --plan          # start in plan mode (propose without executing)
 
 This is useful in scripts or CI pipelines where you want the CLI to immediately begin working in a specific mode without an interactive prompt.
 
+> **Plan mode workspace protection (v1.0.71+)**: Plan mode now **hard-blocks built-in tool calls that would modify the workspace**, so the agent cannot edit files or run mutating shell commands while planning. Built-in mutators like opening a pull request are also blocked; MCP and external tools remain allowed. This ensures plan output is a safe, non-destructive proposal you can review before switching to agent mode.
+
 The `--max-autopilot-continues` flag controls how many times Copilot can automatically continue in autopilot mode before pausing for confirmation. The default is 5:
 
 ```bash

website/src/content/docs/learning-hub/working-with-canvas-extensions.md

@@ -3,7 +3,7 @@ title: 'Working with Canvas Extensions'
 description: 'Create and iterate on GitHub Copilot app canvases using /create-canvas, then shape them into reusable project or personal extensions.'
 authors:
   - GitHub Copilot Learning Hub Team
-lastUpdated: 2026-06-17
+lastUpdated: 2026-07-18
 estimatedReadingTime: '8 minutes'
 tags:
   - copilot-app
@@ -18,10 +18,14 @@ prerequisites:
   - Basic familiarity with GitHub Copilot agent sessions
 ---
 
-Canvas extensions give you shared, interactive work surfaces inside the GitHub Copilot app. Instead of keeping all progress in chat, you can move work into a visible artifact (such as a board, document, checklist, or browser-oriented surface) that both people and agents can update.
+Canvas extensions give you shared, interactive work surfaces inside the GitHub Copilot app and, as of v1.0.71, also in the **GitHub Copilot CLI**. Instead of keeping all progress in chat, you can move work into a visible artifact (such as a board, document, checklist, or browser-oriented surface) that both people and agents can update.
 
 This guide explains what canvases can do, how to create one with `/create-canvas`, and how to use patterns from this repository as reference implementations.
 
+## Canvas support: Copilot app and CLI
+
+Canvases were originally a Copilot app feature. Since v1.0.71, the CLI supports canvas extensions for extension-driven interactions, so the same extension files work across both surfaces. The creation and iteration workflow described below applies to both the Copilot app and the CLI.
+
 ## What canvases can do
 
 A canvas is a bidirectional surface: