Copilot CLI Week of Jan 21 Updates (#59295)

Co-authored-by: Sunbrye Ly <56200261+sunbrye@users.noreply.github.com>

Author: steveward

content/copilot/concepts/agents/about-copilot-cli.md

@@ -31,13 +31,15 @@ For installation instructions, see [AUTOTITLE](/copilot/how-tos/set-up/install-c
 
 ## Modes of use
 
-{% data variables.copilot.copilot_cli %} can be used in two modes:
+{% data variables.copilot.copilot_cli %} can be used in three modes:
 * **Interactive mode**: Start an interactive session by using the `copilot` command. This is the default mode for working with the CLI.
 
   In this mode, you can prompt {% data variables.product.prodname_copilot_short %} to answer a question, or perform a task. You can react to {% data variables.product.prodname_copilot_short %}'s responses in the same session.
 
   ![Screenshot of the Welcome message in the interactive mode of {% data variables.product.prodname_copilot_short %}.](/assets/images/help/copilot/copilot-cli-welcome.png)
 
+* **Plan mode**: Press <kbd>Shift</kbd>+<kbd>Tab</kbd> to cycle in and out of plan mode. In plan mode, {% data variables.product.prodname_copilot_short %} analyzes your request, asks clarifying questions to understand scope and requirements, and builds a structured implementation plan before writing any code. This helps you catch misunderstandings before any code is written, and stay in control of complex, multi-step tasks.
+
 * **Programmatic mode**: You can also pass the CLI a single prompt directly on the command line. You do this by using the `-p` or `--prompt` command-line option. To allow {% data variables.product.prodname_copilot_short %} to modify and execute files you should also use one of the approval options (see [Allowing tools to be used without manual approval](#allowing-tools-to-be-used-without-manual-approval) later in this article). For example:
 
   ```bash copy
@@ -142,16 +144,31 @@ The following sections provide examples of tasks you can complete with {% data v
 
   `Branch off from main and create a {% data variables.product.prodname_actions %} workflow that will run on pull requests, or can be run manually. The workflow should run eslint to check for problems in the changes made in the PR. If warnings or errors are found these should be shown as messages in the diff view of the PR. I want to prevent code with errors from being merged into main so, if any errors are found, the workflow should cause the PR check to fail. Push the new branch and create a pull request.`
 
+## Steering the conversation
+
+You can interact with {% data variables.product.prodname_copilot_short %} while it's thinking to steer the conversation:
+
+* **Enqueue additional messages**: Send follow-up messages to steer the conversation in a different direction, or queue additional instructions for {% data variables.product.prodname_copilot_short %} to process after it finishes its current response. This makes conversations feel more natural and keeps you in control.
+* **Inline feedback on rejection**: When you reject a tool permission request, you can give {% data variables.product.prodname_copilot_short %} inline feedback about the rejection so it can adapt its approach without stopping entirely. This makes the conversation flow more naturally when you want to guide {% data variables.product.prodname_copilot_short %} away from certain actions.
+
+## Automatic context management
+
+{% data variables.copilot.copilot_cli %} automatically manages your conversation context:
+
+* **Auto-compaction**: When your conversation approaches 95% of the token limit, {% data variables.product.prodname_copilot_short %} automatically compresses your history in the background without interrupting your workflow. This enables virtually infinite sessions.
+* **Manual control**: Use `/compact` to manually compress context anytime. Press <kbd>Escape</kbd> to cancel if you change your mind.
+* **Visualize usage**: The `/context` command shows a detailed token usage breakdown so you can understand how your context window is being used.
+
 ## Customizing {% data variables.copilot.copilot_cli %}
 
 You can customize {% data variables.copilot.copilot_cli %} in a number of ways:
 
-* **Custom instructions**: Custom instructions allow you to give {% data variables.product.prodname_copilot_short %} additional context on your project and how to build, test and validate its changes. For more information, see [AUTOTITLE](/copilot/how-tos/use-copilot-agents/use-copilot-cli#use-custom-instructions).
+* **Custom instructions**: Custom instructions allow you to give {% data variables.product.prodname_copilot_short %} additional context on your project and how to build, test and validate its changes. All custom instruction files now combine instead of using priority-based fallbacks. For more information, see [AUTOTITLE](/copilot/how-tos/use-copilot-agents/use-copilot-cli#use-custom-instructions).
 * **Model Context Protocol (MCP) servers**: MCP servers allow you to give {% data variables.product.prodname_copilot_short %} access to different data sources and tools. For more information, see [AUTOTITLE](/copilot/how-tos/use-copilot-agents/use-copilot-cli#add-an-mcp-server).
 * **{% data variables.copilot.custom_agents_caps_short %}**: {% data variables.copilot.custom_agents_caps_short %} allow you to create different specialized versions of {% data variables.product.prodname_copilot_short %} for different tasks. For example, you could customize {% data variables.product.prodname_copilot_short %} to be an expert frontend engineer following your team's guidelines. {% data variables.copilot.copilot_cli %} includes specialized {% data variables.copilot.custom_agents_short %} that it automatically delegates common tasks to. For more information, see [AUTOTITLE](/copilot/how-tos/use-copilot-agents/use-copilot-cli#use-custom-agents).
 * **Hooks**: Hooks allow you to execute custom shell commands at key points during agent execution, enabling you to add validation, logging, security scanning, or workflow automation. See [AUTOTITLE](/copilot/concepts/agents/coding-agent/about-hooks).
 * **Skills**: Skills allow you to enhance the ability of {% data variables.product.prodname_copilot_short %} to perform specialized tasks with instructions, scripts, and resources. For more information, see [AUTOTITLE](/copilot/concepts/agents/about-agent-skills).
-
+* **{% data variables.copilot.copilot_memory %}**: {% data variables.copilot.copilot_memory %} allows {% data variables.product.prodname_copilot_short %} to build a persistent understanding of your repository by storing "memories", which are pieces of information about coding conventions, patterns, and preferences that {% data variables.product.prodname_copilot_short %} deduces as it works. This reduces the need to repeatedly explain context in your prompts and makes future sessions more productive. For more information, see [AUTOTITLE](/copilot/concepts/agents/copilot-memory).
 
 ## Security considerations
 
@@ -276,9 +293,9 @@ You can mitigate the risks associated with using the automatic approval options
 
 The default model used by {% data variables.copilot.copilot_cli %} is {% data variables.copilot.copilot_claude_sonnet_45 %}. {% data variables.product.github %} reserves the right to change this model.
 
-You can change the model used by {% data variables.copilot.copilot_cli %} by using the `/model` slash command. Enter this command, then select a model from the list.
+You can change the model used by {% data variables.copilot.copilot_cli %} by using the `/model` slash command or the `--model` command-line option. Enter this command, then select a model from the list.
 
-Each time you submit a prompt to {% data variables.product.prodname_copilot_short %} in {% data variables.copilot.copilot_cli_short %}'s interactive mode, and each time you use {% data variables.copilot.copilot_cli_short %} in programmatic mode, your monthly quota of {% data variables.product.prodname_copilot_short %} premium requests is reduced by one, multiplied by the multiplier shown in parentheses in the model list. For example, `Claude Sonnet 4.5 (1x)` indicates that with this model each time you submit a prompt your quota of premium requests is reduced by one. For information about premium requests, see [AUTOTITLE](/copilot/managing-copilot/monitoring-usage-and-entitlements/about-premium-requests).
+Each time you submit a prompt to {% data variables.product.prodname_copilot_short %} in {% data variables.copilot.copilot_cli_short %}'s interactive mode, and each time you use {% data variables.copilot.copilot_cli_short %} in programmatic mode, your monthly quota of {% data variables.product.prodname_copilot_short %} premium requests is reduced by one, multiplied by the multiplier shown in parentheses in the model list. For example, `Claude Sonnet 4.5 (1x)` indicates that with this model each time you submit a prompt your quota of premium requests is reduced by one. For information about premium requests, see [AUTOTITLE](/copilot/concepts/billing/copilot-requests).
 
 {% data reusables.cli.feedback %}
 

content/copilot/how-tos/use-copilot-agents/use-copilot-cli.md

@@ -64,16 +64,18 @@ Install {% data variables.copilot.copilot_cli_short %}. See [AUTOTITLE](/copilot
 
    **2. Yes, and approve TOOL for the rest of the running session**:
 
-   Allow {% data variables.product.prodname_copilot_short %} to use this tool—with any options—without asking again, for the rest of the currently running session. You will have to approve the command again in future sessions.
+   Allow {% data variables.product.prodname_copilot_short %} to use this tool—with any options—without asking again, for the rest of the currently running session. Any pending parallel permission requests of the same type will be auto-approved. You will have to approve the command again in future sessions.
 
-   Choosing this option is useful for a many tools—such as `chmod`—as it avoids you having to approve similar commands repeatedly in the same session. However, you should be aware of the security implications of this option. Choosing this option for the command `rm`, for example, would allow {% data variables.product.prodname_copilot_short %} to delete any file in or below the current folder without asking for your approval.
+   Choosing this option is useful for many tools—such as `chmod`—as it avoids you having to approve similar commands repeatedly in the same session. However, be aware of the security implications of this option. For example, choosing this option for the command `rm` would allow {% data variables.product.prodname_copilot_short %} to delete any file in the current directory or its subdirectories without asking for your approval.
 
    **3. No, and tell Copilot what to do differently (Esc)**:
 
    {% data variables.product.prodname_copilot_short %} will not run the command. Instead, it ends the current operation and awaits your next prompt. You can tell {% data variables.product.prodname_copilot_short %} to continue the task but using a different approach.
 
    For example, if you ask {% data variables.product.prodname_copilot_short %} to create a bash script but you do not want to use the script {% data variables.product.prodname_copilot_short %} suggests, you can stop the current operation and enter a new prompt, such as: `Continue the previous task but include usage instructions in the script`.
 
+   When you reject a tool permission request, you can also give {% data variables.product.prodname_copilot_short %} inline feedback about the rejection so it can adapt its approach without stopping entirely.
+
 ## Permissions
 
 {% data variables.copilot.copilot_cli_short %} uses a permissions system to control access to paths and URLs. At times, path and URL permission checks utilize heuristic-based detection, which has limitations to be aware of.
@@ -116,6 +118,14 @@ Optimize your experience with {% data variables.copilot.copilot_cli_short %} wit
 
 If you enter a prompt and then decide you want to stop {% data variables.product.prodname_copilot_short %} from completing the task while it is still "Thinking," press <kbd>Esc</kbd>.
 
+### Use plan mode
+
+Plan mode lets you collaborate with {% data variables.product.prodname_copilot_short %} on an implementation plan before any code is written. Press <kbd>Shift</kbd>+<kbd>Tab</kbd> to cycle in and out of plan mode.
+
+### Steer the conversation while {% data variables.product.prodname_copilot_short %} is thinking
+
+You can interact with {% data variables.product.prodname_copilot_short %} while it's thinking. Send follow-up messages to steer the conversation in a different direction, or queue additional instructions for {% data variables.product.prodname_copilot_short %} to process after it finishes its current response. 
+
 ### Include a specific file in your prompt
 
 To add a specific file to your prompt, use `@` followed by the relative path to the file. For example: `Explain @config/ci/ci-required-checks.yml` or `Fix the bug in @src/app.js`. This adds the contents of the file to your prompt as context for {% data variables.product.prodname_copilot_short %}.
@@ -132,7 +142,7 @@ You can also add a trusted directory manually at any time by using the slash com
 /add-dir /path/to/directory
 ```
 
-If all of the files you want to work with are in a different location, you can switch the current working directory without starting a new {% data variables.copilot.copilot_cli_short %} session by using the slash command:
+If all of the files you want to work with are in a different location, you can switch the current working directory without starting a new {% data variables.copilot.copilot_cli_short %} session by using either the `/cwd` or `/cd` slash commands:
 
 ```shell
 /cwd /path/to/directory
@@ -156,13 +166,19 @@ You can delegate a task using the slash command, followed by a prompt:
 /delegate complete the API integration tests and fix any failing edge cases
 ```
 
+Alternatively, prefix a prompt with `&` to delegate it:
+
+```shell
+& complete the API integration tests and fix any failing edge cases
+```
+
 {% data variables.product.prodname_copilot_short %} will ask to commit any of your unstaged changes as a checkpoint in a new branch it creates. {% data variables.copilot.copilot_coding_agent %} will open a draft pull request, make changes in the background, and request a review from you.
 
 {% data variables.product.prodname_copilot_short %} will provide a link to the pull request and agent session on {% data variables.product.github %} once the session begins.
 
 ### Resume an interactive session
 
-You can use the `--resume` command line option to cycle through and resume local and remote interactive sessions, allowing you to pick up right where you left off with your existing context. You can kick off a {% data variables.copilot.copilot_coding_agent %} session on {% data variables.product.github %}, and then use {% data variables.copilot.copilot_cli %} to bring that session to your local environment.
+You can use the `--resume` command line option or the `/resume` slash command to cycle through and resume local and remote interactive sessions, allowing you to pick up right where you left off with your existing context. You can kick off a {% data variables.copilot.copilot_coding_agent %} session on {% data variables.product.github %}, and then use {% data variables.copilot.copilot_cli %} to bring that session to your local environment.
 
 You can quickly resume the most recently closed local session by using the `--continue` command line option.
 
@@ -261,7 +277,19 @@ Details of your configured MCP servers are stored in the `mcp-config.json` file,
 * `/context`: Provides a visual overview of your current token usage
 * `/compact`: Manually compresses your conversation history to free up context space
 
-{% data variables.copilot.copilot_cli %} automatically compresses your history when approaching 95% of the token limit. When you have less than 20% of a model's token limit remaining, a warning will be displayed indicating the context will be truncated when the limit is reached.
+{% data variables.copilot.copilot_cli %} automatically compresses your history in the background when your conversation approaches 95% of the token limit, without interrupting your workflow. 
+
+### Review code changes
+
+You can use the `/review` slash command to have {% data variables.product.prodname_copilot_short %} analyze code changes without leaving the CLI. This lets you get quick feedback on your changes prior to committing.
+
+### Enable all permissions
+
+For situations where you trust {% data variables.product.prodname_copilot_short %} to run freely, you can use the `--allow-all` or `--yolo` flags to enable all permissions at once.
+
+### Toggle reasoning visibility
+
+Press <kbd>Ctrl</kbd>+<kbd>T</kbd> to show or hide the model's reasoning process while it generates a response. This setting persists across sessions, allowing you to observe how {% data variables.product.prodname_copilot_short %} works through complex problems.
 
 ## Find out more