Update code review effort level docs (#62760)

Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Co-authored-by: hubwriter <hubwriter@github.com>
Copilot-Session: 941f850d-f5f9-4696-afed-1bb9cde971e1

Author: 3 people

content/copilot/concepts/agents/code-review.md

@@ -107,11 +107,11 @@ You can view the {% data variables.product.prodname_actions %} minutes associate
 {% data variables.copilot.copilot_code-review_short %} supports multiple review effort levels, so you can choose the level of thoroughness that matches the criticality of your code.
 
 * **Lite**: Standard review. Provides fast, targeted feedback on common issues such as bugs, security vulnerabilities, and style inconsistencies (default).
-* **Balanced**: Routes pull requests to a higher-reasoning model for longer analysis of complex logic, security-sensitive code, and cross-service changes. Balanced reviews use more {% data variables.product.prodname_ai_credits_short %} and {% data variables.product.prodname_actions %} minutes than Lite reviews. For better performance with Balanced reviews, consider configuring larger or self-hosted runners. See [AUTOTITLE](/copilot/how-tos/copilot-on-github/set-up-copilot/configure-runners).
+* **Balanced**: Routes pull requests to a higher-reasoning model for longer analysis of complex logic, security-sensitive code, and cross-service changes. Balanced reviews use more {% data variables.product.prodname_ai_credits_short %}, and may consume marginally more {% data variables.product.prodname_actions %} minutes, than Lite reviews.
 
 Use Balanced for security-sensitive code, multi-service pull requests, or repositories with strict quality standards. Use Lite for routine changes where fast feedback is more important than exhaustive analysis.
 
-Organization owners can set a default review effort level for automatic code reviews in their organization. Repository administrators can override the organization default for a specific repository.
+You can select the review effort level when requesting a review in the pull request, under the **Reviewers** section where {% data variables.product.prodname_copilot_short %} appears as a reviewer. Organization owners can set a default review effort level for automatic code reviews in their organization. Repository administrators can override the organization default for a specific repository.
 
 After {% data variables.copilot.copilot_code-review_short %} reviews a pull request, the pull request overview comment shows the effort level used for each review run.
 
@@ -121,7 +121,7 @@ A review typically consumes an estimated $0.05 USD to $1 USD worth of {% data va
 
 Consumption generally increases with pull request size and repository custom instructions, and the ranges may change as models evolve. These estimates do not include {% data variables.product.prodname_actions %} minutes.
 
-Repository administrators can set the default review effort level for automatic code reviews. For configuration steps, see [AUTOTITLE](/copilot/how-tos/copilot-on-github/set-up-copilot/configure-automatic-review).
+Repository and organization administrators can set the default review effort level for automatic code reviews. For configuration steps, see [AUTOTITLE](/copilot/how-tos/copilot-on-github/set-up-copilot/configure-automatic-review#configuring-review-effort-level-for-an-organization).
 
 ## Code review usage
 

content/copilot/how-tos/copilot-on-github/set-up-copilot/configure-automatic-review.md

@@ -69,10 +69,10 @@ You can set the default review effort level that {% data variables.copilot.copil
 {% data reusables.profile.org_settings %}
 1. {% data reusables.user-settings.code-planning-automation %} click **{% octicon "copilot" aria-hidden="true" aria-label="copilot" %} {% data variables.product.prodname_copilot_short %}**, then **Code review**.
 1. Next to "Review effort level," select the default effort level for automatic reviews in repositories in your organization.
-   * **Lite**: Standard review (default).
+   * **Lite**: Standard review.
    * **Balanced**: Deeper analysis of complex logic, security-sensitive code, and cross-service changes.
 
-Balanced reviews use more {% data variables.product.prodname_actions %} minutes and {% data variables.product.prodname_ai_credits_short %}. If you use Balanced effort, consider configuring larger or self-hosted runners for better performance. See [AUTOTITLE](/copilot/how-tos/copilot-on-github/set-up-copilot/configure-runners).
+Balanced reviews use more {% data variables.product.prodname_ai_credits_short %}, and may consume marginally more {% data variables.product.prodname_actions %} minutes. For more information on the cost of review effort levels, see [AUTOTITLE](/copilot/concepts/agents/code-review#estimated-consumption).
 
 ## Configuring review effort level for a repository
 
@@ -82,7 +82,7 @@ You can override the organization default and set a different default review eff
 {% data reusables.repositories.sidebar-settings %}
 1. {% data reusables.user-settings.code-planning-automation %} click **{% octicon "copilot" aria-hidden="true" aria-label="copilot" %} {% data variables.product.prodname_copilot_short %}**, then **Code review**.
 1. Next to "Review effort level," select the effort level for automatic reviews in this repository.
-   * **Lite**: Standard review (default).
+   * **Lite**: Standard review.
    * **Balanced**: Deeper analysis of complex logic, security-sensitive code, and cross-service changes.
 
-Balanced reviews use more {% data variables.product.prodname_actions %} minutes and {% data variables.product.prodname_ai_credits_short %}. If you use Balanced effort, consider configuring larger or self-hosted runners for better performance. See [AUTOTITLE](/copilot/how-tos/copilot-on-github/set-up-copilot/configure-runners).
+Balanced reviews use more {% data variables.product.prodname_ai_credits_short %}, and may consume marginally more {% data variables.product.prodname_actions %} minutes. For more information on the cost of review effort levels, see [AUTOTITLE](/copilot/concepts/agents/code-review#estimated-consumption).

content/copilot/how-tos/use-copilot-agents/request-a-code-review/use-code-review.md

@@ -57,6 +57,17 @@ You can also request a review from {% data variables.product.prodname_copilot_sh
 
 By default, you manually request a review from {% data variables.product.prodname_copilot_short %} on each pull request, in the same way you would request a review from a human. However, you can set up {% data variables.product.prodname_copilot_short %} to automatically review all pull requests. See [AUTOTITLE](/copilot/how-tos/copilot-on-github/set-up-copilot/configure-automatic-review).
 
+## Choosing a review effort level
+
+{% data variables.copilot.copilot_code-review_short %} supports multiple review effort levels, so you can choose the level of thoroughness that matches the criticality of your code.
+
+* **Lite**: Standard review that provides fast, targeted feedback on common issues such as bugs, security vulnerabilities, and style inconsistencies (default).
+* **Balanced**: Deeper analysis of complex logic, security-sensitive code, and cross-service changes, using a higher-reasoning model.
+
+You can select the review effort level in the pull request, under the **Reviewers** section where {% data variables.product.prodname_copilot_short %} appears as a reviewer. Organization owners and repository administrators can also set a default effort level for automatic reviews.
+
+For more information, see [AUTOTITLE](/copilot/concepts/agents/code-review#review-effort-level).
+
 ## Working with suggested changes provided by {% data variables.product.prodname_copilot_short %}
 
 Where possible, {% data variables.product.prodname_copilot_short %}'s feedback includes suggested changes which you can apply with a couple of clicks.