[pull] main from github:main

content/admin/monitoring-activity-in-your-enterprise/reviewing-audit-logs-for-your-enterprise/streaming-the-audit-log-for-your-enterprise.md

@@ -79,7 +79,11 @@ You can stream audit logs to multiple endpoints. For example, you can stream you
 
 {% ifversion ghes %}
 
->[!NOTE] The Amazon region `us-east-1` must be reachable from your appliance for streaming to S3 to work. Your S3 bucket can reside in other AWS regions.
+> [!NOTE]
+> For streaming to S3, the AWS region that must be reachable depends on the option you select for the bucket's region.
+>
+> * If you select **Auto Detect**, `us-east-1` must be reachable from your appliance because the AWS SDK uses that region to detect the destination bucket's region.
+> * If you select a specific region, the selected region must be reachable from your appliance. `us-east-1` does not need to be reachable unless it is the selected region.
 
 {% endif %}
 
@@ -113,10 +117,10 @@ From {% data variables.product.prodname_dotcom %}:
 1. Under "Authentication", click **Access keys**.{% endif %}
 1. Configure the stream settings.
 
-    - Under "Region", select the bucket's region. For example, `us-east-1`.
-    - Under "Bucket", type the name of the bucket you want to stream to. For example, `auditlog-streaming-test`.
-    - Under "Access Key ID", type your access key ID. For example, `ABCAIOSFODNN7EXAMPLE1`.
-    - Under "Secret Key", type your secret key. For example, `aBcJalrXUtnWXYZ/A1MDENG/zPxRfiCYEXAMPLEKEY`.
+    * Under "Region", select **Auto Detect** or select the bucket's region. For example, `us-east-1`.
+    * Under "Bucket", type the name of the bucket you want to stream to. For example, `auditlog-streaming-test`.
+    * Under "Access Key ID", type your access key ID. For example, `ABCAIOSFODNN7EXAMPLE1`.
+    * Under "Secret Key", type your secret key. For example, `aBcJalrXUtnWXYZ/A1MDENG/zPxRfiCYEXAMPLEKEY`.
 {% data reusables.audit_log.streaming-check-s3-endpoint %}
 {% data reusables.enterprise.verify-audit-log-streaming-endpoint %}
 

content/copilot/concepts/agents/about-github-agentic-workflows.md

@@ -0,0 +1,157 @@
+---
+title: About GitHub Agentic Workflows
+shortTitle: Agentic Workflows
+intro: 'Automate repetitive repository work with natural language instructions executed by AI coding agents in {% data variables.product.prodname_actions %}.'
+versions:
+  feature: copilot
+contentType: concepts
+category:
+  - Learn about Copilot
+---
+
+{% data reusables.copilot.agentic-workflows-preview-note %}
+
+## About {% data variables.copilot.agentic_workflows_short %}
+
+{% data variables.copilot.github_agentic_workflows %} are AI-powered repository automations that you define in markdown and run as {% data variables.product.prodname_actions %} workflows. Unlike traditional automation with fixed if-then rules, {% data variables.copilot.agentic_workflows_short %} use coding agents to understand context, make decisions, and take meaningful actions—all from natural language instructions.
+
+In practice, compared with traditional workflows that execute predefined steps:
+
+* {% data variables.copilot.agentic_workflows_short_cap %} execute natural language instructions with contextual reasoning.
+* You still define guardrails in frontmatter, such as triggers, permissions, and safe outputs.
+
+With {% data variables.copilot.agentic_workflows_short %}, you can automate tasks like:
+
+* Triaging incoming issues and labeling them by type and priority
+* Investigating CI failures and suggesting fixes
+* Generating daily or weekly repository status reports
+* Keeping documentation up to date with code changes
+* Improving test coverage
+
+## Benefits of using {% data variables.copilot.agentic_workflows_short %}
+
+* **Automate repetitive repository work**. Define issue triage, CI investigation, documentation updates, and reporting in natural language.
+* **Reduce workflow complexity**. Write markdown instructions instead of building complex procedural scripts for every scenario.
+* **Keep human review in the loop**. {% data variables.copilot.agentic_workflows_short_cap %} can generate ready-to-review outputs, such as issues, comments, and pull requests, while you control approvals and merges.
+* **Run agents with layered security**. Agents run in firewalled containers with read-only tokens by default. Write actions are limited to declared "safe outputs" that you have defined, and checked by agentic threat detection.
+
+## Requirements
+
+To create and use {% data variables.copilot.agentic_workflows_short %}, you need:
+
+* {% data variables.product.prodname_actions %} enabled for your repository.
+* An account with an AI engine (agent), such as {% data variables.product.prodname_copilot %}, {% data variables.product.prodname_anthropic_claude %}, {% data variables.product.prodname_openai_codex %}, or Google Gemini.
+* {% data variables.product.prodname_cli %} installed and authenticated
+
+## How {% data variables.copilot.agentic_workflows_short %} work
+
+Each workflow markdown file has two parts:
+
+* **Frontmatter** (YAML between `---` markers): Configures when the workflow runs, what permissions it has, and what write operations are allowed.
+* **Markdown body**: Contains your natural language instructions that the AI agent follows.
+
+At a high level, the process to create and use {% data variables.copilot.agentic_workflows_short %} is:
+
+1. Define the agentic workflow `.md` file, including YAML frontmatter and markdown instructions.
+1. Compile the markdown workflow file into a hardened `.lock.yml` {% data variables.product.prodname_actions %} workflow file.
+1. Commit and push both files to the default branch of your repository.
+1. Run the workflow like any other {% data variables.product.prodname_actions %} workflow, on a trigger or in the {% data variables.product.github %} web interface for your repository. You can also run it from the {% data variables.product.prodname_cli %}.
+
+Here's an example of a workflow to create a daily status report issue for a repository:
+
+```markdown
+---
+on: daily
+
+permissions:
+  contents: read
+  issues: read
+  pull-requests: read
+  copilot-requests: write
+
+network: defaults
+
+tools:
+  github:
+    toolsets: [default]
+
+safe-outputs:
+  create-issue:
+
+---
+
+# Daily Repo Status Report
+
+Review recent activity in the repository, including issues, pull requests, discussions, and code changes.
+
+Create a {% data variables.product.github %} issue summarizing what changed in the last 24 hours (merged pull requests, closed issues, and new discussions), any blockers or open questions mentioned in comments, progress toward visible goals, and recommended next steps for maintainers.
+
+Keep the summary concise. Adjust the level of detail based on how much activity occurred.
+```
+
+For detailed steps on creating and updating {% data variables.copilot.agentic_workflows_short %}, see [AUTOTITLE](/copilot/how-tos/github-agentic-workflows/creating-github-agentic-workflows).
+
+## Supported coding agents
+
+{% data variables.copilot.github_agentic_workflows %} support multiple coding agents, including:
+
+* {% data variables.product.prodname_copilot %} (requires a {% data variables.product.prodname_copilot %} plan)
+* {% data variables.product.prodname_anthropic_claude %}
+* {% data variables.product.prodname_openai_codex %}
+* Google Gemini
+
+You specify which agent to use in the workflow frontmatter property `engine`. Each engine requires its own authentication secret configured in your repository. {% data variables.product.prodname_copilot %} is the default engine if none is specified.
+
+For more information, see the [engine reference](https://github.github.com/gh-aw/reference/engines/).
+
+## Security guardrails
+
+{% data variables.copilot.github_agentic_workflows %} are designed with security as a priority:
+
+* **Read-only by default**: Workflows have read-only repository permissions unless you explicitly grant more.
+* **Safe outputs**: Write operations (such as creating issues, adding comments, or opening pull requests) are only allowed through validated `safe-outputs` declared in the frontmatter.
+* **Secrets stay outside the agent runtime**: Sensitive credentials are kept in isolated downstream jobs instead of being exposed directly to the agent.
+* **Threat detection**: Proposed outputs are scanned for suspicious or unsafe changes before write actions are applied.
+* **Firewalled execution**: Agents run in isolated {% data variables.product.prodname_actions %} environments.
+* **Role-based access**: You can restrict who can trigger or modify {% data variables.copilot.agentic_workflows_short %} using role-based access controls.
+
+For a full architecture walkthrough, see the [security documentation](https://github.github.com/gh-aw/introduction/architecture/).
+
+## Usage and billing
+
+The total cost of {% data variables.copilot.agentic_workflows_short %} has two parts:
+
+* {% data variables.product.prodname_actions %} minutes consumed by workflow jobs.
+* Inference costs from the configured AI engine.
+
+For inference, {% data variables.copilot.github_agentic_workflows %} use AI Credits (AIC) as a general metric for monitoring and budgeting across engines. `1 AIC = $0.01 USD`.
+
+How billing applies depends on the engine:
+
+* Default {% data variables.product.prodname_copilot %} engine: AIC usage maps to {% data variables.product.prodname_ai_credits_short %} in {% data variables.product.prodname_copilot %} billing.
+* Third-party engine: Inference is billed by that provider.
+
+You can use the {% data variables.product.prodname_cli %} to review usage and estimated cost for {% data variables.copilot.agentic_workflows_short %}. Use `gh aw logs` to view recent workflow runs, including duration, token usage, and AIC estimates across runs. Use `gh aw audit RUN-ID` to inspect a single run in more detail, including token usage and estimated inference cost. AIC values are best-effort estimates and may not exactly match provider invoices, so verify final charges in your provider's billing dashboard.
+
+You can also set `max-ai-credits` in workflow frontmatter to cap inference usage for a single run. The default cap is 1,000 AIC per run.
+
+For an overview of billing for {% data variables.copilot.github_agentic_workflows %} and cost optimization guidance, see [Cost management](https://github.github.com/gh-aw/reference/cost-management/) on the {% data variables.copilot.github_agentic_workflows %} documentation site.
+
+### Enabling organization billing for {% data variables.copilot.github_agentic_workflows %}
+
+For {% data variables.product.prodname_copilot %} agentic workflows in organization-owned repositories, if the organization has a {% data variables.product.prodname_copilot %} plan, we strongly recommend using {% data variables.product.prodname_actions %}' built-in `GITHUB_TOKEN`. This approach bills to the organization and avoids using a {% data variables.product.pat_generic %}.
+
+To bill to the organization, you need:
+
+1. An organization administrator to enable "Copilot CLI" and "Allow use of Copilot CLI billed to the organization" in {% data variables.product.prodname_copilot %} policy settings. If "Copilot CLI" is already enabled, the billing policy is enabled by default.
+1. In each workflow frontmatter, include `copilot-requests: write` under the `permissions` object.
+
+When `copilot-requests: write` is set in workflow frontmatter permissions, the {% data variables.product.prodname_actions %}' token is used for Copilot requests, so you don't need a `COPILOT_GITHUB_TOKEN`. If the {% data variables.product.prodname_actions %} token does not have {% data variables.product.prodname_copilot %} access from the organization, the workflow fails when it sends Copilot requests, and you should configure `COPILOT_GITHUB_TOKEN` instead.
+
+For detailed setup instructions, see [Using the built-in `GITHUB_TOKEN`](/copilot/how-tos/github-agentic-workflows/creating-github-agentic-workflows#using-the-built-in-github_token).
+
+## Next steps
+
+* To add your first agentic workflow, see [AUTOTITLE](/copilot/how-tos/github-agentic-workflows/quickstart).
+* For more information on creating and using {% data variables.copilot.agentic_workflows_short %}, see [AUTOTITLE](/copilot/how-tos/github-agentic-workflows/creating-github-agentic-workflows).
+* For the full reference documentation, including advanced patterns and examples, see the [{% data variables.copilot.github_agentic_workflows %} documentation site](https://github.github.com/gh-aw/).

content/copilot/concepts/agents/cloud-agent/about-cloud-agent.md

@@ -58,6 +58,10 @@ When used effectively, {% data variables.copilot.copilot_cloud_agent %} offers p
 
 * With **{% data variables.copilot.copilot_cloud_agent %}**, all coding and iterating happens **on {% data variables.product.github %}**. You can ask {% data variables.product.prodname_copilot_short %} to **research** a repository, **create a plan**, and **make code changes** on a branch—all before opening a pull request. You can create multiple {% data variables.copilot.custom_agents_short %} that specialize in different types of tasks. {% data variables.product.prodname_copilot_short %} **automates** branch creation, commit message writing, and pushing. Developers let the agents **work in the background** and then chooses to **create a pull request** when ready. Working on {% data variables.product.github %} adds **transparency**, with every step happening in a commit and being viewable in logs, and opens up **collaboration** opportunities for the entire team.
 
+### Sharing context between {% data variables.copilot.copilot_chat_short %} and {% data variables.copilot.copilot_cloud_agent %} sessions
+
+When you start a {% data variables.copilot.copilot_cloud_agent %} session from {% data variables.copilot.copilot_chat_short %} on {% data variables.product.github %}, the session carries the context of your chat. You can continue chatting while the session runs, and ask follow-up questions about progress in the same conversation. For more information, see [AUTOTITLE](/copilot/how-tos/copilot-on-github/use-copilot-agents/manage-and-track-agents).
+
 ## {% data variables.copilot.copilot_cloud_agent %} versus agent mode
 
 {% data variables.copilot.copilot_cloud_agent %} is distinct from the "agent mode" feature available in your IDE. {% data variables.copilot.copilot_cloud_agent %} works autonomously in a {% data variables.product.prodname_actions %}-powered environment to complete development tasks assigned through {% data variables.product.github %} issues or {% data variables.copilot.copilot_chat %} prompts. It can research a repository, create a plan, make code changes on a branch, and optionally open a pull request. In contrast, agent mode in your IDE makes autonomous edits directly in your local development environment. For more information about agent mode, see [AUTOTITLE](/copilot/using-github-copilot/copilot-chat/asking-github-copilot-questions-in-your-ide).

content/copilot/concepts/agents/index.md

@@ -10,6 +10,7 @@ children:
   - /copilot-cli
   - /github-copilot-app
   - /code-review
+  - /about-github-agentic-workflows
   - /copilot-memory
   - /hooks
   - /about-enterprise-plugin-standards

content/copilot/concepts/chat.md

@@ -7,7 +7,7 @@ versions:
 redirect_from:
   - /copilot/concepts/about-github-copilot-chat
 contentType: concepts
-category: 
+category:
   - Learn about Copilot
 ---
 
@@ -30,6 +30,14 @@ Different environments may have different features and capabilities, but the cor
 
 {% data variables.copilot.copilot_chat_short %} is designed to assist with coding tasks, but you remain responsible for reviewing and validating the code it generates. It may not always produce correct or optimal solutions, and it can sometimes generate code that contains security vulnerabilities or other issues. Always test and review the code before using it in production.
 
+## Passing context between {% data variables.copilot.copilot_chat_short %} and {% data variables.copilot.copilot_cloud_agent %} sessions
+
+On {% data variables.product.github %}, {% data variables.copilot.copilot_chat_short %} and {% data variables.copilot.copilot_cloud_agent %} can share context. When you start an agent session from a chat, the session incorporates the context of your conversation, and while the session runs you can continue chatting with {% data variables.product.prodname_copilot_short %} about its progress.
+
+{% data variables.copilot.copilot_chat_short %} can also answer questions about pull requests created by {% data variables.product.prodname_copilot_short %} by pulling in the relevant agent session logs, so you can ask what changed, what was validated, and why, without leaving the conversation.
+
+This context passing is scoped to the {% data variables.copilot.copilot_chat_short %} and {% data variables.copilot.copilot_cloud_agent_short %} sessions you are actively working with. It is distinct from {% data variables.copilot.copilot_memory %}, which builds a longer-term, persistent understanding of your repositories and preferences across sessions. For more information, see [AUTOTITLE](/copilot/how-tos/copilot-on-github/use-copilot-agents/manage-and-track-agents).
+
 ## Customizing {% data variables.copilot.copilot_chat_short %} responses
 
 {% data variables.product.prodname_copilot %} in {% data variables.product.github %}, {% data variables.product.prodname_vscode %}, and {% data variables.product.prodname_vs %} can provide chat responses that are tailored to the way your team works, the tools you use, the specifics of your project, or your personal preferences, if you provide it with enough context to do so. Instead of repeating instructions in each prompt, you can create and save instructions for {% data variables.copilot.copilot_chat_short %} to customize what responses you receive.

content/copilot/how-tos/copilot-on-github/chat-with-copilot/chat-in-github.md

@@ -19,7 +19,7 @@ redirect_from:
   - /copilot/how-tos/chat-with-copilot/use-chat-in-github
   - /copilot/how-tos/chat-with-copilot/chat-in-github
 contentType: how-tos
-category: 
+category:
   - Author and optimize with Copilot
 ---
 
@@ -72,6 +72,10 @@ The response to your edited question is displayed in a new subthread. An edit co
 
 You can attach images to your prompts by pasting, dragging, or clicking {% octicon "plus" aria-label="Add attachment" %} in the prompt box and then selecting **{% octicon "file-code" aria-hidden="true" %} Upload from computer**. Select a model that supports images from the model picker. For supported file types and example questions, see [AUTOTITLE](/copilot/how-tos/use-copilot-agents/coding-agent/provide-visual-inputs).
 
+### Continuing a conversation alongside an agent session
+
+When you start a {% data variables.copilot.copilot_cloud_agent %} task from {% data variables.copilot.copilot_chat_short %}—for example, by asking {% data variables.product.prodname_copilot_short %} to create a pull request or research a repository—you can keep chatting while the {% data variables.copilot.copilot_cloud_agent_short %} session runs. {% data variables.copilot.copilot_chat_short %} reflects the status of the in-progress session and draws on its context, so you can ask follow-up questions about what the agent is doing. When the session is complete, you can ask further questions about the work or start another session from {% data variables.copilot.copilot_chat_short %}. For more information, see [AUTOTITLE](/copilot/how-tos/copilot-on-github/use-copilot-agents/manage-and-track-agents).
+
 ### Conversation history and retention
 
 {% data variables.copilot.copilot_chat_short %} stores up to 100 of your most recent conversations. Messages within each conversation are kept for 28 days before being permanently deleted. Once a conversation has no messages left, it's automatically removed from your history.

content/copilot/how-tos/copilot-on-github/chat-with-copilot/get-started-with-chat.md

@@ -44,6 +44,8 @@ Navigate to a pull request to ask about changes, reviews, or failing workflows.
 * {% prompt %}Summarize the changes in this PR.{% endprompt %}
 * {% prompt %}What's the purpose of this file?{% endprompt %}
 * {% prompt %}Tell me why this job failed{% endprompt %}
+* {% prompt %}What did {% data variables.product.prodname_copilot_short %} change in this PR and why?{% endprompt %}
+* {% prompt %}What did {% data variables.product.prodname_copilot_short %} validate before opening this PR?{% endprompt %}
 
 ## Security alert questions