diff --git a/CHANGELOG.md b/CHANGELOG.md index 840c65510fca..a78b1e39373b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,13 @@ # Docs changelog +**3 April 2026** + +We've published documentation for the GitHub Copilot SDK, now available in public preview. These docs were migrated from the `github/copilot-sdk` repo and cover getting started, setup, authentication, usage patterns, hooks, observability, integrations, and troubleshooting. + +See [GitHub Copilot SDK documentation](https://docs.github.com/en/copilot/how-tos/copilot-sdk). + +
+ **2 April 2026** We've expanded the documentation for custom agents in Copilot CLI, adding information about the built-in agents. diff --git a/content/actions/tutorials/publish-packages/publish-docker-images.md b/content/actions/tutorials/publish-packages/publish-docker-images.md index a883b44129b9..ee8a4218cf48 100644 --- a/content/actions/tutorials/publish-packages/publish-docker-images.md +++ b/content/actions/tutorials/publish-packages/publish-docker-images.md @@ -234,3 +234,15 @@ Then the `build-push-action` action builds and pushes the Docker image to Docker > * To maintain a consistent digest and allow a single attestation to verify all copies, push to one registry first and use a tool like [`crane copy`](https://github.com/google/go-containerregistry/blob/main/cmd/crane/doc/crane_copy.md) to replicate the image elsewhere. > * If you choose to build and push to each registry separately instead, you must generate a distinct attestation for each one to ensure your artifacts remain verifiable. {% endif %} + +## Hands-on practice + +Practice publishing Docker images with the [Publishing Docker images](https://github.com/skills/publish-docker-images) {% data variables.product.prodname_learning %} exercise. + +In this exercise, you will learn how to: + +* Authenticate to {% data variables.product.prodname_registry %} using the `GITHUB_TOKEN`. +* Build and publish container images to the {% data variables.product.prodname_container_registry %} (`ghcr.io`). +* Use official Docker actions, such as `docker/login-action`, `docker/build-push-action`, and `docker/setup-buildx-action`. +* Generate tags automatically with `docker/metadata-action` based on branches, pull requests, and releases. +* Create features, pull requests, and releases with proper container versioning. diff --git a/content/copilot/responsible-use/pull-request-summaries.md b/content/copilot/responsible-use/pull-request-summaries.md index 133d840f3940..33ded2bf3002 100644 --- a/content/copilot/responsible-use/pull-request-summaries.md +++ b/content/copilot/responsible-use/pull-request-summaries.md @@ -72,6 +72,10 @@ After you rate a summary as good or bad, you can provide written feedback by cli Currently, our team is aware that there are limitations to this feature. Many of them are expected in leveraging our {% data variables.product.prodname_copilot_short %} API; however, there are a few that are specific to {% data variables.copilot.copilot_for_prs %} which pertain to limited scope, longer processing times, and inaccurate responses. We also note that users should expect terms used in their PR to appear in the AI-generated summary. This feature has been subject to RAI Red Teaming and we will continue to monitor the efficacy and safety of the feature over time. For more information, see [Microsoft AI Red Team building future of safer AI](https://www.microsoft.com/en-us/security/blog/2023/08/07/microsoft-ai-red-team-building-future-of-safer-ai/) on the Microsoft security blog. +### Lines changed limits + +Files with more than 400 combined additions and deletions are excluded from summarization. + ### Limited scope Because of capacity, we know that larger pull requests that reference 30 or more files will require more time to be processed thoroughly. We don't have an exact threshold currently, but have observed the first 30 files being accounted for and then any additional files being omitted from the summarization. We are working to address this current scope limitation. diff --git a/content/copilot/tutorials/enhance-agent-mode-with-mcp.md b/content/copilot/tutorials/enhance-agent-mode-with-mcp.md index 880ac2c09557..44c9b3a725dc 100644 --- a/content/copilot/tutorials/enhance-agent-mode-with-mcp.md +++ b/content/copilot/tutorials/enhance-agent-mode-with-mcp.md @@ -214,7 +214,14 @@ Now you can review the pull request and make any adjustments. Once you have veri ## Hands-on practice -Try the [Integrate MCP with {% data variables.product.prodname_copilot %}](https://github.com/skills/integrate-mcp-with-copilot/) Skills exercise for practical experience integrating MCP with {% data variables.product.prodname_copilot %}. +Practice integrating MCP with {% data variables.product.prodname_copilot %} in the [Integrate MCP with {% data variables.product.prodname_copilot %}](https://github.com/skills/integrate-mcp-with-copilot/) Skills exercise. + +In this exercise, you will learn how to: + +* Set up and connect the {% data variables.product.github %} MCP server to {% data variables.product.prodname_copilot %}. +* Use natural language to interact with external services through MCP tools in agent mode. +* Search for and analyze similar projects with MCP. +* Triage, create, and manage {% data variables.product.github %} issues, then implement changes with {% data variables.product.prodname_copilot %}. ## Further reading diff --git a/content/copilot/tutorials/modernize-legacy-code.md b/content/copilot/tutorials/modernize-legacy-code.md index 1e4e0b5598e3..69c74e800bc9 100644 --- a/content/copilot/tutorials/modernize-legacy-code.md +++ b/content/copilot/tutorials/modernize-legacy-code.md @@ -407,7 +407,14 @@ In this example, we looked at an account management system written in COBOL and ## Hands-on practice -Try the [Modernizing your legacy code with {% data variables.product.prodname_copilot %}](https://github.com/skills/modernize-your-legacy-code-with-github-copilot) Skills exercise for practical experience updating a legacy codebase with {% data variables.product.prodname_copilot %}. +Practice modernizing legacy code with the [Modernizing your legacy code with {% data variables.product.prodname_copilot %}](https://github.com/skills/modernize-your-legacy-code-with-github-copilot) Skills exercise. + +In this exercise, you will learn how to: + +* Analyze legacy COBOL code with {% data variables.copilot.copilot_chat %} to understand business logic. +* Generate documentation, such as Mermaid data flow diagrams and test plans. +* Transform a COBOL codebase to Node.js with {% data variables.product.prodname_copilot_short %}. +* Create unit tests based on the generated test plan. ## Further reading diff --git a/data/tables/copilot/model-comparison.yml b/data/tables/copilot/model-comparison.yml index 76e03df101a4..00be728a2ea5 100644 --- a/data/tables/copilot/model-comparison.yml +++ b/data/tables/copilot/model-comparison.yml @@ -22,21 +22,6 @@ excels_at: Multi-step problem solving and architecture-level code analysis further_reading: '[GPT-5.1 model card](https://cdn.openai.com/pdf/4173ec8d-1229-47db-96de-06d87147e07e/5_1_system_card.pdf)' -- name: GPT-5.1-Codex - task_area: Deep reasoning and debugging - excels_at: Multi-step problem solving and architecture-level code analysis - further_reading: 'Not available' - -- name: GPT-5.1 Codex Max - task_area: Agentic software development - excels_at: Agentic tasks - further_reading: '[GPT-5.1-Codex-Max model card](https://cdn.openai.com/pdf/2a7d98b1-57e5-4147-8d0e-683894d782ae/5p1_codex_max_card_03.pdf)' - -- name: GPT-5.1-Codex-Mini - task_area: Deep reasoning and debugging - excels_at: Multi-step problem solving and architecture-level code analysis - further_reading: 'Not available' - - name: GPT-5.2 task_area: Deep reasoning and debugging excels_at: Multi-step problem solving and architecture-level code analysis @@ -109,11 +94,6 @@ excels_at: Fast, reliable answers to lightweight coding questions further_reading: '[Gemini 3 Flash model card](https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-Flash-Model-Card.pdf)' -- name: Gemini 3 Pro - task_area: Deep reasoning and debugging - excels_at: Complex code generation, debugging, and research workflows - further_reading: '[Gemini 3 Pro model card](https://storage.googleapis.com/deepmind-media/Model-Cards/Gemini-3-Pro-Model-Card.pdf)' - - name: Gemini 3.1 Pro task_area: Deep reasoning and debugging excels_at: Effective and efficient edit-then-test loops with high tool precision diff --git a/data/tables/copilot/model-multipliers.yml b/data/tables/copilot/model-multipliers.yml index 5f018ec975f7..ffde2f8d07b4 100644 --- a/data/tables/copilot/model-multipliers.yml +++ b/data/tables/copilot/model-multipliers.yml @@ -45,10 +45,6 @@ multiplier_paid: 0.33 multiplier_free: Not applicable -- name: Gemini 3 Pro - multiplier_paid: 1 - multiplier_free: Not applicable - - name: Gemini 3.1 Pro multiplier_paid: 1 multiplier_free: Not applicable @@ -69,18 +65,6 @@ multiplier_paid: 1 multiplier_free: Not applicable -- name: GPT-5.1-Codex - multiplier_paid: 1 - multiplier_free: Not applicable - -- name: GPT-5.1-Codex-Mini - multiplier_paid: 0.33 - multiplier_free: Not applicable - -- name: GPT-5.1-Codex-Max - multiplier_paid: 1.0 - multiplier_free: Not applicable - - name: GPT-5.2 multiplier_paid: 1.0 multiplier_free: Not applicable diff --git a/data/tables/copilot/model-supported-clients.yml b/data/tables/copilot/model-supported-clients.yml index bd55c4c5a348..e82b9b794ff2 100644 --- a/data/tables/copilot/model-supported-clients.yml +++ b/data/tables/copilot/model-supported-clients.yml @@ -95,15 +95,6 @@ xcode: true jetbrains: true -- name: Gemini 3 Pro - dotcom: true - cli: true - vscode: true - vs: true - eclipse: true - xcode: true - jetbrains: true - - name: Gemini 3.1 Pro dotcom: true cli: false @@ -140,33 +131,6 @@ xcode: true jetbrains: true -- name: GPT-5.1-Codex - dotcom: false - cli: true - vscode: true - vs: false - eclipse: true - xcode: true - jetbrains: true - -- name: GPT-5.1-Codex-Mini - dotcom: false - cli: true - vscode: true - vs: false - eclipse: true - xcode: true - jetbrains: true - -- name: GPT-5.1-Codex-Max - dotcom: true - cli: true - vscode: true - vs: true - eclipse: true - xcode: true - jetbrains: true - - name: GPT-5.2 dotcom: true cli: true diff --git a/data/tables/copilot/model-supported-plans.yml b/data/tables/copilot/model-supported-plans.yml index 1e1e3d9acf3a..38ad2e85100f 100644 --- a/data/tables/copilot/model-supported-plans.yml +++ b/data/tables/copilot/model-supported-plans.yml @@ -85,14 +85,6 @@ business: true enterprise: true -- name: Gemini 3 Pro - free: false - student: true - pro: true - pro_plus: true - business: true - enterprise: true - - name: Gemini 3.1 Pro free: false student: true @@ -125,30 +117,6 @@ business: true enterprise: true -- name: GPT-5.1-Codex - free: false - student: true - pro: true - pro_plus: true - business: true - enterprise: true - -- name: GPT-5.1-Codex-Mini - free: false - student: true - pro: true - pro_plus: true - business: true - enterprise: true - -- name: GPT-5.1-Codex-Max - free: false - student: true - pro: true - pro_plus: true - business: true - enterprise: true - - name: GPT-5.2 free: false student: true diff --git a/src/frame/lib/frontmatter.ts b/src/frame/lib/frontmatter.ts index 3f1ec1339fca..539e707235b6 100644 --- a/src/frame/lib/frontmatter.ts +++ b/src/frame/lib/frontmatter.ts @@ -59,6 +59,10 @@ export const contentTypesEnum = [ 'other', // Everything else. ] +// Values supported in the docsTeamMetrics frontmatter property. Used to track +// related articles (e.g. by feature or subject) that may span different directories. +export const docsTeamMetricsEnum = ['copilot-cli'] + export const schema: Schema = { type: 'object', required: ['title', 'versions'], @@ -246,6 +250,13 @@ export const schema: Schema = { interactive: { type: 'boolean', }, + docsTeamMetrics: { + type: 'array', + items: { + type: 'string', + enum: docsTeamMetricsEnum, + }, + }, communityRedirect: { type: 'object', properties: {