From 5f1d7c6454e45926966dfb7fd995597af63fdc9f Mon Sep 17 00:00:00 2001
From: cwebster-99 <cowebster@microsoft.com>
Date: Wed, 27 May 2026 15:50:14 -0500
Subject: [PATCH 1/3] Initial release notes updates for UBB

---
 release-notes/v1_122.md | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/release-notes/v1_122.md b/release-notes/v1_122.md
index 3e9c8edcc4..d2e50d5b12 100644
--- a/release-notes/v1_122.md
+++ b/release-notes/v1_122.md
@@ -29,6 +29,8 @@ Welcome to the 1.122 release of Visual Studio Code. This release further enhance
 
 * [Rich issue reporting](#improved-issue-reporting-flow): Create rich VS Code issue reports, including screenshots and video recordings.
 
+* [GitHub Copilot moves to usage-based billing](#usage-based-billing-with-github-ai-credits): GitHub Copilot moves to usage-based billing with GitHub AI Credits, with updated usage visibility in VS Code.
+
 Happy Coding!
 
 ---
@@ -46,6 +48,7 @@ To try new features as soon as possible, [**download the nightly Insiders build*
   <nav id="toc-nav">
     <div>In this update</div>
     <ul>
+      <li><a href="#github-copilot">GitHub Copilot moves to usage based billing</a></li>
       <li><a href="#agents">Agents</a></li>
       <li><a href="#language-models">Language Models</a></li>
       <li><a href="#integrated-browser">Integrated browser</a></li>
@@ -58,6 +61,32 @@ To try new features as soon as possible, [**download the nightly Insiders build*
   <div class="notes-main">
 Navigation End -->
 
+## GitHub Copilot moves to usage based billing
+
+GitHub Copilot has moved from request-based billing to usage-based billing. Instead of counting premium requests, Copilot now uses **GitHub AI Credits** as the billing unit, where 1 AI credit = $0.01 USD.
+
+Under the new model, each interaction consumes tokens (input, output, and cached), and the total cost is converted into AI credits based on the model used. More complex interactions and more capable models consume more credits, while lightweight models and simpler tasks use fewer. Code completions and next edit suggestions remain unlimited for all paid plans and are not billed in AI credits.
+
+Learn more about the transition in the GitHub documentation for [usage-based billing for individuals](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals) and [usage-based billing for organizations and enterprises](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-organizations-and-enterprises).
+
+### Updated Copilot status dashboard
+
+The Copilot status dashboard in the VS Code Status Bar now reflects usage-based billing. You can view your AI credits consumption so you can monitor your spending at a glance.
+
+// TODO add screenshot
+
+### Model costs in the model picker
+
+The model picker now displays cost information to help you make informed model choices. Different models have different costs per token type, so choosing the right model for your task can help extend your usage allowance.
+
+You can view all available models, their capabilities, context sizes, and billing details in the Language Models editor. Open it from the model picker by selecting **Manage Models**, or run the **Chat: Manage Language Models** command from the Command Palette.
+
+### Per-turn credit cost in chat
+
+Each chat response now shows the AI credits consumed for that turn. After a response completes, hover over the response header to see a breakdown that includes the model used, and the total AI credits cost for that interaction.
+
+When your AI credits allowance is running low, VS Code shows a warning in the chat input area. You can also check your remaining balance at any time through the [Copilot status dashboard](#updated-copilot-status-dashboard) in the Status Bar.
+
 ## Agents
 
 ### Agents Window (Preview)
@@ -114,6 +143,14 @@ You have two options:
 
 The notification hides automatically once you configure both utility settings, sign in to GitHub, or remove all BYOK models.
 
+### 1M context window for Anthropic and OpenAI models
+
+VS Code now supports 1 million token context windows for compatible Anthropic and OpenAI models. This expanded context window enables you to work with significantly larger codebases and longer conversations without losing important context.
+
+The expanded context window is available when using supported models, such as Claude Opus 4.7 and GPT-5.4. You can monitor how much of the context window is in use through the context window usage indicator in the chat input area.
+
+> **Note**: Larger context windows consume more tokens per interaction, which increases AI credits usage under [usage-based billing](#github-copilot-moves-to-usage-based-billing). Use the context window indicator to stay aware of your token consumption.
+
 ### Custom Endpoint provider in Stable
 
 The Custom Endpoint provider lets you connect models that implement Chat Completions, Responses, or Messages APIs, so you can use chat with your own endpoint and API key. You can use it to connect to self-hosted, enterprise, or other compatible AI endpoints.

From 1ec1b46c7c848318f1e987df65b91204f5aefaee Mon Sep 17 00:00:00 2001
From: cwebster-99 <cowebster@microsoft.com>
Date: Thu, 28 May 2026 11:04:26 -0500
Subject: [PATCH 2/3] Update release notes for Copilot usage-based billing

---
 .../images/1_122/copilot-status-dashboard.png |  3 ++
 .../images/1_122/extended-context.png         |  3 ++
 .../images/1_122/update-model-picker.png      |  3 ++
 release-notes/v1_122.md                       | 44 ++++++++-----------
 4 files changed, 28 insertions(+), 25 deletions(-)
 create mode 100644 release-notes/images/1_122/copilot-status-dashboard.png
 create mode 100644 release-notes/images/1_122/extended-context.png
 create mode 100644 release-notes/images/1_122/update-model-picker.png

diff --git a/release-notes/images/1_122/copilot-status-dashboard.png b/release-notes/images/1_122/copilot-status-dashboard.png
new file mode 100644
index 0000000000..4acf77d855
--- /dev/null
+++ b/release-notes/images/1_122/copilot-status-dashboard.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6998747ad11e0d266b2e21163e17a832547ed907e4dd70a772afcbe1c6756d1d
+size 30355
diff --git a/release-notes/images/1_122/extended-context.png b/release-notes/images/1_122/extended-context.png
new file mode 100644
index 0000000000..0567302b6e
--- /dev/null
+++ b/release-notes/images/1_122/extended-context.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:879757d8968d877a225bfe36aca25adbf342e044065936771d0095f0be2c4a2c
+size 35382
diff --git a/release-notes/images/1_122/update-model-picker.png b/release-notes/images/1_122/update-model-picker.png
new file mode 100644
index 0000000000..54d900c50d
--- /dev/null
+++ b/release-notes/images/1_122/update-model-picker.png
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd23d14bd20f57ce0521a0f051718a1b73c9e5bebb58f94729485826c9080842
+size 100873
diff --git a/release-notes/v1_122.md b/release-notes/v1_122.md
index d2e50d5b12..a1ce3b4e5d 100644
--- a/release-notes/v1_122.md
+++ b/release-notes/v1_122.md
@@ -23,14 +23,14 @@ _Release date: May 28, 2026_
 
 Welcome to the 1.122 release of Visual Studio Code. This release further enhances the agent experience and makes BYOK more flexible, while adding new capabilities for testing web apps across different devices.
 
+* [Support for 1M context windows](#1m-context-window-for-anthropic-and-openai-models): Support for 1M context windows for Anthropic and OpenAI models.
+
 * [Air-gapped BYOK](#use-byok-without-a-github-sign-in): Use your own language models, even when you're not connected.
 
 * [Browser device emulation](#emulate-devices): Test your website's responsiveness across different devices directly in the integrated browser.
 
 * [Rich issue reporting](#improved-issue-reporting-flow): Create rich VS Code issue reports, including screenshots and video recordings.
 
-* [GitHub Copilot moves to usage-based billing](#usage-based-billing-with-github-ai-credits): GitHub Copilot moves to usage-based billing with GitHub AI Credits, with updated usage visibility in VS Code.
-
 Happy Coding!
 
 ---
@@ -48,7 +48,7 @@ To try new features as soon as possible, [**download the nightly Insiders build*
   <nav id="toc-nav">
     <div>In this update</div>
     <ul>
-      <li><a href="#github-copilot">GitHub Copilot moves to usage based billing</a></li>
+      <li><a href="#usage-based-billing-with-github-ai-credits">GitHub Copilot moves to usage-based billing</a></li>
       <li><a href="#agents">Agents</a></li>
       <li><a href="#language-models">Language Models</a></li>
       <li><a href="#integrated-browser">Integrated browser</a></li>
@@ -61,31 +61,25 @@ To try new features as soon as possible, [**download the nightly Insiders build*
   <div class="notes-main">
 Navigation End -->
 
-## GitHub Copilot moves to usage based billing
+## GitHub Copilot moves to usage-based billing
 
-GitHub Copilot has moved from request-based billing to usage-based billing. Instead of counting premium requests, Copilot now uses **GitHub AI Credits** as the billing unit, where 1 AI credit = $0.01 USD.
+GitHub Copilot has moved to [usage-based billing](https://github.blog/news-insights/company-news/github-copilot-is-moving-to-usage-based-billing/).
 
-Under the new model, each interaction consumes tokens (input, output, and cached), and the total cost is converted into AI credits based on the model used. More complex interactions and more capable models consume more credits, while lightweight models and simpler tasks use fewer. Code completions and next edit suggestions remain unlimited for all paid plans and are not billed in AI credits.
-
-Learn more about the transition in the GitHub documentation for [usage-based billing for individuals](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals) and [usage-based billing for organizations and enterprises](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-organizations-and-enterprises).
+Under the new model, each interaction consumes AI credits which are calculated based on token (input, output, and cached) cost based on the model used. More complex interactions and more capable models consume more credits, while lightweight models and simpler tasks use fewer. Learn more about how your usage can impact cost in our [docs]().
 
 ### Updated Copilot status dashboard
 
-The Copilot status dashboard in the VS Code Status Bar now reflects usage-based billing. You can view your AI credits consumption so you can monitor your spending at a glance.
+The Copilot status dashboard now reflects usage-based billing. You can view your AI credits consumption, so you can monitor your usage at a glance.
 
-// TODO add screenshot
+![Screenshot showing the Copilot status dashboard](images/1_122/copilot-status-dashboard.png)
 
 ### Model costs in the model picker
 
-The model picker now displays cost information to help you make informed model choices. Different models have different costs per token type, so choosing the right model for your task can help extend your usage allowance.
-
-You can view all available models, their capabilities, context sizes, and billing details in the Language Models editor. Open it from the model picker by selecting **Manage Models**, or run the **Chat: Manage Language Models** command from the Command Palette.
+The model picker now displays cost information to help you make informed model choices. Different models have different costs per token type, so choosing the right model for your task can help extend your usage.
 
-### Per-turn credit cost in chat
+![Screenshot showing the model picker with cost information](images/1_122/update-model-picker.png)
 
-Each chat response now shows the AI credits consumed for that turn. After a response completes, hover over the response header to see a breakdown that includes the model used, and the total AI credits cost for that interaction.
-
-When your AI credits allowance is running low, VS Code shows a warning in the chat input area. You can also check your remaining balance at any time through the [Copilot status dashboard](#updated-copilot-status-dashboard) in the Status Bar.
+You can view all available models, their capabilities, context sizes, and billing details in the Language Models editor. Open it from the model picker by selecting ⚙️, or run the **Chat: Manage Language Models** command from the Command Palette.
 
 ## Agents
 
@@ -119,6 +113,14 @@ Based on feedback from Insiders users, terminal sandboxing now only applies when
 
 ## Language Models
 
+### 1M context window for Anthropic and OpenAI models
+
+VS Code now supports 1 million token context windows for compatible Anthropic and OpenAI models. This expanded context window enables you to work with significantly larger codebases and longer conversations without losing important context. The expanded context window is available when using supported models, such as Claude Opus 4.7 and GPT-5.5.
+
+![Screenshot showing extended context size options.](images/1_122/extended-context.png)
+
+> **Note**: Larger context windows may consume more tokens per interaction, which increases AI credits usage under [usage-based billing](#github-copilot-moves-to-usage-based-billing).
+
 ### Use BYOK without a GitHub sign in
 
 Previously, using your own language model API key in VS Code required signing in to GitHub. Now, [Bring Your Own Key (BYOK)](https://code.visualstudio.com/docs/copilot/customization/language-models#_bring-your-own-language-model-key) works without signing in, so you can use chat, tools, and MCP servers in air-gapped or restricted environments where GitHub sign-in isn't possible. This also enables fully offline workflows with local models like Ollama.
@@ -143,14 +145,6 @@ You have two options:
 
 The notification hides automatically once you configure both utility settings, sign in to GitHub, or remove all BYOK models.
 
-### 1M context window for Anthropic and OpenAI models
-
-VS Code now supports 1 million token context windows for compatible Anthropic and OpenAI models. This expanded context window enables you to work with significantly larger codebases and longer conversations without losing important context.
-
-The expanded context window is available when using supported models, such as Claude Opus 4.7 and GPT-5.4. You can monitor how much of the context window is in use through the context window usage indicator in the chat input area.
-
-> **Note**: Larger context windows consume more tokens per interaction, which increases AI credits usage under [usage-based billing](#github-copilot-moves-to-usage-based-billing). Use the context window indicator to stay aware of your token consumption.
-
 ### Custom Endpoint provider in Stable
 
 The Custom Endpoint provider lets you connect models that implement Chat Completions, Responses, or Messages APIs, so you can use chat with your own endpoint and API key. You can use it to connect to self-hosted, enterprise, or other compatible AI endpoints.

From 64cf593f8b3056ec7522e44ac03a0150d8c8cf75 Mon Sep 17 00:00:00 2001
From: Nick Trogh <ntrogh@hotmail.com>
Date: Thu, 28 May 2026 20:37:46 +0200
Subject: [PATCH 3/3] Edit pass

---
 release-notes/v1_122.md | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/release-notes/v1_122.md b/release-notes/v1_122.md
index a1ce3b4e5d..60ce25188d 100644
--- a/release-notes/v1_122.md
+++ b/release-notes/v1_122.md
@@ -23,7 +23,7 @@ _Release date: May 28, 2026_
 
 Welcome to the 1.122 release of Visual Studio Code. This release further enhances the agent experience and makes BYOK more flexible, while adding new capabilities for testing web apps across different devices.
 
-* [Support for 1M context windows](#1m-context-window-for-anthropic-and-openai-models): Support for 1M context windows for Anthropic and OpenAI models.
+* [Larger context windows](#1m-context-window-for-anthropic-and-openai-models): Support for 1M context windows for Anthropic and OpenAI models.
 
 * [Air-gapped BYOK](#use-byok-without-a-github-sign-in): Use your own language models, even when you're not connected.
 
@@ -61,11 +61,11 @@ To try new features as soon as possible, [**download the nightly Insiders build*
   <div class="notes-main">
 Navigation End -->
 
-## GitHub Copilot moves to usage-based billing
+## GitHub Copilot moves to usage based billing
 
 GitHub Copilot has moved to [usage-based billing](https://github.blog/news-insights/company-news/github-copilot-is-moving-to-usage-based-billing/).
 
-Under the new model, each interaction consumes AI credits which are calculated based on token (input, output, and cached) cost based on the model used. More complex interactions and more capable models consume more credits, while lightweight models and simpler tasks use fewer. Learn more about how your usage can impact cost in our [docs]().
+Under the new model, each interaction consumes AI credits, which are calculated based on token (input, output, and cached) cost and on the model used. Complex interactions and more capable models consume more credits, while lightweight models and simpler tasks use fewer. Learn more about how you can [optimize your usage](https://code.visualstudio.com/docs/copilot/guides/optimize-usage).
 
 ### Updated Copilot status dashboard