diff --git a/build/sitemap.xml b/build/sitemap.xml index 0e70cf239b..3091636f97 100644 --- a/build/sitemap.xml +++ b/build/sitemap.xml @@ -610,6 +610,11 @@ weekly 0.8 + + https://code.visualstudio.com/docs/copilot/guides/optimize-usage + weekly + 0.8 + https://code.visualstudio.com/docs/copilot/guides/customize-copilot-guide weekly diff --git a/docs/copilot/agents/agent-tools.md b/docs/copilot/agents/agent-tools.md index 8be4fb683f..9b349d3b42 100644 --- a/docs/copilot/agents/agent-tools.md +++ b/docs/copilot/agents/agent-tools.md @@ -97,7 +97,7 @@ When you select the **Autopilot** permission level, the agent behaves differentl Autopilot is available in the Chat view when the `setting(chat.autopilot.enabled)` setting is enabled (on by default). > [!NOTE] -> Autopilot uses premium requests in the same way that these are used when you are working in the standard interactive interface. This means that as the agent continues to work autonomously, it can consume multiple requests. +> Autopilot consumes AI credits in the same way as the standard interactive interface. Learn more about [usage-based billing](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals). ## Tool approval diff --git a/docs/copilot/agents/agents-tutorial.md b/docs/copilot/agents/agents-tutorial.md index 94794b676c..3803b07fa1 100644 --- a/docs/copilot/agents/agents-tutorial.md +++ b/docs/copilot/agents/agents-tutorial.md @@ -18,7 +18,10 @@ Keywords: This tutorial walks you through using different types of agents in Visual Studio Code. You build a todo app from scratch, add a theme toggle, and redesign the layout by delegating work across local, plan, background, and cloud agents. > [!TIP] -> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly limit of inline suggestions and chat interactions. +> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly allowance of inline suggestions and AI credits. + +> [!IMPORTANT] +> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused.
Use browser agent tools to build and automatically test web applications. diff --git a/docs/copilot/agents/third-party-agents.md b/docs/copilot/agents/third-party-agents.md index 7c32df9ea2..cb51eaf5a5 100644 --- a/docs/copilot/agents/third-party-agents.md +++ b/docs/copilot/agents/third-party-agents.md @@ -104,7 +104,7 @@ To disable the OpenAI Codex agent, disable or uninstall the [OpenAI Codex](https * A Copilot Pro+ subscription for authentication * For local sessions, the [OpenAI Codex](https://marketplace.visualstudio.com/items?itemName=openai.chatgpt) extension -OpenAI Codex in VS Code enables you to use your Copilot Pro+ subscription to authenticate and access Codex without additional setup. Get more information about [GitHub Copilot billing and premium requests](https://docs.github.com/en/copilot/concepts/billing/copilot-requests) in the GitHub documentation. +OpenAI Codex in VS Code enables you to use your Copilot Pro+ subscription to authenticate and access Codex without additional setup. Get more information about [GitHub Copilot usage-based billing](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals) in the GitHub documentation. ### Start a Codex session diff --git a/docs/copilot/ai-powered-suggestions.md b/docs/copilot/ai-powered-suggestions.md index f1bbad21a1..410266698a 100644 --- a/docs/copilot/ai-powered-suggestions.md +++ b/docs/copilot/ai-powered-suggestions.md @@ -25,10 +25,7 @@ Follow a hands-on tutorial to build your first app with AI in VS Code. ## Prerequisites * Visual Studio Code installed on your machine. Follow these steps to [set up VS Code](/docs/setup/setup-overview.md). -* Access to a GitHub Copilot subscription. Follow these steps to [set up GitHub Copilot](/docs/copilot/setup.md). You can set up Copilot Free to get a monthly limit of inline suggestions and chat interactions. - -> [!IMPORTANT] -> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, and student plans are temporarily paused. Additionally, we are tightening weekly usage limits. See [GitHub Copilot usage limits](https://docs.github.com/copilot/concepts/usage-limits). +* Access to a GitHub Copilot subscription. Follow these steps to [set up GitHub Copilot](/docs/copilot/setup.md). You can set up Copilot Free to get a monthly allowance of inline suggestions and AI credits. ## Ghost text suggestions diff --git a/docs/copilot/best-practices.md b/docs/copilot/best-practices.md index 8bbe6f8587..7e53d8ada7 100644 --- a/docs/copilot/best-practices.md +++ b/docs/copilot/best-practices.md @@ -42,7 +42,7 @@ AI in VS Code offers several interaction modes. Choosing the right one for the t | Tool | Best for | Example | |------|----------|---------| -| [Inline suggestions](/docs/copilot/ai-powered-suggestions.md) | Staying in the flow while writing code | Code completions, variable names, boilerplate | +| [Inline suggestions](/docs/copilot/ai-powered-suggestions.md) | Staying in the flow while writing code | Inline suggestions, variable names, boilerplate | | [Ask (chat)](/docs/copilot/chat/copilot-chat.md) | Questions, brainstorming, exploring ideas | "How does authentication work in this project?" | | [Inline chat](/docs/copilot/chat/inline-chat.md) | Targeted, in-place edits without switching context | Refactoring a function, adding error handling | | [Agents](/docs/copilot/agents/overview.md) | Multi-file changes that require autonomous planning and tool use | Implementing a feature end-to-end | @@ -133,11 +133,13 @@ Each AI model has different strengths. Some are better at reasoning, others exce * **Use BYOK for additional control.** Bring your own API key for more model choices and hosting options. +* **Consider credit consumption.** More capable models consume more [AI credits](/docs/copilot/concepts/language-models.md#ai-credits-and-model-costs) per token. Auto model selection balances quality and cost automatically. For more tips, see [optimize AI credit usage](/docs/copilot/guides/optimize-usage.md). + For more information, see [selecting AI models](/docs/copilot/customization/language-models.md) and [available models for Copilot Chat](https://docs.github.com/en/copilot/using-github-copilot/ai-models/changing-the-ai-model-for-copilot-chat). ## Plan first, then implement -For complex changes that span multiple files, separate planning from implementation. This approach prevents the AI from solving the wrong problem. +For complex changes that span multiple files, separate planning from implementation. This approach prevents the AI from solving the wrong problem and avoids spending [AI credits](/docs/copilot/concepts/language-models.md#ai-credits-and-model-costs) on code that needs to be thrown away. 1. **Explore.** Use ask mode or a subagent to read the relevant code and understand how it works before making changes. 1. **Plan.** Use the [Plan agent](/docs/copilot/agents/planning.md) to create a structured implementation plan. Review and refine the plan before executing. @@ -164,11 +166,11 @@ For more information, see [GitHub Copilot security](/docs/copilot/security.md) a AI responses might degrade as the conversation fills with irrelevant context. Manage your sessions proactively. -* **Start new sessions for unrelated tasks.** Don't keep piling unrelated questions into one conversation. Context pollution reduces response quality. +* **Start new sessions for unrelated tasks.** Don't keep piling unrelated questions into one conversation. Context pollution reduces response quality and wastes tokens on irrelevant history. * **Remove irrelevant history.** Delete past questions and responses that are no longer relevant, or start a fresh session. -* **Compact context.** Use [/compact](/docs/copilot/chat/copilot-chat-context.md#context-compaction) and provide instructions to selectively compact the context and retain only the most relevant information. +* **Compact context.** Use [/compact](/docs/copilot/chat/copilot-chat-context.md#context-compaction) and provide instructions to selectively compact the context and retain only the most relevant information. Compacting reduces the tokens sent with each subsequent request, which helps [manage AI credit usage](/docs/copilot/guides/optimize-usage.md). * **Use subagents for investigation.** Hint the AI to perform research and exploration in isolation by using [subagents](/docs/copilot/agents/subagents.md) so the findings don't clutter your main context. @@ -176,7 +178,9 @@ AI responses might degrade as the conversation fills with irrelevant context. Ma * **Scale with parallel sessions.** Run multiple sessions in parallel for independent tasks to save time and keep contexts separate. You can have multiple sessions running at once, across local, background, and cloud environments, and switch between them via the [sessions list](/docs/copilot/chat/chat-sessions.md#sessions-list) in VS Code. -For more information, see [session management](/docs/copilot/chat/chat-sessions.md) and [workspace indexing](/docs/copilot/reference/workspace-context.md). +* **Fork instead of re-prompting.** Use [`/fork`](/docs/copilot/chat/chat-sessions.md#fork-a-chat-session) to explore alternatives without losing context, instead of starting over and re-establishing context from scratch. + +For more information, see [session management](/docs/copilot/chat/chat-sessions.md), [workspace indexing](/docs/copilot/reference/workspace-context.md), and [optimize AI credit usage](/docs/copilot/guides/optimize-usage.md). ## Work with large codebases diff --git a/docs/copilot/chat/copilot-chat-context.md b/docs/copilot/chat/copilot-chat-context.md index 5e3fb55e08..cce914cd99 100644 --- a/docs/copilot/chat/copilot-chat-context.md +++ b/docs/copilot/chat/copilot-chat-context.md @@ -133,7 +133,7 @@ As you send more requests in a conversation, the control updates to reflect the ## Context compaction -As a conversation grows, the accumulated messages and context can fill up the model's context window. Context compaction summarizes the conversation history to free up space, so you can continue working in the same session without losing important details. +As a conversation grows, the accumulated messages and context can fill up the model's context window. Context compaction summarizes the conversation history to free up space, so you can continue working in the same session without losing important details. Compacting also reduces the number of tokens sent with each subsequent request, which helps manage [AI credit consumption](/docs/copilot/guides/optimize-usage.md). ### Automatic compaction diff --git a/docs/copilot/chat/copilot-chat.md b/docs/copilot/chat/copilot-chat.md index b05d6c5c84..43e664b0ee 100644 --- a/docs/copilot/chat/copilot-chat.md +++ b/docs/copilot/chat/copilot-chat.md @@ -19,8 +19,8 @@ Follow a hands-on tutorial to experience local, background, and cloud agents in * Access to [GitHub Copilot](/docs/copilot/setup.md). If you don't have a subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup). - > [!IMPORTANT] - > **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, and student plans are temporarily paused. Additionally, we are tightening weekly usage limits. See [GitHub Copilot usage limits](https://docs.github.com/copilot/concepts/usage-limits). +> [!IMPORTANT] +> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. ## Access chat in VS Code diff --git a/docs/copilot/concepts/language-models.md b/docs/copilot/concepts/language-models.md index 27de213d3f..872587d2b7 100644 --- a/docs/copilot/concepts/language-models.md +++ b/docs/copilot/concepts/language-models.md @@ -72,13 +72,15 @@ You can switch models at any time, based on your needs for a particular task. Fo Auto model selection combines two systems to route each request to the optimal model. One system tracks real-time model health and availability, while the other evaluates task complexity. Together, they match each task to the model that can solve it most efficiently, reserving higher-cost reasoning models for problems that need them and routing simpler tasks to faster models. -Auto selects from multiple models and respects your organization's [model access settings](https://docs.github.com/en/copilot/how-tos/use-ai-models/configure-access-to-ai-models). Auto won't select models that have a premium request multiplier greater than 1x, models excluded by administrator policies, or models restricted by data-residency policies. If none of the preferred models are available or you run out of premium requests, auto falls back to a model at 0x multiplier. +Auto selects from multiple models and respects your organization's [model access settings](https://docs.github.com/en/copilot/how-tos/use-ai-models/configure-access-to-ai-models). Auto won't select models excluded by administrator policies or models restricted by data-residency policies. For more details, see [About Copilot auto model selection](https://docs.github.com/en/copilot/concepts/auto-model-selection) in the GitHub documentation. -### Premium requests and multipliers +### AI credits and model costs -Different models consume premium requests at different rates, expressed as a multiplier. For example, a model with a 2x multiplier uses two premium requests per interaction. When you use auto model selection, VS Code applies a variable [model multiplier](https://docs.github.com/en/copilot/concepts/billing/copilot-requests#model-multipliers) based on the selected model. If you are on a paid Copilot plan, auto applies a 10% multiplier discount. +Each Copilot plan includes a monthly allowance of [AI credits](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals). Different models consume AI credits at different rates, based on the model and the number of tokens processed. More capable models cost more per token, while lighter models extend your usage further. When you use auto model selection, VS Code routes each request to an efficient model that balances quality and cost. + +Other factors also affect credit consumption, such as [thinking effort](/docs/copilot/customization/language-models.md#configure-thinking-effort) (higher effort produces more thinking tokens), context window size, and tool usage. For practical tips on reducing credit consumption, see [optimize AI credit usage](/docs/copilot/guides/optimize-usage.md). Learn how to [choose and configure language models](/docs/copilot/customization/language-models.md) in VS Code. diff --git a/docs/copilot/concepts/tools.md b/docs/copilot/concepts/tools.md index 16a3129e2f..6956233de4 100644 --- a/docs/copilot/concepts/tools.md +++ b/docs/copilot/concepts/tools.md @@ -43,6 +43,7 @@ Use the **Configure Tools** button in the chat input field to enable or disable Limiting the available tools can help in several ways: * **Preserve context**: every tool call produces output that consumes space in the [context window](/docs/copilot/concepts/language-models.md#context-window). Fewer tools means the agent is less likely to make unnecessary calls that fill up the context. +* **Reduce credit consumption**: unnecessary tool calls increase token usage and consume more [AI credits](/docs/copilot/concepts/language-models.md#ai-credits-and-model-costs). Disabling tools you don't need for a task helps keep costs down. * **Get more relevant results**: when fewer tools are available, the agent focuses on the most appropriate ones rather than choosing from a large set. * **Improve performance**: a smaller tool set reduces the decision space for the model, which can speed up responses. diff --git a/docs/copilot/copilot-cloud-agent.md b/docs/copilot/copilot-cloud-agent.md index 012f15b2b4..0a98a738a2 100644 --- a/docs/copilot/copilot-cloud-agent.md +++ b/docs/copilot/copilot-cloud-agent.md @@ -45,7 +45,10 @@ Ensure you are signed into the GitHub Pull Request extension with the correct Gi You can also manage coding agent sessions from a dedicated chat editor and view a **Chat Sessions** view by enabling the experimental setting `setting(chat.agentSessionsViewLocation)`. > [!TIP] -> If you don't have Copilot access yet, you can sign up for the [Copilot Free plan](https://github.com/features/copilot/plans) to get a monthly limit of interactions. +> If you don't have Copilot access yet, you can sign up for the [Copilot Free plan](https://github.com/features/copilot/plans) to get a monthly allowance of inline suggestions and AI credits. + +> [!IMPORTANT] +> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. ## Assign work to Copilot cloud agent in VS Code @@ -274,7 +277,7 @@ You can monitor progress through the session logs accessible from the pull reque ### What security protections does Copilot cloud agent have? -Copilot cloud agent includes built-in security protections and operates within GitHub's security framework. For detailed information about security measures, permissions, and branch protection compatibility, see the [GitHub Copilot cloud agent security documentation](https://docs.github.com/en/copilot/concepts/about-copilot-coding-agent#built-in-security-protections). +Copilot cloud agent includes built-in security protections and operates within GitHub's security framework. For detailed information about security measures, permissions, and branch protection compatibility, see the [GitHub Copilot cloud agent security documentation](https://docs.github.com/en/copilot/concepts/agents/cloud-agent/risks-and-mitigations). ### Can I extend Copilot cloud agent with external tools? diff --git a/docs/copilot/customization/hooks.md b/docs/copilot/customization/hooks.md index a99fcf2485..6859c15103 100644 --- a/docs/copilot/customization/hooks.md +++ b/docs/copilot/customization/hooks.md @@ -449,7 +449,7 @@ The `Stop` hook can prevent the agent from stopping: | `reason` | string | Required when decision is `"block"`. Tells the agent why it should continue. | > [!IMPORTANT] -> When a `Stop` hook blocks the agent from stopping, the agent continues running and the additional turns consume [premium requests](https://docs.github.com/en/copilot/managing-copilot/monitoring-usage-and-entitlements/about-premium-requests). Always check the `stop_hook_active` field to prevent the agent from running indefinitely. +> When a `Stop` hook blocks the agent from stopping, the agent continues running and the additional turns consume [AI credits](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals). Always check the `stop_hook_active` field to prevent the agent from running indefinitely. ## SubagentStart diff --git a/docs/copilot/customization/language-models.md b/docs/copilot/customization/language-models.md index 6ae9f95a56..d54dce7575 100644 --- a/docs/copilot/customization/language-models.md +++ b/docs/copilot/customization/language-models.md @@ -42,6 +42,9 @@ Some models support configurable thinking effort, which controls how much reason By default, VS Code sets recommended effort levels and has adaptive reasoning enabled, where the model dynamically determines how much to think based on the complexity of each request. For most use cases, the defaults work well. +> [!TIP] +> Higher thinking effort produces more thinking tokens, which increases [AI credit](/docs/copilot/concepts/language-models.md#ai-credits-and-model-costs) consumption. Only increase thinking effort for genuinely complex tasks. Learn more about [optimizing AI credit usage](/docs/copilot/guides/optimize-usage.md). + To configure the thinking effort: 1. Open the model picker in the chat input field and select a reasoning model. @@ -68,9 +71,6 @@ To use auto model selection, select **Auto** from the model picker in chat. You ![Screenshot of a chat response, showing the selected model on hover.](../images/language-models/chat-response-selected-model.png) -> [!IMPORTANT] -> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, and student plans are temporarily paused. Additionally, we are tightening weekly usage limits. If you hit a weekly limit and you have premium requests remaining, you can continue using Copilot with auto model selection. See [GitHub Copilot usage limits](https://docs.github.com/copilot/concepts/usage-limits). - ## Manage language models You can use the language models editor to view all available models, choose which models are shown in the model picker, and add more models by adding from built-in providers or from extension-provided model providers. diff --git a/docs/copilot/faq.md b/docs/copilot/faq.md index b55b849f2f..b389431d07 100644 --- a/docs/copilot/faq.md +++ b/docs/copilot/faq.md @@ -16,14 +16,14 @@ There are different ways to get access to GitHub Copilot: | Type of User | Description | |--------------------------------|-------------| -| Individual | | +| Individual | | | Organization/Enterprise member | | ### What's the advantage of signing in with a GitHub account? Signing in with a GitHub account that has access to GitHub Copilot has the following benefits: -* [Increased monthly limit of chat interactions](https://docs.github.com/en/copilot/get-started/plans#comparing-copilot-plans) +* [Higher monthly AI credits allowance](https://docs.github.com/en/copilot/get-started/plans#comparing-copilot-plans) * [Access to premium language models in chat](https://docs.github.com/en/copilot/reference/ai-models/supported-models#supported-ai-models-per-copilot-plan) beyond auto model selection * [Bring your own model keys](/docs/copilot/customization/language-models.md#bring-your-own-language-model-key) (BYOK) to access more models * [Remote repository indexing and semantic code search](/docs/copilot/reference/workspace-context.md#remote-index) @@ -37,22 +37,22 @@ Depending on your Copilot plan, you might have different levels of access and li You can view the current Copilot usage in the Copilot status dashboard, available through the VS Code Status Bar. The dashboard shows the following information: -- **Inline suggestions**: The percentage of inline suggestions quota you have used in the current month. -- **Chat messages**: The percentage of chat requests quota you have used in the current month. -- **Premium requests**: The percentage of premium requests quota you have used in the current month. -- **Premium requests overage**: The number of overage premium requests you have used in the current month. +* **Inline suggestions**: The percentage of inline suggestions quota you have used in the current month. Paid plans have an unlimited quota for inline suggestions. +* **AI credits**: The percentage of your monthly AI credits allowance you have used in the current month. -Visit the GitHub Copilot documentation for more information about [monitoring usage and entitlements](https://docs.github.com/en/copilot/managing-copilot/monitoring-usage-and-entitlements/monitoring-your-copilot-usage-and-entitlements). +Visit the GitHub Copilot documentation for more information about [monitoring usage and entitlements](https://docs.github.com/en/copilot/managing-copilot/monitoring-usage-and-entitlements/monitoring-your-copilot-usage-and-entitlements). For tips on reducing credit consumption, see [optimize AI credit usage](/docs/copilot/guides/optimize-usage.md). -### I reached my inline suggestions or chat interactions limit +### I reached my inline suggestions or AI credits limit -Your limit of inline suggestions and chat interactions is reset every month. If you've only reached the chat interactions limit, you can still use inline suggestions. Similarly, if you've reached the limit for inline suggestions, you can still use chat. +Your inline suggestions allowance and AI credits allowance reset every month. If you've only reached the AI credits limit, you can still use inline suggestions. Similarly, if you've reached the limit for inline suggestions, you can still use chat. -For users on Copilot Free, to access more inline suggestions and chat interactions, you can sign up for a [paid plan](https://docs.github.com/en/copilot/concepts/billing/individual-plans) directly from VS Code. Alternatively, you can wait until the next month to continue using Copilot for free. +For users on Copilot Free, to access more inline suggestions and AI credits, you can sign up for a [paid plan](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals) directly from VS Code. Alternatively, you can wait until the next month to continue using Copilot for free. -![Visual indicators in Chat view, Status Bar, and title bar that you reached a limit for Copilot chat messages.](images/faq/copilot-chat-limit-reached.png) + -If you're on a paid plan and use all of your premium requests, you can still use Copilot with one of the included models for the rest of the month. You can also request additional premium requests beyond your plan's limit. Learn more about [getting additional premium requests](https://docs.github.com/en/copilot/concepts/billing/copilot-requests#what-if-i-run-out-of-premium-requests) in the GitHub Copilot documentation. +If you're on a paid plan and exhaust your AI credits, you can set a budget for additional usage and keep working, or wait until the next monthly cycle when your allowance resets. Learn more about [what happens if you exceed your included AI credits](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals#what-happens-if-i-exceed-my-included-ai-credits) in the GitHub Copilot documentation. + +For tips on reducing credit consumption, see [optimize AI credit usage](/docs/copilot/guides/optimize-usage.md). ### My Copilot subscription is not detected in VS Code @@ -118,7 +118,7 @@ Alternatively, use the `setting(github.copilot.enable)` and `setting(github.copi - Verify that [GitHub Copilot is not disabled](#how-do-i-enable-or-disable-inline-suggestions) globally or for this language - Verify that your [GitHub Copilot subscription is active and detected](#my-copilot-subscription-is-not-detected-in-vs-code) - Verify that your [network settings](#network-and-firewall-configuration-for-copilot) are configured to allow connectivity to GitHub Copilot. -- Verify that you have not reached the limit of inline suggestions for the month with the [Copilot Free plan](https://docs.github.com/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/about-github-copilot-free). +- Verify that you have not reached the inline suggestions limit for the month with the [Copilot Free plan](https://docs.github.com/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/about-github-copilot-free). ## Chat @@ -129,7 +129,7 @@ Verify the following requirements to ensure Chat features work in Visual Studio - Make sure you are on the latest version of Visual Studio Code (run **Code: Check for Updates**). - Make sure you have the latest version of both the [GitHub Copilot](https://marketplace.visualstudio.com/items?itemName=GitHub.copilot) and [GitHub Copilot Chat](https://marketplace.visualstudio.com/items?itemName=GitHub.copilot-chat) extensions. - Your GitHub account that is signed into VS Code must have an active Copilot subscription. Check your [Copilot subscription](https://github.com/settings/copilot). -- Verify that you have not reached your limit of chat interactions for the month with the [Copilot Free plan](https://docs.github.com/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/about-github-copilot-free). +- Verify that you have not reached your AI credits limit for the month with the [Copilot Free plan](https://docs.github.com/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/about-github-copilot-free). ### Agents are not available in chat @@ -149,7 +149,7 @@ Yes. Organization administrators can manage Copilot through [enterprise AI setti ### Are agents usage-limited? -Agents use premium requests from your Copilot plan. Paid plans include a monthly allocation of premium requests, and you can request additional capacity. You can run multiple agent sessions in parallel across local, background, and cloud environments. Users on the free plan have a monthly limit of chat interactions. See [GitHub Copilot plans](https://docs.github.com/en/copilot/get-started/plans) for details. +Agents consume AI credits from your Copilot plan. Paid plans include a monthly AI credits allowance, and you can set a budget for additional usage if needed. You can run multiple agent sessions in parallel across local, background, and cloud environments. Users on the free plan have a monthly AI credits allowance. Learn more about [usage-based billing](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals) and [GitHub Copilot plans](https://docs.github.com/en/copilot/get-started/plans). ### Not all models are available in the language model picker diff --git a/docs/copilot/getting-started.md b/docs/copilot/getting-started.md index c539ff805c..b5305a63e0 100644 --- a/docs/copilot/getting-started.md +++ b/docs/copilot/getting-started.md @@ -24,10 +24,10 @@ Use chat in VS Code to generate the sample application in one go. * Access to GitHub Copilot. Follow these steps to [Set up GitHub Copilot in VS Code](/docs/copilot/setup.md). > [!TIP] - > If you don't have a Copilot subscription, you can sign up to use Copilot for free directly from within VS Code and get a monthly limit of inline suggestions and chat interactions. + > If you don't have a Copilot subscription, you can sign up to use Copilot for free directly from within VS Code and get a monthly allowance of inline suggestions and AI credits. > [!IMPORTANT] - > **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, and student plans are temporarily paused. Additionally, we are tightening weekly usage limits. See [GitHub Copilot usage limits](https://docs.github.com/copilot/concepts/usage-limits). + > **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. ## Step 1: Experience inline suggestions diff --git a/docs/copilot/guides/context-engineering-guide.md b/docs/copilot/guides/context-engineering-guide.md index 64fde37597..513fc2bb8c 100644 --- a/docs/copilot/guides/context-engineering-guide.md +++ b/docs/copilot/guides/context-engineering-guide.md @@ -247,6 +247,8 @@ Following these best practices helps you establish a sustainable and effective c **Maintain context isolation**: Keep different types of work (planning, coding, testing, debugging) in separate chat sessions to prevent context mixing and confusion. +**Be mindful of credit consumption**: More context files, larger instruction sets, and complex agent chains all increase token usage and [AI credit](/docs/copilot/concepts/language-models.md#ai-credits-and-model-costs) consumption. Start with concise context and expand only when needed. For more tips, see [optimize AI credit usage](/docs/copilot/guides/optimize-usage.md). + ### Documentation strategies **Create living documents**: Treat your custom instructions, custom agents, and templates as evolving resources. Refine them based on observed AI mistakes or shortcomings. @@ -269,6 +271,8 @@ Following these best practices helps you establish a sustainable and effective c **Version your context**: Use git to track changes to your context engineering setup, allowing you to revert problematic changes and understand what works best. +**Verify cache performance**: Use the [Agent Debug Logs](/docs/copilot/chat/chat-debug-view.md) to check prompt cache hit rates and token usage. Good cache performance means your context setup is structured in a way that the model provider can reuse previous request prefixes, reducing latency and token costs. + ### Anti-patterns to avoid **Context dumping**: Avoid providing excessive, unfocused information that doesn't directly help with decision-making. @@ -279,6 +283,8 @@ Following these best practices helps you establish a sustainable and effective c **One-size-fits-all**: Different team members or project phases may need different context configurations. Be flexible in your approach. +**Over-engineering agent chains**: Deeply nested subagent workflows and excessive tool calls multiply token usage and [credit consumption](/docs/copilot/concepts/language-models.md#ai-credits-and-model-costs). Keep agent chains as shallow as practical and limit tools to what each agent actually needs. + ### Measuring success A successful context engineering setup should result in: diff --git a/docs/copilot/guides/debug-with-copilot.md b/docs/copilot/guides/debug-with-copilot.md index a0e511676f..4fa39f4837 100644 --- a/docs/copilot/guides/debug-with-copilot.md +++ b/docs/copilot/guides/debug-with-copilot.md @@ -15,7 +15,10 @@ Copilot can help with the following debugging tasks: * **Fix issues**: receive suggestions for fixing issues discovered during debugging. > [!TIP] -> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly limit of inline suggestions and chat interactions. +> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly allowance of inline suggestions and AI credits. + +> [!IMPORTANT] +> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. ## Set up debug configuration with Copilot diff --git a/docs/copilot/guides/optimize-usage.md b/docs/copilot/guides/optimize-usage.md new file mode 100644 index 0000000000..0030be9b3b --- /dev/null +++ b/docs/copilot/guides/optimize-usage.md @@ -0,0 +1,106 @@ +--- +ContentId: d4e5f6a7-8b9c-0d1e-2f3a-4b5c6d7e8f9a +DateApproved: 5/20/2026 +MetaDescription: Tips to optimize your AI credit usage in VS Code by choosing efficient models, managing context, and monitoring consumption. +MetaSocialImage: ../images/shared/github-copilot-social.png +--- +# Optimize AI credit usage in VS Code + +Each GitHub Copilot plan includes a monthly allowance of [AI credits](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals). Different actions consume credits at different rates, based on the model and the number of tokens processed. This guide covers practical ways to get the most out of your AI credits in Visual Studio Code. + +## Choose efficient models + +More capable models cost more per token, while lighter models extend your usage further. Match the model to the complexity of the task: + +* Use **lighter models** for quick edits, boilerplate generation, and straightforward questions. +* Use **reasoning models** for complex refactoring, architectural decisions, and multi-step debugging. +* Use **auto model selection** to let VS Code route each request to an efficient model that balances quality and cost. +* Use [custom agents](/docs/copilot/customization/custom-agents.md) with a preferred model to route specific subtasks to specialized, cost-effective models. When you invoke a custom agent as a subagent, it uses its own configured model instead of the chat session's model. + +The model picker in chat shows cost details in the hover menu, including cost per token type and a generic cost tier label (Low, Medium, High). Use this information to make informed choices. + +For more information, see [choosing and configuring language models](/docs/copilot/customization/language-models.md) and [best practices for model selection](/docs/copilot/best-practices.md#choose-the-right-model). + +## Plan before you implement + +Jumping straight into code generation can lead to wasted effort if the approach is wrong. It also requires a model with enough reasoning capability throughout the process, which can consume more credits. Instead, separate the planning and implementation phases. This allows you to use a reasoning model for planning, and then switch to a faster, more efficient model for implementation once the plan is solidified. + +1. Use the [Plan agent](/docs/copilot/agents/planning.md) to research the task and create a structured implementation plan. +1. Review and refine the plan before the agent writes any code. +1. Hand off the approved plan to an implementation agent using a faster model to execute the plan. + +This workflow ensures the agent understands the requirements before it starts generating code, reducing back-and-forth and rework. + +For more information, see [plan first, then implement](/docs/copilot/best-practices.md#plan-first-then-implement). + +## Use thinking effort defaults + +Thinking effort controls how much reasoning a model applies to each request. Higher effort levels produce more thinking tokens, which increases both latency and credit consumption. VS Code sets default effort levels based on evaluations and has adaptive reasoning enabled, where the model dynamically decides how much to think based on the complexity of each request. + +For most tasks, the defaults are sufficient. Only increase thinking effort for genuinely complex problems like architectural planning or multi-step debugging. + +For more information, see [configure thinking effort](/docs/copilot/customization/language-models.md#configure-thinking-effort). + +## Start new chats for new tasks + +As a conversation grows, it accumulates context from previous messages, tool outputs, and file contents. When you switch to an unrelated task in the same session, the model still processes all that irrelevant history, which consumes tokens without improving results. + +Start a [new chat session](/docs/copilot/chat/chat-sessions.md) (`kb(workbench.action.chat.newChat)`) when you change topics. This gives the model a clean context window focused on the current task. + +## Leverage forking + +When you want to explore an alternative approach or ask a side question, [fork the conversation](/docs/copilot/chat/chat-sessions.md#fork-a-chat-session) instead of re-prompting from scratch. Forking creates a new session that inherits the existing conversation history, so you don't need to re-establish context. + +* Type `/fork` in the chat input to fork the entire session up to the current message. +* Hover over a previous message and select **Fork Conversation** to fork from a specific checkpoint. + +## Disable unneeded tools and MCP servers + +Every tool call produces output that consumes space in the [context window](/docs/copilot/concepts/language-models.md#context-window) and contributes to credit consumption. Disable tools you don't need for the current task to prevent unnecessary calls. + +* Use the **Configure Tools** button in the chat input field to enable or disable individual tools or entire MCP servers for the current request. +* In [custom agents](/docs/copilot/customization/custom-agents.md), specify only the tools the agent needs via the `tools` property. This prevents the agent from calling tools that aren't relevant to its workflow. + +For more information, see [control which tools are available](/docs/copilot/concepts/tools.md#control-which-tools-are-available). + +## Exclude files from Copilot context + +Large generated files, build outputs, or irrelevant directories can be included in the AI context, increasing token usage without adding value. Exclude these files to reduce unnecessary context: + +* Use a `.gitignore` file to exclude files from the [workspace index](/docs/copilot/reference/workspace-context.md#what-content-is-included-in-the-semantic-index). The workspace index respects `.gitignore` rules. +* Use the `setting(files.exclude)` setting to hide files from VS Code entirely, which also excludes them from the index. + +For more information, see [workspace context](/docs/copilot/reference/workspace-context.md). + +## Manage context with compaction + +When a conversation grows long, use `/compact` to summarize older parts of the conversation and reclaim context window space. You can optionally add instructions to guide the summary, for example `/compact focus on the API design decisions`. + +For more information, see [context compaction](/docs/copilot/chat/copilot-chat-context.md#context-compaction). + +## Monitor your usage + +You can view your current Copilot usage in the Copilot status dashboard, available through the VS Code Status Bar. The dashboard shows the percentage of your monthly allowance you have used for AI credits (and inline suggestions for the Copilot Free plan). + + + +Visit the GitHub Copilot documentation for more information about [monitoring usage and entitlements](https://docs.github.com/en/copilot/managing-copilot/monitoring-usage-and-entitlements/monitoring-your-copilot-usage-and-entitlements). + +You can also run the `/chronicle:cost-tips` command in any chat session to get personalized recommendations for optimizing your AI credit usage based on your recent activity. Learn more about [session insights and the chronicle command](/docs/copilot/chat/session-insights.md). + +## Inspect token usage and caching + +Use the [Agent Debug Logs](/docs/copilot/chat/chat-debug-view.md) to understand what is consuming credits in a session: + +* The **Summary view** shows aggregate token usage for the session, including total tool calls and overall duration. +* The **Cache Explorer view** shows prompt cache hit rates and how many input tokens were reused. Prompt caching lets model providers reuse the prefix of a request that matches a previous one, which reduces latency and token costs. + +Reviewing these logs helps you identify sessions or workflows that consume more tokens than expected, so you can adjust your approach. + +## Related content + +* [AI credits and model costs](/docs/copilot/concepts/language-models.md#ai-credits-and-model-costs) +* [Choose and configure language models](/docs/copilot/customization/language-models.md) +* [Best practices for GitHub Copilot](/docs/copilot/best-practices.md) +* [GitHub Copilot plans](https://docs.github.com/en/copilot/get-started/plans) +* [Usage-based billing](https://docs.github.com/en/copilot/concepts/billing/usage-based-billing-for-individuals) diff --git a/docs/copilot/guides/test-with-copilot.md b/docs/copilot/guides/test-with-copilot.md index 7efe1bc622..516fa8435b 100644 --- a/docs/copilot/guides/test-with-copilot.md +++ b/docs/copilot/guides/test-with-copilot.md @@ -17,7 +17,10 @@ Copilot can help with the following testing tasks: * **Maintain consistency**: personalize Copilot to generate tests that follow your project's coding practices. > [!TIP] -> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly limit of inline suggestions and chat interactions. +> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly allowance of inline suggestions and AI credits. + +> [!IMPORTANT] +> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. ## Set up your testing framework diff --git a/docs/copilot/overview.md b/docs/copilot/overview.md index b26ff0d3e2..543354e2c0 100644 --- a/docs/copilot/overview.md +++ b/docs/copilot/overview.md @@ -108,6 +108,9 @@ Agents handle coding tasks end-to-end, from a single file change to a full featu 1. Choose a sign-in method and follow the prompts. If you don't have a Copilot subscription yet, you are signed up for the [Copilot Free plan](https://docs.github.com/en/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/managing-copilot-free/about-github-copilot-free). + > [!IMPORTANT] + > **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. + ### Step 2: Start your first agent session 1. Open the **Chat** view (`kb(workbench.action.chat.open)`). @@ -175,10 +178,7 @@ To learn more about Copilot's security, privacy, compliance, and transparency, s ## Pricing -> [!IMPORTANT] -> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, and student plans are temporarily paused. Additionally, we are tightening weekly usage limits. See [GitHub Copilot usage limits](https://docs.github.com/copilot/concepts/usage-limits). - -You can start using GitHub Copilot for free with monthly limits on inline suggestions and chat interactions. For more extensive usage, you can choose from various paid plans. +You can start using GitHub Copilot for free with a monthly allowance of inline suggestions and AI credits. Paid plans offer higher AI credits allowances for more extensive usage. [View detailed GitHub Copilot pricing](https://docs.github.com/en/copilot/get-started/plans) diff --git a/docs/copilot/reference/copilot-settings.md b/docs/copilot/reference/copilot-settings.md index ad4bd25077..fa70252831 100644 --- a/docs/copilot/reference/copilot-settings.md +++ b/docs/copilot/reference/copilot-settings.md @@ -11,10 +11,10 @@ This article lists the configuration settings for GitHub Copilot in Visual Studi The team is continuously working on improving Copilot in VS Code and adding new features. Some features are still experimental. Try them out and share your feedback in [our issues](https://github.com/microsoft/vscode/issues). Get more info about the [feature lifecycle in VS Code](/docs/configure/settings.md#feature-lifecycle). > [!TIP] -> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly limit of inline suggestions and chat interactions. +> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly allowance of inline suggestions and AI credits. > [!IMPORTANT] -> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, and student plans are temporarily paused. Additionally, we are tightening weekly usage limits. See [GitHub Copilot usage limits](https://docs.github.com/copilot/concepts/usage-limits). +> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. ## General settings diff --git a/docs/copilot/reference/copilot-vscode-features.md b/docs/copilot/reference/copilot-vscode-features.md index 729d337ee9..d73e0eb397 100644 --- a/docs/copilot/reference/copilot-vscode-features.md +++ b/docs/copilot/reference/copilot-vscode-features.md @@ -9,7 +9,10 @@ MetaSocialImage: ../images/shared/github-copilot-social.png GitHub Copilot in Visual Studio Code provides autonomous agents, inline suggestions, chat, and smart actions. Agents plan, implement, and verify changes across multiple files and run in parallel, locally, in the background, or in the cloud. Choose from multiple AI models, connect to external tools with MCP, and customize agents for your team's workflows. This cheat sheet gives you a quick overview of all features. > [!TIP] -> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly limit of inline suggestions and chat interactions. +> If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly allowance of inline suggestions and AI credits. + +> [!IMPORTANT] +> **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. ## Essential keyboard shortcuts diff --git a/docs/copilot/setup-simplified.md b/docs/copilot/setup-simplified.md index 782a51ca72..d6f44a9a7b 100644 --- a/docs/copilot/setup-simplified.md +++ b/docs/copilot/setup-simplified.md @@ -31,6 +31,9 @@ To use Copilot in VS Code, you need access to a GitHub Copilot subscription. You If you don't have a Copilot subscription yet, you'll be signed up for the [Copilot Free plan](https://docs.github.com/en/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/managing-copilot-free/about-github-copilot-free). + > [!IMPORTANT] + > **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. + > [!IMPORTANT] > Telemetry in your free version of GitHub Copilot is currently enabled. By default, code suggestions that match public code, including code references in the VS Code and experience, are allowed. You can opt out of telemetry data collection by disabling telemetry in VS Code by setting `setting(telemetry.telemetryLevel)` to `off`, or you can adjust both telemetry and code suggestion settings in [Copilot Settings](https://github.com/settings/copilot). diff --git a/docs/copilot/setup.md b/docs/copilot/setup.md index bcc9f52e87..b4d4918aec 100644 --- a/docs/copilot/setup.md +++ b/docs/copilot/setup.md @@ -25,10 +25,10 @@ Follow these steps to get started with Copilot in VS Code: * If you already have a Copilot subscription for your account, VS Code will use that subscription. - * If you don't have a Copilot subscription yet, you'll be signed up for the [Copilot Free plan](https://docs.github.com/en/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/managing-copilot-free/about-github-copilot-free) and get a monthly limit of inline suggestions and chat interactions. Learn more about the different [GitHub Copilot plans](https://docs.github.com/en/copilot/get-started/plans). + * If you don't have a Copilot subscription yet, you'll be signed up for the [Copilot Free plan](https://docs.github.com/en/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/managing-copilot-free/about-github-copilot-free) and get a monthly allowance of inline suggestions and AI credits. Learn more about the different [GitHub Copilot plans](https://docs.github.com/en/copilot/get-started/plans). > [!IMPORTANT] - > **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, and student plans are temporarily paused. Additionally, we are tightening weekly usage limits. See [GitHub Copilot usage limits](https://docs.github.com/copilot/concepts/usage-limits). + > **Starting April 20, 2026**, new sign-ups for Copilot Pro, Copilot Pro+, Max, and Student plans are temporarily paused. 1. Start using Copilot in VS Code! diff --git a/docs/debugtest/testing.md b/docs/debugtest/testing.md index d933606c87..96cfe10821 100644 --- a/docs/debugtest/testing.md +++ b/docs/debugtest/testing.md @@ -10,7 +10,7 @@ Visual Studio Code provides a rich set of features for testing your code. You ca In this article, you'll learn how to start with testing in VS Code, find popular testing extensions, and explore the testing features. You'll also learn how Copilot in VS Code can help you write tests faster and can assist you in fixing failing tests. > [!TIP] -> If you don't have a Copilot subscription yet, use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup). You'll get a monthly limit of inline suggestions and chat interactions. +> If you don't have a Copilot subscription yet, use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup). You'll get a monthly allowance of inline suggestions and AI credits. diff --git a/docs/editing/intellisense.md b/docs/editing/intellisense.md index 5ae39f62f8..6795c05d6a 100644 --- a/docs/editing/intellisense.md +++ b/docs/editing/intellisense.md @@ -183,7 +183,7 @@ To get started: 1. Discover the key functionality with our [Copilot quickstart](/docs/copilot/getting-started.md). > [!TIP] -> If you don't have a Copilot subscription yet, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly limit of inline suggestions and chat interactions. +> If you don't have a Copilot subscription yet, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly allowance of inline suggestions and AI credits. ## Troubleshooting diff --git a/docs/getstarted/getting-started.md b/docs/getstarted/getting-started.md index 1f33b23e88..f551805707 100644 --- a/docs/getstarted/getting-started.md +++ b/docs/getstarted/getting-started.md @@ -31,7 +31,7 @@ Learn about the key features of Visual Studio Code in our introduction video. * Install [Node.js](https://nodejs.org/) (for running and debugging JavaScript) > [!TIP] -> If you don't have a Copilot subscription yet, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly limit of completions and chat interactions. +> If you don't have a Copilot subscription yet, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly allowance of inline suggestions and AI credits. ## Open a folder in VS Code @@ -172,7 +172,7 @@ Let's use agents to build a recipe list web app from a single prompt. ``` > [!NOTE] - > If you haven't set up GitHub Copilot yet, you are prompted to sign in to your GitHub account and set up Copilot before you can send the prompt. If you don't have a Copilot subscription, you're associated with a free account that gives you a monthly limit of completions and chat interactions. + > If you haven't set up GitHub Copilot yet, you are prompted to sign in to your GitHub account and set up Copilot before you can send the prompt. If you don't have a Copilot subscription, you're associated with a free account that gives you a monthly allowance of inline suggestions and AI credits. 1. Press `kbstyle(Enter)` to send the prompt. diff --git a/docs/setup/setup-overview.md b/docs/setup/setup-overview.md index 6934ef054f..5dd8222950 100644 --- a/docs/setup/setup-overview.md +++ b/docs/setup/setup-overview.md @@ -53,7 +53,7 @@ After you install VS Code, finish setup for your development workflow: * [Start the VS Code tutorial](/docs/getstarted/getting-started.md) for a hands-on tour of the user interface and key features. > [!TIP] -> New Copilot users can start with the [Copilot Free plan](https://github.com/github-copilot/signup), which includes a monthly limit of inline suggestions and chat interactions. +> New Copilot users can start with the [Copilot Free plan](https://github.com/github-copilot/signup), which includes a monthly allowance of inline suggestions and AI credits. ## Update cadence diff --git a/docs/supporting/faq.md b/docs/supporting/faq.md index 2113588dd2..59716a49fe 100644 --- a/docs/supporting/faq.md +++ b/docs/supporting/faq.md @@ -89,7 +89,7 @@ Visual Studio Code is a streamlined code editor with support for development ope Yes, VS Code is free for private or commercial use. See the [product license](https://code.visualstudio.com/license) for details. -If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly limit of inline suggestions and chat interactions. +If you don't yet have a Copilot subscription, you can use Copilot for free by signing up for the [Copilot Free plan](https://github.com/github-copilot/signup) and get a monthly allowance of inline suggestions and AI credits. ## Platform support diff --git a/docs/toc.json b/docs/toc.json index 1929460de9..73ab4295c2 100644 --- a/docs/toc.json +++ b/docs/toc.json @@ -110,6 +110,7 @@ "noCollapse": false, "topics": [ ["Context Engineering", "/docs/copilot/guides/context-engineering-guide"], + ["Optimize AI Credit Usage", "/docs/copilot/guides/optimize-usage"], ["Customize AI", "/docs/copilot/guides/customize-copilot-guide"], ["Test-Driven Development", "/docs/copilot/guides/test-driven-development-guide"], ["Edit Notebooks with AI", "/docs/copilot/guides/notebooks-with-ai"],