Ulugbek Abdullaev
3073c2bb48
* nes: fold currentFile budgeting into the global budget cascade Under the opt-in global budget experiment, the current file now draws its clip budget from the shared pool (its `shares.currentFile` slice of `totalTokens`) and donates whatever it does not use to the cascade as the initial surplus. When the global budget is disabled (prod default) behavior is byte-identical, and the new defaults (totalTokens 8000, shares in eighths) reproduce today's per-part `maxTokens` caps exactly. - xtabPromptOptions: add `GlobalBudgetSharePart`, `currentFileBudget()` and `validate()`; grow `shares` to include `currentFile`; bump `DEFAULT_TOTAL_TOKENS` to 8000 and rebalance `DEFAULT_SHARES`. - promptCrafting: seed the cascade's initial surplus from the current file's leftover budget; delegate validation to the namespace helper. - xtabProvider: size and clip the current file from the pool and compute the surplus, gated on `globalBudget` being defined. - Tests: volume-neutral invariant, `currentFileBudget`/`validate` units, and provider-level regression + new-behavior coverage. - Docs: rewrite globalBudgetCascade.md for the seeded-surplus design. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * nes: collapse global-budget settings into a single exp-driven JSON string Replace the two experiment-driven global-budget settings (globalBudget.enabled boolean + globalBudget.totalTokens number) with a single JSON-encoded string setting, modelled after modelConfigurationString, that defines totalTokens, order, and shares together. - configurationService: remove InlineEditsXtabGlobalBudgetEnabled and InlineEditsXtabGlobalBudgetTotalTokens; add InlineEditsXtabGlobalBudget (string | undefined, ExperimentBased, default undefined). - xtabPromptOptions: add GlobalBudgetOptions.VALIDATOR (all top-level fields optional; shares must be complete when present) and a pure GlobalBudgetOptions.fromConfigString(): Result<GlobalBudgetOptions, string> that JSON-parses, structurally validates, merges over the defaults, then runs the semantic validate(). Never throws. - xtabProvider: inject ITelemetryService; resolve the budget via getGlobalBudget(), returning undefined (disabled, identical to prod) when the string is unset/empty/invalid and emitting incorrectNesGlobalBudgetConfig telemetry on parse/validation failure. - Tests: migrate the provider global-budget tests to the JSON string and add fromConfigString unit tests. - Docs: rewrite the globalBudgetCascade.md Wiring section and migration note. No regression: an unset string keeps the byte-identical legacy path. '{}' enables the budget with the volume-neutral defaults; {"totalTokens":N} only overrides the pool size. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> * nes: clip the current file last under a global budget to reuse cascade leftover Under a global budget the current file is now clipped LAST, sized to its base share plus whatever the budget cascade left unused (`currentFileBudget + finalSurplus`), so it trims less and reuses leftover budget. The cascade runs first (seeded with 0, the current file never donates) and is threaded into `getUserPrompt` via `precomputedCascade` so it renders exactly once. This replaces the earlier two-mode design: the opt-in `reuseLeftoverForCurrentFile` flag and the seeded-surplus "donate-forward" path are dropped, along with all `currentFileBudgetSurplus`/`initialSurplus` threading. Clip-last is now the single behavior under a global budget. The validator hardening (rejecting non-finite or negative `totalTokens`/shares) is kept. No production regression: when `globalBudget` is undefined the current file is still clipped to its own `currentFile.maxTokens` with the legacy await ordering, byte-identical to before. The global budget remains experiment-gated and off in prod. Tests and globalBudgetCascade.md updated for the clip-last-only behavior. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * nes: address review — restore nLinesOfCurrentFileInPrompt telemetry timing - xtabProvider: record setNLinesOfCurrentFileInPrompt inside both budget branches. In the legacy/prod branch the clip happens before the context-gathering awaits, so the telemetry call is moved back there to match prod timing exactly (it is still emitted when a request is cancelled mid-gathering). The clip-last branch records it after the cascade, as the clip is inherently last there. - xtabPromptOptions: fix two stale JSDoc blocks that still described the removed donate-forward behavior; describe clip-last instead. - globalBudgetCascade.md: correct the conservation bound to T·(Σ shares) and document the share-sum tolerance (over-allocation ≤ ~1e-3·T). - promptCrafting.spec: add a cascade test asserting finalSurplus shrinks as the cascade consumes budget (current file reuses less leftover). Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * nes: fix stale DEFAULT_ORDER doc comment to say clip-last Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * nes: rename clipCurrentFileToBudget param to overriddenMaxTokens Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * nes: extract current-file clip + context gathering into a method Pulls the ~55-line global-budget/legacy if-else out of doGetNextEditWithSelection into a private gatherContextAndClipCurrentFile method returning Result<{ clippedTaggedCurrentDoc, areaAroundCodeToEdit, precomputedCascade, langCtx, neighborSnippets }, NoNextEditReason>. Behavior, clip-first/clip-last ordering, and nLinesOfCurrentFileInPrompt telemetry timing are unchanged. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> * nes: recalibrate global-budget defaults to merged currentFile cap (1500) main (#322382) lowered currentFile.maxTokens 2000->1500, which broke the global-budget 'volume-neutral defaults' invariant (floor(total*share) must equal each part's legacy cap). Recalibrate DEFAULT_SHARES to cap/7500 and set DEFAULT_TOTAL_TOKENS to 7500 (the sum of the merged per-part caps: 1500 + 2000 + 2000 + 1000 + 1000), so shares still sum to exactly 1 and every part's base allocation reproduces its cap. finalSurplus stays 6000 (7500 - 1500). Update dependent specs (literal 8000 -> DEFAULT_TOTAL_TOKENS, stale 2000 cap comments -> 1500) and the design doc (defaults table, worked examples, effective caps, ordering caveat, migration note) for T=7500 and currentFile base 1500. Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com> --------- Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
GitHub Copilot - Your autonomous AI peer programmer
GitHub Copilot is an AI peer programming tool that transforms how you write code in Visual Studio Code.
GitHub Copilot agents handle complete coding tasks end-to-end, autonomously planning work, editing files, running commands, and self-correcting when they hit errors. You can also leverage inline suggestions for quick coding assistance and inline chat for precise, focused edits directly in the editor.
Sign up for GitHub Copilot Free!
Getting access to GitHub Copilot
Sign up for GitHub Copilot Free, or request access from your enterprise admin.
To access GitHub Copilot, an active GitHub Copilot subscription is required. You can read more about our business and individual offerings at github.com/features/copilot.
Build with autonomous agents
Let AI agents implement complex features end-to-end. Give an agent a high-level task and it breaks the work into steps, edits multiple files, runs terminal commands, and self-corrects when it hits errors or failing tests. Agents excel at building new features, debugging and fixing failing tests, refactoring codebases, and collaborating via pull requests.
Manage sessions from a central view. Run multiple agent sessions in parallel and track them in one place. Monitor session status, switch between active work, review file changes, and resume where you left off.
Run agents with your preferred harness. Use agents locally in VS Code, in the background via Copilot CLI, or Cloud via Copilot Coding Agent. You can also work with providers like Claude and Codex, and hand tasks off between agent types with context preserved all within the VS Code.
Use agents to plan before you build with the Plan agent, which breaks tasks into structured implementation plans and asks clarifying questions. When your plan is ready, hand it off to an implementation agent to execute it. You can also delegate tasks to cloud agents that create branches, implement changes, and open pull requests for your team to review.
More ways to code with AI
Receive intelligent inline suggestions as you type with ghost text suggestions and next edit suggestions, helping you write code faster. Copilot predicts your next logical change, and you can accept suggestions with the Tab key.
Use inline chat for targeted edits by pressing Ctrl+I/Cmd+I to open a chat prompt directly in the editor. Describe a change and Copilot suggests edits in place for refactoring methods, adding error handling, or explaining complex algorithms without leaving your editor.
Customize AI for your workflow
Agents work best when they understand your project's conventions and have the right tools. Tailor Copilot so it generates code that fits your codebase from the start.
Project context. Use custom instructions to specify project-wide or task-specific context and coding guidelines.
Add specialized capabilities. Teach Copilot specialized capabilities with agent skills or define specialized personas with custom agents.
Connect to external tools and services. Extend agents further with tools from MCP servers and extensions to give Copilot a gateway to external data sources, APIs, or specialized tools.
Supported languages and frameworks
GitHub Copilot works on any language, including Java, PHP, Python, JavaScript, Ruby, Go, C#, or C++. Because it’s been trained on languages in public repositories, it works for most popular languages, libraries and frameworks.
Version compatibility
As Copilot Chat releases in lockstep with VS Code due to its deep UI integration, every new version of Copilot Chat is only compatible with the latest and newest release of VS Code. This means that if you are using an older version of VS Code, you will not be able to use the latest Copilot Chat.
Only the latest Copilot Chat versions will use the latest models provided by the Copilot service, as even minor model upgrades require prompt changes and fixes in the extension.
Privacy and preview terms
By using Copilot Chat you agree to GitHub Copilot chat preview terms. Review the transparency note to understand about usage, limitations and ways to improve Copilot Chat during the technical preview.
Please refer to our Privacy Statement to learn about the data we collect, how we use it, and the controls available to you.
To get the latest security fixes, please use the latest version of the Copilot extension and VS Code.
Resources & next steps
- Sign up for GitHub Copilot Free: Explore Copilot's AI capabilities at no cost before upgrading to a paid plan.
- If you're using Copilot for your business, check out Copilot Business and Copilot Enterprise.
- Copilot Quickstart: Discover the key features of Copilot in VS Code.
- Agents Tutorial: Get started with autonomous agents across different environments.
- VS Code on YouTube: Watch the latest demos and updates on the VS Code channel.
- Frequently Asked Questions: Get answers to commonly asked questions about Copilot in VS Code.
- Provide Feedback: Send us your feedback and feature request to help us make GitHub Copilot better!
Data and telemetry
The GitHub Copilot Extension for Visual Studio Code collects usage data and sends it to Microsoft to help improve our products and services. Read our privacy statement to learn more. This extension respects the telemetry.telemetryLevel setting which you can learn more about at https://code.visualstudio.com/docs/supporting/faq#_how-to-disable-telemetry-reporting.
Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow Microsoft's Trademark & Brand Guidelines. Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos are subject to those third-party's policies.
License
Copyright (c) Microsoft Corporation. All rights reserved.
Licensed under the MIT license.