# GitHub Copilot

An AI coding assistant from GitHub that provides code suggestions, chat assistance, and agent-driven development features.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Gemini 4 Neon in GitHub Copilot

DevFeed: [Gemini 4 Neon in GitHub Copilot](<https://devfeed.tech/articles/gemini-4-neon-in-github-copilot-141431.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-18-gemini-4-neon-in-github-copilot>)

Author: Allison

Published: 2026-11-18T21:49:21Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>)

Tags: [administrator](<https://devfeed.tech/tags/administrator.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [blog](<https://devfeed.tech/tags/blog.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [coding-tasks](<https://devfeed.tech/tags/coding-tasks.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cost](<https://devfeed.tech/tags/cost.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-neon](<https://devfeed.tech/tags/gemini-4-neon.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [google](<https://devfeed.tech/tags/google.md>), [knowledge](<https://devfeed.tech/tags/knowledge.md>), [knowledge-work](<https://devfeed.tech/tags/knowledge-work.md>), [quality](<https://devfeed.tech/tags/quality.md>), [release](<https://devfeed.tech/tags/release.md>), [tool](<https://devfeed.tech/tags/tool.md>), [tool-use](<https://devfeed.tech/tags/tool-use.md>)

### AI overview

Gemini 4 Neon is generally available in GitHub Copilot for Pro+, Max, Business, and Enterprise users, with rollout happening gradually. Google says it approaches Gemini 4 Carbon's quality at a lower token cost per task, responds faster, makes fewer unrequested coding changes, and is less likely to make unsupported claims about code, tools, or test results. It uses provider list pricing under usage-based billing. Users can select it in the model picker across the listed Copilot clients and integrations. Business and Enterprise administrators manage access through Copilot settings; new models are enabled by default unless the global default is off or the model is explicitly disabled.

### Source excerpt

Gemini 4 Neon is now generally available in GitHub Copilot. It is designed for agentic coding, multistep tool use, and knowledge work. According to Google, Gemini 4 Neon delivers quality... The post Gemini 4 Neon in GitHub Copilot appeared first on The GitHub Blog.

## Your coding agent bill doubled. Here's how to fix it.

DevFeed: [Your coding agent bill doubled. Here's how to fix it.](<https://devfeed.tech/articles/your-coding-agent-bill-doubled-here-s-how-to-fix-it-142925.md>)

Original publisher: [Read original article](<https://www.langchain.com/blog/fix-your-coding-agent-bill>)

Author: LangChain Accounts

Published: 2026-11-18T19:33:12Z

Content type: article

Language: en

Sources: [LangChain Blog](<https://devfeed.tech/sources/langchain-blog.md>)

Topics: [codex](<https://devfeed.tech/topics/codex.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [cursor](<https://devfeed.tech/topics/cursor.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>)

Tags: [claude-code](<https://devfeed.tech/tags/claude-code.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cost-management](<https://devfeed.tech/tags/cost-management.md>), [cursor](<https://devfeed.tech/tags/cursor.md>), [engine](<https://devfeed.tech/tags/engine.md>), [gateway](<https://devfeed.tech/tags/gateway.md>), [trace](<https://devfeed.tech/tags/trace.md>)

### AI overview

Coding agent costs become hard to assess when teams use multiple tools that record activity in incompatible formats. The article proposes a cycle of shared visibility, cost comparison, optimization, and spending controls. LangSmith normalizes traces from Claude Code, Codex, Cursor, GitHub Copilot Chat, Pi, and OpenCode, including model usage, tool calls, and subagent activity, so teams can query and compare sessions in one place. Engine analyzes sessions for waste such as repeated context retrieval and suggests changes; LangSmith's LLM Gateway provides user, team, and organization cost caps, with open source model routing described as forthcoming. The article recommends starting with observability and adding optimization and governance as needed. It says teams standardized on one tool with an adequate native dashboard may not need another layer until they adopt a second agent.

### Source excerpt

Learn why coding agent bills spiral out of control -- and how to trace, compare, and govern spend across Claude Code, Cursor, Copilot, and more in one place.

## Customize GitHub Copilot for your team

DevFeed: [Customize GitHub Copilot for your team](<https://devfeed.tech/articles/customize-github-copilot-for-your-team-141430.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-18-customize-github-copilot-for-your-team>)

Author: Allison

Published: 2026-11-18T16:00:13Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [customization](<https://devfeed.tech/tags/customization.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [release](<https://devfeed.tech/tags/release.md>), [team](<https://devfeed.tech/tags/team.md>)

### AI overview

Organization team maintainers and owners can set approved Agent Plugins as optional team defaults in the team's Customize Copilot tab. They can browse plugins in Copilot marketplaces, enterprise marketplaces, and team-added marketplaces, or add a marketplace from a GitHub repository and then enable selected plugins. Defaults apply to direct team members in VS Code, the GitHub Copilot app, and Copilot CLI; child teams do not inherit them. Members may turn plugins off where policy permits. Enterprise and organization policies take precedence, and Copilot clients continue enforcing marketplace allowlists and required or blocked plugin rules. Team customizations are available for Copilot Business and Copilot Enterprise.

### Source excerpt

You can now share the GitHub Copilot plugins your team relies on without asking every member to repeat the same setup. Team customizations are generally available for organization teams. Team... The post Customize GitHub Copilot for your team appeared first on The GitHub Blog.

## Microsoft launches MAI Code 2 models to challenge OpenAI and Anthropic in AI coding

DevFeed: [Microsoft launches MAI Code 2 models to challenge OpenAI and Anthropic in AI coding](<https://devfeed.tech/articles/microsoft-launches-mai-code-2-models-to-challenge-openai-and-anthropic-in-ai-coding-140729.md>)

Original publisher: [Read original article](<https://www.infoworld.com/article/4250152/microsoft-launches-mai-code-2-models-to-challenge-openai-and-anthropic-in-ai-coding.html>)

Author: Nidhi Singal

Published: 2026-11-18T11:43:31Z

Content type: news

Language: en

Sources: [InfoWorld](<https://devfeed.tech/sources/infoworld.md>)

Topics: [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>), [AI in frontend development](<https://devfeed.tech/topics/ai-in-frontend-development.md>), [code security](<https://devfeed.tech/topics/code-security.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-costs](<https://devfeed.tech/tags/ai-costs.md>), [ai-model](<https://devfeed.tech/tags/ai-model.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [artificial-intelligence-development-tools-software-development](<https://devfeed.tech/tags/artificial-intelligence-development-tools-software-development.md>), [azure](<https://devfeed.tech/tags/azure.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [capabilities](<https://devfeed.tech/tags/capabilities.md>), [ceo](<https://devfeed.tech/tags/ceo.md>), [changes](<https://devfeed.tech/tags/changes.md>), [claude](<https://devfeed.tech/tags/claude.md>), [code](<https://devfeed.tech/tags/code.md>), [coding](<https://devfeed.tech/tags/coding.md>), [development-tools](<https://devfeed.tech/tags/development-tools.md>), [language-en](<https://devfeed.tech/tags/language-en.md>), [mai](<https://devfeed.tech/tags/mai.md>), [mai-code-2](<https://devfeed.tech/tags/mai-code-2.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [models](<https://devfeed.tech/tags/models.md>), [openai](<https://devfeed.tech/tags/openai.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [storytype-news](<https://devfeed.tech/tags/storytype-news.md>)

### AI overview

Microsoft's MAI Code 2 targets enterprise coding work such as debugging and multi-file changes; MAI Code 2 Flash is aimed at high-volume explanations, edits and routine fixes. In Microsoft's cited benchmarks, Code 2 averaged 63.2%, below GPT-6.1 Sol (64.1%) and Claude Opus 5.5 (65.3%), while Flash averaged 61%, above GPT-6 Luna (55.1%) and Claude Haiku 5.5 (53.9%) on a different, three-benchmark comparison. Microsoft reports lower average task costs, but those comparisons use 50% promotional pricing; the promotion runs through May 17, 2027 for Code 2, after which token prices double. The excerpt cautions that model fees are only part of software delivery costs, and recommends testing on an organization's own code and tools while tracking cost per merged change, failures and security findings. Microsoft model cards rate both models highly on offensive cyber capabilities, so security and reliability in production also warrant evaluation. The models are not yet tuned for fundamental science research or long-horizon agentic work.

### Source excerpt

Microsoft has launched a pair of AI coding models that it says can compete with offerings from OpenAI and Anthropic, marking its latest effort to build proprietary AI capabilities and reduce reliance on the partners that helped fuel its generative AI push. The two new models, MAI Code 2 and MAI Code 2 Flash, were launched at Ignite 2026. MAI Code 2 is designed for common enterprise coding tasks such as deep debugging, implementing changes across multiple files, repository-wide reasoning, and user interface development. MAI Code 2 Flash, meanwhile, targets high-volume tasks such as code explanations, targeted edits, routine fixes and rapid iterations. Microsoft said it built these models to prioritize the coding work its customers do every day. The new models are explicitly not yet tuned for harder problems, like fundamental science research and long-horizon agentic work, the company noted in the press statement. The launch also marks another step in Microsoft's effort to build its own AI model capabilities and reduce its reliance on external providers. With the launch of new coding models, Microsoft reduces its dependence on OpenAI and Anthropic, said Pareekh Jain, CEO at EIIRTrend & Pareekh Consulting. "Microsoft also has a major advantage through GitHub, Visual Studio and Azure, which are already used by millions of developers. Its immediate goal is to strengthen its developer ecosystem and reduce AI costs. So it doesn't have to pay OpenAI and Anthropic every time someone uses GitHub Copilot. Microsoft is protecting its profits and locking developers into its own tools," he added. Microsoft's models put to the coding test Microsoft compared MAI Code 2 with competing models across four widely used benchmarks in GitHub Copilot: DeepSWE 1.1, Terminal-Bench 2.1, SWE-Atlas and FrontierCode v1.1. In the average pass rate across these benchmarks, MAI Code 2 recorded an average score of 63.2%, compared with 64.1% for OpenAI's GPT-6.1 Sol and 65.3% for Anthropic's Claude O

## Revisiting the Survival of Agent-Attributed Code: How Measurement Choices Decide the Verdict

DevFeed: [Revisiting the Survival of Agent-Attributed Code: How Measurement Choices Decide the Verdict](<https://devfeed.tech/articles/revisiting-the-survival-of-agent-attributed-code-how-measurement-choices-decide-the-verdict-139594.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21784>)

Author: Musfiqur Rahman, Mahi Begoug, Emad Shihab

Published: 2026-11-18T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [code](<https://devfeed.tech/tags/code.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [devin](<https://devfeed.tech/tags/devin.md>), [humans](<https://devfeed.tech/tags/humans.md>), [llm](<https://devfeed.tech/tags/llm.md>), [measurement](<https://devfeed.tech/tags/measurement.md>), [survival](<https://devfeed.tech/tags/survival.md>)

### AI overview

The study finds that choices in post-merge measurement can change whether agent-written code appears to survive longer or be modified sooner. Across 88 analyses of 854,139 lines from 2,802 merged pull requests in 215 AIDev repositories, results for human-supervised agents (mostly GitHub Copilot) changed in magnitude but not direction. For Devin, the verdict varied with the analysis: across-repository comparisons found sooner modification in 15 of 22 specifications when lines were treated as independent, versus 3 when errors were clustered by repository; within-repository analyses found no difference. LLM intent classifiers matched human labels about as well as two humans matched each other, while keyword rules performed worse and led to different explanations for modifications. Humans made most modifications across the tested units and observation windows. Re-running five published designs showed each could change its result with a single measurement choice.

### Source excerpt

arXiv:2611.21784v1 Announce Type: new Abstract: Studies of how long code from AI coding agents survives after it is merged reach conflicting verdicts: agent code is reported to be retained longer than human code, about as long, or modified sooner. Each study makes defensible measurement choices, but how much these choices decide the verdict is unknown. We revisit the survival of agent-attributed code in our earlier study: 854,139 lines that 2,802 merged pull requests (PRs) added to 215 repositories of the AIDev dataset. We vary nine measurement choices in five research questions and build a specification curve of 88 survival analyses, tested under three variance estimators, several observation windows, and permuted labels. For code from human-supervised agents, mostly GitHub Copilot, the choices change the size of the effect but not its direction. For code from the fully-autonomous agent Devin, they decide the verdict. Across repositories, 15 of 22 specifications report it modified sooner when lines are treated as independent, but only 3 when standard errors are clustered by repository, no more than permuted labels produce. Within repositories, no specification detects a difference. LLM intent classifiers agree with human labels about as well as two humans agree with each other, whereas keyword rules do not (kappa = 0.69 to 0.72 against 0.38), and the two reach different verdicts on why agent code is modified. Humans make most modifications to agent code under every unit and window. Re-run on our data, five published designs each change their result with a single choice. Whether agent code survives longer than human code is therefore decided as much by the measurement as by the code. We derive an operationalization checklist for post-merge studies.

## OpenAI's GPT-6.2 Astra and GPT-6.2 Sol now available

DevFeed: [OpenAI's GPT-6.2 Astra and GPT-6.2 Sol now available](<https://devfeed.tech/articles/openai-s-gpt-6-2-astra-and-gpt-6-2-sol-now-available-139403.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-17-openais-gpt-6-2-astra-and-gpt-6-2-sol-now-available>)

Author: Allison

Published: 2026-11-17T20:20:29Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [gpt-6-astra](<https://devfeed.tech/topics/gpt-6-astra.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Code review](<https://devfeed.tech/topics/code-review.md>), [ai code review](<https://devfeed.tech/topics/ai-code-review.md>), [OpenAI](<https://devfeed.tech/topics/openai.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [billing](<https://devfeed.tech/tags/billing.md>), [code-review](<https://devfeed.tech/tags/code-review.md>), [coding-agent](<https://devfeed.tech/tags/coding-agent.md>), [coding-tasks](<https://devfeed.tech/tags/coding-tasks.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [gpt-6-2-astra](<https://devfeed.tech/tags/gpt-6-2-astra.md>), [gpt-6-2-sol](<https://devfeed.tech/tags/gpt-6-2-sol.md>), [openai](<https://devfeed.tech/tags/openai.md>), [pricing](<https://devfeed.tech/tags/pricing.md>), [release](<https://devfeed.tech/tags/release.md>), [sol](<https://devfeed.tech/tags/sol.md>)

### AI overview

GPT-6.2 Astra and GPT-6.2 Sol are generally available in GitHub Copilot for Pro+, Max, Business, and Enterprise users, with a gradual rollout. Both target agentic coding and code review: Astra is also aimed at terminal work and completed tested coding tasks using noticeably fewer tokens than GPT-6 Astra; Sol targets complex coding and in-depth review, catching nearly twice as many real issues as GPT-6.1 Sol in early testing while keeping findings accurate. The post also reports that both caught significantly more real review issues than earlier GPT-6 models while using fewer tokens. They are billed at provider list pricing under usage-based billing, and can be selected in the listed Copilot clients. Business and Enterprise administrators manage access through model policy; new models are enabled by default unless global defaults are off or the models are explicitly disabled.

### Source excerpt

OpenAI's GPT-6.2 Astra and GPT-6.2 Sol are now generally available in GitHub Copilot. Both models are designed for agentic coding and code review, with stronger coding judgment than earlier GPT-6... The post OpenAI's GPT-6.2 Astra and GPT-6.2 Sol now available appeared first on The GitHub Blog.

## Building the Agent Host Protocol for sessions that continue across devices

DevFeed: [Building the Agent Host Protocol for sessions that continue across devices](<https://devfeed.tech/articles/building-the-agent-host-protocol-for-sessions-that-continue-across-devices-139418.md>)

Original publisher: [Read original article](<https://github.blog/engineering/engineering-principles/building-the-agent-host-protocol-for-sessions-that-continue-across-devices/>)

Author: Rob Lourens

Published: 2026-11-17T18:20:40Z

Content type: article

Language: en

Sources: [GitHub Blog](<https://devfeed.tech/sources/github-engineering.md>), [GitHub Engineering](<https://devfeed.tech/sources/github.md>)

Topics: [Protocol (disambiguation)](<https://devfeed.tech/topics/protocol.md>), [long-running](<https://devfeed.tech/topics/long-running.md>), [state-management](<https://devfeed.tech/topics/state-management.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [apps](<https://devfeed.tech/tags/apps.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [devices](<https://devfeed.tech/tags/devices.md>), [editors](<https://devfeed.tech/tags/editors.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [engineering-principles](<https://devfeed.tech/tags/engineering-principles.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [open](<https://devfeed.tech/tags/open.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [sessions](<https://devfeed.tech/tags/sessions.md>), [vs-code](<https://devfeed.tech/tags/vs-code.md>)

### AI overview

The Agent Host Protocol (AHP) lets agent sessions continue across clients and devices through a shared, open protocol instead of separate integrations tied to each app. It uses URI-identified channels and reducer-based state: servers arbitrate state, while clients send actions that can change it or trigger effects. Queued actions can be replayed and reconciled after network interruptions, and clients can interact with the same agents, history, and state. AHP focuses on interaction rather than prescribing agent behavior. VS Code and GitHub built separate hosts in TypeScript and Rust to meet different local and cloud infrastructure needs; implementing the protocol independently exposed portability gaps and assumptions. Libraries are available in Rust, TypeScript, Kotlin, Swift, .NET, and Go. The article describes connecting hosts through the Copilot app or VS Code, and launching or inspecting VS Code's host with `code agent host` and `code agent endpoints`.

### Source excerpt

Discover how we built the open Agent Host Protocol to keep your agent sessions accessible across editors, apps, phones, and the cloud. The post Building the Agent Host Protocol for sessions that continue across devices appeared first on The GitHub Blog.

## GitHub Copilot Fusion updates: more availability, benchmarks, and models

DevFeed: [GitHub Copilot Fusion updates: more availability, benchmarks, and models](<https://devfeed.tech/articles/github-copilot-fusion-updates-more-availability-benchmarks-and-models-139399.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-17-github-copilot-fusion-updates-more-availability-benchmarks-and-models>)

Author: Allison

Published: 2026-11-17T18:04:48Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [android](<https://devfeed.tech/tags/android.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [claude-sonnet-5-5](<https://devfeed.tech/tags/claude-sonnet-5-5.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [copilot-fusion](<https://devfeed.tech/tags/copilot-fusion.md>), [fable-5-2](<https://devfeed.tech/tags/fable-5-2.md>), [github-com](<https://devfeed.tech/tags/github-com.md>), [github-mobile](<https://devfeed.tech/tags/github-mobile.md>), [gpt-6-1-terra](<https://devfeed.tech/tags/gpt-6-1-terra.md>), [harbor](<https://devfeed.tech/tags/harbor.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [ios](<https://devfeed.tech/tags/ios.md>), [leaderboards](<https://devfeed.tech/tags/leaderboards.md>), [mai-code-2](<https://devfeed.tech/tags/mai-code-2.md>), [models](<https://devfeed.tech/tags/models.md>), [opus-5-5](<https://devfeed.tech/tags/opus-5-5.md>), [performance](<https://devfeed.tech/tags/performance.md>), [terminal-bench](<https://devfeed.tech/tags/terminal-bench.md>)

### AI overview

Copilot Fusion Max achieved a 71.2% resolution rate on Terminal-Bench 4.1, 5.4 percentage points ahead of Opus 5.5 and Fable 5.2 in the cited results. The excerpt reports Fusion Max cost 88% less than Fable 5.2 and 57% less than Opus 5.5. Users can select Fusion on the latest github.com and Visual Studio releases and in GitHub Mobile beta for iOS and Android; support in production mobile apps is forthcoming. Fusion selects and coordinates models based on the task and user-set effort level. New model assignments are Claude Sonnet 5.5 for Fusion Max, GPT-6.1 Terra for Fusion High, and MAI-Code-2 for Fusion Standard.

### Source excerpt

Today, we're expanding GitHub Copilot Fusion with new models, available on more Copilot surfaces, and results on two public Terminal-Bench leaderboards, giving you more ways to use Fusion and compare... The post GitHub Copilot Fusion updates: more availability, benchmarks, and models appeared first on The GitHub Blog.

## GitHub Copilot app, Microsoft Ignite releases

DevFeed: [GitHub Copilot app, Microsoft Ignite releases](<https://devfeed.tech/articles/github-copilot-app-microsoft-ignite-releases-139396.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-17-github-copilot-app-microsoft-ignite-releases>)

Author: Allison

Published: 2026-11-17T18:03:42Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Azure DevOps](<https://devfeed.tech/topics/azure-devops.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [Edge](<https://devfeed.tech/topics/edge.md>)

Tags: [azure-devops](<https://devfeed.tech/tags/azure-devops.md>), [browser](<https://devfeed.tech/tags/browser.md>), [chrome](<https://devfeed.tech/tags/chrome.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [github-copilot-app](<https://devfeed.tech/tags/github-copilot-app.md>), [github-enterprise-server](<https://devfeed.tech/tags/github-enterprise-server.md>), [release](<https://devfeed.tech/tags/release.md>)

### AI overview

The GitHub Copilot app adds Azure DevOps repository support in public preview: users can ask an agent to create a branch, edit code, open and track a pull request, address review comments, and--when checks and policies pass--fix CI failures and merge. Azure DevOps cloud sessions are unavailable. Browser use is also in public preview for Chromium browsers through the Copilot Chrome extension; it runs in an isolated tab group, can work alongside computer use, and is off by default. GHES support is generally available in app version 1.2.0 or later, but GHES cloud sessions are unavailable. The text also says browser use is available in Copilot CLI, VS Code, and JetBrains IDEs.

### Source excerpt

Copilot is most useful when it can work where you do. The GitHub Copilot app now supports your Azure DevOps repositories, your GitHub Enterprise Server instance, and the browser you're... The post GitHub Copilot app, Microsoft Ignite releases appeared first on The GitHub Blog.

## MAI Code 2 and MAI Code 2 Flash in GitHub Copilot

DevFeed: [MAI Code 2 and MAI Code 2 Flash in GitHub Copilot](<https://devfeed.tech/articles/mai-code-2-and-mai-code-2-flash-in-github-copilot-139401.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-17-mai-code-2-and-mai-code-2-flash-in-github-copilot>)

Author: Allison

Published: 2026-11-17T18:01:45Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>)

Tags: [administrator](<https://devfeed.tech/tags/administrator.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [automatically](<https://devfeed.tech/tags/automatically.md>), [billing](<https://devfeed.tech/tags/billing.md>), [cli](<https://devfeed.tech/tags/cli.md>), [cloud-agent](<https://devfeed.tech/tags/cloud-agent.md>), [complex](<https://devfeed.tech/tags/complex.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [development](<https://devfeed.tech/tags/development.md>), [eclipse](<https://devfeed.tech/tags/eclipse.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [github-com](<https://devfeed.tech/tags/github-com.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [github-copilot-app](<https://devfeed.tech/tags/github-copilot-app.md>), [github-mobile](<https://devfeed.tech/tags/github-mobile.md>), [implementation](<https://devfeed.tech/tags/implementation.md>), [ios](<https://devfeed.tech/tags/ios.md>), [mai](<https://devfeed.tech/tags/mai.md>), [mai-code-2](<https://devfeed.tech/tags/mai-code-2.md>), [mai-code-2-flash](<https://devfeed.tech/tags/mai-code-2-flash.md>), [release](<https://devfeed.tech/tags/release.md>)

### AI overview

GitHub Copilot adds two usage-billed MAI coding models aimed at different workloads. MAI Code 2 targets complex work such as deep debugging, multi-file implementation, refactoring, and repository-wide reasoning, with focused responses and practical code changes. MAI Code 2 Flash is a lightweight, cost-efficient option for explanations, targeted edits, routine fixes, and rapid iteration. Both are designed for agentic coding workflows and are available to eligible subscribers on annual plans across the listed Copilot interfaces. Code 2 is listed for Pro, Pro+, Max, Business, and Enterprise; Flash also includes Free and Student. Business and Enterprise administrators can manage access through model policy settings; new models are enabled by default unless the global default or a specific model is disabled.

### Source excerpt

The next generation of Microsoft AI (MAI) coding models has arrived in GitHub Copilot. Introducing MAI Code 2 and MAI Code 2 Flash, two new models that represent a major... The post MAI Code 2 and MAI Code 2 Flash in GitHub Copilot appeared first on The GitHub Blog.

## GitHub Copilot in JetBrains, Ignite releases

DevFeed: [GitHub Copilot in JetBrains, Ignite releases](<https://devfeed.tech/articles/github-copilot-in-jetbrains-ignite-releases-139400.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-17-github-copilot-in-jetbrains-ignite-releases>)

Author: Allison

Published: 2026-11-17T18:00:59Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [releases](<https://devfeed.tech/topics/releases.md>), [IntelliJ IDEA](<https://devfeed.tech/topics/intellij-idea.md>)

Tags: [browser](<https://devfeed.tech/tags/browser.md>), [client-apps](<https://devfeed.tech/tags/client-apps.md>), [context](<https://devfeed.tech/tags/context.md>), [controls](<https://devfeed.tech/tags/controls.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [device](<https://devfeed.tech/tags/device.md>), [diffs](<https://devfeed.tech/tags/diffs.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [ides](<https://devfeed.tech/tags/ides.md>), [ignite](<https://devfeed.tech/tags/ignite.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [jetbrains-ides](<https://devfeed.tech/tags/jetbrains-ides.md>), [on-device](<https://devfeed.tech/tags/on-device.md>), [release](<https://devfeed.tech/tags/release.md>), [releases](<https://devfeed.tech/tags/releases.md>), [remote](<https://devfeed.tech/tags/remote.md>), [remote-access](<https://devfeed.tech/tags/remote-access.md>), [shortcuts](<https://devfeed.tech/tags/shortcuts.md>), [voice](<https://devfeed.tech/tags/voice.md>), [voice-dictation](<https://devfeed.tech/tags/voice-dictation.md>)

### AI overview

GitHub Copilot for JetBrains adds cloud sandbox sessions, phased opt-in remote access, browser use through the Chrome plugin, and on-device voice dictation on supported native packages with Editor Preview enabled. Remote development is supported in split mode when the plugin is installed on both the local client and remote backend; dictation remains an editable draft until sent. Workflow updates include Enter to steer a running agent and Ctrl+Enter (Command+Enter on macOS) to queue a follow-up, plus session deletion, timestamps, token details, and historical diffs on newer IDE EAP builds. The update also improves chat persistence and recovery, restores automatic Maven vulnerability checks by sending dependency coordinates to GitHub Advisories, and moves code review to the agent review engine while retaining the inline results interface. Enterprise policies govern Claude, Codex, and Fusion tier defaults. JetBrains IDE 2025.2 is no longer supported; use 2025.3 or later, with 2026.2 or later recommended.

### Source excerpt

This update brings remote access, on-device voice dictation, and browser use controls to GitHub Copilot for JetBrains. Copilot users in JetBrains IDEs also get context usage shortcuts, historical diffs, simpler... The post GitHub Copilot in JetBrains, Ignite releases appeared first on The GitHub Blog.

## Monitor GitHub Copilot activity through Microsoft Agent 365

DevFeed: [Monitor GitHub Copilot activity through Microsoft Agent 365](<https://devfeed.tech/articles/monitor-github-copilot-activity-through-microsoft-agent-365-139402.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-17-monitor-github-copilot-activity-through-microsoft-agent-365>)

Author: Allison

Published: 2026-11-17T18:00:59Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [Purview](<https://devfeed.tech/topics/purview.md>), [Microsoft](<https://devfeed.tech/topics/microsoft.md>)

Tags: [agent-365](<https://devfeed.tech/tags/agent-365.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [audit](<https://devfeed.tech/tags/audit.md>), [audit-log](<https://devfeed.tech/tags/audit-log.md>), [cli](<https://devfeed.tech/tags/cli.md>), [cloud](<https://devfeed.tech/tags/cloud.md>), [cloud-agents](<https://devfeed.tech/tags/cloud-agents.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [defender](<https://devfeed.tech/tags/defender.md>), [eclipse](<https://devfeed.tech/tags/eclipse.md>), [enterprise-cloud](<https://devfeed.tech/tags/enterprise-cloud.md>), [github](<https://devfeed.tech/tags/github.md>), [github-com](<https://devfeed.tech/tags/github-com.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [github-enterprise-cloud](<https://devfeed.tech/tags/github-enterprise-cloud.md>), [ides](<https://devfeed.tech/tags/ides.md>), [jetbrains](<https://devfeed.tech/tags/jetbrains.md>), [microsoft](<https://devfeed.tech/tags/microsoft.md>), [purview](<https://devfeed.tech/tags/purview.md>), [release](<https://devfeed.tech/tags/release.md>)

### AI overview

GitHub Enterprise Cloud customers with Enterprise Managed Users can stream GitHub Copilot agent activity into Microsoft Agent 365. Administrators can review sessions--including prompts, responses, and tool calls--and usage trends across GitHub.com cloud agents, Copilot CLI, Visual Studio Code, Visual Studio, and partner IDEs such as JetBrains and Eclipse. The integration also provides access to risk information in Microsoft Purview and Defender for investigation and mitigation.

### Source excerpt

Enterprises can now stream GitHub Copilot agent activity directly into Microsoft Agent 365. This lets you bring audit data from across GitHub Copilot clients into Microsoft's agent control plane, where... The post Monitor GitHub Copilot activity through Microsoft Agent 365 appeared first on The GitHub Blog.

## GitHub Copilot Evals is now in public preview

DevFeed: [GitHub Copilot Evals is now in public preview](<https://devfeed.tech/articles/github-copilot-evals-is-now-in-public-preview-139398.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-17-github-copilot-evals-is-now-in-public-preview>)

Author: Allison

Published: 2026-11-17T18:00:33Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [after](<https://devfeed.tech/tags/after.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [app](<https://devfeed.tech/tags/app.md>), [can](<https://devfeed.tech/tags/can.md>), [change](<https://devfeed.tech/tags/change.md>), [client-apps](<https://devfeed.tech/tags/client-apps.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [evals](<https://devfeed.tech/tags/evals.md>), [getting](<https://devfeed.tech/tags/getting.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [models](<https://devfeed.tech/tags/models.md>), [optimize](<https://devfeed.tech/tags/optimize.md>), [preview](<https://devfeed.tech/tags/preview.md>), [prompts](<https://devfeed.tech/tags/prompts.md>), [public](<https://devfeed.tech/tags/public.md>), [release](<https://devfeed.tech/tags/release.md>), [skills](<https://devfeed.tech/tags/skills.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

GitHub Copilot Evals helps assess whether skills, custom agents, and MCP tools in a Copilot setup behave as intended, including after changes. Create a repeatable eval by giving an agent a realistic task and defining what a good result looks like; run it with approval, inspect passed and failed checks, investigate failures, and compare runs before and after a change to spot improvements or regressions. Evals uses Vally, an extensible local evaluation tool. It is available through extensions or plugins for Visual Studio Code, Copilot CLI, and the GitHub Copilot app, and is in public preview for Copilot Individual, Business, and Enterprise plans.

### Source excerpt

You can now use GitHub Copilot Evals to optimize GitHub Copilot for yourself. As your prompts, models, skills, and tools change, are you still getting the most out of Copilot?... The post GitHub Copilot Evals is now in public preview appeared first on The GitHub Blog.

## GitHub Copilot weekly releases -- November 9

DevFeed: [GitHub Copilot weekly releases -- November 9](<https://devfeed.tech/articles/github-copilot-weekly-releases-november-9-137188.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-16-github-copilot-weekly-releases-november-9>)

Author: Allison

Published: 2026-11-16T21:34:53Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [releases](<https://devfeed.tech/topics/releases.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [GitHub](<https://devfeed.tech/topics/github.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [also](<https://devfeed.tech/tags/also.md>), [app](<https://devfeed.tech/tags/app.md>), [can](<https://devfeed.tech/tags/can.md>), [claude](<https://devfeed.tech/tags/claude.md>), [code](<https://devfeed.tech/tags/code.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-server](<https://devfeed.tech/tags/enterprise-server.md>), [first](<https://devfeed.tech/tags/first.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [github-enterprise](<https://devfeed.tech/tags/github-enterprise.md>), [github-enterprise-server](<https://devfeed.tech/tags/github-enterprise-server.md>), [models](<https://devfeed.tech/tags/models.md>), [need](<https://devfeed.tech/tags/need.md>), [release](<https://devfeed.tech/tags/release.md>), [repositories](<https://devfeed.tech/tags/repositories.md>), [server](<https://devfeed.tech/tags/server.md>), [sessions](<https://devfeed.tech/tags/sessions.md>), [this](<https://devfeed.tech/tags/this.md>)

### AI overview

This release adds GitHub Enterprise Server support for repositories, issues, and pull requests in the Copilot app; it requires a GitHub.com or GHE.com account, and cloud sessions are unavailable for GHES. Claude Fable 5.2 and Gemini 4 Carbon are offered to Copilot Pro+, Max, Business, and Enterprise users. Claude Fable 5.2 requires default data retention, and Business and Enterprise administrators must enable its policy. Other additions include opening cloud and Codespace sessions from GitHub Mobile, reconnecting MCP servers in a conversation, minute-level Project automation schedules, multilingual dictation, custom-field issue and pull request filters, and expanded accessibility options. In VS Code, experimental Inbox mode prioritizes agent sessions needing attention, and an experimental tool can run model comparisons. Chat windows are in preview; extension management is also experimental. The Copilot harness is the default for new sessions, and the Local harness is scheduled for removal in February 2027.

### Source excerpt

This week, bring GitHub Enterprise Server repositories into the Copilot app and see which agent sessions need you first in VS Code. You can also try two new models, Claude... The post GitHub Copilot weekly releases -- November 9 appeared first on The GitHub Blog.

## GitHub Copilot models deprecated on November 16, 2026

DevFeed: [GitHub Copilot models deprecated on November 16, 2026](<https://devfeed.tech/articles/github-copilot-models-deprecated-on-november-16-2026-137187.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-16-github-copilot-models-deprecated-on-november-16-2026>)

Author: Allison

Published: 2026-11-16T20:25:20Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [GitHub](<https://devfeed.tech/topics/github.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [agent](<https://devfeed.tech/tags/agent.md>), [alternatives](<https://devfeed.tech/tags/alternatives.md>), [chat](<https://devfeed.tech/tags/chat.md>), [claude](<https://devfeed.tech/tags/claude.md>), [claude-opus](<https://devfeed.tech/tags/claude-opus.md>), [claude-opus-4-8](<https://devfeed.tech/tags/claude-opus-4-8.md>), [claude-opus-5](<https://devfeed.tech/tags/claude-opus-5.md>), [code](<https://devfeed.tech/tags/code.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [deprecated](<https://devfeed.tech/tags/deprecated.md>), [deprecations](<https://devfeed.tech/tags/deprecations.md>), [documentation](<https://devfeed.tech/tags/documentation.md>), [edits](<https://devfeed.tech/tags/edits.md>), [enablement](<https://devfeed.tech/tags/enablement.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [fallback](<https://devfeed.tech/tags/fallback.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [models](<https://devfeed.tech/tags/models.md>), [retired](<https://devfeed.tech/tags/retired.md>)

### AI overview

GitHub deprecated several models across most Copilot experiences on November 16, 2026, following an October 15 announcement. Claude Opus 4.8 remains available to individual subscribers on annual plans; Claude Opus 5 is no longer in the model picker but can still serve as a runtime refusal fallback through existing authorized access. Existing enterprise model policies continue to apply. Enterprise and Business customers should use supported alternatives; suggested alternatives are enabled by default unless an administrator disabled the global default or the model. If the global default is off, administrators can enable alternatives through Copilot model policies. Users then see enabled models in the Chat selector in supported experiences. No action is needed to remove deprecated models.

### Source excerpt

As of today, November 16, 2026, we have deprecated the following models across most GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions). Note... The post GitHub Copilot models deprecated on November 16, 2026 appeared first on The GitHub Blog.

## Control where GitHub Copilot customizations come from

DevFeed: [Control where GitHub Copilot customizations come from](<https://devfeed.tech/articles/control-where-github-copilot-customizations-come-from-137185.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-16-control-where-github-copilot-customizations-come-from>)

Author: Allison

Published: 2026-11-16T19:48:33Z

Content type: article

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [GitHub](<https://devfeed.tech/topics/github.md>)

Tags: [administrator](<https://devfeed.tech/tags/administrator.md>), [agents](<https://devfeed.tech/tags/agents.md>), [canvas](<https://devfeed.tech/tags/canvas.md>), [canvases](<https://devfeed.tech/tags/canvases.md>), [categories](<https://devfeed.tech/tags/categories.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [enterprise](<https://devfeed.tech/tags/enterprise.md>), [enterprise-administrator](<https://devfeed.tech/tags/enterprise-administrator.md>), [extensions](<https://devfeed.tech/tags/extensions.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [github-enterprise-cloud](<https://devfeed.tech/tags/github-enterprise-cloud.md>), [hooks](<https://devfeed.tech/tags/hooks.md>), [improvement](<https://devfeed.tech/tags/improvement.md>), [managed](<https://devfeed.tech/tags/managed.md>), [marketplace](<https://devfeed.tech/tags/marketplace.md>), [mcp-tools](<https://devfeed.tech/tags/mcp-tools.md>), [plugins](<https://devfeed.tech/tags/plugins.md>), [project](<https://devfeed.tech/tags/project.md>), [settings](<https://devfeed.tech/tags/settings.md>), [skills](<https://devfeed.tech/tags/skills.md>)

### AI overview

Enterprise administrators can use `strictPluginOnlyCustomization` to block standalone user and project customizations for selected Copilot categories while still allowing eligible plugins and managed settings, subject to other policies. The restriction can cover all five supported categories--skills, custom agents, hooks, MCP servers, and executable Copilot extensions--or only selected ones. Extensions here include executable canvas providers, not VS Code Marketplace extensions. Plugin-only mode does not limit plugins to enterprise-managed ones or serve as a marketplace allowlist; pair it with `strictKnownMarketplaces` to restrict marketplace sources. The controls apply on GitHub Enterprise Cloud to members with enterprise-issued Copilot Business or Copilot Enterprise licenses.

### Source excerpt

As an enterprise administrator, you can now require selected GitHub Copilot customizations to come from plugins or managed settings, rather than standalone user or project configuration. Combined with marketplace restrictions,... The post Control where GitHub Copilot customizations come from appeared first on The GitHub Blog.

## VS Code retires the Local harness in February 2027

DevFeed: [VS Code retires the Local harness in February 2027](<https://devfeed.tech/articles/vs-code-retires-the-local-harness-in-february-2027-137190.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-16-vs-code-retires-the-local-harness-in-february-2027>)

Author: Allison

Published: 2026-11-16T19:22:56Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Visual Studio Code](<https://devfeed.tech/topics/visual-studio-code.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [GitHub Copilot SDK](<https://devfeed.tech/topics/github-copilot-sdk.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [agent-runtime](<https://devfeed.tech/tags/agent-runtime.md>), [agents](<https://devfeed.tech/tags/agents.md>), [app](<https://devfeed.tech/tags/app.md>), [assessment](<https://devfeed.tech/tags/assessment.md>), [blocks](<https://devfeed.tech/tags/blocks.md>), [canvases](<https://devfeed.tech/tags/canvases.md>), [client-apps](<https://devfeed.tech/tags/client-apps.md>), [context](<https://devfeed.tech/tags/context.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [copilot-agent](<https://devfeed.tech/tags/copilot-agent.md>), [editor](<https://devfeed.tech/tags/editor.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [harness](<https://devfeed.tech/tags/harness.md>), [local](<https://devfeed.tech/tags/local.md>), [model](<https://devfeed.tech/tags/model.md>), [retired](<https://devfeed.tech/tags/retired.md>), [sessions](<https://devfeed.tech/tags/sessions.md>), [tools](<https://devfeed.tech/tags/tools.md>), [visual-studio-code](<https://devfeed.tech/tags/visual-studio-code.md>), [vs-code](<https://devfeed.tech/tags/vs-code.md>)

### AI overview

VS Code 1.146 deprecates the Local harness, with removal planned for February 2027; new features will focus on the Copilot harness, which has been the default for new sessions since VS Code 1.143. The transition does not move files to the cloud, and the Local harness remains available for three months where organizational policy permits. To switch, start a new VS Code session and choose Copilot under Session Target. Review customizations for compatibility, since switching does not convert them automatically. Administrators should verify workflows, permission controls, and sandbox settings: the Copilot harness supports managed runtime permissions and sandbox restrictions the Local harness cannot enforce, but selecting it does not enable sandboxing. Features such as connectors and canvases are in preview; availability depends on plan, settings, and organization policy. Assisted permissions still require confirmation for calls that fail risk assessment.

### Source excerpt

Visual Studio Code 1.146 deprecates the Local harness, the older software that coordinates the model, context, and tools for GitHub Copilot agent sessions in the editor. The Local harness will... The post VS Code retires the Local harness in February 2027 appeared first on The GitHub Blog.

## Your Team Agrees on the Fix in Teams, Then Retypes It Into GitHub

DevFeed: [Your Team Agrees on the Fix in Teams, Then Retypes It Into GitHub](<https://devfeed.tech/articles/your-team-agrees-on-the-fix-in-teams-then-retypes-it-into-github-136237.md>)

Original publisher: [Read original article](<https://blog.devops.dev/github-app-microsoft-teams-copilot-thread-to-pull-request-606a8ca2150a?source=rss----33f8b2d9a328---4>)

Author: Dave R | Microsoft Azure & AI MVP ☁

Published: 2026-11-16T13:26:12Z

Content type: article

Language: en

Sources: [DevOps.dev](<https://devfeed.tech/sources/devops-dev.md>)

Topics: [Microsoft Teams](<https://devfeed.tech/topics/microsoft-teams.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>)

Tags: [admin](<https://devfeed.tech/tags/admin.md>), [agent](<https://devfeed.tech/tags/agent.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent](<https://devfeed.tech/tags/ai-agent.md>), [artificial-intelligence](<https://devfeed.tech/tags/artificial-intelligence.md>), [cloud-agent](<https://devfeed.tech/tags/cloud-agent.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [github-issue](<https://devfeed.tech/tags/github-issue.md>), [microsoft-teams](<https://devfeed.tech/tags/microsoft-teams.md>), [permissions](<https://devfeed.tech/tags/permissions.md>), [pull-request](<https://devfeed.tech/tags/pull-request.md>), [rules](<https://devfeed.tech/tags/rules.md>), [sandbox](<https://devfeed.tech/tags/sandbox.md>), [software-development](<https://devfeed.tech/tags/software-development.md>), [teams](<https://devfeed.tech/tags/teams.md>), [thread](<https://devfeed.tech/tags/thread.md>)

### AI overview

The Microsoft Teams GitHub app is generally available and lets users mention @GitHub to turn thread context into GitHub issues or Copilot pull requests, avoiding manual re-entry. Copilot works in a cloud sandbox, while existing GitHub permissions and approval rules continue to govern the work. Its identity depends on where it is invoked: in a direct message it acts as the user's GitHub account; in a channel or group chat it acts as the app, and pull requests require an additional approval.

### Source excerpt

The GitHub app in Microsoft Teams is now GA. How @GitHub turns a thread into a Copilot pull request, who it acts as, and what to set up... Continue reading on DevOps.dev "

## Chargeback and showback for AI coding agents

DevFeed: [Chargeback and showback for AI coding agents](<https://devfeed.tech/articles/chargeback-and-showback-for-ai-coding-agents-135244.md>)

Original publisher: [Read original article](<https://nirmata.com/2026/11/17/chargeback-and-showback-for-ai-coding-agents/>)

Author: Ritesh Patel

Published: 2026-11-16T12:00:48.928398Z

Content type: article

Language: en

Sources: [Nirmata](<https://devfeed.tech/sources/nirmata.md>)

Topics: [Finance](<https://devfeed.tech/topics/finance.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [OpenTelemetry](<https://devfeed.tech/topics/opentelemetry.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-agents](<https://devfeed.tech/tags/ai-coding-agents.md>), [ai-governance](<https://devfeed.tech/tags/ai-governance.md>), [amazon-bedrock](<https://devfeed.tech/tags/amazon-bedrock.md>), [budget](<https://devfeed.tech/tags/budget.md>), [business](<https://devfeed.tech/tags/business.md>), [chargeback](<https://devfeed.tech/tags/chargeback.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cost-management](<https://devfeed.tech/tags/cost-management.md>), [costs](<https://devfeed.tech/tags/costs.md>), [finops](<https://devfeed.tech/tags/finops.md>), [team](<https://devfeed.tech/tags/team.md>)

### AI overview

Reliable team allocation starts by mapping each paid request to one team, then reporting spend as showback before charging it to team budgets. Each provider exposes different allocation keys: Claude Code's Analytics API reports estimated daily cost by actor, while Claude Console's API groups by workspace, API key, model and actor; for Claude Code, use the actor rather than its shared workspace. Cloud bills need per-developer assumed-role sessions or tagged, team-specific Bedrock inference profiles to identify teams. GitHub Copilot supports cost centers, with license costs assigned by users and usage-based costs by repositories or organizations. Keep a versioned roster linking identities to exactly one team, map API keys separately, and retain unmatched spend in an unallocated bucket. Reports have limits: seat allowance usage is not dollar-metered, Claude Code estimates use list pricing unless managed settings apply contracted rates, and monthly values may change for about seven days after month end. Team caps also differ: workspace limits are shared across Claude Code users, gateway group caps are per member, and Copilot budgets block usage only when the stop option is enabled.

### Source excerpt

Showback reports AI coding agent spend by team, and chargeback bills it to the team's budget. Map each tool's spend to a team key before you allocate it.

## Upcoming deprecation of selected GitHub Copilot models in December

DevFeed: [Upcoming deprecation of selected GitHub Copilot models in December](<https://devfeed.tech/articles/upcoming-deprecation-of-selected-github-copilot-models-in-december-133490.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-13-upcoming-deprecation-of-selected-github-copilot-models-in-december>)

Author: Allison

Published: 2026-11-13T20:40:05Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Claude](<https://devfeed.tech/topics/claude.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [deprecation](<https://devfeed.tech/tags/deprecation.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [models](<https://devfeed.tech/tags/models.md>), [retired](<https://devfeed.tech/tags/retired.md>)

### AI overview

GitHub will deprecate selected Copilot models across Copilot Chat, inline edits, ask and agent modes, and code completions on December 14, 2026. Claude Haiku 4.5 remains available to individual subscribers on annual plans. GitHub asks users to update workflows and integrations before the date. For Copilot Business and Enterprise, suggested alternatives are enabled by default unless an administrator disables the global default or the specific model; administrators who turned off the global default can enable alternatives through model policies in Copilot settings. Enabled models appear in the Chat model selector in supported experiences. No action is needed to remove deprecated models.

### Source excerpt

We will deprecate the following models across all GitHub Copilot experiences (including Copilot Chat, inline edits, ask and agent modes, and code completions) on December 14, 2026: Model Deprecation date... The post Upcoming deprecation of selected GitHub Copilot models in December appeared first on The GitHub Blog.

## GitHub Enterprise Server support in the GitHub Copilot app

DevFeed: [GitHub Enterprise Server support in the GitHub Copilot app](<https://devfeed.tech/articles/github-enterprise-server-support-in-the-github-copilot-app-133230.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-13-github-enterprise-server-support-in-the-github-copilot-app>)

Author: Allison

Published: 2026-11-13T18:27:13Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [GitHub](<https://devfeed.tech/topics/github.md>)

Tags: [copilot](<https://devfeed.tech/tags/copilot.md>), [ghes](<https://devfeed.tech/tags/ghes.md>), [github](<https://devfeed.tech/tags/github.md>), [github-com](<https://devfeed.tech/tags/github-com.md>), [github-copilot-app](<https://devfeed.tech/tags/github-copilot-app.md>), [github-enterprise](<https://devfeed.tech/tags/github-enterprise.md>), [github-enterprise-server](<https://devfeed.tech/tags/github-enterprise-server.md>), [release](<https://devfeed.tech/tags/release.md>)

### AI overview

GitHub Enterprise Server support is generally available in the GitHub Copilot app, allowing users to work with remote repositories, issues, and pull requests. To add a GHES account, first sign in with a GitHub.com or GHE.com account, then go to Settings > Accounts > Add account and choose GitHub Enterprise Server. The feature requires app version 1.2.0 or later; cloud sessions aren't available for GHES.

### Source excerpt

You can now bring your work on GitHub Enterprise Server (GHES) into the GitHub Copilot app. Add your GHES account to work with remote repositories, issues, and pull requests. This... The post GitHub Enterprise Server support in the GitHub Copilot app appeared first on The GitHub Blog.

## Gemini 4 Hydrogen in GitHub Copilot

DevFeed: [Gemini 4 Hydrogen in GitHub Copilot](<https://devfeed.tech/articles/gemini-4-hydrogen-in-github-copilot-133229.md>)

Original publisher: [Read original article](<https://github.blog/changelog/2026-11-13-gemini-4-hydrogen-in-github-copilot>)

Author: Allison

Published: 2026-11-13T18:23:48Z

Content type: release

Language: en

Sources: [GitHub Changelog](<https://devfeed.tech/sources/github-changelog.md>)

Topics: [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [GitHub Copilot CLI](<https://devfeed.tech/topics/github-copilot-cli.md>)

Tags: [administrator](<https://devfeed.tech/tags/administrator.md>), [agentic](<https://devfeed.tech/tags/agentic.md>), [agentic-coding](<https://devfeed.tech/tags/agentic-coding.md>), [coding](<https://devfeed.tech/tags/coding.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [fast](<https://devfeed.tech/tags/fast.md>), [flash](<https://devfeed.tech/tags/flash.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [gemini-4](<https://devfeed.tech/tags/gemini-4.md>), [gemini-4-hydrogen](<https://devfeed.tech/tags/gemini-4-hydrogen.md>), [github](<https://devfeed.tech/tags/github.md>), [github-copilot](<https://devfeed.tech/tags/github-copilot.md>), [google](<https://devfeed.tech/tags/google.md>), [google-s](<https://devfeed.tech/tags/google-s.md>), [hydrogen](<https://devfeed.tech/tags/hydrogen.md>), [latest](<https://devfeed.tech/tags/latest.md>), [model](<https://devfeed.tech/tags/model.md>), [release](<https://devfeed.tech/tags/release.md>), [tool](<https://devfeed.tech/tags/tool.md>), [tool-use](<https://devfeed.tech/tags/tool-use.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

Gemini 4 Hydrogen is generally available in GitHub Copilot for Pro, Pro+, Max, Business, and Enterprise users. The text describes it as a fast, efficient Flash model for agentic coding, tool use, and multistep workflows, with improved instruction following over Gemini 3.8 Flash. It is billed at provider list pricing under usage-based billing. It can be selected across the listed Copilot surfaces, including VS Code, Visual Studio, Copilot CLI, GitHub.com, mobile, and several IDEs; rollout is gradual. Business and Enterprise administrators control access through the model policy: new models are enabled by default unless the global default is off or this model is explicitly disabled.

### Source excerpt

Gemini 4 Hydrogen, Google's latest Flash model, is now generally available in GitHub Copilot. It is designed for fast, efficient agentic coding, tool use, and multistep workflows, with improved instruction... The post Gemini 4 Hydrogen in GitHub Copilot appeared first on The GitHub Blog.

## GitHub availability report: October 2026

DevFeed: [GitHub availability report: October 2026](<https://devfeed.tech/articles/github-availability-report-october-2026-132661.md>)

Original publisher: [Read original article](<https://github.blog/news-insights/company-news/github-availability-report-october-2026/>)

Author: Jakub Oleksy

Published: 2026-11-13T00:20:16Z

Content type: news

Language: en

Sources: [GitHub Blog](<https://devfeed.tech/sources/github-engineering.md>)

Topics: [Availability](<https://devfeed.tech/topics/availability.md>), [Production Engineering](<https://devfeed.tech/topics/production-engineering.md>), [GitHub](<https://devfeed.tech/topics/github.md>), [GitHub Actions](<https://devfeed.tech/topics/github-actions.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>)

Tags: [2026](<https://devfeed.tech/tags/2026.md>), [actions](<https://devfeed.tech/tags/actions.md>), [api](<https://devfeed.tech/tags/api.md>), [audit-log](<https://devfeed.tech/tags/audit-log.md>), [audit-logs](<https://devfeed.tech/tags/audit-logs.md>), [availability](<https://devfeed.tech/tags/availability.md>), [azure](<https://devfeed.tech/tags/azure.md>), [blog](<https://devfeed.tech/tags/blog.md>), [cache](<https://devfeed.tech/tags/cache.md>), [capacity](<https://devfeed.tech/tags/capacity.md>), [central](<https://devfeed.tech/tags/central.md>), [clusters](<https://devfeed.tech/tags/clusters.md>), [company-news](<https://devfeed.tech/tags/company-news.md>), [github](<https://devfeed.tech/tags/github.md>), [github-availability-report](<https://devfeed.tech/tags/github-availability-report.md>), [incidents](<https://devfeed.tech/tags/incidents.md>), [news-insights](<https://devfeed.tech/tags/news-insights.md>), [october](<https://devfeed.tech/tags/october.md>), [october-2026](<https://devfeed.tech/tags/october-2026.md>), [performance](<https://devfeed.tech/tags/performance.md>), [report](<https://devfeed.tech/tags/report.md>), [services](<https://devfeed.tech/tags/services.md>)

### AI overview

GitHub reported eight incidents in October and expanded Azure Central US capacity while addressing reliability risks exposed by the outages. As of November 9, 140 of 151 production services and 32 of 50 MySQL primaries ran there; the region served 63% of migrated-service reads, 66% of monolith reads, and 52% of Git reads. Nine Kubernetes clusters more than doubled compute capacity, and migrated-service traffic had grown 82% since March. Incidents included shared database overload from large migration queries, unsafe database routing changes that caused two write outages, reconnect bursts that saturated network links, and a regional Azure network disruption that cascaded into GitHub Actions failures. Other events involved overloaded event-streaming servers, an invalid Copilot model-provider credential, and a saturated database connection pool. Mitigations included batching importer queries, stronger routing validation, connection and retry controls, and improved monitoring. East US 3 was about a week behind plan, with its first validated traffic ramp targeted for the first week of December.

### Source excerpt

In October, we experienced eight incidents that resulted in degraded performance across GitHub services. The post GitHub availability report: October 2026 appeared first on The GitHub Blog.

## I Used AI Coding Tools for 30 Days. Here's What Made Me Faster (And What Didn't)

DevFeed: [I Used AI Coding Tools for 30 Days. Here's What Made Me Faster (And What Didn't)](<https://devfeed.tech/articles/i-used-ai-coding-tools-for-30-days-here-s-what-made-me-faster-and-what-didn-t-130599.md>)

Original publisher: [Read original article](<https://hackernoon.com/i-used-ai-coding-tools-for-30-days-heres-what-made-me-faster-and-what-didnt?source=rss>)

Author: Yashpal Waghela

Published: 2026-11-12T15:38:49Z

Content type: opinion

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [coding assistant](<https://devfeed.tech/topics/coding-assistant.md>), [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [GitHub Copilot](<https://devfeed.tech/topics/github-copilot.md>), [Claude](<https://devfeed.tech/topics/claude.md>), [React](<https://devfeed.tech/topics/react.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted-debugging](<https://devfeed.tech/tags/ai-assisted-debugging.md>), [ai-coding](<https://devfeed.tech/tags/ai-coding.md>), [ai-coding-time-savings](<https://devfeed.tech/tags/ai-coding-time-savings.md>), [ai-coding-tools](<https://devfeed.tech/tags/ai-coding-tools.md>), [ai-generated-code-review](<https://devfeed.tech/tags/ai-generated-code-review.md>), [ai-pair-programming](<https://devfeed.tech/tags/ai-pair-programming.md>), [ai-productivity-experiment](<https://devfeed.tech/tags/ai-productivity-experiment.md>), [ai-vs-human-coding](<https://devfeed.tech/tags/ai-vs-human-coding.md>), [boilerplate](<https://devfeed.tech/tags/boilerplate.md>), [bug](<https://devfeed.tech/tags/bug.md>), [bug-reports](<https://devfeed.tech/tags/bug-reports.md>), [bugs](<https://devfeed.tech/tags/bugs.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [claude](<https://devfeed.tech/tags/claude.md>), [copilot](<https://devfeed.tech/tags/copilot.md>), [database](<https://devfeed.tech/tags/database.md>), [database-indexing](<https://devfeed.tech/tags/database-indexing.md>), [debugging](<https://devfeed.tech/tags/debugging.md>), [design-thinking](<https://devfeed.tech/tags/design-thinking.md>), [developer-productivity-with-ai](<https://devfeed.tech/tags/developer-productivity-with-ai.md>), [docs](<https://devfeed.tech/tags/docs.md>), [net](<https://devfeed.tech/tags/net.md>), [tools](<https://devfeed.tech/tags/tools.md>), [workflow](<https://devfeed.tech/tags/workflow.md>)

### AI overview

Across a 30-day experiment using ChatGPT, Claude, and GitHub Copilot, deliberate use saved roughly 14 hours, mainly by drafting boilerplate, explaining unfamiliar code, suggesting edge cases, and helping debug. The author found that specific prompts with framework versions, expected and actual behavior, error details, and relevant code produced more useful answers; breaking work into small pieces also helped. The gains came with costs: unchecked output introduced a pagination bug, broad feature prompts produced inconsistent code, and relying on answers while learning hindered retention. The author's workflow is to plan first, delegate repetitive tasks, review and test generated code, and check official documentation for version-sensitive APIs. The estimate comes from an informal time log, not a scientific study.

### Source excerpt

I tracked my AI coding assistant usage for 30 days. Here's where ChatGPT, Claude, and Copilot saved time, caused mistakes, and changed my workflow.

[Next page](<https://devfeed.tech/topics/github-copilot.md?cursor=WyIyMDI2LTExLTEyVDE1OjM4OjQ5KzAwOjAwIiwgImE0N2M5N2MwLWNkZmItNDNjMC1iNDc5LTY3ZDE0ZGI1Y2ZlMyJd>)