github

GitHub has optimized token usage in its production agentic workflows that run on every pull request. The company instrumented its own Copilot workflows to identify inefficiencies and built agents to address them, aiming to reduce accumulated API costs.

GitHub details how it reduced token consumption in production agentic workflows that run on every pull request. The company instrumented its own workflows to identify inefficiencies and built automated agents to address them.

GitHub has published a research approach for validating AI coding agents when traditional correctness testing breaks down. The company proposes dominatory analysis as an alternative to brittle scripts and black-box LLM judges for building what it calls a 'Trust Layer' for GitHub Copilot Coding Agents.

GitHub has published research on validating agentic AI behavior when there's no single "correct" answer. The company proposes dominance analysis as an alternative to brittle scripts or opaque LLM-as-judge approaches for building a trust layer in GitHub Copilot coding agents.

Microsoft's GitHub is ending flat-rate billing for Copilot on June 1, 2026, switching to usage-based metered tokens after acknowledging the request-based model is no longer sustainable. Copilot Pro subscribers ($10/month) will receive 1,000 GitHub AI Credits monthly, with each credit worth $0.01.

GitHub Copilot transitions to token-based pricing effective June 1, 2026, replacing its premium request unit system. Base subscription prices remain unchanged at $10/month for Pro and $39/month for Pro+, but users now receive equivalent monthly AI Credits that deplete with usage—and service stops when credits run out.

GitHub Copilot customers are experiencing rate limits lasting up to 181 hours after the company fixed a token counting bug that had been undercharging for usage of newer models including Claude Opus 4.6 and GPT-5.4. GitHub has suspended Pro free trials and removed Anthropic's Opus 4.6 Fast model from Pro+ tiers.

Anthropic has released routines for Claude Code, allowing automated bug fixes, code reviews, and deployment monitoring to run on cloud infrastructure without requiring users' local machines. The feature is available in research preview with daily limits of 5-25 runs depending on subscription tier.

Anthropic's Claude.ai and Claude Code suffered a 48-minute outage on April 13, 2026, from 15:31 to 16:19 UTC with elevated error rates. GitHub quality complaints have increased 3.5× from the January-February baseline, though SWE-Bench-Pro scores show no substantive change since February.

GitHub has integrated Copilot directly into its security assessment tools, enabling organization admins and security managers to request real-time explanations and guided remediation steps from detected secret risks and code vulnerabilities without leaving the assessment interface.

GitHub has extended Dependabot to allow direct assignment of security alerts to AI coding agents including Copilot, Claude, and Codex. The feature targets vulnerabilities requiring code changes beyond simple version bumps, automating remediation workflows across entire projects.

GitHub has disabled Copilot's ability to insert promotional tips into pull requests following developer backlash. The feature, which injected Raycast ads into over 11,400 pull requests without explicit developer consent, was enabled when Copilot was mentioned in PRs it didn't create. GitHub's product manager acknowledged the decision was a mistake.

GitHub will use Copilot interaction data from Free, Pro, and Pro+ plan users to train AI models starting April 24, 2026, unless users actively opt out. The policy does not affect Copilot Business and Enterprise customers. Data shared will include prompts, outputs, code snippets, filenames, and repository structures.

GitHub has removed premium AI models including GPT-5.4, Claude Opus, and Claude Sonnet from its free Copilot Student plan effective March 12, 2026. The change leaves students with access only to lower-cost models: Claude 4.5 Haiku, Gemini 3.1 Pro, and GPT-5.3 Codex. GitHub's decision triggered 2,874 downvotes versus 21 upvotes on the announcement, with students arguing they need premium models to learn industry-standard tools.

GitHub is positioning AI interaction as a shift from prompt-response text interfaces to programmable execution models. The company announced a GitHub Copilot SDK that enables agentic workflows to run directly within applications, marking a transition toward AI systems that take concrete actions rather than generate text responses.

GitHub has published technical details on the security architecture underlying its Agentic Workflows feature, which runs AI agents within GitHub Actions. The system implements process isolation, output constraints, and comprehensive audit logging to contain agent behavior.

GitHub Copilot has reached 60 million code reviews, marking significant adoption of AI-assisted code review workflows. The milestone reflects growing reliance on AI to manage review backlogs as development velocity increases across organizations.

OpenAI is building an internal alternative to GitHub, Microsoft's dominant code collaboration platform, according to The Information. The move marks OpenAI's entry into developer tools and could create tension with its largest investor, Microsoft.

GitHub has published a hands-on guide demonstrating how developers can use GitHub Copilot CLI to move from initial intent through to creating reviewable pull requests. The guide shows how CLI-based development naturally integrates with IDE workflows and GitHub's collaborative tools.