GitHub Copilot Code Review: ~20% cost cut and org default review depth
Copilot Code Review switched to grep/rg/glob/view tools and now costs ~20% less. Admins can set default review depth for the whole org. CLI adds queueing and debug-logs.
Categories: xAI, GitHub, Perplexity, Linear, Vercel, Anysphere (AI features)
29 noviniek
Results
Nedeľa 28. júna 2026
Sobota 27. júna 2026
GitHub Copilot enterprise managed settings now support strictKnownMarketplaces in VS Code and Copilot CLI
GitHub Copilot added an enterprise admin setting strictKnownMarketplaces that locks extension/plugin installs to approved marketplaces. It applies to both VS Code and the Copilot CLI, closing a supply-chain attack vector via third-party extensions.
Deep Agents and OpenCode are now available in the AI SDK Harness
Vercel added two new adapters to the AI SDK Harness — LangChain Deep Agents and OpenCode — letting you run either coding-agent runtime through one unified HarnessAgent API inside a Vercel Sandbox.
Introducing /goal in Grok Build
xAI added /goal to Grok Build — a long-running autonomous mode that plans, executes and verifies multi-step coding tasks with status, pause, resume and clear controls.
Piatok 26. júna 2026
GitHub Copilot for Jira is now generally available
Copilot for Jira moves from public preview to GA, with streaming agent progress in Jira tickets, post-session steering that continues on the same draft PR, and simplified org/repo onboarding.
Štvrtok 25. júna 2026
Vercel AI Gateway adds GLM 5.2 Fast via Wafer at 170+ tokens/s
Z.ai's GLM 5.2 Fast is now available via Wafer on Vercel AI Gateway, averaging 170+ tokens/s with 2x the throughput of other providers.
Vercel AI SDK 7.0.19: First framework-native MCP Tool Drift Detection against malicious tool redefinition
Vercel AI SDK 7.0.19 introduces Tool Drift Detection — the first framework-native protection against MCP 'rug pulls' where malicious servers dynamically redefine tool schemas mid-session. Each MCP tool receives a fingerprint at registration.
GitHub Copilot changes model selection for Free and Student plans
GitHub adjusted the model lineup for Copilot's Free and Student tiers, changing which models are reachable from those plans.
Streda 24. júna 2026
GitHub Copilot CLI new terminal interface is generally available
GitHub shipped GA of a new Copilot CLI TUI with tabs for Session, Gists, Issues, and PRs, inline MCP/skills/plugin commands, and screen reader detection.
Utorok 23. júna 2026
New features and Claude as agent provider preview in JetBrains IDEs
GitHub Copilot in JetBrains IDEs now lets users pick Claude from the agent provider menu by pointing at a local Claude Code CLI install. The same release adds org/enterprise GitHub agents, queue-and-steer in Copilot CLI sessions, and an agent debug-logs summary view.
Grok 4.3 Available on Amazon Bedrock
xAI becomes the third independent lab on Bedrock after Anthropic and OpenAI. 1M context, configurable reasoning effort, $1.25/$2.50 per M tokens.
Sakana Fugu Ultra now available on AI Gateway
Vercel AI Gateway added Sakana AI's Fugu Ultra, a multi-agent orchestration model that routes work across 1-3 frontier-model agents and merges results, benchmarking comparably to Claude Mythos Preview and Fable 5.
Introducing Grok for Microsoft Word
Free Grok add-in for Word, Excel and PowerPoint with live web research, inline source citations, X data lookups, Mermaid diagrams, and connectors for email, SharePoint and Google Drive.
Grok Comes to Databricks Agent Bricks
Grok models are now natively available in Databricks Agent Bricks. Agents can reason directly over Lakehouse data without exfiltration, with governance through Unity Catalog.
Pondelok 22. júna 2026
Perplexity Comet for iOS: phone actions, iPad sidebar, Finance Deep Dive tab
Comet for iOS shipped its eighth round of improvements: one-tap phone-number actions (Call, FaceTime, Message, save to Contacts), a refined iPad sidebar, and Finance Deep Dive opening as a real browser tab.
xAI Grok Build: Voice Agent Builder Beta — No-Code Voice AI at $0.05/min with SIP and Voice Cloning
xAI launched Voice Agent Builder in beta — a no-code platform for production voice agents on Grok Voice with telephony, SIP, voice cloning, and observability at $0.05/min. Available from July 1, 2026.
Vercel Connect: Secure access to external services for your agents
Vercel launched Connect, a new agent-infrastructure primitive providing short-lived scoped OAuth tokens for Slack, GitHub, Linear, Notion, Salesforce, Figma, Snowflake, Discord, plus generic OAuth/API-key and MCP server connectors.
Nedeľa 21. júna 2026
Linear: release pipeline changelogs, private sub-teams and per-tab desktop history
Linear adds auto-generated changelogs to release pipelines, ships private sub-teams for Business/Enterprise, and rebuilt desktop tabs so each tab keeps its own navigation history.
GitHub Copilot — Fix PR Comments via Cloud Agent Directly from Mobile
GitHub Mobile app gained the ability to fix pull request comments using the Copilot cloud agent directly on iOS/Android — no desktop editor required.
Vercel Launches Konsistent for Unified Code Standards Across AI Agents and Humans, Plus Security Dashboard and Dry-Run Deployments
Vercel shipped Konsistent on July 1 to enforce uniform code standards for both AI agents and human developers, alongside a Security Dashboard in private beta and dry-run deployments for the Vercel CLI.
Grok 4.3 hits GA on Amazon Bedrock with 1M context on the new Mantle inference engine
The first xAI model on Bedrock — Grok 4.3 with a 1M context window, configurable reasoning effort, $1.25 in / $2.50 out per MTok. Cheapest US-lab frontier reasoner on Bedrock.
Sobota 20. júna 2026
MAI-Code-1-Flash available on more Copilot surfaces
Microsoft's small coding model MAI-Code-1-Flash is rolling out across eight Copilot surfaces: CLI, Copilot app, Chat on GitHub, Visual Studio, GitHub Mobile, JetBrains, Eclipse, and Xcode.
AI credits consumed per user now in the Copilot usage metrics API
The Copilot usage metrics API now exposes an 'ai_credits_used' field with total AI credit consumption per user in both daily and 28-day reports at the enterprise and org levels.
Upcoming deprecation of Opus 4.6 (fast) in Copilot
GitHub announced the deprecation of the Opus 4.6 (fast) model in Copilot; users are advised to migrate to current Opus generations or to Microsoft's MAI-Code-1-Flash for fast tasks.
Piatok 19. júna 2026
Cursor 3.8: /automate skill, GitHub and Slack triggers, computer use
Cursor 3.8 introduces a /automate skill that creates an automation in your local agent session from a plain-language description, plus new GitHub and Slack triggers and computer-use support.
Cursor Router: Intelligent Model Routing with Intelligence, Balance, and Cost Modes
Cursor launched Cursor Router on July 22, an intelligent model routing system that classifies each request by type and complexity and routes it to the optimal model based on quality or cost preference.
GitHub Copilot app generally available
The native desktop home for agent-driven development hit GA on all three OSes. Voice conversations via on-device speech-to-text, integrated with session management and github.com.
Introducing eve — open-source agent framework
Eve is a TypeScript-native open-source framework where every agent = a directory of files (instructions.md + tools/ + skills/). Built in: durable execution, per-agent sandbox, human approvals, evals, OpenTelemetry. Plus the Sandbox runtime now goes up to 24h.
Cursor Bugbot now on Composer 2.5: 3× faster, cheaper
The new Bugbot cuts review time from ~5 minutes to ~90 seconds, finds 10 % more bugs and costs 22 % less per run; adds a /review pre-push flow.