47 noviniek
Copilot CLI from July 1 automatically selects the best model per task (Auto mode, 10% discount). Enterprise customers now get real-time streaming of Copilot agent session data into external tools via a streaming endpoint or REST API.
Anthropic on July 22 updated the Claude Managed Agents API: configurable effort levels on model configuration, webhooks for environment and memory store lifecycle events, session seeding with initial events, and event deltas for subagent thread streaming.
Claude Opus 4.8 and Haiku 4.5 are now GA in Microsoft Azure Foundry with native Azure authentication, consolidated billing through Microsoft Enterprise Agreements, and optional US data zone for compliance.
Anthropic released Claude Apps Gateway — a self-hosted control plane for enterprise Claude Code on Amazon Bedrock and Google Cloud, with SSO (OIDC), central policy enforcement, per-user spend limits, and OTLP telemetry.
The July 19, 2026 Claude Code update changes /verify and /code-review skill behavior — Claude no longer triggers them autonomously, only on direct invocation. Increases agentic pipeline predictability.
GitHub Copilot added Kimi K2.7 Code from Moonshot AI as the first open-weight model in the model picker, rolling out to Pro, Pro+, and Max plans with Business and Enterprise expansion planned.
Copilot Agent is now available inside JetBrains AI Assistant, expanding agentic coding to millions of IntelliJ-based IDE users. Enterprise admins can now set per-user AI credit budgets for cost centers. Claude Sonnet 5 is also GA in Copilot.
Anthropic raised Claude API rate limits across the board — Sonnet and Haiku now match Opus at every tier — and collapsed usage tiers into three (Start, Build, Scale), powered by a new SpaceX compute deal.
GitHub Copilot now offers Claude Opus 4.8 in a new fast-mode preview that delivers significantly faster output token speeds while keeping the same intelligence as standard Opus. The variant is rolling out to Copilot users in preview, aimed at speeding up agentic and long-form coding tasks.
Vercel's AI Gateway adds beta support for realtime voice agents, text-to-speech, and speech-to-text, so developers can build conversational voice apps without juggling separate providers. Audio models route through AI SDK 7 with the same observability, BYOK and spend controls as text models, at no extra Gateway fee.
The desktop Copilot app can now connect your own API keys to OpenAI, Azure, Anthropic, Ollama or LM Studio. Keys are stored in the OS keychain and traffic routes through your own account or gateway.
The Copilot usage metrics API adds a new total_pull_requests_merged field in adoption phase reports. Enterprise admins now see daily merged PR counts by user adoption phase.
New `vercel metrics` command exposes Web Analytics directly via the CLI. Supports filters, dimensions, and is positioned for coding agents to answer questions about UTM campaign performance or mobile-vs-desktop conversion.
Concurrent build capacity for Pro teams jumped from 12 to 500. Enabled by default on Pro and Enterprise plans, billed on actual build minutes consumed.
Vercel auto-detects server.ts in the root or src/ and deploys it as a Node.js application without configuration. Supports native Node HTTP, Express, Koa, and NestJS.
Perplexity Deep Research upgrades to Claude Opus 4.6 for Max users. Finance equity pages gained analyst ratings, 52-week price targets, and AI-synthesized news. The Agent API adds GPT-5.6 Sol/Terra/Luna and Grok 4.5 as first-party options.
Microsoft on June 26 made MAI-Code-1-Flash, its fast 5B-parameter coding model, generally available for GitHub Copilot Business and Enterprise plans.
GitHub Desktop 3.6 brings native Git worktree support and Copilot SDK-powered commit messages and merge conflict resolution.
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.
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.
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.
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.
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 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 adjusted the model lineup for Copilot's Free and Student tiers, changing which models are reachable from those plans.
Anthropic released Claude Tag — a Slack-native agent you tag with @Claude to delegate work. Internally it ships 65% of product team code changes.
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.
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.
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.
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.
Anthropic shipped new versions of three Claude API tools. code_execution_20260521 surfaces the 90-second per-cell execution limit. web_search_20260318 and web_fetch_20260318 add a response_inclusion parameter to trim consumed result blocks in agentic workflows.
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.
Claude Code version 2.1.219 (July 24, 2026) sets Claude Opus 5 as the default Opus model with 1M context window, adds sandbox.network.strictAllowlist setting for sandboxed commands, and introduces a DirectoryAdded hook that fires when a new working directory is registered mid-session.
Claude Code now has /config key=value mid-conversation, macOS sandbox controls, and Apple Events — it can drive Mail, Calendar, Finder. The companion v2.1.183 blocks destructive git commands in Auto Mode.
Anthropic shipped a set of Claude Managed Agents API updates on July 22, 2026: effort levels on agent model config, webhooks for environment and memory store lifecycle events, session seeding with initial events, and thread-level event streaming deltas.
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 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.
Google deprecated temperature, top_p, and top_k sampling parameters for the latest Gemini models. The API also now allows combining built-in tools (Google Search, code execution) with custom function calling in a single request.
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.
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.
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.
A Claude Code session can now be turned into a sharable, interactive HTML page with live code and multiple data sources — one URL for the team. Repositions Claude Code from assistant to internal-app builder.
The new Claude Design keeps a project aligned with the design system, syncs both ways with Claude Code via /design-sync, and lets you edit directly on the canvas. Imports brand from a GitHub repo, design files, or raw uploads.
Mid-conversation system messages are now GA without a beta header on Claude Fable 5, Mythos 5, and Opus 4.8 across the Claude API, Amazon Bedrock, and Google Cloud. Updating system instructions mid-conversation no longer invalidates cache prefixes.
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.
Fable 5 is the first public-facing version of the Mythos generation; top-tier software engineering, knowledge work and vision, with hard safety guardrails.
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.
