Anthropic Releases Eight Claude Code Updates in August Focused on Multi-Agent Workflows
Between August 13 and 21, Anthropic released eight versions of Claude Code (2.1.232 through 2.1.239). The updates focus on scaling agent-based workflows so that multiple agents can operate in parallel for extended periods.
The most significant change arrived in 2.1.232 with subagent forking. When a subagent is launched using subagent_type: "fork", it now inherits the full context and prompt cache of the parent session. This eliminates the need to re-explain project architecture, database schemas, test locations, and prior decisions. Forking is enabled by default.
Interactive sessions also received background execution improvements. Non-teammate agents move to the background and no longer occupy the main dialog. The /code-review command at high, xhigh, and max effort levels now runs as a background agent, allowing developers to continue working on new features while reviews proceed.
Sessions gained the ability to communicate with each other. Users can mention another session by name using the @ symbol, triggering a SendMessage call. Interactive sessions on the same machine now receive unique names automatically. Version 2.1.236 added notify_when_idle support, and cross-session messaging reached Windows in 2.1.239.
In 2.1.234, Claude Code gained the ability to automatically resume a turn after the claude.ai usage limit resets. The feature can be disabled in configuration under “Continue automatically at usage limit.” Combined with background agents and forking, this extends the practical horizon for long-running tasks.
Starting August 14, new interactive sessions on Pro, Max, and Team plans launch in auto mode by default. A separate classifier model evaluates actions instead of prompting the user for every permission. Existing permission rules such as permissions.deny and permissions.ask still take precedence. Users can define environment policies and hard_deny rules in natural language within the autoMode section of their configuration.
Additional updates include the new ANTHROPIC_DEFAULT_MODEL environment variable, a Concise output style, improved GitLab worktree and merge request support, memory leak fixes for long sessions, and native add-on support for Alpine and musl builds in 2.1.239. Several quiet changes also appeared, such as the disabling of todo tools for newer models and optional memory limits for Bash commands via cgroup.
Related articles
Deploying Self-Hosted Hysteria 2 Proxy on Debian-Based Linux VPS via Terminal
A detailed guide explains how to set up a personal Hysteria 2 proxy server on a KVM VPS running Debian or Ubuntu without any web panels. The process begins with generating ed25519 SSH keys, hardening the sshd_config file, and restricting access with ufw to only TCP port 22 and UDP port 443. Hysteria 2 is downloaded from GitHub, made executable, and configured using a TOML file that enables salamander obfuscation and a self-signed TLS certificate. A custom systemd unit ensures the service restarts on failure. The client configuration includes SHA256 pinning of the server certificate to prevent MITM attacks. The guide emphasizes manual CLI operations that apply equally to other services such as Nginx and stresses checking local laws before deployment.
Rostec Scales PCAT Platform Nationwide as Russia's First Industrial Marketplace
Rostec has expanded its PCAT platform to every organization within the state corporation that manufactures civilian products. Operating since 2025 and upgraded in September 2026, the platform now unites more than 180 enterprises and research organizations. Its catalog contains over 1,250 finished products along with 370 technological and manufacturing competencies. Visitors can locate not only equipment and components but also partners able to design, test, or produce required solutions. The portal receives more than 23,000 weekly visits, 60 percent of them from corporations and large enterprises. Rostec is extending the network into the regions through supply-chain agreements already signed with Krasnodar Krai and the oblasts of Tver, Tula, and Ryazan. In parallel the corporation launched the Robot Management System in November 2025 for centralized control of robots, sensors, and related IT services.
Kate Mobile Loses VK API Access After New Request Limits Exhaust Quota in 1.5 Days
Popular third-party Android client Kate Mobile has been cut off from VK services following the introduction of strict monthly API request caps. VK implemented the new limits on September 7, offering verified partners up to 100 million requests per month while requiring payment for additional access by third-party services. Kate Mobile developers had requested pricing details in advance but received no response from VK. Calculations showed that the app's real user base would consume the entire 100-million-request allowance in roughly 36 hours, with the messages.send method alone generating twice the allowed volume. Caching optimizations cannot mitigate the issue because message sending cannot be cached. Developers view the change as an effort to eliminate alternative clients rather than a genuine monetization strategy. Users expressed disappointment, praising the app's long-term support and criticizing the official VK client for excessive features and advertising.
Russian AI Research Ranks High in Global Science but Struggles with Commercialization
Russia has secured third place among BRICS nations and twentieth worldwide in the number of scientific papers presented at ten leading international conferences on machine learning and artificial intelligence. According to a study by the Scientometric Center of HSE University, Russian organizations contributed 560 papers between 2020 and 2025 that received over 12,300 citations. The average international citation rate reached 3.59, surpassing India despite fewer total publications. Russian strengths are most evident in the mathematics of machine learning, optimization, and formal concept analysis, with notable results also in computer vision and speech technologies. More than 40 percent of domestic publications involve business participation, led by Yandex among companies, HSE University and Skoltech among universities, and AIRI among non-profit organizations. Significant barriers remain, including shortages of computing power, limited access to high-quality data, and weak transfer of research into commercial products, particularly in natural language processing, AI agents, and infrastructure technologies. The Ministry of Digital Development has announced plans to stimulate demand for domestic AI solutions, expand computing infrastructure, improve regulation, and accelerate the implementation of scientific developments.