coding agents

Cline CLI v3.0.69 raises the default MCP server startup timeout from 3 seconds to 10 seconds. On Windows, servers launched via npx or uvx were being silently dropped. The release also fixes Claude requests through custom Anthropic base URLs, reasoning-level mismatches, and a broken `cline config --json` command.

Cline CLI v3.0.68 fixes a performance bug in which every streamed chunk re-saved the entire agent-team state, slowing long runs and letting ~/.cline/data/db/teams.db grow to gigabytes. The release also refreshes the model catalog and changes default models for five providers.

Unbiased has released Pareto, a multimodal composite model aimed at research, coding, and agentic workflows. The model offers a 262K context window and is priced at $2.50 per million input tokens and $7.50 per million output tokens via OpenRouter.

Augment Code says its internal 'software factory'—a network of specialized agents built on its Cosmos platform—drove a 4.5x increase in size-adjusted developer output and cut median PR merge time from 11.2 to 3.1 hours over nine months. The company frames this as evidence that once AI writes nearly all new code, the bottleneck shifts to review, verification, and incident response.

Meta's new Muse Spark model comes with a two-tier pricing scheme: a standard rate, and a discounted 'contributor' rate — up to 95% cheaper — for customers who let Meta use their prompts and outputs for training future models. The move follows a failed attempt earlier this year to track employee computer usage for the same purpose.

GitHub has published a beginner-focused guide explaining how to run multiple Copilot agents concurrently within the GitHub Copilot app. The post walks new users through the workflow of parallel agent execution rather than announcing a new model or feature.

Slack has launched Slack Code, a feature that gives AI coding agents dedicated project channels where developers and non-technical staff can watch, review, and redirect their work in real time. Anthropic, GitHub, OpenAI, Cognition, and Vercel are building integrations, bringing Claude, Copilot, ChatGPT, and Devin into Slack's group chat environment.

OpenAI has shipped a security update for Codex after users reported that GPT-5.6 Sol was autonomously deleting real files instead of temporary ones. The bug stemmed from misused system variables like $HOME pointing cleanup commands at actual home directories.

Alibaba's Qwen team has released Qwen3.8-27B, a 27-billion-parameter dense vision-language model with 262,144-token native context extensible to 1 million tokens. The model shows gains over Qwen3.6-27B and Qwen3.7-Plus across coding, agentic, and multimodal benchmarks, according to Alibaba.

ByteDance Seed has released Seed 2.1 Turbo, a multimodal model targeting coding and long-horizon agent workflows with a 262K token context window. The model is priced at $0.50 per 1M input tokens and $2.50 per 1M output tokens, and is now listed on OpenRouter.

OpenAI has published a field report documenting eight scientific computing projects that used its Codex coding agent — alone or alongside Anthropic's Claude Code — to reduce software build times. The report is a vendor-authored survey, not an independent study.

A new Epoch/METR benchmark called MirrorCode shows Claude Opus 4.7 reimplementing large software programs from scratch in tasks estimated to take humans 2-17 weeks, for $251 in inference cost. Separately, Anthropic reports Opus 4.7 completed a suite of quadruped robot tasks in 9 minutes 35 seconds, down from 181 minutes with an earlier model assisting humans.

Mistral AI released Medium 3.5, a 128B dense model with a 256k context window that scores 77.6% on SWE-Bench Verified. The model powers new remote coding agents in Mistral Vibe that run asynchronously in the cloud, plus a new Work mode in Le Chat for multi-step agentic tasks.