AI Coding Live News

At 20:14 UTC on 2026-10-25, Moonshot AI's official account @Kimi_Moonshot (post) acknowledged rate limits and unnecessary quota consumption on the K3.1 Pro subscription plan, saying "these were our issues, and we should have fixed them sooner." Every subscriber on every plan gets a one-time usage reset that restores 25% of their monthly quota (usage below 25% resets to zero), equal to about one week of usage; usage bars update by end of day PST. Kimi also adjusted the plan's parameters and is cutting unnecessary subagent calls and output length so quota lasts longer.

@DanKornas shipped herdr-agent-quota (github.com/levi-qiao/herdr-agent-quota): an MIT Herdr plugin that groups agents under Spaces and shows model, context, and subscription quota for Claude, Codex, Grok, Agy, OpenCode, Pi, OMP, Devin, Muse, and Cursor, with remaining/used gauges and configurable low-quota alerts so parallel agents do not silently drain a shared pool.

@Jolyne_AI highlighted Pulse, a lightweight edge sidebar that live-aggregates remaining quotas and rate-limit windows across 19 AI coding services including Claude Code, Codex, and Cursor, so you need not open each vendor page. Repo: https://github.com/qunqin24/Pulse.

@DanKornas highlighted JKHeadley/instar, an open-source framework that pairs real Claude Code processes with persistent SQLite memory, cron jobs, and messaging so agents keep working across sessions. Features include SQLite/FTS5/rolling summaries with context re-injection, priority- and quota-aware scheduled work, Telegram/WhatsApp/iMessage, per-session tools/hooks/skills/MCP, plus behavioral hooks and external-operation gates. MIT.

Cline said Kimi K3 is now free in Cline Desktop for a limited time to celebrate new users and give them more tokens to explore. The team will keep it running as long as it can—a promotional quota for the open-weights Desktop experience.

OpenAI Developers announced clearer Codex usage visibility: break down quota by tasks, subagents, and individual chats so teams can tune workflows. A quoted post points developers to the Analytics tab in the Codex app and recommends updating to the latest version.

Anthropic’s temporary +50% Claude Code weekly-limit promo ends 2026-09-13; from Sep 14 the permanent +25% uplift (index 125 vs today’s 150) applies. Versus current quota that is roughly 1.25/1.5≈83%—about a 17% cut users will feel. Doubled 5-hour limits remain. Details: Claude Help Center weekly-limits promotion article.

Julius (@jullerino) announced a new Limits section under Usage in T3 Chat / T3 Code: add a CLI Proxy hub for multi-account setups, and view/redeem banked Codex usage resets inside the app. Aimed at heavy Codex and CLI-proxy users managing quotas.

OpenAI Codex/ChatGPT lead Tibo (@thsottiaux) said OpenAI will do a global usage reset for all paid subscriptions so people can keep using Astra after burning through quota. Expected around 6pm PST today.

OpenAI Codex/ChatGPT lead Tibo (@thsottiaux) says Astra usage for long-tail power users logged in with a ChatGPT account has been improved: same quality, and on the long tail up to ~3–4× less subscription usage drawn. Direct win for long-horizon coding-agent sessions.

GLM ecosystem account Lou (@louszbd) said all Coding Plan users get higher GLM-5.3-Flash usage: unlimited in ZCode from 8:00–18:00 PT daily, and — after feedback on Hermes, OpenClaw, and similar coding agents — double the standard Flash quota in other agents, applied automatically. It aligns with Zhipu lead Zixuan Li’s Sep 3–20 promo window and is a real quota bump for subscribers running GLM Flash coding agents.

OpenAI Codex/ChatGPT lead Tibo confirmed GPT-6 Astra rolled out ahead of schedule and announced a full banked usage reset today for all Plus, Pro, and Business users, landing by end of day—accounts created or upgraded before 8pm PT also qualify. A meaningful quota top-up for subscribers using ChatGPT/Codex for coding and agent work.

Anthropic's developer account said that with Fable 5.1 out, it has also reset 5-hour and weekly limits for all users. Paired with same-day availability in Claude Code and the Claude Platform, developers can try the new model against a full quota instead of waiting for the next natural reset.