vibehacker
News
GitHub (mistralai/mistral-vibe) ·

Mistral Vibe 3.0.1 lets admins ban YOLO mode and makes headless runs wait for, and price, their subagents

Released Oct 20, a day after 3.0.0, it adds an admin-managed enable_auto_approve = false that hides auto-approve agents and ignores --yolo, makes vibe -p wait for subagents its turn left running and export each one's model, usage, and cost, and adds an experimental vibe run-server that runs many headless sessions from one process. It also drops the Python 3.14 requirement 3.0.0 introduced back to 3.12+, and retries answers cut off at the output-token limit instead of ending the turn.

Read at github.com
Mistral
Le Chat and frontier open-weight models from Mistral AI

More news

View all

OpenCode 2.1 adds Windows persistent terminals and todo lists, but breaks plugin and SDK contracts

The Oct 20 release brings persistent PTYs to Windows x64 and ARM64, an opt in todowrite task list via { "experimental": { "todo": true } } , TUI and plugin commands that can outlive Bun's five minute fetch deadline, restored session archiving, editable saved permissions, and compaction that summarizes the whole conversation and kicks in earlier. Plugin, SDK, and HTTP message/event integrations must adopt renamed fields (provider replay data is now native ), though existing sessions and credentials still load with no database migration…

OpenCode Changelog

AWS's kiro-trace mines Kiro's own runs for fixes, but only deterministic checks decide what ships

The internal loop finds where Kiro fails or wastes effort, proposes one prompt or tool change at a time, and keeps it only if a code based gate (including a full benchmark run against a re run control) and then a human reviewer accept it; in its first week it opened eight PRs and seven merged, including an 83% cut in redundant file re reads and a compaction fix that raised retention from 0.82 to 0.92. A leaner tool and prompt profile that scored 82.4% vs 77.5% pass@1 on Terminal Bench 2.1 at about a third of the token cost is still under review, and all figures are Amazon's internal experiment deltas…

Kiro Blog

GitHub Copilot drops GPT-5.5, GPT-5.4, Grok 4.5, and Gemini 3.7 Flash as of Oct 19

The six models, including GPT 5.4 mini and GPT 5 mini, are gone from Copilot Chat, inline edits, ask and agent modes, and completions; GitHub suggests GPT 6.1 Sol, GPT 6 Luna, Grok 4.7, or Gemini 3.8 Flash instead, which Enterprise admins may need to enable. Admins can now also read and change those model policies at the enterprise, team, app, and org level through new GA REST endpoints (changelog)…

GitHub Changelog

Mintlify Autopilot watches your merges, Slack, and support tickets, then opens doc-update PRs on its own

The always on agent, now in beta on Pro and Enterprise plans, reads merged diffs, repeated support questions, and flagged Slack threads, drafts the doc change, and opens a pull request that a teammate must merge, learning your team's tone from each review. It costs 250 credits per PR it opens or updates (runs that find nothing are free), and Pro plans can only connect GitHub and Slack…

Mintlify Blog

Spotted something we missed? Start a thread.