Skip to content
MV

Mistral Vibe v3.1.3

Released · Mistral AI

BreakingSecurity fixChanges hooks, subagent definitions, permission rules, settings files, skills and plugins

Models:Makes Mistral Large 4 the default

What the release notes say

Added

  • Ctrl+S stashes the input box draft, which comes back after you send another message
  • /goal <objective> sets a goal Vibe keeps working on across turns until it is done. /goal edit, /goal pause, /goal resume and /goal clear manage it
  • max_goal_token_budget in config.toml caps the token budget a goal may set, and is the budget of a goal set without one
  • The /model picker has a / fuzzy search row that filters the model list as you type. Arrows and Enter keep working while searching, and Esc leaves the search, clears the filter, then closes
  • vibe -p --thinking LEVEL sets the model's thinking level for one run, without saving it
  • /raw [on|off] shows agent messages as raw Markdown, so a selection copies their source text
  • pre_llm hooks run before each call to the model and can stop the turn
  • post_llm hooks run after each model response, tool calls included, and can ask the model to try again, within a budget of 3 retries per turn shared with post_agent hooks
  • /loop on its own opens a loop manager that lists the scheduled loops with their schedule and next run, deletes one with d, and adds one from a title, an interval or cron, and instructions with n. While the session is idle, the row above the input shows the next scheduled loop and its title
  • Inside tmux with mouse off, a startup warning explains how to scroll the conversation, and Ctrl+N hides it for good
  • /trusted-folders lists trusted and untrusted folders, flips or forgets a decision, and trusts a new folder with path completion
  • The post_agent hook payload includes turn_id and response_text, the turn's final answer
  • show_dangerous_directory_warning = false hides the startup warning shown when Vibe runs in the home directory or another risky folder

Changed

  • When Vibe quits, it waits for session_end and notification hooks still running for 2s at most, instead of 5s
  • A project's .vibe/config.toml or an agent profile can turn usage telemetry off but no longer turn it back on: its enable_telemetry = true is ignored with a warning
  • post_agent hooks now share their 3 retries per turn with post_llm hooks. A retry the turn has no step left for fails the turn, naming the hook, instead of an internal error
  • vibe -p prints the reason when a hook ends the turn without the model's answer
  • Image paths are only turned into image placeholders when pasted or dropped on their own, never while typing or when recalling a prompt. Pasting a path again right after it became an image placeholder or @ mention keeps it as plain text
  • Picking a model's default thinking level no longer pins it in your config, so the model follows later changes of that default
  • A pause inside a script the agent runs now reads "Script in progress, next step in 5s" instead of "Sleeping"
  • When your API key does not use your Vibe Pro plan, a box under the banner now says so on every start and explains how to switch keys, and /whoami explains it too. The Vibe Pro upgrade offer now shows in its own box under the release notes
  • Vibe no longer shows a warning when a provider's model catalog has no entry for the model or cannot be reached, since it falls back to its built-in model table. The warning is only written to vibe.log
  • When you return to an answered question, a green › marks the answer you gave
  • On a question you answered with your own text, ←→ keep switching questions and e edits the answer
  • After interrupting a turn, ↑ selects the queued messages so you can edit or remove them before sending the queue
  • When your Mistral provider's api_base is outside mistral.ai and its subdomains (a self-hosted deployment), Vibe no longer contacts Mistral's experiment service and no longer sends crash reports to Mistral, even with telemetry on
  • Voice dictation and read-aloud now use the server of your Mistral provider's api_base instead of api.mistral.ai (except api.eu.mistral.ai and api.us.mistral.ai, which keep api.mistral.ai), unless transcribe_providers or tts_providers in your config set another address
  • A model's own auto_compact_threshold, such as the one the model catalog sets, now wins over a top-level one, including one from your organization's admin config. To apply one value to every model, an admin adds a [[models]] entry per model with its name, provider and auto_compact_threshold
  • The welcome banner cat plays one animation round on start and stops. A click on it replays the round
  • Voice features are now installed by default on ARM64 Linux, so the voice and voice-aarch64 extras are no longer needed
  • Shell commands that read protected files now ask for approval even when the reading command is otherwise allowed, in POSIX shells and PowerShell. When Vibe cannot tell exactly which files a read touches (variables, brace expansion, recursive or piped reads, a change of directory, an interpreter wrapper), the approval covers only that exact command
  • /resume shows a Resuming spinner while the picked session loads
  • Mistral Large 4 is now the default model. To stay on Mistral Medium 3.5, or if your own Mistral server does not offer Large 4, set active_model = "mistral-medium-3.5"

Fixed

  • With tool calls made together, each pre_tool hook line shows above its own tool instead of all of them above the first tool
  • Undo now restores a prompt draft cleared with Ctrl+C or a double Esc
  • Approving permanently no longer fails after the directory Vibe was started in is deleted
  • vibe.log no longer reports a model provided by an experiment as unavailable at startup, and reports a model that is really missing only once per process
  • Allowing a tool for the session or permanently now also approves the parallel calls it covers, instead of asking for each one
  • Reaching max_subagents no longer blocks new subagents: the one that has waited longest is closed to make room, up to 128 subagents per session