pypi mistral-vibe 3.1.3
v3.1.3

one hour ago

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
  • On a first run, --model naming a model from Mistral's model list no longer fails with "Unknown model" while that list is still loading
  • Installing or upgrading Vibe on Python 3.15 no longer fails building cffi or rpds-py from source, and the documented install commands now pass --python 3.14
  • A pasted image that cannot be attached now shows why, such as a full disk or a missing file, instead of failing with 'Image file is outside the workspace or session attachments'
  • Third-party providers that add name to streamed chunks after the first one (such as OVHcloud AI Endpoints) no longer fail every call
  • On Windows, auto-approved file reads and writes on Git Bash paths like /c/Users/... no longer land in a stray C:\c\... directory
  • Sessions with many images or large tool results no longer become impossible to resume with "stored JSON document is at capacity: runtime-state.json"
  • Smart approve no longer asks for approval on every tool call when the session uses a model that rejects temperature 0, such as some reasoning models
  • Subagents no longer fail with "child Session does not retain the requested generation" when a pre_agent hook is configured
  • A subagent's view now names the model its active_model selects instead of the main session's model
  • Resuming a session that used many subagents no longer takes minutes to show the prompt
  • First run on Linux without an API key no longer hangs at "Starting the app server…" waiting on a keyring unlock prompt
  • A VIBE_* environment variable Vibe cannot use now shows a warning naming the wrong fields, instead of being ignored silently
  • Tool filters naming a former tool, such as grep or web_fetch, now show a warning saying what replaced it, rather than silently matching nothing
  • The install script and vibe update now work behind TLS-inspecting corporate proxies (uv 0.11+): the install script makes uv trust the system certificate store, and vibe update does so when enable_system_trust_store is on
  • A third-party provider that ends its answer without any content is now retried twice, then fails the turn with a clear error instead of being retried for minutes
  • A folder whose only project config is .vibe/hooks.toml or .vibe/skills.toml now asks to be trusted, and vibe -p warns that it is ignored until --trust, instead of skipping it silently
  • On Windows, creating a new file in a git worktree or a repository with .gitattributes no longer hangs
  • On Windows, Enter and Ctrl shortcuts keep working after a command run by the agent changes the console's input mode
  • Question tabs wrap onto several rows in narrow terminals instead of being cut off
  • Removing the oldest of several queued messages no longer shows the remaining one twice once it is sent
  • @ file completion now finds files anywhere in large repositories, not only those sorted among the first 32,000 paths
  • vibe --setup onboarding screens no longer go blank in small terminals: the theme picker and the sign-in options render in short terminals, with an enlarge-terminal notice only when nothing fits
  • A trusted folders file that cannot be read or parsed is now kept instead of being reset to empty at startup
  • Plugins are no longer listed under "Not loaded" in /plugins by mistake: plugin knowledge no longer fails with a permission error, and plugins that loaded are no longer listed there or warned about at startup because of informational notes
  • A turn that was running while the computer slept now continues after the wake instead of failing with an invalid API key error: it waits up to two minutes for your Mistral sign-in, and retries once with a refreshed one
  • A config list entry missing its name, such as an empty [[mcp_servers]], now shows a configuration error saying what to fix instead of an internal error
  • mistral-large-latest is treated as the model the Mistral API serves under it, today Mistral Large 4: a 1,048,576-token window, low, medium and high thinking (off uses low), and earlier reasoning kept in its requests
  • Payment refusals now say why: a turn refused because the account has no credit left says so instead of a generic backend error, and an HTTP 402 refusal, such as a reached spending limit, shows the reason without the raw error body and no longer offers /retry
  • Requests no longer fail with process() takes no keyword arguments when an old brotli package is installed, as in some conda environments
  • Connectors exposing more than 128 tools now load with all their tools instead of being dropped
  • Moving a local session to another project right after its turn ends no longer fails with "Session is already open"
  • Quitting while the session is still shutting down no longer crashes the app server
  • Plugins that ship manifests for several agents, such as Superpowers, now load instead of being rejected as ambiguous
  • Under OIDC sign-in, model calls now use the session's own organization and workspace instead of the first one your account can reach, which could be an organization without access to the model
  • A model your plan does not include no longer makes every later message fail with "credential was rejected" until a restart
  • When the provider refuses a model call for a reason other than the API key, such as the model not being in your subscription tier, Vibe now shows the provider's reason instead of calling it an invalid API key
  • Pull request status keeps syncing between Vibe sessions on Linux when the file watcher limit is reached
  • Typing /teleport or /remote-project now shows that the command was removed instead of sending it to the model

Removed

  • The "Hello , how can I help you?" greeting under the startup banner, and its show_greeting setting. Configs that still set show_greeting load without a warning

Don't miss a new mistral-vibe release

NewReleases is sending notifications on new releases.