Skip to main content
Glama

mistral_request

Destructive

Run Mistral Vibe CLI requests synchronously with support for structured prompts, agent modes, and async fallback. Controls output format, session management, and approval policies.

Instructions

Run a Mistral Vibe CLI request synchronously (when async jobs are enabled, auto-defers to a pollable job past the sync deadline; otherwise runs to completion). Requires exactly one of prompt or promptParts. Defaults to --agent accept-edits (auto-accepts file edits; dangerous ops such as shell stay gated); pass permissionMode auto-approve (or set LLM_GATEWAY_APPROVAL_ALLOW_BYPASS) for unattended tool execution.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelNoModel alias (e.g. mistral-medium-3.5, latest). Resolved alias is injected via VIBE_ACTIVE_MODEL env var; Vibe has no --model flag.
trustNoEmit `--trust` so Vibe trusts the cwd for this invocation only (not persisted to trusted_folders.toml) and skips the interactive trust prompt (Phase 4 slice γ).
addDirNoVibe --add-dir <DIR>: additional writable workspace directories. Each entry is emitted as its own --add-dir instance (Vibe states this flag may be specified multiple times). Stdio/local callers may pass local paths directly. Remote HTTP/OAuth callers must use relative paths inside a selected registered workspace. Do not call workspace_* tools to fix stdio/local provider path access.
promptNoPrompt text for Mistral Vibe (mutually exclusive with promptParts)
maxPriceNoVibe `--max-price DOLLARS`: interrupt the session when cumulative cost crosses this cap (programmatic mode only, Phase 4 slice δ). Bounded to finite values ≤ 10000 USD.
maxTurnsNoVibe `--max-turns N`: cap the agent-loop iteration count (programmatic mode only, Phase 4 slice δ). Bounded to safe integers ≤ 10000.
worktreeNoSlice λ: run this request inside a dedicated git worktree owned by the gateway. `true` creates a fresh worktree at `<repoRoot>/.worktrees/<uuid>` branched from HEAD. `{ name?, ref? }` lets the caller supply a sanitized name and/or a git ref (default: HEAD). When the request carries a sessionId and the session already has a worktree, that worktree is reused. The gateway spawns the child CLI with `cwd: <worktree-path>` — no `-w`/`--worktree` flag is ever emitted to the underlying CLI. On session_delete or TTL eviction the gateway runs `git worktree remove --force`. Successful responses are prefixed with `[gateway] worktree=<absolute-path>\n` so callers can use the path. NOTE: callers should `.gitignore` the `.worktrees/` directory in their repo (the gateway does NOT auto-gitignore — see slice λ spec Q4).
maxTokensNoVibe `--max-tokens N`: cap cumulative prompt + completion tokens for the session (programmatic mode only). Bounded to safe integers ≤ 100000000.
sessionIdNoSession ID (user-provided CLI handle for --resume). Current Vibe defaults session logging on; doctor flags explicit [session_logging] enabled = false. Note: the gw-* id minted for a brand-new session is not resumable via sessionId; continue with resumeLatest:true.
transportNoTransport: 'cli' (default) runs the Vibe CLI; 'acp' routes through `vibe-acp` when [acp].enabled and the provider's runtime_enabled are set (fails closed otherwise).cli
workspaceNoRegistered workspace alias for remote HTTP/OAuth provider calls. Do not use this field, workspace_list, or workspace_register_existing_repo as a fallback for stdio/local provider path access; pass workingDir/addDir/includeDirs directly instead.
mcpServersNoMCP server names for approval tracking (Vibe manages its own MCP config via `vibe mcp`)
workingDirNoVibe --workdir <DIR>: change to this directory before running. Single value (Vibe accepts one --workdir per invocation). Stdio/local callers may pass local paths directly. Remote HTTP/OAuth callers must use relative paths inside a selected registered workspace. Do not call workspace_* tools to fix stdio/local provider path access.
promptPartsNoCache-aware structured prompt: { system?, tools?, context?, task }. Mutually exclusive with prompt. Stable parts hash into cache_state for prefix-discipline tracking.
allowedToolsNoAllowlist of built-in tools — each emitted as a separate --enabled-tools <tool> flag
forceRefreshNoBypass dedup and force a fresh CLI run even if a recent identical request exists
outputFormatNoOutput format for Vibe 2.x (text|json|streaming). Legacy aliases plain→text and stream-json→streaming are accepted.
resumeLatestNoResume most recent Vibe session in cwd (--continue). Note: the gw-* id minted for a brand-new session is not resumable via sessionId; continue with resumeLatest:true.
correlationIdNoRequest trace ID (auto if omitted)
idleTimeoutMsNoIdle timeout in ms (min 30s, max 1h, omit=CLI default)
approvalPolicyNoApproval policy when approvalStrategy is mcp_managed: strict|balanced|permissive (default balanced). Ignored under legacy strategy.
optimizePromptNoOptimize prompt before execution
permissionModeNoVibe --agent name. Builtins: default|plan|accept-edits|auto-approve; Vibe also accepts install-gated builtins (e.g. lean) and custom agents from ~/.vibe/agents, so any name is passed through. Defaults to accept-edits; pass auto-approve (or set LLM_GATEWAY_APPROVAL_ALLOW_BYPASS) for unattended tool execution.
disallowedToolsNoAccepted for caller parity; Vibe has no deny-list flag, so values are ignored (a warning is logged).
approvalStrategyNoApproval strategy: legacy (default) lets the provider CLI's own flags decide; mcp_managed routes the run through the gateway approval gate (required for approvalPolicy and approval_list). Under mcp_managed the caller's permissionMode/alwaysApprove may be overridden by the gate.legacy
compressResponseNoCompress the response display text via the native compressor (default: [compression].enabled in config.toml, off unless opted in). Skipped for structured output.
createNewSessionNoForce new session
optimizeResponseNoOptimize response output
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses behavioral traits beyond annotations: synchronous run logic, auto-deferral, default permission mode, dangerous ops gating, worktree lifecycle. No contradiction with annotations (destructiveHint=true aligns with potential file edits).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense with information but efficiently front-loaded. Every sentence serves a purpose, though it could be slightly more concise without losing crucial details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite no output schema, the description covers core behavior, async fallback, parameter key notes, and output format options. It provides adequate completeness for a complex tool with 28 parameters and nested objects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 100% schema coverage, baseline is 3. The description adds significant value by explaining permissionMode defaults, trust bypass, sessionId limitations, worktree details, and parameter interactions (e.g., promptParts structure).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool executes a Mistral Vibe CLI request synchronously, with auto-deferral to async when necessary. It distinguishes from the async sibling tool by specifying synchronous execution and fallback behavior.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description specifies that exactly one of prompt or promptParts is required, and explains defaults for permissionMode and unattended execution. While not explicitly stating when not to use, the synchronous vs async distinction provides clear context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/verivus-oss/llm-cli-gateway'

If you have feedback or need assistance with the MCP directory API, please join our Discord server