Skip to main content
Glama

mistral_request

Destructive

Execute Mistral Vibe CLI coding tasks synchronously using a prompt or structured prompt parts, auto-accepting file edits while gating dangerous shell commands.

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).

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, reuse requires same-host ownership metadata and a matching live Git registration. Named path collisions never reuse manager state. Gateway-managed worktrees work with file-backed and PostgreSQL session managers. Shared PostgreSQL rows do not transfer filesystem ownership; reuse and cleanup remain limited to the owning host. The Grok, Devin, and Mistral adapters require an explicit provider-native sessionId; fresh, createNewSession, and resumeLatest-only worktree requests fail closed because they cannot durably reselect the worktree. The request must select a registered workspace explicitly, through caller-owned session metadata, or through the configured default. Worktrees never fall back to the gateway process cwd and cannot be combined with local workingDir, addDir, or includeDirs paths. The gateway spawns the child CLI with `cwd: <worktree-path>`; no `-w`/`--worktree` flag is ever emitted to the underlying CLI. On worktree materialization, the gateway suppresses repository, system, and global Git hooks and configured clean, smudge, and process checkout filters, sparse checkout, and lazy object fetching. Filter-dependent content such as Git LFS remains in its repository representation instead of executing host commands. On session_delete, session_clear_all or file-backed TTL eviction, both managers hide a durably owned worktree session while cleanup runs. Failed Git removal retains a cleanup-pending tombstone, blocks reuse, and is retried when a manager is registered on the owning host; the record is finalized only once Git no longer registers the worktree, which is read back rather than inferred from the recorded path being absent. A worktree that moved, or whose owner marker cannot be read, is not a removal. Deletion processed by another host removes no worktree and leaves the owning host's record intact. The database-side cleanup_expired_sessions function stages the same tombstone instead of deleting a worktree-bearing session; it invokes no gateway observer and so attempts no removal itself. A tombstone is not bounded by retention. Successful responses are prefixed with `[gateway] worktree=<absolute-path>\n` so callers can use the path. For Claude approvalStrategy:mcp_managed, requesting or reusing a worktree requires approval and LLM_GATEWAY_APPROVAL_ALLOW_BYPASS=1. Other adapters reject mcp_managed before launch. 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.
mcpServersNoThis provider does not receive gateway-managed MCP configuration. mcpServers has no effect with legacy, and mcp_managed is rejected before launch because ambient MCP configuration cannot be isolated.
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)
idleTimeoutMsNoTotal-runtime bound, not an idle timer: this provider emits no output until it exits, so the child is killed after this duration even while healthy. Min 30s, max 1h, omit=1h default.
providerFlagsNoFlags passed to the provider binary verbatim, keyed exactly as the binary spells them (e.g. {"--best-of-n": "3", "--verbatim": true, "--rules": ["a", "b"]}). Use this for any flag your installed CLI accepts that this schema does not name: the binary decides what it supports, not the gateway. true emits the flag alone; a list REPEATS the flag once per item (pass a joined string if your CLI wants a comma-separated value). Values may not start with '-', and a flag the gateway is already emitting for this request is refused rather than duplicated. LOCAL stdio callers only: remote HTTP/OAuth callers are refused every flag here and should use this tool's declared parameters, which carry their own host-path and approval gates.
approvalPolicyNoapprovalPolicy is unavailable for this provider. It has no effect with legacy, and mcp_managed is rejected before launch because ambient MCP configuration cannot be isolated.
optimizePromptNoOptimize prompt before execution
permissionModeNoVibe --agent name. Legacy requests pass builtins (default|plan|accept-edits|auto-approve), install-gated builtins (e.g. lean), and custom agents from ~/.vibe/agents through to Vibe.
disallowedToolsNoDenylist of built-in tools, each emitted as a separate --disabled-tools <tool> flag
approvalStrategyNoApproval strategy: legacy is supported. mcp_managed is rejected before launch because this adapter cannot isolate ambient MCP configuration.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

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.2.1
    • changedInput schema / properties / worktree / description
      Previous value: -"Slice 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, reuse requires same-host ownership metadata and a matching live Git registration. Named path collisions never reuse manager state. Gateway-managed worktrees require the local file-backed session manager and fail closed with PostgreSQL sessions. The Grok, Devin, and Mistral adapters require an explicit provider-native sessionId; fresh, createNewSession, and resumeLatest-only worktree requests fail closed because they cannot durably reselect the worktree. The request must select a registered workspace explicitly, through caller-owned session metadata, or through the configured default. Worktrees never fall back to the gateway process cwd and cannot be combined with local workingDir, addDir, or includeDirs paths. The gateway spawns the child CLI with `cwd: <worktree-path>`; no `-w`/`--worktree` flag is ever emitted to the underlying CLI. On worktree materialization, the gateway suppresses repository, system, and global Git hooks and configured clean, smudge, and process checkout filters, sparse checkout, and lazy object fetching. Filter-dependent content such as Git LFS remains in its repository representation instead of executing host commands. On session_delete or TTL eviction the gateway hides the session and runs `git worktree remove --force`. Failed removal retains a durable cleanup-pending tombstone which blocks reuse and is retried when the file store is registered on the owning host. The tombstone is finalized only after verified Git removal. Successful responses are prefixed with `[gateway] worktree=<absolute-path>\\n` so callers can use the path. For Claude approvalStrategy:mcp_managed, requesting or reusing a worktree requires approval and LLM_GATEWAY_APPROVAL_ALLOW_BYPASS=1. Other adapters reject mcp_managed before launch. NOTE: callers should `.gitignore` the `.worktrees/` directory in their repo (the gateway does NOT auto-gitignore; see slice λ spec Q4)."New value: +"Slice 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, reuse requires same-host ownership metadata and a matching live Git registration. Named path collisions never reuse manager state. Gateway-managed worktrees work with file-backed and PostgreSQL session managers. Shared PostgreSQL rows do not transfer filesystem ownership; reuse and cleanup remain limited to the owning host. The Grok, Devin, and Mistral adapters require an explicit provider-native sessionId; fresh, createNewSession, and resumeLatest-only worktree requests fail closed because they cannot durably reselect the worktree. The request must select a registered workspace explicitly, through caller-owned session metadata, or through the configured default. Worktrees never fall back to the gateway process cwd and cannot be combined with local workingDir, addDir, or includeDirs paths. The gateway spawns the child CLI with `cwd: <worktree-path>`; no `-w`/`--worktree` flag is ever emitted to the underlying CLI. On worktree materialization, the gateway suppresses repository, system, and global Git hooks and configured clean, smudge, and process checkout filters, sparse checkout, and lazy object fetching. Filter-dependent content such as Git LFS remains in its repository representation instead of executing host commands. On session_delete, session_clear_all or file-backed TTL eviction, both managers hide a durably owned worktree session while cleanup runs. Failed Git removal retains a cleanup-pending tombstone, blocks reuse, and is retried when a manager is registered on the owning host; the record is finalized only once Git no longer registers the worktree, which is read back rather than inferred from the recorded path being absent. A worktree that moved, or whose owner marker cannot be read, is not a removal. Deletion processed by another host removes no worktree and leaves the owning host's record intact. The database-side cleanup_expired_sessions function stages the same tombstone instead of deleting a worktree-bearing session; it invokes no gateway observer and so attempts no removal itself. A tombstone is not bounded by retention. Successful responses are prefixed with `[gateway] worktree=<absolute-path>\\n` so callers can use the path. For Claude approvalStrategy:mcp_managed, requesting or reusing a worktree requires approval and LLM_GATEWAY_APPROVAL_ALLOW_BYPASS=1. Other adapters reject mcp_managed before launch. NOTE: callers should `.gitignore` the `.worktrees/` directory in their repo (the gateway does NOT auto-gitignore; see slice λ spec Q4)."
  2. Addedv3.2.0
  3. Removedv3.0.0
  4. First observedv2.16.0

TDQS

A4.5/5.0
Behavior5/5

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

The description goes well beyond the annotations by disclosing concrete behavioral details: it defaults to --agent accept-edits, auto-accepts file edits, keeps dangerous operations like shell gated, and may auto-defer to a pollable job. These are safety-relevant behaviors an agent needs to know before invoking, and they align with the destructiveHint=true annotation.

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

Conciseness5/5

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

The description is compact and front-loaded: it opens with the core action, then gives the sync/async nuance, then the required-argument constraint, then the safety default. Every sentence earns its place and there is no redundant restating of schema information.

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

Completeness3/5

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

The description is strong for a high-level overview, but the tool is complex, has 29 parameters, and has no output schema. It does not explain what a 'pollable job' returns or how to retrieve its result, and it does not explicitly orient the agent toward the async alternative. The parameter schema carries most of the operational detail, so the description is adequate but leaves some selection and follow-up gaps.

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?

Schema description coverage is 100%, so the baseline is 3. The description adds meaningful cross-parameter semantics by stating that exactly one of prompt or promptParts is required, which is not inferable from the schema's optional fields alone. It also adds the default --agent accept-edits context, which helps the agent understand permissionMode defaults without reading every parameter description.

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 runs a Mistral Vibe CLI request synchronously, identifies the specific provider and resource, and distinguishes it from the async variant by mentioning auto-deferral to a pollable job. It also immediately conveys the key requirement of exactly one of prompt or promptParts, so an agent can understand what this tool does and how it differs from sibling request tools.

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 provides clear context: this is the synchronous request path, with automatic deferral to a pollable job when async jobs are enabled and the sync deadline is exceeded. It also states the required mutual exclusivity of prompt vs promptParts. It does not explicitly name an alternative tool such as mistral_request_async or list when-not-to-use conditions, but the sync/async behavior is clearly enough to guide basic tool selection.

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