Skip to main content
Glama

gemini_request

Destructive

Run Google Antigravity CLI requests synchronously through the gateway, using a plain prompt or structured prompt parts to produce results.

Instructions

Run a Google Antigravity CLI (agy) request through the Gemini-compatible gateway tool 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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yoloNoEmit `--dangerously-skip-permissions` to auto-approve all actions.
modelNoModel name or alias passed to agy --model (e.g. gemini-3-pro-preview, gemini-2.5-flash, pro, flash, latest)
promptNoPrompt text for Antigravity CLI (mutually exclusive with promptParts)
projectNoAntigravity 1.0.13 --project <ID>: select the project for this session. Mutually exclusive with newProject.
sandboxNoRun Antigravity in sandbox mode (--sandbox)
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).
sessionIdNoAntigravity conversation ID to resume (emits --conversation <id>). agy owns conversation ids; a fresh request returns no resumable sessionId, continue via resumeLatest:true.
skipTrustNoUnsupported for Antigravity CLI; true is rejected.
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.
newProjectNoAntigravity 1.0.13 --new-project: create a new project for this session. Mutually exclusive with project.
workingDirNoLocal Antigravity process working directory. 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.
attachmentsNoUnsupported for Antigravity CLI; non-empty values are rejected.
includeDirsNoAdditional workspace directories passed as --add-dir. 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.
policyFilesNoUnsupported for Antigravity CLI; non-empty values are rejected.
promptPartsNoCache-aware structured prompt: { system?, tools?, context?, task }. Mutually exclusive with prompt. Stable parts hash into cache_state for prefix-discipline tracking.
allowedToolsNoUnsupported for Antigravity CLI; non-empty values are rejected
approvalModeNoApproval mode for legacy strategy: default leaves agy prompted, auto_edit emits --mode accept-edits, plan emits --mode plan, and yolo emits --dangerously-skip-permissions.
forceRefreshNoBypass dedup and force a fresh CLI run even if a recent identical request exists
outputFormatNoOutput format (text|json|stream-json), default text. stream-json is the only agy wire that carries the working directory, the tool list, per-tool parameters and per-step token usage; text carries none of them, so per-request usage and cost are unavailable on the default.text
printTimeoutNoAntigravity --print-timeout <DURATION>: print-mode wait timeout as a Go duration string (e.g. '5m0s', '30s').
resumeLatestNoContinue the most recent conversation. agy owns conversation ids; a fresh request returns no resumable sessionId, continue via 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
adminPolicyFilesNoUnsupported for Antigravity CLI; non-empty values are rejected.
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

A4.4/5.0
Behavior4/5

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

Annotations already carry destructiveHint=true, readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the safety profile is established. The description adds beyond those: it discloses the synchronous execution model, auto-deferral to a pollable job, and run-to-completion behavior. No contradiction with annotations.

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?

Two sentences with no wasted words. The most operationally important facts—what it runs, how it executes, and the cardinality constraint—are front-loaded. This is appropriately conose given the heavy lifting already done by the schema.

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?

For a 32-parameter tool with no output schema, the description covers the key execution and prompt-selection behavior while the schema covers parameters in detail. The main gap is that it doesn't specify what a pollable-job result looks like or explicitly route callers to gemini_request_async/job_status, but the outputFormat parameter and sibling names partially fill this.

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 description doesn't need to restate parameters. It does add a critical semantic constraint not enforced by the schema's required fields: "Requires exactly one of prompt or promptParts". This is valuable beyond the mutual-exclusion notes inside individual parameter descriptions.

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 states a specific action and resource: "Run a Google Antigravity CLI (`agy`) request through the Gemini-compatible gateway tool synchronously." It distinguishes this tool from sibling provider request tools by naming Gemini/Antigravity, and from gemini_request_async by emphasizing synchronous execution with auto-deferral to a pollable job.

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 gives clear usage context: it runs synchronously, auto-defers past the sync deadline when async jobs are enabled, and otherwise runs to completion. It doesn't explicitly name gemini_request_async as the alternative or state when to prefer it, so it stops short of full alternative routing, but the sync-vs-async behavior is clear.

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