Ask Antigravity (new conversation)
antigravity_askAsk Antigravity CLI a question in a new conversation, using existing AI Pro authentication to return the model's final text response—ideal for short tasks and fast tool-calling.
Instructions
Ask Antigravity (agy CLI, Gemini by default) a question in a NEW conversation.
Uses your existing AI Pro authentication (silent-auth via Windows Credential
Manager). Returns the model's final response as text. Good for fast
tool-calling and short tasks; for heavier reasoning pick a bigger model or
use the host model directly.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| plan | No | If true, run agy in PLAN mode (agy 1.1.12+): it investigates and writes an implementation plan instead of touching anything. Verified on 1.1.20 that a file write and a shell command are both refused and diverted into a plan document under agy's own directory — even when the prompt insists, and even though the bridge still passes --dangerously-skip-permissions — while file READS answer normally. Use it to point Antigravity at a repo you don't want it editing. Two caveats. It is agent-enforced, not an OS sandbox: it constrains agy's agent loop, so treat it as a strong default rather than a boundary you'd rely on against a hostile prompt (Codex has the real one — see codex_ask's sandbox, and its Windows caveat: as of codex 0.149.1 a sandboxed run there refuses every command and answers anyway). And it is exclusive with the bridge's slash-command shield, because agy silently disables plan mode when that shield is on; a prompt whose first token is a slash command is therefore rejected up front rather than run. Raises on agy older than 1.1.12, which ignores --mode in print mode, rather than silently running your prompt unrestricted. Default false. | |
| model | No | Optional model slug to run this conversation on (agy's --model), e.g. "gemini-3.1-pro-high" or "claude-sonnet-4-6". Omit to use the model set in agy's settings.json (gemini-3.7-flash-high by default). Must be one of `agy models` — an unknown slug is rejected up front (agy would otherwise silently ignore it and fall back to the default). agy 1.1.5 replaced the old human labels ("Gemini 3.1 Pro (High)") with these slugs, and the default has since moved to the gemini-3.7-flash family; the old form is no longer accepted. See antigravity_status / `agy models` for the valid slugs. | |
| watch | No | If true, open a live "watch" view in your browser that streams agy's steps (narration + the real commands it runs) as it works. agy still runs headless; the same final text is returned. Best- effort and cross-platform — if the browser can't open, the run completes normally. Default false. | |
| prompt | Yes | Question or instruction for Antigravity. | |
| schema | No | Optional JSON Schema (an object, or its JSON text). When given, agy is asked to produce output matching it (agy 1.1.8's --json-schema) and this tool returns the VALIDATED OBJECT as JSON text instead of prose — json.loads it. What comes back is agy's own `structured_output`, which carries exactly the declared fields; agy's prose `response` on the same run also picks up its internal toolAction/toolSummary keys and can be prefixed with a sentence, so the two are NOT interchangeable. If agy produces no structured output the call RAISES rather than handing back prose you would have to parse anyway. Needs agy 1.1.8+. IMPORTANT — write the prompt so the ANSWER is in the turn, and let the schema only shape it. agy fills the schema in a finishing pass that does not re-reason about the content, so a field the turn never established gets guessed from the schema itself. Measured on 1.1.20 with "this broke my build and wasted my whole afternoon": with enum ["positive","negative"] it answered "positive" 3 times out of 4, and simply REVERSING the enum to ["negative","positive"] flipped it to "negative" 2 out of 2 — it was following field order, not the sentence. Adding a `reason` field did not help; the reason came back "Completed sentiment classification task." Asking the prompt to state the verdict and why, and keeping the same biased enum, was correct 3 out of 3. So: extraction of what the model has already worked out is reliable; a judgment delegated to the schema is not. | |
| timeout_s | No | Max seconds to wait for agy to complete. Default 180. | |
| workspace | No | Working directory for the conversation. Defaults to cwd. Choose an existing project dir for context-aware responses. |
Output Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |