Skip to content
Proposals/Upgrade Antigravity CLI to 1.2.13 and abort retr
proposaldeveloperP4Worth a lookGoogle Antigravity

Upgrade Antigravity CLI to 1.2.13 and abort retries on daily or billing caps

Antigravity 1.2.13 waits the model API’s retry delay instead of a fixed 5s, and stops immediately when that delay exceeds 30s or the quota is a daily/billing cap. Also cheaper conversation redraws, named artifact m hints, and wrapping on ~40-column terminals.

Why this loop

Pre-1.2.13, the CLI always waited 5 seconds on rate limits and could keep retrying when the server asked for a long delay or when the quota was a daily/billing cap. After upgrading, treat Retry-After as authoritative: wait the server delay, and treat >30s delays and daily/billing caps as hard stops so you do not burn cycles or hide a real quota block. The same release also cuts CPU and memory churn while the conversation view redraws (fast scroll or while the agent is working), so long sessions should stay in the live view instead of restarting the CLI. Artifact mode switching is no longer labeled toggle ASCII/toggle raw; m now names the target (diagram ASCII, diagram source, math image). Workspace trust, /help, sign-in, and MCP auth no longer clip at ~40 columns—use them as-is instead of widening the terminal.

Proposed actions

  1. Upgrade Google Antigravity CLI to 1.2.13 from https://github.com/google-antigravity/antigravity-cli/releases/tag/1.2.13 before the next agent run so rate-limit waits, conversation redraws, artifact m hints, and narrow-terminal dialogs match this release.
  2. When the model API returns a retry delay, wait that exact delay instead of 5 seconds; if the delay is longer than 30 seconds or the quota is a daily or billing cap, stop the CLI immediately and do not retry.
  3. Keep the conversation view open during fast scrolling and while the agent is working; 1.2.13 cuts CPU use and memory churn on redraws, so do not restart the CLI to recover from scroll lag.
  4. In the artifact viewer, press m and follow the new named hints (diagram ASCII, diagram source, math image) instead of the old toggle ASCII or toggle raw labels.
  5. On terminals around 40 columns, run workspace trust, /help, sign-in, and MCP authentication in-place: long lines and navigation hints now wrap, and the /help tab bar compacts instead of clipping.

Agent prompt

Paste into your agent or query via MCP (get_agent_prompt) — free, no extra AI cost

Google Antigravity / agent task

DevAgentRadar → Google Antigravity

Goal: turn this release signal into a safe pilot plan for my stack.

Context

Assistant: Google Antigravity Proposal: Upgrade Antigravity CLI to 1.2.13 and abort retries on daily or billing caps Summary: Antigravity 1.2.13 waits the model API’s retry delay instead of a fixed 5s, and stops immediately when that delay exceeds 30s or the quota is a daily/billing cap. Also cheaper conversation redraws, named artifact m hints, and wrapping on ~40-column terminals. Primary source: https://github.com/google-antigravity/antigravity-cli/releases/tag/1.2.13

Why it matters

Pre-1.2.13, the CLI always waited 5 seconds on rate limits and could keep retrying when the server asked for a long delay or when the quota was a daily/billing cap. After upgrading, treat Retry-After as authoritative: wait the server delay, and treat >30s delays and daily/billing caps as hard stops so you do not burn cycles or hide a real quota block. The same release also cuts CPU and memory churn while the conversation view redraws (fast scroll or while the agent is working), so long sessions should stay in the live view instead of restarting the CLI. Artifact mode switching is no longer labeled toggle ASCII/toggle raw; m now names the target (diagram ASCII, diagram source, math image). Workspace trust, /help, sign-in, and MCP auth no longer clip at ~40 columns—use them as-is instead of widening the terminal.

Suggested actions

  1. Upgrade Google Antigravity CLI to 1.2.13 from https://github.com/google-antigravity/antigravity-cli/releases/tag/1.2.13 before the next agent run so rate-limit waits, conversation redraws, artifact m hints, and narrow-terminal dialogs match this release.
  2. When the model API returns a retry delay, wait that exact delay instead of 5 seconds; if the delay is longer than 30 seconds or the quota is a daily or billing cap, stop the CLI immediately and do not retry.
  3. Keep the conversation view open during fast scrolling and while the agent is working; 1.2.13 cuts CPU use and memory churn on redraws, so do not restart the CLI to recover from scroll lag.
  4. In the artifact viewer, press m and follow the new named hints (diagram ASCII, diagram source, math image) instead of the old toggle ASCII or toggle raw labels.
  5. On terminals around 40 columns, run workspace trust, /help, sign-in, and MCP authentication in-place: long lines and navigation hints now wrap, and the /help tab bar compacts instead of clipping.

Config surfaces this release may change

  • MCP servers — check your repo before applying

After you finish

Do not report this as applied to DevAgentRadar. You cannot write the visitor's loop.

Tell the human: open https://devagentradar.com/proposals/google-antigravity-1-2-13-upgrade-antigravity-cli-to-1-2-13-and-abort-re and mark Applied, Skipped, or Failed. Proposal id: ac6faff1-64eb-4f67-95bc-dfb87b0b6c88

Please:

  1. Map the change to concrete pilot steps
  2. Flag security / permission implications
  3. Keep the pilot reversible
agentmcpmodelpricingcliRelease source ↗

Your loop

This browser · no sign-in · not shared as “you”

After you run the prompt

Only you can mark this. Agents cannot write your loop.

Your decision stays on this device. A public tally appears after a few votes.

Originating release signal

Google Antigravity1.2.13Sep 29, 2026

1.2.13

Improved rate-limit handling when the model API returns a retry delay: the CLI now waits the delay the server asks for instead of a fixed 5 seconds, and stops right away instead of retrying when the delay is longer than 30 seconds or the quota is a daily or billing cap · Improved rendering efficiency, cutting CPU use and memory churn while the conversation view redraws, such as during fast scrolling or while the agent is working · +2 more changes
Verified excerpt — the source's own words
  • Improved rate-limit handling when the model API returns a retry delay: the CLI now waits the delay the server asks for instead of a fixed 5 seconds, and stops right away instead of retrying when the delay is longer than 30 seconds or the quota is a daily or billing cap
  • Improved rendering efficiency, cutting CPU use and memory churn while the conversation view redraws, such as during fast scrolling or while the agent is working
  • Improved the artifact viewer's m hint to name the content and the mode it switches to, such as diagram ASCII, diagram source, or math image, instead of toggle ASCII or toggle raw
  • Fixed the workspace trust dialog, the /help panel, and the sign-in and MCP authentication screens clipping text on narrow terminals of around 40 columns; long lines and navigation hints now wrap, and the /help tab bar compacts to fit
Primary source ↗