Agent is terminated from 3-4 days

Google Antigravity
1

Trajectory ID: 1aa25e3f-f5dc-48a6-9307-0ba6dbcd96..
Error: HTTP 429 Too Many Requests
Sherlog:
TraceID: 0x4463b49e582dd3..
Headers: {“Alt-Svc”:[“h3=”:443"; ma=2592000,h3-29=“:443”; ma=2592000"],“Content-Length”:[“139”],“Content-Type”:[“text/event-stream”],“Date”:[“Mon, 07 Sep 2026 11:09:32 GMT”],“Server”:[“ESF”],“Server-Timing”:[“gfet4t7; dur=565”],“Vary”:[“Origin”,“X-Origin”,“Referer”],“X-Cloudaicompanion-Trace-Id”:[“4463b49e582dd3..”],“X-Content-Type-Options”:[“nosniff”],“X-Frame-Options”:[“SAMEORIGIN”],“X-Xss-Protection”:[“0”]}

{
“error”: {
“code”: 429,
“message”: “Resource has been exhausted (e.g. check quota).”,
“status”: “RESOURCE_EXHAUSTED”
}
}

2

Hi @Sumit_Mahajan ,

Thank you for providing the details.

When the agent repeatedly terminates with HTTP 429 RESOURCE_EXHAUSTED, it is typically caused by an oversized chat session exceeding per-minute token throughput limits, or outdated client endpoint routing.

To resolve this and restore agent operation:

  1. Start a Fresh Chat Session:

    • If you are continuing in an existing chat thread, the agent re-submits the entire conversation history on every turn. This large payload immediately triggers a 429 error and terminates the agent. Starting a new chat session resets the token payload.

  2. Update to the Latest Build (v2.14):

  3. Switch Model Allocation:

    • In the model selector, switch to a Flash model such as Gemini 3.8 Flash. Flash models offer higher rate-limit ceilings and dedicated throughput pools for agent workflows.

  4. Reset Onboarding Session:

    • Open the Command Palette (Ctrl+Shift+P on Windows/Linux or Cmd+Shift+P on macOS), select Antigravity: Reset Onboarding, and sign in again to refresh your OAuth claims.

If the issue still persists, please reach out back to us.