BUG - Antigravity Unusable for over a week - Agent keeps crashing

Antigravity has been unusable for me over a week. Being a pro user, this is extremely frustrating
First there is this multi week / multi day lockout for all models.
Then when finally I get gemini 3 flash model at 100% not even a single prompt to gemini works. I keep getting “*Agent Terminated due to Error"
*
I can keep trying to retry, but it keeps crashing.
I used to be a loyal Google user, but the latest experience has left me questioning if I should continue or not

daily-cloudcode-pa.googleapis.com/v1internal:streamGenerateContent?alt=sse Trace: 0xfd30f837f6121544

2026-03-15 15:17:41.395 [info] E0315 15:17:41.395026 32219 checkpoint_validation.go:70] bad checkpoint state: no valid checkpoint to use

2026-03-15 15:17:41.542 [info] I0315 15:17:41.541880 32219 planner_generator.go:285] Requesting planner with 8 chat messages at model retry attempt 1 and API retry attempt 1

2026-03-15 15:17:44.157 [info] I0315 15:17:44.156136 32219 http_helpers.go:123] URL: https://daily-cloudcode-pa.googleapis.com/v1internal:streamGenerateContent?alt=sse Trace: 0x34d1bd375c4d7a56

2026-03-15 15:17:45.103 [info] I0315 15:17:45.102815 32219 client.go:56] CEL: Sending error - type=LS_ERROR ideName=antigravity appName=antigravity_desktop version=1.20.5

2026-03-15 15:17:46.047 [info] E0315 15:17:46.046977 32219 checkpoint_validation.go:70] bad checkpoint state: no valid checkpoint to use

2026-03-15 15:17:46.108 [info] E0315 15:17:46.108157 32219 log.go:398] agent executor error: trajectory converted to zero chat messages
1 Like

Same here, it’s getting really frustrating - that I had to create an account on this platform to register my complaint. I had been facing this issue some weeks backs and after back-to-back updates, with the latest version, I assumed everything had been resolved. But the same “Agent terminated due to Error” has returned.

Still no resolution @Google_Google ?? I seem to be burning through my tokens with multiple retry attempts but literally squat nothing as an answer to the queries.

and then there is a multi day lockout .

Seriously considering moving to another platform

Trajectory ID: 6b9dde83-db85-4113-ab49-272fb4e45b51
Error: agent executor error: trajectory converted to zero chat messages
(1) attached stack trace
– stack trace:
| google3/third_party/jetski/cortex/cortex.(*CascadeManager).executeHelper.func1
| third_party/jetski/cortex/cascade_manager.go:2088
| […repeated from below…]
Wraps: (2) agent executor error
Wraps: (3) attached stack trace
– stack trace:
| google3/third_party/gemini_coder/framework/generator/generator.(*requestBuilder).buildRequest
| third_party/gemini_coder/framework/generator/request_builder.go:122
| google3/third_party/gemini_coder/framework/generator/generator.(*PlannerGenerator).generateWithAPIRetry
| third_party/gemini_coder/framework/generator/planner_generator.go:279
| google3/third_party/gemini_coder/framework/generator/generator.(*PlannerGenerator).generateWithModelOutputRetry
| third_party/gemini_coder/framework/generator/planner_generator.go:156
| google3/third_party/gemini_coder/framework/generator/generator.(*PlannerGenerator).Generate
| third_party/gemini_coder/framework/generator/planner_generator.go:94
| google3/third_party/gemini_coder/framework/executor/executor.(*Executor).executeLoop
| third_party/gemini_coder/framework/executor/executor.go:355
| google3/third_party/gemini_coder/framework/executor/executor.(*Executor).Execute
| third_party/gemini_coder/framework/executor/executor.go:277
| google3/third_party/jetski/cortex/cortex.(*CascadeManager).executeHelper.func1
| third_party/jetski/cortex/cascade_manager.go:2053
| google3/third_party/jetski/cortex/cortex.(*CascadeManager).executeHelper.func2
| third_party/jetski/cortex/cascade_manager.go:2136
| runtime.goexit
| third_party/go/gc/src/runtime/asm_amd64.s:1774
Wraps: (4) trajectory converted to zero chat messages
Error types: (1) *withstack.withStack (2) *errutil.withPrefix (3) *withstack.withStack (4) *errutil.leafError

is this the same problem ?

I think they are related.

Hi @Ashwin_Krishnan ,

Thank you for bringing the issue to our attention. Our engineering team is currently investigating the matter, and we appreciate your patience as we work toward a resolution.