This issue has been reported for weeks and still no fix or official update.
“Agent execution terminated due to error” makes Antigravity completely unusable, regardless of model or prompt.
For a paid Google AI Ultra product, this lack of response is unacceptable.
Please acknowledge the bug and provide a status update or workaround.
Every model works randomly, it has been weeks guys, and still no official answer from Google. Before Antigravity i was using Cursor, never happened anything close to this.
Your lack of communications is even worse than the problem itself.
It seems to be working for me now quite well, without getting constant errors. Model also doesnt feel as nerfed as before.
are you on the new 1.15.8 update, or it just magically fixed itself, cause Im still getting ;
“2026-01-27 15:03:15.258 [info] I0127 15:03:15.120944 176484 server.go:472] Created extension server client at port 63714
2026-01-27 15:03:15.654 [info] (Antigravity) 2026-01-27 15:03:15.653 [INFO]: Language server started
2026-01-27 15:03:15.661 [info] W0127 15:03:15.642071 176484 client.go:137] failed to set auth token
2026-01-27 15:03:15.661 [info] W0127 15:03:15.644070 176484 log_context.go:106] Cache(userInfo): Singleflight refresh failed: You are not logged into Antigravity.
2026-01-27 15:03:15.661 [info] I0127 15:03:15.659517 176484 server.go:1504] initialized server successfully in 1.3544114s
2026-01-27 15:03:16.183 [info] (Antigravity) 2026-01-27 15:03:16.182 [INFO]: LS lspClient started successfully
2026-01-27 15:04:20.017 [info] E0127 15:04:20.017312 176484 log.go:354] encountered conflicting override on experiment: cascade-include-ephemeral-message
2026-01-27 15:04:20.019 [info] E0127 15:04:20.018928 176484 log.go:354] encountered conflicting override on experiment: cascade-knowledge-config
2026-01-27 15:04:20.096 [info] I0127 15:04:20.095985 176484 planner_generator.go:275] Requesting planner with 6 chat messages at model retry attempt 1 and API retry attempt 1
2026-01-27 15:04:21.097 [info] E0127 15:04:21.096571 176484 log.go:362] agent executor error: PERMISSION_DENIED (code 403): You are currently configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact your administrator to request a license. (#3501): PERMISSION_DENIED (code 403): You are currently configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact your administrator to request a license. (#3501)“
Can you check the output and confirm whether you’re also getting 503 (no capacity) errors?
The main reason for the crashes is that Google doesn’t have enough servers to handle the number of subscribers for the models. I’m getting these errors all the time.
yeah, I see that it’s a different bug in your case.
If I were you, I’d test your account on a different PC profile (a new Windows/Linux/macOS profile) and see if that helps - it could be some corrupted local Gemini config
I repeat tested on 2 existing Windows profiles different pcs, 1 completely different user profile which is a new build, and Ubuntu.. The consistent issue is my account, not rate limits or availability aside from that error about no model being selected, use another account it’s fine.. Use my account.. error.
Agent execution terminated due to error. Getting the same error. it is not usable. I’m on Ultra plan. wasted $200
here’s an example of my account not working, me signing out using another account and that works, red is dead green is good.
still the same…,………………
so everyone is good except me?..
The image provided shows a screenshot of the Google Antigravity agentic development platform, which is an AI-powered Integrated Development Environment (IDE) that uses autonomous agents to perform coding tasks. The interface displays log messages and chat interactions with “Antigravity, an AI coding assistant”.
Two issues are indicated in the logs:
Permission Denied Error: Several log entries show a PERMISSION_DENIED (code 403) error, stating, “You are currently configured to use a Google Cloud Project but lack a Gemini Code Assist license”. This occurs when an account is linked to a Google Cloud project but lacks the necessary license for the enterprise features, or sometimes for the no-cost individual version due to a known bug.
Capacity Error: Other logs show an UNAVAILABLE (code 503) error with the message “No capacity available for model claude-opus-4-5-thinking on the server”. This suggests a server-side issue with high demand or insufficient capacity for that specific AI model, which has been a widely reported problem.
The platform allows developers to work at a higher, task-oriented level. The AI handles planning, execution, and verification across the editor, terminal, and browser. Progress is communicated through “artifacts” like screenshots and walkthroughs.
5028-03-28 14:37:19.064 [info] E0128 14:37:10.053848 174872 log-go:354] encountered conflicting override on experiment: cascade-knowledge-config
2005-03-28 14:37:19.091 [info] 18128 14:47:219.8989 174872 planner_generator.go:275] Requesting planner with 15 chat messages at model retry
attempt 1 and API retry attempt 1
2825-03-28 14:37:19.894 [info] E0128 14:57:219.895187 174872 log.go:362] agent executor error: PERMISSION DENIED (code 403): You are currently
configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact your administrator to request a license. (#3581): PERMISSION DENIED (code 403): You are currently configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact
your administrator to request a license. (#3581)
2624-01-28 14:37:20.340 [info] E0128 14:37:20.339425 174872 log.go:354] encountered conflicting override on experiment: cascade-knowledge-config
2026-01-28 14:37:20.375 [info] 10128 14:37:20.374351 174872 planner_generator.go:275] Requesting planner with 17 chat messages at model retry
attempt 1 and API retry attempt 1
2026-01-28 14:37:21.220 [info] E0128 14:37:21.770306 174872 log.go:362] agent executor error: PERMISSION DENIED (code 403): You are currently
configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact your administrator to request a license. (#3581): PERMISSION DENIED (code 403): You are currently configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact
your administrator to request a license. (#3581)
2026-01-28 14:37:31.384 [info] E0128 14:37:31.383330 174872 log.go:354] encountered conflicting override on experiment: cascade-knowledge-config
2025-01-28 14:37:31.403 [info] 10128 14:37:31.402332 174872 planner_generator.go:275] Requesting planner with 19 chat messages at model retry
attempt 1 and API retry attempt 1
2025-01-28 14:37:32.203 [info] E0128 14:37:32.220305 174872 log.go:362] agent executor error: PERMISSION DENIED (code 403): You are currently
configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact your administrator to request a license. (#3581): PERMISSION DENIED (code 403): You are currently configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact
your administrator to request a license. (#3581)
2025-01-28 14:38:00.872 [log] context.go:106] Removing OAuth token info
2025-01-28 14:38:18.145 [info] 10128 14:38:18.144514 174872 log_context.go:106] Removing OAuth token info
2026-01-28 14:38:47.024 [info] E0128 14:38:47.024437 174872 log.go:354] encountered conflicting override on experiment: cascade-knowledge-config
2026-01-28 14:38:47.086 [info] 10128 14:38:47.085854 174872 planner_generator.go:275] Requesting planner with 7 chat messages at model retry
attempt 1 and API retry attempt 1
2026-01-28 14:38:49.821 [info] 10128 14:38:49.820931 174872 http_helpers.go:124] URL: https://daily-cloudcode-pa.googleapis.com/
v1internal:streamGenerateContent?alt=sse trace=0xb7f4bc8ee33b652d
2026-01-28 14:38:53.083 [info] 10128 14:38:53.082964 174872 http_helpers.go:124] URL: https://daily-cloudcode-pa.googleapis.com/
v1internal:streamGenerateContent?alt=sse trace=0x8adc85dfca1887d7
2026-01-28 14:39:19.785 [info] E0128 14:39:19.785073 174872 log.go:354] encountered conflicting override on experiment: cascade-knowledge-config
2025-01-28 14:39:19.802 [info] 10128 14:39:19.802241 174872 planner_generator.go:275] Requesting planner with 9 chat messages at model retry
attempt 1 and API retry attempt 1
2026-01-28 14:39:25.777 [info] E0128 14:39:25.776341 174872 log.go:362] UNAVAILABLE (code 503): No capacity available for model
claude-opus-4-5-thinking on the server: UNAVAILABLE (code 503): No capacity available for model claude-opus-4-5-thinking on the server
2025-01-28 14:39:25.778 [info] 10128 14:39:25.777929 174872 planner_generator.go:275] Requesting planner with 10 chat messages at model retry
attempt 1 and API retry attempt 2
2025-01-28 14:39:37.328 [info] E0128 14:39:37.327145 174872 log.go:362] UNAVAILABLE (code 503): No capacity available for model
claude-opus-4-5-thinking on the server: UNAVAILABLE (code 503): No capacity available for model claude-opus-4-5-thinking on the server
2025-01-28 14:39:37.930 [info] 10128 14:39:37.9298 174872 planner_generator.go:275] Requesting planner with 11 chat messages at model retry
attempt 1 and API retry attempt 3
2025-01-28 14:39:40.76 [info] 10128 14:39:40.7501 174872 http_helpers.go:124] URL: https://daily-cloudcode-pa.googleapis.com/
v1internal:streamGenerateContent?alt=sse trace=0x2f5
No, still got the same issues as well. I’m on Ultra too. Have to hit “continue” every couple of seconds
ETA: 2 colleagues are on Ultra as well. For one it is working fine (a handful of Agent Termination Errors a day), for the other one just like for me. We are working on the same codeprojects…
A complete clean reinstall with all settings / caches erased did not help either.
EDIT 3: Third time it might have worked. I got rid of everything with
sudo find / -type d ( -iname “antigravity” -o -iname “.gemini” ) -print 2>/dev/null
and then did not import from VS Code after install and now it seems to be working
yey, new update same error message but at least this time we get a “copy debug info” button, now I still have an issue of how I remove myself from the “Google Cloud project” i never joined in the first place but cant seem to get out of… dude its a free account;
Error: HTTP 403 Forbidden
Sherlog:
TraceID: 0x4b2c86ee623f9315
Headers: {“Alt-Svc”:[“h3=“:443”; ma=2592000,h3-29=“:443”; ma=2592000”],“Content-Length”:[“700”],“Content-Type”:[“text/event-stream”],“Date”:[“Thu, 05 Feb 2026 09:15:26 GMT”],“Server”:[“ESF”],“Server-Timing”:[“gfet4t7; dur=787”],“Vary”:[“Origin”,“X-Origin”,“Referer”],“X-Cloudaicompanion-Trace-Id”:[“4b2c86ee623f9315”],“X-Content-Type-Options”:[“nosniff”],“X-Frame-Options”:[“SAMEORIGIN”],“X-Xss-Protection”:[“0”]}
{
“error”: {
“code”: 403,
“details”: [
{
“@type”: “type .googleapiscom/google.rpc.ErrorInfo”,
“domain”: “cloudaicompanion..googleapis.com”,
“reason”: “SUBSCRIPTION_REQUIRED”
},
{
“@type”: “type..googleapis.com/google.rpc.Help”,
“links”: [
{
“description”: “Learn more”,
“url”: “https: //cloud..google.com/ gemini/docs/codeassist/request-license”
}
]
}
],
“message”: “You are currently configured to use a Google Cloud Project but lack a Gemini Code Assist license. Please contact your administrator to request a license. (#3501)”,
“status”: “PERMISSION_DENIED”
}
}“
I am also experiencing this issue. Switching from Ubuntu to a fresh install of Mint failed to fix the issue.
I am on the AI Ultra plan. I recently started (approximately one week), and had no issues for the first few days. Now, I get an error every few seconds.
any solution for this error? I’ve had this bug for 7 days now….
Same issue for me right now. It even still uses up quota even though it terminates!! This is a reoccurring issue. Antigravity is probably the worst Agent IDE only because of the countless bugs.
dear god, I think somebody might actually be doing something once got a new error message, how do you check your quota on a few plan, still the same flashback wow message, but the “copy debug info” is doing its job an getting to the core of the problem at least;
“Trajectory ID: 59d46d85-4491-42ce-afdb-05fce4b8fc70
Error: model unreachable: RESOURCE_EXHAUSTED (code 429): Resource has been exhausted (e.g. check quota).: RESOURCE_EXHAUSTED (code 429): Resource has been exhausted (e.g. check quota).: model api cannot be reached
(1) attached stack trace
– stack trace:
| google3/third_party/gemini_coder/framework/generator/generator.(*PlannerGenerator).generateWithModelOutputRetry
| third_party/gemini_coder/framework/generator/planner_generator.go:194
| google3/third_party/gemini_coder/framework/generator/generator.(*PlannerGenerator).Generate
| third_party/gemini_coder/framework/generator/planner_generator.go:95
| google3/third_party/gemini_coder/framework/executor/executor.(*Executor).Execute
| third_party/gemini_coder/framework/executor/executor.go:303
| google3/third_party/jetski/cortex/cortex.(*CascadeManager).executeHelper.func1
| third_party/jetski/cortex/cascade_manager.go:1558
| […repeated from below…]
Wraps: (2) secondary error attachment
| RESOURCE_EXHAUSTED (code 429): Resource has been exhausted (e.g. check quota).: RESOURCE_EXHAUSTED (code 429): Resource has been exhausted (e.g. check quota).
| (1) tags: map[stream_receive_count:0 streaming_duration:0s]
| Wraps: (2) attached stack trace
| – stack trace:
| | google3/third_party/gemini_coder/framework/generator/generator.(*streamResponseHandler).processStream
| | third_party/gemini_coder/framework/generator/stream_handler.go:338
| | google3/third_party/gemini_coder/framework/generator/generator.(*PlannerGenerator).attemptGenerate
| | third_party/gemini_coder/framework/generator/planner_generator.go:437
| | google3/third_party/gemini_coder/framework/generator/generator.(*PlannerGenerator).generateWithAPIRetry
| | third_party/gemini_coder/framework/generator/planner_generator.go:278
| | google3/third_party/gemini_coder/framework/generator/generator.(*PlannerGenerator).generateWithModelOutputRetry
| | third_party/gemini_coder/framework/generator/planner_generator.go:154
| | google3/third_party/gemini_coder/framework/generator/generator.(*PlannerGenerator).Generate
| | third_party/gemini_coder/framework/generator/planner_generator.go:95
| | google3/third_party/gemini_coder/framework/executor/executor.(*Executor).Execute
| | third_party/gemini_coder/framework/executor/executor.go:303
| | google3/third_party/jetski/cortex/cortex.(*CascadeManager).executeHelper.func1
| | third_party/jetski/cortex/cascade_manager.go:1558
| | google3/third_party/jetski/cortex/cortex.(*CascadeManager).executeHelper.func2
| | third_party/jetski/cortex/cascade_manager.go:1676
| | runtime.goexit
| | third_party/go/gc/src/runtime/asm_amd64.s:1771
| Wraps: (3) RESOURCE_EXHAUSTED (code 429): Resource has been exhausted (e.g. check quota).
| Wraps: (4) RESOURCE_EXHAUSTED (code 429): Resource has been exhausted (e.g. check quota).
| Error types: (1) *go_utils.withTags (2) *withstack.withStack (3) *errutil.withPrefix (4) *utils.HTTPError
Wraps: (3) model unreachable: RESOURCE_EXHAUSTED (code 429): Resource has been exhausted (e.g. check quota).: RESOURCE_EXHAUSTED (code 429): Resource has been exhausted (e.g. check quota).
Wraps: (4) attached stack trace
– stack trace:
| google3/third_party/jetski/cortex/shared/shared.init
| third_party/jetski/cortex/shared/interfaces.go:21
| runtime.doInit1
| third_party/go/gc/src/runtime/proc.go:8105
| runtime.doInit
| third_party/go/gc/src/runtime/proc.go:8072
| runtime.main
| third_party/go/gc/src/runtime/proc.go:258
| runtime.goexit
| third_party/go/gc/src/runtime/asm_amd64.s:1771
Wraps: (5) model api cannot be reached
Error types: (1) *withstack.withStack (2) *secondary.withSecondaryError (3) *errutil.withPrefix (4) *withstack.withStack (5) *errutil.leafError
