-
Notifications
You must be signed in to change notification settings - Fork 13.6k
CLI constantly get stuck for 15 minutes or more on a simple implmentation plan review #25110
Copy link
Copy link
Closed
Task
Copy link
Labels
area/agentIssues related to Core Agent, Tools, Memory, Sub-Agents, Hooks, Agent QualityIssues related to Core Agent, Tools, Memory, Sub-Agents, Hooks, Agent Qualityarea/coreIssues related to User Interface, OS Support, Core FunctionalityIssues related to User Interface, OS Support, Core Functionalitystatus/need-triageIssues that need to be triaged by the triage automation.Issues that need to be triaged by the triage automation.workstream-rollupLabel used to tag epics and features that are associated with one of the three primary workstreamsLabel used to tag epics and features that are associated with one of the three primary workstreams
Metadata
Metadata
Assignees
Labels
area/agentIssues related to Core Agent, Tools, Memory, Sub-Agents, Hooks, Agent QualityIssues related to Core Agent, Tools, Memory, Sub-Agents, Hooks, Agent Qualityarea/coreIssues related to User Interface, OS Support, Core FunctionalityIssues related to User Interface, OS Support, Core Functionalitystatus/need-triageIssues that need to be triaged by the triage automation.Issues that need to be triaged by the triage automation.workstream-rollupLabel used to tag epics and features that are associated with one of the three primary workstreamsLabel used to tag epics and features that are associated with one of the three primary workstreams
Type
Fields
Give feedbackNo fields configured for Task.
Projects
Status
Closed
What happened?
I wrote a plan to change few things on a codebase, shared with cli to validate, and it got stuck for 30m try again more 15m with o response at all. Unusable
What did you expect to happen?
Get a response promptly instead of waiting ages with Thinking spinner on the cli, and having nothing done.
Client information
Login information
No response
Anything else we need to know?
Plan: Gemini Code Assist in Google One AI Pro
Thanks all for the feedback!
I suggest we resolve this by falling back to flash model when pro model is not available