-
Notifications
You must be signed in to change notification settings - Fork 9k
Closed as duplicate of#8089
Labels
bugSomething isn't workingSomething isn't working
Description
Description
I've this this a few times now running long sessions:
{"type":"error","sequence_number":2,"error":{"type":"invalid_request_error","code":"context_length_exceeded","message":"Your input exceeds the context window of this model. Please adjust your input and try again.","param":"input"}}
I'm using GPT-5.2 Codex via OpenAI OAuth. Ideally codex's auto-compation would work, but in the absence of that I thought the opencode auto compaction would run before the error is triggered. I've set this explicitly in my config:
"compaction": {
"auto": true,
"prune": true,
},
Plugins
none
OpenCode version
1.1.18
Steps to reproduce
No response
Screenshot and/or share link
Operating System
macOS 15.6.1
Terminal
ghostty
Metadata
Metadata
Assignees
Labels
bugSomething isn't workingSomething isn't working