|
| ▲ | SyneRyder 3 hours ago | parent | next [-] |
| Sounds like that's the problem then, 275k is a tiny context window. I regularly have sessions that go to 450k or even up to 700k for an unattended overnight Claude Opus session. Apparently OpenAI makes you manually setup their 1 Million context window, and it seems to be only documented on X: https://x.com/thsottiaux/status/2089082893804896524 There's at least a forum thread about it here: https://community.openai.com/t/why-does-codex-report-a-258-4... |
| |
| ▲ | gf000 2 hours ago | parent [-] | | But that 250k context worth way more than 1M in terms of how well it's utilized, so actually I do like codex trying to keep you at that sweet spot. |
|
|
| ▲ | jeremyjh 2 hours ago | parent | prev | next [-] |
| I don’t usually have a problem doing a complete task in that context size. OMP does make a lot of use of rewind which may be helping - basically forks itself and sends back a summary after a long tangent. Coding tasks use a Luna max agent. I’ve also found compaction not to be a problem when it does happen. |
| |
| ▲ | threecheese an hour ago | parent [-] | | How do you trigger this? I've been messing with OMP lately for funsies. | | |
| ▲ | jeremyjh 41 minutes ago | parent [-] | | Its in settings under Tools->Checkpoint/Rewind. I don't know why its not enabled by default and actually forgot I had to enable it. But its a great feature that can really stretch context. |
|
|
|
| ▲ | onlyrealcuzzo 2 hours ago | parent | prev | next [-] |
| If it's compacting every 5 mins, you're going to notice it in your cache miss ratio and your costs... It also presumably means it's regularly not able to get everything it wants to have to make decisions in context, which means it's going to perform poorly... |
|
| ▲ | sally_glance 3 hours ago | parent | prev [-] |
| Same for me, I started wondering if maybe workflows using compaction instead of clear + markdown memory would be more efficient. Writing a plan or tasks to a file often has the next session repeat part of the exploration, compaction seems to keep most relevant context. |
