{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiccg6ly5r4rpd54fjlfgnxykt4s2z4gdgmvswfr546bfjoj6x36xe",
"uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mgwtbv6bwqn2"
},
"path": "/t/codex-becomes-extremely-slow-and-causes-severe-ui-lag-when-working-with-many-files/1376629#post_2",
"publishedAt": "2026-03-13T11:31:18.000Z",
"site": "https://community.openai.com",
"textContent": "Hey Jal!\n\nIt sounds like you’re using a single session until the context window fills up, which then requires reoccurring compaction.\n\nHave you considered starting a new chat session once the context reaches around 70% capacity? This can help you avoid wasting tokens on compaction, reduce the risk of losing information during summarization, and give you a clearer sense of what the new session already knows.\n\nOne useful practice when switching sessions regularly is to carry over only the necessary context. Keeping a local `memory.md` file for the project is a great way to record important information you don’t want to lose and can quickly reference in a new session.\n\n- Eric",
"title": "Codex becomes extremely slow and causes severe UI lag when working with many files"
}