clone/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-04-24 06:35:50 +00:00
Code Issues Packages Projects Releases Wiki Activity

Raise image byte estimate for compaction token accounting (#12717)

Browse Source 
Increase `IMAGE_BYTES_ESTIMATE` from 340 bytes to 7,373 bytes so the
existing 4-bytes/token heuristic yields an image estimate of ~1,844
tokens instead of ~85. This makes auto-compaction more conservative for
image-heavy transcripts and avoids underestimating context usage, which
can otherwise cause compaction to fail when there is not enough free
context remaining. The new value was chosen because that's the image
resolution cap used for our latest models.

Follow-up to [#12419](https://github.com/openai/codex/pull/12419).
Refs [#11845](https://github.com/openai/codex/issues/11845).
This commit is contained in:
Eric Traut
2026-02-24 16:11:38 -08:00
committed by GitHub
parent 5571a022eb
commit 8da40c9251
1 changed files with 3 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
codex-rs/core/src/context_manager/history.rs
View File

@@ -421,9 +421,9 @@ fn estimate_item_token_count(item: &ResponseItem) -> i64 {
/// Approximate model-visible byte cost for one image input.
///
/// The estimator later converts bytes to tokens using a 4-bytes/token heuristic,
/// so 340 bytes is approximately 85 tokens.
const IMAGE_BYTES_ESTIMATE: i64 = 340;
/// The estimator later converts bytes to tokens using a 4-bytes/token heuristic
/// with ceiling division, so 7,373 bytes maps to approximately 1,844 tokens.
const IMAGE_BYTES_ESTIMATE: i64 = 7373;
pub(crate) fn estimate_response_item_model_visible_bytes(item: &ResponseItem) -> i64 {
match item {