Eric Traut 8da40c9251 Raise image byte estimate for compaction token accounting (#12717) ...

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).

8da40c9251 · 2026-02-24 16:11:38 -08:00

History

..

history_tests.rs

Improve token usage estimate for images (#12419)

2026-02-21 14:25:36 -08:00

history.rs

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

2026-02-24 16:11:38 -08:00

mod.rs

Centralize context update diffing logic (#11807)

2026-02-17 09:21:44 -08:00

normalize.rs

Strip unsupported images from prompt history to guard against model switch (#11349)

2026-02-10 11:58:00 -08:00

updates.rs

feat(core) Introduce Feature::RequestPermissions (#11871)

2026-02-24 09:48:57 -08:00