jif e7f5de0a6a Move v2 extraction chunking into the memory writer (#43808) ...

Move `extraction_messages` from `MemoryContextFragment` in `codex-core` to
`codex-rs/memories/write/src/rollout_input.rs` and update the phase-one caller.
Preserve the existing 8,900-byte chunk limit and Unicode-safe boundaries.

Move the accompanying test with the helper, retaining coverage that bounded
user messages reconstruct the original evidence without loss.

GitOrigin-RevId: 48ac501acbfa50c4195195fd40efc7588a6c714d

2026-09-08 12:46:39 +00:00

..

src

Move v2 extraction chunking into the memory writer (#43808)

2026-09-08 12:46:39 +00:00

templates

Add summary-only extraction for memory v2 (#43800)

2026-09-08 11:25:15 +00:00

BUILD.bazel

build: run buildifier from just fmt (#28125)

2026-06-13 21:43:39 -07:00

Cargo.toml

feat: use provider defaults for memory models (#27129)

2026-06-09 23:49:09 +00:00