## What changed
Read rollout evidence from newest to oldest for both memory versions, retaining up to 8 MiB of sanitized response items and inter-agent communications, then restore chronological order. Skip malformed records and records larger than 1 MiB, and require valid session metadata in the first record within that limit.
## Testing
Add coverage for the retained byte budget, newest-record ordering, malformed and oversized records, and unsupported session metadata. Extend extraction request tests for both memory versions to verify that evidence after an oversized record reaches the model.
GitOrigin-RevId: 55ccbc2477ecb059830d3a55be12bcbc21235303
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
## Why
Memory extraction has a limited rollout budget. Select evidence by source so human input and assistant final responses take priority over commentary, context, and tool output.
## What changed
- Use tiered selection for memory v2, preferring newer evidence within each tier and rendering selected items in chronological order with omission markers.
- Keep answered `request_user_input` questions alongside human replies, label evidence sources, replace message media with placeholders, and bound tool output and individual rows.
- Add typed memory context fragments with bounded messages and Unicode-safe extraction chunking.
## Testing
Add tests for memory v2 startup using tiered input and for extraction chunks preserving Unicode evidence within message bounds.
GitOrigin-RevId: 1b2bba4e3264b4fda271e429ad3b7d5f69caed59