jif 48524f337a Preserve pending agent messages across compaction (#59404) ...

## Why

Agent messages that arrive after a model request starts must survive compaction until a normal inference request includes them. Compactor output alone does not establish that those messages were delivered.

## What changed

- Persist history sequences and sampling checkpoints in harness metadata, capturing the input prefix for each normal inference request.
- Retain pending agent messages within existing size budgets during local and remote compaction, placing the summary before pending messages and subsequent caller input.
- Preserve sampling progress across history replacement and resume, and drain queued mail after interrupted sampling even when compaction leaves context above the token limit.

## Testing

Add regression coverage for request-boundary sampling checkpoints, pending messages across local compaction and repeated remote compaction with resume, and injected messages that interrupt sampling before mid-turn compaction.

GitOrigin-RevId: 26c04ab96b5a1c3cc1d6625ccc74a0f00201d14c

2026-11-04 13:03:01 +00:00

..

v2

Preserve pending agent messages across compaction (#59404)

2026-11-04 13:03:01 +00:00

auth.rs

Show the selected ChatGPT workspace in /status (#57366)

2026-10-27 05:22:23 +00:00

conversation_summary.rs

Introduce a dedicated context window ID type (#59328)

2026-11-04 06:05:16 +00:00

fuzzy_file_search.rs

Simplify app-server integration test setup (#34786)

2026-07-22 16:30:12 +00:00

logging.rs

Validate thread providers before resume and input (#57840)

2026-10-28 21:33:02 +00:00

mod.rs

app-server: structure and test JSON shutdown logs (#30314)

2026-06-26 18:19:56 -07:00

strict_config.rs

Expose effective login methods in config requirements (#45495)

2026-09-14 19:11:29 +00:00