jif c2837d8ece Batch metadata reads when resolving thread names (#49305) ...

## Why

Thread name resolution performs a separate SQLite metadata lookup for each thread. Batch these reads to reduce database queries for large result sets.

## What changed

Add `StateRuntime::get_threads` and use it in `resolve_thread_names`. Fetch metadata in batches of at most 999 IDs to stay within SQLite's bind limit, skipping missing or invalid records independently so valid metadata remains available.

## Testing

Add regression coverage for reads spanning multiple batches, invalid and missing records, duplicate IDs, and empty input.

GitOrigin-RevId: a403416f1da5adea56705c70839850760d3eb550

2026-09-29 16:36:07 +00:00

..

goals_migrations

Preserve thread context when retrying or editing turns (#33211)

2026-07-15 02:35:49 +00:00

logs_migrations

Align SQLite feedback logs with feedback formatter (#13494)

2026-03-18 22:44:31 +00:00

memory_migrations

Add memory dual writing and v2 readiness reporting (#43827)

2026-09-08 14:23:23 +00:00

migrations

Keep archived threads with empty previews visible in listings (#48199)

2026-09-25 20:11:47 +00:00

queue_migrations

Dispatch queued messages written by other processes (#39034)

2026-08-17 17:19:46 +00:00

src

Batch metadata reads when resolving thread names (#49305)

2026-09-29 16:36:07 +00:00

thread_history_migrations

Preserve and expose thread item lifecycle timestamps (#47114)

2026-09-21 22:23:26 +00:00

BUILD.bazel

Shard state unit tests under Bazel (#37478)

2026-08-07 17:49:48 +00:00

Cargo.toml

Avoid building a host SQLite driver for SQLx macros (#47084)

2026-09-21 18:30:31 +00:00