Fix compressed rollout search path matching (#27407)

## Why

`thread/search` found content inside compressed rollouts but could drop
the result when joining it with SQLite-backed thread metadata. Search
returned the physical `.jsonl.zst` path while SQLite retained the
logical `.jsonl` path, so exact path matching failed.

## What changed

- Key rollout search matches by their canonical logical `.jsonl` path,
independent of the on-disk representation.
- Canonicalize thread-list paths before joining them with content-search
matches.
- Update compressed-rollout coverage to assert the logical-path
contract.

## Validation

- Ran `just fmt`.
- Ran `git diff --check`.
- Tests and Clippy were intentionally left to CI.
This commit is contained in:
jif
2026-06-10 18:23:42 +01:00
committed by GitHub
Unverified
parent 2ef007dc1a
commit d3abd8774e
3 changed files with 13 additions and 6 deletions
+2 -3
View File
@@ -106,14 +106,13 @@ async fn append_rollout_item_materializes_compressed_rollout() -> anyhow::Result
}
#[tokio::test]
async fn search_rollout_matches_returns_compressed_snippet() -> anyhow::Result<()> {
async fn search_rollout_matches_uses_logical_path_for_compressed_rollout() -> anyhow::Result<()> {
let home = TempDir::new()?;
let uuid = Uuid::from_u128(15);
let thread_id = ThreadId::from_string(&uuid.to_string())?;
let rollout_path = rollout_path(home.path(), "2025-01-03T12-00-00", uuid);
write_rollout(&rollout_path, thread_id, "targeted search term")?;
compress_now(&rollout_path)?;
let compressed_path = compressed_rollout_path(&rollout_path);
let matches = search_rollout_matches(
std::path::Path::new("missing-rg-for-test"),
@@ -124,7 +123,7 @@ async fn search_rollout_matches_returns_compressed_snippet() -> anyhow::Result<(
.await?;
assert_eq!(
matches.get(compressed_path.as_path()),
matches.get(rollout_path.as_path()),
Some(&Some("targeted search term".to_string()))
);
Ok(())
+9 -2
View File
@@ -21,6 +21,7 @@ use super::compression;
const MATCH_CONTEXT_BEFORE_CHARS: usize = 48;
const MATCH_CONTEXT_AFTER_CHARS: usize = 96;
/// Search matches keyed by the canonical `.jsonl` path for each rollout.
pub type RolloutSearchMatches = HashMap<PathBuf, Option<String>>;
pub async fn search_rollout_paths(
@@ -145,7 +146,10 @@ async fn scan_rollout_matches(
if let Some(snippet) =
first_rollout_content_match_snippet(rollout_file.path(), search_term).await?
{
matches.insert(rollout_file.into_path(), Some(snippet));
matches.insert(
compression::plain_rollout_path(rollout_file.path()),
Some(snippet),
);
}
continue;
}
@@ -217,7 +221,10 @@ async fn scan_compressed_rollout_matches(
if let Some(snippet) =
first_rollout_content_match_snippet(rollout_file.path(), search_term).await?
{
matches.insert(rollout_file.into_path(), Some(snippet));
matches.insert(
compression::plain_rollout_path(rollout_file.path()),
Some(snippet),
);
}
}
}
@@ -109,7 +109,8 @@ pub(super) async fn search_threads(
)
.await?;
for item in page.items {
let Some(snippet) = (match remaining_rollouts.remove(item.path.as_path()) {
let logical_path = codex_rollout::plain_rollout_path(item.path.as_path());
let Some(snippet) = (match remaining_rollouts.remove(logical_path.as_path()) {
Some(Some(snippet)) => Some(snippet),
Some(None) => first_rollout_content_match_snippet(item.path.as_path(), search_term)
.await