mirror of
https://github.com/openai/codex.git
synced 2026-05-04 19:36:45 +00:00
feat: resumable backfill (#10745)
## Summary This PR makes SQLite rollout backfill resumable and repeatable instead of one-shot-on-db-create. ## What changed - Added a persisted backfill state table: - state/migrations/0008_backfill_state.sql - Tracks status (pending|running|complete), last_watermark, and last_success_at. - Added backfill state model/types in codex-state: - BackfillState, BackfillStatus (state/src/model/backfill_state.rs) - Added runtime APIs to manage backfill lifecycle/progress: - get_backfill_state - mark_backfill_running - checkpoint_backfill - mark_backfill_complete - Updated core startup behavior: - Backfill now runs whenever state is not Complete (not only when DB file is newly created). - Reworked backfill execution: - Collect rollout files, derive deterministic watermark per path, sort, resume from last_watermark. - Process in batches (BACKFILL_BATCH_SIZE = 200), checkpoint after each batch. - Mark complete with last_success_at at the end. ## Why Previous behavior could leave users permanently partially backfilled if the process exited during initial async backfill. This change allows safe continuation across restarts and avoids restarting from scratch.
This commit is contained in:
@@ -31,11 +31,9 @@ pub(crate) async fn init_if_enabled(
|
||||
config: &Config,
|
||||
otel: Option<&OtelManager>,
|
||||
) -> Option<StateDbHandle> {
|
||||
let state_path = codex_state::state_db_path(config.codex_home.as_path());
|
||||
if !config.features.enabled(Feature::Sqlite) {
|
||||
return None;
|
||||
}
|
||||
let existed = tokio::fs::try_exists(&state_path).await.unwrap_or(false);
|
||||
let runtime = match codex_state::StateRuntime::init(
|
||||
config.codex_home.clone(),
|
||||
config.model_provider_id.clone(),
|
||||
@@ -55,7 +53,17 @@ pub(crate) async fn init_if_enabled(
|
||||
return None;
|
||||
}
|
||||
};
|
||||
if !existed {
|
||||
let should_backfill = match runtime.get_backfill_state().await {
|
||||
Ok(state) => state.status != codex_state::BackfillStatus::Complete,
|
||||
Err(err) => {
|
||||
warn!(
|
||||
"failed to read backfill state at {}: {err}",
|
||||
config.codex_home.display()
|
||||
);
|
||||
true
|
||||
}
|
||||
};
|
||||
if should_backfill {
|
||||
let runtime_for_backfill = Arc::clone(&runtime);
|
||||
let config_for_backfill = config.clone();
|
||||
let otel_for_backfill = otel.cloned();
|
||||
|
||||
Reference in New Issue
Block a user