issue: update 1e2a - document completed retry logic and remaining work

2026-10-05 15:08:24 +00:00 · 2026-01-27 21:23:42 +00:00
parent 642d6fa89c
commit 1d2eebd7a1
1 changed files with 19 additions and 0 deletions
@@ -48,6 +48,25 @@ This is particularly problematic because:
 ## Progress
 ### 2026-01-27 [Session 17:30]
 - **Completed:** Basic retry logic implemented in migration-v2 branch
  - Retry loop that excludes failed OIDs and retries with remaining OIDs (src/purgatory/sync/context.rs:363-471)
  - Debug-level logging for retry operations
  - Proper error reporting with URLs for all failure cases
 - **Remaining work:**
  - Throttling integration: Respect domain throttling limits between retries
  - Metrics: Track retry attempts, successes, and confirmed missing OIDs
  - OID prioritization: Implement tiered fetching strategy:
    - First: Latest state events (kind 30617)
    - Second: Earlier state events
    - Third: PR refs
    - After successful fetch, retry to get remaining OIDs that aren't confirmed missing
  - Note: Rate limiting retries is better handled through throttling integration rather than separate backoff logic
 - **Not needed:**
  - Partial success handling (git servers don't support partial fetches - they fail atomically)
 ### 2026-01-27 [Session]
 - Implemented Phase 1: retry logic for "not our ref" errors
 - When fetch fails with "not our ref", extracts missing OID and retries with remaining OIDs