[codex] Fix Claude auto fallback for MCP-only keychain#1992
Conversation
|
ClawSweeper review: did not complete due to Codex infrastructure failure. Reviewed July 8, 2026, 9:53 AM ET / 13:53 UTC. Summary Reproducibility: unclear. The review failed before ClawSweeper could establish a reproduction path. Review metrics: none identified. Merge readiness This is a ClawSweeper/Codex infrastructure failure, not a PR readiness or patch-quality verdict. Risk before merge
Maintainer options:
Next step before merge
Review detailsBest possible solution: Retry the Codex review after fixing the execution failure. Do we have a high-confidence way to reproduce the issue? Unclear. The review failed before ClawSweeper could establish a reproduction path. Is this the best way to solve the issue? Unclear. Retry the review first so ClawSweeper can evaluate the actual issue and fix direction. AGENTS.md: unclear because the file could not be read completely. Codex review notes: model internal, reasoning high; reviewed against aa401f1d8b74. Label changesLabel changes:
Evidence reviewedWhat I checked:
Likely related people:
How this review workflow works
Review history (3 earlier review cycles) |
Automode when the cached Claude CLI-owned OAuth credential is expired and the live Claude keychain only contains MCP OAuth state.Verification:
swift test --filter ClaudeOAuthFetchStrategyAvailabilityTestsSettings...→Debug→Fetch strategy attemptswith providerClaude:claude.oauth (oauth) unavailableclaude.cli (cli) availableThe live proof shows the background Auto planner/fetch attempts falling past OAuth to the CLI fallback. The focused regression test covers the matching user-initiated path remaining available.