Observed

Source-reviewed: a $50 configured budget produced $764.78 actual spend via the AzureOpenAI client — a 15x overshoot with no alert (#12977, closed not-planned 2025-10-31, no fix); user budgets are skipped entirely for virtual keys belonging to teams (#12905, closed not-planned); pass-through routes are not budget-tracked at all (#10750, closed not-planned); the underlying in-memory counters lose 75-93% of increments under 4+ concurrent threads (#20977 — stale-bot closed not-planned 2026-05-20 while the atomic-increment fix PR #20979 remains open unmerged, re-checked 2026-06-11); multi-replica deployments keep independent counters, allowing an N-replica deployment to breach a cap N times.

1. UPDATE 2026-07-17: the AWS-Bedrock-specific pass-through budget bypass (#12789) was fixed via merged PR #12847 (2025-07-22) — general pass-through routes (#10750) remain untracked. The team-virtual-key budget bypass (#12905) has a merged fix as of 2026-07-14 (PR #32005, breaking change, opt-out via skip_user_budget_on_team_key) but it is NOT yet in a released version — source inspection of v1.90.5 and v1.93.0-rc.2 confirms the old bypass guard is still present in both. The AzureOpenAI-client overshoot (#12977) remains unfixed with no PR in flight.