mirror of
https://github.com/BerriAI/litellm.git
synced 2026-09-21 00:21:49 +00:00
4a70bc3ba3
Budget is enforced once during auth, against the requested model group. `_is_model_cost_zero` waives every budget check for a zero-cost group, and the router then picks a fallback target afterwards, inside `run_async_fallback`, where nothing re-checks budget. A free model with a paid fallback therefore bills with no budget gate at all. Add `fallback_budget_check`, the budget sibling of the existing `fallback_access_check`: a predicate awaited per fallback target that skips targets the caller cannot pay for. The primary attempt is untouched, so a zero-cost model is never blocked by budget and only the paid fallback is refused. Counter reads pass `max_budget` so `get_current_spend` verifies against authoritative recorded spend, matching the auth-time key and user checks; a counter restored from an older snapshot reads as a hit rather than a clean miss, so without it a stale-low value would keep admitting paid fallbacks. A zero-cost fallback target is always allowed, and a team key does not inherit the key owner's personal budget unless `apply_user_budget_to_team_keys` is set, matching `_PROXY_MaxBudgetLimiter`. Scope is key and user budgets. Team, team-member, end-user, org, global and per-model budgets are not covered yet: those auth-path functions enforce rather than report, so reusing them would fire threshold alerts and take spend reservations for a target that is then skipped. Two limitations of that scope are documented in the module docstring: the check reads the spend counter rather than reserving against it, so concurrent fallbacks can cross a cap together; and a request reaching the router without `metadata["user_api_key_auth"]` is not restricted. Both are shared with `fallback_model_access.py`. Opt-in via `general_settings.enforce_fallback_budget`. Relates to #41344 Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| test_admin_viewer_handler_access.py | ||
| test_auth_checks.py | ||
| test_auth_exception_handler.py | ||
| test_auth_hot_path_network_requests.py | ||
| test_auth_object_prefetch.py | ||
| test_auth_utils.py | ||
| test_banned_params_extra_body.py | ||
| test_cli_auth.py | ||
| test_custom_auth_end_user_budget.py | ||
| test_fallback_budget.py | ||
| test_fallback_model_access.py | ||
| test_handle_jwt.py | ||
| test_info_routes.py | ||
| test_litellm_license.py | ||
| test_login_utils.py | ||
| test_mcp_ip_filtering.py | ||
| test_model_access_group_budgets.py | ||
| test_model_checks.py | ||
| test_model_checks_fallbacks.py | ||
| test_multi_budget_windows.py | ||
| test_network.py | ||
| test_oauth2_proxy_hook.py | ||
| test_object_permission_loading.py | ||
| test_onboarding.py | ||
| test_organization_budget_enforcement.py | ||
| test_password_hashing.py | ||
| test_password_policy.py | ||
| test_resolvers_exceptions.py | ||
| test_resolvers_grants.py | ||
| test_resolvers_models.py | ||
| test_resolvers_seam.py | ||
| test_resolvers_store.py | ||
| test_route_checks.py | ||
| test_router_override_fallback_auth.py | ||
| test_team_grants.py | ||
| test_team_member_budget.py | ||
| test_unmapped_model_budget_enforcement.py | ||
| test_user_api_key_auth.py | ||