fix(proxy): add tpd_limit to deleted token table and fix CI fixtures

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

litellm-proxy-extras/litellm_proxy_extras/migrations/20260913000000_add_tpd_limit/migration.sql

@@ -9,3 +9,6 @@ ALTER TABLE "LiteLLM_DeletedTeamTable" ADD COLUMN IF NOT EXISTS "tpd_limit" BIGI
 
 -- AlterTable
 ALTER TABLE "LiteLLM_VerificationToken" ADD COLUMN IF NOT EXISTS "tpd_limit" BIGINT;
+
+-- AlterTable
+ALTER TABLE "LiteLLM_DeletedVerificationToken" ADD COLUMN IF NOT EXISTS "tpd_limit" BIGINT;

litellm-proxy-extras/litellm_proxy_extras/schema.prisma

@@ -538,6 +538,7 @@ model LiteLLM_DeletedVerificationToken {
     blocked                 Boolean?
     tpm_limit               BigInt?
     rpm_limit               BigInt?
+    tpd_limit               BigInt?
     max_budget              Float?
     budget_duration         String?
     budget_reset_at         DateTime?

litellm/proxy/management_endpoints/organization_endpoints.py

@@ -362,6 +362,7 @@ async def new_organization(
     - max_budget: *Optional[float]* - Max budget for org
     - tpm_limit: *Optional[int]* - Max tpm limit for org
     - rpm_limit: *Optional[int]* - Max rpm limit for org
+    - tpd_limit: *Optional[int]* - Max tokens per day stored on the org budget. Batch submissions enforce tpd_limit at the key, team and end user scopes only.
     - model_rpm_limit: *Optional[Dict[str, int]]* - The RPM (Requests Per Minute) limit per model for this organization.
     - model_tpm_limit: *Optional[Dict[str, int]]* - The TPM (Tokens Per Minute) limit per model for this organization.
     - max_parallel_requests: *Optional[int]* - [Not Implemented Yet] Max parallel requests for org

litellm/proxy/schema.prisma

@@ -538,6 +538,7 @@ model LiteLLM_DeletedVerificationToken {
     blocked                 Boolean?
     tpm_limit               BigInt?
     rpm_limit               BigInt?
+    tpd_limit               BigInt?
     max_budget              Float?
     budget_duration         String?
     budget_reset_at         DateTime?

schema.prisma

@@ -538,6 +538,7 @@ model LiteLLM_DeletedVerificationToken {
     blocked                 Boolean?
     tpm_limit               BigInt?
     rpm_limit               BigInt?
+    tpd_limit               BigInt?
     max_budget              Float?
     budget_duration         String?
     budget_reset_at         DateTime?

tests/test_litellm/proxy/management_endpoints/test_customer_endpoints.py

@@ -743,6 +743,7 @@ _EXPECTED_CUSTOMER = {
         "max_parallel_requests": None,
         "tpm_limit": None,
         "rpm_limit": None,
+        "tpd_limit": None,
         "model_max_budget": None,
         "budget_duration": "30d",
         "allowed_models": [],

ui/litellm-dashboard/src/app/(dashboard)/budgets/_components/BudgetTable.test.tsx

@@ -152,9 +152,8 @@ describe("BudgetTable", () => {
   });
 
   it("should show n/a for missing rate limits and Unlimited for a missing max budget", () => {
-    const list = makeList({
-      rows: [makeBudget({ max_budget: null, tpm_limit: null, rpm_limit: null, tpd_limit: null })],
-    });
+    const noLimits = { max_budget: null, tpm_limit: null, rpm_limit: null, tpd_limit: null };
+    const list = makeList({ rows: [makeBudget(noLimits)] });
     renderWithProviders(<BudgetTable {...defaultProps} list={list} />);
     expect(screen.getAllByText("n/a")).toHaveLength(3);
     expect(screen.getByText("Unlimited")).toBeInTheDocument();