fix(accounting): isolate only rows the raw insert cannot encode

Catching every ValueError also swallowed unexpected insert errors that main
re-raises. The raw insert now raises RejectedSpendLogRow for an unknown column
or non-JSON value, and only that is isolated as a rejected row.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

litellm/proxy/utils.py

@@ -277,6 +277,7 @@ from litellm.proxy.policy_engine.policy_registry import get_policy_registry
 from litellm.proxy.policy_engine.policy_resolver import PolicyResolver
 from litellm.repositories.budget_repository import BudgetRepository
 from litellm.repositories.config_repository import ConfigRepository
+from litellm.repositories.spend_log_insert import RejectedSpendLogRow
 from litellm.repositories.table_repositories import (
     EndUserRepository,
     HealthCheckRepository,
@@ -9174,7 +9175,10 @@ async def _keep_charges_of_dropped_logs(repo: SpendLogsRepository, rows: Sequenc
     try:
         await repo.insert_with_deliveries(charged)
     except Exception as e:  # noqa: BLE001  # the request log is already lost; keep the flush going for other rows
-        if not (PrismaDBExceptionHandler.is_rejected_row_error(e) or isinstance(e, (UnicodeEncodeError, ValueError))):
+        if not (
+            PrismaDBExceptionHandler.is_rejected_row_error(e)
+            or isinstance(e, (UnicodeEncodeError, RejectedSpendLogRow))
+        ):
             raise
         spend_log_error(
             "Spend tracking - could not keep the charges of %d dropped spend log rows. error=%s",
@@ -9215,7 +9219,10 @@ async def _create_spend_logs_with_poison_isolation(
         await repo.insert_with_deliveries(rows)
         return failure_budget
     except Exception as e:
-        if not (PrismaDBExceptionHandler.is_rejected_row_error(e) or isinstance(e, (UnicodeEncodeError, ValueError))):
+        if not (
+            PrismaDBExceptionHandler.is_rejected_row_error(e)
+            or isinstance(e, (UnicodeEncodeError, RejectedSpendLogRow))
+        ):
             raise
         if PrismaDBExceptionHandler.is_database_service_unavailable_error(e):
             raise

litellm/repositories/spend_log_insert.py

@@ -2,7 +2,7 @@ from collections.abc import Mapping, Sequence
 from datetime import datetime, timezone
 from typing import Final
 
-from pydantic import JsonValue, TypeAdapter
+from pydantic import JsonValue, TypeAdapter, ValidationError
 from typing_extensions import LiteralString
 
 from litellm.litellm_core_utils.safe_json_dumps import safe_dumps
@@ -50,12 +50,19 @@ _COLUMNS: Final[tuple[LiteralString, ...]] = (
 _JSON_COLUMNS: Final = frozenset({"metadata", "request_tags", "messages", "response", "proxy_server_request"})
 
 
+class RejectedSpendLogRow(ValueError):
+    """A row the raw insert cannot encode, so it is isolated like a row Postgres refuses."""
+
+
 def _json_value(column: str, value: object) -> object:
     if isinstance(value, datetime):
         return value.isoformat()
-    if column in _JSON_COLUMNS and isinstance(value, str):
+    if column not in _JSON_COLUMNS or not isinstance(value, str):
+        return value
+    try:
         return _JSON.validate_json(value)
-    return value
+    except ValidationError as error:
+        raise RejectedSpendLogRow(f"Spend log column {column} is not valid JSON") from error
 
 
 def spend_log_insert_statement(rows: Sequence[Mapping[str, object]]) -> tuple[LiteralString, str]:
@@ -63,7 +70,7 @@ def spend_log_insert_statement(rows: Sequence[Mapping[str, object]]) -> tuple[Li
         raise ValueError("Spend log insert requires at least one row")
     fields: Final = frozenset(rows[0]) | {"created_at", "updated_at"}
     if not fields.issubset(_COLUMNS) or any(frozenset(row) | {"created_at", "updated_at"} != fields for row in rows):
-        raise ValueError("Spend log insert requires matching known columns")
+        raise RejectedSpendLogRow("Spend log insert requires matching known columns")
     columns: Final = ", ".join('"' + column + '"' for column in _COLUMNS if column in fields)
     now: Final = datetime.now(timezone.utc).isoformat()
     values: Final = tuple(