fix(proxy/hooks): populate llm_provider on batch-rate-limit 429s

batch_rate_limiter._raise_rate_limit_error now takes a
requested_model kwarg threaded from data['model'] in
_check_and_increment_batch_counters. The batch-creation 429 is what
gets raised when the input file's tokens/requests count would push
the per-key TPM/RPM window over its limit.

Co-authored-by: Mateo Wang <mateo-berri@users.noreply.github.com>

litellm/proxy/hooks/batch_rate_limiter.py

@@ -31,6 +31,10 @@ from litellm.batches.batch_utils import (
 )
 from litellm.integrations.custom_logger import CustomLogger
 from litellm.proxy._types import UserAPIKeyAuth
+from litellm.proxy.hooks.rate_limiter_utils import (
+    ProxyHTTPRateLimitError,
+    resolve_llm_provider_for_rate_limit,
+)
 
 if TYPE_CHECKING:
     from opentelemetry.trace import Span as _Span
@@ -104,6 +108,7 @@ class _PROXY_BatchRateLimiter(CustomLogger):
         descriptors: List["RateLimitDescriptor"],
         batch_usage: BatchFileUsage,
         limit_type: str,
+        requested_model: Optional[str] = None,
     ) -> None:
         """Raise HTTPException for rate limit exceeded."""
         from datetime import datetime
@@ -148,7 +153,10 @@ class _PROXY_BatchRateLimiter(CustomLogger):
                 f"Limit resets at: {reset_time_formatted}"
             )
 
-        raise HTTPException(
+        resolved_model, llm_provider = resolve_llm_provider_for_rate_limit(
+            requested_model
+        )
+        raise ProxyHTTPRateLimitError(
             status_code=429,
             detail=detail,
             headers={
@@ -156,6 +164,8 @@ class _PROXY_BatchRateLimiter(CustomLogger):
                 "rate_limit_type": limit_type,
                 "reset_at": reset_time_formatted,
             },
+            model=resolved_model,
+            llm_provider=llm_provider,
         )
 
     async def _check_and_increment_batch_counters(
@@ -197,6 +207,7 @@ class _PROXY_BatchRateLimiter(CustomLogger):
         )
 
         if rate_limit_response["overall_code"] == "OVER_LIMIT":
+            requested_model = data.get("model") if data else None
             for status in rate_limit_response["statuses"]:
                 if status["code"] == "OVER_LIMIT":
                     self._raise_rate_limit_error(
@@ -204,6 +215,7 @@ class _PROXY_BatchRateLimiter(CustomLogger):
                         descriptors,
                         batch_usage,
                         status["rate_limit_type"],
+                        requested_model=requested_model,
                     )
 
     async def count_input_file_usage(