fix(proxy): strip LiteLLM policy tracking from OpenAI batch metadata (#28425)

* fix(proxy): strip LiteLLM policy tracking from OpenAI batch metadata

Batch create was failing with `Invalid type for 'metadata.applied_policies':
expected a string, but got an array instead` whenever a policy attachment
matched the request. The policy engine helpers wrote `applied_policies`,
`applied_guardrails`, and `policy_sources` into `data["metadata"]`
unconditionally, and `/v1/batches` forwarded that dict straight to OpenAI,
which only accepts string values.

- Route proxy-internal tracking into `litellm_metadata` for batch/file
  routes via a shared `_get_or_create_proxy_metadata_bucket` helper.
- Sanitize `data["metadata"]` in `create_batch` to drop known internal
  keys and non-string values before building the OpenAI request.
- Cover both behaviors with unit + endpoint tests.

Co-authored-by: Cursor <cursoragent@cursor.com>

* fix(proxy): merge metadata buckets for batch policy response headers

Ensure get_logging_caching_headers reads both metadata and litellm_metadata so policy/guardrail headers are emitted on batch routes with user metadata, and log dropped non-string OpenAI metadata at debug level.

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>

tests/test_litellm/proxy/common_utils/test_callback_utils.py

@@ -8,11 +8,14 @@ sys.path.insert(
 )  # Adds the parent directory to the system path
 
 from litellm.proxy.common_utils.callback_utils import (
+    add_policy_to_applied_policies_header,
     decrypt_callback_vars,
     encrypt_callback_vars,
+    get_logging_caching_headers,
     initialize_callbacks_on_proxy,
     get_remaining_tokens_and_requests_from_request_data,
     normalize_callback_names,
+    sanitize_openai_provider_metadata,
 )
 import litellm
 
@@ -92,6 +95,50 @@ def test_normalize_callback_names_lowercases_strings():
     ]
 
 
+def test_add_policy_to_applied_policies_header_uses_litellm_metadata_bucket():
+    request_data = {
+        "input_file_id": "file-abc123",
+        "litellm_metadata": {},
+    }
+
+    add_policy_to_applied_policies_header(
+        request_data=request_data, policy_name="global-baseline"
+    )
+
+    assert request_data["litellm_metadata"]["applied_policies"] == ["global-baseline"]
+    assert "applied_policies" not in request_data.get("metadata", {})
+
+
+def test_sanitize_openai_provider_metadata_strips_internal_tracking_fields():
+    metadata = {
+        "customer_id": "cust-123",
+        "applied_policies": ["global-baseline"],
+        "applied_guardrails": ["pii_blocker"],
+        "note": 42,
+    }
+
+    sanitized = sanitize_openai_provider_metadata(metadata)
+
+    assert sanitized == {"customer_id": "cust-123"}
+
+
+def test_get_logging_caching_headers_merges_metadata_and_litellm_metadata():
+    request_data = {
+        "metadata": {"customer_id": "cust-123"},
+        "litellm_metadata": {
+            "applied_policies": ["global-baseline"],
+            "applied_guardrails": ["pii_blocker"],
+            "policy_sources": {"global-baseline": "team_default"},
+        },
+    }
+
+    headers = get_logging_caching_headers(request_data)
+
+    assert headers["x-litellm-applied-policies"] == "global-baseline"
+    assert headers["x-litellm-applied-guardrails"] == "pii_blocker"
+    assert headers["x-litellm-policy-sources"] == "global-baseline=team_default"
+
+
 def test_initialize_callbacks_on_proxy_instantiates_compression_interception(
     monkeypatch,
 ):