From 5994ef90944e7fae543c3ff011ac073c14e9cc28 Mon Sep 17 00:00:00 2001
From: shivam <shivam@berri.ai>
Date: Sat, 23 May 2026 14:22:28 -0700
Subject: [PATCH] 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>
---
 litellm/proxy/common_utils/callback_utils.py  | 20 ++++++++++++++-----
 .../proxy/common_utils/test_callback_utils.py | 18 +++++++++++++++++
 2 files changed, 33 insertions(+), 5 deletions(-)

diff --git a/litellm/proxy/common_utils/callback_utils.py b/litellm/proxy/common_utils/callback_utils.py
index 7d558781320..c5b97db07a0 100644
--- a/litellm/proxy/common_utils/callback_utils.py
+++ b/litellm/proxy/common_utils/callback_utils.py
@@ -409,11 +409,15 @@ def get_remaining_tokens_and_requests_from_request_data(data: Dict) -> Dict[str,
 
 
 def get_logging_caching_headers(request_data: Dict) -> Optional[Dict]:
-    _metadata = request_data.get("metadata", None)
-    if not _metadata:
-        _metadata = request_data.get("litellm_metadata", None)
-    if not isinstance(_metadata, dict):
-        _metadata = {}
+    _metadata: Dict = {}
+    metadata_bucket = request_data.get("metadata")
+    litellm_metadata_bucket = request_data.get("litellm_metadata")
+    if isinstance(metadata_bucket, dict):
+        _metadata.update(metadata_bucket)
+    if isinstance(litellm_metadata_bucket, dict):
+        # Batch/file routes store proxy tracking in litellm_metadata while
+        # user-facing metadata stays in metadata; merge both for headers.
+        _metadata.update(litellm_metadata_bucket)
     headers = {}
     if "applied_guardrails" in _metadata:
         headers["x-litellm-applied-guardrails"] = ",".join(
@@ -529,6 +533,12 @@ def sanitize_openai_provider_metadata(
             continue
         if isinstance(value, str):
             sanitized[key] = value
+        else:
+            verbose_proxy_logger.debug(
+                "sanitize_openai_provider_metadata: dropping key %r with non-string value of type %s",
+                key,
+                type(value).__name__,
+            )
     return sanitized or None
 
 
diff --git a/tests/test_litellm/proxy/common_utils/test_callback_utils.py b/tests/test_litellm/proxy/common_utils/test_callback_utils.py
index 9ece72c2f99..d328d68dcd4 100644
--- a/tests/test_litellm/proxy/common_utils/test_callback_utils.py
+++ b/tests/test_litellm/proxy/common_utils/test_callback_utils.py
@@ -11,6 +11,7 @@ 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,
@@ -121,6 +122,23 @@ def test_sanitize_openai_provider_metadata_strips_internal_tracking_fields():
     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,
 ):