[Fix] Responses bridge variable mismatch and outdated CI tests

Fix genuine regression in responses_api_bridge_check where the second
call assigned to `model_info` instead of `responses_api_model_info`,
preventing gpt-5.4 + tools + reasoning_effort from routing to the
Responses API bridge.

Also update outdated tests:
- Vantage tests: match "csv" file key and use supported column names
- Anthropic caching test: add "type": "custom" to expected tool payload
- Claude Agent SDK test: remove non-deterministic LLM content assertion

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

litellm/main.py

@@ -1613,7 +1613,7 @@ def completion(  # type: ignore # noqa: PLR0915
             )
 
         ## RESPONSES API BRIDGE LOGIC ## - check if model has 'mode: responses' in litellm.model_cost map
-        model_info, model = responses_api_bridge_check(
+        responses_api_model_info, model = responses_api_bridge_check(
             model=model,
             custom_llm_provider=custom_llm_provider,
             web_search_options=web_search_options,

tests/local_testing/test_anthropic_prompt_caching.py

@@ -151,6 +151,7 @@ async def test_litellm_anthropic_prompt_caching_tools():
                         },
                         "required": ["location"],
                     },
+                    "type": "custom",
                 }
             ],
             "max_tokens": 64000,

tests/proxy_e2e_anthropic_messages_tests/test_claude_agent_sdk.py

@@ -110,8 +110,8 @@ async def test_claude_agent_sdk_streaming(litellm_proxy_config, model_name, mode
         # Note: Very short responses might come in 1 chunk, so we just verify we got content
         assert len(received_chunks) > 0, f"No chunks received from {model_name}"
         
-        # Verify response contains expected content (case insensitive)
-        assert "hello" in full_response.lower(), f"Response doesn't contain expected greeting: {full_response}"
+        # Verify response is non-empty (don't assert on specific LLM content — it's non-deterministic)
+        assert len(full_response.strip()) > 0, f"Empty response received from {model_name}"
         
         print(f"✅ Test passed for {model_name}")
         

tests/test_litellm/integrations/focus/test_vantage_destination.py

@@ -100,8 +100,9 @@ async def test_should_upload_csv_to_correct_url():
 async def test_should_batch_large_content():
     dest = FocusVantageDestination(prefix="exports", config=_config())
 
-    # Create content larger than 2 MB
-    header = b"col1,col2,col3"
+    # Create content larger than 2 MB — use supported column names so
+    # _strip_unsupported_columns does not remove them.
+    header = b"ChargeCategory,ChargePeriodStart,BilledCost"
     row = b"a" * 100 + b"," + b"b" * 100 + b"," + b"c" * 100
     num_rows = (VANTAGE_MAX_BYTES_PER_UPLOAD // len(row)) + 100
     large_content = header + b"\n" + b"\n".join([row] * num_rows) + b"\n"
@@ -119,8 +120,8 @@ async def test_should_batch_large_content():
 
     async def capture_post(url, **kwargs):
         files = kwargs.get("files", {})
-        if "file" in files:
-            upload_calls.append(files["file"][1])
+        if "csv" in files:
+            upload_calls.append(files["csv"][1])
         return mock_response
 
     mock_client.post = capture_post
@@ -144,7 +145,7 @@ async def test_should_batch_by_row_count():
     """Verify batching triggers when row count exceeds 10K even if under 2 MB."""
     dest = FocusVantageDestination(prefix="exports", config=_config())
 
-    header = b"col1"
+    header = b"ChargeCategory"
     # Short rows so total size stays well under 2 MB
     row = b"x"
     num_rows = VANTAGE_MAX_ROWS_PER_UPLOAD + 500
@@ -165,8 +166,8 @@ async def test_should_batch_by_row_count():
 
     async def capture_post(url, **kwargs):
         files = kwargs.get("files", {})
-        if "file" in files:
-            upload_calls.append(files["file"][1])
+        if "csv" in files:
+            upload_calls.append(files["csv"][1])
         return mock_response
 
     mock_client.post = capture_post