Merge pull request #14587 from timelfrink/fix/streaming-tool-call-indices

Fix: Streaming tool call index assignment for multiple tool calls

Author: krrishdholakia

litellm/types/utils.py

@@ -757,10 +757,12 @@ def __init__(
             self.function_call = function_call
         if tool_calls is not None and isinstance(tool_calls, list):
             self.tool_calls = []
+            current_index = 0
             for tool_call in tool_calls:
                 if isinstance(tool_call, dict):
                     if tool_call.get("index", None) is None:
-                        tool_call["index"] = 0
+                        tool_call["index"] = current_index
+                        current_index += 1
                     self.tool_calls.append(ChatCompletionDeltaToolCall(**tool_call))
                 elif isinstance(tool_call, ChatCompletionDeltaToolCall):
                     self.tool_calls.append(tool_call)

tests/litellm_utils_tests/test_utils.py

@@ -2328,6 +2328,54 @@ def test_get_whitelisted_models():
     print("whitelisted_models written to whitelisted_bedrock_models.txt")
 
 
+def test_delta_tool_calls_sequential_indices():
+    """
+    Test that multiple tool calls without explicit indices receive sequential indices.
+
+    When providers don't include index fields in tool calls, the Delta class
+    should automatically assign sequential indices (0, 1, 2, ...) instead of
+    defaulting all tool calls to index=0.
+    """
+    import json
+    from litellm.types.utils import Delta
+
+    # Simulate tool calls from streaming responses without explicit indices
+    tool_calls_without_indices = [
+        {
+            "id": "call_1",
+            "function": {
+                "name": "get_weather_for_dallas",
+                "arguments": json.dumps({})
+            },
+            "type": "function",
+            # Note: no "index" field - simulates provider response
+        },
+        {
+            "id": "call_2",
+            "function": {
+                "name": "get_weather_precise",
+                "arguments": json.dumps({"location": "Dallas, TX"})
+            },
+            "type": "function",
+            # Note: no "index" field - simulates provider response
+        }
+    ]
+
+    # Create Delta object as LiteLLM would when processing streaming response
+    delta = Delta(
+        content=None,
+        tool_calls=tool_calls_without_indices
+    )
+
+    # Verify tool calls have sequential indices
+    assert delta.tool_calls is not None, "Tool calls should not be None"
+    assert len(delta.tool_calls) == 2
+    assert delta.tool_calls[0].index == 0, f"First tool call should have index 0, got {delta.tool_calls[0].index}"
+    assert delta.tool_calls[1].index == 1, f"Second tool call should have index 1, got {delta.tool_calls[1].index}"
+
+    # Verify tool call details are preserved
+    assert delta.tool_calls[0].function.name == "get_weather_for_dallas"
+    assert delta.tool_calls[1].function.name == "get_weather_precise"
 
 def test_completion_with_no_model():
     """