From d3e695f0552a6637d9a0f573a1c86f83eecfa47c Mon Sep 17 00:00:00 2001
From: Guilherme Pires <gpires@altius.org>
Date: Thu, 12 Feb 2026 22:26:49 -0800
Subject: [PATCH] Fix Gemini parallel tool call ID mismatch in Responses API
 translation

When litellm converts Responses API function_call input items to Chat
Completion messages, each function_call item becomes a separate assistant
message with a single tool_calls entry. For providers like Gemini that
issue parallel tool calls in one model turn, this produces multiple
assistant messages instead of one with multiple tool_calls.

The Gemini message converter later walks the history looking for the
'last assistant message with tool calls' to match a tool result. With
split messages, it only finds the last call's assistant message and
fails to match earlier calls' tool results, producing:

  Missing corresponding tool call for tool response message.
  Received - message={'role': 'tool', 'content': '...', 'tool_call_id': 'call_xxx'}

Fix: merge consecutive function_call-derived assistant messages into a
single assistant message with multiple tool_calls entries, re-indexing
as needed. This preserves the one-turn-one-message invariant that
downstream converters expect.

Affects: Gemini 3 models with parallel tool calls via the Responses API
(litellm.aresponses / /v1/responses endpoint).
---
 .../transformation.py                         | 46 ++++++++++++++++++-
 1 file changed, 45 insertions(+), 1 deletion(-)

diff --git a/litellm/responses/litellm_completion_transformation/transformation.py b/litellm/responses/litellm_completion_transformation/transformation.py
index 08e31c59662..fdd70657cf6 100644
--- a/litellm/responses/litellm_completion_transformation/transformation.py
+++ b/litellm/responses/litellm_completion_transformation/transformation.py
@@ -434,7 +434,51 @@ class LiteLLMCompletionResponsesConfig:
                     messages.extend(deduped_in_place)
                     continue
 
-                messages.extend(chat_completion_messages)
+                ###########################################################
+                # Merge consecutive function_call items into a single
+                # assistant message.  Providers like Gemini require that
+                # parallel tool calls that were issued in one model turn
+                # appear as *one* assistant message with multiple
+                # tool_calls, not as separate assistant messages.
+                ###########################################################
+                for m in chat_completion_messages:
+                    role = m.get("role") if isinstance(m, dict) else getattr(m, "role", "")
+                    if role != "assistant":
+                        messages.append(m)
+                        continue
+
+                    new_tcs: Any = (
+                        m.get("tool_calls")
+                        if isinstance(m, dict)
+                        else getattr(m, "tool_calls", None)
+                    ) or []
+
+                    # Try to merge into the last message if it is an
+                    # assistant message that already carries tool_calls.
+                    merged = False
+                    if messages:
+                        last = messages[-1]
+                        last_role = last.get("role") if isinstance(last, dict) else getattr(last, "role", "")
+                        if last_role == "assistant":
+                            existing_tcs: Any = (
+                                last.get("tool_calls")
+                                if isinstance(last, dict)
+                                else getattr(last, "tool_calls", None)
+                            )
+                            if existing_tcs is not None:
+                                # Re-index and append
+                                for tc in new_tcs:
+                                    idx = len(existing_tcs)
+                                    if isinstance(tc, dict):
+                                        tc["index"] = idx
+                                    elif hasattr(tc, "index"):
+                                        tc.index = idx
+                                    existing_tcs.append(tc)
+                                merged = True
+
+                    if not merged:
+                        messages.append(m)
+
         return messages
 
     @staticmethod