chore!: Update finish reason in output of HuggingFaceAPIChatGenerator to match between stream and non-stream modes (#9686)

* Update finish reason

* Fix unit test

* Add reno

* Update releasenotes/notes/update-finish-reason-hf-api-chat-gen-c700042a079733e8.yaml

Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>

* Update async as well

* Fix unit test

---------

Co-authored-by: Amna Mubashar <amnahkhan.ak@gmail.com>

haystack/components/generators/chat/hugging_face_api.py

@@ -40,6 +40,7 @@ with LazyImport(message="Run 'pip install \"huggingface_hub[inference]>=0.27.0\"
         ChatCompletionInputStreamOptions,
         ChatCompletionInputTool,
         ChatCompletionOutput,
+        ChatCompletionOutputComplete,
         ChatCompletionOutputToolCall,
         ChatCompletionStreamOutput,
         ChatCompletionStreamOutputChoice,
@@ -112,7 +113,9 @@ def _convert_tools_to_hfapi_tools(
     return hf_tools
 
 
-def _map_hf_finish_reason_to_haystack(choice: "ChatCompletionStreamOutputChoice") -> Optional[FinishReason]:
+def _map_hf_finish_reason_to_haystack(
+    choice: Union["ChatCompletionStreamOutputChoice", "ChatCompletionOutputComplete"],
+) -> Optional[FinishReason]:
     """
     Map HuggingFace finish reasons to Haystack FinishReason literals.
 
@@ -133,7 +136,10 @@ def _map_hf_finish_reason_to_haystack(choice: "ChatCompletionStreamOutputChoice"
         return None
 
     # Check if this choice contains tool call information
-    has_tool_calls = choice.delta.tool_calls is not None or choice.delta.tool_call_id is not None
+    if isinstance(choice, ChatCompletionStreamOutputChoice):
+        has_tool_calls = choice.delta.tool_calls is not None or choice.delta.tool_call_id is not None
+    else:
+        has_tool_calls = choice.message.tool_calls is not None or choice.message.tool_call_id is not None
 
     # If we detect tool calls, override the finish reason
     if has_tool_calls:
@@ -565,9 +571,10 @@ class HuggingFaceAPIChatGenerator:
 
         tool_calls = _convert_hfapi_tool_calls(choice.message.tool_calls)
 
+        mapped_finish_reason = _map_hf_finish_reason_to_haystack(choice) if choice.finish_reason else None
         meta: dict[str, Any] = {
             "model": self._client.model,
-            "finish_reason": choice.finish_reason,
+            "finish_reason": mapped_finish_reason,
             "index": choice.index,
         }
 
@@ -629,9 +636,10 @@ class HuggingFaceAPIChatGenerator:
 
         tool_calls = _convert_hfapi_tool_calls(choice.message.tool_calls)
 
+        mapped_finish_reason = _map_hf_finish_reason_to_haystack(choice) if choice.finish_reason else None
         meta: dict[str, Any] = {
             "model": self._async_client.model,
-            "finish_reason": choice.finish_reason,
+            "finish_reason": mapped_finish_reason,
             "index": choice.index,
         }
 

releasenotes/notes/update-finish-reason-hf-api-chat-gen-c700042a079733e8.yaml

@@ -0,0 +1,18 @@
+---
+upgrade:
+  - |
+    The `finish_reason` field behavior in `HuggingFaceAPIChatGenerator` has been
+    updated. Previously, the new `finish_reason` mapping (introduced in Haystack 2.15.0 release) was only applied when streaming was enabled. When streaming was disabled,
+    the old `finish_reason` was still returned. This change ensures the updated
+    `finish_reason` values are consistently returned regardless of streaming mode.
+
+    **How to know if you're affected:**
+    If you rely on `finish_reason` in responses from `HuggingFaceAPIChatGenerator`
+    with streaming disabled, you may see different values after this upgrade.
+
+    **What to do:**
+    Review the updated mapping:
+      - `length` → `length`
+      - `eos_token` → `stop`
+      - `stop_sequence` → `stop`
+      - If tool calls are present → `tool_calls`

test/components/generators/chat/test_hugging_face_api.py

@@ -587,7 +587,7 @@ class TestHuggingFaceAPIChatGenerator:
         assert response["replies"][0].tool_calls[0].arguments == {"city": "Paris"}
         assert response["replies"][0].tool_calls[0].id == "0"
         assert response["replies"][0].meta == {
-            "finish_reason": "stop",
+            "finish_reason": "tool_calls",
             "index": 0,
             "model": "meta-llama/Llama-3.1-70B-Instruct",
             "usage": {"completion_tokens": 30, "prompt_tokens": 426},
@@ -1040,7 +1040,7 @@ class TestHuggingFaceAPIChatGenerator:
         assert response["replies"][0].tool_calls[0].arguments == {"city": "Paris"}
         assert response["replies"][0].tool_calls[0].id == "0"
         assert response["replies"][0].meta == {
-            "finish_reason": "stop",
+            "finish_reason": "tool_calls",
             "index": 0,
             "model": "meta-llama/Llama-3.1-70B-Instruct",
             "usage": {"completion_tokens": 30, "prompt_tokens": 426},