17731891188

Committed 15 Sep 2025 11:44AM UTC coverage: 92.047% (-0.01%) from 92.058%

Build # 17731891188

Build Type

push

github

Committed by

web-flow

Commit Message

feat: Add reasoning content to streaming chunk (#9777)

* Add reasoning content to streaming chunk

* Add reno

* Update print_streaming_chunk

Run Details

12974 of 14095 relevant lines covered (92.05%)

0.92 hits per line

Source File
Press 'n' to go to next uncovered line, 'b' for previous

87.04

haystack/components/generators/utils.py

# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
#
# SPDX-License-Identifier: Apache-2.0

import json

from haystack import logging
from haystack.dataclasses import ChatMessage, StreamingChunk, ToolCall

logger = logging.getLogger(__name__)


def print_streaming_chunk(chunk: StreamingChunk) -> None:
    """
    Callback function to handle and display streaming output chunks.

    This function processes a `StreamingChunk` object by:
    - Printing tool call metadata (if any), including function names and arguments, as they arrive.
    - Printing tool call results when available.
    - Printing the main content (e.g., text tokens) of the chunk as it is received.

    The function outputs data directly to stdout and flushes output buffers to ensure immediate display during
    streaming.

    :param chunk: A chunk of streaming data containing content and optional metadata, such as tool calls and
        tool results.
    """
    if chunk.start and chunk.index and chunk.index > 0:
        # If this is the start of a new content block but not the first content block, print two new lines
        print("\n\n", flush=True, end="")

    ## Tool Call streaming
    if chunk.tool_calls:
        # Typically, if there are multiple tool calls in the chunk this means that the tool calls are fully formed and
        # not just a delta.
        for tool_call in chunk.tool_calls:
            # If chunk.start is True indicates beginning of a tool call
            # Also presence of tool_call.tool_name indicates the start of a tool call too
            if chunk.start:
                # If there is more than one tool call in the chunk, we print two new lines to separate them
                # We know there is more than one tool call if the index of the tool call is greater than the index of
                # the chunk.
                if chunk.index and tool_call.index > chunk.index:
                    print("\n\n", flush=True, end="")

                print(f"[TOOL CALL]\nTool: {tool_call.tool_name} \nArguments: ", flush=True, end="")

            # print the tool arguments
            if tool_call.arguments:
                print(tool_call.arguments, flush=True, end="")

    ## Tool Call Result streaming
    # Print tool call results if available (from ToolInvoker)
    if chunk.tool_call_result:
        # Tool Call Result is fully formed so delta accumulation is not needed
        print(f"[TOOL RESULT]\n{chunk.tool_call_result.result}", flush=True, end="")

    ## Normal content streaming
    # Print the main content of the chunk (from ChatGenerator)
    if chunk.content:
        if chunk.start:
            print("[ASSISTANT]\n", flush=True, end="")
        print(chunk.content, flush=True, end="")

    ## Reasoning content streaming
    # Print the reasoning content of the chunk (from ChatGenerator)
    if chunk.reasoning:
        if chunk.start:
            print("[REASONING]\n", flush=True, end="")
        print(chunk.reasoning.reasoning_text, flush=True, end="")

    # End of LLM assistant message so we add two new lines
    # This ensures spacing between multiple LLM messages (e.g. Agent) or multiple Tool Call Results
    if chunk.finish_reason is not None:
        print("\n\n", flush=True, end="")


def _convert_streaming_chunks_to_chat_message(chunks: list[StreamingChunk]) -> ChatMessage:
    """
    Connects the streaming chunks into a single ChatMessage.

    :param chunks: The list of all `StreamingChunk` objects.

    :returns: The ChatMessage.
    """
    text = "".join([chunk.content for chunk in chunks])
    tool_calls = []

    # Process tool calls if present in any chunk
    tool_call_data: dict[int, dict[str, str]] = {}  # Track tool calls by index
    for chunk in chunks:
        if chunk.tool_calls:
            for tool_call in chunk.tool_calls:
                # We use the index of the tool_call to track the tool call across chunks since the ID is not always
                # provided
                if tool_call.index not in tool_call_data:
                    tool_call_data[tool_call.index] = {"id": "", "name": "", "arguments": ""}

                # Save the ID if present
                if tool_call.id is not None:
                    tool_call_data[tool_call.index]["id"] = tool_call.id

                if tool_call.tool_name is not None:
                    tool_call_data[tool_call.index]["name"] += tool_call.tool_name
                if tool_call.arguments is not None:
                    tool_call_data[tool_call.index]["arguments"] += tool_call.arguments

    # Convert accumulated tool call data into ToolCall objects
    sorted_keys = sorted(tool_call_data.keys())
    for key in sorted_keys:
        tool_call_dict = tool_call_data[key]
        try:
            arguments = json.loads(tool_call_dict.get("arguments", "{}")) if tool_call_dict.get("arguments") else {}
            tool_calls.append(ToolCall(id=tool_call_dict["id"], tool_name=tool_call_dict["name"], arguments=arguments))
        except json.JSONDecodeError:
            logger.warning(
                "The LLM provider returned a malformed JSON string for tool call arguments. This tool call "
                "will be skipped. To always generate a valid JSON, set `tools_strict` to `True`. "
                "Tool call ID: {_id}, Tool name: {_name}, Arguments: {_arguments}",
                _id=tool_call_dict["id"],
                _name=tool_call_dict["name"],
                _arguments=tool_call_dict["arguments"],
            )

    # finish_reason can appear in different places so we look for the last one
    finish_reasons = [chunk.finish_reason for chunk in chunks if chunk.finish_reason]
    finish_reason = finish_reasons[-1] if finish_reasons else None

    meta = {
        "model": chunks[-1].meta.get("model"),
        "index": 0,
        "finish_reason": finish_reason,
        "completion_start_time": chunks[0].meta.get("received_at"),  # first chunk received
        "usage": chunks[-1].meta.get("usage"),  # last chunk has the final usage data if available
    }

    return ChatMessage.from_assistant(text=text or None, tool_calls=tool_calls, meta=meta)

1	# SPDX-FileCopyrightText: 2022-present deepset GmbH <info@deepset.ai>
2	#
3	# SPDX-License-Identifier: Apache-2.0
4
5	import json	1✔
6
7	from haystack import logging	1✔
8	from haystack.dataclasses import ChatMessage, StreamingChunk, ToolCall	1✔
9
10	logger = logging.getLogger(__name__)	1✔
11
12
13	def print_streaming_chunk(chunk: StreamingChunk) -> None:	1✔
14	"""
15	Callback function to handle and display streaming output chunks.
16
17	This function processes a `StreamingChunk` object by:
18	- Printing tool call metadata (if any), including function names and arguments, as they arrive.
19	- Printing tool call results when available.
20	- Printing the main content (e.g., text tokens) of the chunk as it is received.
21
22	The function outputs data directly to stdout and flushes output buffers to ensure immediate display during
23	streaming.
24
25	:param chunk: A chunk of streaming data containing content and optional metadata, such as tool calls and
26	tool results.
27	"""
28	if chunk.start and chunk.index and chunk.index > 0:	1✔
29	# If this is the start of a new content block but not the first content block, print two new lines
30	print("\n\n", flush=True, end="")	×
31
32	## Tool Call streaming
33	if chunk.tool_calls:	1✔
34	# Typically, if there are multiple tool calls in the chunk this means that the tool calls are fully formed and
35	# not just a delta.
36	for tool_call in chunk.tool_calls:	1✔
37	# If chunk.start is True indicates beginning of a tool call
38	# Also presence of tool_call.tool_name indicates the start of a tool call too
39	if chunk.start:	1✔
40	# If there is more than one tool call in the chunk, we print two new lines to separate them
41	# We know there is more than one tool call if the index of the tool call is greater than the index of
42	# the chunk.
43	if chunk.index and tool_call.index > chunk.index:	1✔
44	print("\n\n", flush=True, end="")	×
45
46	print(f"[TOOL CALL]\nTool: {tool_call.tool_name} \nArguments: ", flush=True, end="")	1✔
47
48	# print the tool arguments
49	if tool_call.arguments:	1✔
50	print(tool_call.arguments, flush=True, end="")	1✔
51
52	## Tool Call Result streaming
53	# Print tool call results if available (from ToolInvoker)
54	if chunk.tool_call_result:	1✔
55	# Tool Call Result is fully formed so delta accumulation is not needed
56	print(f"[TOOL RESULT]\n{chunk.tool_call_result.result}", flush=True, end="")	1✔
57
58	## Normal content streaming
59	# Print the main content of the chunk (from ChatGenerator)
60	if chunk.content:	1✔
61	if chunk.start:	1✔
62	print("[ASSISTANT]\n", flush=True, end="")	1✔
63	print(chunk.content, flush=True, end="")	1✔
64
65	## Reasoning content streaming
66	# Print the reasoning content of the chunk (from ChatGenerator)
67	if chunk.reasoning:	1✔
68	if chunk.start:	×
69	print("[REASONING]\n", flush=True, end="")	×
70	print(chunk.reasoning.reasoning_text, flush=True, end="")	×
71
72	# End of LLM assistant message so we add two new lines
73	# This ensures spacing between multiple LLM messages (e.g. Agent) or multiple Tool Call Results
74	if chunk.finish_reason is not None:	1✔
75	print("\n\n", flush=True, end="")	1✔
76
77
78	def _convert_streaming_chunks_to_chat_message(chunks: list[StreamingChunk]) -> ChatMessage:	1✔
79	"""
80	Connects the streaming chunks into a single ChatMessage.
81
82	:param chunks: The list of all `StreamingChunk` objects.
83
84	:returns: The ChatMessage.
85	"""
86	text = "".join([chunk.content for chunk in chunks])	1✔
87	tool_calls = []	1✔
88
89	# Process tool calls if present in any chunk
90	tool_call_data: dict[int, dict[str, str]] = {} # Track tool calls by index	1✔
91	for chunk in chunks:	1✔
92	if chunk.tool_calls:	1✔
93	for tool_call in chunk.tool_calls:	1✔
94	# We use the index of the tool_call to track the tool call across chunks since the ID is not always
95	# provided
96	if tool_call.index not in tool_call_data:	1✔
97	tool_call_data[tool_call.index] = {"id": "", "name": "", "arguments": ""}	1✔
98
99	# Save the ID if present
100	if tool_call.id is not None:	1✔
101	tool_call_data[tool_call.index]["id"] = tool_call.id	1✔
102
103	if tool_call.tool_name is not None:	1✔
104	tool_call_data[tool_call.index]["name"] += tool_call.tool_name	1✔
105	if tool_call.arguments is not None:	1✔
106	tool_call_data[tool_call.index]["arguments"] += tool_call.arguments	1✔
107
108	# Convert accumulated tool call data into ToolCall objects
109	sorted_keys = sorted(tool_call_data.keys())	1✔
110	for key in sorted_keys:	1✔
111	tool_call_dict = tool_call_data[key]	1✔
112	try:	1✔
113	arguments = json.loads(tool_call_dict.get("arguments", "{}")) if tool_call_dict.get("arguments") else {}	1✔
114	tool_calls.append(ToolCall(id=tool_call_dict["id"], tool_name=tool_call_dict["name"], arguments=arguments))	1✔
115	except json.JSONDecodeError:	×
116	logger.warning(	×
117	"The LLM provider returned a malformed JSON string for tool call arguments. This tool call "
118	"will be skipped. To always generate a valid JSON, set `tools_strict` to `True`. "
119	"Tool call ID: {_id}, Tool name: {_name}, Arguments: {_arguments}",
120	_id=tool_call_dict["id"],
121	_name=tool_call_dict["name"],
122	_arguments=tool_call_dict["arguments"],
123	)
124
125	# finish_reason can appear in different places so we look for the last one
126	finish_reasons = [chunk.finish_reason for chunk in chunks if chunk.finish_reason]	1✔
127	finish_reason = finish_reasons[-1] if finish_reasons else None	1✔
128
129	meta = {	1✔
130	"model": chunks[-1].meta.get("model"),
131	"index": 0,
132	"finish_reason": finish_reason,
133	"completion_start_time": chunks[0].meta.get("received_at"), # first chunk received
134	"usage": chunks[-1].meta.get("usage"), # last chunk has the final usage data if available
135	}
136
137	return ChatMessage.from_assistant(text=text or None, tool_calls=tool_calls, meta=meta)	1✔

deepset-ai / haystack / 17731891188

Source File Press 'n' to go to next uncovered line, 'b' for previous

Source File
Press 'n' to go to next uncovered line, 'b' for previous