reasoning_content -> reasoning (#27752)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
@@ -80,7 +80,7 @@ FUNC_ARGS = """{"city": "Dallas", "state": "TX", "unit": "fahrenheit"}"""
|
||||
|
||||
|
||||
def extract_reasoning_and_calls(chunks: list):
|
||||
reasoning_content = ""
|
||||
reasoning = ""
|
||||
tool_call_idx = -1
|
||||
arguments = []
|
||||
function_names = []
|
||||
@@ -99,9 +99,9 @@ def extract_reasoning_and_calls(chunks: list):
|
||||
if tool_call.function.arguments:
|
||||
arguments[tool_call_idx] += tool_call.function.arguments
|
||||
else:
|
||||
if hasattr(chunk.choices[0].delta, "reasoning_content"):
|
||||
reasoning_content += chunk.choices[0].delta.reasoning_content
|
||||
return reasoning_content, arguments, function_names
|
||||
if hasattr(chunk.choices[0].delta, "reasoning"):
|
||||
reasoning += chunk.choices[0].delta.reasoning
|
||||
return reasoning, arguments, function_names
|
||||
|
||||
|
||||
# test streaming
|
||||
@@ -119,8 +119,8 @@ async def test_chat_streaming_of_tool_and_reasoning(client: openai.AsyncOpenAI):
|
||||
async for chunk in stream:
|
||||
chunks.append(chunk)
|
||||
|
||||
reasoning_content, arguments, function_names = extract_reasoning_and_calls(chunks)
|
||||
assert len(reasoning_content) > 0
|
||||
reasoning, arguments, function_names = extract_reasoning_and_calls(chunks)
|
||||
assert len(reasoning) > 0
|
||||
assert len(function_names) > 0 and function_names[0] == FUNC_NAME
|
||||
assert len(arguments) > 0 and arguments[0] == FUNC_ARGS
|
||||
|
||||
@@ -136,6 +136,6 @@ async def test_chat_full_of_tool_and_reasoning(client: openai.AsyncOpenAI):
|
||||
stream=False,
|
||||
)
|
||||
|
||||
assert len(tool_calls.choices[0].message.reasoning_content) > 0
|
||||
assert len(tool_calls.choices[0].message.reasoning) > 0
|
||||
assert tool_calls.choices[0].message.tool_calls[0].function.name == FUNC_NAME
|
||||
assert tool_calls.choices[0].message.tool_calls[0].function.arguments == FUNC_ARGS
|
||||
|
||||
@@ -180,8 +180,8 @@ async def test_function_tool_use(
|
||||
extra_body={"chat_template_kwargs": {"enable_thinking": enable_thinking}},
|
||||
)
|
||||
if enable_thinking:
|
||||
assert chat_completion.choices[0].message.reasoning_content is not None
|
||||
assert chat_completion.choices[0].message.reasoning_content != ""
|
||||
assert chat_completion.choices[0].message.reasoning is not None
|
||||
assert chat_completion.choices[0].message.reasoning != ""
|
||||
assert chat_completion.choices[0].message.tool_calls is not None
|
||||
assert len(chat_completion.choices[0].message.tool_calls) > 0
|
||||
else:
|
||||
@@ -200,9 +200,9 @@ async def test_function_tool_use(
|
||||
async for chunk in output_stream:
|
||||
if chunk.choices:
|
||||
if enable_thinking and getattr(
|
||||
chunk.choices[0].delta, "reasoning_content", None
|
||||
chunk.choices[0].delta, "reasoning", None
|
||||
):
|
||||
reasoning.append(chunk.choices[0].delta.reasoning_content)
|
||||
reasoning.append(chunk.choices[0].delta.reasoning)
|
||||
if chunk.choices[0].delta.tool_calls:
|
||||
output.extend(chunk.choices[0].delta.tool_calls)
|
||||
|
||||
|
||||
@@ -232,9 +232,9 @@ def test_reasoning_parser():
|
||||
assert isinstance(line_dict, dict)
|
||||
assert line_dict["error"] is None
|
||||
|
||||
# Check that reasoning_content is present and not empty
|
||||
reasoning_content = line_dict["response"]["body"]["choices"][0]["message"][
|
||||
"reasoning_content"
|
||||
# Check that reasoning is present and not empty
|
||||
reasoning = line_dict["response"]["body"]["choices"][0]["message"][
|
||||
"reasoning"
|
||||
]
|
||||
assert reasoning_content is not None
|
||||
assert len(reasoning_content) > 0
|
||||
assert reasoning is not None
|
||||
assert len(reasoning) > 0
|
||||
|
||||
@@ -151,57 +151,57 @@ class TestBaseThinkingReasoningParserMethods:
|
||||
class TestBaseThinkingReasoningParserExtraction:
|
||||
"""Test reasoning content extraction methods."""
|
||||
|
||||
def test_extract_reasoning_content_with_both_tokens(self, test_tokenizer):
|
||||
def test_extract_reasoning_with_both_tokens(self, test_tokenizer):
|
||||
"""Test extraction when both start and end tokens are present."""
|
||||
parser = TestThinkingReasoningParser(test_tokenizer)
|
||||
request = ChatCompletionRequest(messages=[], model="test-model")
|
||||
|
||||
model_output = "<test:think>This is reasoning</test:think>This is content"
|
||||
reasoning, content = parser.extract_reasoning_content(model_output, request)
|
||||
reasoning, content = parser.extract_reasoning(model_output, request)
|
||||
|
||||
assert reasoning == "This is reasoning"
|
||||
assert content == "This is content"
|
||||
|
||||
def test_extract_reasoning_content_only_end_token(self, test_tokenizer):
|
||||
def test_extract_reasoning_only_end_token(self, test_tokenizer):
|
||||
"""Test extraction when only end token is present."""
|
||||
parser = TestThinkingReasoningParser(test_tokenizer)
|
||||
request = ChatCompletionRequest(messages=[], model="test-model")
|
||||
|
||||
model_output = "This is reasoning</test:think>This is content"
|
||||
reasoning, content = parser.extract_reasoning_content(model_output, request)
|
||||
reasoning, content = parser.extract_reasoning(model_output, request)
|
||||
|
||||
assert reasoning == "This is reasoning"
|
||||
assert content == "This is content"
|
||||
|
||||
def test_extract_reasoning_content_no_end_token(self, test_tokenizer):
|
||||
def test_extract_reasoning_no_end_token(self, test_tokenizer):
|
||||
"""Test extraction when no end token is present."""
|
||||
parser = TestThinkingReasoningParser(test_tokenizer)
|
||||
request = ChatCompletionRequest(messages=[], model="test-model")
|
||||
|
||||
model_output = "This is just content"
|
||||
reasoning, content = parser.extract_reasoning_content(model_output, request)
|
||||
reasoning, content = parser.extract_reasoning(model_output, request)
|
||||
|
||||
assert reasoning == "This is just content"
|
||||
assert content is None
|
||||
|
||||
def test_extract_reasoning_content_empty_output(self, test_tokenizer):
|
||||
def test_extract_reasoning_empty_output(self, test_tokenizer):
|
||||
"""Test extraction with empty output."""
|
||||
parser = TestThinkingReasoningParser(test_tokenizer)
|
||||
request = ChatCompletionRequest(messages=[], model="test-model")
|
||||
|
||||
model_output = ""
|
||||
reasoning, content = parser.extract_reasoning_content(model_output, request)
|
||||
reasoning, content = parser.extract_reasoning(model_output, request)
|
||||
|
||||
assert reasoning == ""
|
||||
assert content is None
|
||||
|
||||
def test_extract_reasoning_content_only_tokens(self, test_tokenizer):
|
||||
def test_extract_reasoning_only_tokens(self, test_tokenizer):
|
||||
"""Test extraction with only tokens and no content."""
|
||||
parser = TestThinkingReasoningParser(test_tokenizer)
|
||||
request = ChatCompletionRequest(messages=[], model="test-model")
|
||||
|
||||
model_output = "<test:think></test:think>"
|
||||
reasoning, content = parser.extract_reasoning_content(model_output, request)
|
||||
reasoning, content = parser.extract_reasoning(model_output, request)
|
||||
|
||||
assert reasoning == ""
|
||||
assert content is None
|
||||
|
||||
@@ -21,97 +21,97 @@ def deepseek_r1_qwen_tokenizer():
|
||||
|
||||
SIMPLE_REASONING = {
|
||||
"output": "This is a reasoning section</think>This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
COMPLETE_REASONING = {
|
||||
"output": "This is a reasoning section</think>",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
NO_CONTENT = {
|
||||
"output": "This is content",
|
||||
"reasoning_content": "This is content",
|
||||
"reasoning": "This is content",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
NO_REASONING_STREAMING = {
|
||||
"output": "This is a reasoning section",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
MULTIPLE_LINES = {
|
||||
"output": "This\nThat</think>This is the rest\nThat",
|
||||
"reasoning_content": "This\nThat",
|
||||
"reasoning": "This\nThat",
|
||||
"content": "This is the rest\nThat",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
SHORTEST_REASONING_NO_STREAMING = {
|
||||
"output": "</think>This is the rest",
|
||||
"reasoning_content": "",
|
||||
"reasoning": "",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
SHORTEST_REASONING = {
|
||||
"output": "</think>This is the rest",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
REASONING_WITH_THINK = {
|
||||
"output": "<think>This is a reasoning section</think>This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
COMPLETE_REASONING_WITH_THINK = {
|
||||
"output": "<think>This is a reasoning section</think>",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
MULTIPLE_LINES_WITH_THINK = {
|
||||
"output": "<think>This\nThat</think>This is the rest\nThat",
|
||||
"reasoning_content": "This\nThat",
|
||||
"reasoning": "This\nThat",
|
||||
"content": "This is the rest\nThat",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
SHORTEST_REASONING_NO_STREAMING_WITH_THINK = {
|
||||
"output": "</think>This is the rest",
|
||||
"reasoning_content": "",
|
||||
"reasoning": "",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
SHORTEST_REASONING_WITH_THINK = {
|
||||
"output": "</think>This is the rest",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
THINK_NO_END = {
|
||||
"output": "<think>This is a reasoning section",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
EMPTY = {
|
||||
"output": "",
|
||||
"reasoning_content": "",
|
||||
"reasoning": "",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
EMPTY_STREAMING = {
|
||||
"output": "",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
NEW_LINE = {
|
||||
"output": "\n<think>This is a reasoning section</think>\nThis is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "\nThis is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
@@ -121,7 +121,7 @@ NEW_LINE = {
|
||||
# or not.
|
||||
NEW_LINE_STREAMING = {
|
||||
"output": "\n<think>This is a reasoning section</think>\nThis is the rest",
|
||||
"reasoning_content": "\nThis is a reasoning section",
|
||||
"reasoning": "\nThis is a reasoning section",
|
||||
"content": "\nThis is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
@@ -269,7 +269,7 @@ def test_reasoning(
|
||||
parser, output_tokens, streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == param_dict["reasoning_content"]
|
||||
assert reasoning == param_dict["reasoning"]
|
||||
assert content == param_dict["content"]
|
||||
|
||||
# Test is_reasoning_end
|
||||
|
||||
@@ -44,14 +44,14 @@ def test_identity_reasoning_parser_basic(tokenizer):
|
||||
# Test extract_content_ids returns all input_ids
|
||||
assert parser.extract_content_ids(input_ids) == input_ids
|
||||
|
||||
# Test extract_reasoning_content returns (None, model_output)
|
||||
# Test extract_reasoning returns (None, model_output)
|
||||
request = ChatCompletionRequest(model="test-model", messages=[], temperature=1.0)
|
||||
reasoning, content = parser.extract_reasoning_content(input_text, request)
|
||||
reasoning, content = parser.extract_reasoning(input_text, request)
|
||||
assert reasoning is None
|
||||
assert content == input_text
|
||||
|
||||
# Test extract_reasoning_content_streaming returns DeltaMessage or None
|
||||
result = parser.extract_reasoning_content_streaming(
|
||||
# Test extract_reasoning_streaming returns DeltaMessage or None
|
||||
result = parser.extract_reasoning_streaming(
|
||||
previous_text="",
|
||||
current_text="Hello world",
|
||||
delta_text="Hello world",
|
||||
@@ -63,7 +63,7 @@ def test_identity_reasoning_parser_basic(tokenizer):
|
||||
assert result.content == "Hello world"
|
||||
|
||||
# If delta_text is empty, should return None
|
||||
result_none = parser.extract_reasoning_content_streaming(
|
||||
result_none = parser.extract_reasoning_streaming(
|
||||
previous_text="Hello world",
|
||||
current_text="Hello world",
|
||||
delta_text="",
|
||||
|
||||
@@ -20,36 +20,36 @@ def ernie45_tokenizer():
|
||||
# 带 </think>,非stream
|
||||
WITH_THINK = {
|
||||
"output": "abc</think>def",
|
||||
"reasoning_content": "abc",
|
||||
"reasoning": "abc",
|
||||
"content": "def",
|
||||
}
|
||||
# 带 </think>,stream
|
||||
WITH_THINK_STREAM = {
|
||||
"output": "abc</think>def",
|
||||
"reasoning_content": "abc",
|
||||
"reasoning": "abc",
|
||||
"content": "def",
|
||||
}
|
||||
# without </think>, all is reasoning_content
|
||||
# without </think>, all is reasoning
|
||||
WITHOUT_THINK = {
|
||||
"output": "abc",
|
||||
"reasoning_content": "abc",
|
||||
"reasoning": "abc",
|
||||
"content": None,
|
||||
}
|
||||
# without </think>, all is reasoning_content
|
||||
# without </think>, all is reasoning
|
||||
WITHOUT_THINK_STREAM = {
|
||||
"output": "abc",
|
||||
"reasoning_content": "abc",
|
||||
"reasoning": "abc",
|
||||
"content": None,
|
||||
}
|
||||
|
||||
COMPLETE_REASONING = {
|
||||
"output": "abc</think>",
|
||||
"reasoning_content": "abc",
|
||||
"reasoning": "abc",
|
||||
"content": None,
|
||||
}
|
||||
MULTILINE_REASONING = {
|
||||
"output": "abc\nABC</think>def\nDEF",
|
||||
"reasoning_content": "abc\nABC",
|
||||
"reasoning": "abc\nABC",
|
||||
"content": "def\nDEF",
|
||||
}
|
||||
|
||||
@@ -120,5 +120,5 @@ def test_reasoning(
|
||||
|
||||
print()
|
||||
|
||||
assert reasoning == param_dict["reasoning_content"]
|
||||
assert reasoning == param_dict["reasoning"]
|
||||
assert content == param_dict["content"]
|
||||
|
||||
@@ -21,54 +21,54 @@ def glm45_tokenizer():
|
||||
|
||||
WITH_THINK = {
|
||||
"output": "<think>This is a reasoning section</think>This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
|
||||
WITH_THINK_STREAM = {
|
||||
"output": "<think>This is a reasoning section</think>This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
|
||||
WITHOUT_THINK = {
|
||||
"output": "This is the rest",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
|
||||
WITHOUT_THINK_STREAM = {
|
||||
"output": "This is the rest",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
|
||||
COMPLETE_REASONING = {
|
||||
"output": "<think>This is a reasoning section</think>",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
MULTILINE_REASONING = {
|
||||
"output": "<think>This is a reasoning\nsection</think>This is the rest\nThat",
|
||||
"reasoning_content": "This is a reasoning\nsection",
|
||||
"reasoning": "This is a reasoning\nsection",
|
||||
"content": "This is the rest\nThat",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
ONLY_OPEN_TAG = {
|
||||
"output": "<think>This is a reasoning section",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "<think>This is a reasoning section",
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
|
||||
ONLY_OPEN_TAG_STREAM = {
|
||||
"output": "<think>This is a reasoning section",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
@@ -184,7 +184,7 @@ def test_reasoning(
|
||||
parser, output_tokens, streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == param_dict["reasoning_content"]
|
||||
assert reasoning == param_dict["reasoning"]
|
||||
assert content == param_dict["content"]
|
||||
|
||||
output_ids = glm45_tokenizer.convert_tokens_to_ids(output)
|
||||
|
||||
@@ -12,37 +12,37 @@ START_RESPONSE = "Here is my response:"
|
||||
|
||||
SIMPLE_REASONING = {
|
||||
"output": f"{START_REASONING}This is a reasoning section{START_RESPONSE}This is the rest", # noqa: E501
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
}
|
||||
COMPLETE_REASONING = {
|
||||
"output": f"{START_REASONING}This is a reasoning section{START_RESPONSE}",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
}
|
||||
NO_REASONING = {
|
||||
"output": "This is content",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is content",
|
||||
}
|
||||
MULTIPLE_LINES = {
|
||||
"output": f"{START_REASONING}This\nThat{START_RESPONSE}This is the rest\nThat",
|
||||
"reasoning_content": "This\nThat",
|
||||
"reasoning": "This\nThat",
|
||||
"content": "This is the rest\nThat",
|
||||
}
|
||||
REASONING_WITH_THINK = {
|
||||
"output": f"{START_REASONING}This is a reasoning section{START_RESPONSE}This is the rest", # noqa: E501
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
}
|
||||
COMPLETE_REASONING_WITH_THINK = {
|
||||
"output": f"{START_REASONING}This is a reasoning section{START_RESPONSE}",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
}
|
||||
MULTIPLE_LINES_WITH_THINK = {
|
||||
"output": f"{START_REASONING}This\nThat{START_RESPONSE}This is the rest\nThat",
|
||||
"reasoning_content": "This\nThat",
|
||||
"reasoning": "This\nThat",
|
||||
"content": "This is the rest\nThat",
|
||||
}
|
||||
|
||||
@@ -141,7 +141,7 @@ def test_reasoning(
|
||||
parser, output_tokens, streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == param_dict["reasoning_content"]
|
||||
assert reasoning == param_dict["reasoning"]
|
||||
assert content == param_dict["content"]
|
||||
|
||||
|
||||
@@ -155,7 +155,7 @@ STREAMING_1 = {
|
||||
"previous_text": None,
|
||||
"current_text": "Here",
|
||||
"delta_text": "Here",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": None,
|
||||
}
|
||||
# When we fail, we should give what was previously being silenced first
|
||||
@@ -163,7 +163,7 @@ STREAMING_2 = {
|
||||
"previous_text": "Here is my thought",
|
||||
"current_text": "Here is my thought failure",
|
||||
"delta_text": " failure",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "Here is my thought failure",
|
||||
}
|
||||
# But then after the first one, we should only add the delta text to content
|
||||
@@ -171,7 +171,7 @@ STREAMING_3 = {
|
||||
"previous_text": "Here wrong",
|
||||
"current_text": " words",
|
||||
"delta_text": " Here wrong words",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": " words",
|
||||
}
|
||||
# But then after the first one, we should only add the delta text to content
|
||||
@@ -179,7 +179,7 @@ STREAMING_4 = {
|
||||
"previous_text": "Here is my thought",
|
||||
"current_text": "Here is my thought process:",
|
||||
"delta_text": " process:",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": None,
|
||||
}
|
||||
# Reasoning started successfully; parse reasoning content
|
||||
@@ -187,7 +187,7 @@ STREAMING_5 = {
|
||||
"previous_text": "Here is my thought process:",
|
||||
"current_text": "Here is my thought process: foo",
|
||||
"delta_text": " foo",
|
||||
"reasoning_content": " foo",
|
||||
"reasoning": " foo",
|
||||
"content": None,
|
||||
}
|
||||
# Response special sequence has started, but not finished.
|
||||
@@ -195,7 +195,7 @@ STREAMING_6 = {
|
||||
"previous_text": "Here is my thought process: foo",
|
||||
"current_text": "Here is my thought process: foo Here is",
|
||||
"delta_text": " Here is",
|
||||
"reasoning_content": " ",
|
||||
"reasoning": " ",
|
||||
"content": None,
|
||||
}
|
||||
# Response special sequence started, but was broken; the reasoning
|
||||
@@ -204,7 +204,7 @@ STREAMING_7 = {
|
||||
"previous_text": "Here is my thought process: foo Here is",
|
||||
"current_text": "Here is my thought process: foo Here is Here",
|
||||
"delta_text": " Here",
|
||||
"reasoning_content": "Here is ",
|
||||
"reasoning": "Here is ",
|
||||
"content": None,
|
||||
}
|
||||
# Response special sequence is ongoing
|
||||
@@ -212,7 +212,7 @@ STREAMING_8 = {
|
||||
"previous_text": "Here is my thought process: foo Here is my response:",
|
||||
"current_text": "Here is my thought process: foo Here is my response: bar",
|
||||
"delta_text": " bar",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": " bar",
|
||||
}
|
||||
# The delta text has everything; we should be able to correctly parse both
|
||||
@@ -220,7 +220,7 @@ STREAMING_9 = {
|
||||
"previous_text": None,
|
||||
"current_text": "Here is my thought process: foo Here is my response: bar",
|
||||
"delta_text": "Here is my thought process: foo Here is my response: bar",
|
||||
"reasoning_content": " foo ",
|
||||
"reasoning": " foo ",
|
||||
"content": " bar",
|
||||
}
|
||||
## The Response is ongoing, and the delta mixes reasoning content / content
|
||||
@@ -228,7 +228,7 @@ STREAMING_10 = {
|
||||
"previous_text": "Here is my thought process: foo",
|
||||
"current_text": "Here is my thought process: foo bar Here is my response: baz",
|
||||
"delta_text": " bar Here is my response: baz",
|
||||
"reasoning_content": " bar ",
|
||||
"reasoning": " bar ",
|
||||
"content": " baz",
|
||||
}
|
||||
# The delta text starts a new substring that might be a response special seq
|
||||
@@ -236,7 +236,7 @@ STREAMING_11 = {
|
||||
"previous_text": "Here is my thought process: This is a reasoning section ",
|
||||
"current_text": "Here is my thought process: This is a reasoning section Here",
|
||||
"delta_text": "Here",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": None,
|
||||
}
|
||||
# The delta text is finishing the response special seq
|
||||
@@ -244,14 +244,14 @@ STREAMING_12 = {
|
||||
"previous_text": "Here is my thought process: foo Here is my response",
|
||||
"current_text": "Here is my thought process: foo Here is my response:",
|
||||
"delta_text": ":",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": None,
|
||||
}
|
||||
STREAMING_13 = {
|
||||
"previous_text": "Here is my thought process: foo Here",
|
||||
"current_text": "Here is my thought process: foo Here was",
|
||||
"delta_text": " was",
|
||||
"reasoning_content": "Here was",
|
||||
"reasoning": "Here was",
|
||||
"content": None,
|
||||
}
|
||||
|
||||
@@ -326,7 +326,7 @@ def test_streaming_subcases(param_dict):
|
||||
tokenizer
|
||||
)
|
||||
|
||||
response = parser.extract_reasoning_content_streaming(
|
||||
response = parser.extract_reasoning_streaming(
|
||||
previous_text=param_dict["previous_text"],
|
||||
current_text=param_dict["current_text"],
|
||||
delta_text=param_dict["delta_text"],
|
||||
@@ -336,9 +336,9 @@ def test_streaming_subcases(param_dict):
|
||||
)
|
||||
# Streaming currently expects at least one of reasoning content / content,
|
||||
# so the response should return None in that case.
|
||||
if param_dict["reasoning_content"] is None and param_dict["content"] is None:
|
||||
if param_dict["reasoning"] is None and param_dict["content"] is None:
|
||||
assert response is None
|
||||
else:
|
||||
assert isinstance(response, DeltaMessage)
|
||||
assert param_dict["reasoning_content"] == response.reasoning_content
|
||||
assert param_dict["reasoning"] == response.reasoning
|
||||
assert param_dict["content"] == response.content
|
||||
|
||||
@@ -14,49 +14,49 @@ END_RESPONSE = "\n</answer>"
|
||||
|
||||
NO_REASONING_QUICK_THROUGHT = {
|
||||
"output": f"{START_REASONING}{START_RESPONSE}This is the rest{END_RESPONSE}", # noqa: E501
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is the rest",
|
||||
}
|
||||
|
||||
SIMPLE_REASONING = {
|
||||
"output": f"{START_REASONING}This is a reasoning section{START_RESPONSE}This is the rest{END_RESPONSE}", # noqa: E501
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
}
|
||||
COMPLETE_REASONING = {
|
||||
"output": f"{START_REASONING}This is a reasoning section{START_RESPONSE}",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
}
|
||||
|
||||
COMPLETE_REASONING_WITH_SYMBOL = {
|
||||
"output": f"{START_REASONING}This is a reasoning section!{START_RESPONSE}",
|
||||
"reasoning_content": "This is a reasoning section!",
|
||||
"reasoning": "This is a reasoning section!",
|
||||
"content": None,
|
||||
}
|
||||
NO_REASONING = {
|
||||
"output": "This is content",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is content",
|
||||
}
|
||||
MULTIPLE_LINES = {
|
||||
"output": f"{START_REASONING}This\nThat{START_RESPONSE}This is the rest\nThat",
|
||||
"reasoning_content": "This\nThat",
|
||||
"reasoning": "This\nThat",
|
||||
"content": "This is the rest\nThat",
|
||||
}
|
||||
REASONING_WITH_THINK = {
|
||||
"output": f"{START_REASONING}This is a reasoning section{START_RESPONSE}This is the rest", # noqa: E501
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
}
|
||||
COMPLETE_REASONING_WITH_THINK = {
|
||||
"output": f"{START_REASONING}This is a reasoning section{START_RESPONSE}",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
}
|
||||
MULTIPLE_LINES_WITH_THINK = {
|
||||
"output": f"{START_REASONING}This\nThat{START_RESPONSE}This is the rest\nThat",
|
||||
"reasoning_content": "This\nThat",
|
||||
"reasoning": "This\nThat",
|
||||
"content": "This is the rest\nThat",
|
||||
}
|
||||
|
||||
@@ -164,5 +164,5 @@ def test_reasoning(
|
||||
parser, output_tokens, streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == param_dict["reasoning_content"]
|
||||
assert reasoning == param_dict["reasoning"]
|
||||
assert content == param_dict["content"]
|
||||
|
||||
@@ -20,97 +20,97 @@ def mistral_tokenizer():
|
||||
|
||||
SIMPLE_REASONING = {
|
||||
"output": "This is a reasoning section[/THINK]This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
COMPLETE_REASONING = {
|
||||
"output": "This is a reasoning section[/THINK]",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
NO_CONTENT = {
|
||||
"output": "This is content",
|
||||
"reasoning_content": "This is content",
|
||||
"reasoning": "This is content",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
NO_REASONING_STREAMING = {
|
||||
"output": "This is a reasoning section",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
MULTIPLE_LINES = {
|
||||
"output": "This\nThat[/THINK]This is the rest\nThat",
|
||||
"reasoning_content": "This\nThat",
|
||||
"reasoning": "This\nThat",
|
||||
"content": "This is the rest\nThat",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
SHORTEST_REASONING_NO_STREAMING = {
|
||||
"output": "[/THINK]This is the rest",
|
||||
"reasoning_content": "",
|
||||
"reasoning": "",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
SHORTEST_REASONING = {
|
||||
"output": "[/THINK]This is the rest",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
REASONING_WITH_THINK = {
|
||||
"output": "[THINK]This is a reasoning section[/THINK]This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
COMPLETE_REASONING_WITH_THINK = {
|
||||
"output": "[THINK]This is a reasoning section[/THINK]",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
MULTIPLE_LINES_WITH_THINK = {
|
||||
"output": "[THINK]This\nThat[/THINK]This is the rest\nThat",
|
||||
"reasoning_content": "This\nThat",
|
||||
"reasoning": "This\nThat",
|
||||
"content": "This is the rest\nThat",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
SHORTEST_REASONING_NO_STREAMING_WITH_THINK = {
|
||||
"output": "[/THINK]This is the rest",
|
||||
"reasoning_content": "",
|
||||
"reasoning": "",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
SHORTEST_REASONING_WITH_THINK = {
|
||||
"output": "[/THINK]This is the rest",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
THINK_NO_END = {
|
||||
"output": "[THINK]This is a reasoning section",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
EMPTY = {
|
||||
"output": "",
|
||||
"reasoning_content": "",
|
||||
"reasoning": "",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
EMPTY_STREAMING = {
|
||||
"output": "",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
NEW_LINE = {
|
||||
"output": "\n[THINK]This is a reasoning section[/THINK]\nThis is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "\nThis is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
@@ -120,7 +120,7 @@ NEW_LINE = {
|
||||
# or not.
|
||||
NEW_LINE_STREAMING = {
|
||||
"output": "\n[THINK]This is a reasoning section[/THINK]\nThis is the rest",
|
||||
"reasoning_content": "\nThis is a reasoning section",
|
||||
"reasoning": "\nThis is a reasoning section",
|
||||
"content": "\nThis is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
@@ -307,7 +307,7 @@ def test_mistral_reasoning(
|
||||
parser, output_tokens, streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == param_dict["reasoning_content"]
|
||||
assert reasoning == param_dict["reasoning"]
|
||||
assert content == param_dict["content"]
|
||||
|
||||
# Test is_reasoning_end
|
||||
|
||||
@@ -13,43 +13,43 @@ END_REASONING = "</think>"
|
||||
|
||||
NO_REASONING = {
|
||||
"output": f"{START_REASONING}{END_REASONING}No thoughts, head empty!",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "No thoughts, head empty!",
|
||||
}
|
||||
|
||||
NO_REASONING_WITH_NEWLINE = {
|
||||
"output": f"{START_REASONING}\n{END_REASONING}\n\nNo thoughts, head empty!",
|
||||
"reasoning_content": "\n",
|
||||
"reasoning": "\n",
|
||||
"content": "\n\nNo thoughts, head empty!",
|
||||
}
|
||||
|
||||
SIMPLE_REASONING = {
|
||||
"output": f"{START_REASONING}This is a reasoning section{END_REASONING}This is the rest", # noqa: E501
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
}
|
||||
|
||||
SIMPLE_REASONING_WITH_NEWLINE = {
|
||||
"output": f"{START_REASONING} Look!\n\nI'm thinking...{END_REASONING}\nThis is the rest", # noqa: E501
|
||||
"reasoning_content": " Look!\n\nI'm thinking...",
|
||||
"reasoning": " Look!\n\nI'm thinking...",
|
||||
"content": "\nThis is the rest",
|
||||
}
|
||||
|
||||
SIMPLE_REASONING_WITH_MULTIPLE_NEWLINES = {
|
||||
"output": f"{START_REASONING}\nLook!\nI'm thinking...\n\n{END_REASONING}\n\n\nThis is the rest", # noqa: E501
|
||||
"reasoning_content": "\nLook!\nI'm thinking...\n\n",
|
||||
"reasoning": "\nLook!\nI'm thinking...\n\n",
|
||||
"content": "\n\n\nThis is the rest",
|
||||
}
|
||||
|
||||
NO_REASONING_ONLY_END_THINK = {
|
||||
"output": f"{END_REASONING}\n\nNo thoughts, head empty!",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "\n\nNo thoughts, head empty!",
|
||||
}
|
||||
|
||||
REASONING_ONLY_END_THINK = {
|
||||
"output": f"The user is asking me not to think.{END_REASONING}No thoughts!",
|
||||
"reasoning_content": "The user is asking me not to think.",
|
||||
"reasoning": "The user is asking me not to think.",
|
||||
"content": "No thoughts!",
|
||||
}
|
||||
|
||||
@@ -148,5 +148,5 @@ def test_reasoning(
|
||||
reasoning_parser=parser, model_output=model_output, streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == param_dict["reasoning_content"]
|
||||
assert reasoning == param_dict["reasoning"]
|
||||
assert content == param_dict["content"]
|
||||
|
||||
@@ -22,47 +22,47 @@ def qwen3_tokenizer():
|
||||
# 带 <think></think>,非stream
|
||||
WITH_THINK = {
|
||||
"output": "<think>This is a reasoning section</think>This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
}
|
||||
# 带 <think></think>,stream
|
||||
WITH_THINK_STREAM = {
|
||||
"output": "<think>This is a reasoning section</think>This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
}
|
||||
# 不带 <think></think>,非stream
|
||||
WITHOUT_THINK = {
|
||||
"output": "This is the rest",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is the rest",
|
||||
}
|
||||
# 不带 <think></think>,stream
|
||||
WITHOUT_THINK_STREAM = {
|
||||
"output": "This is the rest",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "This is the rest",
|
||||
}
|
||||
|
||||
COMPLETE_REASONING = {
|
||||
"output": "<think>This is a reasoning section</think>",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
}
|
||||
MULTILINE_REASONING = {
|
||||
"output": "<think>This is a reasoning\nsection</think>This is the rest\nThat",
|
||||
"reasoning_content": "This is a reasoning\nsection",
|
||||
"reasoning": "This is a reasoning\nsection",
|
||||
"content": "This is the rest\nThat",
|
||||
}
|
||||
ONLY_OPEN_TAG = {
|
||||
"output": "<think>This is a reasoning section",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": "<think>This is a reasoning section",
|
||||
}
|
||||
|
||||
ONLY_OPEN_TAG_STREAM = {
|
||||
"output": "<think>This is a reasoning section",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
}
|
||||
|
||||
@@ -138,5 +138,5 @@ def test_reasoning(
|
||||
parser, output_tokens, streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == param_dict["reasoning_content"]
|
||||
assert reasoning == param_dict["reasoning"]
|
||||
assert content == param_dict["content"]
|
||||
|
||||
@@ -28,49 +28,49 @@ def seedoss_tokenizer():
|
||||
|
||||
SIMPLE_REASONING: dict[str, Any] = {
|
||||
"output": "This is a reasoning section</seed:think>This is the rest",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
COMPLETE_REASONING: dict[str, Any] = {
|
||||
"output": "This is a reasoning section</seed:think>",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
NO_CONTENT: dict[str, Any] = {
|
||||
"output": "This is content",
|
||||
"reasoning_content": "This is content",
|
||||
"reasoning": "This is content",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
NO_REASONING_STREAMING: dict[str, Any] = {
|
||||
"output": "This is a reasoning section",
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
MULTIPLE_LINES: dict[str, Any] = {
|
||||
"output": "This\nThat</seed:think>This is the rest\nThat",
|
||||
"reasoning_content": "This\nThat",
|
||||
"reasoning": "This\nThat",
|
||||
"content": "This is the rest\nThat",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
WITH_START_TOKEN: dict[str, Any] = {
|
||||
"output": ("<seed:think>This is a reasoning section</seed:think>This is the rest"),
|
||||
"reasoning_content": "This is a reasoning section",
|
||||
"reasoning": "This is a reasoning section",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
ONLY_END_TOKEN: dict[str, Any] = {
|
||||
"output": "Some reasoning</seed:think>This is the rest",
|
||||
"reasoning_content": "Some reasoning",
|
||||
"reasoning": "Some reasoning",
|
||||
"content": "This is the rest",
|
||||
"is_reasoning_end": True,
|
||||
}
|
||||
NO_TOKENS: dict[str, Any] = {
|
||||
"output": "This is just content without any reasoning tokens",
|
||||
"reasoning_content": "This is just content without any reasoning tokens",
|
||||
"reasoning": "This is just content without any reasoning tokens",
|
||||
"content": None,
|
||||
"is_reasoning_end": False,
|
||||
}
|
||||
@@ -95,7 +95,7 @@ def test_simple_reasoning(seedoss_tokenizer, streaming):
|
||||
parser, [cast(str, SIMPLE_REASONING["output"])], streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == SIMPLE_REASONING["reasoning_content"]
|
||||
assert reasoning == SIMPLE_REASONING["reasoning"]
|
||||
assert content == SIMPLE_REASONING["content"]
|
||||
|
||||
|
||||
@@ -109,7 +109,7 @@ def test_complete_reasoning(seedoss_tokenizer, streaming):
|
||||
parser, [cast(str, COMPLETE_REASONING["output"])], streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == COMPLETE_REASONING["reasoning_content"]
|
||||
assert reasoning == COMPLETE_REASONING["reasoning"]
|
||||
assert content == COMPLETE_REASONING["content"]
|
||||
|
||||
|
||||
@@ -123,7 +123,7 @@ def test_no_content(seedoss_tokenizer, streaming):
|
||||
parser, [cast(str, NO_CONTENT["output"])], streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == NO_CONTENT["reasoning_content"]
|
||||
assert reasoning == NO_CONTENT["reasoning"]
|
||||
assert content == NO_CONTENT["content"]
|
||||
|
||||
|
||||
@@ -137,7 +137,7 @@ def test_multiple_lines(seedoss_tokenizer, streaming):
|
||||
parser, [cast(str, MULTIPLE_LINES["output"])], streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == MULTIPLE_LINES["reasoning_content"]
|
||||
assert reasoning == MULTIPLE_LINES["reasoning"]
|
||||
assert content == MULTIPLE_LINES["content"]
|
||||
|
||||
|
||||
@@ -151,7 +151,7 @@ def test_with_start_token(seedoss_tokenizer, streaming):
|
||||
parser, [cast(str, WITH_START_TOKEN["output"])], streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == WITH_START_TOKEN["reasoning_content"]
|
||||
assert reasoning == WITH_START_TOKEN["reasoning"]
|
||||
assert content == WITH_START_TOKEN["content"]
|
||||
|
||||
|
||||
@@ -168,7 +168,7 @@ def test_only_end_token(seedoss_tokenizer, streaming):
|
||||
parser, [cast(str, ONLY_END_TOKEN["output"])], streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == ONLY_END_TOKEN["reasoning_content"]
|
||||
assert reasoning == ONLY_END_TOKEN["reasoning"]
|
||||
assert content == ONLY_END_TOKEN["content"]
|
||||
|
||||
|
||||
@@ -182,7 +182,7 @@ def test_no_tokens(seedoss_tokenizer, streaming):
|
||||
parser, [cast(str, NO_TOKENS["output"])], streaming=streaming
|
||||
)
|
||||
|
||||
assert reasoning == NO_TOKENS["reasoning_content"]
|
||||
assert reasoning == NO_TOKENS["reasoning"]
|
||||
assert content == NO_TOKENS["content"]
|
||||
|
||||
|
||||
|
||||
+13
-10
@@ -9,25 +9,28 @@ from vllm.transformers_utils.tokenizers.mistral import MistralTokenizer
|
||||
|
||||
class StreamingReasoningReconstructor:
|
||||
def __init__(self):
|
||||
self.reasoning_content = None
|
||||
self.reasoning = None
|
||||
self.other_content = None
|
||||
|
||||
def append_delta(self, delta: DeltaMessage):
|
||||
# content and the reasoning content should not be present
|
||||
# at the same time
|
||||
assert delta.content is None or delta.reasoning_content is None, (
|
||||
assert delta.content is None or delta.reasoning is None, (
|
||||
"Both content and reasoning content are present in the delta message"
|
||||
)
|
||||
assert delta.reasoning == delta.reasoning_content, (
|
||||
"reasoning_content should be present for backwards compatibility"
|
||||
)
|
||||
if delta.content is not None:
|
||||
if self.other_content is None:
|
||||
self.other_content = delta.content
|
||||
else:
|
||||
self.other_content += delta.content
|
||||
else:
|
||||
if self.reasoning_content is None:
|
||||
self.reasoning_content = delta.reasoning_content
|
||||
if self.reasoning is None:
|
||||
self.reasoning = delta.reasoning
|
||||
else:
|
||||
self.reasoning_content += delta.reasoning_content
|
||||
self.reasoning += delta.reasoning
|
||||
|
||||
|
||||
def run_reasoning_extraction(
|
||||
@@ -43,7 +46,7 @@ def run_reasoning_extraction(
|
||||
request,
|
||||
)
|
||||
return (
|
||||
reconstructor.reasoning_content,
|
||||
reconstructor.reasoning,
|
||||
reconstructor.other_content or None,
|
||||
)
|
||||
else:
|
||||
@@ -69,7 +72,7 @@ def run_reasoning_extraction_mistral(
|
||||
request,
|
||||
)
|
||||
return (
|
||||
reconstructor.reasoning_content,
|
||||
reconstructor.reasoning,
|
||||
reconstructor.other_content or None,
|
||||
)
|
||||
else:
|
||||
@@ -88,7 +91,7 @@ def run_reasoning_extraction_nonstreaming(
|
||||
request: ChatCompletionRequest | None = None,
|
||||
) -> tuple[str | None, str | None]:
|
||||
request = request or ChatCompletionRequest(messages=[], model="test-model")
|
||||
return reasoning_parser.extract_reasoning_content(
|
||||
return reasoning_parser.extract_reasoning(
|
||||
model_output="".join(model_output), request=request
|
||||
)
|
||||
|
||||
@@ -110,7 +113,7 @@ def run_reasoning_extraction_streaming(
|
||||
]
|
||||
current_text = previous_text + delta
|
||||
current_tokens = previous_tokens + token_delta
|
||||
delta_message = reasoning_parser.extract_reasoning_content_streaming(
|
||||
delta_message = reasoning_parser.extract_reasoning_streaming(
|
||||
previous_text,
|
||||
current_text,
|
||||
delta,
|
||||
@@ -142,7 +145,7 @@ def run_reasoning_extraction_streaming_mistral(
|
||||
delta = reasoning_parser.model_tokenizer.convert_ids_to_tokens([model_delta])[0]
|
||||
current_text = previous_text + delta
|
||||
current_tokens = previous_tokens + token_delta
|
||||
delta_message = reasoning_parser.extract_reasoning_content_streaming(
|
||||
delta_message = reasoning_parser.extract_reasoning_streaming(
|
||||
previous_text,
|
||||
current_text,
|
||||
delta,
|
||||
|
||||
@@ -102,7 +102,7 @@ def test_prepare_apply_chat_template_tools_and_messages(
|
||||
assert actual_request == expected_mistral_output
|
||||
|
||||
|
||||
# Tool use with list content and reasoning_content
|
||||
# Tool use with list content and reasoning
|
||||
@pytest.mark.parametrize(
|
||||
"openai_request,expected_mistral_output",
|
||||
[
|
||||
@@ -115,7 +115,7 @@ def test_prepare_apply_chat_template_tools_and_messages(
|
||||
},
|
||||
{
|
||||
"role": "assistant",
|
||||
"reasoning_content": None,
|
||||
"reasoning": None,
|
||||
"content": None,
|
||||
"tool_calls": [
|
||||
{
|
||||
|
||||
@@ -337,7 +337,7 @@ def test_extract_tool_calls_streaming_incremental(
|
||||
if (
|
||||
delta_message.role is None
|
||||
and delta_message.content is None
|
||||
and delta_message.reasoning_content is None
|
||||
and delta_message.reasoning is None
|
||||
and len(delta_message.tool_calls) == 0
|
||||
):
|
||||
continue
|
||||
|
||||
@@ -674,10 +674,10 @@ def test_structured_output_with_reasoning_matrices(
|
||||
assert output is not None and isinstance(output, RequestOutput)
|
||||
prompt = output.prompt
|
||||
generated_text = output.outputs[0].text
|
||||
reasoning_content, content = run_reasoning_extraction(reasoner, [generated_text])
|
||||
print(f"Prompt: {prompt!r}\nReasoning: {reasoning_content!r}\nContent: {content!r}")
|
||||
reasoning, content = run_reasoning_extraction(reasoner, [generated_text])
|
||||
print(f"Prompt: {prompt!r}\nReasoning: {reasoning!r}\nContent: {content!r}")
|
||||
|
||||
assert content is not None and reasoning_content is not None
|
||||
assert content is not None and reasoning is not None
|
||||
output_json = json.loads(content)
|
||||
jsonschema.validate(instance=output_json, schema=reasoning_schema)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user