【Hackathon 9th Sprint No.60】【RFC】为 FastDeploy 新增支持 DeepSeek 模型的 Reason ing Parser & Tool Parser #5412

fgeygfe · 2025-12-05T18:18:18Z

No description provided.

…ing Parser & Tool Parser

paddle-bot · 2025-12-05T18:18:24Z

Thanks for your contribution!

Copilot

Pull request overview

This pull request adds comprehensive support for DeepSeek models (V3.1, V3-0324, and R1) to FastDeploy by implementing both Reasoning Parser and Tool Parser functionality. The implementation follows existing patterns in the codebase and includes thorough test coverage.

Key Changes:

Implements DeepSeekReasoningParser to extract reasoning content from DeepSeek model outputs with support for both streaming and non-streaming modes
Implements DeepSeekToolParser to parse tool calls from DeepSeek models, supporting two different formats (V3.1 and V3-0324/R1)
Adds comprehensive test suites for both parsers covering edge cases and protocol violations
Updates documentation in both English and Chinese with examples and error handling guidance

Reviewed changes

Copilot reviewed 8 out of 8 changed files in this pull request and generated 10 comments.

Show a summary per file

File	Description
`fastdeploy/reasoning/deepseek_reasoning_parser.py`	New reasoning parser implementation for DeepSeek models with `<think>` tag extraction
`fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py`	New tool parser supporting V3.1 and V3-0324/R1 format variations with streaming support
`tests/reasoning/test_reasoning_parser.py`	Adds comprehensive test cases for DeepSeek reasoning parser with 18 test methods
`tests/entrypoints/openai/tool_parsers/test_deepseek_tool_parser.py`	New test file with 15 test cases covering both model formats and edge cases
`docs/zh/features/tool_calling.md`	Chinese documentation with DeepSeek model table and error handling examples
`docs/zh/features/reasoning_output.md`	Chinese documentation for reasoning output with model compatibility table
`docs/features/tool_calling.md`	English documentation with DeepSeek model table and error handling examples
`docs/features/reasoning_output.md`	English documentation for reasoning output with model compatibility table

Comments suppressed due to low confidence (3)

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py:164

Except block directly handles BaseException.

                    except:

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py:294

Except block directly handles BaseException.

                                except:

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py:322

Except block directly handles BaseException.

                        except:

Copilot · 2025-12-05T18:24:26Z

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py

+                if tool_calls_begin_pos > 0:
+                    # 检查中间是否有非空白字符
+                    between_text = after_reasoning[:tool_calls_begin_pos]
+                    if between_text.strip() and not between_text.strip().isspace():


The logic between_text.strip() and not between_text.strip().isspace() is redundant. After calling .strip(), the result is already stripped of whitespace, so .strip().isspace() will always return False for any non-empty string. Simply use:

if between_text.strip(): # 有非空白字符，协议不规范，不解析工具调用 return ExtractedToolCallInformation(tools_called=False, tool_calls=None, content=model_output)

This achieves the same result more efficiently.

Suggested change

if between_text.strip() and not between_text.strip().isspace():

if between_text.strip():

Copilot · 2025-12-05T18:24:27Z

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py

+
+def random_tool_call_id() -> str:
+    """Generate a random tool call ID"""
+    return f"chatcmpl-tool-{str(uuid.uuid4().hex)}"


Simplify the redundant str() conversion. uuid.uuid4().hex already returns a string, so wrapping it in str() is unnecessary:

return f"chatcmpl-tool-{uuid.uuid4().hex}"

Suggested change

return f"chatcmpl-tool-{str(uuid.uuid4().hex)}"

return f"chatcmpl-tool-{uuid.uuid4().hex}"

Copilot · 2025-12-05T18:24:27Z

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py

+                self.current_tool_id = (
+                    max(self.current_tool_id, 0) if self.current_tool_id == -1 else self.current_tool_id + 1
+                )


[nitpick] The logic for initializing current_tool_id when it's -1 is unnecessarily complex. Consider simplifying:

if self.current_tool_id == -1: self.current_tool_id = 0 else: self.current_tool_id += 1

This achieves the same result as max(self.current_tool_id, 0) if self.current_tool_id == -1 else self.current_tool_id + 1 but is clearer and more readable.

Suggested change

self.current_tool_id = (

max(self.current_tool_id, 0) if self.current_tool_id == -1 else self.current_tool_id + 1

)

if self.current_tool_id == -1:

self.current_tool_id = 0

else:

self.current_tool_id += 1

Copilot · 2025-12-05T18:24:27Z

fastdeploy/reasoning/deepseek_reasoning_parser.py

+
+        if not self.model_tokenizer:
+            raise ValueError(
+                "The model tokenizer must be passed to the ReasoningParser " "constructor during construction."


[nitpick] The error message string is split across two lines using string concatenation. Consider using a single string or parentheses for better readability:

raise ValueError( "The model tokenizer must be passed to the ReasoningParser constructor during construction." )

Suggested change

"The model tokenizer must be passed to the ReasoningParser " "constructor during construction."

"The model tokenizer must be passed to the ReasoningParser constructor during construction."

Copilot · 2025-12-05T18:24:28Z

fastdeploy/reasoning/deepseek_reasoning_parser.py

+
+        if self.think_end_token_id is None:
+            raise RuntimeError(
+                "DeepSeek reasoning parser could not locate think end " "tokens in the tokenizer!"


[nitpick] The error message string is split across two lines using string concatenation. Consider using a single string or parentheses for better readability:

raise RuntimeError( "DeepSeek reasoning parser could not locate think end tokens in the tokenizer!" )

Suggested change

"DeepSeek reasoning parser could not locate think end " "tokens in the tokenizer!"

"DeepSeek reasoning parser could not locate think end tokens in the tokenizer!"

Copilot · 2025-12-05T18:24:28Z

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py

+    """
+    DeepSeek 系列模型的工具调用解析器（支持 V3.1、V3-0324、R1 三种模型）
+
+    支持的格式：
+    - V3.1: <｜tool▁call▁begin｜>function_name<｜tool▁sep｜>{"arg": "value"}<｜tool▁call▁end｜>
+    - V3-0324/R1: <｜tool▁call▁begin｜>function<｜tool▁sep｜>function_name\n```json\n{"arg": "value"}\n```<｜tool▁call▁end｜>
+    """


[nitpick] Consider adding an English translation to the docstring for consistency with the rest of the codebase. Many projects follow bilingual documentation standards. For example:

""" DeepSeek series model tool call parser (supports V3.1, V3-0324, R1 models) DeepSeek 系列模型的工具调用解析器（支持 V3.1、V3-0324、R1 三种模型） Supported formats: 支持的格式： - V3.1: <｜tool▁call▁begin｜>function_name<｜tool▁sep｜>{"arg": "value"}<｜tool▁call▁end｜> - V3-0324/R1: <｜tool▁call▁begin｜>function<｜tool▁sep｜>function_name\n```json\n{"arg": "value"}\n```<｜tool▁call▁end｜> """

Copilot · 2025-12-05T18:24:28Z

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py

+                    # 尝试使用 partial_json_parser
+                    try:
+                        args_dict = partial_json_parser.loads(function_arguments, flags=Allow.ALL)
+                    except:


Avoid using bare except: clauses. Catch specific exception types to ensure proper error handling and avoid masking unexpected errors. Consider catching Exception or specific parser exceptions:

except Exception: args_dict = {}

This applies to all three bare except: clauses in the file (lines 164, 294, 322).

Suggested change

except:

except Exception:

Copilot · 2025-12-05T18:24:29Z

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py

+                                try:
+                                    args_dict = partial_json_parser.loads(args_text, flags=Allow.ALL)
+                                    args_str = json.dumps(args_dict, ensure_ascii=False)
+                                except:


Avoid using bare except: clauses. Catch specific exception types to ensure proper error handling and avoid masking unexpected errors. Consider catching Exception or specific parser exceptions:

except Exception: args_str = args_text

Suggested change

except:

except Exception:

Copilot · 2025-12-05T18:24:29Z

fastdeploy/entrypoints/openai/tool_parsers/deepseek_tool_parser.py

+                            # 使用 partial_json_parser 解析部分 JSON
+                            args_dict = partial_json_parser.loads(args_text, flags=Allow.ALL)
+                            args_str = json.dumps(args_dict, ensure_ascii=False)
+                        except:


Avoid using bare except: clauses. Catch specific exception types to ensure proper error handling and avoid masking unexpected errors. Consider catching Exception or specific parser exceptions:

except Exception: # 如果解析失败，直接使用原始文本 args_str = args_text

Suggested change

except:

except Exception:

Copilot · 2025-12-05T18:24:29Z

tests/entrypoints/openai/tool_parsers/test_deepseek_tool_parser.py

+import json
+import unittest
+
+from fastdeploy.entrypoints.openai.protocol import ChatCompletionRequest, DeltaMessage


Import of 'DeltaMessage' is not used.

Suggested change

from fastdeploy.entrypoints.openai.protocol import ChatCompletionRequest, DeltaMessage

from fastdeploy.entrypoints.openai.protocol import ChatCompletionRequest

codecov-commenter · 2025-12-08T05:37:52Z

Codecov Report

❌ Patch coverage is 78.51240% with 52 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (develop@e43a5fc). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
...points/openai/tool_parsers/deepseek_tool_parser.py	79.26%	20 Missing and 14 partials ⚠️
fastdeploy/reasoning/deepseek_reasoning_parser.py	76.92%	10 Missing and 8 partials ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##             develop    #5412   +/-   ##
==========================================
  Coverage           ?   59.21%           
==========================================
  Files              ?      329           
  Lines              ?    40900           
  Branches           ?     6224           
==========================================
  Hits               ?    24219           
  Misses             ?    14801           
  Partials           ?     1880

Flag	Coverage Δ
GPU	`59.21% <78.51%> (?)`

Flags with carried forward coverage won't be shown. Click here to find out more.

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.

Hackathon 9th Sprint No.60】【RFC】为 FastDeploy 新增支持 DeepSeek 模型的 Reason…

ce3fc9d

…ing Parser & Tool Parser

Copilot AI review requested due to automatic review settings December 5, 2025 18:18

paddle-bot bot added the contributor External developers label Dec 5, 2025

Copilot started reviewing on behalf of fgeygfe December 5, 2025 18:18 View session

Copilot AI reviewed Dec 5, 2025

View reviewed changes

luotao1 mentioned this pull request Dec 8, 2025

【Hackathon 9th】开源贡献个人挑战赛冲刺赛 PaddlePaddle/Paddle#76333

Open

luotao1 added the PaddlePaddle Hackathon label Dec 8, 2025

luotao1 changed the title ~~Hackathon 9th Sprint No.60】【RFC】为 FastDeploy 新增支持 DeepSeek 模型的 Reason ing Parser & Tool Parser~~ 【Hackathon 9th Sprint No.60】【RFC】为 FastDeploy 新增支持 DeepSeek 模型的 Reason ing Parser & Tool Parser Dec 8, 2025

luotao1 assigned luotao1 and LiqinruiG Dec 8, 2025

	if between_text.strip() and not between_text.strip().isspace():
	if between_text.strip():

	return f"chatcmpl-tool-{str(uuid.uuid4().hex)}"
	return f"chatcmpl-tool-{uuid.uuid4().hex}"

-                self.current_tool_id = (
-                    max(self.current_tool_id, 0) if self.current_tool_id == -1 else self.current_tool_id + 1
-                )
+                if self.current_tool_id == -1:
+                    self.current_tool_id = 0
+                else:
+                    self.current_tool_id += 1

	"The model tokenizer must be passed to the ReasoningParser " "constructor during construction."
	"The model tokenizer must be passed to the ReasoningParser constructor during construction."

	"DeepSeek reasoning parser could not locate think end " "tokens in the tokenizer!"
	"DeepSeek reasoning parser could not locate think end tokens in the tokenizer!"

	from fastdeploy.entrypoints.openai.protocol import ChatCompletionRequest, DeltaMessage
	from fastdeploy.entrypoints.openai.protocol import ChatCompletionRequest

【Hackathon 9th Sprint No.60】【RFC】为 FastDeploy 新增支持 DeepSeek 模型的 Reason ing Parser & Tool Parser #5412

Are you sure you want to change the base?

【Hackathon 9th Sprint No.60】【RFC】为 FastDeploy 新增支持 DeepSeek 模型的 Reason ing Parser & Tool Parser #5412

Uh oh!

Conversation

fgeygfe commented Dec 5, 2025

Uh oh!

paddle-bot bot commented Dec 5, 2025

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

Copilot AI Dec 5, 2025

Choose a reason for hiding this comment

Uh oh!

codecov-commenter commented Dec 8, 2025

Codecov Report

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

4 participants