Support DeepSeek-V3.1 tool call (#9446)

Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>

examples/chat_template/tool_chat_template_deepseekv31.jinja

@@ -0,0 +1,91 @@
+{% if not add_generation_prompt is defined %}
+  {% set add_generation_prompt = false %}
+{% endif %}
+{% if not thinking is defined %}
+  {% set thinking = false %}
+{% endif %}
+{% set ns = namespace(is_first=false, is_tool=false, system_prompt='', is_first_sp=true, is_last_user=false) %}
+{%- for message in messages %}
+  {%- if message['role'] == 'system' %}
+    {%- if ns.is_first_sp %}
+      {% set ns.system_prompt = ns.system_prompt + message['content'] %}
+      {% set ns.is_first_sp = false %}
+    {%- else %}
+      {% set ns.system_prompt = ns.system_prompt + '\n\n' + message['content'] %}
+    {%- endif %}
+  {%- endif %}
+{%- endfor %}
+
+{% if tools is defined and tools is not none %}
+  {% set tool_ns = namespace(text='## Tools\nYou have access to the following tools:\n') %}
+  {% for tool in tools %}
+    {% set tool_ns.text = tool_ns.text + '\n### ' + tool.function.name + '\nDescription: ' + tool.function.description + '\n\nParameters: ' + (tool.function.parameters | tojson) + '\n' %}
+  {% endfor %}
+  {% set tool_ns.text = tool_ns.text + "\nIMPORTANT: ALWAYS adhere to this exact format for tool use:\n<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>tool_call_name<｜tool▁sep｜>tool_call_arguments<｜tool▁call▁end｜>{{additional_tool_calls}}<｜tool▁calls▁end｜>\n\nWhere:\n\n- `tool_call_name` must be an exact match to one of the available tools\n- `tool_call_arguments` must be valid JSON that strictly follows the tool's Parameters Schema\n- For multiple tool calls, chain them directly without separators or spaces\n" %}
+  {% set ns.system_prompt = ns.system_prompt + '\n\n' + tool_ns.text %}
+{% endif %}
+
+{{ bos_token }}{{ ns.system_prompt }}
+{%- for message in messages %}
+  {%- if message['role'] == 'user' %}
+    {%- set ns.is_tool = false -%}
+    {%- set ns.is_first = false -%}
+    {%- set ns.is_last_user = true -%}
+    {{'<｜User｜>' + message['content']}}
+  {%- endif %}
+  {%- if message['role'] == 'assistant' and message['tool_calls'] is defined and message['tool_calls'] is not none %}
+    {%- if ns.is_last_user %}
+      {{'<｜Assistant｜></think>'}}
+    {%- endif %}
+    {%- set ns.is_last_user = false -%}
+    {%- set ns.is_first = false %}
+    {%- set ns.is_tool = false -%}
+    {%- for tool in message['tool_calls'] %}
+      {%- if not ns.is_first %}
+        {%- if message['content'] is none %}
+          {{'<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>'+ tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}
+        {%- else %}
+          {{message['content'] + '<｜tool▁calls▁begin｜><｜tool▁call▁begin｜>' + tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}
+        {%- endif %}
+        {%- set ns.is_first = true -%}
+      {%- else %}
+        {{'<｜tool▁call▁begin｜>'+ tool['function']['name'] + '<｜tool▁sep｜>' + tool['function']['arguments'] + '<｜tool▁call▁end｜>'}}
+      {%- endif %}
+    {%- endfor %}
+    {{'<｜tool▁calls▁end｜><｜end▁of▁sentence｜>'}}
+  {%- endif %}
+  {%- if message['role'] == 'assistant' and (message['tool_calls'] is not defined or message['tool_calls'] is none) %}
+    {%- if ns.is_last_user %}
+      {{'<｜Assistant｜>'}}
+      {%- if message['prefix'] is defined and message['prefix'] and thinking %}
+        {{'<think>'}}
+      {%- else %}
+        {{'</think>'}}
+      {%- endif %}
+    {%- endif %}
+    {%- set ns.is_last_user = false -%}
+    {%- if ns.is_tool %}
+      {{message['content'] + '<｜end▁of▁sentence｜>'}}
+      {%- set ns.is_tool = false -%}
+    {%- else %}
+      {%- set content = message['content'] -%}
+      {%- if '</think>' in content %}
+        {%- set content = content.split('</think>', 1)[1] -%}
+      {%- endif %}
+      {{content + '<｜end▁of▁sentence｜>'}}
+    {%- endif %}
+  {%- endif %}
+  {%- if message['role'] == 'tool' %}
+    {%- set ns.is_last_user = false -%}
+    {%- set ns.is_tool = true -%}
+    {{'<｜tool▁output▁begin｜>' + message['content'] + '<｜tool▁output▁end｜>'}}
+  {%- endif %}
+{%- endfor -%}
+{%- if add_generation_prompt and ns.is_last_user and not ns.is_tool %}
+  {{'<｜Assistant｜>'}}
+  {%- if not thinking %}
+    {{'</think>'}}
+  {%- else %}
+    {{'<think>'}}
+  {%- endif %}
+{% endif %}

python/sglang/srt/function_call/deepseekv31_detector.py

@@ -0,0 +1,222 @@
+import json
+import logging
+import re
+from typing import List
+
+from sglang.srt.entrypoints.openai.protocol import Tool
+from sglang.srt.function_call.base_format_detector import BaseFormatDetector
+from sglang.srt.function_call.core_types import (
+    StreamingParseResult,
+    StructureInfo,
+    ToolCallItem,
+    _GetInfoFunc,
+)
+from sglang.srt.function_call.ebnf_composer import EBNFComposer
+from sglang.srt.function_call.utils import _is_complete_json
+
+logger = logging.getLogger(__name__)
+
+
+class DeepSeekV31Detector(BaseFormatDetector):
+    """
+    Detector for DeepSeek V3 model function call format.
+
+    The DeepSeek V3 format uses special Unicode tokens to delimit function calls
+    with JSON code blocks for arguments.
+
+    Format Structure:
+    ```
+    <｜tool▁calls▁begin｜><｜tool▁call▁begin｜>{function_name}<｜tool▁sep｜>{json_arguments}<｜tool▁calls▁end｜><｜end▁of▁sentence｜>
+    ```
+    Examples:
+    ```
+    <｜tool▁calls▁begin｜><｜tool▁call▁begin｜>get_current_weather<｜tool▁sep｜>{"location": "Tokyo"}<｜tool▁call▁end｜><｜tool▁call▁begin｜>get_current_weather<｜tool▁sep｜>{"location": "Paris"}<｜tool▁call▁end｜><｜tool▁calls▁end｜><｜end▁of▁sentence｜>
+    ```
+
+    Key Components:
+    - Tool Calls Section: Wrapped between `<｜tool▁calls▁begin｜>` and `<｜tool▁calls▁end｜>`
+    - Individual Tool Call: Wrapped between `<｜tool▁call▁begin｜>` and `<｜tool▁call▁end｜>`
+    - Function Declaration: `<｜tool▁call▁begin｜>{function_name}<｜tool▁sep｜>`
+    - Arguments: JSON code block between `<｜tool▁sep｜>` and `<｜tool▁call▁end｜>`
+    - Supports multiple tool calls
+
+    Reference: https://www.modelscope.cn/models/deepseek-ai/DeepSeek-V3.1
+    """
+
+    def __init__(self):
+        super().__init__()
+        self.bot_token = "<｜tool▁calls▁begin｜>"
+        self.eot_token = "<｜tool▁calls▁end｜>"
+        self.func_call_regex = r"<｜tool▁call▁begin｜>.*?<｜tool▁call▁end｜>"
+        self.func_detail_regex = (
+            r"<｜tool▁call▁begin｜>(.*)<｜tool▁sep｜>(.*)<｜tool▁call▁end｜>"
+        )
+        self._last_arguments = ""
+        self.current_tool_id = -1
+
+    def has_tool_call(self, text: str) -> bool:
+        """Check if the text contains a deepseek format tool call."""
+        return self.bot_token in text
+
+    def detect_and_parse(self, text: str, tools: List[Tool]) -> StreamingParseResult:
+        """
+        One-time parsing: Detects and parses tool calls in the provided text.
+
+        :param text: The complete text to parse.
+        :param tools: List of available tools.
+        :return: ParseResult indicating success or failure, consumed text, leftover text, and parsed calls.
+        """
+        idx = text.find(self.bot_token)
+        normal_text = text[:idx].strip() if idx != -1 else text
+        if self.bot_token not in text:
+            return StreamingParseResult(normal_text=normal_text, calls=[])
+        match_result_list = re.findall(self.func_call_regex, text, re.DOTALL)
+        calls = []
+        try:
+            for match_result in match_result_list:
+                # Get function name
+                func_detail = re.search(self.func_detail_regex, match_result, re.DOTALL)
+                func_name = func_detail.group(1)
+                func_args = func_detail.group(2)
+                func_args = json.loads(func_args)
+                # construct match_result for parse_base_json
+                match_result = {"name": func_name, "parameters": func_args}
+                calls.extend(self.parse_base_json(match_result, tools))
+            return StreamingParseResult(normal_text=normal_text, calls=calls)
+        except Exception as e:
+            logger.error(f"Error in detect_and_parse: {e}")
+            # return the normal text if parsing fails
+            return StreamingParseResult(normal_text=text)
+
+    def parse_streaming_increment(
+        self, new_text: str, tools: List[Tool]
+    ) -> StreamingParseResult:
+        """
+        Streaming incremental parsing tool calls for DeepSeekV3 format.
+        """
+        self._buffer += new_text
+        current_text = self._buffer
+
+        # Check if we have a tool call (either the start token or individual tool call)
+        has_tool_call = (
+            self.bot_token in current_text or "<｜tool▁call▁begin｜>" in current_text
+        )
+
+        if not has_tool_call:
+            self._buffer = ""
+            for e_token in [self.eot_token, "<｜tool▁call▁end｜>"]:
+                if e_token in new_text:
+                    new_text = new_text.replace(e_token, "")
+            return StreamingParseResult(normal_text=new_text)
+
+        if not hasattr(self, "_tool_indices"):
+            self._tool_indices = self._get_tool_indices(tools)
+
+        calls: list[ToolCallItem] = []
+        try:
+            partial_match = re.search(
+                pattern=r"<｜tool▁call▁begin｜>(.*)<｜tool▁sep｜>(.*)<｜tool▁call▁end｜>",
+                string=current_text,
+                flags=re.DOTALL,
+            )
+            if partial_match:
+                func_name = partial_match.group(1).strip()
+                func_args_raw = partial_match.group(2).strip()
+
+                # Initialize state if this is the first tool call
+                if self.current_tool_id == -1:
+                    self.current_tool_id = 0
+                    self.prev_tool_call_arr = []
+                    self.streamed_args_for_tool = [""]
+
+                # Ensure we have enough entries in our tracking arrays
+                while len(self.prev_tool_call_arr) <= self.current_tool_id:
+                    self.prev_tool_call_arr.append({})
+                while len(self.streamed_args_for_tool) <= self.current_tool_id:
+                    self.streamed_args_for_tool.append("")
+
+                if not self.current_tool_name_sent:
+                    calls.append(
+                        ToolCallItem(
+                            tool_index=self.current_tool_id,
+                            name=func_name,
+                            parameters="",
+                        )
+                    )
+                    self.current_tool_name_sent = True
+                    # Store the tool call info for serving layer completions endpoint
+                    self.prev_tool_call_arr[self.current_tool_id] = {
+                        "name": func_name,
+                        "arguments": {},
+                    }
+                else:
+                    argument_diff = (
+                        func_args_raw[len(self._last_arguments) :]
+                        if func_args_raw.startswith(self._last_arguments)
+                        else func_args_raw
+                    )
+
+                    if argument_diff:
+                        calls.append(
+                            ToolCallItem(
+                                tool_index=self.current_tool_id,
+                                name=None,
+                                parameters=argument_diff,
+                            )
+                        )
+                        self._last_arguments += argument_diff
+                        self.streamed_args_for_tool[
+                            self.current_tool_id
+                        ] += argument_diff
+
+                    if _is_complete_json(func_args_raw):
+                        # Update the stored arguments
+                        try:
+                            parsed_args = json.loads(func_args_raw)
+                            self.prev_tool_call_arr[self.current_tool_id][
+                                "arguments"
+                            ] = parsed_args
+                        except json.JSONDecodeError:
+                            pass
+
+                        # Find the end of the current tool call and remove only that part from buffer
+                        tool_call_end_pattern = (
+                            r"<｜tool▁call▁begin｜>.*?<｜tool▁call▁end｜>"
+                        )
+                        match = re.search(
+                            tool_call_end_pattern, current_text, re.DOTALL
+                        )
+                        if match:
+                            # Remove the completed tool call from buffer, keep any remaining content
+                            self._buffer = current_text[match.end() :]
+                        else:
+                            self._buffer = ""
+
+                        result = StreamingParseResult(normal_text="", calls=calls)
+                        self.current_tool_id += 1
+                        self._last_arguments = ""
+                        self.current_tool_name_sent = False
+                        return result
+
+            return StreamingParseResult(normal_text="", calls=calls)
+
+        except Exception as e:
+            logger.error(f"Error in parse_streaming_increment: {e}")
+            return StreamingParseResult(normal_text=current_text)
+
+    def structure_info(self) -> _GetInfoFunc:
+        return lambda name: StructureInfo(
+            begin="<｜tool▁call▁begin｜>" + name + "<｜tool▁sep｜>",
+            end="<｜tool▁call▁end｜>",
+            trigger="<｜tool▁call▁begin｜>" + name + "<｜tool▁sep｜>",
+        )
+
+    def build_ebnf(self, tools: List[Tool]):
+        return EBNFComposer.build_ebnf(
+            tools,
+            sequence_start_token=self.bot_token,
+            sequence_end_token=self.eot_token,
+            tool_call_separator="",
+            call_rule_fmt='"<｜tool▁call▁begin｜>{name}<｜tool▁sep｜>{arguments_rule}<｜tool▁call▁end｜>"',
+            function_format="json",
+        )

python/sglang/srt/function_call/function_call_parser.py

@@ -10,6 +10,7 @@ from sglang.srt.entrypoints.openai.protocol import (
 from sglang.srt.function_call.base_format_detector import BaseFormatDetector
 from sglang.srt.function_call.core_types import ToolCallItem
 from sglang.srt.function_call.deepseekv3_detector import DeepSeekV3Detector
+from sglang.srt.function_call.deepseekv31_detector import DeepSeekV31Detector
 from sglang.srt.function_call.glm4_moe_detector import Glm4MoeDetector
 from sglang.srt.function_call.gpt_oss_detector import GptOssDetector
 from sglang.srt.function_call.kimik2_detector import KimiK2Detector
@@ -37,6 +38,7 @@ class FunctionCallParser:
         "qwen25": Qwen25Detector,
         "mistral": MistralDetector,
         "deepseekv3": DeepSeekV3Detector,
+        "deepseekv31": DeepSeekV31Detector,
         "pythonic": PythonicDetector,
         "kimi_k2": KimiK2Detector,
         "qwen3_coder": Qwen3CoderDetector,