Agent 策略插件

本文档由 AI 自动翻译。如有任何不准确之处，请参考英文原版。

Agent 策略插件为 LLM 提供推理与决策逻辑，使其能够选择工具、调用工具并处理工具结果，从而自主解决问题。本指南将带你构建一个 Function Calling 策略，让模型自行获取当前时间。

前置条件

Dify 插件脚手架工具
Python 环境（版本 3.12）

有关准备插件开发工具的详细信息，参见 CLI。

在终端中运行 dify version 以确认脚手架工具已安装。

1. 初始化插件模板

运行以下命令为你的 Agent 插件创建开发模板：

dify plugin init

按照屏幕提示操作，下方注释解释了每一项选择。

➜  Dify Plugins Developing dify plugin init
Edit profile of the plugin
Plugin name (press Enter to next step): # Enter the plugin name
Author (press Enter to next step): Author name # Enter the plugin author
Description (press Enter to next step): Description # Enter the plugin description
---
Select the language you want to use for plugin development, and press Enter to con
BTW, you need Python 3.12+ to develop the Plugin if you choose Python.
-> python # Select Python environment
  go (not supported yet)
---
Based on the ability you want to extend, we have divided the Plugin into four type

- Tool: It's a tool provider, but not only limited to tools, you can implement an
- Model: Just a model provider, extending others is not allowed.
- Extension: Other times, you may only need a simple http service to extend the fu
- Agent Strategy: Implement your own logics here, just by focusing on Agent itself

What's more, we have provided the template for you, you can choose one of them b
  tool
-> agent-strategy # Select Agent strategy template
  llm
  text-embedding
---
Configure the permissions of the plugin, use up and down to navigate, tab to sel
Backwards Invocation:
Tools:
    Enabled: [✔]  You can invoke tools inside Dify if it's enabled # Enabled by default
Models:
    Enabled: [✔]  You can invoke models inside Dify if it's enabled # Enabled by default
    LLM: [✔]  You can invoke LLM models inside Dify if it's enabled # Enabled by default
    Text Embedding: [✘]  You can invoke text embedding models inside Dify if it'
    Rerank: [✘]  You can invoke rerank models inside Dify if it's enabled
...

初始化会创建一个文件夹，包含插件开发所需的全部资源：

├── GUIDE.md               # User guide and documentation
├── PRIVACY.md             # Privacy policy and data handling guidelines
├── README.md              # Project overview and setup instructions
├── _assets/               # Static assets directory
│   └── icon.svg           # Agent strategy provider icon/logo
├── main.py                # Main application entry point
├── manifest.yaml          # Basic plugin configuration
├── provider/              # Provider configurations directory
│   └── basic_agent.yaml   # Your agent provider settings
├── requirements.txt       # Python dependencies list
└── strategies/            # Strategy implementation directory
    ├── basic_agent.py     # Basic agent strategy implementation
    └── basic_agent.yaml   # Basic agent strategy configuration

此插件的所有关键功能都在 strategies/ 目录中。

2. 开发插件

Agent 策略插件的开发围绕两个文件展开：

插件声明：strategies/basic_agent.yaml
插件实现：strategies/basic_agent.py

2.1 定义参数

首先在 strategies/basic_agent.yaml 中声明插件的参数。这些参数驱动插件的核心功能，例如调用 LLM 或使用工具。建议先从以下四个参数开始：

model：要调用的大语言模型（例如 GPT-4、GPT-4o-mini）。
tools：增强插件功能的工具列表。
query：发送给模型的用户输入或提示词内容。
maximum_iterations：最大迭代次数，用于防止过度计算。

示例：

identity:
  name: basic_agent # the name of the agent_strategy
  author: novice # the author of the agent_strategy
  label:
    en_US: BasicAgent # the English label of the agent_strategy
description:
  en_US: BasicAgent # the English description of the agent_strategy
parameters:
  - name: model # the name of the model parameter
    type: model-selector # model-type
    scope: tool-call&llm # the scope of the parameter
    required: true
    label:
      en_US: Model
      zh_Hans: 模型
      pt_BR: Model
  - name: tools # the name of the tools parameter
    type: array[tools] # the type of tool parameter
    required: true
    label:
      en_US: Tools list
      zh_Hans: 工具列表
      pt_BR: Tools list
  - name: query # the name of the query parameter
    type: string # the type of query parameter
    required: true
    label:
      en_US: Query
      zh_Hans: 查询
      pt_BR: Query
  - name: maximum_iterations
    type: number
    required: false
    default: 5
    label:
      en_US: Maxium Iterations
      zh_Hans: 最大迭代次数
      pt_BR: Maxium Iterations
    max: 50 # if you set the max and min value, the display of the parameter will be a slider
    min: 1
extra:
  python:
    source: strategies/basic_agent.py

Dify 会根据这些参数声明自动渲染配置界面：

2.2 获取参数并执行

用户填写这些字段后，插件会收到提交的值。在 strategies/basic_agent.py 中，定义一个 Pydantic 模型来校验传入的参数：

from dify_plugin.entities.agent import AgentInvokeMessage
from dify_plugin.interfaces.agent import AgentModelConfig, AgentStrategy, ToolEntity
from pydantic import BaseModel

class BasicParams(BaseModel):
    maximum_iterations: int
    model: AgentModelConfig
    tools: list[ToolEntity]
    query: str

然后在 _invoke 中解析参数并运行你的策略逻辑：

class BasicAgentAgentStrategy(AgentStrategy):
    def _invoke(self, parameters: dict[str, Any]) -> Generator[AgentInvokeMessage]:
        params = BasicParams(**parameters)

3. 调用模型

调用模型是 Agent 策略的核心。使用 SDK 中的 session.model.llm.invoke() 调用 LLM，处理文本生成、对话等任务。要让 LLM 驱动工具调用，它必须输出与各工具接口匹配的结构化参数，即根据用户指令推导出工具可接受的输入。该方法接受以下参数：

model
prompt_messages
tools
stop
stream

方法签名：

def invoke(
        self,
        model_config: LLMModelConfig,
        prompt_messages: list[PromptMessage],
        tools: list[PromptMessageTool] | None = None,
        stop: list[str] | None = None,
        stream: bool = True,
    ) -> Generator[LLMResultChunk, None, None] | LLMResult:...

完整实现参见下方示例代码中的 Invoke Model 标签页。完成上述设置后，每当用户输入命令，插件就会调用 LLM，根据模型输出构造工具调用参数，并让模型调度已配置的工具来完成复杂任务。

4. 调用工具

模型生成工具参数后，插件必须实际调用这些工具。使用 session.tool.invoke() 发起这些请求。该方法接受以下参数：

provider
tool_name
parameters

方法签名：

 def invoke(
        self,
        provider_type: ToolProviderType,
        provider: str,
        tool_name: str,
        parameters: dict[str, Any],
    ) -> Generator[ToolInvokeMessage, None, None]:...

要让 LLM 自行生成工具调用参数，将模型提取出的工具调用传入你的调用代码：

tool_instances = (
    {tool.identity.name: tool for tool in params.tools} if params.tools else {}
)
for tool_call_id, tool_call_name, tool_call_args in tool_calls:
    tool_instance = tool_instances[tool_call_name]
    self.session.tool.invoke(
        provider_type=ToolProviderType.BUILT_IN,
        provider=tool_instance.identity.provider,
        tool_name=tool_instance.identity.name,
        parameters={**tool_instance.runtime_parameters, **tool_call_args},
    )

现在，你的插件即可自动执行 Function Calling，例如获取当前时间。

5. 创建日志

复杂任务通常需要多个步骤，你需要跟踪每一步的结果，以分析决策并优化策略。SDK 的 create_log_message 和 finish_log_message 可在每次调用前后记录状态，从而加快问题诊断。例如：

在调用模型之前记录一条「开始模型调用」消息，以显示执行进度。
模型响应后记录一条「调用成功」消息，使其输出可端到端追踪。

model_log = self.create_log_message(
            label=f"{params.model.model} Thought",
            data={},
            metadata={"start_at": model_started_at, "provider": params.model.provider},
            status=ToolInvokeMessage.LogMessage.LogStatus.START,
        )
yield model_log
self.session.model.llm.invoke(...)
yield self.finish_log_message(
    log=model_log,
    data={
        "output": response,
        "tool_name": tool_call_names,
        "tool_input": tool_call_inputs,
    },
    metadata={
        "started_at": model_started_at,
        "finished_at": time.perf_counter(),
        "elapsed_time": time.perf_counter() - model_started_at,
        "provider": params.model.provider,
    },
)

设置完成后，工作流日志会显示执行结果：

当任务跨越多轮时，在日志调用中设置 parent 参数，将日志嵌套为层级结构，便于跟踪：

function_call_round_log = self.create_log_message(
    label="Function Call Round1 ",
    data={},
    metadata={},
)
yield function_call_round_log

model_log = self.create_log_message(
    label=f"{params.model.model} Thought",
    data={},
    metadata={"start_at": model_started_at, "provider": params.model.provider},
    status=ToolInvokeMessage.LogMessage.LogStatus.START,
    # add parent log
    parent=function_call_round_log,
)
yield model_log

示例代码

调用模型
处理工具
完整功能代码示例

以下代码为 Agent 策略插件赋予调用模型的能力：

import json
from collections.abc import Generator
from typing import Any, cast

from dify_plugin.entities.agent import AgentInvokeMessage
from dify_plugin.entities.model.llm import LLMModelConfig, LLMResult, LLMResultChunk
from dify_plugin.entities.model.message import (
    PromptMessageTool,
    UserPromptMessage,
)
from dify_plugin.entities.tool import ToolInvokeMessage, ToolParameter, ToolProviderType
from dify_plugin.interfaces.agent import AgentModelConfig, AgentStrategy, ToolEntity
from pydantic import BaseModel

class BasicParams(BaseModel):
    maximum_iterations: int
    model: AgentModelConfig
    tools: list[ToolEntity]
    query: str

class BasicAgentAgentStrategy(AgentStrategy):
    def _invoke(self, parameters: dict[str, Any]) -> Generator[AgentInvokeMessage]:
        params = BasicParams(**parameters)
        chunks: Generator[LLMResultChunk, None, None] | LLMResult = (
            self.session.model.llm.invoke(
                model_config=LLMModelConfig(**params.model.model_dump(mode="json")),
                prompt_messages=[UserPromptMessage(content=params.query)],
                tools=[
                    self._convert_tool_to_prompt_message_tool(tool)
                    for tool in params.tools
                ],
                stop=params.model.completion_params.get("stop", [])
                if params.model.completion_params
                else [],
                stream=True,
            )
        )
        response = ""
        tool_calls = []
        tool_instances = (
            {tool.identity.name: tool for tool in params.tools} if params.tools else {}
        )

        for chunk in chunks:
            # check if there is any tool call
            if self.check_tool_calls(chunk):
                tool_calls = self.extract_tool_calls(chunk)
                tool_call_names = ";".join([tool_call[1] for tool_call in tool_calls])
                try:
                    tool_call_inputs = json.dumps(
                        {tool_call[1]: tool_call[2] for tool_call in tool_calls},
                        ensure_ascii=False,
                    )
                except json.JSONDecodeError:
                    # ensure ascii to avoid encoding error
                    tool_call_inputs = json.dumps(
                        {tool_call[1]: tool_call[2] for tool_call in tool_calls}
                    )
                print(tool_call_names, tool_call_inputs)
            if chunk.delta.message and chunk.delta.message.content:
                if isinstance(chunk.delta.message.content, list):
                    for content in chunk.delta.message.content:
                        response += content.data
                        print(content.data, end="", flush=True)
                else:
                    response += str(chunk.delta.message.content)
                    print(str(chunk.delta.message.content), end="", flush=True)

            if chunk.delta.usage:
                # usage of the model
                usage = chunk.delta.usage

        yield self.create_text_message(
            text=f"{response or json.dumps(tool_calls, ensure_ascii=False)}\n"
        )
        result = ""
        for tool_call_id, tool_call_name, tool_call_args in tool_calls:
            tool_instance = tool_instances[tool_call_name]
            tool_invoke_responses = self.session.tool.invoke(
                provider_type=ToolProviderType.BUILT_IN,
                provider=tool_instance.identity.provider,
                tool_name=tool_instance.identity.name,
                parameters={**tool_instance.runtime_parameters, **tool_call_args},
            )
            if not tool_instance:
                tool_invoke_responses = {
                    "tool_call_id": tool_call_id,
                    "tool_call_name": tool_call_name,
                    "tool_response": f"there is not a tool named {tool_call_name}",
                }
            else:
                # invoke tool
                tool_invoke_responses = self.session.tool.invoke(
                    provider_type=ToolProviderType.BUILT_IN,
                    provider=tool_instance.identity.provider,
                    tool_name=tool_instance.identity.name,
                    parameters={**tool_instance.runtime_parameters, **tool_call_args},
                )
                result = ""
                for tool_invoke_response in tool_invoke_responses:
                    if tool_invoke_response.type == ToolInvokeMessage.MessageType.TEXT:
                        result += cast(
                            ToolInvokeMessage.TextMessage, tool_invoke_response.message
                        ).text
                    elif (
                        tool_invoke_response.type == ToolInvokeMessage.MessageType.LINK
                    ):
                        result += (
                            f"result link: {cast(ToolInvokeMessage.TextMessage, tool_invoke_response.message).text}."
                            + " please tell user to check it."
                        )
                    elif tool_invoke_response.type in {
                        ToolInvokeMessage.MessageType.IMAGE_LINK,
                        ToolInvokeMessage.MessageType.IMAGE,
                    }:
                        result += (
                            "image has been created and sent to user already, "
                            + "you do not need to create it, just tell the user to check it now."
                        )
                    elif (
                        tool_invoke_response.type == ToolInvokeMessage.MessageType.JSON
                    ):
                        text = json.dumps(
                            cast(
                                ToolInvokeMessage.JsonMessage,
                                tool_invoke_response.message,
                            ).json_object,
                            ensure_ascii=False,
                        )
                        result += f"tool response: {text}."
                    else:
                        result += f"tool response: {tool_invoke_response.message!r}."

                tool_response = {
                    "tool_call_id": tool_call_id,
                    "tool_call_name": tool_call_name,
                    "tool_response": result,
                }
        yield self.create_text_message(result)

    def _convert_tool_to_prompt_message_tool(
        self, tool: ToolEntity
    ) -> PromptMessageTool:
        """
        convert tool to prompt message tool
        """
        message_tool = PromptMessageTool(
            name=tool.identity.name,
            description=tool.description.llm if tool.description else "",
            parameters={
                "type": "object",
                "properties": {},
                "required": [],
            },
        )

        parameters = tool.parameters
        for parameter in parameters:
            if parameter.form != ToolParameter.ToolParameterForm.LLM:
                continue

            parameter_type = parameter.type
            if parameter.type in {
                ToolParameter.ToolParameterType.FILE,
                ToolParameter.ToolParameterType.FILES,
            }:
                continue
            enum = []
            if parameter.type == ToolParameter.ToolParameterType.SELECT:
                enum = (
                    [option.value for option in parameter.options]
                    if parameter.options
                    else []
                )

            message_tool.parameters["properties"][parameter.name] = {
                "type": parameter_type,
                "description": parameter.llm_description or "",
            }

            if len(enum) > 0:
                message_tool.parameters["properties"][parameter.name]["enum"] = enum

            if parameter.required:
                message_tool.parameters["required"].append(parameter.name)

        return message_tool

    def check_tool_calls(self, llm_result_chunk: LLMResultChunk) -> bool:
        """
        Check if there is any tool call in llm result chunk
        """
        return bool(llm_result_chunk.delta.message.tool_calls)

    def extract_tool_calls(
        self, llm_result_chunk: LLMResultChunk
    ) -> list[tuple[str, str, dict[str, Any]]]:
        """
        Extract tool calls from llm result chunk

        Returns:
            List[Tuple[str, str, Dict[str, Any]]]: [(tool_call_id, tool_call_name, tool_call_args)]
        """
        tool_calls = []
        for prompt_message in llm_result_chunk.delta.message.tool_calls:
            args = {}
            if prompt_message.function.arguments != "":
                args = json.loads(prompt_message.function.arguments)

            tool_calls.append(
                (
                    prompt_message.id,
                    prompt_message.function.name,
                    args,
                )
            )

        return tool_calls

以下代码调用模型，并向模型所选的工具发送格式规范的请求：

import json
from collections.abc import Generator
from typing import Any, cast

from dify_plugin.entities.agent import AgentInvokeMessage
from dify_plugin.entities.model.llm import LLMModelConfig, LLMResult, LLMResultChunk
from dify_plugin.entities.model.message import (
    PromptMessageTool,
    UserPromptMessage,
)
from dify_plugin.entities.tool import ToolInvokeMessage, ToolParameter, ToolProviderType
from dify_plugin.interfaces.agent import AgentModelConfig, AgentStrategy, ToolEntity
from pydantic import BaseModel

class BasicParams(BaseModel):
    maximum_iterations: int
    model: AgentModelConfig
    tools: list[ToolEntity]
    query: str

class BasicAgentAgentStrategy(AgentStrategy):
    def _invoke(self, parameters: dict[str, Any]) -> Generator[AgentInvokeMessage]:
        params = BasicParams(**parameters)
        chunks: Generator[LLMResultChunk, None, None] | LLMResult = (
            self.session.model.llm.invoke(
                model_config=LLMModelConfig(**params.model.model_dump(mode="json")),
                prompt_messages=[UserPromptMessage(content=params.query)],
                tools=[
                    self._convert_tool_to_prompt_message_tool(tool)
                    for tool in params.tools
                ],
                stop=params.model.completion_params.get("stop", [])
                if params.model.completion_params
                else [],
                stream=True,
            )
        )
        response = ""
        tool_calls = []
        tool_instances = (
            {tool.identity.name: tool for tool in params.tools} if params.tools else {}
        )

        for chunk in chunks:
            # check if there is any tool call
            if self.check_tool_calls(chunk):
                tool_calls = self.extract_tool_calls(chunk)
                tool_call_names = ";".join([tool_call[1] for tool_call in tool_calls])
                try:
                    tool_call_inputs = json.dumps(
                        {tool_call[1]: tool_call[2] for tool_call in tool_calls},
                        ensure_ascii=False,
                    )
                except json.JSONDecodeError:
                    # ensure ascii to avoid encoding error
                    tool_call_inputs = json.dumps(
                        {tool_call[1]: tool_call[2] for tool_call in tool_calls}
                    )
                print(tool_call_names, tool_call_inputs)
            if chunk.delta.message and chunk.delta.message.content:
                if isinstance(chunk.delta.message.content, list):
                    for content in chunk.delta.message.content:
                        response += content.data
                        print(content.data, end="", flush=True)
                else:
                    response += str(chunk.delta.message.content)
                    print(str(chunk.delta.message.content), end="", flush=True)

            if chunk.delta.usage:
                # usage of the model
                usage = chunk.delta.usage

        yield self.create_text_message(
            text=f"{response or json.dumps(tool_calls, ensure_ascii=False)}\n"
        )
        result = ""
        for tool_call_id, tool_call_name, tool_call_args in tool_calls:
            tool_instance = tool_instances[tool_call_name]
            tool_invoke_responses = self.session.tool.invoke(
                provider_type=ToolProviderType.BUILT_IN,
                provider=tool_instance.identity.provider,
                tool_name=tool_instance.identity.name,
                parameters={**tool_instance.runtime_parameters, **tool_call_args},
            )
            if not tool_instance:
                tool_invoke_responses = {
                    "tool_call_id": tool_call_id,
                    "tool_call_name": tool_call_name,
                    "tool_response": f"there is not a tool named {tool_call_name}",
                }
            else:
                # invoke tool
                tool_invoke_responses = self.session.tool.invoke(
                    provider_type=ToolProviderType.BUILT_IN,
                    provider=tool_instance.identity.provider,
                    tool_name=tool_instance.identity.name,
                    parameters={**tool_instance.runtime_parameters, **tool_call_args},
                )
                result = ""
                for tool_invoke_response in tool_invoke_responses:
                    if tool_invoke_response.type == ToolInvokeMessage.MessageType.TEXT:
                        result += cast(
                            ToolInvokeMessage.TextMessage, tool_invoke_response.message
                        ).text
                    elif (
                        tool_invoke_response.type == ToolInvokeMessage.MessageType.LINK
                    ):
                        result += (
                            f"result link: {cast(ToolInvokeMessage.TextMessage, tool_invoke_response.message).text}."
                            + " please tell user to check it."
                        )
                    elif tool_invoke_response.type in {
                        ToolInvokeMessage.MessageType.IMAGE_LINK,
                        ToolInvokeMessage.MessageType.IMAGE,
                    }:
                        result += (
                            "image has been created and sent to user already, "
                            + "you do not need to create it, just tell the user to check it now."
                        )
                    elif (
                        tool_invoke_response.type == ToolInvokeMessage.MessageType.JSON
                    ):
                        text = json.dumps(
                            cast(
                                ToolInvokeMessage.JsonMessage,
                                tool_invoke_response.message,
                            ).json_object,
                            ensure_ascii=False,
                        )
                        result += f"tool response: {text}."
                    else:
                        result += f"tool response: {tool_invoke_response.message!r}."

                tool_response = {
                    "tool_call_id": tool_call_id,
                    "tool_call_name": tool_call_name,
                    "tool_response": result,
                }
        yield self.create_text_message(result)

    def _convert_tool_to_prompt_message_tool(
        self, tool: ToolEntity
    ) -> PromptMessageTool:
        """
        convert tool to prompt message tool
        """
        message_tool = PromptMessageTool(
            name=tool.identity.name,
            description=tool.description.llm if tool.description else "",
            parameters={
                "type": "object",
                "properties": {},
                "required": [],
            },
        )

        parameters = tool.parameters
        for parameter in parameters:
            if parameter.form != ToolParameter.ToolParameterForm.LLM:
                continue

            parameter_type = parameter.type
            if parameter.type in {
                ToolParameter.ToolParameterType.FILE,
                ToolParameter.ToolParameterType.FILES,
            }:
                continue
            enum = []
            if parameter.type == ToolParameter.ToolParameterType.SELECT:
                enum = (
                    [option.value for option in parameter.options]
                    if parameter.options
                    else []
                )

            message_tool.parameters["properties"][parameter.name] = {
                "type": parameter_type,
                "description": parameter.llm_description or "",
            }

            if len(enum) > 0:
                message_tool.parameters["properties"][parameter.name]["enum"] = enum

            if parameter.required:
                message_tool.parameters["required"].append(parameter.name)

        return message_tool

    def check_tool_calls(self, llm_result_chunk: LLMResultChunk) -> bool:
        """
        Check if there is any tool call in llm result chunk
        """
        return bool(llm_result_chunk.delta.message.tool_calls)

    def extract_tool_calls(
        self, llm_result_chunk: LLMResultChunk
    ) -> list[tuple[str, str, dict[str, Any]]]:
        """
        Extract tool calls from llm result chunk

        Returns:
            List[Tuple[str, str, Dict[str, Any]]]: [(tool_call_id, tool_call_name, tool_call_args)]
        """
        tool_calls = []
        for prompt_message in llm_result_chunk.delta.message.tool_calls:
            args = {}
            if prompt_message.function.arguments != "":
                args = json.loads(prompt_message.function.arguments)

            tool_calls.append(
                (
                    prompt_message.id,
                    prompt_message.function.name,
                    args,
                )
            )

        return tool_calls

一个完整示例，涵盖模型调用、工具处理和多轮日志记录：

import json
import time
from collections.abc import Generator
from typing import Any, cast

from dify_plugin.entities.agent import AgentInvokeMessage
from dify_plugin.entities.model.llm import LLMModelConfig, LLMResult, LLMResultChunk
from dify_plugin.entities.model.message import (
    PromptMessageTool,
    UserPromptMessage,
)
from dify_plugin.entities.tool import ToolInvokeMessage, ToolParameter, ToolProviderType
from dify_plugin.interfaces.agent import AgentModelConfig, AgentStrategy, ToolEntity
from pydantic import BaseModel

class BasicParams(BaseModel):
    maximum_iterations: int
    model: AgentModelConfig
    tools: list[ToolEntity]
    query: str

class BasicAgentAgentStrategy(AgentStrategy):
    def _invoke(self, parameters: dict[str, Any]) -> Generator[AgentInvokeMessage]:
        params = BasicParams(**parameters)
        function_call_round_log = self.create_log_message(
            label="Function Call Round1 ",
            data={},
            metadata={},
        )
        yield function_call_round_log
        model_started_at = time.perf_counter()
        model_log = self.create_log_message(
            label=f"{params.model.model} Thought",
            data={},
            metadata={"start_at": model_started_at, "provider": params.model.provider},
            status=ToolInvokeMessage.LogMessage.LogStatus.START,
            parent=function_call_round_log,
        )
        yield model_log
        chunks: Generator[LLMResultChunk, None, None] | LLMResult = (
            self.session.model.llm.invoke(
                model_config=LLMModelConfig(**params.model.model_dump(mode="json")),
                prompt_messages=[UserPromptMessage(content=params.query)],
                tools=[
                    self._convert_tool_to_prompt_message_tool(tool)
                    for tool in params.tools
                ],
                stop=params.model.completion_params.get("stop", [])
                if params.model.completion_params
                else [],
                stream=True,
            )
        )
        response = ""
        tool_calls = []
        tool_instances = (
            {tool.identity.name: tool for tool in params.tools} if params.tools else {}
        )
        tool_call_names = ""
        tool_call_inputs = ""
        for chunk in chunks:
            # check if there is any tool call
            if self.check_tool_calls(chunk):
                tool_calls = self.extract_tool_calls(chunk)
                tool_call_names = ";".join([tool_call[1] for tool_call in tool_calls])
                try:
                    tool_call_inputs = json.dumps(
                        {tool_call[1]: tool_call[2] for tool_call in tool_calls},
                        ensure_ascii=False,
                    )
                except json.JSONDecodeError:
                    # ensure ascii to avoid encoding error
                    tool_call_inputs = json.dumps(
                        {tool_call[1]: tool_call[2] for tool_call in tool_calls}
                    )
                print(tool_call_names, tool_call_inputs)
            if chunk.delta.message and chunk.delta.message.content:
                if isinstance(chunk.delta.message.content, list):
                    for content in chunk.delta.message.content:
                        response += content.data
                        print(content.data, end="", flush=True)
                else:
                    response += str(chunk.delta.message.content)
                    print(str(chunk.delta.message.content), end="", flush=True)

            if chunk.delta.usage:
                # usage of the model
                usage = chunk.delta.usage

        yield self.finish_log_message(
            log=model_log,
            data={
                "output": response,
                "tool_name": tool_call_names,
                "tool_input": tool_call_inputs,
            },
            metadata={
                "started_at": model_started_at,
                "finished_at": time.perf_counter(),
                "elapsed_time": time.perf_counter() - model_started_at,
                "provider": params.model.provider,
            },
        )
        yield self.create_text_message(
            text=f"{response or json.dumps(tool_calls, ensure_ascii=False)}\n"
        )
        result = ""
        for tool_call_id, tool_call_name, tool_call_args in tool_calls:
            tool_instance = tool_instances[tool_call_name]
            tool_invoke_responses = self.session.tool.invoke(
                provider_type=ToolProviderType.BUILT_IN,
                provider=tool_instance.identity.provider,
                tool_name=tool_instance.identity.name,
                parameters={**tool_instance.runtime_parameters, **tool_call_args},
            )
            if not tool_instance:
                tool_invoke_responses = {
                    "tool_call_id": tool_call_id,
                    "tool_call_name": tool_call_name,
                    "tool_response": f"there is not a tool named {tool_call_name}",
                }
            else:
                # invoke tool
                tool_invoke_responses = self.session.tool.invoke(
                    provider_type=ToolProviderType.BUILT_IN,
                    provider=tool_instance.identity.provider,
                    tool_name=tool_instance.identity.name,
                    parameters={**tool_instance.runtime_parameters, **tool_call_args},
                )
                result = ""
                for tool_invoke_response in tool_invoke_responses:
                    if tool_invoke_response.type == ToolInvokeMessage.MessageType.TEXT:
                        result += cast(
                            ToolInvokeMessage.TextMessage, tool_invoke_response.message
                        ).text
                    elif (
                        tool_invoke_response.type == ToolInvokeMessage.MessageType.LINK
                    ):
                        result += (
                            f"result link: {cast(ToolInvokeMessage.TextMessage, tool_invoke_response.message).text}."
                            + " please tell user to check it."
                        )
                    elif tool_invoke_response.type in {
                        ToolInvokeMessage.MessageType.IMAGE_LINK,
                        ToolInvokeMessage.MessageType.IMAGE,
                    }:
                        result += (
                            "image has been created and sent to user already, "
                            + "you do not need to create it, just tell the user to check it now."
                        )
                    elif (
                        tool_invoke_response.type == ToolInvokeMessage.MessageType.JSON
                    ):
                        text = json.dumps(
                            cast(
                                ToolInvokeMessage.JsonMessage,
                                tool_invoke_response.message,
                            ).json_object,
                            ensure_ascii=False,
                        )
                        result += f"tool response: {text}."
                    else:
                        result += f"tool response: {tool_invoke_response.message!r}."

                tool_response = {
                    "tool_call_id": tool_call_id,
                    "tool_call_name": tool_call_name,
                    "tool_response": result,
                }
        yield self.create_text_message(result)

    def _convert_tool_to_prompt_message_tool(
        self, tool: ToolEntity
    ) -> PromptMessageTool:
        """
        convert tool to prompt message tool
        """
        message_tool = PromptMessageTool(
            name=tool.identity.name,
            description=tool.description.llm if tool.description else "",
            parameters={
                "type": "object",
                "properties": {},
                "required": [],
            },
        )

        parameters = tool.parameters
        for parameter in parameters:
            if parameter.form != ToolParameter.ToolParameterForm.LLM:
                continue

            parameter_type = parameter.type
            if parameter.type in {
                ToolParameter.ToolParameterType.FILE,
                ToolParameter.ToolParameterType.FILES,
            }:
                continue
            enum = []
            if parameter.type == ToolParameter.ToolParameterType.SELECT:
                enum = (
                    [option.value for option in parameter.options]
                    if parameter.options
                    else []
                )

            message_tool.parameters["properties"][parameter.name] = {
                "type": parameter_type,
                "description": parameter.llm_description or "",
            }

            if len(enum) > 0:
                message_tool.parameters["properties"][parameter.name]["enum"] = enum

            if parameter.required:
                message_tool.parameters["required"].append(parameter.name)

        return message_tool

    def check_tool_calls(self, llm_result_chunk: LLMResultChunk) -> bool:
        """
        Check if there is any tool call in llm result chunk
        """
        return bool(llm_result_chunk.delta.message.tool_calls)

    def extract_tool_calls(
        self, llm_result_chunk: LLMResultChunk
    ) -> list[tuple[str, str, dict[str, Any]]]:
        """
        Extract tool calls from llm result chunk

        Returns:
            List[Tuple[str, str, Dict[str, Any]]]: [(tool_call_id, tool_call_name, tool_call_args)]
        """
        tool_calls = []
        for prompt_message in llm_result_chunk.delta.message.tool_calls:
            args = {}
            if prompt_message.function.arguments != "":
                args = json.loads(prompt_message.function.arguments)

            tool_calls.append(
                (
                    prompt_message.id,
                    prompt_message.function.name,
                    args,
                )
            )

        return tool_calls

6. 调试插件

声明文件和实现代码完成后，验证插件能否正常运行。Dify 支持远程调试：前往 插件管理 获取调试密钥和远程服务器地址。

在插件项目中，将 .env.example 复制为 .env，并填入远程服务器地址和调试密钥。

INSTALL_METHOD=remote
REMOTE_INSTALL_URL=debug.dify.ai:5003
REMOTE_INSTALL_KEY=********-****-****-****-************

然后运行：

python -m main

插件会出现在你的工作空间中，团队成员也可以访问。

打包插件（可选）

一切正常后，运行以下命令打包你的插件：

# Replace ./basic_agent/ with your actual plugin project path.

dify plugin package ./basic_agent/

当前文件夹中会出现一个名为 basic_agent.difypkg（与你的插件名称匹配）的文件。这就是你的最终插件包。恭喜！你已经开发、测试并打包了你的 Agent 策略插件。

发布插件（可选）

你现在可以将插件包上传到 Dify 插件仓库。在此之前，确保它符合插件发布指南。一旦获得批准，你的代码将合并到主分支，插件将自动在 Dify 市场上线。

进一步探索

复杂任务通常需要多轮思考和工具调用，会重复「模型调用 → 工具使用」的循环，直到任务结束或达到迭代上限。在此过程中，妥善管理提示词至关重要。参见完整的 Function Calling 实现，了解让模型调用外部工具并处理其输出的标准化方法。

​前置条件

​1. 初始化插件模板

​2. 开发插件

​2.1 定义参数

​2.2 获取参数并执行

​3. 调用模型

​4. 调用工具

​5. 创建日志

​示例代码

​6. 调试插件

​打包插件（可选）

​发布插件（可选）

​进一步探索

前置条件

1. 初始化插件模板

2. 开发插件

2.1 定义参数

2.2 获取参数并执行

3. 调用模型

4. 调用工具

5. 创建日志

示例代码

6. 调试插件

打包插件（可选）

发布插件（可选）

进一步探索