Generate a conversation

Request syntax

POST /web-search-agent/chat/completions HTTP/1.1

Request parameters

Note: If you provide dynamic parameters in the request, they override the corresponding status values in the application configuration.

Parameter	Type	Required	Description
stream	bool	Yes	Must be set to `true`. The current version only supports streaming responses. The request will fail if this parameter is set to `false` or is omitted.
input	object	Yes	Input fields.
input.request_id	str	No	A user-defined request ID.
input.messages	array[object]	Yes	A list of conversation messages.
input.messages.[].role	str	Yes	The role of the message sender. Valid values: `user` and `assistant`.
input.messages.[].content	str	Yes	The content of the message.
parameters	object	Yes	Configuration parameters.
parameters.agent_options	object	Yes	Agent-specific parameters.
parameters.agent_options.agent_id	string	Yes	The application ID.
parameters.agent_options.agent_version	string	Yes	The application version.
parameters.agent_options.session_knowledge	string	No	Specifies the session-level knowledge to use.
parameters.agent_options.system_prompt	string	No	Specifies the system prompt.
parameters.agent_options.agent_policy	string	No	The execution policy. `standard`: The default policy (recommended). `agentic`: Forces the agent to use an iterative search-and-think process. `turbo`: Turbo mode.
parameters.agent_options.forced_search	bool	No	Specifies whether to force a search. If this is set to `true`, the `agent_policy` parameter defaults to `standard`.
parameters.agent_options.enable_citation	bool	No	Specifies whether to include citations in the response.
parameters.agent_options.enable_text_image_mixed	bool	No	Specifies whether to enable text-image mixed generation.
parameters.agent_options.enable_lemma	bool	No	Specifies whether to include encyclopedia entries in the response.
parameters.agent_options.related_video	bool	No	Specifies whether to include related videos in the response.
parameters.agent_options.enable_rec_question	bool	No	Specifies whether to include related questions in the response.
parameters.agent_options.show_step_info	bool	No	Specifies whether to include tool call status information in the response. The default value is `false`.
parameters.agent_options.location	object	No	Location information for the request.
parameters.agent_options.location.address	string	No	The specific address.
parameters.agent_options.location.province	string	No	The province.
parameters.agent_options.location.city	string	No	The city.
parameters.agent_options.location.district	string	No	The district or county.
parameters.agent_options.location.longitude	string	No	The longitude, accurate to 6 decimal places.
parameters.agent_options.location.latitude	string	No	The latitude, accurate to 6 decimal places.

Response parameters

Parameter	Type	Required	Description
request_id	str	Yes	The request ID from the DashScope platform.
code	str	Yes	The status code. `200` indicates success.
message	str	Yes	The status message.
output	object	Yes	The output object.
output.request_id	str	No	A custom request ID defined by your application.
output.choices	array[object]	Yes	A list of completion choices generated by the model.
output.choices.[].finish_reason	str	Yes	The finish reason. A value of `stop` indicates the final chunk.
output.choices.[].message	object	Yes	The message object.
output.choices.[].message.role	str	Yes	The role of the message author. Valid values: `user`, `assistant`, and `tool`.
output.choices.[].message.content	str \| array[object]	Yes	The text generated by the model, or the output from a tool.
output.choices.[].message.reasoning_content	str	No	The model's thought process or reasoning steps.
output.choices.[].message.tool_calls	array[object]	No	The tool calls requested by the model.
output.choices.[].message.tool_calls[0].arguments	dict[str,object]	No	The arguments to pass to the tool function.
output.choices.[].message.tool_calls[0].name	str	No	The name of the tool to call.
output.choices.[].message.additional_kwargs.extra_json	Any	No	Additional structured data associated with a tool call.
output.choices.[].message.extra	dict	No	Contains details about the current execution step.
output.choices.[].message.extra.group	str	No	The execution phase.
output.choices.[].message.extra.step_change	str	No	The step change event.
output.choices.[].message.extra.step	str	No	The current step.
output.choices.[].message.response_metadata	dict	No	Details about the model invocation for the request.
output.usage	object	No	Usage statistics.
output.usage.input_tokens	int	No	The number of input tokens.
output.usage.output_tokens	int	No	The number of output tokens.
output.usage.total_tokens	int	No	The total number of tokens.

Execution stage enumeration

Execution stage (`group`)	Description	Description
planning	planning	Associated with the `plan` model. This indicates the system is in the task planning stage, which includes `planning start` and `planning end` events.
generating	generating	Associated with the `generation` model. This indicates the system is in the result generation stage, which includes `generation start` and `generation end` events.

Current step (`step`)	Description
planning	planning
generating	generating
tool_calling	tool calling
tool_calling_{tool_name}	A tool call is in progress. The specific tool is identified by its name.

Due to model limitations, the step_change value may be absent. Use the persistent step flag whenever possible.
For an empty packet, the step, step_change, and group fields may be absent.
The plan and generation processes each consist of a *_start event and a *_end event.
A tool_call consists of three events: tool_call_start, tool_calling, and tool_return.
tool_call_start indicates the beginning of a tool call. The system emits the tool_calling event after gathering the complete tool call parameters; this event contains the parameters. tool_return contains the structured result from the tool.

Value of `step`	Step change event (`step_change`)	Event name	Description
`planning`	plan_start	planning start	The `step` state changes to `planning`, which indicates the start of the corresponding state (including the current package).
`planning`	(empty)	planning	Indicates the system is reasoning or performing tool calls.
`planning`	plan_end	planning end	When the `step` starts to change to another state, an event that occurs while the `step` is still `planning` indicates the end of the planning state (including the current package).
`generating`	generation_start	generation start	Similar to the `plan` events.
`generating`	(empty)	generating	Indicates the system is generating output.
`generating`	generation_end	generation end	Similar to the `plan` events.
`tool_calling_{tool_name}`	tool_call_start	tool call start	Indicates the start of a tool call.
`tool_calling_{tool_name}`	tool_calling	tool calling	Contains the specific parameters and name for the tool call. The `step` state changes to `tool_calling_{tool_name}`.
`tool_calling_{tool_name}`	tool_return	tool return	The response contains the tool return information, and the `step` begins to change to other states. However, when the event occurs, the `step` is still `tool_calling_{tool_name}`.

Step value and tool name mapping

When a tool is called, the ["extra"]["step"] field contains a value, such as tool_calling_xx, that identifies the tool used. The following tables map each step value to its corresponding tool name.

Text QA

Step value	Tool name
tool_calling_search	web search
tool_calling_visit	web page reading
tool_calling_video_search	video search
tool_calling_lemma_search	Baidu entry
tool_calling_query_suggesting	follow-up query

Multimodal QA

In addition to the text QA tools, this mode adds text-to-image search and reverse image search.

Step value	Tool name
tool_calling_image_search	text-to-image search
tool_calling_image_to_image_search	reverse image search

Local service POI tools

Step value	Tool name
tool_calling_poi_search	keyword search
tool_calling_around_search	nearby search

Tool call status

Parameters

The status of a tool call is in the ["extra"]["step_change"] field of the message. Detailed information about the call is in the ["extra"]["step_info"] field. The following table maps tool call statuses to their corresponding status information.

Tool call status	Description	Status information (`step_info`)
tool_call_start	Start tool call	Starting to call the [tool_name] tool.
tool_calling	Calling tool	Calling the [tool_name] tool.
tool_return	Tool call completed	Call to the [tool_name] tool completed: [result_details].

For example, a call to the web search tool progresses through the following states:

"step_change": "tool_call_start", "step": "tool_calling_search","step_info": "Starting to call the web search tool"
"step_change": "tool_calling", "step": "tool_calling_search","step_info": "Calling the web search tool"
"step_change": "tool_return", "step": "tool_calling_search",  "step_info": "Call to the web search tool completed: retrieved 10 web pages"

Rich media message protocol

When rich media is enabled, the model interleaves text with images by embedding them in the message body with the HTML <img> tag, as shown in the example below:

<img src=\"xxx\" data-type=\"image\" data-url=\"xxx\" data-title=\"Hangzhou after the typhoon: Blue sky and white clouds as refreshing as a comic book️\" alt=\"Hangzhou clear day blue sky\" width=\"1080\" height=\"1410\">

The attributes in this tag are defined as follows:

data-type: Specifies the data type. A value of image indicates image data.
src: The URL of the image.
data-url: The URL of the image's source content page.
data-title: The image title.
width/height: The image's width and height.

For messages containing an image, the additional_kwargs field contains the following two fields:

data_type: For a rich media message containing an image, this value is set to image.
data_json: A JSON array of all images related to the content. Only one of these images is displayed in the message body.
- In data_json, each image object contains the following fields:
  - idx: The image ID.
  - url: The source URL of the image's content page.
  - title: The image title.
  - published: The publication date of the source content.
  - image_info["url"]: The URL of the image file.
  - image_info["width"]: The image width.
  - image_info["height"]: The image height.

{"idx": 15, "query": "Hangzhou clear day blue sky", "url": "xxx", "title": "xx", "published": "2024-11-04 03:04:04", "image_info": {"url": "xxx", "width": 1080, "height": 1410}}

The following example shows a rich media message delivered in three message packets:

data: {
    "status_code": 200,
    "code": "",
    "message": "",
    "output": {
        "choices": [
            {
                "finish_reason": "",
                "message": {
                    "content": "Sightseeing.\n\n",
                    "additional_kwargs": {},
                    "response_metadata": {},
                    "type": "ai",
                    "name": null,
                    "id": "run--019e63e4-e728-7421-b3e5-57b408d6d4b0",
                    "example": false,
                    "tool_calls": [],
                    "invalid_tool_calls": [],
                    "usage_metadata": null,
                    "tool_call_chunks": [],
                    "reasoning_content": "",
                    "role": "assistant",
                    "extra": {
                        "group": "generating",
                        "step_change": "",
                        "step": "generating"
                    }
                }
            }
        ]
    },
    "usage": null,
    "request_id": "chenwen-test-web-search-01"
}

data: {
    "status_code": 200,
    "code": "",
    "message": "",
    "output": {
        "choices": [
            {
                "finish_reason": "",
                "message": {
                    "content": "<img src=\"http://miaobi-lite.bj.bcebos.com/miaobi/5mao/b%275Y%2Bw6aOO6L%2BH5ZCO55qE5Zu%2B54mHXzE3MzA2NTY4MTMuMTQ0MDA1NQ%3D%3D%27/0.png\" data-type=\"image\" data-url=\"http://mbd.baidu.com/newspage/data/dtlandingsuper?nid=dt_4158884509151638702\" data-title=\"Hangzhou after the typhoon: Blue sky and white clouds as refreshing as a comic book\" alt=\"Hangzhou clear day blue sky\" width=\"1080\" height=\"1410\">\n\n\n",
                    "additional_kwargs": {
                        "data_type": "image",
                        "data_json": [
                            {
                                "idx": 15,
                                "query": "Hangzhou clear day blue sky",
                                "url": "http://mbd.baidu.com/newspage/data/dtlandingsuper?nid=dt_4158884509151638702",
                                "title": "Hangzhou after the typhoon: Blue sky and white clouds as refreshing as a comic book",
                                "published": "2024-11-04 03:04:04",
                                "image_info": {
                                    "url": "http://miaobi-lite.bj.bcebos.com/miaobi/5mao/b%275Y%2Bw6aOO6L%2BH5ZCO55qE5Zu%2B54mHXzE3MzA2NTY4MTMuMTQ0MDA1NQ%3D%3D%27/0.png",
                                    "width": 1080,
                                    "height": 1410
                                }
                            },
                            {
                                "idx": 16,
                                "query": "Hangzhou clear day blue sky",
                                "url": "http://m.dianping.com/ugcdetail/175828244?sceneType=0&bizType=29&msource=baiduappugc",
                                "title": "The sky in Hangzhou is so beautiful!",
                                "published": "2023-07-26 00:00:00",
                                "image_info": {
                                    "url": "http://qcloud.dpfile.com/pc/VWohABccM5j2sRMTT4YdH7qapT46U8bLlM3Wp-xKeMm3OVoihIkmurvV3052Y9Xt.jpg",
                                    "width": 2048,
                                    "height": 2731
                                }
                            },
                            {
                                "idx": 17,
                                "query": "Hangzhou clear day blue sky",
                                "url": "http://m.dianping.com/ugcdetail/175964222?sceneType=0&bizType=29&msource=baiduappugc",
                                "title": "The blue sky and white clouds in Hangzhou are beautiful, but you always get a tan",
                                "published": "2023-07-27 00:00:00",
                                "image_info": {
                                    "url": "http://qcloud.dpfile.com/pc/6ScKLghe1ZcE15OpzbomPigY1VkO6o_UTx9z6UB_BoNtf5OGAsnbF-AFIAJjozRl.jpg",
                                    "width": 2048,
                                    "height": 2731
                                }
                            }
                        ]
                    },
                    "response_metadata": {},
                    "type": "ai",
                    "name": null,
                    "id": "run--019e63e4-e728-7421-b3e5-57b408d6d4b0",
                    "example": false,
                    "tool_calls": [],
                    "invalid_tool_calls": [],
                    "usage_metadata": null,
                    "tool_call_chunks": [],
                    "reasoning_content": "",
                    "role": "assistant",
                    "extra": {
                        "group": "generating",
                        "step_change": "",
                        "step": "generating"
                    }
                }
            }
        ]
    },
    "usage": null,
    "request_id": "chenwen-test-web-search-01"
}

data: {
    "status_code": 200,
    "code": "",
    "message": "",
    "output": {
        "choices": [
            {
                "finish_reason": "",
                "message": {
                    "content": "**Summary**:",
                    "additional_kwargs": {},
                    "response_metadata": {},
                    "type": "ai",
                    "name": null,
                    "id": "run--019e63e4-e728-7421-b3e5-57b408d6d4b0",
                    "example": false,
                    "tool_calls": [],
                    "invalid_tool_calls": [],
                    "usage_metadata": null,
                    "tool_call_chunks": [],
                    "reasoning_content": "",
                    "role": "assistant",
                    "extra": {
                        "group": "generating",
                        "step_change": "",
                        "step": "generating"
                    }
                }
            }
        ]
    },
    "usage": null,
    "request_id": "chenwen-test-web-search-01"
}

Render local life POI cards

When local life is enabled, the model returns location-based Point of Interest (POI) search results. If rich text and image display is also enabled, the POI search results include images. Images in the message body use the standard HTML image format, as shown in the following example:

<img src=\"https://aos-comment.amap.com/B0FFGD1PB5/comment/content_media_external_file_9739_ss__1749454867961_64014666.jpg\" data-type=\"poi\" data-url=\"https://www.amap.com/detail/B0FFGD1PB5\" data-title=\"Wu山景区吴山广场-吴山文化公园\" alt=\"Wu山景区吴山广场-吴山文化公园\" width=\"400\" height=\"auto\"/>\n

The attributes in this tag are defined as follows:

data-type: The data type. A value of poi indicates a map card.
src: The URL of the first image for the card.
data-url: The Amap URL that corresponds to the card.
data-title: The card title.
width/height: The width and height of the image.

In model messages that contain images, the additional_kwargs field includes the following fields:

data_type: For map card images, the value is poi.
data_json: A JSON object of all related map cards. Although the message body displays only one card, this field contains all relevant cards.

In data_json, each map card uses the following fields:

Field	Type	Description
name	string	The place name.
id	string	The unique identifier for the place.
distance	string	The distance from the center point, in meters. This field is returned only for nearby searches.
location	string	The longitude and latitude of the POI.
type	string	The POI category.
typecode	string	The category code of the POI.
pname	string	The province where the POI is located.
cityname	string	The city where the POI is located.
adname	string	The district where the POI is located.
address	string	The detailed address of the POI.
photos	array	Contains information about the POI images.
photos[].title	string	A description of the POI image.
photos[].url	string	The download URL for the POI image.
business	object	If available, contains the business information for the POI.

Custom fields in business

Field	Type	Description
business_area	string	The business area where the POI is located.
opentime_today	string	Today's business hours for the POI, such as 08:30-17:30, 08:30-09:00, 12:00-13:30, or 09:00-13:00.
opentime_week	string	A text description of the POI's weekly business hours. For example: "Monday to Friday: 08:30-17:30 (extended service hours: 08:30-09:00; 12:00-13:30); Saturday extended service hours: 09:00-13:00 (excluding legal holidays)".
tel	string	The contact number for the POI.
tag	string	Highlights of the POI. This field is currently returned only for dining POIs.
rating	string	The rating of the POI. This field is currently returned only for POIs in the dining, hotel, attraction, and cinema categories.
cost	string	The average spend at the POI. This field is currently returned only for POIs in the dining, hotel, attraction, and cinema categories.
parking_type	string	The parking type (underground, ground-level, or roadside). This field is currently returned only for parking lot POIs.

The following example shows the response when local life and rich text and image display are enabled.

"additional_kwargs": {
  "data_type": "poi",
  "data_json": [
    {
      "address": "Siyi Pavilion, Wushan Scenic Area (150m walk from Exit D of Wushan Square Metro Station)",
      "distance": "352",
      "business": {
        "opentime_today": "Open 24 hours",
        "keytag": "City Park",
        "rating": "3.8",
        "business_area": "Wushan",
        "tel": "0571-8703****",
        "rectag": "City Park",
        "opentime_week": "Monday to Sunday 00:00-24:00"
      },
      "pcode": "330000",
      "adcode": "330102",
      "pname": "Zhejiang Province",
      "cityname": "Hangzhou",
      "type": "Scenic Spot; Park and Square; Park",
      "photos": [
        {
          "title": "",
          "url": "https://aos-comment.amap.com/B0FFGD1PB5/comment/content_media_external_file_9739_ss__1749454867961_64014666.jpg"
        },
        {
          "title": "",
          "url": "https://aos-comment.amap.com/B0FFGD1PB5/comment/content_media_external_images_media_1000008441_ss__1751303656358_97699056.jpg"
        },
        {
          "title": "",
          "url": "https://aos-comment.amap.com/B0FFGD1PB5/comment/content_media_external_file_9746_ss__1749454867953_49866303.jpg"
        }
      ],
      "typecode": "110101",
      "adname": "Shangcheng District",
      "citycode": "0571",
      "navi": {
        "navi_poiid": "H51F022002_375744",
        "entr_location": "120.163399,30.239046",
        "gridcode": "4520218310"
      },
      "name": "Wushan Scenic Area Wushan Square - Wushan Cultural Park",
      "indoor": {
        "indoor_map": "0"
      },
      "location": "120.163789,30.238795",
      "id": "B0FFGD1PB5",
      "distance_text": "352m from Wushan Xiaoputuo Wushan Scenic Area, Ziyang Subdistrict",
      "from": "Wushan Xiaoputuo Wushan Scenic Area, Ziyang Subdistrict, Shangcheng District, Hangzhou, Zhejiang Province"
    }
  ]
}

Multimodal image Q&A

The Web Search Agent multimodal API lets you include images in your conversations. Provide an image URL with your question, and the Agent will interpret the image, call the necessary tools, and generate a response.

Request parameters

Parameter	Type	Required	Description
input	object	Yes	The request's input object.
input.messages	array	Yes	The list of messages in the conversation.
input.messages[].role	string	Yes	The message sender's role. The value must be `user`.
input.messages[].content	array	Yes	An array of content parts, which can be text or images.
input.messages[].content[].type	string	No	The type of the content part. For images, set this to `image_url`. The following describes the supported formats for the image URL: 1. URL format (Recommended): https://example.com/image.jpg 2. Base64 format: `data:<content_type>;base64,<base64_data>`, where `content_type` is the image's MIME type (e.g., `image/jpeg`).
input.messages[].content[].image_url	object	Conditional	An object containing the image URL. Required if `type` is `image_url`.

Examples

Sample requests

Text request

{
    "input": {
        "messages": [
            {
                "role": "user",
                "content": "What is the current date?"
            }
        ]
    },
    "stream": true,
    "parameters": {
        "agent_options": {
            "agent_id": "aid-xxx",
            "agent_version": "beta"
        }
    }
}

Multimodal request

{
    "input": {
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "image_url": {
                            "url": "http://other-general-huabei2.oss-cn-beijing.aliyuncs.com/upload/36e553b350e98ba81f6b33b08833a784.png"
                        },
                        "type": "image_url"
                    },
                    {
                        "text": "What animal is this, and in which regions does it typically live?",
                        "type": "text"
                    }
                ]
            }
        ]
    },
    "stream": true,
    "parameters": {
        "agent_options": {
            "agent_version": "beta",
            "agent_id": "aid-xxx"
        }
    }
}

Sample response

data: {
    "status_code": 200,
    "code": "",
    "message": "",
    "output": {
        "choices": [
            {
                "finish_reason": "",
                "message": {
                    "content": "xxx",
                    "additional_kwargs": {},
                    "response_metadata": {
                        "headers": {
                            "vary": "Origin",
                            "x-request-id": "ca7a41ad-3994-9dcf-adf6-f7aa56bec62b",
                            "content-type": "text/event-stream;charset=UTF-8",
                            "x-dashscope-call-gateway": "true",
                            "req-cost-time": "508",
                            "req-arrive-time": "1773800485527",
                            "resp-start-time": "1773800486035",
                            "x-envoy-upstream-service-time": "506",
                            "date": "Wed, 18 Mar 2026 02:21:25 GMT",
                            "server": "istio-envoy",
                            "transfer-encoding": "chunked"
                        }
                    },
                    "type": "ai",
                    "name": null,
                    "id": "run--019cfebf-7194-78b3-ad12-c3df6b6423b1",
                    "example": false,
                    "tool_calls": [],
                    "invalid_tool_calls": [],
                    "usage_metadata": null,
                    "tool_call_chunks": [],
                    "reasoning_content": "",
                    "role": "assistant",
                    "extra": {
                        "group": "generating",
                        "step_change": "generation_start",
                        "step": "generating"
                    }
                }
            }
        ]
    },
    "usage": null,
    "request_id": "xxxx-xxxx"
}

Code sample

# coding=utf-8

import os
import json
import requests

chat_completions_url = 'https://dashscope.aliyuncs.com/api/v2/apps/web-search-agent/chat/completions'

headers = {
    'Authorization': f'Bearer {os.getenv("DASHSCOPE_API_KEY", "")}',  # Configure the API key.
    'Content-Type': 'application/json'
}

if __name__ == "__main__":
    params = {
        "input": {
            "messages": [{"role": "user", "content": "What are the mainstream multimodal models in China? Please analyze their performance and effectiveness."}]  # Set the request message.
        },
        "parameters": {
            "agent_options": {  # Set agent options.
                "agent_id": "${agent_id}",  # The application ID, found on the Application Management page (e.g., aid-8fd***e00).
                "agent_version": "${agent_version}"  # The application version. Use 'beta' for the beta version or 'release' for the release version.
            }
        },
        "stream": True
    }

    response = requests.post(chat_completions_url, headers=headers, json=params, stream=True)

    resultlist = []
    stage = ''
    action = ''
    content = ''
    reasoning_content = ''
    for chunk in response.iter_lines():
        if chunk:
            chunk_str = chunk.decode('utf-8').strip()
            if chunk_str.startswith('data:'):
                json_str = chunk_str[len('data:'):].strip()
                try:
                    obj = json.loads(json_str)
                    # Check for a service error.
                    if obj.get('code') != '200':
                        print("Service error:", obj)
                    # Extract the message body.
                    msg = obj.get('output', {}).get('choices', [{}])[0].get('message', {})
                    extra_flags = msg.get('extra', {})  # Get the 'extra' field, which contains model state flags.

                    if stage != extra_flags.get('group', ''):  # Get the current model stage.
                        print(f"agent stage: {extra_flags.get('group', '')}")
                    stage = extra_flags.get('group', '')

                    if action != extra_flags.get('step', '') and extra_flags.get('step', ''):  # Get the current model step.
                        print(f"agent action: {extra_flags.get('step', '')}")
                    action = extra_flags.get('step', '')

                    role = msg.get('role', '')  # Get the role, e.g., 'assistant' or 'tool'.
                    content = msg.get('content')  # Get the generated content.
                    toolcalls = msg.get('tool_calls', [])  # Get the tool calls.
                    if toolcalls:
                        print(f'{toolcalls}')

                    if role == "tool":
                        print("\\n" + content + "\\n", end='')  # Wrap the tool output in newlines for readability.
                    else:
                        print(content, end='')  # Streaming output.
                    # Save the results as needed.
                    resultlist.append(obj)
                except Exception as e:
                    print("Parse error:", e)

​Request syntax

​Request parameters

​Response parameters

​Execution stage enumeration

​Step value and tool name mapping

​Text QA

​Multimodal QA

​Local service POI tools

​Tool call status

​Parameters

​Rich media message protocol

​Render local life POI cards

​Multimodal image Q&A

​Request parameters

​Examples

​Sample requests

​Sample response

​Code sample

Request syntax

Request parameters

Response parameters

Execution stage enumeration

Step value and tool name mapping

Text QA

Multimodal QA

Local service POI tools

Tool call status

Parameters

Rich media message protocol

Render local life POI cards

Multimodal image Q&A

Request parameters

Examples

Sample requests

Sample response

Code sample