将生成图片或图片路径写入上下文中放弃自控图片上下文

2026-03-30 19:37:10 +08:00
parent ed9406732d
commit d6836fefc2
6 changed files with 394 additions and 111 deletions
--- a/src/server/deep_agent/tools/generate_furniture_sketch.py
+++ b/src/server/deep_agent/tools/generate_furniture_sketch.py
@@ -1,23 +1,25 @@
 import uuid
+from typing import Optional
+
 import httpx
 import logging

 from langchain_core.runnables import RunnableConfig
 from minio import Minio
-from pathlib import Path
-from datetime import datetime
+# from pathlib import Path
+# from datetime import datetime
 from langchain_core.tools import tool
 from langgraph.prebuilt import ToolRuntime
 from src.core.config import settings, MONGO_URI
-from src.server.deep_agent.utils.mongodb_util import ThreadImageMinIOStore
+# from src.server.deep_agent.utils.mongodb_util import ThreadImageMinIOStore

 logger = logging.getLogger(__name__)
 minio_client = Minio(settings.MINIO_URL, access_key=settings.MINIO_ACCESS, secret_key=settings.MINIO_SECRET, secure=settings.MINIO_SECURE)
-image_store = ThreadImageMinIOStore(MONGO_URI, "agent_tool_generate_db")
+# image_store = ThreadImageMinIOStore(MONGO_URI, "agent_tool_generate_db")


@tool
-async def generate_furniture(prompt: str, runtime: ToolRuntime):
+async def generate_furniture(runtime: ToolRuntime, prompts: list[str] = None, num_images: Optional[int] = 1):
    """
    使用图像生成模型根据用户提供的详细英文提示词，从零生成一张全新的家具设计草图。

@@ -28,6 +30,7 @@ async def generate_furniture(prompt: str, runtime: ToolRuntime):
    参数说明：
    - prompt (str): **必须是详细的英文提示词**，越详细越好，包含家具类型、风格、颜色、材质、尺寸比例、背景、视角、光影等具体要求。
      示例："Generate a modern minimalist dining chair made of light oak wood and white leather, with slim metal legs, photographed in a bright Scandinavian living room with natural sunlight, high detail, 8k resolution."
+    - num_images (int, 可选): 要生成的图片数量，默认 1 张。最大只能是 4 张。如果输入超过 4，会自动限制为 4。

    返回值：
    返回新生成家具图片的 image_url，后续对话中 Agent 可直接引用该图片进行描述、进一步编辑或分析。
@@ -42,85 +45,232 @@ async def generate_furniture(prompt: str, runtime: ToolRuntime):
    - 生成的图片会自动携带到整个对话上下文中，支持后续使用 edit_furniture 等工具进行迭代修改。
    - 如果需要生成多个方案，可以多次调用本工具或在 prompt 中明确要求生成不同变体。
    """
-    current_checkpoint_id = runtime.store.get(namespace=("image_history",), key="checkpoint_id", ).value.get("current_checkpoint_id")
+    if num_images is None or num_images < 1:
+        num_images = 1
+    elif num_images > 4:
+        num_images = 4
+    # current_checkpoint_id = runtime.store.get(namespace=("image_history",), key="checkpoint_id", ).value.get("current_checkpoint_id")

    logger.info(f"\n[系统日志] 正在调用 generate_furniture ...当前checkpoint_id={current_checkpoint_id}")

    try:
-        image_url = await generate_or_edit_image(prompt=prompt)
+        bucket_name = "fida-public-bucket"
+        object_name = f"furniture/sketches/{uuid.uuid4()}"
+        image_urls = []
+        for i in range(num_images):
+            image_urls.append(await generate_or_edit_image(prompt=prompts[i], bucket_name=bucket_name, object_name=f"{object_name}-{i}.png"))

-        if image_url:
-            image_store.save_image_path(thread_id=current_checkpoint_id, object_path=image_url, metadata={"prompt": prompt, "generated_at": str(datetime.now())})
-            return image_url
-        else:
-            return "Image generation failed."
+        # if image_urls:
+        #     image_store.save_image_path(thread_id=current_checkpoint_id, object_path=image_urls, metadata={"prompt": prompt, "generated_at": str(datetime.now())})
+        return image_urls
+        # else:
+        #     return "Image generation failed."
    except Exception as e:
        logger.warning(f"绘图流程异常：{e}")
        return "generate furniture error"


@tool
-async def edit_furniture(prompt: str, runtime: ToolRuntime, config: RunnableConfig):
+async def edit_furniture(runtime: ToolRuntime, config: RunnableConfig, input_image_paths: list[str] = None, prompts: list[str] = None, ):
    """
-    使用先进的图像编辑模型（image editing model）对家具设计草图进行精准修改。
+    使用先进的图像编辑模型对家具设计草图进行精准修改。

    功能说明：
-    - 根据用户提供的**详细英文提示词**，生成修改后的新家具图片。
+    - 支持批量处理多张家具图片，根据对应的提示词生成修改后的新图片。
+    - input_image_paths 和 prompts 必须一一对应，数量完全一致。
+    - 最多支持同时处理 4 对图片和提示词（即最多 4 张图片）。

    参数说明：
-    - prompt (str): **必须是详细的英文提示词**，描述想要的具体修改（风格、颜色、材质、形状、添加/删除元素、比例等）。
-      示例："Change the sofa to a modern minimalist style with dark gray fabric and metal legs, add a matching coffee table, make the overall lighting warmer and more luxurious."
+
+    - input_image_paths (list[str]):
+      输入图片在 MinIO 中的存储路径列表。
+      示例：["furniture/designs/sofa_concept_v1.png", "projects/room_2026/chair_v2.jpg"]
+      注意：路径必须是有效的 MinIO 对象路径，工具会自动下载对应图片。
+
+    - prompts (list[str]):
+      与图片一一对应的详细英文提示词列表。
+      每个提示词描述对对应图片的具体修改要求（风格、颜色、材质、形状、添加/删除元素等）。
+      示例：["Change the sofa to a modern minimalist style with dark gray fabric and metal legs, add a matching coffee table.",
+             "Convert the chair to Scandinavian Nordic style with light wood and soft beige upholstery."]
+
+    使用要求（重要）：
+    - input_image_paths 和 prompts 的长度必须完全相同。
+    - 列表长度必须在 1 到 4 之间（最多 4 对）。
+    - input_image_paths[0] 对应 prompts[0]，以此类推，一一对应进行编辑。

    使用场景：
-    - 家具设计迭代
-    - 室内设计方案修改
-    - 风格转换（现代/北欧/工业风等）
-    - 材质/颜色调整
+    - 家具设计方案迭代
+    - 室内设计多方案对比修改
+    - 批量风格转换（现代/北欧/工业/奢华风等）
+    - 材质、颜色、细节批量调整

+    示例调用：
+    input_image_paths = ["designs/sofa1.png", "designs/chair1.png"]
+    prompts = [
+        "Make the sofa more luxurious with velvet fabric and gold accents.",
+        "Change the chair to a sleek modern design with black leather and chrome legs."
+    ]
    """
-    image_history = runtime.store.get(namespace=("image_history",), key="checkpoint_id", )
-    last_checkpoint_id = image_history.value.get("last_checkpoint_id")
-    current_checkpoint_id = image_history.value.get("current_checkpoint_id")

-    logger.info(f"\n[系统日志] 正在调用 edit_furniture ...current_checkpoint_id={current_checkpoint_id}  ---  last_checkpoint_id={last_checkpoint_id}")
-
-    input_path = []
-    if image_store.get_image_path(last_checkpoint_id):
-        current_image_path = image_store.get_image_path(last_checkpoint_id).get("current_image_path", False)
-    else:
-        current_image_path = None
+    # image_history = runtime.store.get(namespace=("image_history",), key="checkpoint_id", )
+    # last_checkpoint_id = image_history.value.get("last_checkpoint_id")
+    # current_checkpoint_id = image_history.value.get("current_checkpoint_id")
+    #
+    # logger.info(f"\n[系统日志] 正在调用 edit_furniture ...current_checkpoint_id={current_checkpoint_id}  ---  last_checkpoint_id={last_checkpoint_id}")
+    #
+    # if image_store.get_image_path(last_checkpoint_id):
+    #     current_image_path = image_store.get_image_path(last_checkpoint_id).get("current_image_path", False)
+    #     if current_image_path:
+    #         if isinstance(current_image_path, list):
+    #             #  只取最后一张
+    #             current_image_path = current_image_path[-1]
+    # else:
+    #     current_image_path = None

+    # input_path = []
    try:
-        user_input_image_paths = runtime.state.get("files").get("input_image", [])
-        user_quote_image_path = runtime.state.get("files").get("quote_image", "")
-
-        if current_image_path:
-            if len(user_input_image_paths) or current_image_path:
-                for path in user_input_image_paths:
-                    input_path.append(path)
-                if user_quote_image_path:
-                    input_path.append(user_quote_image_path)
-                if not len(user_input_image_paths) and not user_quote_image_path:
-                    input_path = [current_image_path]
-
+        # user_input_image_paths = runtime.state.get("files").get("input_image", [])
+        # user_quote_image_path = runtime.state.get("files").get("quote_image", "")
+        result = []
+        if len(input_image_paths):
+            for i in range(len(input_image_paths)):
                bucket_name = "fida-public-bucket"
                object_name = f"furniture/sketches/{uuid.uuid4()}.png"
-                image_url = await generate_or_edit_image(input_path=input_path, prompt=prompt, bucket_name=bucket_name, object_name=object_name)
-                if image_url:
-                    image_store.save_image_path(thread_id=current_checkpoint_id, object_path=image_url, metadata={"prompt": prompt, "generated_at": str(datetime.now())})
-                    return image_url
-                else:
-                    return "Image generation failed."
-            else:
-                return "The picture to be edited does not exist."
-        else:
-            return "No recent image found, please upload or cite it"
+                image_url = await generate_or_edit_image(input_path=[input_image_paths[i]], prompt=prompts[i], bucket_name=bucket_name, object_name=f"{object_name}-{i}.png")
+                result.append(image_url)
+                # image_url = await generate_or_edit_image(input_path=input_path, prompt=prompt, bucket_name=bucket_name, object_name=object_name)
+                # if image_url:
+                #     image_store.save_image_path(thread_id=current_checkpoint_id, object_path=[image_url], metadata={"prompt": prompt, "generated_at": str(datetime.now())})
+        return result
+        # else:
+        #     return "Image generation failed."
+        # else:
+        #     return "The picture to be edited does not exist."
+        # else:
+        #     return "No recent image found, please upload or cite it"

    except Exception as e:
        logger.warning(f"edit_furniture error ：{e}")
        return "edit_furniture error"


+@tool
+async def edit_quote_upload_furniture(image_paths: list[str] = None, mode: str = "auto", prompts: list[str] = None, ):
+    """
+        使用先进的图像编辑模型对家具图片进行精准批量修改。
+
+        支持四种模式：
+        - one_to_one（最常用）：多张图片 + 多个提示词，一一对应编辑
+        - one_to_many：多张图片 + 1个提示词（所有图片统一修改）
+        - many_to_one：1张图片 + 多个提示词（同一张图生成多个不同变体，例如不同颜色）
+        - many_to_many（新增）：多张图片 + 多个提示词，一一对应（多对多交叉编辑）
+
+        参数说明：
+        - image_paths (list[str]): MinIO 图片路径列表，长度建议 1~4
+        - prompts (list[str]): 详细英文提示词列表
+        - mode (str): "one_to_one", "one_to_many", "many_to_one", "many_to_many", "auto"（默认自动判断）
+
+        使用要求：
+        - image_paths 长度必须在 1~4 之间
+        - mode="auto" 时会根据长度智能判断
+        - many_to_many 模式下：image_paths 和 prompts 的长度必须完全相同
+
+        示例：
+
+        示例1：many_to_many（多对多，一一对应）
+        image_paths = ["sofa1.png", "chair1.png", "table1.png"]
+        prompts = [
+            "Change to bright yellow modern style.",
+            "Change to deep green luxury style.",
+            "Change to soft beige Scandinavian style."
+        ]
+        mode = "many_to_many"
+
+        示例2：many_to_one（同一张图多个颜色版本）
+        image_paths = ["sofa_original.png"]
+        prompts = ["yellow version", "green version", "blue version", "black version"]
+        mode = "many_to_one"
+        """
+    try:
+        # ====================== 参数校验（直接返回错误信息） ======================
+        if not image_paths or len(image_paths) < 1 or len(image_paths) > 4:
+            return f"参数错误：image_paths 必须提供，且长度需要在 1 到 4 张之间。目前收到 {len(image_paths) if image_paths else 0} 张。"
+
+        if not prompts:
+            return "参数错误：prompts 不能为空，请至少提供一个修改提示词。"
+
+        if mode not in ["one_to_one", "one_to_many", "many_to_one", "many_to_many", "auto"]:
+            return f"参数错误：mode 参数无效。可用值：one_to_one, one_to_many, many_to_one, many_to_many, auto。当前收到：{mode}"
+
+        # Auto 模式智能判断
+        if mode == "auto":
+            if len(image_paths) == 1 and len(prompts) > 1:
+                mode = "many_to_one"
+            elif len(prompts) == 1:
+                mode = "one_to_many"
+            elif len(image_paths) == len(prompts):
+                mode = "many_to_many"  # 新增：数量相等时优先 many_to_many
+            else:
+                mode = "one_to_one"
+
+        # 各模式严格校验
+        if mode == "many_to_one":
+            if len(image_paths) != 1:
+                return f"参数错误：many_to_one 模式只能传入 1 张图片，当前传入了 {len(image_paths)} 张。"
+            if len(prompts) < 1:
+                return "参数错误：many_to_one 模式下 prompts 至少需要 1 个。"
+
+        elif mode == "one_to_many":
+            if len(prompts) != 1:
+                return f"参数错误：one_to_many 模式下 prompts 必须只有 1 个，当前有 {len(prompts)} 个。"
+
+        elif mode in ["one_to_one", "many_to_many"]:
+            if len(prompts) != len(image_paths):
+                return (f"参数错误：{mode} 模式下 image_paths 和 prompts 数量必须完全一致。\n"
+                        f"当前 image_paths 有 {len(image_paths)} 张，prompts 有 {len(prompts)} 个。")
+
+        # ====================== 执行编辑 ======================
+        result = []
+        bucket_name = "fida-public-bucket"
+
+        if mode == "many_to_one":
+            # 同一张图片 + 多个 prompt
+            base_image = image_paths[0]
+            for i, prompt in enumerate(prompts):
+                object_name = f"furniture/sketches/{uuid.uuid4()}.png"
+                image_url = await generate_or_edit_image(
+                    input_path=[base_image],
+                    prompt=prompt,
+                    bucket_name=bucket_name,
+                    object_name=f"{object_name}-var{i}.png"
+                )
+                result.append(image_url)
+
+        else:
+            # one_to_one、many_to_many、one_to_many 统一处理
+            for i in range(len(image_paths)):
+                # 根据模式决定当前使用的 prompt
+                if mode == "one_to_many":
+                    current_prompt = prompts[0]
+                else:
+                    current_prompt = prompts[i]  # one_to_one 和 many_to_many 都用对应位置的 prompt
+
+                object_name = f"furniture/sketches/{uuid.uuid4()}.png"
+                image_url = await generate_or_edit_image(
+                    input_path=[image_paths[i]],
+                    prompt=current_prompt,
+                    bucket_name=bucket_name,
+                    object_name=f"{object_name}-{i}.png"
+                )
+                result.append(image_url)
+
+        return result
+
+    except Exception as e:
+        logger.error(f"edit_quote_upload_furniture 执行异常: {e}", exc_info=True)
+        return f"工具执行失败：{str(e)}，请检查参数后重试。"
+
+
 async def generate_or_edit_image(input_path=None, bucket_name="fida-public-bucket",
                                 object_name=f"furniture/sketches/{uuid.uuid4()}.png",
                                 prompt="Generate a modern minimalist dining chair made of light "