feat: supports image compressing

astrbot/core/astr_main_agent.py

@@ -1,14 +1,19 @@
 from __future__ import annotations
 
 import asyncio
+import base64
 import copy
 import datetime
+import io
 import json
 import os
+import time
 import zoneinfo
 from collections.abc import Coroutine
 from dataclasses import dataclass, field
 
+from PIL import Image as PILImage
+
 from astrbot.core import logger, sp
 from astrbot.core.agent.handoff import HandoffTool
 from astrbot.core.agent.mcp_client import MCPTool
@@ -448,7 +453,7 @@ async def _ensure_img_caption(
         caption = await _request_img_caption(
             image_caption_provider,
             cfg,
-            req.image_urls,
+            [await _compress_image_internal(url) for url in req.image_urls],
             plugin_context,
         )
         if caption:
@@ -458,6 +463,9 @@ async def _ensure_img_caption(
             req.image_urls = []
     except Exception as exc:  # noqa: BLE001
         logger.error("处理图片描述失败: %s", exc)
+        req.extra_user_content_parts.append(TextPart(text="图片解析失败"))
+    finally:
+        req.image_urls = []
 
 
 def _append_quoted_image_attachment(req: ProviderRequest, image_path: str) -> None:
@@ -523,7 +531,11 @@ async def _process_quote_message(
             if prov and isinstance(prov, Provider):
                 llm_resp = await prov.text_chat(
                     prompt=IMAGE_CAPTION_DEFAULT_PROMPT,
-                    image_urls=[await image_seg.convert_to_file_path()],
+                    image_urls=[
+                        await _compress_image_internal(
+                            await image_seg.convert_to_file_path()
+                        )
+                    ],
                 )
                 if llm_resp.completion_text:
                     content_parts.append(
@@ -936,7 +948,9 @@ async def build_main_agent(
             # media files attachments
             for comp in event.message_obj.message:
                 if isinstance(comp, Image):
-                    image_path = await comp.convert_to_file_path()
+                    image_path = await _compress_image_internal(
+                            await comp.convert_to_file_path()
+                        )
                     req.image_urls.append(image_path)
                     req.extra_user_content_parts.append(
                         TextPart(text=f"[Image Attachment: path {image_path}]")
@@ -963,7 +977,9 @@ async def build_main_agent(
                     for reply_comp in comp.chain:
                         if isinstance(reply_comp, Image):
                             has_embedded_image = True
-                            image_path = await reply_comp.convert_to_file_path()
+                            image_path = await _compress_image_internal(
+                                await reply_comp.convert_to_file_path()
+                            )
                             req.image_urls.append(image_path)
                             _append_quoted_image_attachment(req, image_path)
                         elif isinstance(reply_comp, File):
@@ -1164,3 +1180,47 @@ async def build_main_agent(
         provider=provider,
         reset_coro=reset_coro if not apply_reset else None,
     )
+
+# 异步图片压缩
+def _do_compress_sync(data: bytes, temp_dir: str) -> str:
+    """同步执行图片压缩逻辑，由 asyncio.to_thread 调用"""
+
+    img = PILImage.open(io.BytesIO(data))
+    if img.mode in ("RGBA", "P"):
+        img = img.convert("RGB")
+    max_size = 1280
+    if max(img.size) > max_size:
+        img.thumbnail((max_size, max_size), PILImage.Resampling.LANCZOS)
+
+    timestamp = int(time.time() * 1000)
+    save_path = os.path.join(temp_dir, f"compressed_{timestamp}.jpg")
+    img.save(save_path, "JPEG", quality=85, optimize=True)
+    return save_path
+
+# 压缩用户上传的大体积图片 未来可以提取为通用工具
+async def _compress_image_internal(url_or_path: str) -> str:
+    try:
+        data = None
+        # 若为远程图片则直接返回原值 无需压缩
+        if url_or_path.startswith("http"):
+            return url_or_path
+        elif url_or_path.startswith("data:image"):
+            header, encoded = url_or_path.split(",", 1)
+            data = base64.b64decode(encoded)
+        elif os.path.exists(url_or_path):
+            if os.path.getsize(url_or_path) < 1024 * 1024:
+                return url_or_path
+            with open(url_or_path, "rb") as f:
+                data = f.read()
+
+        if not data:
+            return url_or_path
+
+        temp_dir = os.path.join(os.path.dirname(os.path.dirname(os.path.dirname(os.path.abspath(__file__)))), "data/temp")
+
+        # 使用 asyncio.to_thread 将同步阻塞的图片处理任务交给线程池
+        return await asyncio.to_thread(_do_compress_sync, data, temp_dir)
+
+    except Exception as e:
+        logger.error("图片压缩失败: %s", e)
+        return url_or_path