修改解题脚本以添补视觉部分

scripts/solve.py

@@ -82,6 +82,18 @@ def build_prompt(question_data: dict, typ_content: str | None) -> str:
     return "".join(parts)
 
 
+def get_image_attachments(question_data: dict) -> list[tuple[str, Path]]:
+    """Return list of (attachment_name, path) for image attachments."""
+    images = []
+    for att in question_data.get("attachments", []):
+        att_path = DATA_DIR / att
+        if att_path.exists() and att.lower().endswith(
+            (".png", ".jpg", ".jpeg", ".gif", ".bmp", ".webp")
+        ):
+            images.append((att, att_path))
+    return images
+
+
 async def call_api_streaming(
     session: aiohttp.ClientSession,
     question_name: str,
@@ -90,13 +102,34 @@ async def call_api_streaming(
     api_key: str,
     model: str,
     logger: logging.Logger,
+    image_contents: list[tuple[str, Path]] | None = None,
 ) -> str | None:
     """Call the AI API with streaming to solve the question."""
+    import base64
+
     headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
 
+    messages = [{"role": "user", "content": [{"type": "text", "text": prompt}]}]
+
+    if image_contents:
+        for att_name, att_path in image_contents:
+            with open(att_path, "rb") as f:
+                image_data = base64.b64encode(f.read()).decode("utf-8")
+            suffix = att_path.suffix[1:].lower()
+            if suffix in ("jpg", "jpeg"):
+                mime_type = "image/jpeg"
+            else:
+                mime_type = f"image/{suffix}"
+            messages[0]["content"].append(
+                {
+                    "type": "image_url",
+                    "image_url": {"url": f"data:{mime_type};base64,{image_data}"},
+                }
+            )
+
     payload = {
         "model": model,
-        "messages": [{"role": "user", "content": [{"type": "text", "text": prompt}]}],
+        "messages": messages,
         "max_tokens": 4096,
         "stream": True,
     }
@@ -182,6 +215,7 @@ async def solve_question(
         )
 
     prompt = build_prompt(question_data, typ_content)
+    image_contents = get_image_attachments(question_data)
 
     content = await call_api_streaming(
         session,
@@ -191,6 +225,7 @@ async def solve_question(
         api_config["key"],
         api_config["model"],
         logger,
+        image_contents,
     )
 
     if content is None: