feat: add configurable vision focus prompts

backend/services/vision.py

@@ -22,6 +22,12 @@ VISION_ANALYSIS_SYSTEM_PROMPT = (
     "你是一个视觉理解模型。请只根据图片内容和用户问题给出准确、简洁的中文观察结果。"
     "如果画面不足以判断，请明确说明不确定。"
 )
+VISION_FOCUS_GENERATION_SYSTEM_PROMPT = (
+    "你负责把对话助手提示词整理成一段可编辑的视觉关注目标。"
+    "只提取图片中能够直接观察的对象、属性、状态、输出要求和不确定性边界；"
+    "不要复制对话流程、工具调用规则或结束条件，不要要求根据画面推断身份、责任、"
+    "意图等不可直接观察的信息。使用简洁中文，控制在 100 至 500 字，只输出关注目标正文。"
+)
 
 
 def _require(value: str, label: str) -> str:
@@ -30,6 +36,85 @@ def _require(value: str, label: str) -> str:
     raise ValueError(f"缺少模型资源配置: {label}")
 
 
+def vision_system_hint(focus_prompt: str = "") -> str:
+    """Describe when to use vision and keep a configured business focus visible."""
+
+    focus = focus_prompt.strip()
+    if not focus:
+        return VISION_SYSTEM_HINT
+    return (
+        f"{VISION_SYSTEM_HINT}\n"
+        f"视觉关注目标（用于补充本次用户问题；冲突时以本次问题为准）：{focus}"
+    )
+
+
+def vision_analysis_system_prompt(focus_prompt: str = "") -> str:
+    """Keep the safety baseline fixed while appending an editable business focus."""
+
+    focus = focus_prompt.strip()
+    if not focus:
+        return VISION_ANALYSIS_SYSTEM_PROMPT
+    return (
+        f"{VISION_ANALYSIS_SYSTEM_PROMPT}\n\n"
+        f"[业务视觉关注目标]\n{focus}\n"
+        "该目标用于补充当前用户问题；如果二者范围不同，优先回答当前用户问题。"
+    )
+
+
+def vision_tool_description(focus_prompt: str = "") -> str:
+    base = (
+        "获取用户当前摄像头画面。当用户询问当前画面、看到了什么、"
+        "人/物品/环境状态或需要视觉判断时调用。"
+    )
+    focus = " ".join(focus_prompt.split())
+    return f"{base} 当前业务重点：{focus[:600]}" if focus else base
+
+
+async def generate_vision_focus_prompt(
+    resource: RuntimeModelResource,
+    source_prompt: str,
+) -> str:
+    """Generate one editable focus draft with an existing LLM resource."""
+
+    if resource.interface_type not in {"openai-llm", "dashscope-llm"}:
+        raise ValueError(f"当前模型接口不支持提示词生成: {resource.interface_type}")
+    source = source_prompt.strip()
+    if not source:
+        raise ValueError("助手提示词不能为空")
+    values = resource.values or {}
+    secrets = resource.secrets or {}
+    extra_body = values.get("extraBody")
+    extra = {"extra_body": extra_body} if isinstance(extra_body, dict) else {}
+    client = AsyncOpenAI(
+        api_key=_require(str(secrets.get("apiKey") or ""), "LLM apiKey"),
+        base_url=_require(str(values.get("apiUrl") or ""), "LLM apiUrl"),
+    )
+    try:
+        response = await client.chat.completions.create(
+            model=_require(str(values.get("modelId") or ""), "LLM modelId"),
+            messages=[
+                {"role": "system", "content": VISION_FOCUS_GENERATION_SYSTEM_PROMPT},
+                {"role": "user", "content": source},
+            ],
+            **extra,
+        )
+    finally:
+        await client.close()
+    content = response.choices[0].message.content if response.choices else ""
+    result = (
+        content.strip()
+        if isinstance(content, str)
+        else str(content or "").strip()
+    )
+    if not result:
+        raise ValueError("模型没有生成有效的视觉关注目标")
+    if result.startswith("```") and result.endswith("```"):
+        result = result[3:-3].strip()
+        if result.startswith("text"):
+            result = result[4:].strip()
+    return result[:4000]
+
+
 def image_jpeg_bytes(frame: UserImageRawFrame) -> bytes:
     """Encode one Pipecat camera frame as a storage- and model-ready JPEG."""
     if not frame.format:
@@ -86,7 +171,12 @@ async def analyze_image_with_vision_model(
         response = await client.chat.completions.create(
             model=_require(cfg.vision_model, "Vision LLM modelId"),
             messages=[
-                {"role": "system", "content": VISION_ANALYSIS_SYSTEM_PROMPT},
+                {
+                    "role": "system",
+                    "content": vision_analysis_system_prompt(
+                        cfg.vision_focus_prompt
+                    ),
+                },
                 {
                     "role": "user",
                     "content": [