Merge pull request #2759 from zhayujie/feat-multimodel

feat(vision): prioritize main model for image recognition

models/bot.py

@@ -2,12 +2,27 @@
 Auto-replay chat robot abstract class
 """
 
-
 from bridge.context import Context
 from bridge.reply import Reply
 
 
 class Bot(object):
+    """
+    Base class for all chat-bot implementations.
+
+    Subclasses may also implement:
+
+        call_with_tools(messages, tools=None, stream=False, **kwargs)
+            -> dict | generator  (OpenAI-compatible format)
+
+        call_vision(image_url, question, model=None, max_tokens=1000)
+            -> dict with keys: model, content, usage  (or error/message)
+
+    These are NOT defined here to avoid shadowing concrete implementations
+    provided by mixin classes (e.g. OpenAICompatibleBot) in the MRO.
+    Use ``hasattr(bot, 'call_vision')`` to detect support at runtime.
+    """
+
     def reply(self, query, context: Context = None) -> Reply:
         """
         bot auto-reply content

models/claudeapi/claude_api_bot.py

@@ -1,7 +1,10 @@
 # encoding:utf-8
 
+import base64
 import json
+import re
 import time
+from typing import Optional
 
 import requests
 
@@ -224,6 +227,79 @@ class ClaudeAPIBot(Bot, OpenAIImage):
             return 64000
         return 8192
 
+    @staticmethod
+    def _parse_data_url(data_url: str):
+        """Parse a data:<mime>;base64,<data> URL into (media_type, base64_data)."""
+        m = re.match(r"^data:([^;]+);base64,(.+)$", data_url, re.DOTALL)
+        if m:
+            return m.group(1), m.group(2)
+        return None, None
+
+    def call_vision(self, image_url: str, question: str,
+                    model: Optional[str] = None,
+                    max_tokens: int = 1000) -> dict:
+        """Analyze an image using Claude Messages API (native image blocks)."""
+        try:
+            actual_model = model or self._model_mapping(conf().get("model"))
+
+            # Build Claude-native image content block
+            if image_url.startswith("data:"):
+                media_type, b64_data = self._parse_data_url(image_url)
+                if not b64_data:
+                    return {"error": True, "message": "Invalid base64 data URL"}
+                image_block = {
+                    "type": "image",
+                    "source": {"type": "base64",
+                               "media_type": media_type or "image/jpeg",
+                               "data": b64_data},
+                }
+            else:
+                image_block = {
+                    "type": "image",
+                    "source": {"type": "url", "url": image_url},
+                }
+
+            data = {
+                "model": actual_model,
+                "max_tokens": max_tokens,
+                "messages": [{
+                    "role": "user",
+                    "content": [
+                        image_block,
+                        {"type": "text", "text": question},
+                    ],
+                }],
+            }
+
+            headers = {
+                "x-api-key": self.api_key,
+                "anthropic-version": "2023-06-01",
+                "content-type": "application/json",
+            }
+            proxies = {"http": self.proxy, "https": self.proxy} if self.proxy else None
+            resp = requests.post(f"{self.api_base}/messages",
+                                 headers=headers, json=data, proxies=proxies)
+
+            if resp.status_code != 200:
+                return {"error": True, "message": f"HTTP {resp.status_code}: {resp.text[:300]}"}
+
+            body = resp.json()
+            text_parts = [b.get("text", "") for b in body.get("content", [])
+                          if b.get("type") == "text"]
+            usage = body.get("usage", {})
+            return {
+                "model": actual_model,
+                "content": "".join(text_parts),
+                "usage": {
+                    "prompt_tokens": usage.get("input_tokens", 0),
+                    "completion_tokens": usage.get("output_tokens", 0),
+                    "total_tokens": usage.get("input_tokens", 0) + usage.get("output_tokens", 0),
+                },
+            }
+        except Exception as e:
+            logger.error(f"[CLAUDE] call_vision error: {e}")
+            return {"error": True, "message": str(e)}
+
     def call_with_tools(self, messages, tools=None, stream=False, **kwargs):
         """
         Call Claude API with tool support for agent integration

models/dashscope/dashscope_bot.py

@@ -1,6 +1,8 @@
 # encoding:utf-8
 
 import json
+from typing import Optional
+
 from models.bot import Bot
 from models.session_manager import SessionManager
 from bridge.context import ContextType
@@ -153,6 +155,56 @@ class DashscopeBot(Bot):
             else:
                 return result
 
+    def call_vision(self, image_url: str, question: str,
+                    model: Optional[str] = None,
+                    max_tokens: int = 1000) -> dict:
+        """Analyze an image using DashScope MultiModalConversation API."""
+        try:
+            dashscope.api_key = self.api_key
+            vision_model = model or "qwen-vl-max"
+
+            # DashScope multimodal format: {"image": url} + {"text": question}
+            messages = [{
+                "role": "user",
+                "content": [
+                    {"image": image_url},
+                    {"text": question},
+                ],
+            }]
+
+            response = MultiModalConversation.call(
+                model=vision_model,
+                messages=messages,
+                max_tokens=max_tokens,
+            )
+
+            if response.status_code != HTTPStatus.OK:
+                return {
+                    "error": True,
+                    "message": f"{response.code} - {response.message}",
+                }
+
+            resp_dict = self._response_to_dict(response)
+            choice = resp_dict["output"]["choices"][0]
+            content = choice.get("message", {}).get("content", "")
+            if isinstance(content, list):
+                content = "".join(
+                    item.get("text", "") for item in content if isinstance(item, dict)
+                )
+            usage = resp_dict.get("usage", {})
+            return {
+                "model": vision_model,
+                "content": content,
+                "usage": {
+                    "prompt_tokens": usage.get("input_tokens", 0),
+                    "completion_tokens": usage.get("output_tokens", 0),
+                    "total_tokens": usage.get("total_tokens", 0),
+                },
+            }
+        except Exception as e:
+            logger.error(f"[DASHSCOPE] call_vision error: {e}")
+            return {"error": True, "message": str(e)}
+
     def call_with_tools(self, messages, tools=None, stream=False, **kwargs):
         """
         Call DashScope API with tool support for agent integration

models/doubao/doubao_bot.py

@@ -2,6 +2,7 @@
 
 import json
 import time
+from typing import Optional
 
 import requests
 from models.bot import Bot
@@ -147,6 +148,49 @@ class DoubaoBot(Bot):
             else:
                 return result
 
+    def call_vision(self, image_url: str, question: str,
+                    model: Optional[str] = None,
+                    max_tokens: int = 1000) -> dict:
+        """Analyze an image using Doubao (Volcengine Ark) OpenAI-compatible API."""
+        try:
+            vision_model = model or self.args.get("model", "doubao-seed-2-0-pro-260215")
+            payload = {
+                "model": vision_model,
+                "max_tokens": max_tokens,
+                "messages": [{
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": question},
+                        {"type": "image_url", "image_url": {"url": image_url}},
+                    ],
+                }],
+            }
+            headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Content-Type": "application/json",
+            }
+            resp = requests.post(f"{self.base_url}/chat/completions",
+                                 headers=headers, json=payload, timeout=60)
+            if resp.status_code != 200:
+                return {"error": True, "message": f"HTTP {resp.status_code}: {resp.text[:300]}"}
+            data = resp.json()
+            if "error" in data:
+                return {"error": True, "message": data["error"].get("message", str(data["error"]))}
+            content = data.get("choices", [{}])[0].get("message", {}).get("content", "")
+            usage = data.get("usage", {})
+            return {
+                "model": vision_model,
+                "content": content,
+                "usage": {
+                    "prompt_tokens": usage.get("prompt_tokens", 0),
+                    "completion_tokens": usage.get("completion_tokens", 0),
+                    "total_tokens": usage.get("total_tokens", 0),
+                },
+            }
+        except Exception as e:
+            logger.error(f"[DOUBAO] call_vision error: {e}")
+            return {"error": True, "message": str(e)}
+
     # ==================== Agent mode support ====================
 
     def call_with_tools(self, messages, tools=None, stream: bool = False, **kwargs):
@@ -434,31 +478,37 @@ class DoubaoBot(Bot):
                 continue
 
             if role == "user":
-                text_parts = []
-                tool_results = []
+                has_tool_result = any(
+                    isinstance(b, dict) and b.get("type") == "tool_result" for b in content
+                )
+                if has_tool_result:
+                    text_parts = []
+                    tool_results = []
 
-                for block in content:
-                    if not isinstance(block, dict):
-                        continue
-                    if block.get("type") == "text":
-                        text_parts.append(block.get("text", ""))
-                    elif block.get("type") == "tool_result":
-                        tool_call_id = block.get("tool_use_id") or ""
-                        result_content = block.get("content", "")
-                        if not isinstance(result_content, str):
-                            result_content = json.dumps(result_content, ensure_ascii=False)
-                        tool_results.append({
-                            "role": "tool",
-                            "tool_call_id": tool_call_id,
-                            "content": result_content
-                        })
+                    for block in content:
+                        if not isinstance(block, dict):
+                            continue
+                        if block.get("type") == "text":
+                            text_parts.append(block.get("text", ""))
+                        elif block.get("type") == "tool_result":
+                            tool_call_id = block.get("tool_use_id") or ""
+                            result_content = block.get("content", "")
+                            if not isinstance(result_content, str):
+                                result_content = json.dumps(result_content, ensure_ascii=False)
+                            tool_results.append({
+                                "role": "tool",
+                                "tool_call_id": tool_call_id,
+                                "content": result_content
+                            })
 
-                # Tool results first (must come right after assistant with tool_calls)
-                for tr in tool_results:
-                    converted.append(tr)
+                    for tr in tool_results:
+                        converted.append(tr)
 
-                if text_parts:
-                    converted.append({"role": "user", "content": "\n".join(text_parts)})
+                    if text_parts:
+                        converted.append({"role": "user", "content": "\n".join(text_parts)})
+                else:
+                    # Keep as-is for multimodal content (e.g. image_url blocks)
+                    converted.append(msg)
 
             elif role == "assistant":
                 openai_msg = {"role": "assistant"}

models/gemini/google_gemini_bot.py

@@ -12,6 +12,8 @@ import mimetypes
 import os
 import re
 import time
+from typing import Optional
+
 import requests
 from models.bot import Bot
 from models.session_manager import SessionManager
@@ -144,7 +146,12 @@ class GoogleGeminiBot(Bot):
             return "", []
         pattern = r"\[图片:\s*([^\]]+)\]"
         image_paths = [m.strip().strip("'\"") for m in re.findall(pattern, content) if m.strip()]
-        cleaned_text = re.sub(pattern, "", content)
+        # Replace markers with path-only hints so the model still knows the
+        # original file location (needed when it calls tools like vision).
+        def _replace_with_hint(m):
+            path = m.group(1).strip().strip("'\"")
+            return f"[attached image: {path}]"
+        cleaned_text = re.sub(pattern, _replace_with_hint, content)
         cleaned_text = re.sub(r"\n{3,}", "\n\n", cleaned_text).strip()
         return cleaned_text, image_paths
 
@@ -225,6 +232,57 @@ class GoogleGeminiBot(Bot):
         logger.warning(f"[Gemini] Unsupported image URL format: {image_url[:120]}")
         return None
 
+    def call_vision(self, image_url: str, question: str,
+                    model: Optional[str] = None,
+                    max_tokens: int = 1000) -> dict:
+        """Analyze an image using Gemini REST API."""
+        try:
+            model_name = model or self.model or "gemini-2.0-flash"
+            image_part = self._build_inline_part_from_image_url({"url": image_url})
+            if not image_part:
+                return {"error": True, "message": f"Cannot process image URL: {image_url[:120]}"}
+
+            payload = {
+                "contents": [{
+                    "role": "user",
+                    "parts": [image_part, {"text": question}],
+                }],
+                "generationConfig": {"maxOutputTokens": max_tokens},
+                "safetySettings": [
+                    {"category": "HARM_CATEGORY_HATE_SPEECH", "threshold": "BLOCK_NONE"},
+                    {"category": "HARM_CATEGORY_HARASSMENT", "threshold": "BLOCK_NONE"},
+                    {"category": "HARM_CATEGORY_SEXUALLY_EXPLICIT", "threshold": "BLOCK_NONE"},
+                    {"category": "HARM_CATEGORY_DANGEROUS_CONTENT", "threshold": "BLOCK_NONE"},
+                ],
+            }
+            endpoint = f"{self.api_base}/v1beta/models/{model_name}:generateContent"
+            headers = {"x-goog-api-key": self.api_key, "Content-Type": "application/json"}
+            resp = requests.post(endpoint, headers=headers, json=payload, timeout=60)
+
+            if resp.status_code != 200:
+                return {"error": True, "message": f"HTTP {resp.status_code}: {resp.text[:300]}"}
+
+            body = resp.json()
+            candidates = body.get("candidates", [])
+            text_parts = []
+            for part in candidates[0].get("content", {}).get("parts", []) if candidates else []:
+                if "text" in part:
+                    text_parts.append(part["text"])
+
+            usage_meta = body.get("usageMetadata", {})
+            return {
+                "model": model_name,
+                "content": "".join(text_parts),
+                "usage": {
+                    "prompt_tokens": usage_meta.get("promptTokenCount", 0),
+                    "completion_tokens": usage_meta.get("candidatesTokenCount", 0),
+                    "total_tokens": usage_meta.get("totalTokenCount", 0),
+                },
+            }
+        except Exception as e:
+            logger.error(f"[Gemini] call_vision error: {e}")
+            return {"error": True, "message": str(e)}
+
     def call_with_tools(self, messages, tools=None, stream=False, **kwargs):
         """
         Call Gemini API with tool support using REST API (following official docs)

models/minimax/minimax_bot.py

@@ -2,6 +2,8 @@
 
 import time
 import json
+from typing import Optional
+
 import requests
 
 from models.bot import Bot
@@ -175,6 +177,51 @@ class MinimaxBot(Bot):
             else:
                 return result
 
+    def call_vision(self, image_url: str, question: str,
+                    model: Optional[str] = None,
+                    max_tokens: int = 1000) -> dict:
+        """Analyze an image using MiniMax OpenAI-compatible API.
+        Always uses MiniMax-Text-01 — other MiniMax models do not support vision.
+        """
+        try:
+            vision_model = "MiniMax-Text-01"
+            payload = {
+                "model": vision_model,
+                "max_tokens": max_tokens,
+                "messages": [{
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": question},
+                        {"type": "image_url", "image_url": {"url": image_url}},
+                    ],
+                }],
+            }
+            headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Content-Type": "application/json",
+            }
+            resp = requests.post(f"{self.api_base}/chat/completions",
+                                 headers=headers, json=payload, timeout=60)
+            if resp.status_code != 200:
+                return {"error": True, "message": f"HTTP {resp.status_code}: {resp.text[:300]}"}
+            data = resp.json()
+            if "error" in data:
+                return {"error": True, "message": data["error"].get("message", str(data["error"]))}
+            content = data.get("choices", [{}])[0].get("message", {}).get("content", "")
+            usage = data.get("usage", {})
+            return {
+                "model": vision_model,
+                "content": content,
+                "usage": {
+                    "prompt_tokens": usage.get("prompt_tokens", 0),
+                    "completion_tokens": usage.get("completion_tokens", 0),
+                    "total_tokens": usage.get("total_tokens", 0),
+                },
+            }
+        except Exception as e:
+            logger.error(f"[MINIMAX] call_vision error: {e}")
+            return {"error": True, "message": str(e)}
+
     def call_with_tools(self, messages, tools=None, stream=False, **kwargs):
         """
         Call MiniMax API with tool support for agent integration
@@ -273,37 +320,41 @@ class MinimaxBot(Bot):
             if role == "user":
                 # Handle user message
                 if isinstance(content, list):
-                    # Extract text from content blocks
-                    text_parts = []
-                    tool_results = []
+                    has_tool_result = any(
+                        isinstance(b, dict) and b.get("type") == "tool_result" for b in content
+                    )
+                    if has_tool_result:
+                        text_parts = []
+                        tool_results = []
 
-                    for block in content:
-                        if isinstance(block, dict):
-                            if block.get("type") == "text":
-                                text_parts.append(block.get("text", ""))
-                            elif block.get("type") == "tool_result":
-                                # Tool result should be a separate message with role="tool"
-                                tool_call_id = block.get("tool_use_id") or ""
-                                if not tool_call_id:
-                                    logger.warning(f"[MINIMAX] tool_result missing tool_use_id")
-                                result_content = block.get("content", "")
-                                if not isinstance(result_content, str):
-                                    result_content = json.dumps(result_content, ensure_ascii=False)
-                                tool_results.append({
-                                    "role": "tool",
-                                    "tool_call_id": tool_call_id,
-                                    "content": result_content
-                                })
+                        for block in content:
+                            if isinstance(block, dict):
+                                if block.get("type") == "text":
+                                    text_parts.append(block.get("text", ""))
+                                elif block.get("type") == "tool_result":
+                                    tool_call_id = block.get("tool_use_id") or ""
+                                    if not tool_call_id:
+                                        logger.warning(f"[MINIMAX] tool_result missing tool_use_id")
+                                    result_content = block.get("content", "")
+                                    if not isinstance(result_content, str):
+                                        result_content = json.dumps(result_content, ensure_ascii=False)
+                                    tool_results.append({
+                                        "role": "tool",
+                                        "tool_call_id": tool_call_id,
+                                        "content": result_content
+                                    })
 
-                    if text_parts:
-                        converted.append({
-                            "role": "user",
-                            "content": "\n".join(text_parts)
-                        })
+                        if text_parts:
+                            converted.append({
+                                "role": "user",
+                                "content": "\n".join(text_parts)
+                            })
 
-                    # Add all tool results (not just the last one)
-                    for tool_result in tool_results:
-                        converted.append(tool_result)
+                        for tool_result in tool_results:
+                            converted.append(tool_result)
+                    else:
+                        # Keep as-is for multimodal content (e.g. image_url blocks)
+                        converted.append(msg)
                 else:
                     # Simple text content
                     converted.append({

models/moonshot/moonshot_bot.py

@@ -2,6 +2,7 @@
 
 import json
 import time
+from typing import Optional
 
 import requests
 from models.bot import Bot
@@ -147,6 +148,49 @@ class MoonshotBot(Bot):
             else:
                 return result
 
+    def call_vision(self, image_url: str, question: str,
+                    model: Optional[str] = None,
+                    max_tokens: int = 1000) -> dict:
+        """Analyze an image using Moonshot (Kimi) OpenAI-compatible API."""
+        try:
+            vision_model = model or self.args.get("model", "kimi-k2.5")
+            payload = {
+                "model": vision_model,
+                "max_tokens": max_tokens,
+                "messages": [{
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": question},
+                        {"type": "image_url", "image_url": {"url": image_url}},
+                    ],
+                }],
+            }
+            headers = {
+                "Authorization": f"Bearer {self.api_key}",
+                "Content-Type": "application/json",
+            }
+            resp = requests.post(f"{self.base_url}/chat/completions",
+                                 headers=headers, json=payload, timeout=60)
+            if resp.status_code != 200:
+                return {"error": True, "message": f"HTTP {resp.status_code}: {resp.text[:300]}"}
+            data = resp.json()
+            if "error" in data:
+                return {"error": True, "message": data["error"].get("message", str(data["error"]))}
+            content = data.get("choices", [{}])[0].get("message", {}).get("content", "")
+            usage = data.get("usage", {})
+            return {
+                "model": vision_model,
+                "content": content,
+                "usage": {
+                    "prompt_tokens": usage.get("prompt_tokens", 0),
+                    "completion_tokens": usage.get("completion_tokens", 0),
+                    "total_tokens": usage.get("total_tokens", 0),
+                },
+            }
+        except Exception as e:
+            logger.error(f"[MOONSHOT] call_vision error: {e}")
+            return {"error": True, "message": str(e)}
+
     # ==================== Agent mode support ====================
 
     def call_with_tools(self, messages, tools=None, stream: bool = False, **kwargs):
@@ -435,31 +479,37 @@ class MoonshotBot(Bot):
                 continue
 
             if role == "user":
-                text_parts = []
-                tool_results = []
+                has_tool_result = any(
+                    isinstance(b, dict) and b.get("type") == "tool_result" for b in content
+                )
+                if has_tool_result:
+                    text_parts = []
+                    tool_results = []
 
-                for block in content:
-                    if not isinstance(block, dict):
-                        continue
-                    if block.get("type") == "text":
-                        text_parts.append(block.get("text", ""))
-                    elif block.get("type") == "tool_result":
-                        tool_call_id = block.get("tool_use_id") or ""
-                        result_content = block.get("content", "")
-                        if not isinstance(result_content, str):
-                            result_content = json.dumps(result_content, ensure_ascii=False)
-                        tool_results.append({
-                            "role": "tool",
-                            "tool_call_id": tool_call_id,
-                            "content": result_content
-                        })
+                    for block in content:
+                        if not isinstance(block, dict):
+                            continue
+                        if block.get("type") == "text":
+                            text_parts.append(block.get("text", ""))
+                        elif block.get("type") == "tool_result":
+                            tool_call_id = block.get("tool_use_id") or ""
+                            result_content = block.get("content", "")
+                            if not isinstance(result_content, str):
+                                result_content = json.dumps(result_content, ensure_ascii=False)
+                            tool_results.append({
+                                "role": "tool",
+                                "tool_call_id": tool_call_id,
+                                "content": result_content
+                            })
 
-                # Tool results first (must come right after assistant with tool_calls)
-                for tr in tool_results:
-                    converted.append(tr)
+                    for tr in tool_results:
+                        converted.append(tr)
 
-                if text_parts:
-                    converted.append({"role": "user", "content": "\n".join(text_parts)})
+                    if text_parts:
+                        converted.append({"role": "user", "content": "\n".join(text_parts)})
+                else:
+                    # Keep as-is for multimodal content (e.g. image_url blocks)
+                    converted.append(msg)
 
             elif role == "assistant":
                 openai_msg = {"role": "assistant"}

models/openai_compatible_bot.py

@@ -9,6 +9,8 @@ This includes: OpenAI, LinkAI, Azure OpenAI, and many third-party providers.
 
 import json
 import openai
+import requests
+from typing import Optional
 from common.log import logger
 from agent.protocol.message_utils import drop_orphaned_tool_results_openai
 
@@ -306,3 +308,51 @@ class OpenAICompatibleBot:
                 openai_messages.append(msg)
 
         return drop_orphaned_tool_results_openai(openai_messages)
+
+    def call_vision(self, image_url: str, question: str,
+                    model: Optional[str] = None,
+                    max_tokens: int = 1000) -> dict:
+        """Analyze an image using the OpenAI-compatible /chat/completions endpoint."""
+        try:
+            api_config = self.get_api_config()
+            vision_model = model or api_config.get("model", "gpt-4o")
+            api_key = api_config.get("api_key", "")
+            api_base = (api_config.get("api_base") or "https://api.openai.com/v1").rstrip("/")
+
+            payload = {
+                "model": vision_model,
+                "messages": [{
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": question},
+                        {"type": "image_url", "image_url": {"url": image_url}},
+                    ],
+                }],
+            }
+            headers = {
+                "Authorization": f"Bearer {api_key}",
+                "Content-Type": "application/json",
+            }
+            resp = requests.post(
+                f"{api_base}/chat/completions",
+                headers=headers, json=payload, timeout=60,
+            )
+            if resp.status_code != 200:
+                body = resp.text[:500]
+                logger.error(f"[{self.__class__.__name__}] call_vision HTTP {resp.status_code}: {body}")
+                return {"error": True, "message": f"HTTP {resp.status_code}: {body}"}
+            data = resp.json()
+            content = data.get("choices", [{}])[0].get("message", {}).get("content", "")
+            usage = data.get("usage", {})
+            return {
+                "model": vision_model,
+                "content": content,
+                "usage": {
+                    "prompt_tokens": usage.get("prompt_tokens", 0),
+                    "completion_tokens": usage.get("completion_tokens", 0),
+                    "total_tokens": usage.get("total_tokens", 0),
+                },
+            }
+        except Exception as e:
+            logger.error(f"[{self.__class__.__name__}] call_vision error: {e}")
+            return {"error": True, "message": str(e)}

models/zhipuai/zhipuai_bot.py

@@ -2,6 +2,7 @@
 
 import time
 import json
+from typing import Optional
 
 from models.bot import Bot
 from models.zhipuai.zhipu_ai_session import ZhipuAISession
@@ -149,6 +150,40 @@ class ZHIPUAIBot(Bot, ZhipuAIImage):
             else:
                 return result
 
+    def call_vision(self, image_url: str, question: str,
+                    model: Optional[str] = None,
+                    max_tokens: int = 1000) -> dict:
+        """Analyze an image using ZhipuAI OpenAI-compatible SDK.
+        Always uses glm-5v-turbo — the text models (glm-5-turbo etc.) do not support vision.
+        """
+        try:
+            vision_model = "glm-5v-turbo"
+            response = self.client.chat.completions.create(
+                model=vision_model,
+                max_tokens=max_tokens,
+                messages=[{
+                    "role": "user",
+                    "content": [
+                        {"type": "text", "text": question},
+                        {"type": "image_url", "image_url": {"url": image_url}},
+                    ],
+                }],
+            )
+            content = response.choices[0].message.content or ""
+            usage = response.usage
+            return {
+                "model": vision_model,
+                "content": content,
+                "usage": {
+                    "prompt_tokens": getattr(usage, "prompt_tokens", 0),
+                    "completion_tokens": getattr(usage, "completion_tokens", 0),
+                    "total_tokens": getattr(usage, "total_tokens", 0),
+                },
+            }
+        except Exception as e:
+            logger.error(f"[ZHIPU_AI] call_vision error: {e}")
+            return {"error": True, "message": str(e)}
+
     def call_with_tools(self, messages, tools=None, stream=False, **kwargs):
         """
         Call ZhipuAI API with tool support for agent integration