Method call

bridge/agent_bridge.py:139–197

Call the model using COW's bot infrastructure

(self, request: LLMRequest)

        return self._bot

    def call(self, request: LLMRequest):
        """
        Call the model using COW's bot infrastructure
        """
        try:
            # For non-streaming calls, we'll use the existing reply method
            # This is a simplified implementation
            if hasattr(self.bot, 'call_with_tools'):
                # Use tool-enabled call if available
                kwargs = {
                    'messages': request.messages,
                    'tools': getattr(request, 'tools', None),
                    'stream': False,
                    'model': self.model  # Pass model parameter
                }
                # Only pass max_tokens if it's explicitly set
                if request.max_tokens is not None:
                    kwargs['max_tokens'] = request.max_tokens

                # Extract system prompt if present
                system_prompt = getattr(request, 'system', None)
                if system_prompt:
                    kwargs['system'] = system_prompt

                # Pass context metadata to bot
                channel_type = getattr(self, 'channel_type', None) or ''
                if channel_type:
                    kwargs['channel_type'] = channel_type
                session_id = getattr(self, 'session_id', None)
                if session_id:
                    kwargs['session_id'] = session_id

                # Thinking mode is a global toggle independent of the channel.
                # IM channels (WeChat/WeCom/DingTalk/Feishu) won't render the
                # reasoning trace, but still benefit from the higher answer
                # quality the thinking pass produces.
                from config import conf
                thinking_enabled = bool(conf().get("enable_thinking", False))
                kwargs['thinking'] = (
                    {"type": "enabled"} if thinking_enabled
                    else {"type": "disabled"}
                )
                # Reasoning effort is only meaningful when thinking is on.
                # Bots that don't understand the kwarg drop it silently.
                if thinking_enabled:
                    effort = conf().get("reasoning_effort", "high")
                    if effort in ("high", "max"):
                        kwargs['reasoning_effort'] = effort

                response = self.bot.call_with_tools(**kwargs)
                return self._format_response(response)
            else:
                # Fallback to regular call
                # This would need to be implemented based on your specific needs
                raise NotImplementedError("Regular call not implemented yet")
                
        except Exception as e:
            logger.error(f"AgentLLMModel call error: {e}")