claw/src/agent/runtime.rs

use serde_json::{json, Map, Value};

use crate::llm::{ChatMessage, LlmError, LlmProvider, ToolDefinition, ToolFunctionCall};
use crate::pipe::{Action, AgentMessage, BrowserPipeTool, PipeError, Transport};

/// Legacy browser-only runtime kept for dev-only validation and narrow regression coverage.
/// Production browser submit flow uses `compat::runtime` plus `runtime::engine`.
pub const LEGACY_DEV_ONLY: bool = true;

const BROWSER_ACTION_TOOL_NAME: &str = "browser_action";

#[derive(Debug, Clone, PartialEq)]
struct BrowserActionCall {
    action: Action,
    expected_domain: String,
    params: Value,
}

pub fn execute_task_with_provider<P: LlmProvider, T: Transport>(
    transport: &T,
    browser_tool: &BrowserPipeTool<T>,
    provider: &P,
    instruction: &str,
) -> Result<String, PipeError> {
    let messages = vec![
        ChatMessage {
            role: "system".to_string(),
            content: "You are sgClaw. Use browser_action to complete the browser task.".to_string(),
        },
        ChatMessage {
            role: "user".to_string(),
            content: instruction.to_string(),
        },
    ];
    let tools = vec![browser_action_tool_definition()];
    let calls = provider
        .chat(&messages, &tools)
        .map_err(map_llm_error_to_pipe_error)?;

    for call in calls {
        let browser_call =
            parse_browser_action_call(call).map_err(|err| PipeError::Protocol(err.to_string()))?;

        transport.send(&AgentMessage::LogEntry {
            level: "info".to_string(),
            message: format!(
                "{} {}",
                browser_call.action.as_str(),
                browser_call.expected_domain
            ),
        })?;

        let result = browser_tool.invoke(
            browser_call.action,
            browser_call.params,
            &browser_call.expected_domain,
        )?;
        if !result.success {
            return Err(PipeError::Protocol(format!(
                "browser action failed: {}",
                result.data
            )));
        }
    }

    Ok(format!("已通过 Agent 执行任务: {instruction}"))
}

pub fn browser_action_tool_definition() -> ToolDefinition {
    ToolDefinition {
        name: BROWSER_ACTION_TOOL_NAME.to_string(),
        description: "Execute browser actions in SuperRPA".to_string(),
        parameters: json!({
            "type": "object",
            "required": ["action", "expected_domain"],
            "properties": {
                "action": { "type": "string", "enum": ["click", "type", "navigate", "getText"] },
                "expected_domain": { "type": "string" },
                "selector": { "type": "string" },
                "text": { "type": "string" },
                "url": { "type": "string" },
                "clear_first": { "type": "boolean" }
            }
        }),
    }
}

fn parse_browser_action_call(call: ToolFunctionCall) -> Result<BrowserActionCall, RuntimeError> {
    if call.name != BROWSER_ACTION_TOOL_NAME {
        return Err(RuntimeError::UnsupportedTool(call.name));
    }

    let mut args = match call.arguments {
        Value::Object(args) => args,
        other => {
            return Err(RuntimeError::InvalidArguments(format!(
                "expected object arguments, got {other}"
            )))
        }
    };

    let action_name = take_required_string(&mut args, "action")?;
    let expected_domain = take_required_string(&mut args, "expected_domain")?;
    let action = parse_action(&action_name)?;
    let params = Value::Object(action_params_from_args(args));

    Ok(BrowserActionCall {
        action,
        expected_domain,
        params,
    })
}

fn map_llm_error_to_pipe_error(err: LlmError) -> PipeError {
    PipeError::Protocol(err.to_string())
}

fn parse_action(action_name: &str) -> Result<Action, RuntimeError> {
    match action_name {
        "click" => Ok(Action::Click),
        "type" => Ok(Action::Type),
        "navigate" => Ok(Action::Navigate),
        "getText" => Ok(Action::GetText),
        other => Err(RuntimeError::UnsupportedAction(other.to_string())),
    }
}

fn take_required_string(
    args: &mut Map<String, Value>,
    key: &'static str,
) -> Result<String, RuntimeError> {
    match args.remove(key) {
        Some(Value::String(value)) if !value.trim().is_empty() => Ok(value),
        Some(other) => Err(RuntimeError::InvalidArguments(format!(
            "{key} must be a non-empty string, got {other}"
        ))),
        None => Err(RuntimeError::MissingField(key)),
    }
}

fn action_params_from_args(args: Map<String, Value>) -> Map<String, Value> {
    args
}

#[derive(Debug, thiserror::Error)]
enum RuntimeError {
    #[error("unsupported tool: {0}")]
    UnsupportedTool(String),
    #[error("unsupported action: {0}")]
    UnsupportedAction(String),
    #[error("missing required field: {0}")]
    MissingField(&'static str),
    #[error("invalid tool arguments: {0}")]
    InvalidArguments(String),
}