claw/tests/agent_runtime_test.rs

mod common;

use std::fs;
use std::path::PathBuf;
use std::sync::Arc;
use std::time::Duration;

use uuid::Uuid;

use common::MockTransport;
use sgclaw::agent::{
    handle_browser_message, handle_browser_message_with_context, AgentRuntimeContext,
};
use sgclaw::agent::runtime::{browser_action_tool_definition, execute_task_with_provider};
use sgclaw::compat::runtime::CompatTaskContext;
use sgclaw::config::SgClawSettings;
use sgclaw::llm::{ChatMessage, LlmError, LlmProvider, ToolDefinition, ToolFunctionCall};
use sgclaw::pipe::{Action, AgentMessage, BrowserMessage, BrowserPipeTool, Timing};
use sgclaw::security::MacPolicy;

struct FakeProvider {
    calls: Vec<ToolFunctionCall>,
}

impl LlmProvider for FakeProvider {
    fn chat(
        &self,
        _messages: &[ChatMessage],
        _tools: &[ToolDefinition],
    ) -> Result<Vec<ToolFunctionCall>, LlmError> {
        Ok(self.calls.clone())
    }
}

fn provider_path_test_policy() -> MacPolicy {
    policy_for_domains(&["www.baidu.com"])
}

fn direct_runtime_test_policy() -> MacPolicy {
    policy_for_domains(&["95598.sgcc.com.cn"])
}

fn policy_for_domains(domains: &[&str]) -> MacPolicy {
    MacPolicy::from_json_str(
        &serde_json::json!({
            "version": "1.0",
            "domains": { "allowed": domains },
            "pipe_actions": {
                "allowed": ["click", "type", "navigate", "getText", "eval"],
                "blocked": []
            }
        })
        .to_string(),
    )
    .unwrap()
}

fn build_direct_runtime_skill_root() -> PathBuf {
    let root = std::env::temp_dir().join(format!(
        "sgclaw-agent-runtime-skill-root-{}",
        Uuid::new_v4()
    ));
    let skill_dir = root.join("fault-details-report");
    let script_dir = skill_dir.join("scripts");

    fs::create_dir_all(&script_dir).unwrap();
    fs::write(
        skill_dir.join("SKILL.toml"),
        r#"
[skill]
name = "fault-details-report"
description = "Collect 95598 fault detail data via browser eval."
version = "0.1.0"

[[tools]]
name = "collect_fault_details"
description = "Collect structured fault detail rows for a specific period."
kind = "browser_script"
command = "scripts/collect_fault_details.js"

[tools.args]
period = "YYYY-MM period to collect."
"#,
    )
    .unwrap();
    fs::write(
        script_dir.join("collect_fault_details.js"),
        r#"
return {
  fault_type: "outage",
  observed_at: `${args.period}-15 09:00`,
  affected_scope: "line-7",
  expected_domain: args.expected_domain,
  artifact_payload: "report artifact payload"
};
"#,
    )
    .unwrap();

    root
}

fn write_direct_submit_config(workspace_root: &std::path::Path, skill_root: &std::path::Path) -> PathBuf {
    let config_path = workspace_root.join("sgclaw_config.json");
    fs::write(
        &config_path,
        serde_json::json!({
            "providers": [],
            "skillsDir": skill_root,
            "directSubmitSkill": "fault-details-report.collect_fault_details"
        })
        .to_string(),
    )
    .unwrap();
    config_path
}

fn direct_submit_runtime_context(skill_root: &std::path::Path) -> AgentRuntimeContext {
    let workspace_root = std::env::temp_dir().join(format!(
        "sgclaw-agent-runtime-workspace-{}",
        Uuid::new_v4()
    ));
    fs::create_dir_all(&workspace_root).unwrap();
    let config_path = write_direct_submit_config(&workspace_root, skill_root);
    AgentRuntimeContext::new(Some(config_path), workspace_root)
}

fn submit_fault_details_message() -> BrowserMessage {
    BrowserMessage::SubmitTask {
        instruction: "请采集 2026-03 的故障明细并返回结果".to_string(),
        conversation_id: String::new(),
        messages: vec![],
        page_url: "https://95598.sgcc.com.cn/".to_string(),
        page_title: "网上国网".to_string(),
    }
}

fn submit_zhihu_hotlist_export_message() -> BrowserMessage {
    BrowserMessage::SubmitTask {
        instruction: "打开知乎热榜，获取前10条数据，并导出 Excel".to_string(),
        conversation_id: String::new(),
        messages: vec![],
        page_url: String::new(),
        page_title: String::new(),
    }
}

fn direct_submit_mode_logs(sent: &[AgentMessage]) -> Vec<String> {
    sent.iter()
        .filter_map(|message| match message {
            AgentMessage::LogEntry { level, message } if level == "mode" => Some(message.clone()),
            _ => None,
        })
        .collect()
}

fn direct_submit_completion(sent: &[AgentMessage]) -> Option<(bool, String)> {
    sent.iter().find_map(|message| match message {
        AgentMessage::TaskComplete { success, summary } => Some((*success, summary.clone())),
        _ => None,
    })
}

fn success_browser_response(seq: u64, data: serde_json::Value) -> BrowserMessage {
    BrowserMessage::Response {
        seq,
        success: true,
        data,
        aom_snapshot: vec![],
        timing: Timing {
            queue_ms: 1,
            exec_ms: 10,
        },
    }
}

fn report_artifact_browser_response(
    seq: u64,
    status: &str,
    partial_reasons: &[&str],
    detail_rows: Vec<serde_json::Value>,
    summary_rows: Vec<serde_json::Value>,
) -> BrowserMessage {
    success_browser_response(
        seq,
        serde_json::json!({
            "text": {
                "type": "report-artifact",
                "report_name": "fault-details-report",
                "period": "2026-03",
                "selected_range": {
                    "start": "2026-03-08 16:00:00",
                    "end": "2026-03-09 16:00:00"
                },
                "columns": ["qxdbh"],
                "rows": detail_rows,
                "sections": [{
                    "name": "summary-sheet",
                    "columns": ["index"],
                    "rows": summary_rows
                }],
                "counts": {
                    "detail_rows": detail_rows.len(),
                    "summary_rows": summary_rows.len()
                },
                "status": status,
                "partial_reasons": partial_reasons,
                "downstream": {
                    "export": {
                        "attempted": true,
                        "success": status != "blocked" && status != "error",
                        "path": "http://localhost/export.xlsx"
                    },
                    "report_log": {
                        "attempted": true,
                        "success": partial_reasons.is_empty(),
                        "error": partial_reasons
                            .first()
                            .copied()
                            .unwrap_or("")
                    }
                }
            }
        }),
    )
}

#[test]
fn direct_submit_runtime_executes_fault_details_skill_without_provider_path() {
    let skill_root = build_direct_runtime_skill_root();
    let transport = Arc::new(MockTransport::new(vec![success_browser_response(
        1,
        serde_json::json!({
            "text": {
                "fault_type": "outage",
                "observed_at": "2026-03-15 09:00",
                "affected_scope": "line-7"
            }
        }),
    )]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        direct_runtime_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));
    let mut settings = SgClawSettings::from_legacy_deepseek_fields(
        "unused-key".to_string(),
        "http://127.0.0.1:9".to_string(),
        "unused-model".to_string(),
        Some(skill_root.clone()),
    )
    .unwrap();
    settings.direct_submit_skill = Some("fault-details-report.collect_fault_details".to_string());

    let summary = sgclaw::compat::direct_skill_runtime::execute_direct_submit_skill(
        browser_tool,
        "请采集 2026-03 的故障明细并返回结果",
        &CompatTaskContext {
            page_url: Some("https://95598.sgcc.com.cn/".to_string()),
            ..CompatTaskContext::default()
        },
        PathBuf::from(env!("CARGO_MANIFEST_DIR")).as_path(),
        &settings,
    )
    .unwrap();

    assert!(summary.success);
    assert!(summary.summary.contains("fault_type"));
    let sent = transport.sent_messages();
    assert!(sent.iter().all(|message| !matches!(message, AgentMessage::LogEntry { level, message } if level == "info" && message.contains("DeepSeek config loaded"))));
    assert!(matches!(
        &sent[0],
        AgentMessage::Command {
            seq,
            action,
            params,
            security,
        } if *seq == 1
            && action == &Action::Eval
            && security.expected_domain == "95598.sgcc.com.cn"
            && params["script"].as_str().is_some_and(|script| script.contains("2026-03"))
    ));
}

#[test]
fn submit_task_uses_direct_skill_mode_without_llm_configuration() {
    std::env::remove_var("DEEPSEEK_API_KEY");
    std::env::remove_var("DEEPSEEK_BASE_URL");
    std::env::remove_var("DEEPSEEK_MODEL");

    let skill_root = build_direct_runtime_skill_root();
    let runtime_context = direct_submit_runtime_context(&skill_root);
    let transport = Arc::new(MockTransport::new(vec![success_browser_response(
        1,
        serde_json::json!({
            "text": {
                "fault_type": "outage",
                "observed_at": "2026-03-15 09:00",
                "affected_scope": "line-7",
                "artifact_payload": "report artifact payload"
            }
        }),
    )]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        direct_runtime_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));

    handle_browser_message_with_context(
        transport.as_ref(),
        &browser_tool,
        &runtime_context,
        submit_fault_details_message(),
    )
    .unwrap();

    let sent = transport.sent_messages();
    let completion = direct_submit_completion(&sent).expect("task completion");

    assert!(completion.0, "expected direct submit task to succeed: {sent:?}");
    assert!(
        completion.1.contains("report artifact payload"),
        "expected report artifact payload in summary: {}",
        completion.1
    );
    assert!(
        !completion.1.contains("未配置大语言模型"),
        "did not expect missing-llm summary: {}",
        completion.1
    );
}

#[test]
fn submit_task_rejects_invalid_direct_submit_skill_config_before_routing() {
    std::env::remove_var("DEEPSEEK_API_KEY");
    std::env::remove_var("DEEPSEEK_BASE_URL");
    std::env::remove_var("DEEPSEEK_MODEL");

    let skill_root = build_direct_runtime_skill_root();
    let workspace_root = std::env::temp_dir().join(format!(
        "sgclaw-invalid-direct-submit-workspace-{}",
        Uuid::new_v4()
    ));
    fs::create_dir_all(&workspace_root).unwrap();
    let config_path = workspace_root.join("sgclaw_config.json");
    fs::write(
        &config_path,
        serde_json::json!({
            "providers": [],
            "skillsDir": skill_root,
            "directSubmitSkill": "fault-details-report"
        })
        .to_string(),
    )
    .unwrap();

    let runtime_context = AgentRuntimeContext::new(Some(config_path), workspace_root);
    let transport = Arc::new(MockTransport::new(vec![]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        direct_runtime_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));

    handle_browser_message_with_context(
        transport.as_ref(),
        &browser_tool,
        &runtime_context,
        submit_fault_details_message(),
    )
    .unwrap();

    let sent = transport.sent_messages();
    assert!(matches!(
        sent.last(),
        Some(AgentMessage::TaskComplete { success, summary })
            if !success && summary.contains("skill.tool")
    ));
    assert!(direct_submit_mode_logs(&sent).is_empty());
    assert!(!sent.iter().any(|message| matches!(message, AgentMessage::Command { .. })));
}

#[test]
fn submit_task_treats_partial_report_artifact_as_success_with_warning_summary() {
    std::env::remove_var("DEEPSEEK_API_KEY");
    std::env::remove_var("DEEPSEEK_BASE_URL");
    std::env::remove_var("DEEPSEEK_MODEL");

    let skill_root = build_direct_runtime_skill_root();
    let runtime_context = direct_submit_runtime_context(&skill_root);
    let transport = Arc::new(MockTransport::new(vec![report_artifact_browser_response(
        1,
        "partial",
        &["report_log_failed"],
        vec![serde_json::json!({ "qxdbh": "QX-1" })],
        vec![serde_json::json!({ "index": 1 })],
    )]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        direct_runtime_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));

    handle_browser_message_with_context(
        transport.as_ref(),
        &browser_tool,
        &runtime_context,
        submit_fault_details_message(),
    )
    .unwrap();

    let sent = transport.sent_messages();
    let completion = direct_submit_completion(&sent).expect("task completion");

    assert!(completion.0, "expected partial artifact to succeed: {sent:?}");
    assert!(completion.1.contains("fault-details-report"));
    assert!(completion.1.contains("2026-03"));
    assert!(completion.1.contains("status=partial"));
    assert!(completion.1.contains("detail_rows=1"));
    assert!(completion.1.contains("summary_rows=1"));
    assert!(completion.1.contains("report_log_failed"));
}

#[test]
fn submit_task_treats_empty_report_artifact_as_success() {
    std::env::remove_var("DEEPSEEK_API_KEY");
    std::env::remove_var("DEEPSEEK_BASE_URL");
    std::env::remove_var("DEEPSEEK_MODEL");

    let skill_root = build_direct_runtime_skill_root();
    let runtime_context = direct_submit_runtime_context(&skill_root);
    let transport = Arc::new(MockTransport::new(vec![report_artifact_browser_response(
        1,
        "empty",
        &[],
        vec![],
        vec![],
    )]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        direct_runtime_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));

    handle_browser_message_with_context(
        transport.as_ref(),
        &browser_tool,
        &runtime_context,
        submit_fault_details_message(),
    )
    .unwrap();

    let sent = transport.sent_messages();
    let completion = direct_submit_completion(&sent).expect("task completion");

    assert!(completion.0, "expected empty artifact to succeed: {sent:?}");
    assert!(completion.1.contains("status=empty"));
    assert!(completion.1.contains("detail_rows=0"));
}

#[test]
fn submit_task_treats_blocked_report_artifact_as_failure() {
    std::env::remove_var("DEEPSEEK_API_KEY");
    std::env::remove_var("DEEPSEEK_BASE_URL");
    std::env::remove_var("DEEPSEEK_MODEL");

    let skill_root = build_direct_runtime_skill_root();
    let runtime_context = direct_submit_runtime_context(&skill_root);
    let transport = Arc::new(MockTransport::new(vec![report_artifact_browser_response(
        1,
        "blocked",
        &["selected_range_unavailable"],
        vec![],
        vec![],
    )]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        direct_runtime_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));

    handle_browser_message_with_context(
        transport.as_ref(),
        &browser_tool,
        &runtime_context,
        submit_fault_details_message(),
    )
    .unwrap();

    let sent = transport.sent_messages();
    let completion = direct_submit_completion(&sent).expect("task completion");

    assert!(!completion.0, "expected blocked artifact to fail: {sent:?}");
    assert!(completion.1.contains("status=blocked"));
    assert!(completion.1.contains("selected_range_unavailable"));
}

#[test]
fn submit_task_treats_error_report_artifact_as_failure() {
    std::env::remove_var("DEEPSEEK_API_KEY");
    std::env::remove_var("DEEPSEEK_BASE_URL");
    std::env::remove_var("DEEPSEEK_MODEL");

    let skill_root = build_direct_runtime_skill_root();
    let runtime_context = direct_submit_runtime_context(&skill_root);
    let transport = Arc::new(MockTransport::new(vec![report_artifact_browser_response(
        1,
        "error",
        &["detail_normalization_failed"],
        vec![],
        vec![],
    )]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        direct_runtime_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));

    handle_browser_message_with_context(
        transport.as_ref(),
        &browser_tool,
        &runtime_context,
        submit_fault_details_message(),
    )
    .unwrap();

    let sent = transport.sent_messages();
    let completion = direct_submit_completion(&sent).expect("task completion");

    assert!(!completion.0, "expected error artifact to fail: {sent:?}");
    assert!(completion.1.contains("status=error"));
    assert!(completion.1.contains("detail_normalization_failed"));
}

#[test]
fn submit_task_routes_zhihu_hotlist_export_before_direct_submit() {
    std::env::remove_var("DEEPSEEK_API_KEY");
    std::env::remove_var("DEEPSEEK_BASE_URL");
    std::env::remove_var("DEEPSEEK_MODEL");

    let skill_root = build_direct_runtime_skill_root();
    let runtime_context = direct_submit_runtime_context(&skill_root);
    let transport = Arc::new(MockTransport::new(vec![]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        policy_for_domains(&["www.zhihu.com"]),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));

    handle_browser_message_with_context(
        transport.as_ref(),
        &browser_tool,
        &runtime_context,
        submit_zhihu_hotlist_export_message(),
    )
    .unwrap();

    let sent = transport.sent_messages();
    let mode_logs = direct_submit_mode_logs(&sent);
    let completion = direct_submit_completion(&sent).expect("task completion");

    assert_eq!(mode_logs, vec!["zeroclaw_process_message_primary".to_string()]);
    assert!(
        !completion.0,
        "expected zhihu export without page context to fail before browser actions: {sent:?}"
    );
    assert!(
        !completion
            .1
            .contains("direct submit skill requires page_url so expected_domain can be derived"),
        "unexpected direct submit fallback: {sent:?}"
    );
}

#[test]
fn direct_skill_mode_logs_direct_skill_primary() {
    std::env::remove_var("DEEPSEEK_API_KEY");
    std::env::remove_var("DEEPSEEK_BASE_URL");
    std::env::remove_var("DEEPSEEK_MODEL");

    let skill_root = build_direct_runtime_skill_root();
    let runtime_context = direct_submit_runtime_context(&skill_root);
    let transport = Arc::new(MockTransport::new(vec![success_browser_response(
        1,
        serde_json::json!({
            "text": {
                "fault_type": "outage",
                "observed_at": "2026-03-15 09:00",
                "affected_scope": "line-7",
                "artifact_payload": "report artifact payload"
            }
        }),
    )]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        direct_runtime_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));

    handle_browser_message_with_context(
        transport.as_ref(),
        &browser_tool,
        &runtime_context,
        submit_fault_details_message(),
    )
    .unwrap();

    let sent = transport.sent_messages();
    let mode_logs = direct_submit_mode_logs(&sent);

    assert_eq!(mode_logs, vec!["direct_skill_primary".to_string()]);
    assert!(
        !mode_logs.iter().any(|mode| mode == "compat_llm_primary"),
        "unexpected compat mode logs: {mode_logs:?}"
    );
    assert!(
        !mode_logs
            .iter()
            .any(|mode| mode == "zeroclaw_process_message_primary"),
        "unexpected zeroclaw mode logs: {mode_logs:?}"
    );
}

#[test]
fn browser_action_tool_definition_uses_expected_name() {
    let tool = browser_action_tool_definition();

    assert_eq!(tool.name, "browser_action");
    assert_eq!(tool.parameters["required"][0], "action");
    assert_eq!(tool.parameters["required"][1], "expected_domain");
}

#[test]
fn runtime_executes_provider_tool_calls_and_returns_summary() {
    let transport = Arc::new(MockTransport::new(vec![
        BrowserMessage::Response {
            seq: 1,
            success: true,
            data: serde_json::json!({ "navigated": true }),
            aom_snapshot: vec![],
            timing: Timing {
                queue_ms: 1,
                exec_ms: 10,
            },
        },
        BrowserMessage::Response {
            seq: 2,
            success: true,
            data: serde_json::json!({ "typed": true }),
            aom_snapshot: vec![],
            timing: Timing {
                queue_ms: 1,
                exec_ms: 10,
            },
        },
    ]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        provider_path_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));
    let provider = FakeProvider {
        calls: vec![
            ToolFunctionCall {
                id: "call-1".to_string(),
                name: "browser_action".to_string(),
                arguments: serde_json::json!({
                    "action": "navigate",
                    "expected_domain": "www.baidu.com",
                    "url": "https://www.baidu.com"
                }),
            },
            ToolFunctionCall {
                id: "call-2".to_string(),
                name: "browser_action".to_string(),
                arguments: serde_json::json!({
                    "action": "type",
                    "expected_domain": "www.baidu.com",
                    "selector": "#kw",
                    "text": "天气",
                    "clear_first": true
                }),
            },
        ],
    };

    let summary = execute_task_with_provider(
        transport.as_ref(),
        &browser_tool,
        &provider,
        "打开百度搜索天气",
    )
    .unwrap();
    let sent = transport.sent_messages();

    assert_eq!(summary, "已通过 Agent 执行任务: 打开百度搜索天气");
    assert!(matches!(
        &sent[0],
        AgentMessage::LogEntry { level, message }
            if level == "info" && message == "navigate www.baidu.com"
    ));
    assert!(matches!(
        &sent[1],
        AgentMessage::Command { seq, action, .. }
            if *seq == 1 && action == &Action::Navigate
    ));
    assert!(matches!(
        &sent[2],
        AgentMessage::LogEntry { level, message }
            if level == "info" && message == "type www.baidu.com"
    ));
    assert!(matches!(
        &sent[3],
        AgentMessage::Command { seq, action, .. }
            if *seq == 2 && action == &Action::Type
    ));
}

#[test]
fn legacy_agent_runtime_is_explicitly_dev_only() {
    assert!(sgclaw::agent::runtime::LEGACY_DEV_ONLY);
}

#[test]
fn production_submit_task_does_not_route_into_legacy_runtime_without_llm_config() {
    std::env::remove_var("DEEPSEEK_API_KEY");
    std::env::remove_var("DEEPSEEK_BASE_URL");
    std::env::remove_var("DEEPSEEK_MODEL");

    let transport = Arc::new(MockTransport::new(vec![]));
    let browser_tool = BrowserPipeTool::new(
        transport.clone(),
        provider_path_test_policy(),
        vec![1, 2, 3, 4, 5, 6, 7, 8],
    )
    .with_response_timeout(Duration::from_secs(1));

    handle_browser_message(
        transport.as_ref(),
        &browser_tool,
        BrowserMessage::SubmitTask {
            instruction: "打开百度".to_string(),
            conversation_id: String::new(),
            messages: vec![],
            page_url: String::new(),
            page_title: String::new(),
        },
    )
    .unwrap();

    let sent = transport.sent_messages();
    assert!(matches!(
        sent.last(),
        Some(AgentMessage::TaskComplete { success, summary })
            if !success && summary.contains("未配置大语言模型")
    ));
    assert!(!sent
        .iter()
        .any(|message| { matches!(message, AgentMessage::Command { .. }) }));
}