feat: add generated scene skill platform hardening

This commit is contained in:
木炎
2026-04-21 23:19:06 +08:00
parent 118fc77935
commit 956f0c2b68
439 changed files with 61974 additions and 3645 deletions

View File

@@ -8,14 +8,13 @@ use std::sync::{Arc, Mutex, OnceLock};
use std::thread;
use std::time::Duration;
use chrono::{Datelike, Local};
use common::MockTransport;
use serde_json::{json, Value};
use sgclaw::agent::{
handle_browser_message, handle_browser_message_with_context, AgentRuntimeContext,
};
use sgclaw::compat::workflow_executor::finalize_screen_export;
use sgclaw::compat::runtime::{execute_task, execute_task_with_sgclaw_settings, CompatTaskContext};
use sgclaw::compat::workflow_executor::finalize_screen_export;
use sgclaw::config::{DeepSeekSettings, SgClawSettings};
use sgclaw::pipe::{
Action, AgentMessage, BrowserMessage, BrowserPipeTool, ConversationMessage, Timing,
@@ -268,7 +267,9 @@ fn task_complete_summary(sent: &[AgentMessage]) -> String {
AgentMessage::TaskComplete { success, summary } if *success => Some(summary.clone()),
_ => None,
})
.unwrap_or_else(|| panic!("expected successful task completion, sent messages were: {sent:?}"))
.unwrap_or_else(|| {
panic!("expected successful task completion, sent messages were: {sent:?}")
})
}
fn extract_generated_artifact_path(summary: &str, extension: &str) -> PathBuf {
@@ -279,24 +280,6 @@ fn extract_generated_artifact_path(summary: &str, extension: &str) -> PathBuf {
.expect("expected artifact path in task summary")
}
fn expected_default_month() -> String {
let today = Local::now().date_naive();
let (year, month) = if today.month() == 1 {
(today.year() - 1, 12)
} else {
(today.year(), today.month() - 1)
};
format!("{year}-{month:02}")
}
fn expected_default_week_range() -> (String, String, String) {
let today = Local::now().date_naive();
let month_start = today.with_day(1).expect("current month should have day 1");
let start = month_start.format("%Y-%m-%d").to_string();
let end = today.format("%Y-%m-%d").to_string();
(format!("{start}{end}"), start, end)
}
#[test]
fn compat_runtime_uses_zeroclaw_provider_path_and_executes_browser_actions() {
let _guard = env_lock().lock().unwrap_or_else(|err| err.into_inner());
@@ -2217,7 +2200,9 @@ fn handle_browser_message_chains_hotlist_skill_into_xlsx_export_and_auto_open()
let summary = task_complete_summary(&sent);
let generated = extract_generated_artifact_path(&summary, ".xlsx");
assert!(summary.contains("已导出知乎热榜 Excel") || summary.contains("已导出并打开知乎热榜 Excel"));
assert!(
summary.contains("已导出知乎热榜 Excel") || summary.contains("已导出并打开知乎热榜 Excel")
);
assert!(summary.contains(".xlsx"));
assert!(generated.exists());
assert!(sent.iter().any(|message| {
@@ -2333,7 +2318,10 @@ fn handle_browser_message_chains_hotlist_skill_into_screen_export_and_auto_open(
security,
..
} if action == &Action::Navigate
&& security.expected_domain == "__sgclaw_local_dashboard__" => Some((params, security)),
&& security.expected_domain == "__sgclaw_local_dashboard__" =>
{
Some((params, security))
}
_ => None,
})
.expect("dashboard route should emit local-dashboard navigate request");
@@ -2405,7 +2393,8 @@ fn handle_browser_message_chains_hotlist_skill_into_screen_export_and_auto_open(
}
#[test]
fn handle_browser_message_reports_dashboard_auto_open_protocol_error_when_presentation_url_is_missing() {
fn handle_browser_message_reports_dashboard_auto_open_protocol_error_when_presentation_url_is_missing(
) {
let _guard = env_lock().lock().unwrap_or_else(|err| err.into_inner());
let transport = Arc::new(MockTransport::new(vec![]));
@@ -2437,7 +2426,8 @@ fn handle_browser_message_reports_dashboard_auto_open_protocol_error_when_presen
assert!(summary.contains("已生成知乎热榜大屏"));
assert!(summary.contains(output_path.to_string_lossy().as_ref()));
assert!(summary.contains("但浏览器自动打开失败screen_html_export did not return presentation.url"));
assert!(summary
.contains("但浏览器自动打开失败screen_html_export did not return presentation.url"));
let sent = transport.sent_messages();
assert!(!sent.iter().any(|message| {
@@ -2710,11 +2700,13 @@ fn ws_cleanup_no_longer_detects_fault_details_scene_route() {
#[test]
fn ws_cleanup_scene_keywords_do_not_trigger_primary_orchestration() {
assert!(!sgclaw::compat::orchestration::should_use_primary_orchestration(
"请处理95598抢修市指监测",
Some("https://95598.example.invalid/dispatch"),
Some("95598抢修市指监测"),
));
assert!(
!sgclaw::compat::orchestration::should_use_primary_orchestration(
"请处理95598抢修市指监测",
Some("https://95598.example.invalid/dispatch"),
Some("95598抢修市指监测"),
)
);
}
#[test]
@@ -3916,7 +3908,7 @@ fn handle_browser_message_executes_real_zhihu_write_skill_flow() {
}
fn staged_lineloss_skills_root() -> PathBuf {
PathBuf::from("D:/data/ideaSpace/rust/sgClaw/claw/claw/skills/skill_staging/skills")
PathBuf::from("D:/data/ideaSpace/rust/sgClaw/claw-new/examples/generated_scene_platform/skills")
}
fn build_fault_details_direct_skill_root() -> PathBuf {
@@ -4033,9 +4025,10 @@ fn deterministic_lineloss_runtime_passes_canonical_args_to_browser_script_tool()
AgentMessage::TaskComplete { success, summary }
if *success
&& summary.contains("tq-lineloss-report")
&& summary.contains("国网兰州供电公司")
&& summary.contains("2026-03")
&& summary.contains("rows=1")
&& summary.contains("status=ok")
&& summary.contains("detail_rows=1")
&& summary.contains("summary_rows=0")
)
}));
assert!(sent.iter().any(|message| {
@@ -4064,7 +4057,6 @@ fn deterministic_lineloss_runtime_passes_canonical_args_to_browser_script_tool()
#[test]
fn deterministic_lineloss_runtime_defaults_missing_month_period_to_page_semantics() {
let _guard = env_lock().lock().unwrap_or_else(|err| err.into_inner());
let expected_month = expected_default_month();
let workspace_root = temp_workspace_root();
let config_path = write_deepseek_config_with_skills_dir(
@@ -4076,35 +4068,7 @@ fn deterministic_lineloss_runtime_defaults_missing_month_period_to_page_semantic
);
let runtime_context = AgentRuntimeContext::new(Some(config_path), workspace_root.clone());
let transport = Arc::new(MockTransport::new(vec![success_browser_response(
1,
json!({
"text": {
"type": "report-artifact",
"report_name": "tq-lineloss-report",
"status": "ok",
"org": {
"label": "国网兰州供电公司",
"code": "62401"
},
"period": {
"mode": "month",
"mode_code": "1",
"value": expected_month,
"payload": {
"fdate": expected_default_month()
}
},
"rows": [
{ "ORG_NAME": "国网兰州供电公司", "LINE_LOSS_RATE": "3.21" }
],
"counts": {
"rows": 1
},
"reasons": []
}
}),
)]));
let transport = Arc::new(MockTransport::new(vec![]));
let browser_tool = BrowserPipeTool::new(
transport.clone(),
policy_for_domains(&["20.76.57.61"]),
@@ -4132,39 +4096,18 @@ fn deterministic_lineloss_runtime_defaults_missing_month_period_to_page_semantic
matches!(
message,
AgentMessage::TaskComplete { success, summary }
if *success
&& summary.contains("tq-lineloss-report")
&& summary.contains("国网兰州供电公司")
&& summary.contains(&expected_default_month())
&& summary.contains("rows=1")
)
}));
assert!(sent.iter().any(|message| {
matches!(
message,
AgentMessage::Command {
action,
params,
security,
..
}
if action == &Action::Eval
&& security.expected_domain == "20.76.57.61"
&& params["script"].as_str().is_some_and(|script|
script.contains("\"period_mode\":\"month\"")
&& script.contains("\"period_mode_code\":\"1\"")
&& script.contains(&format!("\"period_value\":\"{}\"", expected_default_month()))
&& script.contains("\"period_payload\":\"{")
&& script.contains(&format!("\\\"fdate\\\":\\\"{}\\\"", expected_default_month()))
)
if !*success
&& summary.contains("已命中台区线损报表技能但缺少统计周期请补充如“2026-03”或“2026年第12周”。")
)
}), "sent messages were: {sent:?}");
assert!(!sent
.iter()
.any(|message| matches!(message, AgentMessage::Command { .. })));
}
#[test]
fn deterministic_lineloss_runtime_defaults_missing_week_period_to_page_semantics() {
let _guard = env_lock().lock().unwrap_or_else(|err| err.into_inner());
let (expected_value, expected_start, expected_end) = expected_default_week_range();
let workspace_root = temp_workspace_root();
let config_path = write_deepseek_config_with_skills_dir(
@@ -4176,38 +4119,7 @@ fn deterministic_lineloss_runtime_defaults_missing_week_period_to_page_semantics
);
let runtime_context = AgentRuntimeContext::new(Some(config_path), workspace_root.clone());
let transport = Arc::new(MockTransport::new(vec![success_browser_response(
1,
json!({
"text": {
"type": "report-artifact",
"report_name": "tq-lineloss-report",
"status": "ok",
"org": {
"label": "国网兰州供电公司",
"code": "62401"
},
"period": {
"mode": "week",
"mode_code": "2",
"value": expected_value,
"payload": {
"tjzq": "week",
"level": "00",
"weekSfdate": expected_start,
"weekEfdate": expected_end
}
},
"rows": [
{ "ORG_NAME3": "国网兰州供电公司", "LINELOSS_RATE": "3.21" }
],
"counts": {
"rows": 1
},
"reasons": []
}
}),
)]));
let transport = Arc::new(MockTransport::new(vec![]));
let browser_tool = BrowserPipeTool::new(
transport.clone(),
policy_for_domains(&["20.76.57.61"]),
@@ -4235,34 +4147,13 @@ fn deterministic_lineloss_runtime_defaults_missing_week_period_to_page_semantics
matches!(
message,
AgentMessage::TaskComplete { success, summary }
if *success
&& summary.contains("tq-lineloss-report")
&& summary.contains("国网兰州供电公司")
&& summary.contains(&expected_value)
&& summary.contains("rows=1")
)
}));
assert!(sent.iter().any(|message| {
matches!(
message,
AgentMessage::Command {
action,
params,
security,
..
}
if action == &Action::Eval
&& security.expected_domain == "20.76.57.61"
&& params["script"].as_str().is_some_and(|script|
script.contains("\"period_mode\":\"week\"")
&& script.contains("\"period_mode_code\":\"2\"")
&& script.contains(&format!("\"period_value\":\"{}\"", expected_value))
&& script.contains("\"period_payload\":\"{")
&& script.contains(&format!("\\\"weekSfdate\\\":\\\"{}\\\"", expected_start))
&& script.contains(&format!("\\\"weekEfdate\\\":\\\"{}\\\"", expected_end))
)
if !*success
&& summary.contains("已命中台区线损报表技能但缺少统计周期请补充如“2026-03”或“2026年第12周”。")
)
}), "sent messages were: {sent:?}");
assert!(!sent
.iter()
.any(|message| matches!(message, AgentMessage::Command { .. })));
}
#[test]
@@ -4307,10 +4198,13 @@ fn deterministic_lineloss_missing_company_prompt_skips_browser_execution() {
matches!(
message,
AgentMessage::TaskComplete { success, summary }
if !*success && (summary.contains("缺少供电单位") || summary.contains("兰州公司"))
if !*success
&& summary.contains("已命中台区线损报表技能,但缺少供电单位。")
)
}));
assert!(!sent.iter().any(|message| matches!(message, AgentMessage::Command { .. })));
assert!(!sent
.iter()
.any(|message| matches!(message, AgentMessage::Command { .. })));
}
#[test]
@@ -4385,7 +4279,8 @@ fn deterministic_lineloss_runtime_maps_partial_artifact_to_success_summary() {
AgentMessage::TaskComplete { success, summary }
if *success
&& summary.contains("status=partial")
&& summary.contains("rows=1")
&& summary.contains("detail_rows=1")
&& summary.contains("summary_rows=0")
&& summary.contains("reasons=report_log_failed")
)
}));
@@ -4508,10 +4403,13 @@ fn deterministic_suffix_non_lineloss_request_does_not_fall_into_zhihu_logic() {
matches!(
message,
AgentMessage::TaskComplete { success, summary }
if !*success && summary.contains("台区线损")
if !*success
&& summary.contains("确定性提交当前只支持已注册的报表采集场景")
)
}));
assert!(!sent.iter().any(|message| matches!(message, AgentMessage::Command { .. })));
assert!(!sent
.iter()
.any(|message| matches!(message, AgentMessage::Command { .. })));
assert!(!sent.iter().any(|message| {
matches!(
message,