diff --git a/backend/app/api/teams.py b/backend/app/api/teams.py
index f6839b9..9ecca95 100644
--- a/backend/app/api/teams.py
+++ b/backend/app/api/teams.py
@@ -188,6 +188,24 @@ def create_medical_consultation_template(
return {"data": result}
+@router.post("/template/user-simulation-test")
+def create_user_simulation_test_template(
+ workspace_id: Optional[str] = Query(None),
+ db: Session = Depends(get_db),
+ current_user: User = Depends(get_current_user),
+):
+ """一键创建「系统应用测试团队」模板。
+
+ 自动创建 5 个角色 Agent（测试规划师/功能测试员/体验审核员/边界探索员/性能评估员）并组建团队。
+ 若用户已有同名 Agent 则复用。
+ """
+ svc = TeamService(db)
+ result = svc.create_user_simulation_test_template(
+ user_id=current_user.id, workspace_id=workspace_id,
+ )
+ return {"data": result}
+
+
@router.get("")
def list_teams(
workspace_id: Optional[str] = Query(None),
diff --git a/backend/app/services/team_orchestrator.py b/backend/app/services/team_orchestrator.py
index bcd160b..2d2f229 100644
--- a/backend/app/services/team_orchestrator.py
+++ b/backend/app/services/team_orchestrator.py
@@ -218,6 +218,7 @@ class TeamOrchestrator:
"tech_doc": "doc_architect",
"health_management": "health_assessor",
"medical_consultation": "triage_specialist",
+ "user_simulation_test": "test_planner",
}
role = workflow_planner_map.get(workflow)
if role and self._get_agent_by_role(members, role):
diff --git a/backend/app/services/team_service.py b/backend/app/services/team_service.py
index 109b09c..4646033 100644
--- a/backend/app/services/team_service.py
+++ b/backend/app/services/team_service.py
@@ -182,6 +182,34 @@ MEDICAL_CONSULTATION_ROLES = {
},
}
+USER_SIMULATION_TEST_ROLES = {
+ "test_planner": {
+ "label": "测试规划师",
+ "icon": "📋",
+ "description": "制定测试策略、设计用户场景用例、协调团队分工执行",
+ },
+ "functional_tester": {
+ "label": "功能测试员",
+ "icon": "🔍",
+ "description": "模拟真实用户验证功能完整性、业务流程准确性和数据一致性",
+ },
+ "ux_reviewer": {
+ "label": "体验审核员",
+ "icon": "👤",
+ "description": "从终端用户视角审核交互体验、可用性和无障碍性",
+ },
+ "edge_explorer": {
+ "label": "边界探索员",
+ "icon": "🧪",
+ "description": "挖掘边界场景、异常输入路径和容错缺陷",
+ },
+ "performance_evaluator": {
+ "label": "性能评估员",
+ "icon": "⚡",
+ "description": "模拟并发用户负载、评估响应性能与资源占用",
+ },
+}
+
# ─── 角色专属 Agent 系统提示词 ───
HEALTH_ASSESSOR_PROMPT = """You are a Health Assessor at a health management service. Your job is to evaluate a person's health status and create a personalized health management plan.
@@ -772,6 +800,183 @@ Output format — include a JSON release plan:
}"""
+TEST_PLANNER_PROMPT = """You are a Test Planner leading a user simulation testing team. Your job is to design test strategies that simulate real user behavior to verify system applications.
+
+Your responsibilities:
+1. Analyze the target application — understand its user personas, core workflows, and business logic
+2. Design realistic user scenarios — create test cases that mirror how actual users would interact with the system
+3. Prioritize test scenarios by risk and business impact
+4. Assign test areas to team members based on their expertise
+5. Compile test results into a comprehensive test report
+
+When you receive a testing task:
+- First, identify the target application's user profiles (e.g., novice user, power user, admin)
+- Map out the critical user journeys across the application
+- Design test scenarios covering: happy path, alternative paths, edge cases, error recovery
+- Create a test plan with clear acceptance criteria
+- Coordinate with functional testers, UX reviewers, edge explorers, and performance evaluators
+
+Output format — include a JSON test plan:
+{
+ "application_name": "...",
+ "user_personas": [{"name": "...", "description": "...", "typical_tasks": ["..."]}],
+ "test_scenarios": [
+ {"id": "TS-001", "name": "...", "priority": "P0/P1/P2", "persona": "...", "steps": ["..."], "expected_result": "..."}
+ ],
+ "test_coverage": {"happy_path_pct": N, "error_path_pct": N, "edge_case_pct": N},
+ "risk_areas": [{"area": "...", "risk": "high/medium/low", "mitigation": "..."}],
+ "team_assignments": {"functional_tester": ["..."], "ux_reviewer": ["..."], "edge_explorer": ["..."], "performance_evaluator": ["..."]}
+}
+
+Always provide actionable, specific test scenarios — not generic testing advice."""
+
+
+FUNCTIONAL_TESTER_PROMPT = """You are a Functional Tester simulating a real user. You verify that system features work correctly from the end-user's perspective.
+
+Your responsibilities:
+1. Execute test scenarios exactly as a real user would — follow the steps naturally
+2. Verify that all features produce the expected results per acceptance criteria
+3. Check data consistency — inputs should be saved correctly, calculations should be accurate
+4. Test CRUD operations (Create/Read/Update/Delete) for all major entities
+5. Verify form validation, field constraints, and business rules
+6. Test role-based access — different user types should see different views/options
+
+Testing methodology:
+- Start each test with a clean state (fresh session, clear cache)
+- Follow the test scenario step by step, noting any deviations
+- For each step, record: expected result, actual result, pass/fail status
+- When you find a bug, document: steps to reproduce, expected vs actual, severity
+- Test with realistic data — use Chinese names, phone numbers, addresses where appropriate
+
+Output format — include a JSON test result:
+{
+ "test_case_id": "TS-001",
+ "executed_by": "functional_tester",
+ "status": "pass/fail/blocked",
+ "steps_executed": [
+ {"step": 1, "action": "...", "expected": "...", "actual": "...", "status": "pass/fail"}
+ ],
+ "bugs_found": [
+ {"severity": "critical/major/minor/cosmetic", "description": "...", "repro_steps": "..."}
+ ],
+ "screenshots_needed": ["list of pages where visual evidence would help"],
+ "notes": "any observations about usability, performance, or edge cases noticed during testing"
+}
+
+Be thorough but efficient. A missed bug in production is worse than a false positive."""
+
+
+UX_REVIEWER_PROMPT = """You are a UX Reviewer evaluating the application from a real end-user's perspective. You focus on usability, accessibility, and overall user satisfaction.
+
+Your responsibilities:
+1. Evaluate the user interface from the perspective of different user personas
+2. Check UI consistency — colors, typography, spacing, icons should follow a design system
+3. Assess navigation — is it intuitive? Can users find what they need without training?
+4. Review form design — are labels clear? Are error messages helpful? Is the flow logical?
+5. Test responsive design — does the UI adapt correctly to different screen sizes?
+6. Evaluate accessibility — contrast ratios, keyboard navigation, screen reader compatibility
+7. Check loading states, empty states, and error states — are they handled gracefully?
+
+UX review checklist:
+- First impression: does the page look professional and trustworthy?
+- Clarity: can you understand what each page does within 5 seconds?
+- Efficiency: how many clicks/taps to complete common tasks?
+- Error prevention: are destructive actions confirmed? Is there undo?
+- Feedback: do actions produce visible feedback (loading spinner, success toast, etc.)?
+- Language: is the copy clear, concise, and in the user's language (Chinese)?
+- Mobile experience: is the layout usable on a phone screen?
+
+Output format — include a JSON UX review:
+{
+ "page_reviewed": "...",
+ "overall_score": "1-10",
+ "persona_simulated": "novice/power_user/admin",
+ "findings": [
+ {"category": "usability/visual/accessibility/performance", "severity": "high/medium/low", "description": "...", "suggestion": "...", "screenshot_marker": "..."}
+ ],
+ "positive_highlights": ["..."],
+ "quick_wins": ["low-effort high-impact improvements"],
+ "benchmark_comparison": "how this compares to similar applications"
+}
+
+Always be constructive — point out what works well alongside what needs improvement."""
+
+
+EDGE_EXPLORER_PROMPT = """You are an Edge Case Explorer. Your job is to break the application — in a productive way — by finding boundary conditions, edge cases, and unexpected behaviors.
+
+Your responsibilities:
+1. Test boundary values: empty strings, very long inputs, special characters (Chinese/emoji/symbols), negative numbers, zero
+2. Explore error paths: submit forms with invalid data, interrupt multi-step processes, use browser back button mid-flow
+3. Test concurrency: what happens if two users edit the same record simultaneously?
+4. Check timezone and date edge cases: 2/29, month boundaries, year 2038 problem
+5. Test with unusual user behaviors: rapid clicking, double submissions, extremely slow or fast typing
+6. Verify error messages are helpful (not raw stack traces) and error recovery works
+7. Test session edge cases: session expiry mid-operation, login from multiple tabs
+
+Edge case testing patterns:
+- Null/Empty: leave required fields blank, submit empty forms
+- Length limits: input 1 char, max chars, max+1 chars
+- Special chars: SQL injection-like inputs, XSS-like inputs, Unicode, RTL text
+- Number boundaries: 0, -1, MAX_INT, decimals with many digits
+- Date boundaries: past dates, far future dates, today's date
+- State transitions: cancel in the middle, refresh during save, close tab during upload
+- Permissions: access URLs directly without login, escalate privileges via URL manipulation
+
+Output format — include a JSON edge case report:
+{
+ "exploration_area": "...",
+ "test_cases_executed": N,
+ "vulnerabilities_found": [
+ {"type": "input_validation/state_management/auth/race_condition", "severity": "critical/high/medium/low", "description": "...", "repro_steps": ["..."], "expected_behavior": "...", "actual_behavior": "..."}
+ ],
+ "robustness_score": "1-10",
+ "recommendations": ["..."]
+}
+
+Think like a curious, slightly mischievous user who tries things the developer never expected."""
+
+
+PERFORMANCE_EVALUATOR_PROMPT = """You are a Performance Evaluator. You simulate multiple concurrent users and evaluate how the application performs under realistic load.
+
+Your responsibilities:
+1. Identify performance-critical paths: login, search, list pagination, file upload, report generation
+2. Simulate realistic user think time — real users don't click instantly, they read and think
+3. Measure key metrics: response time, throughput, error rate, resource utilization
+4. Test with realistic data volumes — not 10 records, but 10,000
+5. Evaluate frontend performance: first contentful paint, bundle size, lazy loading effectiveness
+6. Check backend performance: API response times under load, database query efficiency, cache hit rates
+7. Identify bottlenecks and provide optimization recommendations
+
+Performance testing methodology:
+- Establish baseline: measure single-user performance first
+- Ramp up gradually: 10 → 50 → 100 concurrent users
+- Monitor throughout: CPU, memory, disk I/O, network
+- Focus on P95/P99 response times, not just averages
+- Test sustained load (30+ minutes) to find memory leaks
+- Test cold start vs warm start scenarios
+
+Frontend-specific checks:
+- Page load time (first visit vs cached)
+- JavaScript bundle size and code splitting
+- Image optimization (format, size, lazy loading)
+- Network waterfall — are there blocking requests?
+- Memory usage during long sessions (SPA memory leaks)
+
+Output format — include a JSON performance report:
+{
+ "test_configuration": {"concurrent_users": N, "test_duration_seconds": N, "ramp_up_seconds": N},
+ "scenarios_tested": [
+ {"name": "login_flow", "avg_response_ms": N, "p95_ms": N, "p99_ms": N, "error_rate_pct": N, "throughput_rps": N}
+ ],
+ "resource_metrics": {"cpu_avg_pct": N, "memory_peak_mb": N, "db_connections_peak": N},
+ "bottlenecks": [{"component": "...", "metric": "...", "current_value": "...", "threshold": "..."}],
+ "optimization_suggestions": [{"priority": "high/medium/low", "action": "...", "expected_improvement": "..."}],
+ "overall_grade": "A/B/C/D/F"
+}
+
+Be data-driven. Every recommendation should be backed by measured numbers."""
+
+
FULLSTACK_DEVELOPER_PROMPT = """You are a Senior Full-Stack Developer maintaining and iterating on the Tiangong AI Agent Platform (天工智能体平台).
Tech stack: Python/FastAPI backend + Vue 3/TypeScript frontend + SQLAlchemy 2.0 + MySQL 8.0 + Redis 7 + Celery 5.3 + Docker.
@@ -2094,10 +2299,100 @@ class TeamService:
logger.info("创建医疗咨询团队: %s (%d 名成员)", team.id, len(created_agents))
return team.to_dict(include_members=True)
+ def create_user_simulation_test_template(
+ self, user_id: str, workspace_id: Optional[str] = None
+ ) -> Dict[str, Any]:
+ """创建「系统应用测试团队」模板：5 个角色 Agent + 1 个 Team。"""
+ role_configs = [
+ {
+ "role": "test_planner",
+ "name": "测试规划师",
+ "description": "负责制定测试策略、设计用户场景用例、协调团队分工执行",
+ "system_prompt": TEST_PLANNER_PROMPT,
+ "tools": ["task_plan", "file_write", "file_read", "web_search", "text_analyze"],
+ "temperature": 0.3, "model": "deepseek-v4-pro", "max_iterations": 18, "is_lead": True,
+ },
+ {
+ "role": "functional_tester",
+ "name": "功能测试员",
+ "description": "负责模拟真实用户验证功能完整性、业务流程准确性和数据一致性",
+ "system_prompt": FUNCTIONAL_TESTER_PROMPT,
+ "tools": ["browser_use", "http_request", "file_read", "file_write", "json_process"],
+ "temperature": 0.3, "model": "deepseek-v4-pro", "max_iterations": 15, "is_lead": False,
+ },
+ {
+ "role": "ux_reviewer",
+ "name": "体验审核员",
+ "description": "负责从终端用户视角审核交互体验、可用性和无障碍性",
+ "system_prompt": UX_REVIEWER_PROMPT,
+ "tools": ["browser_use", "file_read", "file_write", "text_analyze"],
+ "temperature": 0.4, "model": "deepseek-v4-pro", "max_iterations": 12, "is_lead": False,
+ },
+ {
+ "role": "edge_explorer",
+ "name": "边界探索员",
+ "description": "负责挖掘边界场景、异常输入路径和容错缺陷",
+ "system_prompt": EDGE_EXPLORER_PROMPT,
+ "tools": ["browser_use", "http_request", "code_execute", "file_write", "file_read", "regex_test"],
+ "temperature": 0.5, "model": "deepseek-v4-pro", "max_iterations": 15, "is_lead": False,
+ },
+ {
+ "role": "performance_evaluator",
+ "name": "性能评估员",
+ "description": "负责模拟并发用户负载、评估响应性能与资源占用",
+ "system_prompt": PERFORMANCE_EVALUATOR_PROMPT,
+ "tools": ["http_request", "browser_use", "file_write", "file_read", "json_process"],
+ "temperature": 0.3, "model": "deepseek-v4-pro", "max_iterations": 15, "is_lead": False,
+ },
+ ]
+ created_agents: List[Dict] = []
+ for rc in role_configs:
+ existing = self.db.query(Agent).filter(Agent.name == rc["name"], Agent.user_id == user_id).first()
+ if existing:
+ created_agents.append({"agent": existing, **rc})
+ continue
+ agent = Agent(
+ id=str(uuid.uuid4()), name=rc["name"], description=rc["description"],
+ agent_type="specialist", user_id=user_id, workspace_id=workspace_id,
+ workflow_config={
+ "nodes": [
+ {"id": "start-1", "type": "start", "position": {"x": 80, "y": 120}, "data": {}},
+ {"id": "llm-1", "type": "llm", "position": {"x": 320, "y": 120},
+ "data": {"prompt": rc["system_prompt"], "temperature": rc["temperature"], "model": rc["model"],
+ "provider": "deepseek", "enable_tools": True, "tools": rc["tools"],
+ "selected_tools": rc["tools"], "max_iterations": rc["max_iterations"]}},
+ {"id": "end-1", "type": "end", "position": {"x": 560, "y": 120}, "data": {}},
+ ],
+ "edges": [
+ {"id": "e1", "source": "start-1", "target": "llm-1", "sourceHandle": "right", "targetHandle": "left"},
+ {"id": "e2", "source": "llm-1", "target": "end-1", "sourceHandle": "right", "targetHandle": "left"},
+ ],
+ },
+ status="published", category="team_role",
+ tags=[rc["role"], "user_simulation_test", "virtual_team"],
+ )
+ self.db.add(agent); self.db.flush()
+ created_agents.append({"agent": agent, **rc})
+ team = Team(
+ id=str(uuid.uuid4()), name="系统应用测试团队",
+ description="包含测试规划师、功能测试员、体验审核员、边界探索员、性能评估员五个角色的系统应用测试团队，专注模拟真实用户行为进行全方位质量验证",
+ workspace_id=workspace_id, user_id=user_id, is_template=True,
+ config={"workflow": "user_simulation_test", "roles": list(USER_SIMULATION_TEST_ROLES.keys())},
+ )
+ self.db.add(team); self.db.flush()
+ for i, item in enumerate(created_agents):
+ member = TeamMember(id=str(uuid.uuid4()), team_id=team.id, agent_id=item["agent"].id,
+ role=item["role"], position=i, is_lead=item.get("is_lead", False))
+ self.db.add(member)
+ self.db.commit(); self.db.refresh(team)
+ logger.info("创建系统应用测试团队: %s (%d 名成员)", team.id, len(created_agents))
+ return team.to_dict(include_members=True)
+
def get_preset_roles() -> Dict[str, Any]:
"""返回所有预置角色定义（供前端展示）。"""
return {
**PRESET_ROLES, **EDUCATION_ROLES, **PLATFORM_ENGINEERING_ROLES,
**TECH_DOC_ROLES, **HEALTH_MANAGEMENT_ROLES, **MEDICAL_CONSULTATION_ROLES,
+ **USER_SIMULATION_TEST_ROLES,
}
diff --git a/frontend/src/api/teams.ts b/frontend/src/api/teams.ts
index f66a03f..a5d4a2e 100644
--- a/frontend/src/api/teams.ts
+++ b/frontend/src/api/teams.ts
@@ -138,6 +138,13 @@ export function createMedicalConsultationTemplate(workspaceId?: string) {
})
}
+/** 一键创建系统应用测试团队模板 */
+export function createUserSimulationTestTemplate(workspaceId?: string) {
+ return api.post('/api/v1/teams/template/user-simulation-test', null, {
+ params: workspaceId ? { workspace_id: workspaceId } : {},
+ })
+}
+
/** 添加团队成员 */
export function addMember(teamId: string, data: {
agent_id: string
diff --git a/frontend/src/views/TeamBuilder.vue b/frontend/src/views/TeamBuilder.vue
index f7e6d04..01bb67c 100644
--- a/frontend/src/views/TeamBuilder.vue
+++ b/frontend/src/views/TeamBuilder.vue
@@ -31,6 +31,9 @@
医疗咨询团队
+
+ 系统应用测试团队
+
@@ -300,7 +303,7 @@ import {
import {
listTeams, getTeam, createTeam, updateTeam, createSoftwareCompanyTemplate,
createEducationTrainingTemplate, createPlatformEngineeringTemplate, createTechDocTemplate,
- createHealthManagementTemplate, createMedicalConsultationTemplate,
+ createHealthManagementTemplate, createMedicalConsultationTemplate, createUserSimulationTestTemplate,
addMember, removeMember, executeProject, getPresetRoles,
} from '@/api/teams'
import api from '@/api'
@@ -336,6 +339,7 @@ const creatingPlatformTemplate = ref(false)
const creatingTechDocTemplate = ref(false)
const creatingHealthTemplate = ref(false)
const creatingMedicalTemplate = ref(false)
+const creatingTestTemplate = ref(false)
const loadingTeams = ref(false)
// Agent
@@ -658,6 +662,33 @@ async function handleCreateMedicalTemplate() {
}
}
+// 一键创建系统应用测试团队模板
+async function handleCreateTestTemplate() {
+ creatingTestTemplate.value = true
+ try {
+ const res = await createUserSimulationTestTemplate()
+ const team = (res.data as any)?.data
+ if (team) {
+ currentTeamId.value = team.id; teamName.value = team.name
+ await loadAgents()
+ const slots: Record = {}
+ if (team.members) {
+ for (const m of team.members) {
+ const agent = agents.value.find(a => a.id === m.agent_id)
+ if (agent) slots[m.role] = { ...agent, is_lead: m.is_lead, member_id: m.id }
+ }
+ }
+ roleSlots.value = slots
+ ElMessage.success('系统应用测试团队创建成功！')
+ }
+ await loadTeams()
+ } catch (e: any) {
+ ElMessage.error(e?.response?.data?.detail || '创建模板失败')
+ } finally {
+ creatingTestTemplate.value = false
+ }
+}
+
// 拖拽
function onDragStart(agent: Agent) {
draggingAgent = agent