feat: Implement Usecase Demo Agent orchestration and UI components

README.md

@@ -1,6 +1,10 @@
 # Quart + Vite + React Demo Application
 
-**Task:** Visualize the CSV tickets with richer panels (status, priority, timeline, geography, SLA). **How would you like to view the tickets?**
+**Current Task:** Document usecase demo ideas from the CSV-backed ticket dataset and build/iterate pages like `/usecase_demo_1` where each demo page has:
+- a short summary
+- editable agent prompt(s)
+- a button that launches the agent run in background
+- visible results (table/visualization)
 
 > A teaching-oriented full-stack sample that pairs a Python Quart backend with a React + FluentUI frontend, real-time Server-Sent Events (SSE), and Playwright tests.
 
@@ -27,6 +31,7 @@ All deep-dive guides now live under `docs/` for easier discovery:
 - [Pydantic Architecture](docs/PYDANTIC_ARCHITECTURE.md) – how models, validation, and operations fit together
 - [Unified Architecture](docs/UNIFIED_ARCHITECTURE.md) – REST + MCP integration details and extension ideas
 - [Troubleshooting](docs/TROUBLESHOOTING.md) – common issues and fixes for setup, dev, and tests
+- [CSV AI Guidance](docs/CSV_AI_GUIDANCE.md) – how AI agents should query and reason over CSV ticket data
 
 
 
@@ -38,7 +43,7 @@ All deep-dive guides now live under `docs/` for easier discovery:
 2. Run the automated bootstrap: `./setup.sh` (creates the repo-level `.venv`, installs frontend deps, installs Playwright, checks for Ollama)
 3. (Optional) Install Ollama for LLM features: `curl -fsSL https://ollama.com/install.sh | sh && ollama pull llama3.2:1b`
 4. Start all servers: `./start-dev.sh` *(or)* use the VS Code "Full Stack: Backend + Frontend" launch config
-5. Open `http://localhost:3001`, switch to the **Tasks** tab, and create a task—the backend and frontend are now synced
+5. Open `http://localhost:3001/usecase_demo_1` and start documenting your usecase demo idea on that page
 6. (Optional) Test Ollama integration: `curl -X POST http://localhost:5001/api/ollama/chat -H "Content-Type: application/json" -d '{"messages":[{"role":"user","content":"Say hello"}]}'`
 7. (Optional) Run the Playwright suite from the repo root: `npm run test:e2e`
 
@@ -95,9 +100,9 @@ Use the “Full Stack: Backend + Frontend” launch config to start backend + fr
 
 ### Smoke test checklist
 - Visit `http://localhost:3001`
-- Dashboard tab should show a ticking clock (SSE via `/api/time-stream`)
-- Tasks tab should show three sample tasks (seeded by `TaskService.initialize_sample_data()`)
-- Create a task, mark it complete, delete it—confirm state updates instantly
+- Tickets tab should render CSV ticket table + stats from `/api/csv-tickets*`
+- Usecase Demo tab (`/usecase_demo_1`) should show editable prompt + background run controls
+- Fields tab should list mapped CSV fields from `/api/csv-tickets/fields`
 
 ## Docker (one command delivery)
 
@@ -113,9 +118,10 @@ docker run --rm -p 5001:5001 quart-react-demo
 - Hot reloading is not part of the container flow—use the regular dev servers for iterative work and Docker for demos or deployment.
 
 ## Using the app
-- **Dashboard tab:** Streams `{"time","date","timestamp"}` via EventSource; connection errors show inline.
-- **Tasks tab:** Uses FluentUI `DataGrid` + dialogs; `frontend/src/features/tasks/TaskList.jsx` keeps calculations (`getTaskStats`) separate from actions (API calls).
-- **About tab:** Summarizes tech choices and linkable resources.
+- **Tickets tab (`/csvtickets`):** Shows CSV-backed ticket table, filtering, sorting, and pagination.
+- **Usecase Demo tab (`/usecase_demo_1`):** Main demo page for documenting usecase demo ideas with editable prompts and background agent runs.
+- **Fields tab (`/fields`):** Lists mapped CSV schema fields available to UI/MCP/agent flows.
+- **Agent tab (`/agent`):** Chat-style agent interface for CSV ticket analysis.
 - **Ollama API (backend only):**
   - `POST /api/ollama/chat` — Chat with local LLM (supports conversation history)
   - `GET /api/ollama/models` — List available models

backend/agents.py

@@ -309,13 +309,19 @@ def _build_csv_tools(self) -> list[StructuredTool]:
         import json
         service = get_csv_ticket_service()
 
-        def _csv_list_tickets(status: str | None = None, assigned_group: str | None = None, has_assignee: bool | None = None) -> str:
+        def _csv_list_tickets(
+            status: str | None = None,
+            assigned_group: str | None = None,
+            has_assignee: bool | None = None,
+            limit: int = 50,
+        ) -> str:
             try:
                 status_enum = TicketStatus(status.lower()) if status else None
             except Exception:
                 status_enum = None
             tickets = service.list_tickets(status=status_enum, assigned_group=assigned_group, has_assignee=has_assignee)
-            return json.dumps([t.model_dump() for t in tickets[:200]], default=str)
+            bounded_limit = max(1, min(limit, 100))
+            return json.dumps([t.model_dump() for t in tickets[:bounded_limit]], default=str)
 
         def _csv_get_ticket(ticket_id: str) -> str:
             try:
@@ -327,7 +333,7 @@ def _csv_get_ticket(ticket_id: str) -> str:
                 return json.dumps({"error": "not found"})
             return json.dumps(ticket.model_dump(), default=str)
 
-        def _csv_search_tickets(query: str, limit: int = 50) -> str:
+        def _csv_search_tickets(query: str, limit: int = 25) -> str:
             q = query.lower()
             tickets = service.list_tickets()
             matched = []
@@ -356,7 +362,12 @@ def _csv_ticket_fields() -> str:
             StructuredTool.from_function(
                 func=_csv_list_tickets,
                 name="csv_list_tickets",
-                description="List tickets from CSV with optional filters: status (new, assigned, in_progress, pending, resolved, closed, cancelled), assigned_group, has_assignee (true/false). Returns JSON array.",
+                description=(
+                    "List tickets from CSV with optional filters: status "
+                    "(new, assigned, in_progress, pending, resolved, closed, cancelled), "
+                    "assigned_group, has_assignee (true/false), and limit (default 50, max 100). "
+                    "Returns JSON array."
+                ),
             ),
             StructuredTool.from_function(
                 func=_csv_get_ticket,

backend/app.py

@@ -20,6 +20,7 @@
 import os
 from datetime import datetime
 from pathlib import Path
+from uuid import UUID
 
 # Load environment variables from .env file
 from dotenv import load_dotenv
@@ -35,11 +36,13 @@
 
 # CSV ticket service
 from csv_data import Ticket, get_csv_ticket_service
+from usecase_demo import UsecaseDemoRunCreate, usecase_demo_run_service
 
 # FastMCP client for direct ticket MCP calls (no AI)
 from fastmcp import Client as MCPClient
 from mcp_handler import handle_mcp_request
 from operations import (
+    CSV_TICKET_FIELDS,
     op_create_task,
     op_delete_task,
     op_get_task,
@@ -177,6 +180,47 @@ async def rest_run_agent():
         return jsonify({"error": str(e)}), 500
 
 
+# ============================================================================
+# USECASE DEMO AGENT RUN ENDPOINTS
+# ============================================================================
+
+@app.route("/api/usecase-demo/agent-runs", methods=["POST"])
+async def create_usecase_demo_agent_run():
+    """Queue a background agent run using the provided prompt."""
+    try:
+        data = await request.get_json() or {}
+        payload = UsecaseDemoRunCreate(**data)
+        run = await usecase_demo_run_service.create_run(payload)
+        return jsonify(run.model_dump(mode="json")), 202
+    except ValidationError as e:
+        return jsonify({"error": str(e)}), 400
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+
+@app.route("/api/usecase-demo/agent-runs", methods=["GET"])
+async def list_usecase_demo_agent_runs():
+    """List recent background agent runs."""
+    try:
+        limit = request.args.get("limit", default=20, type=int)
+        runs = await usecase_demo_run_service.list_runs(limit=limit or 20)
+        return jsonify({"runs": [run.model_dump(mode="json") for run in runs]}), 200
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+
+@app.route("/api/usecase-demo/agent-runs/<run_id>", methods=["GET"])
+async def get_usecase_demo_agent_run(run_id: str):
+    """Fetch one background run by ID."""
+    try:
+        run = await usecase_demo_run_service.get_run(run_id)
+        if run is None:
+            return jsonify({"error": "Run not found"}), 404
+        return jsonify(run.model_dump(mode="json")), 200
+    except Exception as e:
+        return jsonify({"error": str(e)}), 500
+
+
 # ============================================================================
 # TICKET MCP EXAMPLE - Direct FastMCP client usage (no AI)
 # ============================================================================
@@ -403,31 +447,6 @@ async def get_qa_tickets():
     print(f"📊 Loaded {_csv_loaded} tickets from CSV")
 
 
-# Define which fields are available for display
-CSV_TICKET_FIELDS = [
-    {"name": "id", "label": "ID", "type": "uuid"},
-    {"name": "summary", "label": "Summary", "type": "string"},
-    {"name": "status", "label": "Status", "type": "enum"},
-    {"name": "priority", "label": "Priority", "type": "enum"},
-    {"name": "assignee", "label": "Assignee", "type": "string"},
-    {"name": "assigned_group", "label": "Assigned Group", "type": "string"},
-    {"name": "requester_name", "label": "Requester", "type": "string"},
-    {"name": "requester_email", "label": "Email", "type": "string"},
-    {"name": "city", "label": "City", "type": "string"},
-    {"name": "country", "label": "Country", "type": "string"},
-    {"name": "service", "label": "Service", "type": "string"},
-    {"name": "incident_type", "label": "Incident Type", "type": "string"},
-    {"name": "product_name", "label": "Product", "type": "string"},
-    {"name": "manufacturer", "label": "Manufacturer", "type": "string"},
-    {"name": "created_at", "label": "Created", "type": "datetime"},
-    {"name": "updated_at", "label": "Updated", "type": "datetime"},
-    {"name": "urgency", "label": "Urgency", "type": "string"},
-    {"name": "impact", "label": "Impact", "type": "string"},
-    {"name": "resolution", "label": "Resolution", "type": "string"},
-    {"name": "notes", "label": "Notes", "type": "string"},
-]
-
-
 @app.route("/api/csv-tickets/fields", methods=["GET"])
 async def get_csv_ticket_fields():
     """Get metadata about available CSV ticket fields."""
@@ -539,6 +558,46 @@ def get_sort_key(ticket: Ticket):
     })
 
 
+@app.route("/api/csv-tickets/<ticket_id>", methods=["GET"])
+async def get_csv_ticket(ticket_id: str):
+    """
+    Get one CSV ticket by ID.
+
+    Query params:
+    - fields: optional comma-separated list of fields to include
+    """
+    try:
+        parsed_id = UUID(ticket_id)
+    except ValueError:
+        return jsonify({"error": "Invalid ticket ID"}), 400
+
+    ticket = _csv_ticket_service.get_ticket(parsed_id)
+    if ticket is None:
+        return jsonify({"error": "Ticket not found"}), 404
+
+    fields_param = request.args.get("fields", "")
+    if fields_param:
+        selected_fields = [f.strip() for f in fields_param.split(",") if f.strip()]
+    else:
+        selected_fields = list(ticket.model_fields.keys())
+
+    result = {}
+    for field in selected_fields:
+        val = getattr(ticket, field, None)
+        if val is None:
+            result[field] = None
+        elif hasattr(val, "value"):
+            result[field] = val.value
+        elif hasattr(val, "isoformat"):
+            result[field] = val.isoformat()
+        elif hasattr(val, "hex"):
+            result[field] = str(val)
+        else:
+            result[field] = val
+
+    return jsonify(result), 200
+
+
 @app.route("/api/csv-tickets/stats", methods=["GET"])
 async def get_csv_ticket_stats():
     """Get statistics about CSV tickets."""