feat(webui): model usage, token cost, latency, and performance analytics (Closes #651)

webui/app.py

@@ -47,6 +47,12 @@ from webui.worktree_views import render_worktrees_page
 from webui.runtime_health import load_runtime_snapshot, snapshot_to_dict as runtime_snapshot_to_dict
 from webui.runtime_views import render_runtime_page
 from webui.timeline import load_timeline, snapshot_to_dict as timeline_snapshot_to_dict
+from webui.analytics_loader import (
+    load_analytics,
+    record_usage,
+    snapshot_to_dict as analytics_snapshot_to_dict,
+)
+from webui.analytics_views import render_analytics_page
 from webui.system_health import (
     API_PATH as SYSTEM_HEALTH_API_PATH,
     load_system_health,
@@ -548,6 +554,72 @@ async def api_v1_timeline(request: Request) -> JSONResponse:
     return JSONResponse(timeline_snapshot_to_dict(snapshot), status_code=status_code)
 
 
+async def analytics(request: Request) -> HTMLResponse:
+    """Read-only model usage, token cost, latency, and performance analytics HTML view (#651)."""
+    snapshot = load_analytics(
+        remote=request.query_params.get("remote"),
+        org=request.query_params.get("org"),
+        repo=request.query_params.get("repo"),
+        role=request.query_params.get("role"),
+        model=request.query_params.get("model"),
+        stage=request.query_params.get("stage"),
+        issue_number=_query_int(request, "issue"),
+        pr_number=_query_int(request, "pr"),
+        limit=_query_int(request, "limit") or 200,
+    )
+    return HTMLResponse(render_analytics_page(snapshot))
+
+
+async def api_v1_analytics(request: Request) -> JSONResponse:
+    """Read-only model usage, token cost, latency, and performance analytics API (#651)."""
+    snapshot = load_analytics(
+        remote=request.query_params.get("remote"),
+        org=request.query_params.get("org"),
+        repo=request.query_params.get("repo"),
+        role=request.query_params.get("role"),
+        model=request.query_params.get("model"),
+        stage=request.query_params.get("stage"),
+        issue_number=_query_int(request, "issue"),
+        pr_number=_query_int(request, "pr"),
+        limit=_query_int(request, "limit") or 500,
+    )
+    status_code = 200 if snapshot.ok else 500
+    return JSONResponse(analytics_snapshot_to_dict(snapshot), status_code=status_code)
+
+
+async def api_v1_analytics_ingest(request: Request) -> JSONResponse:
+    """Optional session instrumentation ingestion endpoint (#651)."""
+    try:
+        body = await request.json()
+    except Exception:
+        return JSONResponse({"error": "invalid_json", "detail": "body must be valid JSON"}, status_code=400)
+
+    if not isinstance(body, dict):
+        return JSONResponse({"error": "invalid_payload", "detail": "payload must be a JSON object"}, status_code=400)
+
+    usage_id = record_usage(
+        session_id=body.get("session_id"),
+        remote=body.get("remote", "dadeschools"),
+        org=body.get("org", ""),
+        repo=body.get("repo", ""),
+        project_id=body.get("project_id"),
+        role=body.get("role", "unknown"),
+        model=body.get("model", "unknown"),
+        issue_number=body.get("issue_number") or body.get("issue"),
+        pr_number=body.get("pr_number") or body.get("pr"),
+        stage=body.get("stage", "unknown"),
+        input_tokens=body.get("input_tokens"),
+        output_tokens=body.get("output_tokens"),
+        total_tokens=body.get("total_tokens"),
+        estimated_cost_usd=body.get("estimated_cost_usd"),
+        latency_ms=body.get("latency_ms"),
+        duration_ms=body.get("duration_ms"),
+        status=body.get("status", "success"),
+        metadata=body.get("metadata"),
+    )
+    return JSONResponse({"ok": True, "usage_id": usage_id}, status_code=201)
+
+
 async def method_not_allowed(request: Request, _exc: Exception) -> Response:
     path = request.url.path
     if path in _AUDIT_MUTATION_PATHS and request.method == "POST":
@@ -588,6 +660,10 @@ def create_app(*, bind_host: str | None = None) -> Starlette:
             Route("/runtime", runtime, methods=["GET"]),
             Route("/api/runtime", api_runtime, methods=["GET"]),
             Route("/api/v1/timeline", api_v1_timeline, methods=["GET"]),
+            Route("/analytics", analytics, methods=["GET"]),
+            Route("/api/analytics", api_v1_analytics, methods=["GET"]),
+            Route("/api/v1/analytics", api_v1_analytics, methods=["GET"]),
+            Route("/api/v1/analytics/usage", api_v1_analytics_ingest, methods=["POST"]),
             Route("/audit", audit, methods=["GET", "POST"]),
             Route("/api/audit", api_audit, methods=["GET", "POST"]),
             Route("/worktrees", worktrees, methods=["GET"]),