feat(scripts): cost_report.py — monthly NocoDB/S3/Ollama rollup (REQ-INB-54)

---ci---
project: inboxos
phase: 1
milestone: v1.4
status: execute
wave: 1
task: T6
---/ci---

pipelines/_tests/test_cost_report_offline.py

@@ -0,0 +1,42 @@
+"""Offline tests for scripts/cost_report.py — REQ-INB-54.
+
+Covers 2 cases:
+  1. NocoDB unreachable emits a row with nocodb.status='unreachable' and continues
+  2. Full happy path emits N rows where N = days in requested month
+"""
+import calendar
+import os
+import sys
+import unittest
+from unittest import mock
+
+sys.path.insert(0, os.path.join(os.path.dirname(__file__), "..", "..", "scripts"))
+import cost_report
+
+
+class TestCostReport(unittest.TestCase):
+    def test_nocodb_unreachable_continues(self):
+        with mock.patch.object(cost_report, "nocodb_row_counts", return_value={
+            "status": "unreachable", "reason": "test"
+        }):
+            with mock.patch.object(cost_report, "s3_archive_size_gb", return_value=-1.0):
+                with mock.patch.object(cost_report, "ollama_token_count", return_value=0):
+                    rows = cost_report.report("2026-02")
+        self.assertGreater(len(rows), 0)
+        self.assertEqual(rows[0]["nocodb"]["status"], "unreachable")
+
+    def test_happy_path_emits_rows_per_day(self):
+        with mock.patch.object(cost_report, "nocodb_row_counts", return_value={
+            "status": "ok", "finance": 10, "crm": 5, "intel": 3, "promotions": 7
+        }):
+            with mock.patch.object(cost_report, "s3_archive_size_gb", return_value=1.5):
+                with mock.patch.object(cost_report, "ollama_token_count", return_value=1000):
+                    rows = cost_report.report("2026-02")
+        _, days = calendar.monthrange(2026, 2)
+        self.assertEqual(len(rows), days)
+        self.assertEqual(rows[0]["s3_archive_gb"], 1.5)
+        self.assertEqual(rows[0]["ollama_tokens"], 1000)
+
+
+if __name__ == "__main__":
+    unittest.main()

scripts/cost_report.py

@@ -0,0 +1,121 @@
+#!/usr/bin/env python3
+"""Cost report: monthly NocoDB / S3 / Ollama rollup.
+
+v1.4 REQ-INB-54.
+"""
+from __future__ import annotations
+
+import argparse
+import calendar
+import json
+import os
+import sys
+from datetime import datetime, timezone
+
+import requests
+
+
+NOCODB_BASE_URL = os.environ.get("NOCODB_BASE_URL", "http://localhost:8080")
+NOCODB_API_TOKEN = os.environ.get("NOCODB_API_TOKEN", "")
+SEAWEEDFS_S3_BUCKET = os.environ.get("SEAWEEDFS_S3_BUCKET", "inboxos")
+
+
+def _nocodb_headers() -> dict[str, str]:
+    return {"xc-token": NOCODB_API_TOKEN, "Content-Type": "application/json"}
+
+
+def nocodb_row_counts() -> dict[str, int]:
+    if not NOCODB_API_TOKEN:
+        return {"status": "unreachable", "reason": "NOCODB_API_TOKEN unset"}
+    counts: dict[str, int] = {"status": "ok"}
+    for module in ("finance", "crm", "intel", "promotions"):
+        table_id = os.environ.get(f"NOCODB_TABLE_{module.upper()}", "")
+        if not table_id:
+            counts[module] = 0
+            continue
+        try:
+            r = requests.get(
+                f"{NOCODB_BASE_URL}/api/v2/tables/{table_id}/records",
+                headers=_nocodb_headers(),
+                params={"limit": 1, "where": "(Id,gt,0)"},
+                timeout=10,
+            )
+            r.raise_for_status()
+            counts[module] = r.json().get("pageInfo", {}).get("totalRows", 0)
+        except requests.RequestException as exc:
+            counts["status"] = "unreachable"
+            counts[f"{module}_error"] = str(exc)
+            counts[module] = 0
+    return counts
+
+
+def s3_archive_size_gb() -> float:
+    try:
+        import boto3
+        s3 = boto3.client("s3")
+        resp = s3.list_objects_v2(Bucket=SEAWEEDFS_S3_BUCKET)
+        total = sum(obj["Size"] for obj in resp.get("Contents", []))
+        return round(total / (1024 ** 3), 3)
+    except Exception as exc:
+        return -1.0
+
+
+def ollama_token_count(month: str) -> int:
+    metrics_path = os.path.join("pipelines", "_metrics", f"tokens-{month}.jsonl")
+    if not os.path.exists(metrics_path):
+        return 0
+    total = 0
+    with open(metrics_path) as f:
+        for line in f:
+            try:
+                total += json.loads(line).get("total_tokens", 0)
+            except json.JSONDecodeError:
+                continue
+    return total
+
+
+def report(month: str) -> list[dict]:
+    year, mo = map(int, month.split("-"))
+    _, days_in_month = calendar.monthrange(year, mo)
+    nocodb = nocodb_row_counts()
+    s3_gb = s3_archive_size_gb()
+    tokens = ollama_token_count(month)
+    rows = []
+    for day in range(1, days_in_month + 1):
+        rows.append({
+            "date": f"{month}-{day:02d}",
+            "nocodb": nocodb,
+            "s3_archive_gb": s3_gb,
+            "ollama_tokens": tokens,
+        })
+    return rows
+
+
+def main() -> int:
+    p = argparse.ArgumentParser(description="Monthly NocoDB/S3/Ollama cost report")
+    p.add_argument("--month", help="YYYY-MM (default: current month)")
+    p.add_argument("--format", choices=["json", "csv"], default="json")
+    args = p.parse_args()
+
+    if not args.month:
+        args.month = datetime.now(timezone.utc).strftime("%Y-%m")
+
+    rows = report(args.month)
+
+    if args.format == "json":
+        print(json.dumps(rows, indent=2))
+    else:
+        print("date,nocodb_status,finance,crm,intel,promotions,s3_archive_gb,ollama_tokens")
+        for r in rows:
+            n = r["nocodb"]
+            print(
+                f"{r['date']},{n.get('status', '?')},"
+                f"{n.get('finance', 0)},{n.get('crm', 0)},"
+                f"{n.get('intel', 0)},{n.get('promotions', 0)},"
+                f"{r['s3_archive_gb']},{r['ollama_tokens']}"
+            )
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())