Files
terra-view/backend/services/report_orchestrator.py
serversdown fdd0426884 fix(reports): code-review findings — XSS, SMTP, blocking, unit link, email guard
- #1 XSS: escape user-controlled values (location name, baseline values, recent-
  report fields, SMTP status message) in the modals via the existing _mergeEsc
  helper — they were concatenated raw into innerHTML (stored XSS via location name).
- #2 SMTP: an unrecognized REPORT_SMTP_SECURITY no longer silently downgrades to a
  plaintext connection while still calling login() — it falls back to starttls and
  warns; warn on intentional security=none + auth.
- #3 scheduler: run the (blocking smtplib + Excel) nightly report in a worker thread
  (asyncio.to_thread + its own DB session) so it can't stall the loop that drives
  time-sensitive device cycles. New _run_one_report helper.
- #4 cycle ingest: set unit_id on the ingested data session (ingest_nrl_zip leaves
  it None) before dropping the empty placeholder, preserving the unit<->session link;
  repoint old_session_id at the real row.
- #7 robustness: wrap send_report_email in the orchestrator and run_nightly_report in
  /view + /run so a render/SMTP error returns a clean error instead of a raw 500
  after artifacts are written.

Verified: SMTP paths (typo->starttls, none, starttls, ssl), off-thread tick stamps
last_run_date + writes the file, /view 200, escaping wired, app imports.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-12 02:37:28 +00:00

151 lines
5.8 KiB
Python

"""
Nightly Report Orchestrator.
Ties the pieces together: compute → render → write-to-disk → email.
This is what the daily cycle (or a manual trigger) calls. It ALWAYS writes the
rendered report to disk — `data/reports/{project_id}/{night_date}/report.html`
(+ `report.json` with the raw numbers) — so there's a viewable artifact even
when email is in dry-run (SMTP not configured yet). The email step is
best-effort and never aborts the run.
"""
from __future__ import annotations
import json
import logging
from datetime import date
from pathlib import Path
from typing import Optional
from sqlalchemy.orm import Session
from backend.services.report_pipeline import (
ProjectNightReport, build_project_night_report, Window,
)
from backend.services.report_renderers import render_html_summary, render_excel
from backend.services.report_email import send_report_email, Attachment, XLSX_MIME
logger = logging.getLogger(__name__)
DEFAULT_OUTPUT_ROOT = "data/reports"
def _report_to_dict(report: ProjectNightReport) -> dict:
"""Serialise the report data model to plain JSON (for the on-disk record)."""
return {
"project_id": report.project_id,
"project_name": report.project_name,
"night_date": report.night_date.isoformat(),
"metrics": [m.key for m in report.metrics],
"locations": [
{
"name": loc.location_name,
"night_interval_count": loc.night_interval_count,
"baseline_nights_used": loc.baseline_nights_used,
"notes": loc.notes,
"windows": {
w.key: {
"label": w.label,
"metrics": {
m.key: {
"label": m.label,
"last_night": loc.table[w.key][m.key].last_night,
"baseline": loc.table[w.key][m.key].baseline,
"delta": loc.table[w.key][m.key].delta,
}
for m in loc.metrics
},
}
for w in loc.windows
},
}
for loc in report.locations
],
}
def run_nightly_report(
db: Session,
project_id: str,
night_date: date,
*,
metric_keys: Optional[list[str]] = None,
windows: Optional[list[Window]] = None,
baseline_mode: str = "captured",
baseline_start: Optional[date] = None,
baseline_end: Optional[date] = None,
recipients: Optional[list[str]] = None,
output_root: str = DEFAULT_OUTPUT_ROOT,
send: bool = True,
) -> dict:
"""Build, persist, and (dry-run) email the night report for a project.
Returns a result dict with the on-disk artifact paths and the email result.
Designed to be called from the daily cycle or a manual trigger.
"""
report = build_project_night_report(
db, project_id, night_date,
metric_keys=metric_keys, windows=windows,
baseline_mode=baseline_mode,
baseline_start=baseline_start, baseline_end=baseline_end,
)
html = render_html_summary(report)
subject = f"{report.project_name} — night report {night_date:%m/%d/%y}"
# --- Always persist a viewable copy ---
out_dir = Path(output_root) / project_id / f"{night_date:%Y-%m-%d}"
out_dir.mkdir(parents=True, exist_ok=True)
html_path = out_dir / "report.html"
html_path.write_text(html, encoding="utf-8")
json_path = out_dir / "report.json"
json_path.write_text(json.dumps(_report_to_dict(report), indent=2), encoding="utf-8")
# --- Excel (the email attachment; also written to disk for the archive) ---
attachments: list[Attachment] = []
xlsx_path = None
try:
xlsx_bytes = render_excel(report)
xlsx_path = out_dir / "report.xlsx"
xlsx_path.write_bytes(xlsx_bytes)
safe_name = "".join(c for c in report.project_name if c.isalnum() or c in " -_").strip().replace(" ", "_")
attachments.append(Attachment(
f"{safe_name or 'report'}_{night_date:%Y-%m-%d}_night_report.xlsx",
xlsx_bytes, *XLSX_MIME,
))
except Exception as e: # noqa: BLE001 — never let the spreadsheet sink the report
logger.error("Excel render failed for %s (%s): %s", project_id, night_date, e, exc_info=True)
# --- Email (best-effort; dry-run until SMTP is configured) ---
email_result = {"sent": False, "dry_run": False, "skipped": True, "error": None}
if send:
try:
email_result = send_report_email(
subject, html, attachments=attachments, recipients=recipients,
)
except Exception as e: # noqa: BLE001 — artifacts are already written; never abort on email
logger.error("send_report_email raised for %s (%s): %s", project_id, night_date, e, exc_info=True)
email_result = {"sent": False, "dry_run": False, "skipped": False, "error": str(e)}
result = {
"project_id": project_id,
"project_name": report.project_name,
"night_date": night_date.isoformat(),
"subject": subject,
"location_count": len(report.locations),
"html_path": str(html_path),
"json_path": str(json_path),
"xlsx_path": str(xlsx_path) if xlsx_path else None,
"html": html, # for callers that want to display it inline
"email": email_result,
}
logger.info(
"Nightly report for %s (%s): %d location(s) → %s; email=%s",
report.project_name, night_date, len(report.locations), html_path,
"sent" if email_result.get("sent") else
("dry-run" if email_result.get("dry_run") else
("skipped" if email_result.get("skipped") else f"error: {email_result.get('error')}")),
)
return result