feat(sp18): structured JSON logging + PII scrubber

Cyclone previously emitted stdlib default-formatted log lines that
operators couldn't parse with anything beyond grep. SP18 replaces
that with:

- JsonFormatter: newline-delimited JSON, ISO-8601 ms timestamps,
  structured "extra" dict, exception tracebacks serialized as a
  single string.
- CycloneDevFormatter: tabular format for tail -f in dev.
- PiiScrubber: logging.Filter that redacts NPIs, SSNs, DOBs,
  patient names — both inline in the message ("npi 1881068062")
  and via PHI-keyed extras ({"dob": "1980-04-12"}).
- setup_logging(): idempotent entry point used by the API lifespan
  and CLI main; respects CYCLONE_LOG_LEVEL/FILE/JSON/NO_PII_SCRUB.
- CLI --log-format=json|dev + --log-file=… flags.
- Migrate 9 highest-value log sites in scheduler/backup_scheduler/
  backup_service to use extra={...} (input_filename, claims, parser,
  backup_id, db_fingerprint, etc.).

34 new tests (test_logging_formatter + test_logging_scrubber +
test_logging_setup). All 867 backend tests pass.
This commit is contained in:
Tyler
2026-06-21 09:59:34 -06:00
parent daf3206d55
commit 47e0f80786
12 changed files with 1586 additions and 19 deletions
+165
View File
@@ -0,0 +1,165 @@
"""SP18 — JsonFormatter + CycloneDevFormatter tests.
Covers the structural shape of log records, exception handling,
and the ``extra`` kwarg passthrough.
"""
from __future__ import annotations
import io
import json
import logging
import pytest
from cyclone.logging_config import (
CycloneDevFormatter,
JsonFormatter,
setup_logging,
)
def _make_record(
msg: str = "hello",
args: tuple = (),
level: int = logging.INFO,
name: str = "test.logger",
extras: dict | None = None,
exc_info=None,
) -> logging.LogRecord:
record = logging.getLogger(name).makeRecord(
name=name,
level=level,
fn="t.py",
lno=1,
msg=msg,
args=args,
exc_info=exc_info,
)
if extras:
for k, v in extras.items():
setattr(record, k, v)
return record
# ---------------------------------------------------------------------------
# JsonFormatter
# ---------------------------------------------------------------------------
def test_json_formatter_basic_shape():
f = JsonFormatter()
line = f.format(_make_record(msg="hello %s", args=("cyclone",)))
parsed = json.loads(line)
assert parsed["level"] == "INFO"
assert parsed["logger"] == "test.logger"
assert parsed["msg"] == "hello cyclone"
assert "ts" in parsed
# ts must be ISO 8601 with milliseconds + Z suffix.
assert parsed["ts"].endswith("Z") or "+" in parsed["ts"]
def test_json_formatter_includes_extras():
f = JsonFormatter()
line = f.format(_make_record(
msg="processed",
extras={"input_filename": "foo.x12", "parser_kind": "parse_999", "claims": 3},
))
parsed = json.loads(line)
assert parsed["extra"] == {
"input_filename": "foo.x12", "parser_kind": "parse_999", "claims": 3,
}
def test_json_formatter_handles_exception_info():
f = JsonFormatter()
try:
raise ValueError("boom")
except ValueError:
import sys
rec = _make_record(msg="oops", exc_info=sys.exc_info())
line = f.format(rec)
parsed = json.loads(line)
assert "traceback" in parsed
assert "ValueError: boom" in parsed["traceback"]
def test_json_formatter_no_extras_key_when_none():
f = JsonFormatter()
line = f.format(_make_record(msg="plain"))
parsed = json.loads(line)
assert "extra" not in parsed
def test_json_formatter_handles_non_serializable_extras():
"""Non-JSON-serializable extras go through ``default=str``."""
class Opaque:
def __str__(self):
return "opaque-string"
f = JsonFormatter()
line = f.format(_make_record(msg="x", extras={"thing": Opaque()}))
parsed = json.loads(line)
assert parsed["extra"]["thing"] == "opaque-string"
def test_json_formatter_preserves_warning_level():
f = JsonFormatter()
line = f.format(_make_record(msg="careful", level=logging.WARNING))
parsed = json.loads(line)
assert parsed["level"] == "WARNING"
# ---------------------------------------------------------------------------
# CycloneDevFormatter
# ---------------------------------------------------------------------------
def test_dev_formatter_basic_shape():
f = CycloneDevFormatter()
line = f.format(_make_record(msg="hello %s", args=("cyclone",)))
assert "INFO" in line
assert "test.logger" in line
assert "hello cyclone" in line
def test_dev_formatter_includes_extras():
f = CycloneDevFormatter()
line = f.format(_make_record(
msg="processed",
extras={"input_filename": "foo.x12", "claims": 3},
))
assert "input_filename='foo.x12'" in line
assert "claims=3" in line
def test_dev_formatter_handles_exception():
f = CycloneDevFormatter()
try:
raise RuntimeError("nope")
except RuntimeError:
import sys
rec = _make_record(msg="oops", exc_info=sys.exc_info())
line = f.format(rec)
assert "RuntimeError: nope" in line
# ---------------------------------------------------------------------------
# setup_logging (light — deeper coverage in test_logging_setup.py)
# ---------------------------------------------------------------------------
def test_setup_logging_attaches_handler_to_root():
setup_logging(level="DEBUG", json_format=True)
root = logging.getLogger()
assert len(root.handlers) >= 1
assert isinstance(root.handlers[0].formatter, JsonFormatter)
def test_setup_logging_is_idempotent():
"""Re-calling clears handlers; the formatter toggle takes effect."""
setup_logging(level="INFO", json_format=True)
setup_logging(level="INFO", json_format=False)
root = logging.getLogger()
assert len(root.handlers) == 1
assert isinstance(root.handlers[0].formatter, CycloneDevFormatter)
# Reset back to JSON for the rest of the test suite.
setup_logging(level="INFO", json_format=True)
+157
View File
@@ -0,0 +1,157 @@
"""SP18 — PII scrubber tests.
Covers each PHI pattern, the false-positive guard, and the
disable toggle.
"""
from __future__ import annotations
import logging
import pytest
from cyclone.logging_config import (
PiiScrubber,
get_scrubber,
setup_logging,
)
def _make_record(msg: str, extras: dict | None = None) -> logging.LogRecord:
record = logging.getLogger("test.scrub").makeRecord(
name="test.scrub", level=logging.INFO, fn="t.py", lno=1,
msg=msg, args=(), exc_info=None,
)
if extras:
for k, v in extras.items():
setattr(record, k, v)
return record
@pytest.fixture(autouse=True)
def _reset_scrubber():
"""Make sure the scrubber is enabled + on the root after each test."""
yield
get_scrubber().enable()
# ---------------------------------------------------------------------------
# NPI
# ---------------------------------------------------------------------------
def test_scrubs_ten_digit_npi_in_message():
scrubber = PiiScrubber()
rec = _make_record("processed claim with npi 1881068062 ok")
assert scrubber.filter(rec) is True
assert rec.getMessage() == "processed claim with npi <redacted:npi> ok"
def test_scrubs_npi_in_extras():
scrubber = PiiScrubber()
rec = _make_record("ok", extras={"provider_npi": "1881068062"})
scrubber.filter(rec)
assert rec.provider_npi == "<redacted:npi>"
def test_does_not_scrub_short_numbers():
scrubber = PiiScrubber()
rec = _make_record("processed 5 claims in 2 batches")
scrubber.filter(rec)
assert rec.getMessage() == "processed 5 claims in 2 batches"
def test_does_not_scrub_eleven_digit_numbers():
"""11+ digit numbers aren't NPIs — leave them alone."""
scrubber = PiiScrubber()
rec = _make_record("control number 12345678901")
scrubber.filter(rec)
assert rec.getMessage() == "control number 12345678901"
# ---------------------------------------------------------------------------
# SSN
# ---------------------------------------------------------------------------
def test_scrubs_dashed_ssn_in_message():
scrubber = PiiScrubber()
rec = _make_record("ssn=123-45-6789 detected")
scrubber.filter(rec)
assert rec.getMessage() == "ssn=<redacted:ssn> detected"
def test_scrubs_undashed_ssn_at_phrase_boundary():
"""A bare 9-digit number is ambiguous — we scrub it when followed
by whitespace/punctuation/closing paren/brace/comma (so we don't
hit claim control numbers or zip codes mid-sentence)."""
scrubber = PiiScrubber()
rec = _make_record("ssn 123456789 on file")
scrubber.filter(rec)
assert "<redacted:ssn>" in rec.getMessage()
# ---------------------------------------------------------------------------
# DOB
# ---------------------------------------------------------------------------
def test_scrubs_dob_field():
scrubber = PiiScrubber()
rec = _make_record("dob=1980-04-12 verified")
scrubber.filter(rec)
assert rec.getMessage() == "dob=<redacted:dob> verified"
def test_scrubs_dob_in_extras():
scrubber = PiiScrubber()
rec = _make_record("ok", extras={"date_of_birth": "1980-04-12"})
scrubber.filter(rec)
assert rec.date_of_birth == "<redacted:dob>"
def test_does_not_scrub_bare_iso_date():
"""A YYYY-MM-DD without a dob= prefix isn't necessarily PHI."""
scrubber = PiiScrubber()
rec = _make_record("parsed at 2026-06-21")
scrubber.filter(rec)
assert rec.getMessage() == "parsed at 2026-06-21"
# ---------------------------------------------------------------------------
# Patient name
# ---------------------------------------------------------------------------
def test_scrubs_patient_name_field():
scrubber = PiiScrubber()
rec = _make_record('patient_name="John Doe" verified')
scrubber.filter(rec)
assert "John Doe" not in rec.getMessage()
assert "<redacted:patient_name>" in rec.getMessage()
def test_does_not_scrub_random_words():
scrubber = PiiScrubber()
rec = _make_record("the parser ran successfully")
scrubber.filter(rec)
assert rec.getMessage() == "the parser ran successfully"
# ---------------------------------------------------------------------------
# Disable toggle
# ---------------------------------------------------------------------------
def test_scrubber_disabled_leaves_message_intact():
scrubber = PiiScrubber()
scrubber.disable()
rec = _make_record("npi 1881068062 ok")
scrubber.filter(rec)
assert rec.getMessage() == "npi 1881068062 ok"
def test_scrubber_does_not_crash_on_unusual_records():
"""Even with weird attribute combinations the filter returns True."""
scrubber = PiiScrubber()
rec = _make_record("ok", extras={"weird": object()})
assert scrubber.filter(rec) is True
+127
View File
@@ -0,0 +1,127 @@
"""SP18 — ``setup_logging`` entry-point tests.
Covers level resolution, handler attachment, env-var overrides, and
the idempotent re-setup behavior used by the FastAPI lifespan and
the CLI's ``main()``.
"""
from __future__ import annotations
import logging
import os
from pathlib import Path
import pytest
from cyclone.logging_config import (
CycloneDevFormatter,
JsonFormatter,
PiiScrubber,
setup_logging,
)
@pytest.fixture(autouse=True)
def _reset_root_logger():
"""Strip our handlers + filters before each test so setup runs clean."""
root = logging.getLogger()
for h in list(root.handlers):
root.removeHandler(h)
for flt in list(root.filters):
if isinstance(flt, PiiScrubber):
root.removeFilter(flt)
yield
for h in list(root.handlers):
root.removeHandler(h)
for flt in list(root.filters):
if isinstance(flt, PiiScrubber):
root.removeFilter(flt)
def test_setup_respects_level_string():
setup_logging(level="DEBUG", json_format=True)
assert logging.getLogger().level == logging.DEBUG
setup_logging(level="WARNING", json_format=True)
assert logging.getLogger().level == logging.WARNING
def test_setup_attaches_rotating_file_handler(tmp_path: Path):
log_file = tmp_path / "cyclone.log"
setup_logging(level="INFO", log_file=str(log_file), json_format=True)
root = logging.getLogger()
assert len(root.handlers) == 1
h = root.handlers[0]
# RotatingFileHandler has ``baseFilename`` attr.
assert hasattr(h, "baseFilename")
assert Path(h.baseFilename).name == "cyclone.log"
def test_setup_defaults_to_json_formatter():
setup_logging(level="INFO")
root = logging.getLogger()
assert isinstance(root.handlers[0].formatter, JsonFormatter)
def test_setup_dev_toggle_uses_dev_formatter():
setup_logging(level="INFO", json_format=False)
root = logging.getLogger()
assert isinstance(root.handlers[0].formatter, CycloneDevFormatter)
def test_setup_idempotent_re_setup_replaces_handlers():
"""Re-calling setup_logging clears the previous handler(s)."""
setup_logging(level="INFO", json_format=True)
setup_logging(level="DEBUG", json_format=False)
root = logging.getLogger()
assert len(root.handlers) == 1
assert isinstance(root.handlers[0].formatter, CycloneDevFormatter)
assert root.level == logging.DEBUG
def test_setup_quietens_noisy_third_party_loggers():
setup_logging(level="DEBUG", json_format=True)
for noisy in ("urllib3", "paramiko", "sqlalchemy.engine"):
assert logging.getLogger(noisy).level >= logging.WARNING
def test_setup_attaches_pii_scrubber_by_default():
setup_logging(level="INFO", json_format=True)
root = logging.getLogger()
assert any(isinstance(f, PiiScrubber) for f in root.filters)
def test_setup_honors_scrub_pii_false():
setup_logging(level="INFO", json_format=True, scrub_pii=False)
root = logging.getLogger()
# Scrubber is still attached but disabled.
scrubbers = [f for f in root.filters if isinstance(f, PiiScrubber)]
assert len(scrubbers) == 1
assert scrubbers[0]._enabled is False # noqa: SLF001
def test_setup_honors_env_var_no_pii_scrub(monkeypatch):
monkeypatch.setenv("CYCLONE_LOG_NO_PII_SCRUB", "1")
setup_logging(level="INFO", json_format=True)
scrubbers = [f for f in logging.getLogger().filters if isinstance(f, PiiScrubber)]
assert scrubbers and scrubbers[0]._enabled is False # noqa: SLF001
def test_setup_emits_json_to_stderr_by_default(caplog):
"""Records emitted after setup flow through JsonFormatter."""
setup_logging(level="INFO", json_format=True)
logger = logging.getLogger("cyclone.test_setup")
logger.info("hello %s", "world", extra={"x": 1})
# Cyclone attaches the handler to root, not the named logger; caplog
# won't capture unless we propagate (which is the default).
# Just assert the handler is on root and would format correctly.
root = logging.getLogger()
h = root.handlers[0]
record = logger.makeRecord(
name="cyclone.test_setup", level=logging.INFO, fn="t.py", lno=1,
msg="hello %s", args=("world",), exc_info=None,
)
record.x = 1
formatted = h.formatter.format(record)
import json as _json
parsed = _json.loads(formatted)
assert parsed["msg"] == "hello world"
assert parsed["extra"]["x"] == 1