Files
odysseus/tests/test_log_safety.py
T
nopoz 7e5db9a3c6 fix(security): redact credential-bearing URLs and PII from logs (#4750)
* fix(security): redact credential-bearing URLs and PII from logs

Several log statements emitted sensitive data in clear text:

- model_routes / chat_routes / contacts_routes logged endpoint URLs raw.
  Admin-configured URLs can embed credentials in userinfo or query
  (e.g. https://user:pass@host, ?api_key=...). Route them through a
  shared core.log_safety.redact_url() that drops userinfo/query/fragment.
- note_routes / task_scheduler logged operator email addresses (smtp_user,
  recipient). Replaced with presence booleans, which keeps the diagnostic
  ("why didn't this send") without writing PII to logs.

model_routes already had a local redactor on its HTTPStatusError branch;
the generic except branch was missed, so reuse the existing helper there.

Clears CodeQL py/clear-text-logging-sensitive-data alerts 264, 317, 324,
325, 343, 344, 528.

* fix(security): re-bracket IPv6 hosts and single-source the URL redactor

Address review on #4750:
- redact_url now re-brackets IPv6 literals so host:port stays
  unambiguous (https://[2001:db8::1]:8443/v1, not the bracket-less
  ambiguous form).
- point model_routes._redact_url_for_log at the shared helper so the
  two redactors are single-sourced (also picks up the IPv6 fix).
2026-06-22 23:12:39 +02:00

33 lines
1.0 KiB
Python

from core.log_safety import redact_url
def test_strips_userinfo():
assert redact_url("https://user:pass@host.example/v1/models") == "https://host.example/v1/models"
def test_strips_query_and_fragment():
assert redact_url("https://host.example/v1?api_key=secret#frag") == "https://host.example/v1"
def test_keeps_port_and_path():
assert redact_url("http://host.example:8080/api/tags") == "http://host.example:8080/api/tags"
def test_ipv6_host_keeps_brackets():
assert redact_url("https://user:pass@[2001:db8::1]:8443/v1") == "https://[2001:db8::1]:8443/v1"
assert redact_url("https://[2001:db8::1]/v1") == "https://[2001:db8::1]/v1"
def test_no_credentials_passthrough():
assert redact_url("https://host.example/v1/models") == "https://host.example/v1/models"
def test_empty_and_none():
assert redact_url("") == ""
assert redact_url(None) == ""
def test_garbage_does_not_raise():
# urlparse is lenient; just assert no credential-looking userinfo survives.
assert "@" not in redact_url("::::not a url::::")