fix(skillopt-sleep): redact secrets before persisting cycle diagnostics
PR #92 added a per-cycle diagnostics.json that surfaces backend stderr, optimizer replies, and task responses so a 0.0 night is self-diagnosing. Those free-text fields can carry credentials (e.g. a codex 401 stderr dump containing an auth token), so persisting them verbatim was a new on-disk leak surface. - Add a shared redact_secrets() in staging.py and route diagnostics.json's call_error / reflect_raw_head / holdout_detail through it before writing. - Redact the codex and Claude auth-error log lines too (a secondary sink when a file log handler is attached); last_call_error stays raw in memory so _AUTH_MARKERS matching is unaffected. - Centralize _SECRET_PATTERNS in staging.py (harvest_codex now reuses them) and extend coverage to AWS / GitHub / Slack / Google / JWT token shapes. - Tests: secret-shape coverage, private-key blocks, recursive/scalar passthrough, no over-redaction of plain prose, fail-fast auth-error log redaction, and an end-to-end check that diagnostics.json has no secret. Observability-only; the gate and learning algorithm are unchanged. Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
@@ -16,29 +16,9 @@ from skillopt_sleep.harvest import (
|
||||
_iter_jsonl,
|
||||
_project_matches,
|
||||
)
|
||||
from skillopt_sleep.staging import _SECRET_PATTERNS
|
||||
from skillopt_sleep.types import SessionDigest
|
||||
|
||||
_SECRET_PATTERNS: tuple[tuple[re.Pattern[str], str], ...] = (
|
||||
(re.compile(r"sk-[A-Za-z0-9_-]{10,}"), "[REDACTED_OPENAI_KEY]"),
|
||||
(re.compile(r"(?i)(Authorization:\s*Bearer\s+)[^\s\"']+"), r"\1[REDACTED]"),
|
||||
(re.compile(r"(?i)(Authorization:\s*Basic\s+)[^\s\"']+"), r"\1[REDACTED]"),
|
||||
(
|
||||
re.compile(r"(?i)\b(api[_-]?key|token|password|secret)\b(\s*[:=]\s*)[^\s\"']+"),
|
||||
r"\1\2[REDACTED]",
|
||||
),
|
||||
(
|
||||
re.compile(r"(?i)\b(api[_-]?key|token|password|secret)\b(\s+)[^\s\"']+"),
|
||||
r"\1\2[REDACTED]",
|
||||
),
|
||||
(
|
||||
re.compile(
|
||||
r"-----BEGIN [A-Z ]*PRIVATE KEY-----.*?-----END [A-Z ]*PRIVATE KEY-----",
|
||||
re.DOTALL,
|
||||
),
|
||||
"[REDACTED_PRIVATE_KEY]",
|
||||
),
|
||||
)
|
||||
|
||||
|
||||
def _payload(rec: Dict[str, Any]) -> Dict[str, Any]:
|
||||
payload = rec.get("payload")
|
||||
|
||||
Reference in New Issue
Block a user