Skip to main contentModule utils
Source - SanitizeAction
- Sanitize result: allow / redact (content cleaned) / discard (reject write).
- content_hash
- cosine_similarity
- Cosine similarity between two equal-length slices. Returns 0.0 on zero norms.
- default_sanitize
- Default sanitizer per §二·六 design doc.
Injection patterns → discard (priority over redact).
Secret/credential patterns → redact ([REDACTED] substitution).
- estimate_tokens
- Rough token estimate: 1 token ≈ 4 chars.
- gen_uuid
- pack_embedding
- Pack a Vec into bytes (little-endian f32 array).
- sanitize
- Public sanitize function used by KnowledgeBase — wraps default_sanitize.
Returns (cleaned_content, action).
- unpack_embedding
- Unpack bytes into Vec.
- utc_now_iso