Sweep 19 Sep 2026 · 02:36Z Build v2.1.278 500 read Stable v2.1.267 Latest v2.1.278 Next v2.1.278 Feeds RSS JSON llms.txt Unofficial
Claude Code v2.1.271 ·

Sensitive-data redaction split into context-pass and token-pass with confidence tiers

Sensitive-data redaction now runs in two passes split by confidence level

TierUnder the hoodhow much it should matter to you
Useful2my rating, 1 to 5
Signal2worth watching, 1 to 5
AreaElsewherewhat it touches
KindInternal Changesin v2.1.271,
Under the hood

Sensitive-data redaction now runs in two passes split by confidence level

What

The logic that redacts sensitive data (for example, before sending logs or telemetry) is now split into two passes: redactContext, which applies only rules marked "low" confidence, and redactTokens, which applies only rules marked "high" confidence. Both are combined together in the overall redact() function, replacing a single pass that applied all rules uniformly.

Why

Separating redaction by confidence tier likely allows each pass to be applied differently or tuned independently, rather than treating all matches the same regardless of how confident the match is.

How sure we are
Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.
The writer flagged doubtThe finding doesn't say why the two passes need to be separate or what different treatment each receives.

See this entry in the whole of v2.1.271 →