f09b917f1a
Framework-agnostic PII anonymization extracted from Mobiletic's chatbot. Pluggable LLM detection + configurable regex fallback, deterministic coreference, and streaming-safe de-anonymization. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
18 lines
925 B
Markdown
18 lines
925 B
Markdown
# Changelog
|
|
|
|
All notable changes to this project are documented here. The format is based on
|
|
[Keep a Changelog](https://keepachangelog.com/en/1.1.0/), and this project adheres to
|
|
[Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
|
|
## [0.1.0] - Unreleased
|
|
|
|
### Added
|
|
|
|
- Initial public release, extracted from Mobiletic's production Swiss-nLPD chatbot.
|
|
- `Anonymizer` — pre-filter → LLM → regex fallback, bidirectional validation, deterministic coreference,
|
|
and de-collision across question and retrieved chunks (`anonymize`, `anonymizeChunks`, `deanonymize`).
|
|
- `makeStreamDeanonymizer` — streaming-safe de-anonymization that never leaks a split placeholder.
|
|
- `openAICompatibleProvider` — pluggable LLM detection over any OpenAI-compatible Chat Completions API.
|
|
- `presets.swiss` and `presets.generic` regex pattern sets; fully configurable custom patterns.
|
|
- Regex-only mode (no LLM provider required).
|