Merged
Conversation
Introduce multi-language architecture with a marker registry abstraction,
Japanese marker definitions (スピリチュアル, 霊感商法, カルト, etc.),
and a `lang` parameter ("en" | "ja") flowing through the core library,
CLI (--lang), and REST API. All existing English behaviour is preserved
(default lang="en"). Includes Japanese NLP pipeline (ja_core_news_sm),
201 tests at 99% coverage, CI updates, and a strategy document.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Deploying si-protocols with
|
| Latest commit: |
b876a73
|
| Status: | ✅ Deploy successful! |
| Preview URL: | https://5cbdd887.si-protocols.pages.dev |
| Branch Preview URL: | https://feature-japanese-language-su.si-protocols.pages.dev |
Owner
Author
|
I will be updating |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
marker_registry.py) — newMarkerSetfrozen dataclass andget_markers(lang)dispatch function with lazy loading and caching, making the core library language-aware and extensiblemarkers_ja.py) — all 12 marker categories culturally adapted for Japanese spiritual contexts (スピリチュアル, 霊感商法, カルト, 秘密結社, etc.)langparameter ("en"|"ja", default"en") flows throughtech_analysis(),hybrid_score(), CLI (--lang), and API (langfield onPOST /analyse)_nlpwith_nlp_cachedict for per-language lazy loading (en_core_web_sm/ja_core_news_sm)ja_core_news_smmodel added to test matrixdocs/STRATEGY.mdarticulating mission, SI definition, approach, audience, and roadmaplang="en");markers.py,output.py,test_markers.py, andtest_output.pyuntouchedNew files (6)
src/si_protocols/marker_registry.pysrc/si_protocols/markers_ja.pytests/test_marker_registry.pytests/test_markers_ja.pyexamples/synthetic_suspicious_ja.txtdocs/STRATEGY.mdModified files (7)
src/si_protocols/threat_filter.py— multi-model loading,langparam, marker dispatchapp/schemas.py—langfield onAnalyseRequestapp/main.py— passlangthroughtests/test_threat_filter.py— Japanese fixture texts and test classestests/test_api.py— Japanese API tests.github/workflows/ci.yml— installja_core_news_smCLAUDE.md— updated architecture and dev commandsTest plan
🤖 Generated with Claude Code