sync: multi-branch scanning, discovery strategies, UTF-8 fix, curation improvements

- Add multi-branch scanning to discover skills on non-default branches
- Add popular repos and commits search discovery strategies
- Fix UTF-8 encoding sanitization in skill parser
- Add repo_created_at for threshold-based duplicate tie-breaking
- Add indexer tests and vitest config

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
airano
2026-02-22 04:16:35 +03:30
parent 3f599a23fb
commit b05cb21a65
20 changed files with 1314 additions and 64 deletions

View File

@@ -65,6 +65,7 @@ CREATE TABLE IF NOT EXISTS skills (
-- Timestamps
created_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP NOT NULL,
updated_at TIMESTAMP WITH TIME ZONE DEFAULT CURRENT_TIMESTAMP NOT NULL,
repo_created_at TIMESTAMP WITH TIME ZONE,
indexed_at TIMESTAMP WITH TIME ZONE,
last_downloaded_at TIMESTAMP WITH TIME ZONE
);
@@ -478,6 +479,13 @@ CREATE INDEX IF NOT EXISTS idx_skills_type ON skills(skill_type);
CREATE INDEX IF NOT EXISTS idx_skills_duplicate ON skills(is_duplicate);
CREATE INDEX IF NOT EXISTS idx_skills_content_hash ON skills(content_hash);
-- Review pipeline columns (Phase 4+5 - February 2026)
ALTER TABLE skills ADD COLUMN IF NOT EXISTS review_status TEXT DEFAULT 'unreviewed';
CREATE INDEX IF NOT EXISTS idx_skills_review_status ON skills(review_status);
-- Repo creation date for duplicate tie-breaking (T074b)
ALTER TABLE skills ADD COLUMN IF NOT EXISTS repo_created_at TIMESTAMP WITH TIME ZONE;
-- Grant permissions
GRANT ALL PRIVILEGES ON ALL TABLES IN SCHEMA public TO postgres;
GRANT ALL PRIVILEGES ON ALL SEQUENCES IN SCHEMA public TO postgres;