Commit Graph
4 Commits
Author SHA1 Message Date
mrleo1nidandClaude Opus 5.5 fb07f962eb feat: taste onboarding for new listeners (M6)
ci / contract / contract (сгенерированный код совпадает с openapi.yaml) (push) Successful in 1m2s
ci / db / db (push) Failing after 1m29s
ci / ts / ts (packages + web) (push) Successful in 49s
ci / api / api (push) Successful in 1m25s
ci / mobile / mobile (Metro-бандл Android) (push) Successful in 48s
ci / recommender / recommender (push) Successful in 21s
- GET /onboarding offers the library's top artists (with album covers)
  and genres and says whether to show it (not done and < 10 plays);
  PUT /me/onboarding stores the choice or a skip (migration 00009).
- The recommender seeds the taste from it while the user has fewer than
  30 scored tracks: chosen artists' tracks +1, chosen genres +0.5.
- Web: onboarding replaces the wave on the home page until done or
  skipped; artist grid with covers, genre chips, at least 3 artists.
- e2e journey and the recommender DB test cover it.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 22:35:43 +03:00
mrleo1nidandClaude Opus 5.5 ff0aafdb1e feat(recommender): Thompson-sampling bandit over candidate sources (M6)
ci / recommender / recommender (push) Failing after 4s
ci / db / db (push) Failing after 2m21s
Nightly Beta(α, β) per user and source from wave impressions (reward:
complete or like, ×0.99 daily decay) stored in user_profiles_rec.bandit;
the wave adds 0.2·(θ − 0.5) per candidate source, sources without data
stay neutral. The user's exploration share now follows how well `fresh`
does against the other sources.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 22:31:24 +03:00
mrleo1nidandClaude Opus 5.5 3afed02f23 feat(recommender): nightly ALS with offline metrics and CF candidates in the wave (M6)
ci / recommender / recommender (push) Successful in 37s
- Implicit scores from play events and reactions per the signals table
  (90-day half-life, weaker skips outside the wave, dislikes override).
- numpy ALS for implicit feedback; time-split evaluation on the last
  7 days (NDCG@10, Recall@50) against a popularity baseline; a new model
  is activated only if NDCG@10 does not regress by more than 2%.
- Vectors are written to track_embeddings.cf and user_profiles_rec.taste_cf,
  versions to model_versions; NightlyTrainer runs at TRAIN_HOUR and on
  first start, `pipu-rec train` runs it manually.
- Wave: cf and item_cf candidate sources and a 0.10 cf term in the v1
  score; impressions are tagged heuristic-v1+cf.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-20 17:54:25 +03:00
mrleo1nidandClaude Opus 5.5 9eb1c25147 docs: add product idea, design prototypes and development documentation
- IDEA.md: product vision from the user's perspective (input for design)
- Architecture, ADRs, data model, REST API overview
- Auth and roles, library storage (NFS, path regexes, scanner, search),
  playback, recommendation system ("My Wave"), track upload queue
- Web, Android (offline, self-update), i18n, design system
- Testing strategy, Gitea Actions CI/CD, deployment, conventions, roadmap
- Clickable web/Android design prototypes and wave button variants
- .claude/launch.json to serve the prototypes locally

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-19 23:21:31 +03:00