The Explore walk got stuck in dense signatures — neighbours all too similar, so
forward-arrow couldn't escape and Random was the only exit. Root cause: MMR only
diversifies WITHIN the nearest ~400 pool; in a dense cluster that whole pool is
near-identical, so there's no escape route in it.
- gallery_service.similar(reach=0.0, exclude_ids=None): reach>0 widens the pool
(cap 400→1000) and _reach_sample strides across an outward-growing distance span
so the set handed to MMR spans near→mid-far (guaranteed escape routes), not just
the tight cluster. exclude_ids drops already-walked images. Gallery 'more like
this' (reach=0) is unchanged.
- api/gallery similar: parse reach + exclude_ids.
- explore store: default reach 0.4 (auto-diversifies without touching the dial),
pass the breadcrumb as exclude_ids, setReach action.
- ExploreView: a Near↔Far reach slider in the trail.
- tests: _reach_sample math (deeper ranks with higher reach, near kept); similar
exclude_ids drops walked + reach path runs clean.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Explore's neighbour grid (/api/gallery/similar → gallery_service.similar) now
takes an Explore-only exclude_wip flag that drops `wip` system-tagged images
from the candidates, alongside the banner/editor presentation tags. The
gallery's own "similar" button is unchanged (keeps wip, #1274) — only the
Explore store passes exclude_wip=1. The anchor itself may still be a WIP; only
neighbours are filtered.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Step 3 of milestone #128. Presentation-tagged images cluster on UI
chrome rather than content, so near any one of them they fill the whole
more-like-this grid. Excluded from candidates in the ONE whole-image
similarity surface (gallery similar mode, explore walk, and RelatedStrip
all ride GalleryService.similar) — the anchor itself may be a banner,
and wip stays surfaced: only the training pipelines exclude it.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
Pure nearest-cosine piled near-identical images into the neighbour grid — a
reposted banner filled all 24 slots, and once you wandered into a B&W /
comic-panel cluster every neighbour was more of the same with no way back to
colour without the Random button (operator-reported, with screenshot).
similar() now over-fetches a wide candidate pool (5x the requested limit, cap
200), then diversifies down to `limit`:
- pHash near-duplicate collapse: drop candidates within 6 Hamming bits of the
anchor or an already-kept candidate, so a repost (and the anchor's own clones)
appears at most once.
- MMR re-rank: greedily pick for closeness-to-anchor minus similarity-to-already
-picked (lambda 0.55), so the result SPANS clusters instead of returning 40
variations of one image. Falls back to nearest-order on any failure / small
pool, so existing nearest-first behaviour is unchanged when there's nothing to
diversify.
Frontend forwardTarget drops the now-redundant skip-nearest-third hack (the list
is already diversified server-side) — plain random-over-unvisited gives the
variance now.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
GalleryService.similar() ranks images by pgvector cosine distance to a source
image's precomputed SigLIP embedding — no query-time ML inference. Composes
with the Phase-1/2 scope filters (AND) but replaces the date sort (always
nearest-first, bounded top-N, no cursor). Returns None for a missing source
(→404), [] for a source with no embedding (video / pending ML); excludes self
and NULL-embedding rows. New GET /api/gallery/similar?similar_to=<id>&limit=N.
Image-detail payload gains has_embedding so the UI can hide the surface.
Alembic 0036 adds an HNSW vector_cosine_ops index on siglip_embedding (1152<2000
dims) so the search is sub-50ms ANN instead of a full scan; one-time ~30-60s
build over existing embeddings on deploy. Shared _gallery_images/_image_json
helpers de-dup the scroll/similar builders.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
bvandeusen