Tagging-v2: heads are the suggestion source (learn-from-tags) + rail accept/reject #142

Merged

bvandeusen merged 7 commits from dev into main 2026-06-28 11:55:49 -04:00

Conversation 0 Commits 7 Files Changed 28

+1586 -494

bvandeusen commented 2026-06-28 11:55:41 -04:00

Owner

Copy Link

Copy Source

Lands the first production milestone of tagging-v2 (#114): suggestions now come from per-concept heads that learn from the operator's tags, replacing the static Camie predictions + per-tag centroid.

What's in this merge

• Rail interaction: green ✓ / red ✗ verdict pair on suggestion rows; rejection is now visible + reversible (dismissed tags stay flagged with one-click undo, survive reload).
• Heads backend (slice A): tag_head + head_training_run (migration 0058), heads.py train/score service (reuses the eval's proven math), train_heads Celery task + recovery/retention/beat, /api/heads endpoints, head_min_positives / head_auto_apply_precision settings.
• Admin UI (slice B): Settings → Tagging → Concept heads — train/retrain, live status, per-concept strength table (AP / precision / recall / ⚡auto-apply-ready).
• Suggestion swap (slice C): SuggestionService.for_image sources from heads.score_image; Camie prediction + centroid removed from the suggestion path. Suggestion tests rewritten head-based.

Deploy sequence (order matters)

1. Redeploy :latest — migration 0058 runs automatically.
2. Settings → Tagging → Concept heads → Train heads (one-time pass on the ml-worker).
3. Rail then shows head-driven suggestions. Empty until trained — expected.

Deliberately deferred (follow-up)

The wider Camie rip (ingest tagger + ImagePrediction table + inert alias UI) and the next milestone slice (CCIP characters + comic-panel/region crops) are separate.

🤖 Generated with Claude Code

Lands the first production milestone of tagging-v2 (#114): suggestions now come from per-concept **heads** that learn from the operator's tags, replacing the static Camie predictions + per-tag centroid. ## What's in this merge - **Rail interaction**: green ✓ / red ✗ verdict pair on suggestion rows; rejection is now **visible + reversible** (dismissed tags stay flagged with one-click undo, survive reload). - **Heads backend** (slice A): `tag_head` + `head_training_run` (migration 0058), `heads.py` train/score service (reuses the eval's proven math), `train_heads` Celery task + recovery/retention/beat, `/api/heads` endpoints, `head_min_positives` / `head_auto_apply_precision` settings. - **Admin UI** (slice B): Settings → Tagging → **Concept heads** — train/retrain, live status, per-concept strength table (AP / precision / recall / ⚡auto-apply-ready). - **Suggestion swap** (slice C): `SuggestionService.for_image` sources from `heads.score_image`; Camie prediction + centroid removed from the suggestion path. Suggestion tests rewritten head-based. ## Deploy sequence (order matters) 1. Redeploy `:latest` — migration 0058 runs automatically. 2. Settings → Tagging → Concept heads → **Train heads** (one-time pass on the ml-worker). 3. Rail then shows head-driven suggestions. **Empty until trained — expected.** ## Deliberately deferred (follow-up) The wider Camie rip (ingest tagger + ImagePrediction table + inert alias UI) and the next milestone slice (CCIP characters + comic-panel/region crops) are separate. 🤖 Generated with [Claude Code](https://claude.com/claude-code)

bvandeusen added 7 commits 2026-06-28 11:55:41 -04:00

feat(modal): green ✓ / red ✗ verdict pair on suggestion rows ... 1d39afa3b6

Replace the single "Accept" pill in the modal Suggestions rail with the
eval card's green ✓ / red ✗ language: ✓ accepts the tag (positive), ✗
dismisses it for this image — which already persists a TagSuggestionRejection
(hard negative the heads train on). The pair occupies ~the footprint of the
old pill, so per-image rejection becomes a one-click peer of accepting
instead of being buried in the kebab.

Dismiss moves off the 3-dot menu, so the kebab now only carries alias
actions and is hidden when none apply (centroid hits with no alias option).

Toward #1134 (native per-image negatives in the rail). The bigger piece —
heads as a suggestion source feeding this panel — is still ahead.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

feat(suggestions): visible, reversible rejection in the modal rail ... 179c1a9dcc

A red-✗ dismissal no longer makes the suggestion vanish. The rejected tag
stays in the rail — dimmed, struck-through, with a "rejected" pill and a
one-click undo (↶) in place of the ✗ — so a misclick is recoverable and the
operator can see what they've said no to (operator-asked 2026-06-27).

Backend: SuggestionService.for_image now KEEPS rejected tags, flagged
rejected=True, sorted to the bottom of their category, instead of dropping
them. New AllowlistService.undismiss + POST /suggestions/undismiss clears the
TagSuggestionRejection. Rejected items are still excluded from bulk consensus
(for_selection) and the type-to-add dropdown, whose jobs are unchanged.

Frontend: store.dismiss flags in place (canonical tags) rather than dropping;
new store.undismiss reverts. SuggestionItem renders the rejected state and
swaps ✗→↶; ✓ still accepts (which clears the rejection server-side).

Tests: rejected-surfaced-flagged-then-reversible (service) + undismiss
endpoint idempotency (API).

Completes #1134's reversible-rejection half. Heads-as-suggestion-source is
the remaining piece.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

feat(heads): production per-concept heads — train + score backend (#114 A) ... 22c3b54746

The eval (#1130) proved the frozen-embedding + trained-head spine; this lands
its production form (the first of three slices that make heads the suggestion
source, replacing Camie + centroid).

- tag_head: one logistic-regression head per general/character concept with
  enough labelled positives. Weights (pgvector), honest CV-derived suggest
  threshold + earned-auto-apply point, and per-concept quality metrics.
- head_training_run: persisted batch lifecycle (mirrors tag_eval_run) so the
  admin card shows live + historical status across navigation.
- services/ml/heads.py: TRAIN (sync, ml worker, reuses tag_eval's proven data
  loaders + metric math so production heads match measured eval numbers) and
  SCORE (async, API worker — numpy via pgvector, no scikit-learn): score one
  image's embedding against all heads → the rail's suggestions, cached on
  (count, max trained_at) so a retrain invalidates without per-request loads.
- tasks.ml.train_heads (ml queue, commits per head so a kill leaves progress)
  + recover_stalled_head_training_runs sweep + retention(20) + 5-min beat
  (rule 89).
- api/heads.py: POST /api/heads/train (one run at a time, 409 guard) + GET
  /api/heads (count, graduated, last-trained, running, per-concept table,
  recent runs).
- ml_settings: head_min_positives + head_auto_apply_precision, tunable via
  /api/ml/settings.

Scoring isn't wired into the rail yet (slice C) and the admin UI is slice B —
this slice makes training + scoring exist and CI-verifiable. 'precision' column
stored as precision_cv (SQL reserved word). Migration 0058.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

fix(test): match rejected suggestion by id, not display casing ... 291b90803d

test_rejected_tag_surfaced_flagged_then_reversible asserted "Rejectme" but an
existing tag keeps its stored name ("rejectme"), so the suggestion's
display_name is lowercase. Match by canonical_tag_id instead (casing-robust).
The feature was correct — only the assertion was wrong (run 1595 integration).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

style(heads): fix import ordering (ruff I001) ... 1ed0895e8d

Alphabetize HeadTrainingRun in models/__init__ + maintenance imports (H before
I), and drop the inline comment that split heads.py's import block. Pure import
ordering — no behavior change. (run 1601 lint)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

feat(heads): admin card to train + inspect concept heads (#114 B) ... 06d5e83da4

The UI for the heads subsystem: Settings → Tagging → "Concept heads". Shows
head count, auto-apply-ready count, and last-trained; a Train/Retrain button
(one run at a time, polls while running, surfaces a failed run's error); an
empty state guiding the operator to tag first; and a per-concept table (name,
category, +tags, AP, P, R, auto-apply ⚡) sorted strongest-first so weak/under-
tagged concepts are obvious. Rehydrates status from GET /api/heads on mount so
it survives navigation. Pulls head_min_positives from ML settings for copy.

Slice C (swap the rail's suggestions to heads, remove Camie + centroid) is next.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

feat(suggestions): heads are the suggestion source — Camie + centroid removed (#114 C) ... ca1c17446c

The rail's Suggestions now come from the trained per-concept heads. SuggestionService.for_image scores the image's frozen SigLIP embedding against
every head (heads.score_image) and surfaces concepts above each head's own
suggest threshold; the typed-dropdown's min=0 "show everything" mode maps to a
flat floor so any head-scored concept can still be picked. Already-applied tags
drop; rejected tags stay flagged + reversible (unchanged).

REMOVED from the suggestion path (rule 22, no fallback): the Camie
ImagePrediction candidate/alias/merge pipeline and the per-tag centroid
augmentation, plus the now-dead SuggestionService internals (_load_predictions,
_threshold_for, _settings, self.aliases, self.centroids). Head suggestions are
always canonical tags, so raw_name/via_alias are null/false and the rail's
alias kebab is inert by data (its removal + the Camie ingest-tagger rip are the
flagged follow-up). for_selection (bulk consensus) now aggregates head
suggestions unchanged.

Tests rewritten to the head path: test_ml_suggestions (surfaces/applied/
rejected-reversible/override/no-embedding/no-heads), test_suggestions_bulk
(consensus), test_api_suggestions (get + dropped the Camie-alias roundtrip),
and test_ml_artist_retired (artist not head-eligible via _HEAD_KINDS).

DEPLOY NOTE: after this lands, the rail is empty until you run Train heads
(Settings → Tagging → Concept heads) — deploy, train, then the rail populates.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa

bvandeusen merged commit 1bef68aa29 into main 2026-06-28 11:55:49 -04:00

bvandeusen referenced this pull request 2026-06-29 07:30:33 -04:00

Earned auto-apply (fire + observability + UI), retrain cadences, Explore arrow-nav #143

Sign in to join this conversation.

Reviewers

No Reviewers

Labels

No items

No Label

Milestone

No items

No Milestone

Projects

Clear projects

No project

Assignees

Clear assignees

bvandeusen

No Assignees

1 Participants

Notifications

Subscribe

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: bvandeusen/FabledCurator#142