presentation_auto_apply_sweep fires banner/editor-screenshot heads at the FLAT
presentation threshold (source=presentation_auto). Two guards: (1) hard-skip any
image already carrying a human/confirmed content tag — you valued it, so the model
can't bury it; (2) if an auto-hide ALSO scores >= presentation_conflict_threshold
on a content head, hide it but record a PresentationReview row (conflict tag +
score) for the Hidden view.
_auto_apply_heads now excludes system tags, so a graduated wip/banner can't fire
via the content path (and wip never auto-applies at all). presentation_auto added
to _AUTO_SOURCES so auto-hidden chrome never self-trains. Tests: applies,
hard-skip valued, conflict-flag, disabled no-op, ignores wip, content-path
excludes system. Settings UI + scheduling land next.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
- heads.py: conf_map = dict(conf) instead of a dict comprehension (ruff C416).
- postCard.spec.js: the modal-playlist rename (postImageIds→playlistIds) missed
this frontend test (grep was src-only); update the expected call args.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
Completes "no self-training": unconfirmed auto-applied character tags no longer
seed CCIP references — character_references + the prototype builder
(_current_fingerprints/_rebuild_one) gain a shared _positive_char_tag filter
(human-applied OR operator-confirmed), mirroring the head-positive exclusion.
Confirming a tag also has to move the change-detectors, or an incremental
refresh/Retrain right after a confirm wouldn't fold the tag in (only the nightly
full pass would): the CCIP global gate now counts character confirmations, and
the head training fingerprint counts confirmations. Test for the CCIP path.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
Makes auto-apply truly "soft" for heads: _ids_with_tag (head positives) and
_eligible_tag_ids (graduation count) now count human-applied + operator-confirmed
tags only, via a shared _AUTO_SOURCES (head_auto/ccip_auto/ml_auto) exclusion.
Unconfirmed auto-applied tags no longer train the head that judges them, so a
misfire can't reinforce itself and the retraction sweep can actually drop it.
Confirming a tag (TagPositiveConfirmation) promotes it to a positive AND protects
it from retraction. sklearn-free tests. CCIP reference exclusion is the companion
piece, next.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
Daily scheduled_retract_auto_tags re-scores standing auto-applied tags and drops
the ones the model no longer supports:
- retract_auto_applied_heads: per graduated head, re-score its source='head_auto'
images (bounded — only the images already carrying the auto-tag, not the whole
library) and remove ones now < auto_apply_threshold.
- retract_auto_applied_ccip: per source='ccip_auto' character tag, max-cosine the
image's figure vectors vs that character's prototypes; remove ones now below the
ccip auto-apply threshold.
Both SKIP operator-confirmed tags (TagPositiveConfirmation) and are SILENT — a low
score isn't proof the tag was wrong, so no hard negative is recorded (that's
reserved for an operator removal). No-op unless the relevant auto-apply switch is
on. New daily beat. sklearn-free tests for both paths + the disabled no-op.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
train_all_heads is now incremental by default: a per-tag training-data
fingerprint (positive + rejection count/latest-timestamp, stored on
tag_head.train_fingerprint) means a manual Retrain refits ONLY the tags whose
data changed — O(what you touched), not O(all heads). The nightly
scheduled_train_heads passes full=True to reconcile sampled-negative + hygiene
drift across every head. First incremental run after deploy still refits
everyone (NULL fingerprints), stamping them, then it's incremental.
The refit decision + fingerprint are split into sklearn-free helpers
(_head_fingerprints, _heads_needing_retrain) so the incremental logic is
unit-tested directly (train_head itself needs scikit-learn). Migration 0080.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
Applied tags aren't scored live, so compute the grounding on demand: run the
tag's head over the image's max-over-bag (whole-image + concept crops), argmax
→ the region that best explains the tag on this image, mirroring what
score_image records for live suggestions.
- heads.py: extract _image_bag (now shared by score_image) + ground_applied_tag.
Returns (grounding, has_head): has_head False = no head to localize with →
no overlay; grounding None = the whole-image vector won → whole-image frame.
- tags.py: GET /api/images/<id>/tags/<id>/grounding → {grounding, has_head}.
- TagChip/TagPanel: applied chips inject fcSuggestionHover and fetch grounding
on hover (cached per image+tag, race-guarded), reusing Step 3's overlay in
both the modal and Explore. No new frontend overlay code.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
score_image now keeps the ARGMAX beside the max-over-bag: which bag row won each
head. The region query also selects bbox/kind/detector_version, a parallel
bag_meta maps each row → its region (None for the whole-image vector), and every
hit gains grounding {bbox,kind,detector} (null when the global vector won). Threaded
through SuggestionService (new Suggestion.grounding field) → /api/.../suggestions
payload. This is the data the #1206 hover-overlay draws. CCIP-only hits ground null
for now (figure grounding = step 2). Tests: winning crop grounds the tag with its
bbox+kind; whole-image win → grounding None.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
System tags are kind=general, so their suggestions previously landed in the
General group. Give them their own 'system' suggestion category so the operator
reviews them apart from content tags: _current_heads maps is_system heads to
category 'system' (still trained as general heads, still gated by the 0.65
floor). Frontend: CATEGORY_ORDER/LABELS gain 'system'; SuggestionsPanel renders
a 'System' group first (small, collapsible, open — false positives easy to spot
and reject); the typed-dropdown shows the shield icon for system entries. Safe:
system-tag suggestions always carry a canonical_tag_id, so the create-by-kind
path (which would send 'system' as a TagKind) is never hit.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
System tags (wip/banner/editor) already get heads (kind=general) and aren't
filtered from suggestions, but they surfaced only at each head's precision-tuned
suggest_threshold — high enough to hide the borderline/false-positive guesses the
operator wants to SEE and REJECT (hard-negative mining: 'negatively reinforce
what isn't a system tag'). score_image now uses a flat _SYSTEM_TAG_SUGGEST_FLOOR
(0.65, operator-set) for system-tag heads instead of their auto threshold;
content-tag heads keep their own, and the typed-dropdown threshold_override still
overrides everything. _current_heads carries Tag.is_system into the head meta to
drive it.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
Step 2 of milestone #128. _hygiene_excluded_ids (training_data.py) is the
one shared predicate: images carrying any system tag are dropped from
every OTHER concepts head training — not positives (a rough wip tagged
as a character drags the head toward generic-sketch) and not rejection
or sampled negatives (a wip OF character X is not evidence against X).
A system tags own head trains on them unfiltered; that is what makes
auto-flagging banners work. Selection is split out of train_head as the
sklearn-free head_training_ids so CI (no sklearn) can pin the behavior.
CCIP: reference prototypes skip hygiene-tagged images — a faceless wip
figure region must never become an identity reference — and the ref
cache signature now counts hygiene applications, since tagging an image
wip changes the reference set without touching character/region counts.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
The head-vs-centroid eval (#1130) existed to prove the 'frozen embedding +
trained head' spine; the operator accepted the tagging system and dropped the
harness. Removed per rule 22: TagEvalCard + store, /api/tag_eval blueprint,
tag_eval_run ml task, recover-stalled-tag-eval-runs sweep + beat entry,
TagEvalRun model + table (migration 0073), and its tests.
The eval's data loaders + metric helpers were NOT eval-specific — the nightly
heads trainer runs on them — so they moved verbatim to
services/ml/training_data.py (heads.py import updated; behavior unchanged).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
Make the SigLIP embedder an operator choice (drop-in to SigLIP 2:
google/siglip2-so400m-patch16-512 is a verified 1152-d model at 512px → no
schema change, better small-cue fidelity). A swap = set model + re-embed +
retrain, all operator-driven; the GPU agent does the re-embed so it's fast.
- settings: embedder_model_name is now a setting (migration 0065) alongside the
existing embedder_model_version; both editable + validated (non-empty) in the
ml admin API. The server embedder loads by HF name (AutoImageProcessor/Model,
model-agnostic), preferring the pre-downloaded local dir for the default so
existing deploys don't re-download; rebuilds on a name change.
- agent: new 'embed' job = whole-image SigLIP embedding (mean-pool video frames)
under the lease-announced model → POST /jobs/submit_embedding writes
image_record.siglip_embedding + siglip_model_version. The lease now announces
the model FROM THE SETTING (not a constant).
- re-embed routing: enqueue_gpu_backfill('embed') selects unembedded + stale-
version images; 'siglip' now re-embeds concept crops whose version != current
(so a swap re-triggers crops, not just the never-embedded back-catalogue). The
CPU ml-worker backfill no longer re-embeds on a version mismatch (it can't
churn the library at 512px) — the GPU agent owns version re-embeds. Daily
'embed' + 'siglip' beats self-heal.
- scoring: score_image only bags embeddings in the CURRENT model's space (whole-
image gated by siglip_model_version, concept regions by embedding_version) so a
mid-swap stale vector isn't scored by new-space heads; legacy NULL = current.
- UI: GpuAgentCard "Embedding model (advanced)" — edit name/version, Save, and
"Re-embed library (GPU)" (queues embed + siglip); points at SigLIP 2.
Tests: lease announces model + submit_embedding round-trip; enqueue 'embed'
selects stale/unembedded; stale-version excluded from scoring; embedder model
settable + empty rejected; siglip gate updated to current-version concept.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
Lift recall on small/local concepts (glasses, cum, stomach-bulge, xray,
lactation) that the whole-image SigLIP vector washes out: the GPU agent now
embeds figure crops with SigLIP too, stored as kind='concept' regions, and the
suggestion rail scores each image as a BAG (whole-image + every concept crop),
taking each head's MAX over the bag. The whole-image vector is always in the
bag, so this can never score lower than before.
Model-agnostic by construction: the server ANNOUNCES the embedding model
(HF name + version) in the lease, so the agent loads whatever the heads were
trained in and stays in lock-step — a model swap is a server setting + a
re-embed migration, never an agent change.
- agent: model-agnostic CropEmbedder (torch/transformers get_image_features,
fp16 on CUDA, inference-locked); worker branches on job.task — 'ccip' emits
figure(CCIP)+concept(SigLIP) in one pass, 'siglip' emits concept-only so the
back-catalogue backfill never churns figure/CCIP regions; torch cu124 +
transformers in the image.
- server: lease announces embed_model_name/embed_version; score_image is
max-over-bag (version-filtered region embeddings); enqueue_gpu_backfill
'siglip' gates on a missing concept region (drains the back-catalogue,
retries failures, no double-enqueue); daily siglip-backfill beat; UI button;
/api/ccip/overview reports images_with_concept_siglip.
- v1 scope: suggestion rail only — auto-apply stays whole-image (conservative;
heads' thresholds were calibrated on whole-image). Bulk-apply bag = follow-up.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
Graduated heads can now apply their tag without a human — gated so it's safe:
- FIRING GATE: a head fires only when the master switch (head_auto_apply_enabled,
default OFF) is on AND it has >= head_auto_apply_min_positives (default 30)
clean labels. A precise-looking but under-supported low-N head can't spray tags.
- auto_apply_sweep (heads.py): streams every embedded image in chunks, scores
against the eligible heads (numpy, no sklearn), applies each head's tag where
score >= its auto_apply_threshold and the tag isn't already applied/rejected,
with source='head_auto' (distinguishable + reversible). dry_run counts only.
- HeadAutoApplyRun (migration 0059) tracks each sweep / preview; apply_head_tags
task (ml queue) + scheduled_apply_head_tags daily beat (no-op unless enabled)
+ recovery sweep + retention(20).
- API: POST /api/heads/auto-apply {dry_run} (202 / 409 running / 400 disabled),
GET /api/heads/auto-apply (recent runs + per-concept report). Settings
head_auto_apply_enabled + min_positives via /api/ml/settings.
Tests: sweep applies above threshold, dry-run writes nothing, skips under-
supported + ungraduated heads; API disabled/dry-run/conflict guards.
NEXT (slice 2): the observability the operator asked for — per-concept misfire
(auto-applied-then-removed) + under-fire tracking, time-series snapshots, and a
reporting API to tune. Slice 3: the UI (enable, preview, trends).
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
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
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
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
bvandeusen