2b093958a47546937fc0f2b9a5a5d4fd0a792bc6
42
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
  bvandeusenandClaude Opus 5
|
7f1693a40d |
fix: the ML dial offered slots the machine had no cores to feed (4295)
CI and images / lint (push) Successful in 2s
CI and images / frontend-build (push) Successful in 22s
CI and images / extension-version (push) Successful in 3s
CI and images / backend-lint-and-test (push) Successful in 32s
CI and images / integration (push) Successful in 2m21s
CI and images / sign-extension (push) Successful in 3s
CI and images / build-agent (push) Successful in 5s
CI and images / build-web (push) Successful in 1m42s
CI and images / smoke-web (push) Successful in 1m7s
CI and images / promote (push) Skipped
Operator's 2026-09-23 log: embed_image taking 107-246s each, ~49 slots in flight by Little's law, and the daily CCIP sweep dying on its 1800s soft limit in a numpy matmul. The billiard/pool.py frame in that traceback is the soft-timeout signal handler, not a pool fault. Two causes, both mine. 1. `derived_ceiling` computed the ML lane from MEMORY ALONE. Meanwhile `embedder.py` carried `_INTRA_OP_THREADS = 4` beside a comment reading "keep N_replicas x this within the cores allotted to ML" — a constraint stated where nothing could act on it. A large-memory host offered ~49 slots, the operator took what the dial offered, and the lane asked the box for ~200 torch threads. The number moves onto the lane as `threads_per_slot`, the embedder reads it rather than restating it, and the ceiling is now the smaller of the two bounds. They fail differently on purpose: too little memory is honestly zero, because the first task would OOM the container; too few cores is merely slow, so it floors at one rather than making the lane unreachable on a small box. 2. `scheduled_ccip_auto_apply` scored one image per matmul, over every image in the library, on every daily run — ~119k products each too small to pay for its own BLAS setup. `char_maxima` does the same arithmetic in blocks bounded by elements, so its memory stays flat as either axis grows. Batching changes no arithmetic: a character's score for an image is a max over that image's figures AND that character's prototypes, and max does not care how it is grouped. Pinned against the old loop written out longhand, and against itself with the blocking forced to split every row. The UI copy said the ML ceiling came from memory; it says cores or memory, whichever runs out first. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LVjrnpQjRgHdvq95rASoiR |
||
|
bvandeusenandClaude Opus 5
|
ffcd13096a |
feat: one image for every lane, with the model fetch gated on enabling (4296)
CI / lint (push) Successful in 2s
CI / extension-version (push) Successful in 2s
Build images / sign-extension (push) Successful in 3s
Build images / build-agent (push) Successful in 6s
CI / frontend-build (push) Successful in 20s
CI / backend-lint-and-test (push) Failing after 31s
extension / lint (push) Successful in 23s
CI / integration (push) Successful in 2m16s
Build images / build-ml (push) Successful in 3m8s
Build images / build-web (push) Successful in 3m16s
Build images / smoke-web (push) Skipped
Build images / promote (push) Skipped
Milestone 422 step 6. Dockerfile.ml is gone; the main image carries torch,
torchvision, transformers, onnxruntime and opencv, and serves every lane.
WHY IT HAD TO MERGE: step 5 runs every lane in one process tree, so a second
image would mean the `ml` lane could never be enabled from the UI — there
would be no worker in that container to enable. The switch needs something to
switch.
THE MODEL NO LONGER DOWNLOADS AT BOOT. `entrypoint.sh`'s ml-worker role ran
download_models before celery started, so every boot of that role reached
HuggingFace for ~3.5GB — a startup dependency on a third party for a feature
the operator may never use. Rule 164 permits a runtime fetch only for
something "optional and clearly off", so the fetch is now a TASK, enqueued
the moment the lane is ENABLED.
Being a task is what makes it visible: it gets a TaskRun row, so the download
shows in Activity with a duration and a status, and a failure is something an
operator can see and retry rather than a container that quietly never became
useful. Idempotent, so re-enabling a provisioned lane costs one no-op.
Enqueued only when the lane actually came ON (`enabled is True`, not the
resolved value) so re-saving slots does not re-fetch, and only when the
consumer change landed — a task queued onto a queue nothing consumes would
sit pending with no explanation.
`fabledcurator-ml` KEEPS PUBLISHING, from the merged Dockerfile. The
operator's Swarm stack references that name and lives outside this repo;
dropping it would not break their deploy, it would freeze it silently at the
last publish — the exact failure class this milestone keeps finding. Retiring
the NAME is its own task, gated on that stack moving. Same two-phase shape
#406 used for pixiv.
THREE LIVE BREAKAGES from deleting the file, found by grepping for it rather
than assuming the build was the only consumer:
- `docker-compose.override.yml` built the ml service from it (contributor
path would have failed at `docker compose build`).
- `tests/test_artifact_paths.py` pins the ml path set.
- `scripts/artifacts.sh` ML_PATHS named it. A path set naming a deleted file
silently stops contributing to the derived revision — which the reuse check
and the version string both read. That is #3202's recorded shape.
The `--with-ml` flag is gone from the generator and the healthcheck rather
than left defaulting to true. One image carries every lane now, so a flag
that can only be passed one way is a branch pretending to be a choice.
The advisory shipped in
|
||
|
bvandeusenandClaude Opus 4.8
|
666b3a2ec8 |
refactor(ml): DRY pass — shared sweep helpers + table-driven settings (#161)
Consolidate duplication accrued across the ML tagging + settings backend, behavior-preserving (over-DRY guard applied — the three auto-apply sweep BODIES stay separate; only their shared inner helpers are extracted). - _sigmoid / _conflict_scores / _insert_presentation_review (heads.py): the score→prob transform (6 inlined sites), the presentation conflict signal (2 sites), and the ring-loud PresentationReview insert (2 sites, single- sourced so the mode column can't drift on the shared composite PK). - _applied_or_rejected (training_data.py): the per-tag "applied ∪ rejected" skip-set, byte-identical at 3 sweep sites (heads.py x2, tasks/ml.py ccip). - ccip sweep divergence fixes: import ccip._FIGURE_KINDS + training_data._l2norm instead of local copies that silently drift when the canonical changes. - MLSettings.load / .load_sync classmethods (mirror ImportSettings); route all 8 scalar_one singleton reads through them (the session.get None-path stays). - GET serializers for MLSettings + ImportSettings are now table-driven off the same _EDITABLE tuples PATCH writes, so a new field can't be silently absent from GET (the split that historically dropped fields). - AUTO_APPLY_THRESHOLD_MIN/MAX constant single-sources the [0.5,0.999] operating range across the service clamp + the 5 API validators. - test_ml_dry_helpers.py pins _applied_or_rejected + _sigmoid. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01NsmJSQxnNxGgtM5Yz4GAqi |
||
|
bvandeusenandClaude Opus 4.8
|
af0d39ed52 |
feat(wip): soft title tier — sketch/doodle vocab + ring-loud audit (#1474)
Extends WIP title-tagging to lower-precision cues (sketch/doodle/scribble) safely. - wip_title.py: soft matcher (word-anchored; sketchbook/kadoodle don't trip it); WIP_TITLE_SOFT_SOURCE + soft SQL prefilter; apply_wip_image_tags takes a source arg. - training_data._AUTO_SOURCES += 'wip_title_soft' → the soft tier is PROVISIONAL and never trains the wip head (a finished "sketch" can't pollute it). Only the hard tier (wip_title) + manual train. - ImportSettings.wip_soft_title_tagging_enabled (OFF by default, opt-in). Migration 0087. - importer: hard tier wins, soft is the fallback (source wip_title_soft). - backfill: refactored into a shared _backfill_wip_tier; hard always, soft when enabled. - heads.soft_wip_conflict_audit + daily beat: score soft-tagged images against content heads, flag ring-loud ones (PresentationReview mode=process) for the review strip — the operator's "measure if they got falsely tagged" safety. - api settings toggle; ImportFiltersForm soft toggle. - tests: soft matcher pos/neg; soft source not a training positive; audit flags ring-loud + spares quiet. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
bvandeusenandClaude Opus 4.8
|
ad2a5fc5fe |
feat(system-tags): process vs chrome groups + WIP provisional auto-apply (#1464)
Backend for the system-tag behavior refactor (milestone #157). editor screenshot moves from chrome (hidden) to the PROCESS group (shown, like wip); wip+editor gain provisional auto-apply so they stop needing endless manual identification — without a runaway loop. - tag.py: split PRESENTATION_SYSTEM_TAGS → CHROME_SYSTEM_TAGS (banner) + PROCESS_SYSTEM_TAGS (wip, editor screenshot). - heads.py: generalize presentation_auto_apply_sweep → system_tag_auto_apply_sweep (mode chrome|process). Same Guard 1 (skip human/confirmed) + Guard 2 (ring-loud conflict → PresentationReview). process mode uses source 'process_auto' and does NOT hide (hide is a gallery-query effect of group membership). - training_data._AUTO_SOURCES += 'process_auto' → the head never trains on its own auto-applied output; only wip_title/manual train it (the runaway break). - ml_settings: process_auto_apply_enabled (OFF, opt-in) + threshold + conflict threshold. presentation_review.mode ('chrome'|'process'). Migration 0086. - gallery_service: default-hide reads CHROME only (editor now shows); Explore neighbors exclude the whole PROCESS group. - tasks/ml + celery beat: scheduled_process_auto_apply (daily, opt-in); prune covers both modes. - api: ml_admin process_* CRUD+validation; hidden-review returns mode. - tests: rename chrome sweep calls; new test_process_auto_apply (apply, guards, mode flag, no-self-train); gallery test asserts editor now visible. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
bvandeusenandClaude Opus 4.8
|
2bcaa20b22 |
feat(ml): schedule presentation auto-hide sweep + retention (#141 step 6)
scheduled_presentation_auto_apply (daily beat) runs presentation_auto_apply_sweep — idempotent, so an interrupted run just re-runs next cycle (that's the recovery), wall-clock bounded by soft/hard task time limits. prune_presentation_reviews (daily beat) drops RESOLVED review flags older than 30 days (rule 89 retention). Tests run both tasks via a monkeypatched session factory. Milestone 141 complete: the presentation-chrome auto-hide + conflict-flagged review is now live end-to-end. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM |
||
|
bvandeusenandClaude Opus 4.8
|
3006e84cc0 |
feat(ml): soft auto-apply — retract auto-tags now below threshold (milestone 139)
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 |
||
|
bvandeusenandClaude Opus 4.8
|
2cfbb284d5 |
feat(heads): incremental retraining — refit only changed tags (#1317 phase 2, m138)
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 |
||
|
bvandeusenandClaude Opus 4.8
|
a1ed53136e |
feat(ccip): refresh task + beat + retrain hook for character prototypes (#1317, m138 step 3)
- refresh_character_prototypes celery task wraps the incremental builder (sync ml worker); returns skipped / rebuilt=N removed=N. - Beat: every ~15 min (cheap global-gate no-op when idle) + a nightly full=True reconcile as belt-and-suspenders. - train_heads enqueues it on success, so the Retrain button AND the nightly head retrain refresh CCIP on the SAME trigger — unified lifecycle, as asked. The initial (cold) full build loads the whole reference set once in the background, never on a /suggestions request. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM |
||
|
bvandeusenandClaude Fable 5
|
19b962f1a7 |
feat(b3): ml-worker becomes optional — embed-only role, decoupled GPU coordination, cpu-embed switch
The ml-worker's ONLY processing role is now the CPU whole-image embed fallback (tag_and_embed renamed embed_image — Camie tagging was retired #1189 and the name kept implying otherwise; videos were already handled agent-style: frame sampling + mean-pool). Detection/cropping/CCIP stay GPU-agent-only, and their completion is judged per-pipeline: ccip by gpu_job rows, siglip by concept regions at the current model version — never by image_record.siglip_embedding. A CPU embed therefore can NEVER close crop work for the agent (regression test pins this; only the whole-image 'embed' job, the same artifact, is satisfied). Making removal actually safe (operator will drop the container): - GPU-queue coordination (enqueue_gpu_backfill, recover_orphaned_gpu_jobs, reprocess_gpu_jobs) moved verbatim to tasks/gpu_queue.py on the maintenance quick lane — it lived on the 'ml' queue only by module colocation, which made the ml-worker a hard dependency of the whole agent pipeline. - New ml_settings.cpu_embed_enabled (migration 0074, default ON so agent-less installs keep working): OFF stops the four import hooks queueing embed work nothing will consume and no-ops the manual backfill; switch lives on the renamed 'CPU embedding backfill' card. - NB heads training / auto-apply still run on the ml image (sklearn) — a stack that removes the container gives those up too. Deploy note: in-flight messages under the old task names are dropped by the new workers; the 60s orphan sweep + hourly backfill re-fire under the new names immediately. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM |
||
|
bvandeusenandClaude Fable 5
|
eaea4308fc |
chore: retire the tag-eval harness — it proved the heads system, job done (operator-approved)
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 |
||
|
bvandeusenandClaude Fable 5
|
09e2772628 |
fix(gpu-jobs): end the error-tombstone loop — deliberate retry semantics + poison-job guards
The hourly ccip backfill's skip-list lacked 'error' (and the daily
siglip/embed variants re-gated failures on their missing results), so every
permanently-bad file got a fresh doomed job each run — ~24 duplicate error
rows/day per file, the perpetual 'unprocessable' flood. An errored job is now
a TOMBSTONE: no backfill re-enqueues it; retry is deliberate-only via
/retry_errors (an errored back-catalogue needs one button press after a
model swap).
One shared set of dedupe DELETEs (services/ml/gpu_jobs.error_dedupe_statements)
runs before every backfill and inside /retry_errors: error rows made moot by a
later pending/leased/done row go first, then older duplicates (newest reason
survives) — so the error count reads as distinct failing files and a retry
can't fan one file out into duplicate pending jobs. /retry_errors now returns
{requeued, pruned} and the toast shows both.
Poison-loop guards (release and lease-expiry burn no attempts, so a job that
stalls its transfer or crashes the agent every time cycled forever —
operator-observed jobs 99044/125288/131594/143131):
- agent: 3 in-session transient bounces (fetch or submit) → fail with the real
reason instead of another release; strikes never count while stopping, and
clear on submit success. Agent build 2026-07-02.3.
- server: the 60s orphan sweep (statements shared between the beat task and
GpuJobService so they can't drift) converts expired leases with >=5 lease
grants and pending jobs with >=10 to 'error', preserving the last stored
failure reason. Backstops old agent builds.
Tests: tombstone rule across all three backfill variants, moot-row pruning,
poison conversions, and the extended /retry_errors dedupe contract.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM
|
||
|
bvandeusenandClaude Opus 4.8
|
80f8eb4756 |
feat(gpu): re-process trigger to apply new crop detectors to the existing library (#1202)
The siglip/ccip backfills skip images that already have current-version regions, so adding crop detectors only affected NEW images — the back-catalogue would never be re-cropped. Add a reprocess trigger that resets every done/error job of a task back to pending, so the agent re-runs the FULL pipeline (figure detection + CCIP + concept/panel crops) over the whole library under the current detectors. - reprocess_gpu_jobs(task='ccip') task + POST /api/gpu/reprocess. - gpu store reprocess() + GpuAgentCard "Re-process library (re-detect + re-crop)" button with a confirm (it's heavy). - Test: a done job resets to pending (attempts cleared). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa |
||
|
bvandeusenandClaude Opus 4.8
|
485387ff0b |
refactor(ml): retire the Camie tagger + allowlist bulk-apply (#1189)
Heads + CCIP are the tag source and head auto-apply is the earned propagation.
The Camie tagger ran only to feed the allowlist bulk-apply (its ImagePrediction
rows had no other consumer), and the allowlist was a SECOND, un-earned auto-apply
path firing in parallel with heads on every accept — exactly the un-earned spray
the v2 pivot replaced. Retire both.
Behavior change: accepting a suggestion now applies the tag to THAT image only
(source='ml_accepted', a head-training positive) — it no longer allowlists +
fans the tag across the library via Camie. Propagation is heads' earned
auto-apply. (Loses instant cold-start propagation for booru-vocab tags; that was
un-earned and bypassed the precision gate.)
- tag_and_embed is now EMBED-ONLY (no Camie load/infer, no ImagePrediction
writes); backfill enqueues it for images with no embedding.
- Removed: services/ml/tagger.py, apply_allowlist_tags + helpers + daily beat +
every enqueue caller (accept/alias/merge/per-image), api/allowlist.py +
blueprint, ImagePrediction + TagAllowlist models/tables (migration 0067),
AllowlistTable.vue + allowlist store, the accept coverage-projection payload.
- AllowlistService gutted to accept/dismiss/undismiss/reject (the rejection store
the rail still needs); accept returns nothing, API returns {accepted, tag_id}.
- tag merge no longer repoints/triggers the allowlist; _keep_as_alias now keys on
ML-applied image_tag sources (incl. head_auto) instead of the allowlist.
- UI: MLBackfillCard relabelled to embedding-only; accept toast simplified;
MaintenancePanel drops the allowlist tile.
Left for a follow-up hygiene pass (now-inert, harmless): the dead settings
columns (tagger_store_floor, tagger_model_version, suggestion_threshold_*,
video_min_tag_frames), image_record.tagger_model_version, MLThresholdSliders
trim, and the Camie model download in download_models.py.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
|
||
|
bvandeusenandClaude Opus 4.8
|
3d77a38a25 |
refactor(ml): remove the dead per-tag centroid subsystem (#1189)
The v2 pivot replaced per-tag SigLIP centroids with learned heads + CCIP. Centroids were still recomputed (on every tag merge + a daily beat) but NOTHING read them — suggestions come from heads+CCIP and apply_allowlist_tags applies via Camie predictions, not centroids. Pure dead wiring; remove it. Removed: CentroidService, recompute_centroid/recompute_centroids tasks, the daily beat, POST /api/ml/recompute-centroids, the recompute-on-merge trigger, the tag_reference_embedding table + model, the centroid_similarity_threshold + min_reference_images settings (migration 0066), the CentroidRecomputeCard + its store action + MaintenancePanel tile, and the centroid slider in MLThresholdSliders. _keep_as_alias drops its vestigial has-centroid branch (the allowlist branch already covers "could re-emit"); tag merge no longer clears a table that no longer exists. NOT touched (still live, parallel to heads): the Camie tagger, ImagePrediction, and the allowlist bulk-apply — accepting a suggestion still allowlists + applies it across the library. The tag-eval "centroid" baseline metric is unrelated (in-memory) and stays. (image_record.centroid_scores JSON column also remains — separate legacy field, its own micro-cleanup.) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa |
||
|
bvandeusenandClaude Opus 4.8
|
4daa3f2790 |
feat(ml): operator model swap — GPU re-embed + embedder as a setting (#1190)
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
|
||
|
bvandeusenandClaude Opus 4.8
|
c6f38b0dac |
feat(tagging): SigLIP concept crops + max-over-bag scoring (#114)
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 |
||
|
bvandeusenandClaude Opus 4.8
|
b91a230f12 |
feat(ccip): automation + reference quality — keep identity flowing hands-free (#114)
Works through the optional CCIP ideas + the "keep moving even if I forget" ask:
AUTOMATION (no button needed):
- Hourly beat auto-enqueues CCIP backfill — new images get embedded (and errored
ones retried) on their own; the queue never goes idle waiting for a click.
- CCIP auto-apply: a daily sweep tags confident matches (source='ccip_auto') so
identity tags keep flowing. ON by default (opt-out, like head auto-apply);
ml_settings.ccip_auto_apply_enabled + _threshold (0.92, above the suggest cut),
migration 0064. Vectorized (one matmul + reduceat per image), reversible, skips
already-applied/rejected. Switch + threshold in the GPU agent card; GET/PATCH
/api/ml/settings; auto_applied count in /api/ccip/overview.
REFERENCE QUALITY (the over-fire root cause):
- character_references now draws ONLY from single-character images — on a
multi-character image the tag is image-level, so every figure would otherwise
pollute each character's prototypes (a 2-char image tagged 'Velma' made
Daphne's figure a Velma reference). This is the contamination behind residual
over-firing.
- Cached on a cheap signature (char-tag count + ccip-region count/max-id) so the
reference load isn't redone on every modal open.
Tests: multi-character image not used as a reference; auto-apply tags a confident
match as ccip_auto.
NEXT (not done, confirmed): comic-panel cropping + SigLIP concept crops ("spot
interesting content").
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa
|
||
|
bvandeusenandClaude Opus 4.8
|
2cb0427868 |
feat(gpu): fast orphan recovery — graceful release + 60s sweep (#114)
So work an agent orphaned gets picked back up quickly, three layers: - GpuJobService.release(): a graceful agent stop hands its still-leased jobs back to pending instantly (POST /api/gpu/jobs/release), no waiting out the lease. - GpuJobService.recover_orphaned() + recover_orphaned_gpu_jobs Celery task on a 60s beat: resets expired leases (a hard-crashed agent) to pending and keeps the queue counts honest even when nothing is leasing. - Lease TTL 300→180s: still well above any single job (a capped-frame video embed is tens of seconds, and a live worker heartbeats), but a hard crash recovers faster once the sweep fires. Tests: release returns-to-pending (token-scoped), recover_orphaned resets only expired leases, release API round-trip. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa |
||
|
bvandeusenandClaude Opus 4.8
|
558d965a1c |
fix(gpu): count backfill enqueues via RETURNING, not rowcount
result.rowcount is unreliable for INSERT…SELECT (returned -1), failing the idempotency assert. Use .returning(GpuJob.id) and count the rows. (run 1652) Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa |
||
|
bvandeusenandClaude Opus 4.8
|
f247f9247c |
style(gpu): ruff — split as-import, dict(rows) over comprehension
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa |
||
|
bvandeusenandClaude Opus 4.8
|
6cabef07a4 |
feat(gpu): HTTP job API + token auth + backfill — the agent's server side (#114 slice 3b)
The thin HTTP surface over the queue so the desktop agent stays HTTP-only: - Agent endpoints (Authorization: Bearer <token>): POST /api/gpu/jobs/lease (returns jobs + image_url + mime + video frame cadence), /submit (stores regions via RegionService + closes the job; 409 on a stale lease), /heartbeat, /fail. Token validated against AppSetting (mirrors the extension-key pattern, constant-time compare). - Admin (browser): GET/POST /api/gpu/token[/rotate] (generate + show the agent token), GET /api/gpu/status (queue counts), POST /api/gpu/backfill → dispatches enqueue_gpu_backfill. - enqueue_gpu_backfill(task): one INSERT…SELECT enqueues a job per image lacking one for the task (scales to the full library; idempotent). Agent flow: lease over HTTP → fetch pixels via the normal FC image URL → compute on the GPU → submit. Redis/Postgres never exposed. Tests: bearer required (+ wrong-token 401), lease→submit round-trip (region+CCIP vector stored, job done via /status), stale-lease 409, backfill enqueue + idempotency. NEXT: the agent container + control UI, then the CCIP detector/embedder + matcher. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa |
||
|
bvandeusenandClaude Opus 4.8
|
74fef908d2 |
feat(heads): earned auto-apply — sweep mechanism, off by default (#114 auto-apply A)
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
|
||
|
bvandeusenandClaude Opus 4.8
|
77baee49fd |
feat(heads): nightly auto-retrain + inline Retrain button in Explore
Two cadences for keeping heads in sync with your tagging: - PASSIVE: a nightly `scheduled_train_heads` beat (skips if a run is already in flight; creates+commits the run row before dispatching train_heads so the ml worker always finds it). Folds the day's accepts/rejects + newly-eligible concepts into the heads without anyone clicking. - ACTIVE: a "Retrain heads" button in the Explore trail bar — bank the +/- feedback you just gave while walking content, without a trip to Settings. Shared logic in a new useHeadTraining composable (trigger + poll + start/finish toasts), used by the Explore button; reflects an already-running run (incl. the nightly one) on mount. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01Ttrj5P7upUTueSfoJcxEqa |
||
|
bvandeusenandClaude Opus 4.8
|
22c3b54746 |
feat(heads): production per-concept heads — train + score backend (#114 A)
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 |
||
|
bvandeusenandClaude Opus 4.8
|
6e3c5f697f |
feat(ml): tag-eval backend — head-vs-centroid learning-curve eval (persisted)
Slice 1 of milestone #114 (tagging v2). Proves the frozen-embedding + trained- head spine on the operator's own data, reusing the SigLIP embeddings already stored on image_record — no re-embedding, no GPU. Per concept: train a logistic-regression HEAD (positives + negatives = explicit rejections + sampled unlabeled) vs the old single-CENTROID baseline; report cross-validated precision/recall/AP for both, a LEARNING CURVE (AP/F1 as tagged positives grow 10→30→100→300), and example image ids (head-would-suggest / head-doubts-positive) to eyeball. Persisted so the report SURVIVES navigation (operator-flagged): the run + full report live in a new tag_eval_run row (mirrors library_audit_run); the admin card will rehydrate from GET on mount, not transient state. - models.TagEvalRun + migration 0056; runs on the ml queue (only worker with numpy/sklearn) — numpy/sklearn lazy-imported so the API can still enqueue. - services/ml/tag_eval (compute + start helper, one-running guard), tasks.ml .tag_eval_run, api/tag-eval (POST create, GET history light / detail w/ report). - recover_stalled_tag_eval_runs sweep + retention (keep last 20) + 5-min beat (rule 89). scikit-learn added to requirements-ml. - tests: param normalization + the rehydrate read-path + create/conflict. Frontend admin card (trigger + render persisted report) follows next. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
bvandeusenandClaude Opus 4.8
|
51201b459e |
fix(ml): per-task async engine for recompute_centroid (#881)
recompute_centroid + recompute_centroids were the only tasks still using the process-wide singleton extensions.get_session() under asyncio.run(). The async engine's asyncpg pool is bound to the loop it was created on; each Celery task runs a fresh asyncio.run() loop, so after the first invocation the cached engine handed loop-A connections to loop B and raised "Future attached to a different loop" — every recompute after the first in a worker process failed (~35ms, fails on first DB await). Convert both to the established per-task async_session_factory() pattern (NullPool engine created + disposed inside the task's own loop), matching scan/download/admin tasks. No get_session usages remain in tasks/. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
bvandeusenandClaude Opus 4.8
|
369e3de684 |
feat(ml): cadence-based video frame sampling + min-frame tag aggregation (#747)
Video tag noise root cause: frames were a FIXED count (6) max-pooled — a tag firing on one frame survived at peak confidence, and a fixed count under-samples long multi-scene videos so real scene-local tags looked like noise. Redesign (operator-steered): - Sample at a fixed CADENCE — one frame every `video_frame_interval_seconds` (default 4) across the 5–95% window — so a tag's frame-presence reflects real screen time independent of video length. Capped at `video_max_frames` (default 64): a long video stretches the spacing instead of exploding into hundreds of inferences, bounding per-video cost on the single ml-worker (per-frame ffmpeg timeout also cut 60s→30s). - Aggregate with `_aggregate_video_predictions`: keep a tag only if it appears in >= `video_min_tag_frames` sampled frames (≈ that many × interval seconds on screen — duration-independent noise rejection), with confidence = MEAN over the frames it appears in (not max). Clamps the threshold to the sample count so a 1–2-frame short video still tags. - All three knobs are DB-backed ml_settings (migration 0053), patchable via /api/ml/settings + sliders in the ML settings card — replaces the VIDEO_ML_FRAMES env var (product-not-project). Tests: aggregation drops one-frame noise + means corroborated tags + clamps on short videos; settings round-trip + min>max validation. Replaced the _maxpool_predictions unit test. NOTE: this is the QUALITY half of #747. The perf half — the ml-worker runs CPU-only — is GPU enablement, tracked separately in #872. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> |
||
|
bvandeusenandClaude Opus 4.8
|
3610ba495f |
feat(ml): drop image_record.tagger_predictions — image_prediction is sole store (#768 step 3)
Read cutover verified in prod (suggestions + allowlist read image_prediction; backfill complete at 908k rows / 51k images). Removes the old JSON column and everything that fed it: - ImageRecord.tagger_predictions column removed; migration 0046 DROPs it. tagger_model_version kept as the "tagged / current?" signal the backfill sweep reads (needs-tagging check switched to tagger_model_version IS NULL). - tag_and_embed no longer dual-writes the JSON — image_prediction is the only write path. - importer re-import reset drops the JSON line (image_prediction rows are already deleted on re-import). - Retired the one-time #768 backfill task + the #764 prune task, their admin endpoints, and their Maintenance cards (Backfill/PrunePredictionsCard). - Tests seed/assert via image_prediction; stale column refs removed. Disk reclaim is NOT automatic: DROP COLUMN is a catalog change. Run `VACUUM FULL image_record` off-hours afterward to return the ~100 GB to the OS so DB backups go small (#739). image_prediction (~90 MB) stays in pg_dump — it's the source of truth now. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
bvandeusenandClaude Opus 4.8
|
22cdf0f334 |
feat(ml): read suggestions + allowlist from image_prediction (#768 step 2)
Switch every prediction READER off the JSON column onto the normalized
image_prediction table. Parity by construction: each reader loads the same
{raw_name: {category, confidence}} dict it consumed before (via small
_load_predictions helpers), so all downstream threshold/alias/merge/consensus
logic is byte-identical — only the data source changed.
- suggestions.SuggestionService.for_image (and for_selection via it)
- ml.apply_allowlist_tags (iterates images that have prediction rows)
- importer re-import reset deletes the image's prediction rows
The tagger_predictions JSON column is still dual-written (step 1) so it stays
valid during transition; the backfill task's NULL check still works. Removing
the JSON write + DROP column + retiring the #764 prune is the cleanup
follow-up (needs a quiesced-worker window for the DROP lock).
Tests: shared tests/_prediction_helpers.seed_predictions seeds the table;
read-path tests (suggestions, bulk consensus, allowlist apply, API) seed there
instead of ImageRecord.tagger_predictions.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
|
||
|
bvandeusenandClaude Opus 4.8
|
79089b50b0 |
feat(ml): image_prediction table + backfill + dual-write (#768 step 1)
Normalize tagger predictions out of the image_record.tagger_predictions JSON blob into a queryable per-prediction table. Step 1 of the cutover (expand): additive + low-risk — reads still use the JSON, this just adds the table and keeps it populated. - ImagePrediction(image_record_id, raw_name, category, score) — stores the RAW tagger vocab name (not tag_id) so read-time alias→canonical resolution is unchanged. Indexed for per-image reads + by (raw_name, score). - Migration 0045: create table + set-based backfill from the JSON via json_each (fast post-#764-prune). The old column stays (vestigial) and is dropped in a later follow-up — DROP needs an ACCESS EXCLUSIVE lock on the hot image_record table, so it waits for a quiesced-worker window. - tag_and_embed dual-writes the rows (delete-then-insert, idempotent); tagger_store_floor already applied in infer(). Next: switch suggestion + allowlist reads to the table, then drop the JSON write. Plan-task #768. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
bvandeusenandClaude Opus 4.8
|
3f92669f12 |
feat(ml): DB-backed tagger_store_floor (default 0.70), the ingest confidence floor
Promotes the prediction store-floor from the TAGGER_STORE_FLOOR env (default 0.05) to a DB-backed, Settings-UI-tunable ml_settings column (default 0.70). Storing every tag down to 0.05 from a ~10k-tag tagger is what grew image_record's TOAST to ~100 GB; the suggestion path already filters at 0.70 and the centroid/learned path covers lower-confidence preferred tags, so the sub-0.70 tail is redundant. Foundation for plan-task #764 (backfill + reclaim land next; this only changes the write gate for NEW imports). - ml_settings.tagger_store_floor (migration 0044, default 0.70) - tagger.Tagger.infer(store_floor=...); ml task passes settings.tagger_store_floor - ML admin GET/PATCH expose it; PATCH rejects a category suggestion threshold below the floor (nothing below the floor is stored, so the gap surfaces nothing) — server backstop for the UI slider clamp - Settings → ML: store-floor slider + caption; category sliders min-bound to it Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
bvandeusen
|
f2fbe2ae6e |
tweak(ml): default video frame samples 10 to 6
Operator: 10-frame max-pooled tagging on video produces a lot of noisy tags, and the sampling burns time/GPU. Drop the VIDEO_ML_FRAMES default to 6 (still env- overridable). Fewer frames = less per-frame noise into the max-pool and a smaller frame-sampling budget. Quality/perf of the whole video path is being reviewed separately. |
||
|
bvandeusenandClaude Opus 4.8
|
b1778ca9f2 |
obs(ml): tag_and_embed logs file + phase + timing; failures name them
The task logged nothing and SoftTimeLimitExceeded stringifies to empty, so a timeout surfaced as a bare 'SoftTimeLimitExceeded()' with no clue which file or why (operator-flagged 2026-06-08). - Log start (id/path/mime/bytes/video?), per-phase timing (load_models, video probe/sample/infer, tag, embed, persist), and a success summary. - Track a + file ; on SoftTimeLimitExceeded log it and re-raise SoftTimeLimitExceeded WITH that context (keeps the 'timeout' task_run status but gives the activity a real error_message: which file, which phase, elapsed). - On other exceptions, log context then re-raise the ORIGINAL (preserves autoretry for OSError/DBAPIError/OperationalError). Now a stuck run names the culprit — most likely a slow video (frame sampling is up to 10x60s ffmpeg) or a huge image; the phase log will say which. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
bvandeusen
|
e30f50e6fe |
fix(audit-g3): lifecycle batch — recovery sweeps, retention, timeouts
Plugs the FC long-running-entity discipline gaps the 2026-06-02 audit flagged: every entity that can get stuck now has recovery + retention + timeout, and the long-runners no longer collide with the FC-3i sweep. Recovery sweeps (every 5 min): - recover_stalled_backup_runs — flips BackupRun stuck in running/restoring past 7h (covers the 6.5h images-backup hard limit) to error. prune_backups docstring corrected — the FC-3i TaskRun sweep never touched BackupRun rows. - recover_stalled_library_audit_runs — flips LibraryAuditRun stuck past 135 min (10-min buffer above scan_library_for_rule's 2h5m hard limit) to error. Previously a SIGKILL'd row blocked all future audits until manual DB surgery. - recover_stalled_import_batches — finalizes ImportBatch rows stuck running >2h whose child tasks are all terminal (orphan case where the orchestrator crashed before the closing UPDATE). Uses the same EXISTS predicate /api/system/stats already had. Retention (daily): - prune_library_audit_runs — 30-day window. Audit rows carry matched_ids JSONB blobs that can hold tens of thousands of ids. - prune_import_batches — 30-day window. Cascades to ImportTask via the model relationship. time_limits on five long-runners that previously had none (the audit's headline finding — every one of these collided with the recover_stalled_task_runs 5-min default and could be marked 'error' mid-flight): - scan_directory: 60m soft / 70m hard - verify_integrity: 60m / 70m - backfill_phash: 30m / 35m - apply_allowlist_tags: 30m / 35m - recompute_centroids: 30m / 35m QUEUE_STUCK_THRESHOLD_MINUTES now covers maintenance (75) and scan (75) — above the longest task on each — with per-task overrides for the outliers (backup_images_task 420, restore_images_task 420, scan_library_for_rule 130). start_audit_run guard is now age-aware: a 'running' row older than the audit hard limit doesn't block a new run (the sweep will catch it within 5 min). Previously a SIGKILL'd row blocked forever. /api/import/status now uses the same EXISTS predicate /api/system/stats does, so the two endpoints no longer disagree on the active-batch question. DownloadEvent.started_at resets on pending→running so a freshly- promoted event from a busy queue isn't measured against its original enqueue time (was racing recover_stalled_download_events on heavy-queue days). |
||
|
bvandeusen
|
e3cdd0f92b |
feat(import-resilience L3): subprocess-isolated probes for video + archive
Layer 3 — prevent the hard worker crash rather than just recovering from it. The realistic process-crash vectors (operator's observed slow/heavy tasks) are video decode and archive extraction; images decode in-process and Pillow raises-and-skips cleanly, and a subprocess per image would wreck deep-scan throughput, so images are intentionally not probed. New backend/app/utils/safe_probe.py (leaf module, lazy heavy imports so the spawned child stays light): - probe_video(path): validates the container + first video stream via ffprobe (a separate binary — a decoder crash kills only ffprobe, not the worker). Returns width/height, which the importer didn't capture for videos before. crashed=True only on ffprobe timeout. - probe_archive(path): an uncompressed-size bomb guard (MAX_ARCHIVE_UNCOMPRESSED_BYTES = 4 GiB) plus the format integrity test (zipfile.testzip / rarfile.testrar / py7zr.test) run in a spawned child process. A decompression-bomb OOM or native-lib segfault on a malformed archive shows up as a non-zero child exit code → crashed=True, never a dead worker. ProbeResult.crashed distinguishes a HARD failure (subprocess killed / timed out — the poison-pill signature → caller returns terminal 'failed') from a CLEAN rejection (corrupt-but-handled, bomb cap, integrity mismatch → caller's choice of skipped/attached). Wired: - importer._import_media video branch: probe_video before the pipeline; crash → failed, clean reject → invalid_image skip, ok → capture dims. - importer._import_archive: probe_archive before extract_archive; crash → failed, clean reject → still preserve the archive as a PostAttachment (matches extract_archive's fail-soft contract). - ml.tag_and_embed video branch: probe_video before sampling 10 frames, so a corrupt video is rejected (status='bad_video') instead of crashing the ml-worker on frame decode. Tests (test_safe_probe.py): valid/corrupt zip via probe_archive, direct _inspect_archive size+integrity, in-process _archive_probe_target bomb guard (monkeypatch can't reach a spawned child, so the target is called directly), and a non-video → ok=False that's robust to ffprobe presence in CI. |
||
|
bvandeusen
|
407de18ff6 |
fix(ml): video branch needs longer time limits; recovery sweep is now per-queue
Operator-flagged 2026-05-28: tag_and_embed on image 6288 (an mp4) was
marked failed by recover_stalled_task_runs at the 5-min sweep tick
while still legitimately running. The error_type='RecoverySweep' /
"no completion signal received within 5 min" message was misleading
— the worker was busy, not stuck.
Root cause is two interacting limits, both undersized for video work:
tag_and_embed: soft_time_limit=300, time_limit=420
(sized for the image branch, ≈2 GPU ops)
recovery sweep: STUCK_THRESHOLD_MINUTES = 5 across all queues
The video branch samples 10 frames via ffmpeg, then runs tagger +
embedder on EACH frame — ~20 GPU ops vs 2 for an image. A loaded
ml-worker can take 5-10 min on a long video, which trips both
limits well before the task naturally finishes.
**Two-part fix**
1. `tag_and_embed` time limits bumped to soft=900 (15 min) / time=1200
(20 min). Sized for the video path's worst case; image runs return
in seconds and don't care.
2. New `QUEUE_STUCK_THRESHOLD_MINUTES` override dict in maintenance.py.
Queues with legitimately-long-running tasks (currently just `ml` at
25 min — 5-min buffer past the new hard kill) get their own
threshold; queues not in the dict use the default 5 min. The sweep
now issues one UPDATE per distinct threshold value, with
`queue.notin_(override_queues)` on the default pass so each row is
touched at most once.
Tests:
- _make_task_run helper accepts `queue=` (defaults to "default") so
existing tests use the default-threshold path.
- New test `test_recover_stalled_task_runs_ml_queue_uses_longer_threshold`
pins both directions: a 10-min-old ml row survives (fresh by 25-min
override), a 30-min-old ml row gets flagged.
After deploy, operator's mp4 ML jobs run to completion without
spurious RecoverySweep failures.
|
||
|
bvandeusenandClaude Opus 4.7
|
be0f472894 |
fix(workers): worker-level recovery — autoretry on transient errors + tightened sweep (5min) + import_media_file body-wrap so no path leaves rows stuck in 'processing'
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
bvandeusenandClaude Opus 4.7
|
7d8b9c3d90 |
fix(tasks): share one sync engine per worker process to stop connection-pool leak
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
bvandeusen
|
f7f75fcac6 | refactor(fc2c-i): sweep blueprints + ml tasks onto shared get_session (covers tasks/ml.py, a survey gap) | ||
|
bvandeusenandClaude Opus 4.7
|
3e6cc8fffa |
feat(fc2b): add allowlist-apply + centroid recompute tasks + beat
apply_allowlist_tags: 4 modes (tag-only / image-only / both / full sweep), matches a tag to a prediction either by direct name or via alias (name, category) resolution, gates on per-tag min_confidence, skips applied/rejected, applies source='ml_auto'. recompute_centroid / recompute_centroids: async-bridged calls into CentroidService, delta-gated. Beat: daily backfill, daily centroid recompute, daily allowlist sweep. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |
||
|
bvandeusenandClaude Opus 4.7
|
ac7e0d13bc |
feat(fc2b): add tag_and_embed + backfill Celery tasks
tag_and_embed: Camie + SigLIP on one image (video → 10-frame sample, max-pool tags, mean-pool embeddings), stores predictions/embedding with model versions, then enqueues per-image allowlist apply. backfill: keyset-paginated discovery of images missing predictions/embeddings for the current model versions (restart-safe). apply_allowlist_tags stub included so .delay() resolves between commits (filled in Task 9). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> |