Privacy mode left the AI blind twice over: the whole prompt was a token, so
it could not help with light, lens or style, and model and LoRA file names
still went out as written.
- The prompt box has a first field, the gist: the picture in words the user
writes for the AI to read. seal_answer hands it on as written beside the
tokens of the private prompts; either alone can be handed in.
- ai_sealed_models.py: while the Gates window's "Model names in a private
task" is on (the default), each model of the library is one token ([M1],
sealed as its model_id) however an answer writes it: model_id, loader
name, file name in a text, card name. A model's own entry drops name,
file, folder, links and hash and keeps type, base model, the author's
settings and the user's note. expand writes a model token back as the
model_id, as the loader's name among a node's values, as the card's name
inside the AI's words. The task's menu lists what each token stands for.
- The model editor has "Note for the AI" (ai_note, note_for_ai in the
tools, searched by search_models): what a model is for, in words the AI
may read.
- A combo's name is sealed too: unless renamed it is made of its model's
name and the start of its prompt.
- The privacy skill says how to write around a gist and how to pick and
pass on model tokens.
Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
The name big and its Civitai version split off under it in small grey; one small
accent line of type, size, base and the Civitai link (the Size/Base labels were
English in the Chinese window); Add node the one filled button, the rest plain
words. Trigger words, the author's settings, the files it needs, its versions and
its file are one list of rows parted by thin lines; its author's text starts
folded. Size and space carry it, not boxes.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From a Bilibili comment (buttons small and in five places, the file name twice, a title bar
of little use), layout B chosen by the user from three mockups:
- The title bar goes. The head (new model_detail_head.js) tops the right column: a crumb
back (Models / LoRA, or where history leads; still .anomalous-detail-back, so Esc presses
it), the name, the source line with the source links, and one action row: Add node (the
one accent button), Edit, Folder, Outputs, and ... with Copy path, Copy file name, Delete.
- Delete asks in AMB's dialog instead of window.confirm, and is no longer beside Add node.
- model_location.js: one path line with Copy; Show in folder is exported for Folder.
- action_menu.js: the small menu the gallery card's right-click had, shared with the ...
- Narrow (no cover column), a 64 px cover sits beside the name.
- Gone: the jump-to-bottom button, the full-width Outputs button, the location card's file
name row, and their locale keys (back, backToPrev, detailJumpToBottom,
detailPhysicalFilename, detailFullPath).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The editor is rebuilt (it was inline styles everywhere): the cover large
with its choices under it (the current one, Civitai's own when the user
replaced it, the newest pictures, upload, the whole gallery), Name, Source
link and Notes with a word each, Reset / Cancel / Save at the foot. Nothing
is written before Save; fields left as they were are not sent. The source
link (asked for in the "not found" list's hint, but nowhere to type it) is
kept in the user layer; update_metadata refuses one that is no http(s)
address. GET /anomalous/model_covers tells the editor Civitai's kept cover.
A model Civitai does not know: its card reads "推断 <base>", its details
open with a note on what was read from the file and a button to add a name
and link (instead of the English placeholder description), and the scan
page says an online scan infers what Civitai does not find.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- The scan summary marks new models whose safetensors header reads but names no drawing model
kind (a voice model such as F5-TTS) as not_drawing; the scan page asks: don't scan them,
scan them, or see each. The choice lives in <model>.anomalous.json ("scan": "skip" / "scan",
model_identity.scan_choice), saved by POST /anomalous/scan_choice (api/scan_choice.py, this
computer only, at most 2000 models, only readable .safetensors layers).
- "skip": a scan of a whole folder leaves the model out (picked by hand it is still scanned),
the summary counts it apart (excluded) with its own list to change it back, the card and the
details say "不扫描"; the details have the same button.
- The unmatched count warns only for damaged files or lookups still to do; not-found rows say
the fingerprint is kept for repairing workflows.
- model_kind.inspect_file now gives format None when the header cannot be read, as its text said.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A model Civitai has no record of now has its safetensors header checked (model_identity.
safetensors_damage: too short, header longer than the file, not JSON, or a tensor ending past
the file's end; only the header is read). Such files get the unmatched reason "damaged": a red
badge on the card, a line in the details, a warning on the scan page (the summary counts them)
and first place in the unmatched list, with advice to download the model again.
Tests: header cases, a scan telling a damaged file from a whole one; the scan report fixtures
are whole safetensors files now.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The scan page now says which models are unmatched or not scanned yet (type, folder,
why Civitai had nothing) and what each scan did, model by model; rows open the model,
scan it, look it up again or search Civitai. The progress box shows the counts and,
when floating, a way to the result. The activity log records a scan when it ends with
its result, and model edits (from -> to) and deletions (files moved) in detail.
- scraper.py reports one JSON line per changed model (--report-file); a failing model
no longer ends the scan. Unmatched info keeps why (not_found / network / offline);
online scans look network/offline ones up again. After two models in a row without
an answer the rest of the scan infers from the files (--civitai-down for the next
folders) instead of waiting out every timeout.
- civitai_client.py: the network side moved out of scraper.py; tells a 404 from
Civitai being unreachable (CivitaiUnreachable).
- api/scan_report.py: ScanJob turns a scan's reports into one result, kept as the last
scan (/anomalous/last_scan) and logged; /anomalous/scan_model opens a listed model.
- /anomalous/scan_all takes picked or listed models as `targets`, so one scan has one
result; scan_summary lists unmatched and new models with their reason.
- Activity middleware takes details a handler attaches (request[ACTIVITY_DETAIL]).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Cards look as before for models matched on Civitai. Only the exceptions are
marked: a base model inferred from the file shows "≈ <base>" with a dashed
outline, and a .safetensors model not scanned yet says so; both explain
themselves in a tooltip (model_source.js). The detail header's line adds
the source and the fields the user edited; the green title that meant
"renamed" gives way to it (ui_detail.js 755 -> 752 lines).
Fix: the previous commit's locales.js had raw line breaks inside the
"fetch again" confirmation strings, so the plugin did not load. Neither
`node --check` (it passes such .js files on Node 24) nor the structure
check noticed. check_structure.mjs now compiles every web file as the ES
module the browser loads and fails on a parse error; AGENTS.md says so.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
