Follow-up to PR #21:
- The header shows All / Pictures / Videos beside the search (only once the output folder has
a video) instead of twelve chips; the formats move to Settings -> Gallery, stored as hidden
so a format added later shows.
- GET /anomalous/gallery_images lists pictures only unless media= says otherwise, so the recipe
cover picker and the MCP image search are unchanged; hide= drops formats (jpg covers .jpeg);
has_videos tells the gallery whether to offer the switch. .avi is left out (Chrome cannot
play it), .avif is a picture format in the filter too.
- The viewer stops the video however it closes (Esc included).
- Video cards have no View parameters, star or right-click menu, and the workbench steps
through pictures only.
- 图库, not 画廊; the 1.59 CHANGELOG entry credits cocorang and wkdtjs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From cocorang and wkdtjs. The PR's own "v1.58.2" CHANGELOG section is left out (1.58.2 shipped
other changes); the 1.59 entry and the follow-up fixes come in the next commit.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Windows keeps a background program (ComfyUI) from raising a window, so the
folder opened behind the browser and was easy to miss. After starting
Explorer, the route waits up to 3 s for its window (a new one, or the open
one Explorer reused, matched by the folder's name in the title) and raises
it, borrowing the foreground window's input queue for the moment.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From a Bilibili comment (2026-10-13):
- Esc closes the top layer: a dialog or menu (the plugin's alert and confirm
now close on Esc, as OK / Cancel), else the Workflows / Combos workspace,
else the browser. One capture listener decides before the layers act, so a
dialog closing on the same Esc still counts as above. The shortcut and the
Extensions entry toggle the browser.
- A model's file card has Show in folder: POST /anomalous/open_model_folder
(api/model_folder.py) takes type, folder index, subfolder and file name,
never a path, and opens Explorer / Finder with the file selected; a POST,
so local_guard keeps it to this computer. The card moves out of
ui_detail.js into model_location.js.
- A gallery card's right-click menu (gallery_card_menu.js): Insert as a Load
Image node reads the output file in place ("name.png [output]"), and View
Parameters.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
MCP now uses local_guard.is_local (one local check). A backup upload
request that is no upload answers 400 instead of 500. tests/test_local_guard.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
With ComfyUI started with --listen, other devices could use most of AMB's
actions: delete and rename models, save and delete workflows and prompts,
start downloads and scans, export a backup of all data, translate with the
user's key, change settings, switch the plugin version. A probe of all
routes as a LAN device found 9 of 112 refusing.
api/local_guard.py is one middleware in front of every /anomalous/ route:
anything but GET answers only this computer unless it is a read sent as POST
(OPEN_POSTS); a GET is open unless it is more than a read (LOCAL_GETS:
backup file, GitHub releases, local folders). Local = loopback peer, no
proxy headers, loopback Host (DNS rebinding is refused too). Refusals are
403 local_only with a bilingual message; GET /anomalous/access lets the page
show a "view only" chip (remote_view.js). AGENTS.md rule 4 now names it.
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 card opens on two rows of the models' covers, newest first, with an
empty dashed frame for each model not scanned yet (they pulse while a scan
runs): what a scan does, in a picture. The ring, which said the same as the
line under it and the state bar, is gone; narrow, nothing sits alone above
the card any more. The scan summary carries up to 48 covers of scanned models
(components left out) for it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"Pick models to scan" sits beside the scan button; the picks are named
under it and the button scans them, "clear" goes back to everything, so
the all/picked switch is gone. Under the button the page says what this
scan will do, each line with how many of its models are components.
The settings card (ui_scan_settings.js, holding the scan options and the
Civitai key prompt) unfolds in place instead of opening its own page.
The summary counts and lists models in component folders (VAE, text
encoders, CLIP, CLIP Vision, upscalers) apart. The counts at the top and
the not found / not scanned lists leave them out; a card and a list of
their own say that many are not on Civitai and that this is no fault.
The not found list looks up again just the models it shows.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"All models" now lists, from the scan summary, how many models a scan
looks up, keeps, leaves for "look up again" and leaves out, following
the offline and fetch-again switches. "Only ones I pick" names the picks
with their size and says when found ones would only be read again.
The picker (ui_scan_picker.js, GET /anomalous/scan_pickable) lists the
.safetensors files a scan reads with the scan page's states, folder,
base model and size, as a list or covers, narrowed by folder, state,
search and picked-only; "pick these" picks what is shown, shift-click a
run. Picks go to the scan as targets. The old inline-styled selector and
its batch_select route are gone; setWidgetValuePath keeps its own file.
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>
A record inferred from the file alone names model and version after the file. With renaming on, the scan renamed it to name_name, and every later scan doubled it again; the details showed name - name. Such records are no longer renamed (physically or virtually, an earlier doubled virtual name is dropped), and a model and version of one name read once.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Same fixes as feature/next 99576e6, brought into v1.58.0 (the user fixes the
released line directly while it has few users):
- Current node's model picker repaints the chosen card in place instead of
redrawing the grid, which scrolled back to the top.
- The classic combo editor no longer saves when its bilingual tags are shown nor
once per translated tag; one save follows the last translation.
- A long activity before/after pair is cut around its first difference.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Current node's model picker redrew the whole grid to mark the chosen card, so
choosing one further down scrolled back to the top. The cards are repainted in
place (paintCard) instead.
- The classic combo editor saved when its bilingual tags were shown and again for
each tag's translation as it arrived: a long prompt wrote the combo dozens of
times in a second (34 note_save entries in one user's log). Rendering no longer
saves and the translations share one save half a second after the last. Its
prompt placeholder moves into locales.js (no inline language branch).
- Activity values are capped at 400 characters from the start, so an edit late in
a long prompt logged identical before and after. A long before/after pair is now
cut around its first difference (test included).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
PUT /anomalous/import/upload and POST /anomalous/placement/move wrote
into the model folders for any caller, while place and identify already
answered only the computer ComfyUI runs on. With ComfyUI started with
--listen, another device could upload model files or move models
between folders. Both now check mcp_server._is_local first and answer
403 not_local, which the import and Tidy screens already show.
Tests drive both routes through a proxy header and check nothing was
written or moved; they fail without the check. Full suite: structure
check, every tests/*.mjs and 234 Python tests pass.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018P2T2R7TFbJsc3C9maCD8B
Brings stage 1 into stage 2: the gallery drag fix and the change that
follows Anomalous_TTS interface 13 (no server path picker, no storage
change or move, folders shown with the node's settings file).
Conflicts: the picker CSS, the storage-change activity label and its
locale keys are dropped; stage 2's model download and backup entries stay.
tests/tts_setup_api.mjs now checks the pretrained download route instead
of the removed storage and library routes, and that no export sends a
path on the computer.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018P2T2R7TFbJsc3C9maCD8B
Anomalous_TTS no longer takes a folder or file path on this computer from
a request (ComfyUI-Manager review of the node): the storage place, other
character folders and pretrained sources are set only in its settings
file, and imported files are always uploaded.
- GPT-SoVITS settings shows the storage place, other places and package
sources without change, move or remove buttons, and names the node's
settings file (status.settings_file) with a copy button and how to edit it.
- The import window drops "from this computer": no server path picker
(ui_tts_path_picker.js is gone), no local folder scan or local clip
preview; a very large upload is confirmed instead.
- tts_setup_api.js loses the removed routes; formatSize moves there.
- The storage-change activity entry, unused locale keys and picker CSS go.
Verified: tools/check_structure.mjs; tts_setup_api in Node with fetch
stubbed; the settings card, batch hero, add menu, file sources and player
rendered with jsdom and stubbed ComfyUI scripts. Not run in ComfyUI.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_018P2T2R7TFbJsc3C9maCD8B
- The models page has tabs: All models, Tidy (with its count) and Sources;
the type bar keeps the type chips and Import.
- Base model chips under the type chips (All, Illustrious, SDXL, Unknown...),
one per family the listed models have (model_bases.js; SDXL 1.0 = SDXL);
models not scanned are listed by their header's guess (metadata base_guess).
- Tidy is cards with the model's cover and name in two steps: models in a
folder whose loader cannot read them (from -> to, one plain reason, Move
there, Change place), and identical files side by side with the copy to
keep marked (the one in the right folder; click another to change) and one
button for the extra copies. Models that load anyway and extra copies of a
well-placed file are not in step 1. Same-size files up to 256 MB are
compared at once; larger ones on Compare.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The models page's Tidy chip (with a count) reads every model's header
(model_kind) and lists files whose type does not match their folder - such
as an Anima/Flux/Wan diffusion model in checkpoints, which Civitai labels
"Checkpoint" - with why it matters, where it belongs (same subfolder, same
drive) and Move there, taking its cover, info and notes along; never over a
file. A whole checkpoint in diffusion models is marked as loading anyway.
Identical files are grouped by SHA-256 (scan hashes; same-size unscanned
files on Compare); each copy can go to the Recycle Bin. Moves are logged
(model_move). Also: opening the Tidy or Sources view stops cards of an
earlier load from being drawn into it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Models page: "+ Import" chip and model files dropped on the grid open an import
window. model_kind.py tells a file's type (LoRA, checkpoint, VAE, text encoder,
diffusion model, ControlNet, embedding, CLIP Vision, upscaler) and base model from
its safetensors / GGUF header only; .ckpt/.pt are never opened. api/model_import.py
finds the dropped file in Downloads/Desktop (name, size, time) and moves it, or
takes an upload; checks it against Civitai and the scanned models; never replaces
a file (" (2)"). New files are scanned after.
- Model cards show the Civitai version name (metadata version_name).
- Settings page in tabs (Look, Models, Workflows, Prompts, Backup, Help); the
download folder is a choice of ready-made folders or typed by hand; default is now
by base model ({base}).
- The scanner's offline base model uses model_kind (LoRAs, Qwen, Wan, Chroma...).
- AD-019: no Civitai browser inside the plugin.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Settings -> Translation -> DeepL key saves the user's own DeepL API key;
translation then asks DeepL first, else Google's free endpoint, else
MyMemory. Saving a key translates one sentence and says whether it works or
why not (a refused key, a used-up month, busy). Only the key's tag changes,
so the page keeps its scroll place. The key stays on this computer: backups
leave it out like the Civitai key.
DeepL stopped taking the key as an auth_key parameter in 2025, so a key put
in config.json by hand no longer worked. It now goes in the Authorization
header with a JSON body; targets are ZH-HANS and EN-US. When DeepL fails,
the answer carries deepl_error beside the other provider's translation.
Checked live: a made-up key is refused by DeepL's server and the dialog
says so; removing it switches back to Google.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The import dialog said "with 1 picture" for a package with a cover and one
model thumbnail: the cover lives inside recipe.json as a small image, not as
an asset file. Inspect now returns has_cover and model_pictures, and the
dialog says "a cover, N model thumbnails".
The save dialog's cover preview stretched the chosen image to the dialog's
width; it now keeps its proportions (object-fit: contain).
Checked live: a recipe with an output-image cover and a LoRA thumbnail,
exported and imported with the output image moved away, shows both on the
new card and its detail.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
By the user's decision, recipe packages are open again: the card's
export button and the detail's More menu make a .zip named after the
recipe (workflow, notes, tags, parameters, cover, model thumbnails;
versions only when ticked). Dropping one into the Workflows page's
share and import dialog inspects it and keeps it as a new recipe card,
optionally opened on the canvas.
An import never replaces a recipe any more: the "replace" path, which
erased the old recipe for good, is gone; a taken name gets " (2)".
Assets and versions move in before the recipe file, and a failure
removes only this import's new folders. The release gates and their
503 answers are removed. Tests: new card and renaming, nothing left
after a failed import, tampered and escaping packages refused.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A backup now keeps each model's scan file (.info, small; on by default)
so names, trigger words and base models survive Civitai removing a
model, and on request Civitai's covers (stored once as the civitai_bak
copy; they can be hundreds of MB). Putting back writes a scan file only
where the model has none (replaced only with "replace") and Civitai's
cover only where it has no cover, with its civitai_bak copy so it stays
Civitai's and a later user cover still wins.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A backup also keeps a model list (each model's folder, path, size,
SHA-256 and link). Inspecting it names the models this computer lacks
(two copies of one file are one download); "Find downloads..." looks
them up like Model Check (Civitai by hash, the saved link, Hugging
Face), shows size, source and free space, and downloads the ticked ones
one after another into the path they had, each checked against its hash
and scanned after. A file found by name only starts unticked. Verified
on the isolated ComfyUI: an 18 MB Civitai LoRA came back to its folder.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Export packs the stores (recipes, combos, materials, parameters, and
optionally ComfyUI's saved workflows), the plugin settings without the
Civitai key, and each model's user layer and own cover into one .zip to
keep on a cloud drive. Import lists what is new, the same or different
and the models it finds again (by SHA-256, else folder, path and size),
adds only what is missing by default, replaces differing files only on
request with this computer's going to the Recycle Bin first, merges a
model's name and notes field by field and puts the user's cover in
place of a Civitai one. Unsafe or foreign zips are refused. Both are
activity entries. tests/test_backup.py covers the rules; testing.md
names a single test file the way unittest finds it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A combo can now hold its own node structure: pick nodes on the canvas and
New -> From the nodes picked on the canvas keeps the model nodes (a
drop-down of model files) and the text nodes (a multiline text box by the
node's definition) with the links between them; other picked nodes and
links to them are left out, their ports stay open on the canvas.
Slots are per box, so a node with several model drop-downs has several; a
box fed by a link is no slot. Each model slot's folder is the one whose
files hold all its drop-down's model-file options (ComfyUI's /models
lists), never guessed from names. Every other box is stored by name and
put back untouched, in order (a count box adds its rows first).
The save dialog shows what is kept and dropped and lets slots be renamed
or unticked. The editor lists the slots: a picker of that folder's models
with covers, filtered by base model, and text boxes. Put on canvas makes
the nodes (missing node types and their packs are named before anything
is placed), fills the slots by name, links by port name and type, as one
Ctrl+Z step; a box or link that cannot be restored is reported, never
guessed. New -> Same structure as ... starts another combo from a saved
structure. The default combo is unchanged. MCP list_combos lists node
combos by slot and place_combo places them.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Downloads: with the China mirror on, a Civitai match whose very file (same
SHA-256) is on Hugging Face too, by the workflow's link or ComfyUI-Manager's
list, is fetched from Hugging Face; Civitai's name, base model and page stay.
- A file downloaded from Hugging Face gets its model card's first example
image as cover and its base model, trigger words and example prompts as
notes, with the repository as link (api/hf_card.py), never over what the
user or a scan set.
- Text encoders, CLIP vision and upscalers are shown (and scanned) by
default, so shared workflows carry their fingerprints; older configs get
them turned on once (folder_defaults_version 2).
- The models page's search sits in the header (ui_model_search.js) instead
of inside the folder list; it searches the whole type by name, file name,
folder, trigger words, base model and notes, every word; Esc clears it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Models not on Civitai (Flux's VAE, T5 / CLIP text encoders, upscalers,
ControlNets...) are looked up by file name in the model-list.json of the
ComfyUI-Manager installed here (api/manager_catalog.py), keeping entries
that fit the node's folder type. With the workflow's fingerprint only the
listed file with that SHA-256 counts (same-name entries are each asked);
without one, a single entry is offered as "Download by name" with a
warning, never in Download all or the MCP's download_missing_models.
A site that stops answering is skipped for the rest of a lookup while the
others are still asked, so Civitai failing in mainland China no longer
stops Hugging Face through its mirror. GitHub raw file links count as
sources; a Hugging Face file behind a login offers its repository page.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Three MCP tools: download_missing_models (Model Check's Download all for
the open workflow, through the page so the placement rules and the put-in
afterwards are the UI's own), download_model (one model from a Civitai
version link, a Hugging Face / GitHub file link or a Civitai hash, into a
folder of its type) and download_status. The default models folder of a
type is shared by the dialog and the tools.
A Civitai version link without a matching file name now takes the
version's primary model file (people rename their files); a hash, when
there is one, still decides.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Settings > Model downloads can send Hugging Face downloads through
hf-mirror.com, on by default for the Chinese interface. The lookup and the
download use the chosen host whichever one the link names; when the mirror
sends a network outside China back to huggingface.co, the lookup follows
once for the size and SHA-256. A failed download from Hugging Face itself
suggests the mirror.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Model Check offers Download (and Download all) for a missing model whose
source names one exact file: Civitai by the workflow's fingerprint, or a
Civitai version / Hugging Face / GitHub file link the workflow carries.
A dialog shows each file's size, source and full destination, with the
models folder (when there are several) and subfolder changeable; Settings
> Model downloads sets the default: where the workflow says (the node
needs no change) or a set folder, {base} sorting by base model and
matching an existing folder in any spelling.
Downloads run one at a time into <file>.part, continue after an
interruption, are checked against the SHA-256 before they get their name,
never replace a file, and send the Civitai key to Civitai only. Finished
files are put into their nodes (one Ctrl+Z step each), scanned for info
and covers, and recorded in the activity log.
A change of fingerprints alone (after any scan) no longer takes a Ctrl+Z
step that seemed to do nothing.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Current node's "Insert LoRA before / after" refused the most common workflows: a
checkpoint whose CLIP feeds both prompts (one link per output only) and UNet workflows
with their own CLIP loader (MODEL and CLIP had to come from one node).
- graph_splice.js: planLoraInsertion decides the links (after a node: every link of its
MODEL output; before one: only its own MODEL input) and, for LoRAs that train the text
encoder, the CLIP line (same node, a UNet workflow's one CLIP source, or before a
sampler the source its prompts share); spliceLora wires it, all or nothing. The old
analyzeModelChainInsertion / spliceModelChainNode / spliceAfterOutputs are gone.
- api/lora_info.py: GET /anomalous/lora_info reads the LoRA's safetensors header; the
picker asks it on confirm and inserts a model-only loader when there are no
text-encoder weights. The MCP add_lora uses the same helper.
- Insertion messages speak of the MODEL line; the fan-out ones are removed.
- tests/graph_splice.mjs (local) covers checkpoint, UNet + CLIP loader, before a
sampler, and the rollback.
Verified on 8199 through the Current node picker: after a checkpoint feeding two prompts
(full LoRA, both prompts moved) and before a sampler (model-only Flux LoRA).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A model-only LoRA loader was used for every UNet workflow, so a LoRA with text-encoder
weights lost them; and inserting after a checkpoint whose CLIP feeds both prompts was
refused (one link per output only).
- api/mcp_actions.py reads the LoRA's safetensors header: lora_te / te1 / te2 /
text_encoder keys mean it trains the text encoder.
- Such a LoRA becomes a LoraLoader taking MODEL from the model line's end and CLIP from
the same node (checkpoint, full LoRA loader) or a UNet workflow's one CLIP source;
others stay model-only.
- graph_splice.js: spliceAfterOutputs puts a node after outputs on different nodes and
moves every link each output had. The picker's spliceModelChainNode is back to its
committed behavior (the `types` option is gone).
Verified on 8199: UNet + CLIP loader with a text-encoder LoRA, a model-only one after it
and another text-encoder one; a checkpoint feeding two prompts; Ctrl+Z after each.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The second batch of MCP tools: they change things, through the same code the UI uses.
- Canvas, done by the open ComfyUI page: describe_canvas, set_prompt, set_model,
add_lora, place_combo, check_workflow_models, fix_workflow_models, run_workflow,
open_in_anomalous. api/mcp_bridge.py sends the action over ComfyUI's websocket and
waits; web/modules/mcp_bridge.js claims it (visible tab first), does it with
Anomalous's canvas code and answers. Each change is one Ctrl+Z step, shows a toast and
is logged as the AI's (activity entries carry via: "mcp", with their undo).
- This server: scan_models (new / look up again / picked models, via /anomalous/scan_all),
list_voices and speak (Anomalous TTS through /prompt and /history).
- graph_splice.js takes the chain's slot types, so a LoRA can go into a model-only (UNet,
Flux) chain as LoraLoaderModelOnly; the default (MODEL and CLIP) is unchanged.
- Nothing deletes or renames files; acting tools are not marked read-only, so AI apps
ask before calling them.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
An MCP endpoint (Streamable HTTP) inside ComfyUI's server, so Claude, Cursor, Cherry
Studio and other MCP apps can ask about the user's library without anything extra
installed and without memory or VRAM while nobody is connected.
- api/mcp_server.py: one JSON-RPC message per POST, answered with JSON. Serves the
2026-07-28 stateless protocol (headers must match the body) and the earlier
initialize-based versions; no sessions. This computer only: loopback peer, no proxy
headers, loopback Host and Origin (DNS rebinding).
- api/mcp_tools.py: 11 read-only tools: library overview, model search and details
(optional cover), scan status, output-image search and generation settings
(optional thumbnail), combos, workflow recipes, saved prompts, generated audio,
activity log. Ids resolve inside their roots; tool failures come back as isError.
- docs/guides/mcp.md: setup for each app, what can be asked, privacy note.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Tag meanings are brighter and slightly larger, and the top bar picks
their language (Simplified/Traditional Chinese, Japanese, Korean,
Russian, Spanish, French, German, Portuguese, or none) for every
interface language; the old Chinese switch carries over. Typed text in
any language that is not plain English is translated to English, and
translating a box's foreign tags drops one whose English is already
there. The backend skips DeepL for targets it does not take instead of
falling back to English, and lets MyMemory detect other sources.
Unused prompt helpers in translation_service.js are removed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
