A progress block on an AI panel is the AI's own number and never moves.
An AI drew one at 12% during a run, came back after the run with a new
panel and left the old bar standing, which read as live progress. Once
the task goes past a bar without an update (a run ends, a later panel or
note, the task ends), the stage now draws it grey and says when it was
written; update_panel records when a panel's blocks changed. The tool
text tells the AI a run's real progress shows already.
run_status before any run answers state "none" instead of failing, so a
task no longer shows a failed step for asking.
In a wide window the task column keeps its content to about 880 px in
its middle, as chat apps do, instead of stretching across the window.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A task now opens at its newest step instead of where the previous task
was scrolled to, and a timeline read at its foot follows new steps
whatever the task's state (before, only while a step was running).
Read further up, it stays put; a round button over the message box
leads back down, with the count of the AI's new steps on its corner.
It replaces the "new steps below" pill (ui_ai_newest.js).
The side column's grip lay over the timeline's scrollbar, so grabbing
the scrollbar often resized the column instead. It now has a gap of its
own beside the scrollbar, drawn as three dots.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
In one hour Gemini ran 63 shell commands next to 23 AMB calls: checking files, cropping and
comparing parts of pictures, running OpenPose itself to see a skeleton, and painting pixels
with OpenCV (it overwrote an output picture six times).
- api/mcp_look.py zoom_image: part of a picture in the output, input or temp folder shown
larger, the same part of a second picture beside it; read only.
- get_image_info reads the temp folder too; run_status lists a run's PreviewImage pictures
(ai_task_runs.outputs_of(record, "temp"), kept as the step's previews, not its results).
- begin_task and the repaint note: AMB's tools cover looking; change pictures only by running
workflows, never by editing picture files with code of one's own.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The inpaint picture a repaint mark writes is in the input folder, which get_image_info did not
read, so the AI checked it with a shell command (and the user had to allow it). get_image_info
with folder=input gives such a picture's size and the area LoadImage gives as MASK (where and
how much), optionally attached; the marks message says the picture is in place already.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Antigravity saves a tool result over about 4,000 characters to a file and has Gemini open it;
in one evening 16 of its 32 file reads were AMB results (describe_canvas 9 times). Results are
now compact JSON (mcp_tools.tool_text, also for attached answers and run status), the canvas
leaves out the page's own "$$" widgets, and recent_activity gives the last 10 by default.
begin_task also tells the AI that AMB's tools cover models, pictures, nodes, canvas and runs,
so it need not read ComfyUI's folders, source or routes (each asks the user to allow it).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A run's progress comes in alone and only moved the timeline's bar and the header's button, so
the strip over the message box stayed at the run's start ("nodes 0/29, 0%"). The strip keeps
its context and the progress fast path updates it too.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
When the AI page is lower than SHORT_PX (a window not maximised), the task's title, state,
time and steps, the task it goes on from and the tools share one line, the room around them
shrinks, the message box's hint shows only for a failure (its words become the input's
tooltip) and the waiting page's picture is smaller: about a fifth more room for the timeline.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- ui_model_retype.js: on a model's page, and from the toast after importing one model: where it
is, what its header suggests (GET /anomalous/placement/look; picked and marked when it can
tell, nothing guessed when it cannot), every type with its loader, where it goes, moved as
Tidy moves (covers and notes along, never over a file). Kinds and the move's error words are
shared (model_import.IMPORT_KINDS, model_placement.moveErrorText).
- model_import.move_into: a copy to another drive is compared with the original at its start,
middle and end, besides its size, before the original goes.
- model_placement: the model a request names is resolved in one place (_source), which also
refuses a negative root.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
move_into renamed with os.replace, which on Windows replaces a file that appeared after
free_path chose the name. _rename_new refuses a taken name (Windows' rename does by itself;
elsewhere a hard link of the file, or of a link itself), so the move fails and both files stay.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- ui_ai_now.js: over the message box, a run's progress with stop, the AI's step still going, a
gate to allow or refuse there, and the AI's open question with its options as buttons (own
words or skip too; several picks and pictures lead to the stage). progressWords is shared
with the run card; the panel's and gate's answers are exported for it.
- ui_ai_drop.js: pictures dropped on the box or pasted are kept in output/ai_inbox
(POST /anomalous/ai_pictures/upload, ai_pictures.save_upload: read as a picture first,
25 MB cap, never over a file) and attached; ComfyUI output pictures dragged in attach as they are.
- Long AI notes are folded to their first lines with "Show all".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The message box stays at the bottom of the task column however the timeline scrolls. Over the
input, what the message carries (ui_ai_tray.js): pictures with ✎ to mark up (sent on their own)
and ×, chips for what "@" names; gallery pictures are attached, not typed in as "@name". Beside
it the gallery and materials buttons with their counts; the input grows (Enter sends,
Shift+Enter breaks the line) and pictures alone may be sent. "New steps below" appears when the
AI adds steps while the user reads further up; one's own message scrolls into view. Pictures a
message carries show as small image cards with the usual tools. The ready page keeps the big
gallery and what is ready; the box below takes its pictures.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From a hover audit of the AI workbench and the other pages: picked gallery pictures get a thick
glowing frame, tint and big tick; the picture button lights while open and counts the message's
pictures; weak hovers (materials rows, folded reads with a chevron, gate options, mode switch,
source menu, send and copy buttons, model tabs, set-up button, activity rows) are clear. The
Stage button opens an empty stage that says what goes there; "Hand to AI · 0" is disabled with
nothing picked; move_model's step names the file; a one-node change shows one "find"; the task
link chip keeps its size.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A waiting task now switches between Get started and Put ready at the top. Put ready shows the
gallery as a big searchable grid feeding the note below (click to add or drop a picture), the
note (the message box, moved in), the materials button and what is ready so far. The gallery
grid is split out of the message box's picker so both use it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A task waiting for an AI gets a "Put things ready" step: the message box (gallery pictures,
"@") moves into it beside the materials button, and what the user put ready is drawn there;
the AI gets it all when it takes the task. Pictures a message names show as thumbnails.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- model_kind: Anima LLLite, Qwen-Image block-wise and Z-Image Fun ControlNets (and other
ModelPatchLoader files) go to model_patches, not controlnet; import and Tidy follow.
- api/mcp_model_use.py: search_models / get_model say which node types load each model, or
where a misfiled one belongs; move_model moves it there behind a new "files" gate (asks by
default, never overwrites).
- An empty drop-down in add_node says ComfyUI found no file; the task tab switch is no longer
logged as the user's canvas change.
- The folded task list stays while the pointer is in the box around its button and the list.
- The message box's picture button picks gallery pictures; "@" offers the gallery's newest and
searches it as you type.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The whole gap left of the card catches the pointer, top to bottom; the
handle shows faintly at rest and the edge lights up when pointed at.
Focused, the arrow keys resize it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Per sampler: the model and LoRAs feeding it, its prompts, where it starts
(an empty canvas, a picture, or the part before, upscaled) and where it is
saved, "same as part N" when nothing changed; every name finds its node.
Simple (the default) and Full switch in place, kept on this browser.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A task's pictures no longer in the output folder are marked gone when the
task is read and shown as "Picture deleted" (timeline, results strip,
stage panels and picks) instead of a broken picture; "@" no longer offers
them. The AI hears plainly that the user deleted one, and a tool reading a
gone picture says it may have been deleted.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A new task an AI begins while on another, or one the user starts while
looking at a task, keeps it as its "from". Links under the title lead both
ways, the list marks follow-ups, the user can link one by hand or take the
link off (never a loop), and an AI beginning a follow-up hears what was
decided in the task before.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The AI records what was settled with log_decision (a card on the timeline:
what, why, what was left out, who decided, the steps it is about); the
user's own choices in Anomalous count as decisions too (panel answers,
gates, materials, the canvas mode, stops). A Decisions view in the side
column lists them all, links each to its step and notes work done since
the AI's last one; begin_task repeats them to an AI picking the task up.
A step's words move to ui_ai_step_body.js.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"@" lists the task's pictures, combos, models, workflows, prompts, node
packs and node types; what is named rides with the message and the AI gets
each in full (pictures attached with what made them). "/" lists commands
that act at once (stop, undo, side views, new task, canvas mode) or fill in
words to send. get_toolbox shares the lookup.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Instead of a strip to scroll sideways, one "Source: All" button opens the
list of sources (or types), with a search when it is long; a pick, Esc or a
click elsewhere closes it, Esc without closing the browser.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A pack shown in the nodes' second column has a bar to pick it whole
(packs, by folder). The AI gets its node types in get_toolbox and finds
them first; with "only" every node of the pack is allowed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A short panel lists many: badge or small cover, name, where it is from and
the tick per line; the filters become icons beside the search. Switching
between the side panel and the window redraws as lines or cards.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The side column is a card of its own, narrower by default, its width set
by dragging its left edge (kept; double-click resets; the timeline keeps
its room). The task list folds from a title-bar button and peeks over the
page while pointed at. In the docked materials picker a card's detail opens
from its info button, not on hover.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The stage, a run's node map at full size (pick the run; each run step has
"see it large") and the materials picker share the side column; the switch
sits in the window's title bar on the AI page, the shown one again hides the
column, and each view keeps its state. The task header stays on top while
the timeline scrolls.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Every answer, message, set of marks and handed picture shows a pill:
sent and waiting, then the AI has it with the time it did (delivered_at).
Panel questions can be skipped; the AI reads skipped: true.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Each run keeps its shape read from the prompt ComfyUI queued (ai_run_map.py): boxes by role
with their settings, typed links, plumbing wired through, and what changed since the task's
run before. The run step shows a one-line summary, the changes as chips and the boxes (top
down, fitted to the column, each locating its node); show_run_map puts it on the stage.
- By default the AI works in a tab of the task's own (ai_task_canvas.py, mcp_task_tab.js): the
open workflow is copied before its first change, the tab is brought back (a click on
ComfyUI's tab) before later changes, reads and runs, and the user's tab stays untouched.
Per-task switch in the header, default in the Gates window; the AI is told once.
- Output pictures can be handed to the task an AI is on (gallery card menu, the inspector's
✦), with the user's words: the AI gets them attached with what made them (ai_pictures.py).
search_images(with_pictures) attaches the first six.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- A stop button on a running run (timeline, and beside the run-status button), and stop_run for
the AI: only this run's prompts leave the queue or are interrupted; the step ends "cancelled"
and a user's stop reaches the AI as a "stop" message (ai_run_control.py).
- The run's progress carries ComfyUI's console since it began (the bar's note, models loading),
time left and per step, and VRAM; once queued, each sampler's working size is estimated from
the prompt, with warnings for an upscaled picture sampled again, a size past the card and a
huge decode, for the user and in the AI's run news (ai_run_watch.py, ui_ai_run_live.js).
- The materials picker opens as a side panel that leaves the page usable (the full-screen
browser makes room), expands to the large window and back, and remembers the choice.
- Esc closes the run-status card only (data-anomalous-escape).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The marker gains a repaint brush (size adjustable) and "make a repaint
mask": the page sends a mask (white where boxes, circles, lines and brush
strokes are) and the server writes the picture with that area as its
alpha to ComfyUI's input folder (anomalous_inpaint_<step>.png, a new file
each time), so LoadImage gives the picture and the area as MASK. The AI's
marks message carries the file and how to inpaint with it; the timeline
says the mask is ready. Canvas tools read ComfyUI's lists anew once when a
value is not among a drop-down's choices, so they take the new file.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
report takes reply_to, the id of the user's message or marks it answers:
the two steps point at each other and the timeline links them both ways
("Reply to step 2" / "The AI replied · step 4"). The AI's notes are laid
out (headings, lists, bold, code) by ai_text_format.js with textContent
only. The notice that brings the user's marks and messages, the report
description and the server instructions tell the AI to answer in
Anomalous, and to ask which fix with ask_user.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ask_user shows a question in the AI workbench (options with an optional
recommended one, and unless other=false a line for an answer of the
user's own; no options: a line) and waits in the same call for the
answer, returning the choice or the text. Choices blocks gain
recommended and other; the step is named ask_user ("Asked you"). The
server instructions, begin_task and the workbench prompt tell the AI to
ask every question this way, never in its own chat.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The task column (now ui_ai_task_list.js) leads with a New task button, icon
buttons for Connect an AI and the gates, which AI came last, quick filters
by state with counts, and state icons; the current task has an accent bar.
A task's header uses icon buttons (Materials, Undo all, show the stage,
rename and remove as pencil and bin). A waiting task shows a picture, three
numbered steps joined by a line (what to do, the sentence with a large
Copy button, a faint preview of steps) and a connect card that opens the
guide in place; the empty page matches. One set of line icons for the AI
pages (ui_ai_icons.js). Illustrations made with ChatGPT.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The empty pane shows a toolbox with cards rising out of it, and a combo,
workflow or model without a cover shows a stand-in illustration of its
kind, all transparent WebP of a few dozen KB in web/assets (made with
ChatGPT for this window). The hand-drawn SVG picture they replace is gone.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A large window: one search over every kind (/ jumps to it), kinds on the
left with picks and matches, a column by source (each custom node pack
with a badge of its own colour, ComfyUI's own, paid API nodes), prompt
origin or model type, a card grid drawn as it scrolls, the card in focus
in full on the right, and the picks below with thumbnails and a prefer /
only switch. A node card is the node in miniature, sockets in ComfyUI's
colours; combos, workflows and models show their covers; prompts their
text, including the prompts inside combos and workflows (combo:<name>,
workflow:<name>), which get_toolbox now resolves. Vector icons, badges
and the empty picture follow the theme.
It opens at once: node types come from the page's own definitions, the
rest in one answer (api/ai_toolbox_catalog.py) read ahead when a task
header is drawn and kept a minute, refreshed behind an open window.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A Materials button on each AI task opens a picker: every node type of this
ComfyUI grouped by source (built-in, each custom node pack from
/object_info's python_module, page-only helpers, paid API nodes last), plus
combos, saved workflows, prompts and models by the names the AI's tools
use. Picks go to the AI as a user_toolbox step (message kind toolbox), in
begin_task and in full from get_toolbox; "only" makes add_node and
new_workflow refuse other custom or paid node types (built-in stay
allowed). Favourites stand in for tasks without picks. find_nodes lists
picks first and marks paid API nodes. open_workflow opens a saved
workflow in a new tab; a workflow's page can hand it to the AI.
Checked on the isolated ComfyUI with copies of the user's 10 node packs:
all 1642 node types can be placed, and a Comfyroll workflow ran.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
find_nodes looks up this ComfyUI's node types (inputs, outputs, choices)
from its own /object_info. new_workflow opens a new tab, blank or built and
laid out from a workflow in API form, never touching the open one;
add_node, connect_nodes, set_values and remove_nodes edit it. Everything is
checked against the nodes before the canvas changes (types, loops, settings,
choices with close matches); each is one Ctrl+Z step, logged as the AI's
and shown under its workbench step. Receipts now show rewiring ("wired":
what feeds an input, before and after). A run ComfyUI refuses reports
ComfyUI's own reason instead of "Prompt execution failed".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
