- An answer past Antigravity's size is filed away unread (eight LoRA
searches in the exam): search_models answers small (loaders once,
four trigger words, a LoRA's author weight); describe_canvas gives a
big canvas's last nodes a line each; mcp_fit.py keeps any other list
answer within the size and names what it left out.
- An empty canvas: run_workflow, describe_canvas and get_situation say
to open a workflow first; get_image_info says a picture's workflow
opens with open_workflow.
- ask_user does not put a "test" question to the user; a task's picture
count counts what its runs made.
- AMB failed to load now and then: ComfyUI loads every file at once and
ui_ai_workbench.js set ui_ai_toolbox.js's sideHost before it was made
when the toolbox file ran first. Connected on first draw now;
tests/load_order.mjs runs every file first.
- input_facts moved to api/picture_mask.py to keep mcp_tools.py short.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Gemini 3.8 Flash took all 8 standard questions the 1.63 way (the
question in the task's message, the new task page's sentence to the
AI, a blank canvas each): 128 calls, 16% failed (21% last time), no
detours. Written into docs/architecture/tool-exam.md.
- A task's picture count counted a picture twice when the AI's report
showed the one its run had made; pictures are counted once each now.
- After a switch of language the AI workbench kept rows drawn in the
old one until a reload: syncRows makes a row again when the language
it was drawn in is not the one shown.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A run with Gemini 3.8 Flash asked for picture to picture and built it node by node, 13 failed calls on the way, with an official example ready:
- list_workflows was 23,630 characters on 17 cards, 21,033 of them settings. Antigravity files an answer over about 4,000 away, unread. A list of more than 3 now goes with name, route, tags and short notes.
- Examples showed only when no saved workflow matched, and only by English words: 图生图 found nothing. They are always named now, and found by their Chinese titles, img2img, txt2img and inpaint.
- Every card's route line was empty, and cards_of found nothing, since c84b596: _list_recipes leaves the graph out, and the tests fed cards that had one. Both ask for it now, with a test on a file on disk.
A waiting task the user wrote to also takes its name from what they wrote, instead of the AI's "take the task".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
run_workflow(base_only) queues the first pass alone (base_only.js cuts each
queued prompt; save nodes become previews, the canvas stays). When it ends,
ai_bases.py shows the previews on a picks panel; the picked one is copied
into the output folder and its seed held. The next run takes the kept
picture where the rest takes the base's picture, so the base is not drawn
again; a base handed on as a latent (mid-way switch) is drawn again from
its seed and compared with the kept one. Drawn again from the same seed, a
base once came out grainy on a 6 GB card, hence the kept picture.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
AMB only uses: training goes to its own plugin. This takes back the
record of what works (api/ai_evidence.py), the training network and
rounds (api/ai_training.py, ui_ai_network*.js, the round form), the
Gates' record switch, the ways' order by record and the external_skill
field of log_outside that only fed the record.
Kept, as part of using AMB:
- the user's word under a finished run, now only told to the AI
(ai_run_control.set_verdict, ui_ai_verdict.js);
- the Gates' "Custom nodes: only the ways'" rule;
- a picks block left to the AI takes its recommended picture.
Reverts 73518dc, 67bf5b2, 6647b05 and 49d05cf, then puts those three
back with tests in test_ai_run_watch, test_ai_gates and test_ai_panels.
Full suite and structure check pass.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each run the AI starts now counts for the ways it still has, the skills
fetched before it and the custom node packs of its nodes, by the base
model of its main model (api/ai_evidence.py). How it went comes from what
the user does anyway: a picture picked in a picks panel or kept in the
gallery, one passed over, or their word under the run (Turned out well /
Not quite, told to the AI as their message).
begin_task and get_toolbox give the AI the record in a few words, add_nodes
a way's or the packs' own, and add_nodes(use=...) picks the use's way that
did best on the canvas's model. The Ways panel shows each way's and skill's
record by model. The Gates window gets "Custom nodes: Any / Only the ways'",
which keeps the AI to the ways' nodes and the task's picks.
Tests: tests/test_ai_evidence.py; full suite and structure check pass.
Checked on an isolated ComfyUI: a real run was recorded with its model and
skill, the verdict reached the AI, and the ways-only rule refused a custom node.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Each skill the AI fetches with get_toolbox(skill=...) is a "skill" step of its task
(ai_skills.note_use), with the form its advice came in for the canvas's model; the same
advice again before the next run adds nothing. A run's row lists the skills fetched since
the run before it (ai_task_view.skillsBefore). A skill step never names an untitled task.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From a Flash run: after report(done) it showed a before and after and
asked whether the user is happy, and both went into a new task. A
panel, question or note within 5 minutes of the AI's own report(done)
now opens that task again (unless the user started or wrote to
another); a look still leaves it ended. "Just done" now means ended
by a report, not that the report is the last step.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
From the user's first real run: the finished task showed as failed for
one wrong argument corrected on the next call, a look the AI took
right after report(done) made an empty one-step task, and a task the
user started 18 hours earlier still read "waiting for the AI" though
it had lapsed after 12 hours. Now only failures the AI did not get
past mark a task, a read-only call within 5 minutes of report(done)
goes into that task (it stays ended) unless the user started or wrote
to another, and a task the user starts waits until an AI takes it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Gemini 3.8 Flash took seven exam tasks through Antigravity (107 calls, 19
failed, every task done). Nearly all failures were a tool's first use:
empty or guessed arguments. So:
- An argument error lists what the tool takes ("set_prompt takes: prompt
(needed), role, node_id, mode"), and the next call is right.
- One argument name per thing: set_prompt's text is prompt (as in
run_workflow), open_workflow's name is workflow (as in run_workflow).
- A wait over 55 s waits 55 s instead of failing; search_models takes a
model type in the singular too.
- An unread reply older than two hours no longer draws a new chat's calls
into its old task (a two-day-old mark took the first exam task).
The exam doc gets the setup, the Antigravity command line and the results.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The user's marks are rough. propose_repaint_area takes the AI's area for
them (boxes or ellipses, grown and softened by pixels), draws both areas
tinted over the picture into the task's marks folder and shows them side
by side on a panel (block "area"): the AI's, the user's own, or marking
again, or words on what to change. The picked area is written into the
input folder like the user's own mask (ai_marks.write_inpaint, soft edges
kept) before the answer is recorded, so the AI reads inpaint_image and the
inpaint note with it. Building the repaint stays the AI's: the note names
the usual nodes, no template. Options Anomalous makes carry a page word
(label_key). The panel hint and guide say "Your call".
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
When the user wrote to an older task while the AI had moved on, the AI's
next call (once its own task ended or paused) started a new task, where
report(reply_to=...) could not find the message. Now an app with no open
task goes back to the newest task of its own holding a reply it has not
read, and opens it again; an open task it is busy with stays. Naming the
calling app moves to api/ai_callers.py to keep ai_tasks.py under its size.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A daily run took six or seven calls (find the workflow, open it, read
the canvas, set the prompt, the seed...), each a decision a small model
could get wrong. run_workflow now takes workflow (a saved one, opened in
the task's tab the first time and reused after: the page marks the tab
with the workflow's file) and blanks: prompt, negative, seed, width,
height and image (image_node when there are several LoadImage nodes),
planned by mcp_fill.js and checked before anything changes; the rest
stays as saved. A run with blanks asks as the stricter of the GPU's and
the canvas's gate. get_situation sends an AI whose run failed on a
missing model to check_workflow_models instead of other choices.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Anomalous sees only the calls made to it; an AI app's own commands and
scripts are invisible, and one rewrote a result six times. When the AI
calls, Anomalous now looks at the top of the output and input folders
for pictures no ComfyUI run saved and pictures rewritten in place since
its previous call (by the files' own times, bounded, never in the
background; new pictures wait while a prompt runs), shows them as an
"Outside AMB" step and tells the AI with its answer (ai_outside.py).
log_outside is the AI's own word on a command or script it ran.
The connect guide gains rules to paste into the AI app's own rules:
use AMB's tools, change pictures only by running workflows, ask and
explain in AMB, and say what was done outside it.
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 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>
- 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>
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>
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>
- ui_ai_marker.js: ✎ on a picture of the AI page opens the marker (box, circle, arrow, pen; three
colours; a note per mark and one for the whole picture). Send draws the marks onto the picture
and hands both to the task; the timeline shows the marked picture and the notes.
- api/ai_marks.py: the PNG is checked (signature, size, dimensions) and kept with the task in
anomalous/ai_marks/ (never the output folder; removed with the task); a user_marks step the AI
gets as a message of kind "marks", where each mark is in fractions of the picture, with the
marked picture attached as an image to the same answer (also from get_answers, whose tool now
returns the answer and those pictures).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- ui_ai_handoff.js: "Hand to AI" on a model's page, the image inspector (✦) and combo cards.
The user says what they want (prefilled), Anomalous starts a waiting task with `about` (the
model_id, the output image, the combo's name; checked in ai_tasks.start_task) and shows the
sentence to send the AI; begin_task hands `about` to the AI so it needs no search.
- The AI windows sit above the image inspector they can open from; going to the AI page from
there closes the inspector.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- api/ai_gates.py: changing the canvas, using the GPU, downloading and scanning online can each
go ahead, ask first or never (downloads ask by default; anomalous/ai_gates.json). A call that
asks waits on its step (state "asking", what it would do listed) up to 50 s for Allow or No
(with the user's reason for the AI); unanswered, the AI is told to wait and call again, the
later answer reaches it as a message, and the same call after an Allow goes ahead.
- ui_ai_gate.js: the card under a waiting step and the Gates window; a toast while elsewhere.
- ui_ai_flow.js + ai_task_view.flowStages: the task's stages in order, each done, running,
waiting or failed; a stage leads to its first step.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- api/action_catalog.py: every MCP tool's kind, stage of the work and gate in one place (a test
keeps it and the tools in step); steps now carry their stage.
- api/ai_task_changes.py: changes the user makes in Anomalous while an AI works become steps of
its task, reach the AI once with its next call (kind "change": keep it), and the activity
entry names the task; the activity page links to it ("AI task ->").
- api/ai_task_runs.py: run watching moved out of ai_tasks.py (600-line rule); a step a restart
left "running" is marked stopped when the record is read again.
- Pictures: inspector / compare with canvas / keep as tools on hover instead of three buttons
under every picture; tick any two (any step or task) and compare from the bar at the foot of
the page; the results strip shows thumbnails again.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
New task: the user starts a task (POST /anomalous/ai_tasks) that waits for
an AI; the next app that calls takes it over, so its work starts there
instead of joining its last task. Connect an AI (ui_ai_connect.js): the
address, a sentence to send the AI so it adds the server itself and
starts on a waiting task, and each common app's way; beside the task list,
on the empty page and in a waiting task. The stage now lists the task's
panels oldest first with their step numbers, the newest at the bottom (a
new one scrolls there, or "New panel" says it came), and the strip of
results runs oldest to newest. The routes move to ai_tasks_routes.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A box under a task's timeline sends the user's message (POST
/anomalous/ai_tasks/{id}/message), kept as a 'user' step; get_answers now
also brings the user's messages and, with no panel named, waits for one.
The step says whether the AI has seen it; when the task has ended the box
says to ask in the AI app. The task list is grouped by day with an icon
for where each task stands.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
show_panel lays out a panel as a step of the AI's task from fixed blocks
(heading, text, pictures in a row, grid or side by side, the user's models
as cards with covers, table, list, params, progress, divider) and can ask:
buttons (one or several) and a line of text. api/ai_panels.py checks every
block (only these kinds, bounded plain text, pictures only from the output
folder, models only from the user's folders); nothing is run or read as
markup, and ui_ai_panel.js writes text only. Answers come in through
POST /anomalous/ai_tasks/{id}/answer and wait for get_answers (which can
wait up to 55 s); update_panel changes or closes a panel. A toast says
when a panel comes while the browser is elsewhere.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A new rail page keeps each MCP call as a step of a task (api/ai_tasks.py,
one file per task in the user folder, the newest 300): named by the AI
with the new begin_task tool, else one app's calls without a long pause.
A step keeps what it did and what it made (models, the combo, the canvas
change by its activity entry, the pictures a run made, watched in the
history until it ends, spoken audio, scans); the new report tool leaves
the AI's notes and pictures it made another way. The page shows the tasks
and one task's results strip and timeline with links (picture viewer,
model page, combo, find or undo on the canvas, audio), updates live, and
gives the rail a dot while you are elsewhere; Home lists the last tasks.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
