Kalpana Batch

Stops a batch: every job still pending or processing becomes cancelled. A cancelled job is final and is not charged; a render already under way may finish, but its result is discarded. Jobs that already rendered keep their output and their charge. Cancelled jobs cannot be resumed; to render them again, create_batch a new batch with those rows. get_batch shows the cancelled count, and repeating the call cancels nothing more. Needs batches:create on the connection and renders:create in the user's workspace role.

Stops one job that is pending or processing: it becomes cancelled, final and not charged; a render already under way may finish, but its result is discarded. A job that already finished is left as it is. Other jobs in its batch keep rendering; cancel_batch stops them all. Needs batches:create on the connection and renders:create in the user's workspace role.

Saves a new draft batch in the template's workspace with one pending job per row, an image, or a video when outputFormat is mp4, gif, webm or mov; nothing renders and no credits are spent until run_batch. The result's creditCost is the exact number of credits run_batch will spend on these jobs. Every call creates a separate batch, so repeating a call duplicates it; changing an existing draft is update_batch's job. Rows are checked as in validate_batch, and one invalid row rejects the whole request with nothing saved. An animated template renders each image at one moment of its motion: stillTime, else the page's own still time, else the last frame; a video renders all of it and takes no stillTime. Needs templates:read and batches:create.

Returns one batch's overall status with its total, completed, failed, and processing job counts. Rendering after run_batch happens in the background, so repeated calls track it until processing reaches 0. list_batches gives the same counts for many batches at once; per-job values and render errors are in get_batch_jobs, and download URLs in get_batch_outputs. Needs batches:read.

Lists a batch's jobs in row order, one page at a time, with each job's ID, template, current row (keyed and shaped as rows are written), status, render error, and whether it can still be edited. These job IDs and values are the input for update_batch and update_job, and error explains why a render failed. Download URLs are not included (get_batch_outputs has them), and get_batch is lighter for overall progress. Needs batches:read.

Returns the download URLs of a batch's rendered images, one page of jobs at a time, with each job's status and format; downloadUrl is null until that job has rendered. URLs are temporary, so a later call returns fresh ones. Row values and render errors are not included (get_batch_jobs has them), and get_batch is lighter for checking progress. inspect_image can view a downloadUrl. Needs batches:read, renders:read, and creatives:read.

Returns the inputs of one template that batch rows can fill: each input's id, label, text or image type, whether it is required, its default (a text input's value, an image input's asset and preview), image slot size and fit, the key rows use for it (its name, or its id when two layers share the name), a text input's styles (s1, s2, ...) when it has several, and a valueExample; rowExample is a whole ready row. Those keys and values are what validate_batch, create_batch, update_batch, and update_job accept. It needs a template ID; finding templates is search_templates' job. Inputs the author turned off or placed on hidden layers are left out unless requested, and omittedInputs names them: their template text still renders, so check them (dates, terms, links) when the copy changes theme; a row can fill them by key. The template's internal layout is not returned. An animated template also gives its duration and its stillTime, the second its images show unless create_batch gives another. Needs templates:read.

Fetches one PNG, JPEG, or WebP image from a Kalpana URL (a template or asset previewUrl, or a downloadUrl from get_batch_outputs) and returns it as image content with its content type and byte size. Other hosts, other file types, and files over 5 MB are rejected, and a fetch gives up after 15 seconds. It shows one image per call; it does not build contact sheets or render templates, whose look comes from their previewUrl.

Lists the image collections (named groups of images) in the workspace, most recently updated first, with each collection's ID, description, and image count. All matches come back in one response, without pages. A collection ID only narrows search_assets to that collection; finding images by filename, or across the whole workspace, is search_assets alone. Needs assets:read in the workspace.

Lists the workspace's batches, newest first, one page at a time, with each batch's ID, name, status, and total, completed, failed, and processing job counts; total counts every match, so it also answers how many batches exist. Filters narrow by batch name or template. For one known batch ID, get_batch returns the same counts, and job details are in get_batch_jobs. Needs batches:read.

Returns the one Kalpana workspace this connection covers, chosen when the user connected: its ID, name, slug, the user's role, and what that role allows here, both as permission codes and in plain words (for example whether it can render batches). Every other tool works in this workspace, so none takes a workspace ID. A missing permission explains a 403 from another tool, such as run_batch without renders:create. Working in another workspace needs a reconnect that chooses it. Needs workspaces:read.

Queues every pending job in a batch for rendering and returns once they are queued; images render in the background, tracked by get_batch and collected with get_batch_outputs. It spends the workspace organization's credits equal to the pending jobs' cost, which is create_batch's creditCost unless jobs were added or removed since. When the balance is too low nothing is queued, the error says not enough credits, and the batch stays a draft. A successful run publishes a draft, which ends add and remove edits through update_batch; archived batches return an error. Only pending jobs are queued, so a repeat call adds no work and no cost, and jobs reset to pending by update_batch or update_job render on the next call. If the workspace has webhook endpoints, the run's results are sent to them unless webhooks is false. Needs batches:create on the connection and renders:create in the user's workspace role.

Finds images to put into template image inputs: the ready PNG, JPEG, and WebP files under 5 MB in the workspace, one page at a time, with a previewUrl each. With no filters it lists the most recently updated images; collectionId limits results to one collection, query matches filenames, and both combine. An asset's id is the asset_id of an image input in batch rows. Collection IDs come from list_asset_collections; inspect_image shows a previewUrl; the user's own files are added with upload_images. Needs assets:read in the workspace.

Finds the workspace's templates to fill with data, one page at a time, with each template's ID, workspace, pixel size, input count, previewUrl, and a link that opens it in Kalpana. Without query it lists recently updated templates; query matches an exact template ID, name, description, or campaign topic, and the filters narrow by preview availability or exact size. Animated templates are included and marked isAnimated: their images show one moment of the motion. A template's fillable inputs are not included; get_template_inputs returns them for one ID, and inspect_image shows a previewUrl. Needs templates:read.

Renames a batch and, while it is a draft (until run_batch first succeeds), changes, adds, or removes its editable jobs (pending, or failed with no output) in one request. update merges the given fields into each listed job's values and resets it to pending; unlisted jobs are untouched. remove deletes those jobs permanently, and each add creates new jobs, so repeating a request with add duplicates them. Processing and rendered jobs cannot change. Nothing renders until run_batch, and adding or removing jobs changes what it costs. One pending job in a batch that is no longer a draft is update_job's case. Needs templates:read and batches:create.

Changes one pending job that has no output yet, in any batch, including batches that are no longer drafts. The given fields replace those fields' previous values and other fields stay as they are, so repeating the same request gives the same result. Failed, processing, and rendered jobs are rejected; a failed job in a draft can still change through update_batch. Nothing renders until run_batch. Several jobs at once, or adding and removing jobs, is update_batch's case. Needs templates:read and batches:create.

Brings the user's own images (PNG, JPEG, or WebP, up to 5 MB each) into the workspace, optionally into a collection, which is made when no collection has that name. Without files it returns a link to the workspace's Images page (the collection's page with collection) for the user to drop the images into; after they say they are done, search_assets finds them. An agent that has the files (a shell, files on disk) passes files with each one's SHA-256 hash, content type, and size, PUTs each file's bytes to its uploadUrl with that Content-Type header, then calls again with done (each hash and file name) to record them. The recorded images come back with their id, the asset_id of an image input in batch rows. Image data is not accepted inline as base64. Needs assets:create.

Checks batch rows against a template and reports every problem by row index and field, without saving anything or spending credits. It runs the same row checks as create_batch, so rows that pass here are accepted there, while create_batch saves nothing if any row fails. Each row comes back as the server understood it (layer keys, text, and each image resolved to its asset id and file name), so a misread value shows before any credits are spent. A layer name two layers share is refused with their ids: fill each by id and tell the user, who can rename one. It does not measure text, so copy longer than the template's sample can still overflow its box. Needs templates:read.