> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.ovalbee.com/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.ovalbee.com/_mcp/server. # Changelog ## 0.8.0 # 0.8.0 ## New * **Template setup.** A template can bring a short step-by-step setup that asks only what it can't decide for you: the ontology, who labels and reviews, and where the images are. It lists every dataset the flow will create, so you can rename them or use one you already have. Nothing changes until you press **Start**, which creates the ontology and datasets and runs the nodes. **Later** leaves a **Finish setup** bar on the canvas. See [Templates](/build/templates). * **AI chat on the instance's key.** An instance admin sets an OpenAI or Anthropic key and the default model once, in **Admin** → **Configuration** → **Integrations** → **Flow agent**, and every workspace's AI chat uses it. On OvalBee Cloud each model call is charged to the workspace's credits, and the balance shows under the message box. See [AI agent](/build/agent). ## Improvements * [Dataset insights](/node-library/nodes/dataset-ops-dataset-insights) uses the instance's model and no longer asks for your own key. * **Labeling** → **Statistics** counts each object once, shows time in the tool as a median per submission, and measures consensus review up to the last vote. In the CSV export, `toolbox_seconds_per_asset` is now `toolbox_seconds_median`. * The **Billing** page shows how many runs of each machine class are going against your plan's limit. * API tokens can no longer manage API tokens, workspaces or your account. Do that in the browser. * Edge labels on shared and public flows stay readable where an edge crosses them. ## Fixes * Opening the labeling tool after a long break no longer shows an **Unauthorized** page: the session is renewed, or you sign in and come back to the tool. * Version counts and the latest version shown for a dataset are correct again. ## Removed * The **Flow setup** dialog, the node's **Setup Prompt** toggle and the "Setup inputs changed" badge are gone. A template's setup replaces them. * The **Dataset insights** node no longer has **Anthropic credentials** and **Model** inputs, and new **Anthropic** secrets can't be created. Existing ones can still be renamed or deleted. ## 0.7.0 # 0.7.0 ## New * **Compute credits on OvalBee Cloud.** Node runs and deployments are charged in credits for the time they run, at the price per hour shown for each machine class. Running out of credits for the month stops the workspace's running work and refuses new runs until the credits reset; scheduled runs and runs started by an upstream node are skipped. See [Compute](/administration/compute). * **Machine classes on OvalBee Cloud.** CPU (2 vCPU, 8 GB RAM) and whole GPU cards: GPU · 12 GB, GPU · 24 GB and GPU · 32 GB. * **Runs at once per machine class.** A plan sets how many runs of each machine class a workspace can have going at the same time, shown as **max N at once** next to the price. A run over the limit is refused until one of them finishes. * **Credits in the sidebar.** When a workspace's credits run low or run out, the sidebar shows what is left and a banner explains it on every page. ## Improvements * [Labeling](/node-library/nodes/label-labeling) and [Review](/node-library/nodes/label-review) nodes show live labeling statistics on their card. * A Labeling or Review outcome dataset without an ontology uses the ontology picked in **Classes**, so every outcome shares one set of classes. * A node run shows **Preparing launch** while its machine is being set up, and turns running when the node actually starts. * The **Billing** page shows the current credit burn and roughly when the month's credits run out at that rate. ## Fixes * The labeling tool opens items whose tags carry a value. * Dataset insights and annotation quality reports no longer list a report that found something under "nothing found". # 0.6.0 ## New * **Export to cloud storage.** The [Export to cloud storage](/node-library/nodes/export-ops-export-to-cloud-storage) node writes a dataset's images, and their annotations in Supervisely, COCO or YOLO format, to an S3-compatible bucket. **If files exist** chooses whether to overwrite, skip or stop on files already in the bucket. * **The agent runs flows.** An [AI agent](/build/agent) can now start a flow run, follow its status, wait for it to finish, and read the task logs, reports and report files it produced. Before starting, it names any upstream node that has not produced a value yet. * **Hardest images.** The [Evaluate object detection](/node-library/nodes/evaluate-evaluate-object-detection) report shows the images with the lowest F1 first, each opening the ground truth beside the predictions. Sample images similar to failures starts its search from them. ## Improvements * [Labeling](/node-library/nodes/label-labeling), [Review](/node-library/nodes/label-review) and [Consensus review](/node-library/nodes/label-consensus-review) start with default **Outcome statuses**: **Submit** and **Skip** for Labeling, **Accept** and **Reject** for the review nodes. A status left without a dataset gets a new one on the node's first run. * A dataset input wired from another node's output uses the dataset as it is when the node runs, instead of the version the producing node wrote. The node's preview and sidebar show the dataset it will run on. The dataset picker can now select the first version. * **Align layout** on the canvas uses a new layered layout, and parallel connections no longer draw over each other or over nodes. Nodes the agent adds are placed the same way. * The agent's flow edits move only the part of the flow they change, and it can add notes and change connections. * **Prelabel with live training** previews its output dataset on the node card. * Class colors of YOLO annotations no longer change between views. * **Publish...** in the flow menu is disabled outside the public flows workspace and says why, instead of opening a dialog that fails. * On OvalBee Cloud, a new personal workspace starts on the Pro plan during the beta. ## Fixes * [Train/validation split](/node-library/nodes/sample-train-validation-split) applies its default ratio and shuffling again. A node added while they were missing keeps the empty values, so add it again. * Task history opens the datasets a past run produced, not their newest version. * The plan shown after signing in as another user in the same tab is no longer the previous user's. ## Removed * The **Dataset source verification** node is gone, and **Dataset preview** no longer appears in the node picker. The **Dataset** node shows a dataset's assets and annotations on its card. ## 0.5.0 ## New * **Public templates.** **Save as template** can publish a template to every workspace of the installation with **Public template**, and can replace one of your existing templates instead of adding a new one. Tags, a Markdown readme and publishing sit under **Advanced settings**. Official templates now come live from the official OvalBee library, so a new one appears in every installation without an update. See [Templates and sharing](/build/templates). * **Machine classes.** Administrators name the machines node runs and deployments can use under **Machine classes** in the platform settings, and a node or a deployment picks one of them. See [Compute](/administration/compute). * **Import from cloud storage.** The [Import from cloud storage](/node-library/nodes/import-ops-import-from-cloud-storage) node imports images or videos with their annotations from an S3-compatible bucket and detects the annotation format. * **Label train, validation and test.** The [Label train, validation and test](/node-library/nodes/label-labeling-splits) node gives each labeler one queue that works through the three sets in order, and each set's submissions land in a labeled dataset of its own. * **Active learning with live training.** [Prelabel with live training](/node-library/nodes/models-general-prelabel-with-live-training) pre-labels a dataset with the current weights of a running live training session without stopping it, and can accept images whose boxes are all confident enough. [Active learning curve](/node-library/nodes/evaluate-active-learning-curve) plots mAP against the number of labeled images. * **Group styles.** Flow settings offer three styles for groups, and templates keep a flow's groups. * **Running deployments.** The deployments tab filters by **All** or **Running**. ## Improvements * **Official library URL** in the platform settings names the OvalBee instance that official templates and live examples come from. A value that still points at the old catalog manifest keeps working. * Labeling and Review nodes refresh their queues as soon as work arrives. Their scheduled run, now every 15 minutes instead of every minute or two, returns expired claims. * Train/validation split keeps every image of its previous split on rerun and places only new ones, and has an **Add a test split** switch. Random sample names its dataset after its source. * Sample images similar to failures has an optional **Exclude images in** dataset, so images already labeled are not sampled again. * Grid thumbnails draw boxes in the classes' ontology colors, and a class without a color gets the same one every time. * Evaluation reports leave out findings charts and tables that have nothing to show. * Collaborators no longer see Storage, Models and Ontologies. **Sync from disk** in the node picker is shown only to instance administrators. ## Fixes * Embedding map thumbnails no longer go blank a day after their run. * Review, Consensus review and other steps that cannot edit labels no longer offer Smart Tool or Live Training in the labeling tool, and a rejected image is no longer sent to live training. * A Condition node compares numbers as numbers, where a numeric comparison used to stop the flow. * A dataset card no longer says "No assets" after a node refreshed its statistics. * The CLIP index badge no longer drops to 0 images when a scheduled rerun finds the dataset unchanged. * The labeling tool no longer fails to load an image whose pre-label carries a confidence tag. * A template saved without tags in an update keeps the tags it had. ## 0.4.1 ## New * **AI Chat on every workspace page.** The chat is no longer limited to the flow editor: open it from the button in the bottom-right corner of any page in a workspace. Inside a flow, the editor's own chat takes over. * **Predictions into an existing dataset.** Predict YOLO, Predict DEIM, Predict EdgeCrafter, Predict Grounding DINO, Predict MaskDINO, Predict SparseInst, Predict timm and Apply Model have an optional **Destination dataset** input, typically a labeling pool. Predictions are added to what the dataset already holds, and an image it already annotates gets the new prediction instead of a second annotation. Leave it empty to keep writing to the node's own output dataset. * **Links to the Node Library.** The node picker and the node sidebar link each node to its Node Library page. * **Feedback from the app.** **Feedback** in the user menu reports a bug, suggests a feature or asks a question, with a screenshot if you want one. * **Avatars.** Users and spaces without an uploaded image get a generated avatar, and labeling assignees show theirs. * **Invite codes for signup.** Administrators can require an invite code on the signup page. ## Improvements * A node placed on the canvas no longer has a description of its own. **Edit node** changes its name and icon. ## Fixes * Rerunning a predict node after its destination was cleared continues the same dataset instead of starting a second one. * In a dataset input, the first version of a dataset that has newer versions can no longer be picked, since it always resolved to the latest one.