# What changed in ultralytics-platform

> 28 changes in ultralytics-platform 0.1 from its official release notes, upgrade guides and advisories: 4 breaking, 14 new APIs and options. Each one cited. Sources checked 2026-10-19. HTML: https://unstale.sh/pypi/ultralytics-platform/

To see which of these apply to a repository, run `npx @unstale/cli init` in it.

## ultralytics-platform 0.1

### Breaking changes

- The API contract lowers the maximum export image size from 8192 to 4096. (0.1.88) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.88)
- In `ul cloud train`, `predict`, and `export`, a username before the first slash in `project=` selects the workspace, and the remaining path becomes the project name. (0.1.88) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.88)
- Using another workspace requires editor access; if the workspace exists but the user lacks access, the request fails before files are uploaded. (0.1.88) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.88)
- Failed or cancelled cloud jobs now exit with code 1; local input errors continue to exit with code 2. (0.1.84) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.84)

### New APIs and options

- A new option lets similar-image searches include the source dataset and datasets containing copies of the query image. Copies of the query image itself remain excluded. (0.1.90) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.90)
- Sync and async image prediction methods accept up to 200 same-image seed labels—boxes, segments, or oriented boxes—for YOLOE26X prediction. Predictions can include confidence scores and use seed labels’ dataset class IDs; batch annotation does not support visual prompts. (0.1.90) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.90)
- Added an optional field to training callback responses and the Python TrainingMetricsResponse type, linking to the registered model’s page on the Platform. (0.1.89) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.89)
- The API and Python SDK expose task type, thumbnail URL, image count, and dataset size for bulk-import candidates; task type and dataset size are required. (0.1.88) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.88)
- The task field for Roboflow bulk-import candidates supports the listed YOLO task types. (0.1.88) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.88)
- Replaces gemini-3.1-pro-preview in the image-prediction model options. (0.1.86) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.86)
- Synchronous and asynchronous dataset searches now accept optional minimum and maximum image-count filters to narrow results. (0.1.86) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.86)
- Added muse-wonder-1.0 as an image-prediction option in the Platform API contract and synchronous and asynchronous Python SDK methods. (0.1.84) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.84)
- Accepts capture_dataset_version to save an immutable dataset version for a training run. (0.1.84) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.84)
- Reconnects to an existing export by export_id and downloads its result; Ctrl-C shows a resume command while the export continues remotely. (0.1.83) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.83)
- Accepts image or video URLs with a recognizable file extension, downloads them to the working directory, and processes them like local sources. (0.1.83) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.83)
- The Platform API and Python SDK support an optional comma-separated dataset license filter in synchronous and asynchronous Explore search methods. (0.1.81) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.81)
- Added six AMD Xilinx Versal AI Edge Series Gen 2 device targets for export, broadening deployment options for compatible hardware. (0.1.80) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.80)
- Added xilinx as a supported model export format in the API contract and Python SDK, enabling Python SDK users to request Xilinx-targeted exports with typed SDK support. (0.1.80) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.80)

### Performance

- Already-compressed image formats such as JPEG, PNG, and WebP are stored without recompression, reducing CPU time but potentially making archives slightly larger. (0.1.81) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.81)

### Behavior and default changes

- Replaces claude-haiku-4-5-20251001 in the image-prediction model list. (0.1.83) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.83)
- Relevance sorting is now available and is the default for searches; other searches continue to list newest results first. (0.1.83) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.83)
- Displays the GPU when one is reported by the Platform. (0.1.83) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.83)
- Prints per-image YOLO-style prediction lines instead of raw JSON; saved runs still include results.json. (0.1.83) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.83)
- Looks up or creates the project before packaging a local dataset, reporting Platform access problems sooner; a project may be created before local dataset validation completes. (0.1.81) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.81)

### Fixes and other changes

- The API explains that reaching the detection cap may mean more objects exist, and that truncated generative output can omit objects or classes. (0.1.90) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.90)
- Project model listings exclude validation plots; retrieve an individual model to access them. (0.1.86) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.86)
- Malformed model and data addresses are rejected with a clearer error before uploads or Platform requests. (0.1.84) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.84)
- Workflow reruns no longer send duplicate Slack notifications. (0.1.84) — [release notes](https://github.com/ultralytics/sdk/releases/tag/v0.1.84)