Update to Batch Banana

Changed files

Choose a file to see its text changes. Binary or large files show metadata only.

plugin.json →

skills/batch-banana/SKILL.md →

plugin.json

− removed · + added

--- before
+++ after
@@ -1,8 +1,8 @@
 {
   "$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
   "name": "batch-banana",
-  "version": "1.2.0",
-  "description": "Generate and edit images and video with Batch Banana from your agent. Pick a model and a style, generate, and get output URLs back. Search your library to build on earlier work.",
+  "version": "1.3.0",
+  "description": "Generate and edit images and video with Batch Banana from your agent, and run batches of many prompts. Pick a model and a style, generate, see the results, and download them. Search your library to build on earlier work.",
   "author": {
     "name": "Lowside Labs, Inc.",
     "email": "support@batchbanana.com",
@@ -24,7 +24,7 @@
       "interface": {
         "displayName": "Batch Banana",
         "shortDescription": "AI image and video generation",
-        "longDescription": "Batch Banana generates images and video from text prompts and reference images, and edits images you already have.\n\nWhat you can do:\n- Generate images with a choice of image models, aspect ratios, and several different images in one request.\n- Generate short videos from a prompt, a start frame, or reference images.\n- Edit images: remove backgrounds, upscale, relight, expand, restyle, and make text-guided edits.\n- Make images in a named look from the Batch Banana style library, such as watercolor, claymation, or 35mm film. Describe the look you want and the assistant finds the closest styles and shows their example images.\n- Search your Batch Banana library by prompt, kind, model, edit, project, or date to reuse earlier images as references, and file new work under your projects.\n\nHow it works: the assistant lists the available models, starts the job, and returns links to the finished images or video. Every output is also saved to your Batch Banana library.\n\nRequirements: a Batch Banana account. You sign in on batchbanana.com and choose which workspace to connect.\n\nLimitations: generation runs at third-party model providers, which refuse requests that break their content policies. Videos can take several minutes to finish.",
+        "longDescription": "Batch Banana generates images and video from text prompts and reference images, and edits images you already have.\n\nWhat you can do:\n- Generate images with a choice of models and aspect ratios, including several different images in one request.\n- Generate short videos from a prompt, a start frame, or reference images.\n- Edit images: remove backgrounds, upscale, relight, expand, restyle, and make text-guided edits.\n- Make images in a named look from the Batch Banana style library, such as watercolor, claymation, or 35mm film. Describe a look and the assistant finds styles and shows example images.\n- Search your library by prompt, kind, model, edit, project, or date to reuse images as references, and file new work under projects.\n- Run batches of up to 20,000 prompts from a table and follow their progress live.\n- Open any image large and browse with previous and next controls. Download the image you're viewing, or all images from a finished result or batch as a ZIP.\n\nHow it works: the assistant lists available models, starts the job, and shows results in ChatGPT. Every output is also saved to your Batch Banana library.\n\nRequirements: a Batch Banana account. Sign in on batchbanana.com and pick a workspace when you connect. Switch later by asking ChatGPT or choosing Change workspace in Batch Banana's settings. The connection uses one workspace at a time and never switches automatically.\n\nLimitations: generation runs at third-party model providers, which refuse requests that break their content policies. Videos can take several minutes to finish.",
         "developerName": "Lowside Labs, Inc.",
         "category": "Creativity",
         "capabilities": [
@@ -88,6 +88,18 @@
               "prompt": "Make a 5-second video of ocean waves at golden hour and save it to my first project.",
               "tools_triggered": "list_projects, list_models, quote_video_generation, generate_video, get_generation",
               "expected_behavior": "The assistant reads the project id from list_projects, picks a video model, quotes the request, and calls generate_video with durationSeconds 5, the projectId, a new idempotencyKey, and expectedCreditCost. It polls get_generation, waiting the suggested pollAfterMs between calls, until the job completes, then shows the video URL and names the project it was filed under."
+            },
+            {
+              "description": "Generate two images, then download both as one ZIP",
+              "prompt": "Make two square images of a red vintage bicycle leaning on a sunny bakery window, then give me one link to download both.",
+              "tools_triggered": "list_models, quote_image_generation, generate_image, get_generation, download_files",
+              "expected_behavior": "The assistant quotes and generates two images in one generate_image call, polls get_generation until both jobs complete, then calls download_files with the job ids and gives the user one ZIP link on download.batchbanana.com that works for an hour. It does not write code to download the files."
+            },
+            {
+              "description": "See which workspace the connection uses",
+              "prompt": "Which Batch Banana workspaces can you use, and which one are you using now?",
+              "tools_triggered": "list_workspaces",
+              "expected_behavior": "The assistant calls list_workspaces and lists each workspace with its plan and credits, marking the current one. It does not call switch_workspace, because the user did not ask to switch."
             }
           ],
           "negative": [
@@ -110,7 +122,7 @@
         "commerce_description": "Batch Banana does not sell anything inside the assistant. Signed-in users spend credits their workspace already holds."
       },
       "publication": {
-        "release_notes": "Several different images in one request: generate_image takes a list of up to 16 prompts, and every image a reply makes shows together in one results view, with a full-size viewer. Videos show their start frame while they render. show_results brings back earlier work. Clearer messages when an email address isn't verified yet or the workspace is short of credits."
+        "release_notes": "Why a second update today: we published 1.2 earlier today, then tested it in ChatGPT ourselves and found rough edges we didn't want ChatGPT users to hit, so we fixed them right away. Images in the results view, batch images included, now open large with previous and next. Download saves the image you're looking at, and Download all saves a finished result or batch as a ZIP, with links from download.batchbanana.com. Batch cards link to the batch in Batch Banana. When a workspace can't do what was asked, the reply explains why in plain words, links to the pricing page, and mentions another of the user's workspaces that can. A connection works in one of the user's workspaces at a time and changes only when the user asks ChatGPT to switch or chooses Change workspace in Batch Banana's settings. New tools: list_workspaces and switch_workspace. Cancelling a batch run moved out of update_batch into its own cancel_batch tool, marked destructive, so each batch tool states its safety hints accurately. The listing now also describes batches, which the server already supports."
       },
       "apps": "./.app.json"
     }