🚀 Features
reasoningEffort now applies to Mistral Medium 3.5+ in addition to Small 4 (high / none). See the Global Configuration documentation.🔄 Updated Default Models
| Provider | Model | Old | New |
|---|---|---|---|
| Mistral | Generation | mistral-small-latest | mistral-medium-latest |
🚀 Features
Client::generateObject(): Generate JSON objects conforming to a JSON Schema across all supported providers with a single API. See the client reference.ProviderException: A dedicated exception class wraps upstream provider failures with provider, httpCode, and the original Throwable. See the exceptions documentation.
🚀 Features
@skill://id mentions via the new typeahead dropdown; their instructions are injected into the system prompt at submit time. See the skills documentation and the skills config reference.🚀 Features
providers.openai.api to chat for endpoints that don't expose the Responses API. This unlocks Cloudflare AI Gateway's Unified API – route Gemini, Claude, and more through a single endpoint via the OpenAI SDK shape. See the global configuration documentation.🔒 Security
baseUrl. Prevents authenticated Panel users from redirecting traffic to attacker-controlled hosts.🐞 Bug Fixes
🔄 Updated Default Models
| Provider | Model | Old | New |
|---|---|---|---|
| OpenAI | Completion | gpt-5-nano | gpt-5.4-nano |
🚀 Features
@page://page-id to include their content as context for the AI. Insert pages via the toolbar dropdown or type the syntax manually. See the page references documentation for details.{placeholder} tokens and @page:// references with distinct colors for better readability.🐞 Bug Fixes
Kirby::plugin() that extend standard types (e.g. 'mytext' => ['extends' => 'text']) are now correctly resolved and included in the AI schema instead of being silently skipped. (#8)🔄 Updated Default Models
| Provider | Model | Old | New |
|---|---|---|---|
| OpenAI | Generation | gpt-5.2 | gpt-5.4 |
| Generation | gemini-3-pro-preview | gemini-3.1-pro-preview | |
| Anthropic | Generation | claude-sonnet-4-5-20250929 | claude-sonnet-4-6 |
🚀 Features
description key that is passed to the AI schema, giving the model richer context about each block's purpose. See the Blocks & Layouts documentation.type: blocks field (blocks within blocks) now generate inline schemas for nested block types. Nesting depth is capped at one level to keep the generated JSON schema compact for AI structured output. See the Blocks & Layouts documentation.🚀 Features
🐞 Bug Fixes
🚀 Features
return [
'johannschopplich.copilot' => [
'promptTemplates' => [
[
'label' => 'Apply House Style',
'prompt' => 'Format the text according to our editorial style: artist names in bold, album titles in italics, use curly quotation marks.'
]
]
]
];
return [
'johannschopplich.copilot' => [
'promptTemplates' => [
[
'label' => [
'en' => 'Apply House Style',
'de' => 'Redaktionsstil anwenden'
],
'prompt' => [
'en' => 'Format the text according to our editorial style: artist names in bold, album titles in italics, use curly quotation marks.',
'de' => 'Formatiere den Text nach unserem Redaktionsstil: Künstlernamen fett, Albumtitel kursiv, typografische Anführungszeichen verwenden.'
]
]
]
]
];
🚀 Features
apiKey option now accepts closures for dynamic key resolution at runtime. The closure receives the Kirby instance as its first argument, enabling user-specific or context-dependent API keys. See the Global Configuration documentation.Kirby Copilot v3 is a free upgrade for all users with a valid license key for v2. This major release brings significant security improvements and powerful new features.
🔒 Security
🚀 Features
completionModel configuration per provider. Press Tab to accept AI suggestions, Escape to dismiss. Ghost text appears after a brief pause. Manually trigger with Cmd + , / Ctrl + ,. See the Inline Suggestions documentation.reasoningEffort configuration for all reasoning-capable models (GPT-5, Gemini 3, Claude 4). Controls the depth of reasoning during generation. See the Global Configuration documentation.🚨 Breaking Changes
temperature option has been removed. Modern reasoning models (GPT-5, Gemini 3, Claude 4) manage creativity internally. Use reasoningEffort instead.🚀 Features
{fieldName} placeholders at the cursor position. See the Field Placeholders documentation.
🚀 Features
writer and textarea fields. Define a userPrompt in your field configuration to pre-fill the Copilot dialog with context-specific instructions. Works with nested fields in blocks and layouts.fields:
text:
type: writer
marks:
- copilot
copilot:
userPrompt: Check grammar and improve writing style. Keep the original meaning and tone.
🚀 Features
reasoningEffort for OpenAI GPT-5 and GPT-5 Mini, replacing temperature for these models.label – Custom label for the view button. The default depends on the Panel language.userPrompt – Default user prompt that appears when the generation dialog opens. Users can edit the prompt before generating content.systemPrompt – Custom system prompt that controls how the AI structures and formats the generated content. Users cannot see or edit this prompt.theme – Controls the visual appearance and color theme of the button (e.g., blue-icon, positive, negative-icon).logLevel – Set the logging level for debugging AI generation. Options: error, warn, info, debug.For example, the view button with theme: blue-icon:
🚀 Features
excludedBlocks global option lets you prevent specific block types from being generated by Copilot. This is useful when you have custom blocks that require manual content (e.g., embed blocks, form blocks) or blocks that should only be added by editors intentionally.return [
'johannschopplich.copilot' => [
'excludedBlocks' => ['embed', 'form', 'code']
]
];
Another minor version release, but a major feature release!
🚀 Features
object and entries fields for content generation.Although a minor release, this is a major release in terms of features!
🚀 Features
layout fields.🚀 Features
🚀 Features
o3-mini model:
Invalid content type. image_url is only supported by certain models.
🚀 Features
writer fields. The AI output is automatically converted to the writer field's rich text format.Kirby Copilot v2 is a major release with full support for Kirby 5. This release brings improvements across the board and requires a new license key. If you already have a license, you receive either a free upgrade to v2 or a 50% discount on your new license. Head over to the Kirby Tools Hub to get your discount or read more in the license compatibility guide.
🚨 Breaking Changes
🚀 Features
writer and textarea fields.🚀 Features
🚀 Features
🚨 Breaking Changes
As of April 2024, OpenAI has added vision capabilities to the GPT-4 Turbo model. Following this change, the configuration for the OpenAI provider has been simplified to only include the model name.
🚀 Features
gpt-4-turbo as default OpenAI model.🚀 Features
userPrompt and systemPrompt section properties now support Kirby queries. This allows you to dynamically generate prompts based on page content, site settings, or other data. For example, use {{ page.title }} to include the page title in your prompt.🚀 Features
files: auto on a file model copilot section to automatically use the current file (image or PDF) as context source.logLevel section property to debug system and user prompts.baseUrl to define the base URL of a custom Mistral API instance.🚀 Features
files section property.🐞 Bug Fixes
.mjs to .js for better compatibility with hosting providers that do not serve .mjs files with the correct MIME type.🏎 Performance
assets directory. This significantly reduces the initial Panel JavaScript bundle size, resulting in faster Panel loading times.Official Release
This version marks the official public release of Kirby Copilot. The plugin is now available for purchase and production use.
🚀 Features
mistral provider in your global configuration with your API key.files section property.🐞 Bug Fixes
Initial Release
Kirby Copilot v1.0 brings AI-powered content generation directly to the Kirby Panel. Generate text content from prompts using OpenAI's GPT models.
🚀 Features
field section property.For setup instructions, see the Installation guide.