🔒 Security

• Scoped proxy targets: The proxy only accepts the host of the provider named in the request.
• No credential leakage: On sites behind HTTP authentication, the browser's own credentials are no longer forwarded to the AI provider.

🐞 Bug Fixes

• Provider name casing: providers.OpenAI now works like providers.openai and keeps that provider's model defaults.
• Gateway completion models: Gateways that expect prefixed model names – like Cloudflare AI Gateway's Unified API – receive the correct completion model again.

🚀 Features

• Expanded reasoningEffort options: New provider-default, minimal, and xhigh levels join the existing none / low / medium / high. Configure the effort once – it works across all reasoning-capable OpenAI, Google, Anthropic, and Mistral models. See the Global Configuration documentation.

🔄 Updated Default Models

🚀 Features

• Mistral reasoning: reasoningEffort now applies to Mistral Medium 3.5+ in addition to Small 4 (high / none). See the Global Configuration documentation.

🔄 Updated Default Models

🚀 Features

• PHP classes: Generate text and structured JSON from any PHP context – no Panel required. See the PHP classes documentation.
• 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

• Skills: Define reusable prompt instructions – tone, style, or house rules – in your Kirby config. Editors invoke them from the prompt editor with @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

• Chat Completions mode for OpenAI-compatible gateways: Set 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

• Proxy target allowlist: The proxy now restricts upstream requests to known AI provider hosts plus any configured baseUrl. Prevents authenticated Panel users from redirecting traffic to attacker-controlled hosts.
• Scoped API key forwarding: API keys are now only injected into authentication headers. Prevents a Panel user from exfiltrating the key via other forwarded headers.

🐞 Bug Fixes

• Proxy error handling: Upstream provider errors and network failures now surface to the Panel with proper status codes and messages instead of a silent empty stream.

🔄 Updated Default Models

🚀 Features

• Page references: Reference other Kirby pages in your prompt with @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.
• Syntax highlighting: The prompt editor now highlights {placeholder} tokens and @page:// references with distinct colors for better readability.

🐞 Bug Fixes

• Custom field types: Custom field types registered via 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

🚀 Features

• Block descriptions: Custom block blueprints now support an optional description key that is passed to the AI schema, giving the model richer context about each block's purpose. See the Blocks & Layouts documentation.
• Nested blocks support: Custom block blueprints containing a 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

• System view license management: View your license key, activation status, and version compatibility directly in the Kirby Panel system view. Activate new licenses without leaving the Panel – no more manual file editing required.

🐞 Bug Fixes

• Inline Suggestions trigger: Suggestions will now reliably appear only when the writer field is in focus.

🚀 Features

• Config-defined prompt templates: Predefine prompt templates in the Kirby config that appear for all Panel users. Templates support multilingual labels and prompts via language arrays. Config templates are read-only and displayed alongside user-created templates. See the Prompt Templates documentation.

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

• Dynamic API key resolution: The 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.
• Localized prompt templates: Default prompt templates are now available in English, German, French, and Dutch. Templates are automatically selected based on the Panel user's language setting.

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

• Server-side API proxy: All AI provider requests now route through a server-side proxy instead of direct client-side requests. Your API keys are no longer exposed in browser network requests, protecting them from Panel users.

🚀 Features

• Inline suggestions in writer fields with dedicated 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.
• Global 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.
• Writer mark formatting preservation: Replacing selected text now preserves all formatting (bold, italic, links, etc.). Generation supports all Kirby writer built-in marks.
• Prompt preview: Expand the Preview section in the prompt dialog to see field placeholders replaced with their actual values before sending.
• Prompt templates: Save frequently used prompts as templates. Five built-in templates included (Fix Grammar, Make Concise, Simplify, Extend, Summarize). See the Prompt Dialog documentation.
• Enhanced prompt history: Access recent prompts via dropdown menu with arrow key navigation.

🚨 Breaking Changes

• Temperature removal: The temperature option has been removed. Modern reasoning models (GPT-5, Gemini 3, Claude 4) manage creativity internally. Use reasoningEffort instead.

🚀 Features

• Native PDF parsing: PDF files are now sent directly to the AI provider, allowing models to understand document structure, formatting, and content natively. For files larger than 50 MB, the plugin automatically falls back to text extraction. See the Processing PDF Files documentation.
• New Insert field placeholder button in the prompt dialog. Click the dropdown to see all available fields from the current Kirby model and insert {fieldName} placeholders at the cursor position. See the Field Placeholders documentation.

🚀 Features

• Custom user prompts: Custom user prompts for 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

• Reasoning effort support: Support reasoningEffort for OpenAI GPT-5 and GPT-5 Mini, replacing temperature for these models.
• Customizable view button props: You can now configure the Copilot view button directly in your blueprints, overriding global defaults. Available options:
  • 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

• Block type exclusions: The new 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

• Panel view button: New Panel view button to open the prompt dialog anywhere. You can select multiple fields and generate their content with a single prompt.
• Object and entries fields: Support object and entries fields for content generation.

Although a minor release, this is a major release in terms of features!

🚀 Features

• Structure-aware blocks generation: Supports every project's block configuration and generates content based on your unique block definitions. See the Blocks & Layouts documentation.
• Layout fields: Content generation for layout fields.
• Google Gemini: Added Google Gemini models as supported AI provider.

🚀 Features

• Kirby 5 license status integration: The plugin now displays its license status on the Panel's system page, following Kirby 5's plugin license management conventions. This provides a unified view of all plugin licenses alongside Kirby's own license information.

🚀 Features

• Anthropic image input: Enable image input for prompts when using an Anthropic model.
• Per-site prompt history: Prompt history is now stored separately for each Kirby installation, identified by hostname. Previously, all sites shared the same history in local storage. Now, working with multiple Kirby projects keeps each site's prompt history isolated, making it easier to reuse site-specific prompts.
• API error handling: Pass all API errors to the Panel user interface for better error handling. This helps to catch issues, such as the following with the o3-mini model:

  Invalid content type. image_url is only supported by certain models.

🚀 Features

• Prompt history navigation: Use arrow keys (↑/↓) to navigate through your prompt history in the Copilot dialog. This makes it easy to reuse and modify previous prompts. See toolbar buttons for details.
• Markdown formatting in writer fields: Generated content now supports bold, italic, and code Markdown formatting when using 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

• Global system prompt: New global system prompt to cover text generation for all fields. No need to manually configure prompts for response formatting anymore.

🚀 Features

• Toolbar buttons: New toolbar buttons for writer and textarea fields.
• Kirby 5: Full compatibility with Kirby 5 including the new Panel architecture.
• Many more improvements and bug fixes under the hood.

🚀 Features

• Anthropic Claude: Added Anthropic Claude models as supported AI provider.

🚀 Features

• Panel license activation: Activate and manage your license directly in the Kirby Panel without manual file editing. Click the activation link in the Copilot section to enter your license details. Visit the Kirby Tools Hub to purchase or manage licenses.
• Packagist distribution: The plugin is now available via Packagist, simplifying Composer-based installations. The private Composer repository has been deprecated.

🚨 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

• AI SDK migration: Migrate from ModelFusion to Vercel's AI SDK Core.
• New default model: Set gpt-4-turbo as default OpenAI model.

🚀 Features

• Dynamic prompts with Kirby queries: The 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

• Automatic file context: files: auto on a file model copilot section to automatically use the current file (image or PDF) as context source.
• Debug logging: logLevel section property to debug system and user prompts.
• Custom API base URL: Provider option baseUrl to define the base URL of a custom Mistral API instance.

🚀 Features

• PDF context support: Add PDF files as context for AI prompts. Text content is extracted from each PDF and appended to the prompt, enabling AI generation based on document content. Configure PDF files using the files section property.

🐞 Bug Fixes

• Hosting compatibility: Changed plugin asset extension from .mjs to .js for better compatibility with hosting providers that do not serve .mjs files with the correct MIME type.

🏎 Performance

• Reduced bundle size: Externalized the ModelFusion library to the plugin's 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 AI support: Use Mistral AI models as an alternative to OpenAI. Configure the mistral provider in your global configuration with your API key.
• Image context: Add images as context for AI prompts to generate content based on visual input. Configure image files using the files section property.

🐞 Bug Fixes

• Image format restrictions: Limited image context file types to PNG, JPEG, WEBP, and non-animated GIF. These are the formats supported by vision-capable AI models. Animated GIFs and other image formats are not supported for context.

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

• Panel section: Add the Copilot section to any page blueprint to enable AI content generation. The section provides a prompt input field and generates content for your configured blueprint fields.
• OpenAI integration: Generate content using OpenAI GPT models. Configure your API key and preferred model in the global configuration.
• Customizable prompts: Define user prompts and system prompts to tailor AI responses for specific content types.
• Field targeting: Configure which field the generated content should populate using the field section property.

For setup instructions, see the Installation guide.