AI Puffer – Your AI engine for WordPress (formerly AI Power)

2.3.81

• Further performance improvements in the Chatbot module.

2.3.80

• Performance improvements in the Chatbot module.
• Added gpt-5.4 to the OpenAI recommended model list.

2.3.79

• Fixed: On-page chatbots no longer auto-switch to fullscreen on small screens; popup chatbots still fullscreen only when opened.

2.3.78

• Added: A shared Prompt Library for Content Writer, Content Assistant, and Automated Tasks.
• Fixed: OpenAI store lists now update right away in AI Forms and Automated Tasks.
• Fixed: Generated images now save correctly in Content Writer.

2.3.77

• Fixed: OpenRouter image selection now shows only models that can actually create images, and Content Writer/Automated Tasks no longer report image success when no image is created.
• Fixed: OpenRouter now correctly creates the requested number of content images in Content Writer and Automated Tasks.

2.3.76

• Fixed: Webhook call issue in chatbot rules.

2.3.75

• Fixed: Chatbot no longer sends temperature to unsupported OpenAI GPT-5 chat-series models (e.g., gpt-5.2-chat-latest).
• Improved: AI Forms reliability with autosave and unsaved-work protection to reduce accidental data loss.

2.3.74

• Added: New maintenance tools in Settings (backup/import, restore point, cache cleanup, sync all models).

2.3.73

• Added: Duplicate functionality for the chatbots.
• Improved: Redesigned Chatbot settings UI.
• Improved: Trigger validation now avoids blocking incomplete payload fields while rules are inactive.
• Improved: Admin asset cache busting now uses file modification timestamps for dashboard bundles.

2.3.72

• Improved: Added option to enable web search by default for chatbots.
• Added: Image editing support for Image Generator (OpenAI, Google, OpenRouter models).
• Improved: Simplified image generate/edit flow in the shortcode (mode=”generate|edit|both” with default mode and switch).
• Improved: Better image upload experience for edit mode (drag & drop, preview, clear errors).
• Improved: One-click Edit from image history to reuse images without re-uploading.

2.3.71

• Improved: Migrated OpenRouter to the Responses API.
• Added: OpenRouter embeddings support in chatbot, content writer, automated task and ai forms.
• Added: OpenRouter web search support in chatbot and ai forms.
• Added: OpenRouter image analysis support in chatbot.
• Added: OpenRouter image generation support in chatbot, content writer, automated task and image generator module.

2.3.70

NEW!: We have a new AI provider in the house: Claude!

You can now add your Claude API key in AI Settings and use Claude directly in the plugin.

Capabilities:

• Use Claude models across supported modules, including Opus 4.6.
• Generate content and run chatbot conversations with Claude.
• Analyze images in Chatbot with Claude vision support.
• Use chatbot file uploads with Claude Files.

2.3.69

• Our new name is now AI Puffeer with a cute puffer fish.
• Fixed conversation titles in the chatbot sidebar.

2.3.68

• Improved: OpenAI streaming now sends small status updates to keep streams stable.
• Improved: Increased default SSE timeout for AI Forms and Content Writer (can be changed with aipkit_stream_timeout filter).

2.3.67

• Fixed: Chatbot webhooks now send reliably (including JSON body payloads).
• Fixed: AutoGPT prompt placeholders now update correctly by task type.

2.3.66

• Improved: Moved assistant settings from Dashboard into the Content Writer module.
• Improved: UI/UX improvements for the Content Assistant, the post list assistant modal, and the “Add to Vector Store” modal.
• Fixed: Chat logs pagination now renders correctly.
• Fixed: Reasoning effort options now align with OpenAI model rules (e.g., minimal mapped to low).

2.3.65

• Improved: Automated Tasks UI polish.

2.3.64

• Improved: Chatbot custom themes.

2.3.63

• Improved: Chatbot custom themes.

2.3.62

• • Fixed: Chatbot theme override issues.

2.3.61

• Improved: Image Generator UI polish.

2.3.60

• Improved: AI Forms UI polish.
• Improved: Pinecone vector store operations now cache index overview for fewer API calls.