Hi there! We've got some great new features for you in this update. ***1.6.40: • 10 new themed app icons for Halloween and Christmas. • On macOS, the improved menu bar chat now appears only after server setup and opens your current conversation directly in the main app window. • Minor bug fixes and improvements for a smoother experience. ***Recent Updates: • Choose from 20 app icons in Settings on iPhone and iPad. • Long chats now preserve earlier context before the next model response, with safer handling when requests are cancelled or interrupted. • Scroll through long conversations and verify that scrolling remains smooth while the floating date indicator updates. • While a model is responding, scroll through the conversation and verify that the visible history stays stable, then catches up when scrolling stops. • Start a model response, leave OpenClient, and verify that its Live Activity shows progress through reasoning, tool use, image generation, and saving. • Fixed an issue that could cause the app to freeze when manually scrolling while a model was responding, or after several responses. • On macOS, add OpenClient widgets to the desktop or Notification Center and test New Chat, Search, Quick Actions, Continue Chat, Recent, Pinned, and Tagged Conversations. • On macOS, add the New Chat control and verify that it opens the app directly in a new conversation. • Chat messages now show their time, with a floating date indicator when scrolling through conversation history. • Test the new per-tool MCP permissions and approval flow: set tools to Always Allow, Ask, or Deny, then review requested MCP calls before execution. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in Settings.

Hi there! We've got some great new features for you in this update. ***1.6.35: • Choose from 20 app icons in Settings on iPhone and iPad. • Long chats now preserve earlier context before the next model response, with safer handling when requests are cancelled or interrupted. • Scroll through long conversations and verify that scrolling remains smooth while the floating date indicator updates. • While a model is responding, scroll through the conversation and verify that the visible history stays stable, then catches up when scrolling stops. • Start a model response, leave OpenClient, and verify that its Live Activity shows progress through reasoning, tool use, image generation, and saving. • Minor bug fixes and improvements for a smoother experience. ***Recent Updates: • Fixed an issue that could cause the app to freeze when manually scrolling while a model was responding, or after several responses. • On macOS, add OpenClient widgets to the desktop or Notification Center and test New Chat, Search, Quick Actions, Continue Chat, Recent, Pinned, and Tagged Conversations. • On macOS, add the New Chat control and verify that it opens the app directly in a new conversation. • Chat messages now show their time, with a floating date indicator when scrolling through conversation history. • Test the new per-tool MCP permissions and approval flow: set tools to Always Allow, Ask, or Deny, then review requested MCP calls before execution. • You can now support OpenClient with optional monthly or annual subscriptions, alongside one-time coffee purchases. No features are locked. • Fix widgets layout issues. • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • New section in Settings to manage iCloud data. • General stability, reliability, and performance improvements. • You can now generate images directly in chat with supported models. • We’ve added update notifications so you can easily keep the app up to date. • The app can now display important announcements and news directly on the Home screen. • We’ve improved how maintenance periods are handled, providing a clearer experience when the service is temporarily unavailable. • RAW images selected from Photos are now processed correctly before being sent. • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • Fixed several issues with conversations changed or deleted on other devices. • General stability, reliability, and performance improvements. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in Settings.

Hi there! We've got some great new features for you in this update. ***1.6.30: • Fixed an issue that could cause the app to freeze when manually scrolling while a model was responding, or after several responses. • On macOS, add OpenClient widgets to the desktop or Notification Center and test New Chat, Search, Quick Actions, Continue Chat, Recent, Pinned, and Tagged Conversations. • Minor bug fixes and improvements for a smoother experience. ***Recent Updates: • Chat messages now show their time, with a floating date indicator when scrolling through conversation history. • Test the new per-tool MCP permissions and approval flow: set tools to Always Allow, Ask, or Deny, then review requested MCP calls before execution. • You can now support OpenClient with optional monthly or annual subscriptions, alongside one-time coffee purchases. No features are locked. • Fix widgets layout issues. • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • New section in Settings to manage iCloud data. • General stability, reliability, and performance improvements. • You can now generate images directly in chat with supported models. • We’ve added update notifications so you can easily keep the app up to date. • The app can now display important announcements and news directly on the Home screen. • We’ve improved how maintenance periods are handled, providing a clearer experience when the service is temporarily unavailable. • RAW images selected from Photos are now processed correctly before being sent. • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • Fixed several issues with conversations changed or deleted on other devices. • General stability, reliability, and performance improvements. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in Settings.

Hi there! We've got some great new features for you in this update. ***1.6.25: • Chat messages now show their time, with a floating date indicator when scrolling through conversation history. • Minor bug fixes and improvements for a smoother experience. ***Recent Updates: • Test the new per-tool MCP permissions and approval flow: set tools to Always Allow, Ask, or Deny, then review requested MCP calls before execution. • You can now support OpenClient with optional monthly or annual subscriptions, alongside one-time coffee purchases. No features are locked. • Fix widgets layout issues. • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • New section in Settings to manage iCloud data. • General stability, reliability, and performance improvements. • You can now generate images directly in chat with supported models. • We’ve added update notifications so you can easily keep the app up to date. • The app can now display important announcements and news directly on the Home screen. • We’ve improved how maintenance periods are handled, providing a clearer experience when the service is temporarily unavailable. • RAW images selected from Photos are now processed correctly before being sent. • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • Fixed several issues with conversations changed or deleted on other devices. • General stability, reliability, and performance improvements. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in Settings.

Hi there! We've got some great new features for you in this update. ***1.6.20: • Test the new per-tool MCP permissions and approval flow: set tools to Always Allow, Ask, or Deny, then review requested MCP calls before execution. • You can now support OpenClient with optional monthly or annual subscriptions, alongside one-time coffee purchases. No features are locked. • Fix widgets layout issues. • Minor bug fixes and improvements for a smoother experience. ***Recent Updates: • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • New section in Settings to manage iCloud data. • General stability, reliability, and performance improvements. • You can now generate images directly in chat with supported models. • We’ve added update notifications so you can easily keep the app up to date. • The app can now display important announcements and news directly on the Home screen. • We’ve improved how maintenance periods are handled, providing a clearer experience when the service is temporarily unavailable. • RAW images selected from Photos are now processed correctly before being sent. • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • Fixed several issues with conversations changed or deleted on other devices. • General stability, reliability, and performance improvements. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in Settings.

Hi there! We've got some great new features for you in this update. ***1.6.15: • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • New section in Settings to manage iCloud data. • General stability, reliability, and performance improvements. • Minor bug fixes and improvements for a smoother experience. ***Recent Updates: • You can now generate images directly in chat with supported models. • We’ve added update notifications so you can easily keep the app up to date. • The app can now display important announcements and news directly on the Home screen. • We’ve improved how maintenance periods are handled, providing a clearer experience when the service is temporarily unavailable. • RAW images selected from Photos are now processed correctly before being sent. • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • Fixed several issues with conversations changed or deleted on other devices. • General stability, reliability, and performance improvements. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in Settings.

Hi there! We've got some great new features for you in this update. ***1.6.10: • You can now generate images directly in chat with supported models. • We’ve added update notifications so you can easily keep the app up to date. • The app can now display important announcements and news directly on the Home screen. • We’ve improved how maintenance periods are handled, providing a clearer experience when the service is temporarily unavailable. • RAW images selected from Photos are now processed correctly before being sent. • Major improvements to iCloud conversation syncing, especially when switching between devices or returning to the app. • Fixed several issues with conversations changed or deleted on other devices. • General stability, reliability, and performance improvements. • Minor bug fixes and improvements for a smoother experience. ***Recent Updates: • New widgets. • Assistant messages now render the full markdown toolkit: blockquotes, lists with nesting, task lists, horizontal rulers, code blocks with language labels, tables, and inline images all display natively in the chat. • Steer conversations mid-stream: send a follow-up message while the model is still generating; the current stream is cancelled, the partial response is preserved, and your new message continues the conversation with full context. • Connect MCP servers (Model Context Protocol) to give the model access to external tools like GitHub, databases, and more, all configured from your LiteLLM server. • Browse your MCP servers in a dedicated sheet from the chat input bar or from Settings, then drill into each server to enable or disable individual tools with a master toggle. • A new collapsible actions bar keeps the chat composer clean: attachment, web search, and MCP buttons are tucked behind a single + / × toggle, auto-collapsing after use or when sending a message. • Contextual tips introduce MCP servers when the feature becomes available, following the same unobtrusive pattern as other feature tips. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in Settings.

Hi there! We've got some great new features for you in this update. ***1.6.5: • Minor bug fixes and improvements for a smoother experience. ***Latest Updates: • New widgets. • Assistant messages now render the full markdown toolkit: blockquotes, lists with nesting, task lists, horizontal rulers, code blocks with language labels, tables, and inline images all display natively in the chat. • Steer conversations mid-stream, send a follow-up message while the model is still generating; the current stream is cancelled, the partial response is preserved, and your new message continues the conversation with full context. • Connect MCP servers (Model Context Protocol) to give the model access to external tools like GitHub, databases, and more, all configured from your LiteLLM server. • Browse your MCP servers in a dedicated sheet from the chat input bar or from Settings, then drill into each server to enable or disable individual tools with a master toggle. • A new collapsible actions bar keeps the chat composer clean: attachment, web search, and MCP buttons are tucked behind a single + / × toggle, auto-collapsing after use or when sending a message. • Contextual tips introduce MCP servers when the feature becomes available, following the same unobtrusive pattern as other feature tips. • Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. ***1.6.2: • New widgets. • Minor bug fixes and improvements for a smoother experience. ***Latest Updates: • Assistant messages now render the full markdown toolkit: blockquotes, lists with nesting, task lists, horizontal rulers, code blocks with language labels, tables, and inline images all display natively in the chat. • Steer conversations mid-stream, send a follow-up message while the model is still generating; the current stream is cancelled, the partial response is preserved, and your new message continues the conversation with full context. • Connect MCP servers (Model Context Protocol) to give the model access to external tools like GitHub, databases, and more, all configured from your LiteLLM server. • Browse your MCP servers in a dedicated sheet from the chat input bar or from Settings, then drill into each server to enable or disable individual tools with a master toggle. • A new collapsible actions bar keeps the chat composer clean: attachment, web search, and MCP buttons are tucked behind a single + / × toggle, auto-collapsing after use or when sending a message. • Contextual tips introduce MCP servers when the feature becomes available, following the same unobtrusive pattern as other feature tips. • Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. ***1.6.1: • Minor bug fixes and improvements for a smoother experience. ***1.6.0: • Assistant messages now render the full markdown toolkit: blockquotes, lists with nesting, task lists, horizontal rulers, code blocks with language labels, tables, and inline images all display natively in the chat. • Minor bug fixes and improvements for a smoother experience. ***1.5.0: • Steer conversations mid-stream, send a follow-up message while the model is still generating; the current stream is cancelled, the partial response is preserved, and your new message continues the conversation with full context. • Connect MCP servers (Model Context Protocol) to give the model access to external tools like GitHub, databases, and more, all configured from your LiteLLM server. • Browse your MCP servers in a dedicated sheet from the chat input bar or from Settings, then drill into each server to enable or disable individual tools with a master toggle. • A new collapsible actions bar keeps the chat composer clean: attachment, web search, and MCP buttons are tucked behind a single + / × toggle, auto-collapsing after use or when sending a message. • Contextual tips introduce MCP servers when the feature becomes available, following the same unobtrusive pattern as other feature tips. • Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. ***1.6.0: • Assistant messages now render the full markdown toolkit: blockquotes, lists with nesting, task lists, horizontal rulers, code blocks with language labels, tables, and inline images all display natively in the chat. • Minor bug fixes and improvements for a smoother experience. ***1.5.0: • Steer conversations mid-stream, send a follow-up message while the model is still generating; the current stream is cancelled, the partial response is preserved, and your new message continues the conversation with full context. • Connect MCP servers (Model Context Protocol) to give the model access to external tools like GitHub, databases, and more, all configured from your LiteLLM server. • Browse your MCP servers in a dedicated sheet from the chat input bar or from Settings, then drill into each server to enable or disable individual tools with a master toggle. • A new collapsible actions bar keeps the chat composer clean: attachment, web search, and MCP buttons are tucked behind a single + / × toggle, auto-collapsing after use or when sending a message. • Contextual tips introduce MCP servers when the feature becomes available, following the same unobtrusive pattern as other feature tips. • Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. ***1.5.0: • Steer conversations mid-stream, send a follow-up message while the model is still generating; the current stream is cancelled, the partial response is preserved, and your new message continues the conversation with full context. • Connect MCP servers (Model Context Protocol) to give the model access to external tools like GitHub, databases, and more, all configured from your LiteLLM server. • Browse your MCP servers in a dedicated sheet from the chat input bar or from Settings, then drill into each server to enable or disable individual tools with a master toggle. • A new collapsible actions bar keeps the chat composer clean: attachment, web search, and MCP buttons are tucked behind a single + / × toggle, auto-collapsing after use or when sending a message. • Contextual tips introduce MCP servers when the feature becomes available, following the same unobtrusive pattern as other feature tips. ***1.4.5: • Back up and restore your conversations, including attachments and conversation branches, across devices. • Start a Private Chat that keeps messages, files, generated images, web results, and agent activity only in memory, without saving, syncing, or accessing personal memory. • See how much context a conversation is using, including estimated token usage and the model’s context limit. • Configure a custom context window for compatible servers that do not provide model metadata. • Keep longer conversations running smoothly with automatic context compaction. • Improved context handling and agent safeguards for more reliable multi-step workflows. • Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. • Back up and restore your conversations, including attachments and conversation branches, across devices. • Start a Private Chat that keeps messages, files, generated images, web results, and agent activity only in memory, without saving, syncing, or accessing personal memory. • See how much context a conversation is using, including estimated token usage and the model’s context limit. • Configure a custom context window for compatible servers that do not provide model metadata. • Keep longer conversations running smoothly with automatic context compaction. • Improved context handling and agent safeguards for more reliable multi-step workflows. • Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. • Buy Me a Coffee tip jar: A new optional tip jar is now available in Settings. If you'd like to support development, you can offer a small, medium, or big coffee — it's completely voluntary and unlocks nothing. The app remains fully free and open source. • Search tools discovery: Settings → Web Search now includes a "Load Available Tools" button that fetches the list of search providers configured in your LiteLLM server, so you no longer need to type the tool name manually. The first available tool is auto-selected if your saved name is no longer valid. • Privacy screen (iOS): A new toggle in Settings → Privacy lets you hide app content when switching apps or opening the App Switcher, replacing it with a blurred overlay — just like banking apps. • Reasoning streaming in agent mode: Model thinking tokens (reasoning/thinking content) are now streamed in real time during agent mode, so you can follow along as the model reasons through its response. • Minor bug fixes and improvements for a smoother experience, including better resilience when streaming responses finish with empty content. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. • Buy Me a Coffee tip jar: A new optional tip jar is now available in Settings. If you'd like to support development, you can offer a small, medium, or big coffee — it's completely voluntary and unlocks nothing. The app remains fully free and open source. • Search tools discovery: Settings → Web Search now includes a "Load Available Tools" button that fetches the list of search providers configured in your LiteLLM server, so you no longer need to type the tool name manually. The first available tool is auto-selected if your saved name is no longer valid. • Privacy screen (iOS): A new toggle in Settings → Privacy lets you hide app content when switching apps or opening the App Switcher, replacing it with a blurred overlay — just like banking apps. • Reasoning streaming in agent mode: Model thinking tokens (reasoning/thinking content) are now streamed in real time during agent mode, so you can follow along as the model reasons through its response. • Minor bug fixes and improvements for a smoother experience, including better resilience when streaming responses finish with empty content. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. • Share Extension: Share content from any app (Safari, Photos, Files, Telegram, and more) directly into a new conversation. Just tap Share and choose OpenClient. • Drag & Drop: Drag text, images, and PDFs from any other app straight into the chat. Works with Split View, Stage Manager, and Finder on macOS. • Apple Shortcuts: Three new actions (New Chat, Search Chats, and Send File to Chat) are now available in the Shortcuts app and via Siri, so you can automate your workflow however you like. • Help screen: A new Help section in Settings explains how to use the Share Extension, URL scheme, and Shortcuts integration, with example URLs you can copy and try right away. • Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. • Share Extension: Share content from any app (Safari, Photos, Files, Telegram, and more) directly into a new conversation. Just tap Share and choose OpenClient. • Drag & Drop: Drag text, images, and PDFs from any other app straight into the chat. Works with Split View, Stage Manager, and Finder on macOS. • Apple Shortcuts: Three new actions (New Chat, Search Chats, and Send File to Chat) are now available in the Shortcuts app and via Siri, so you can automate your workflow however you like. • Help screen: A new Help section in Settings explains how to use the Share Extension, URL scheme, and Shortcuts integration, with example URLs you can copy and try right away. • Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. · Memory: The app can now remember things about you. Save facts and preferences manually or let the model save them automatically during conversation. Everything is synced via iCloud and injected into every chat so models always know your context. · Model info: Tap the ⓘ button next to any model to see its context window, pricing, provider, and supported capabilities at a glance. · Estimated conversation cost: When pricing data is available, the Model Parameters sheet now shows the estimated cost of your current conversation based on token usage. · Pinch to zoom: You can now pinch to zoom in on images in chat, up to 6×. Double-tap to reset. · The thinking block (for reasoning models) now remembers whether you had it open or closed. · Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've got some great new features for you in this update. · Added a Favourites feature: long-press any message to mark it as a favourite and access all your saved messages instantly from the chat menu. · New Media & Files gallery: browse all images and documents attached in a conversation from a single place, with quick navigation back to the original message. · macOS menu bar companion: access a full chat window directly from the menu bar, without opening the main app. Includes a New Chat button for quick fresh conversations. · The chat options menu now sorts its entries alphabetically based on your device language. · Models that support image generation now correctly display the Image Generation badge. · Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.

Hi there! We've fixed bugs and improved a few things · Improved compatibility with Ollama models, allowing the app to detect their capabilities more reliably even with minimal configuration. · Better organization of model capabilities, now displayed in a clearer and more consistent order. · Fixed issues that could prevent some Ollama models from being correctly recognized. · Resolved connection problems when retrieving model information from certain server setups. · Responses can now continue in the background when you leave the app, with a notification when they are ready or interrupted. · Added notifications to keep you informed when a response finishes while the app is not active. · Improved detection of LiteLLM servers, with helpful feedback if the connected server is not recognized. · Enhanced web search functionality for more accurate and consistent results, including better source display. · Simplified and improved the overall response generation process. · Fixed an issue where responses could be generated twice in some cases. · Fixed problems where web search sources were not being displayed correctly. · Improved compatibility with OpenAI models to prevent request errors. · Fixed issues with quick actions and navigation when launching the app or creating a new chat. · Minor bug fixes and improvements for a smoother experience. Thanks for your continued support and for helping us build the best possible LLM client together. Remember: you can suggest and vote on new features from the Feedback section in settings.