Skip to main content

Help me improve BoltAI

For a bug report, please include the following information:

  • Your OS version.

  • Your BoltAI app version.

  • Are you a Setapp user.

  • The AI provider & model you’re using.

  • Steps to reproduce the issue.

  • The error message

Sign in with ChatGPT

Support Sign in with ChatGPT for OpenAI models so user can use his subscription

Make custom URI/URL scheme links clickable

Right now, if an LLM provides a link to a web site via https:// I can click on that to open the site. However, I cannot click on message:// links to open messages in the Mac Mail app. There’s also a comparable link to open notes in Mac Notes app. Furthermore, I have a number of custom URI/URL schemes set up on my Mac, and those aren’t clickable either. It would be great to have all URI/URL schemes :// rendered so that they are clickable. This could be a preference setting if people don’t want everything clickable.

In Progress

Tool selection keeps resetting

BoltAI: 3.1.0 (build 304) OS: Version 27.2.1 (Build 26B8132) App architecture: arm64 Distribution: Standalone Device ID: macos-63451a802fcf117ff578933b5c9bb4a4418e15cb01ae316711c6d2d86c3b9d6f License: Licensed My tool selections keep resetting themselves. It is repeatedly happening in multiple chats and after restarts of BoltAI. I have started new chats with different providers and same issue occurs. I will have a set of tools selected then at some point in the chat I will have a failure to search web / access a file. When I check the tool selection, all selections have cleared themselves. This is on my main Mac machine. I do have BoltAI running on two other iOS devices so not sure if a sync issue is overwriting them.

Better Chat Attachment Management – Bulk Selection, Sorting and Deletion

Hello Daniel, I'd like to suggest an improvement to how attachments are managed within individual chats. Currently, attachments remain in the chat unless you manually remove them, one by one. This becomes quite inconvenient in long-running conversations where I frequently attach screenshots, images, documents, CSV files and other materials. Sometimes I can end up with dozens or even hundreds of attachments in a single chat. Removing them individually is extremely time-consuming. My suggestions: 1. Bulk selection and deletion Allow users to select multiple attachments at once, with options such as Select All, multi-select and bulk delete. 2. Sorting options Allow attachments to be sorted by: Estimated token usage (largest to smallest). Date added (oldest to newest / newest to oldest). File type. File size. 3. A dedicated attachment manager Instead of having attachments displayed as a simple list, it would be useful to have a folder-like interface where users can browse, filter, sort, select and manage all attachments belonging to a particular chat. Why is this important? As I understand it, attachments associated with messages included in the conversation context are sent to the model again with subsequent requests. For users working with long conversations and frequently attaching images or documents, being able to identify and remove unnecessary attachments in bulk would make a considerable difference. Thanks again for your continued work on BoltAI!

Google Vertex rejects "modified" thinking blocks on Haiku 5.5 call

Error OpenRouter returned this error: [Google] {"type":"error","error":{"type":"invalid_request_error","message":"messages.5.content.1: thinking or redacted_thinking blocks in the latest assistant message cannot be modified. These blocks must remain as they were in the original response."},"request_id":"req_vrtx_011Ch6obiLZEGL17ThpMEvNo"}

MattinBug Reports4 days ago

Edit Office docs / GenOffice integration

Aim: Bolt AI agents can edit office docs in folders they can access. This is technically possible already via GenOffice MCP but a native feature (or native integration) would be smoother and easier for most people to use.

Autonomous agent workflows

Ok, so there’s a heap of people out there who don’t have the time or patience to use OpenClaw, but for whom agent workflows would be super useful. To make this achievable, in addition to the excellent multi-agent workflows added in v3, Bolt would need the following features: Workflows can be owned by a project and inherit its folder access. Workflows can have access to tools/MCPs. Workflows can contain agent loops. Workflows can be scheduled. This would be great: enabling more people to access the power of agent workflows in a safe and relatively simple-to-setup manner.

In Progress

Bug: Instant Chat Bar bugs on 3.1

Mac OS Tahoe, Bolt 3.1 Ok, so v3 brings lots of great features, so I don’t want to moan. But it has totally broken my most common daily workflow, which is: Pull up the instant chat bar by shortcut, ask a question, minimize many times to view other windows, then eventually kill the instant chat bar once done. Problems with v3: There is no way that I can find (either by shortcut, or even by cursor) of hiding the instant chat bar in a way that brings it back, chat included. Previously hitting the instant chat bar shortcut did this. Now the only options are Command+H or Command+W: neither work the same way. Taking the best available option and killing instant chat bar chats with Command+W leaves zombie “BoltAI Web Content” processes (in my case literally dozens during a day) of 200mb to 300mb each. You can’t resize the instant chat bar to be smaller; indeed trying to do so actually makes it bigger. The file picker from the instant chat bar never works at selecting a file the first time you try it; you always have to back out and try again. I don’t object in principle to the merging of the instant chat bar and the pop-out chat window, but please don’t lose key functionality while doing so!

MattinBug Reports7 days ago
1

Custom Fonts

This might seem silly, but I REALLY miss the feature in Bolt v1 where the appearance settings let me set a custom font. That setting disappeared with v2. Using the iA Writer monospace fonts made the app feel more like home, and made me excited to use it more. Can we bring this back in v3?? Whether it’s custom fonts just for the chat window, or ideally the entire interface (like Hermes desktop), I would be so freaking happy.

In QA

Major increase in input tokens after the latest update – long-context chats are becoming unusable

Hello Daniel I'm a writer and researcher, and I use BoltAI extensively for working on long-running writing projects. My workflow depends heavily on maintaining a single, very long conversation containing the entire history of a project: details, timelines, research, notes, previous discussions and decisions. I also use a substantial system prompt. I deliberately use Context Policy: All messages because I need the AI to have access to the entire conversation, from the very beginning. This is fundamental to how I work. The problem started after the latest update. I haven't changed my context settings. I still use All messages, and I'm working in the same existing conversation. However, the number of input tokens being sent to the model has increased dramatically. Here are two examples using the same model (GPT-6 Luna) and the same long-running chat: BEFORE THE UPDATE – November 3 Input tokens: 132,670 Cached tokens: 100,735 Output tokens: 965 Estimated cost: $0.004683 AFTER THE UPDATE – November 9 Input tokens: 799,066 Output tokens: 821 Estimated cost: $0.0803 That's approximately 6 times more input tokens for what should be essentially the same conversation context. I also encountered this OpenRouter error: "The endpoint's maximum context length is 1,048,576 tokens. However, you requested about 1,341,308 tokens (1,209,993 of text input, 243 of tool input, 131,072 in the output)." This means that some models that previously worked with my conversations can no longer process them at all. Others can technically handle the request, but the amount of input tokens and the cost have increased enormously. I noticed the recent changelog mentions improvements to how chat history and attachments are sent to models. I suspect something in the way BoltAI now builds, serializes or includes the conversation history has changed. My questions: Has the way BoltAI constructs and sends conversation history changed in the latest update? Could this explain the significant increase in input tokens? Is there a way to restore the previous behaviour or configure how the conversation history is serialized and sent? Is there a way to reduce the token overhead without losing the ability to give the AI access to the entire conversation and the system prompt? What I really need is to preserve the full conversational context while avoiding this massive increase in input tokens. I absolutely rely on BoltAI for this workflow, and until this update it worked extremely well. Unfortunately, the current behaviour makes it increasingly difficult and expensive to continue using it normally. Could you clarify what changed and whether there is a way to address this? Thank you!

3

Keep code block actions visible while scrolling

In long code blocks, the Copy and Save as… buttons are only visible at the top of the block. After scrolling down through the code, I have to scroll all the way back up to use them. Could these actions remain visible while any part of the code block is on screen? For example, the action bar could stick to the top of the chat viewport while scrolling through a long code block. It would be much easier to copy or save long code after reading or reviewing it.

In QA

Current context window usage

The “Usage (Estimated)” section shows input and output tokens, total tokens, and the number of requests. However, these are cumulative: they don’t reset when the chat context is cleared, but keep increasing with each new request. This is useful for tracking overall usage, but it doesn’t show how much of the selected model’s context window is currently occupied by the active chat. Could you add a separate indicator for current context usage? For example: 10% (100K / 1M) Ideally, the indicator would update when the chat context is cleared, condensed, or otherwise changed, as well as when switching models in a chat: showing the new model’s context window size and recalculating usage if possible.

Remote MCP Bug

macOS Sequoia 15.8.2 BoltAI 2.18.4 (build 96) I am not a Setapp user Z.AI (GLM 5.3, GLM 5.3 Flash), OpenAI (GPT 6.1 Terra) Hi! i'm having an issue with remote mcp - i get errors really often. sometimes after an error, i can't even click the regenerate button. the only way out is to restart the app. i never have any issues with the exact same mcp in other apps (tested them at the same time). error message - Request timed out. The server took too long to respond. Please try again.

tngnnjinBug Reports17 days ago
2

Enable tagging chats and filtering by tags

Summary Something I find myself reaching for frequently is the ability to assign custom tags/labels to chats, and to be able to filter the chat list by these tags. As a bonus, it would be nice to have such tags included in markdown chat exports. Problem As chat history grows, finding related conversations across different topics or projects becomes difficult using only keyword search or chronological browsing. Proposed Solution Chat Tagging: Allow assigning one or more tags to a chat (via sidebar context menu, chat settings, or inline header). Tag Filtering: Add a tag filter/selector in the sidebar or search bar to quickly narrow down chats by tag. Markdown Export Integration: BoltAI already uses YAML front matter for permalinks on export. Include the assigned tags directly in the front matter: --- title: macOS App Design permalink: "boltai://chat/..." tags: - SwiftUI - macOS - development --- This would make organizing workflows within the app much cleaner and integrate seamlessly with personal note systems (like Obsidian) upon export.

1

Sync via Apple CloudKit (private iCloud database) as an alternative to BoltAI Cloud

Hi, Thanks for BoltAI. Having the same chats on Mac, iPhone and iPad is great. A question and a suggestion: why not use Apple's CloudKit (https://developer.apple.com/icloud/cloudkit/), i.e. each user's private iCloud database, to sync BoltAI data, instead of or alongside BoltAI Cloud? From the v2 announcement, BoltAI Cloud runs on Supabase with row-level security, and end-to-end encryption covers API keys. That's a sensible design. It still means my conversations, which often contain sensitive personal and work material, are stored in readable form on a third-party server. For a privacy-focused app, that's the part I'm not comfortable with. What CloudKit would bring: Data stays in the user's own iCloud account. BoltAI never stores it, so there's no extra server to trust, secure, breach or be legally compelled to hand over. Real end-to-end encryption. With Advanced Data Protection turned on, CloudKit fields marked as encrypted (CKRecord.encryptedValues) and all CKAssets are end-to-end encrypted, with keys held only on the user's devices. No separate account. The Apple ID already signed in on the device is the identity. Storage counts against the user's iCloud plan rather than a quota you have to host and pay for, which could also lower your infrastructure costs. Native fit. BoltAI runs on Mac, iPhone and iPad, which is exactly CloudKit's ecosystem, and CKSyncEngine (macOS 14 / iOS 17) handles much of the sync plumbing. Thanks!

Chat input does not always receive focus when opened with a keyboard shortcut

Help me improve BoltAI For a bug report, please include the following information: macOS Tahoe 26.6.2 BoltAI 2.18.0 (build 92) I’m not a Setapp user. Openrouter As described below. No error message When I open the chat using my keyboard shortcut (Ctrl + Space), the text input field is not always focused automatically. Sometimes the cursor is already in the input field and I can start typing right away. Other times, the chat window opens but isn’t active, so I have to click the input field with the mouse before I can type. The cursor also behaves inconsistently: when I move it over the text input, it sometimes stays as an arrow instead of changing to the I-beam text cursor. It seems as though the input field may not be responding to mouse hover correctly.

Ability to specify endpoint provider for a model on OpenRouter

A lot of the coding extensions give a UI option to select the API-call-level variable of which provider you want: eg: novita-fp8, deepinfra-fp4, etc. This would be highly useful on Bolt as OpenRouter has the following non-ideal behavior when this variable is not set: 1) Flitting between different providers even with a heavy cache load. Today, four requests went to four different providers in immediate succession. 2) OpenRouter’s autorouting (or even what is possible by manually configuring guardrails) is limited and often leaves you with endpoints that are more expensive or with a worse quantization than is ideal. This is best solved by utilizing the API-call level config OpenRouter allows. This could be implemented with an optional “choose endpoint” in the model configuration, and/or the ability to switch endpoints in the right chat sidebar.

MattinFeature Requests2 months ago

Delete all prior/preceding messages

You can select a message in a chat and delete all subsequent messages. I’d like to have a similar option to delete all prior messages.