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
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.
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"}
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!
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!
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.
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.
Hi, I keep finding that Opus 5 requests fail silently. I put in a fairly long prompt, hit enter, it goes away thinking for awhile, then just stops. No response, no error, no nothing. Refreshing the prompt tends to create the same effect. If I switch to an OpenAi model, it then works. v 2.15.0 (build 84) on macOS 26.5.2
OS version: macOS 26.6 BoltAI app version: 2.15.0 Setapp user: No AI provider & model: Anthropic, Claude (extended thinking on, web_fetch tool enabled) Steps to reproduce: Start an Anthropic chat with the web_fetch server tool enabled. Ask something that makes the model call web_fetch, and let it also emit regular tool_use blocks in the same assistant turn. Continue the conversation for at least one more turn. Error message: messages.1: web_fetch tool use with id srvtoolu_01RYeaAtRGtJzhpnvMWP8ys7 was found without a corresponding web_fetch_tool_result block What's actually wrong: When BoltAI rebuilds the messages array for the follow-up request, the web_fetch_tool_result block belonging to the MOST RECENT server_tool_use is dropped. Earlier web_fetch calls in the same thread are paired correctly — only the latest one loses its result. Once another turn is appended after it, that server_tool_use is a permanent orphan in the history and every subsequent request 400s. The chat is unrecoverable without editing history. Note on the error text: Anthropic reports the wrong index. It says "messages.1" but the id it quotes belongs to a much later assistant message. Match by block id, not by the index in the message. Expected: the web_fetch_tool_result is persisted alongside its server_tool_use and replayed in every subsequent request. Note: the 2.15.0 changelog entry about "Anthropic-powered chats occasionally failing after tool calls when using extended thinking" does not fix this — I'm on 2.15.0 and still hitting it.
The hanging behavior is a known technical issue in the integration between the local client application (the chat interface or terminal wrapper) and the LLM API. It is called a Tool-Call Loop Hang. Here is the step-by-step sequence that causes the freeze: AI Initiates Tool: The user requests a file modification or read. The AI generates a tool call (e.g., mcp_edit_file_6lpu9l) and stops generating text, as required by the API protocol. MCP Server Executes: The local MCP server successfully executes the file edit and returns the result (the diff or file contents) to the client application. The Integration Gap (The Hang): In a fully automated integration, the client application is supposed to immediately feed the tool's output back to the LLM to trigger the next text generation turn. However, in this specific client setup, the application fails to auto-trigger the next turn. It pauses and waits. The Wake-Up: Because the client is waiting for the AI, and the AI is waiting for the client to send the tool results, the interface hangs. When the user types any message (e.g., "are you stuck again?"), it forces the client application to package the entire conversation history—including the pending tool results—and send it to the LLM. This instantly wakes the AI up, resulting in the immediate "AI-OK" response. 𝐇𝐨𝐰 𝐭𝐨 𝐅𝐢𝐱 𝐨𝐫 𝐌𝐢𝐭𝐢𝐠𝐚𝐭𝐞 𝐭𝐡𝐞 𝐈𝐬𝐬𝐮𝐞 Client-Side Configuration (Permanent Fix): The developer of the client application or terminal wrapper must update the execution logic. The client must automatically post the tool output back to the LLM API endpoint to request the next completion turn without waiting for manual user input. User Workaround (Immediate Fix): Whenever a tool call completes (you will see the green tool response block in the interface) and the interface pauses for more than 3 seconds, type a single character (such as a period . or go) and press Enter. This forces the client to send the tool results to the LLM and resumes execution instantly. AI Mitigation (Combining Steps): The AI will minimize sequential tool calls where possible, combining reads or edits into single multi-file operations to reduce the number of turn transitions.
Gemma4 is supposed to be able to read images. But I’m getting Bad request error. Tried in LM studio it is able to generate the markdown of the table with this model.
I have tried to input my Kagi API key in Settings>Plugins>Kagi Search and it will not accept. I have the latest version and have tested on MacOS, both Paid and Setapp, and on the mobile Beta. The error says that Kagi Search API is in Beta but this is no longer true, it is now Public per Kagi support. Desktop screenshot: Mobile screenshot
Bug report: OS version: macOS 26.5, build 25F71 BoltAI app version: BoltAI 2.13.3, build 72 Setapp user: No. I’m using the standalone app installed at /Applications/BoltAI 2.app. AI provider & model: N/A. This is a window/Dock behavior issue and is not related to an AI provider or model. Steps to reproduce: Open BoltAI 2. Go to Settings > General. Enable “Hide Dock icon when last window closes”. Disable “Show menu bar” because I do not want the menu bar icon either. Close all BoltAI windows, including the Settings window. Do not quit the app. BoltAI continues running in the background, but its Dock icon remains visible. I also tried turning “Show menu bar” back on, toggling “Hide Dock icon when last window closes” off and on again, then restarting BoltAI. The Dock icon still remains visible. Expected behavior: After the last BoltAI window is closed, BoltAI should continue running in the background and the Dock icon should disappear. Actual behavior: BoltAI keeps running in the background, no BoltAI windows are open, but the Dock icon still stays visible. Additional diagnostics: The preference appears to be saved correctly: app.hideDockWhenNoWindows = true System Events reports no open BoltAI windows, but NSRunningApplication still reports BoltAI’s activationPolicy as regular, so macOS keeps showing it in the Dock. Error message: No error message.
V1.0 build 27 - very high cpu usage resulting in phone (16e) getting noticeably warm
OS: MacOS Tahoe 26.5 BoltAI V2 I am having several issues with BoltAI because the documentation appears to be outdated. Google web search does not seem to work given that it no longer supports searching the entire web. Next to that, I can't get any models in BoltAI to perform file operations like Codex does, even though the documentation mentions support for both a Shell and an AppleScript plugin. Neither plugins seem to show up anywhere, no matter which model, cloud or local. Also, the documentation mentions setting a path variable in the settings pane, but I can't find that anywhere either.
When connecting through “Google AI” AI Providers and when selecting any Deep Research model there is an error: Error This model only supports Interactions API. I have all MCPs and plugins disabled… all other Gemini models work. https://ai.google.dev/gemini-api/docs/interactions/deep-research i guess you would need to implement an additional api endpoint for this to work?
Another problem which also exists for PDF Pals, is that after a few days running on my Mac, the app switch from other app to BoltAI 2 GUI is slow. There is a significant delay between the action of switch (e.g., by command + Tab) and the BoltAI 2's GUI shows up.
Your OS version: Sequoia 15.5 Your BoltAI app version. 2.8.0 (build 55) Are you a Setapp user. No. The AI provider & model you’re using. Google Gemini 3.0 Flash Preview on Google Vertex via OpenRouter. Steps to reproduce the issue. Create an agent and in the agent settings specify Google Gemini 3.0 Flash Preview as the model and set Thinking tokens budget to be non-zero. Create a new chat, set the new agent as the active profile then check the LLM Parameters section in the right sidebar. The thinking budget has not been applied. The error message. No error message.
First of all, I want to thank you for integrating Claude Code and the Gemini CLI into Bolt AI. This helps me immensely because I have a Pro subscription, so now I don't need to spend extra API credits. This is truly awesome! That said, I’ve run into a bug. For some reason, the Gemini CLI within Bolt gets the current date wrong, whereas it works perfectly fine in my terminal. This leads to grounding issues, particularly when the model needs to search the internet. It seems like the local environment context isn't being passed through correctly. Perhaps you need to explicitly set an environment variable or inject the date context in your implementation? I’m attaching side-by-side screenshots of the same question asked in Bolt AI and my terminal to show the difference. See here: https://share.cleanshot.com/kjVdFLtn
Hi, over the past few days, and still with the 2.6.2 release (which I just installed, hoping it might fixed the issue, but alas no), responses are now truncated very quickly. Example: Analysis: Quarterly Review Template (FY26 Q1) Lens used: Template Quality Assessment + Messaging-A/B + Inherent Simplicity Executive Summary This is a template deck, not a completed review. Approximately 90% of the content consists of placeholder text ("x", "Example", "Comment", "Project name"). The deck provides structure …and then it gets truncated. This has just started happening in the last day or two. I can say, “continue” and it will go a little bit farther but then truncate again.
See title; I’m unable to record any shortcuts via the settings. If I try to change a preset shortcut, I end up having to reset my settings to get it back. I’ve already given BoltAI all the system permissions it needs. This could totally be a “my machine only” issue caused by one of my apps - has anyone else run into this?