Bug Reports (DISCONTINUED)

Usually when configuring MCP servers you set Streamable HTTP or SSE in the "type" parameter, e.g: { "mcpServers": { "crawl4ai-sse" : { "type": "sse", "url" : "https://crawl4ai.my.domain/mcp/sse" }, "crawl4ai-http" : { "type": "streamableHttp", "url" : "https://crawl4ai.my.domain/mcp/http" } } But when providing either of these Bolt fails to save the config with the error "Invalid JSON format: The data couldn't be read because it is missing." I'm assuming either bolt is using a different configuration parameter for the transport type or only supports local servers running in STDIO mode? If it is the latter - I'd like to request streamable HTTP and SSE transports (although streamable HTTP will replace SSE-only mode in a future MCP specification) as the majority of MCP servers I consume these days are networked.

Anthropic (Claude 3.5/3.7) consistently exceed token rate limits when using search APIs (Google, Brave, Perplexity, + possibly others). Issue persists for 3-6 months, seems to affect only Anthropic models, and lately made the service practically unusable. Details: macOS 15.4.1 BoltAI v1.35.1 (Setapp Version)

Issue: When I use a context command, I get a cut-off AI action indicator that looks like 'Thinkin...'. The ellipsis '...' should be replaced with the letter 'g'. Reproduction: I use a context AI command I see a broken indicator (see attached screenshot)

Steps to reproduce: Set a key binding to global shortcut "Activate Bolt AI Chat" Open multiple new chat windows Switch to another app Press the key binding set for "Activate Bolt AI Chat"- works perfectly: activates the latest chat window Press the key binding again - works perfectly: sends the activated window back Press the key binding again - buggy: now all BoltAI windows come to front (unlike step 4) Expected behaviour: I think pressing the keybinding should simply toggle between step "activating the latest chat window" and sending that window back (step 4 and step 5 respectively) and step 6 should never arise Device Details: MacBook Air M1 8GB MacOS Sequoia 15.2

Occasionally, artifacts appear in the sidebar (see screenshot).

Only "Open in New Window" and "Rename Chat" show up in the context menu of items located within a folder/project. I would like to see the rest of the context menu items such as Archive Chat, Delete Chat, Hide Chat, Move To, and even Pin Chat which would pin the chat to the top of the project/folder.

Your (ugly 😅) competitor, TypingMind, has a nice feature to share conversations, as seen in the screenshot below. Creating a public link and making it accessible for non-users would make easy to, well, share the output of a specific conversation without manually doing so.

This is a mix of a bug and a feature request. When I start a chat in a language other than English, it always responds to me in English (tested only with Perplexity models). I know that I selected "Answer in Language" to "Default," but wouldn't it be more useful if "Default" is the language of the first prompt itself?

Often when I request a model to output a table, BoltAI does not render the table and provides raw markdown instead. Cause: I assume this happens because Bolt only renders when the table starts with an empty line. When output starts with a title (like on the screenshot), the table is broken. Suggestion: Render table despite markdown starting on the same line with a title.

Dragging and dropping folders in the sidebar to reorder them results—not every time, but perhaps every second or third time—in a crash. BoltAI version: 1.27.0 (build 121) macOS version: Sequoia 15.1 Machine: Intel Core i9, 27" iMac (2019), 72GB RAM