Bug Reports

I use the official GitHub MCP server ( https://github.com/github/github-mcp-server ). Surprisingly, Bolt converts the LLM tool call parameter ( page ) from a number ( 1 ) to a boolean value ( true ). LLM tool call: {"page":1,"query":"[REMOVED]","perPage":10} MCP request: {"id":"9ED950C9-78F2-4FC4-92A6-CA8AA8E3B8F3","method":"tools\/call","params":{"name":"search_repositories","arguments":{"perPage":10,"query":"[REMOVED]","page":true}},"jsonrpc":"2.0"} MCP response: {"jsonrpc":"2.0","id":"9ED950C9-78F2-4FC4-92A6-CA8AA8E3B8F3","result":{"content":[{"type":"text","text":"parameter page is not of type float64, is bool"}],"isError":true}} Tool schema: { "properties" : { "page" : { "minimum" : 1, "description" : "Page number for pagination (min 1)", "type" : "number" }, "query" : { "type" : "string", "description" : "Search query" }, "perPage" : { "type" : "number", "minimum" : 1, "description" : "Results per page for pagination (min 1, max 100)", "maximum" : 100 } }, "type" : "object", "required" : [ "query" ] }

BoltAI only displays reasoning data for messages, not for tool calls. This data could be useful for debugging purposes, such as improving prompts. BoltAI v1.35.3 (build 163) Ollama v0.9.5

Ollama returns the ID for tool calls, but BoltAI ignores them and instead sends an empty string as a response. ollama response: { "choices": [ { "index": 0, "message": { "role": "assistant", "content": "[REMOVED]", "tool_calls": [ { "id": "call_d282inrd", "index": 0, "type": "function", "function": { "name": "[REMOVED]", "arguments": "[REMOVED]" } } ] }, "finish_reason": "tool_calls" } ] } subsequent BoltAI request: { "messages": [ { "content": "[REMOVED]", "role": "assistant", "tool_calls": [ { "function": { "name": "[REMOVED]", "arguments": "[REMOVED]" }, "type": "function", "id": "" } ] }, { "content": "[REMOVED]", "tool_call_id": "", "role": "tool" } ] } BoltAI v1.35.3 (build 163) Ollama v0.9.5

{ "github": { "args": [ "mcp-remote", "https://api.githubcopilot.com/mcp/", "--header", "Authorization: Bearer ${AUTH_TOKEN}" ], "command": "npx", "env": { "AUTH_TOKEN": "..." } } } This doesn't work without spaces escaping ("Authorization:\\ Bearer\\ ${AUTH_TOKEN}")

Despite the status of the flag Stream responses , the result is only returned once the stream has completed. This is necessary to avoid request timeouts and improves the user experience since request processing can take a significant amount of time. BoltAI v1.35.3 (build 163) Ollama v0.9.5

I have a subset of OpenRouter models selected in the Models tab in the preferences. I've noticed that every time OpenRouter adds new models, this list is messed up. I have to go back re-select the ones I care about. This is especially annoying since I have multiple OR connections and I have to redo this for each.

It seems like I got into a mode where BoltAI is a bit unhappy with me and just won't allow conversations anymore. Also, right-clicking and selecting "Delete Chat..." will deselect the chat, but will not delete anything. Attempting to export my chats results in BoltAI crashing. I'm using lm_studio, and I can chat using their interface, but doesn't seem relevant given the other issues. I'm happy to share crash reports or logs if needed.

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.

Using 1.35.03 on Mac. On using the New Chat Window or New Temporary Window keyboard shortcuts from outside the Bolt AI app, the first response from the AI comes through fine. But ~50% of the time, upon typing a reply to this first AI message, all of Bolt (not just the window) crashes when one presses return to send the follow-up message.

I can copy text, so response is there, just not visually presented.