karthink

The status of the fix is that I've tried twice to move the directive expansion to the prompt buffer in `gptel-request`, and failed both times because of subtle issues. As...

@aagit wait, I didn't know that `gptel-rewrite-directives-hook` is non-functional. This is different from the above bug report, that the directive expansion happens in the wrong buffer: > Due to a...

Please update and test, the `gptel-rewrite-directive-hook` should now be evaluated in the request buffer, and not in a temporary buffer.

> Is there now a way to runtime detect when a version is fixed? So I can disable the workaround based on that. The only way I can think of...

> How would a not runtime check work? Like scanning the path or something? That > looks a complication. > > I don't get why a gptel-version wouldn't change between...

> @karthink - Do you have any input in how you imagine the workflow to be for this API regarding the GitHub token? > > With the changes made just...

@marcus-lundgren just dropping a note to say this PR remains on my radar -- I just need a longer chunk of time to review it than other PRs since I'm...

If I understand the changes correctly, you can no longer have more than one Github copilot backend defined, since the authentication is now shared across all gh backends? Is this...

> The question is whether gptel can/should support MCP tools when using OpenWebUI as a backend, and if this functionality could be implemented to bridge MCP tools through gptel's existing...

> All I want is to use a LLM (provided by openweb-ui) whereas in gptel I configure MCP servers to which the LLM should have access to. Sorry, I'm not...