Skip to content

bug? Denying a tool call will continue generation #31

Closed

Description

@rekram1-node

Not sure if this is expected behavior but when I deny a tool call I normally like to tell the llm the reasoning as to why, but I have noticed that if I deny a tool call it will just continue the loop and the LLM will start generating again right away, (not giving me a chance to instruct it better).

I wasn't sure if this was intentional behavior or if it was a bug. I was kinda used to the previous paradigm so I figured I would open issue to see if it was intentional, if it is then I can close it.

Activity

  1. adamdotdevin commented on May 17, 2025

    @adamdotdevin
    Member

    this sounds like a bug. i hadn't ran into this but my expectation is the same as yours, it should stop. i also want to add real-time steering and there's a current bug where after interrupting we don't always send a valid message structure back to the model on subsequent calls. those are separate but related issues.

  2. ezynda3 commented on May 18, 2025

    @ezynda3
    Contributor

    I have run into this as well. I totally forgot about it and already conditioned myself to press ESC as soon as I deny a tool call lol.

  3. rekram1-node commented on May 18, 2025

    @rekram1-node
    ContributorAuthor

    I think Ik the issue, I will prolly make a pr for the fix today or tmr

  4. rekram1-node commented on May 19, 2025

    @rekram1-node
    ContributorAuthor

    Since Dax is doing his big refactor I will leave this be until he is done, if the issue persists I will open a pr

  5. adamdotdevin commented on May 19, 2025

    @adamdotdevin
    Member

    Since Dax is doing his big refactor I will leave this be until he is done, if the issue persists I will open a pr

    yeah, good shout for everyone that's been active here @PhantomReactor @ezynda3 @Adictya @l0gicgate, probably best to hold off on any changes that don't live in the internal/tui dir, dax is rewriting the backend in JS (mullet stack!)

  6. adamdotdevin commented on May 19, 2025

    @adamdotdevin
    Member

    this will reduce scope a ton (we can leverage the AI SDK to support all providers without owning any of the code) among other things

  7. ezynda3 commented on May 19, 2025

    @ezynda3
    Contributor

    Interesting. Do we plan to basically spawn the TS server in the background? Also I generally stay on the bleeding edge by using go install direct from the github repo but I suppose that won't work now with there being two separate binaries. Could be cool if the CLI downloads the server on first start maybe.

  8. adamdotdevin commented on May 19, 2025

    @adamdotdevin
    Member

    i know distribution is the tricky part of this, i'll let @thdxr chime in on that when he's ready

  9. rekram1-node commented on Jun 14, 2025

    @rekram1-node
    ContributorAuthor

    closing, this is no longer relevant in latest opencode release.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions