This is likely a separate tool, but I suspect it is trivial to build given the framework you've set up...
What I most want is something that notices if Claude has been thinking for more than say 30 seconds, and if so sends me a slack message when the output is finished and ready to read.
Given that Claude is often thinking for 30 minutes, I context switch onto something else, and wish there were a way to get a notification so it isn't sitting idle waiting for me for ten minutes (or an hour, as sometimes happens)
You've hit the nail on the head of one of the main motivators of this project! I always context switch and miss when its done its task or sometimes forget completely..
So essentially at present when you setup TalkiTo with a Slack bot (instructions are shown by running `talkito --setup-slack`) it will do this its just its sending all the output to slack not just the final completion. I have verbosity levels and I could try tweaking them so that -verbosity 0 essentially does what you want ie filter everything except for prompts to the user. If you put in an issue on GitHub I'll get to it!
Yeah that sounds reasonable. I've been thinking about how to make it more modular. I'll make it so that base TalkiTo doesn't need any heavy libraries.
EDIT: also to be clear whisper doesn't run or even download the model unless it's selected and the user confirms the DL. This can be configured. Google cloud has a free ASR option and ASR can be switched off completely.
This is likely a separate tool, but I suspect it is trivial to build given the framework you've set up...
What I most want is something that notices if Claude has been thinking for more than say 30 seconds, and if so sends me a slack message when the output is finished and ready to read.
Given that Claude is often thinking for 30 minutes, I context switch onto something else, and wish there were a way to get a notification so it isn't sitting idle waiting for me for ten minutes (or an hour, as sometimes happens)
You've hit the nail on the head of one of the main motivators of this project! I always context switch and miss when its done its task or sometimes forget completely..
So essentially at present when you setup TalkiTo with a Slack bot (instructions are shown by running `talkito --setup-slack`) it will do this its just its sending all the output to slack not just the final completion. I have verbosity levels and I could try tweaking them so that -verbosity 0 essentially does what you want ie filter everything except for prompts to the user. If you put in an issue on GitHub I'll get to it!
Would you consider a lightweight app that just does notification?
Installing and running Whisper locally just to get notifications seems like more resource consumption than some of us are looking for.
Some will want one, some will want both.
Yeah that sounds reasonable. I've been thinking about how to make it more modular. I'll make it so that base TalkiTo doesn't need any heavy libraries.
EDIT: also to be clear whisper doesn't run or even download the model unless it's selected and the user confirms the DL. This can be configured. Google cloud has a free ASR option and ASR can be switched off completely.