@jfkimmes this does explain something: it seems to be able to invoke tools when it is planning, but then those tools do not get invoked in the final step.
so it uses tools to read files when planning, then fails to use tools when executing.
@ariadne In any case: as long as the final response is generated by your trained model it will never make a valid tool call since there are probably about zero training examples of the necessary JSON structure required by the tool handling in your furry smut (this is an estimate that could be quite the way off knowing the furry community but still)
@ariadne Oh, is that a OpenClaw specific feature where you can specify that reasoning traces are generated by a separate model than the actual response? I'm not really familiar with OpenClaw's internals.
@EC_DIGIT@EC_OSPO, I find it rather ironic that neither your press release, nor this social media post have a clickable link to https://code.europa.eu – a portal that is the actual topic both talk about. Could you perhaps fix this? Thanks in advance!
This update brings optimized audio files for podcasts, an improved channel collaboration experience, a major overhaul of image processing, and much more…
#PeerTube v8.1 is out!This update brings optimized audio files for podcasts, an improved channel collaboration experience, a major overhaul of image processing, and much more…👉 https://joinpeertube.org/news/release-8.1
@EC_DIGIT @EC_OSPO, I find it rather ironic that neither your press release, nor this social media post have a clickable link to https://code.europa.eu – a portal that is the actual topic both talk about. Could you perhaps fix this? Thanks in advance!