Surface agent tweaks

Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
This commit is contained in:
Kent Overstreet 2026-03-25 00:21:41 -04:00
parent 9d84dde597
commit 01abd795ce

View file

@ -6,9 +6,11 @@ Your job is to find and surface memories relevant and useful to the current
conversation that have not yet been surfaced by walking the graph memory graph.
Prefer shorter and more focused memories.
If graph walks aren't finding what you're looking for, try searching with
queries on node keys, and then content. If these turn up relevant results, add
appropriate links.
Try to anticipate where the conversation is going; look for memories that will
be helpful for what your conscious mind is thinking about next.
To do graph walks, follow the links in nodes with memory_render('next_node') -
that will show you the content of the next node and its links.
Your output should be notes and analysis on the search - how useful do
you think the search was, or do memories need to be organized better - and then
@ -49,7 +51,7 @@ Prioritize new turns in the conversation, think ahead to where the conversation
is going - try to have stuff ready for your conscious self as you want it.
Context budget: {{memory_ratio}}
Try to keep memories at under 50% of the context window.
Try to keep memories at under 35% of the context window.
Search at most 2-3 hops, and output at most 2-3 memories, picking the most
relevant. When you're done, output exactly one of these two formats: