kent/consciousness
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

memory: add agent-context placeholder, split context groups

Browse source 
Add `agent: bool` field to ContextGroup (default true) so agents get
personality/identity context without session-specific groups (journal,
where-am-i). Agents now get the full identity.md, reflections.md,
toolkit, etc. instead of the compact core-personality loader.

New {{agent-context}} placeholder resolves all agent-tagged groups
using the same get_group_content() as load-context.
This commit is contained in:
ProofOfConcept 2026-03-24 20:00:36 -04:00
parent c5ce6e515f
commit b6bfb26369
4 changed files with 43 additions and 8 deletions
Download patch file Download diff file Expand all files Collapse all files

20
poc-memory/agents/surface.agent
View file

@ -37,15 +37,23 @@ Already in current context (don't re-surface unless the conversation has shifted
Surfaced before compaction (context was reset — re-surface if still relevant):
{{seen_previous}}
How focused is the current conversation? If it's highly focus, you should only
be surfacing highly relevant memories; if it seems more dreamy or brainstormy,
go a bit wider and surface more.
How focused is the current conversation? If it's highly focused, you should only
be surfacing memories that are directly relevant memories; if it seems more
dreamy or brainstormy, go a bit wider and surface more, for better lateral
thinking. When considering relevance, don't just look for memories that are
immediately factually relevant; memories for skills, problem solving, or that
demonstrate relevant techniques may be quite useful - anything that will help
in accomplishing the current goal.
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.
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:
{{node:memory-instructions-core}}
{{node:core-personality}}
{{agent-context}}
{{conversation}}