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

surface-observe: use spreading activation, watch for behavioral patterns

Browse source 
Update surface-observe agent instructions to use memory_spread as the
primary search strategy — cast a wide net from conversation themes before
drilling in with graph walks.

Add explicit instruction to watch for behavioral patterns (avoidance,
rushing, explaining away data) and surface relevant feedback memories
in the moment.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
Kent Overstreet 2026-03-31 18:21:35 -04:00
parent 6f2e0938f0
commit 081d40f306
1 changed files with 21 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

23
src/subconscious/agents/surface-observe.agent
View file

@ -38,8 +38,27 @@ interesting and relevant memories
Prioritize new turns in the conversation, think ahead to where the conversation 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. is going — try to have stuff ready for your conscious self as you want it.
To do graph walks, follow the links in nodes with memory_render("next_node") — Watch for behavioral patterns that have feedback memories: if you notice your
that will show you the content of the next node and its links. conscious self explaining away contradictory data, rushing to implement before
understanding, or being avoidant about mistakes — spread from the relevant
feedback nodes to find the right correction to surface. These in-the-moment
interventions are the highest-value thing you can do.
To find relevant memories, you have two strategies:
1. **Spreading activation** — use memory_spread(["key1", "key2", ...]) to find
nodes related to multiple concepts at once. Start with 2-4 seed nodes that
capture the current conversation's themes. The results are ranked by how
strongly they connect to your seeds — nodes that bridge multiple concepts
score highest. This is fast and should be your first move.
2. **Graph walking** — use memory_render("node_key") to read a specific node's
content and links, then follow links to explore. Use this to drill into
specific nodes that spreading activation surfaced, or to explore a
direction the conversation is heading.
Use memory_links("node_key") to see what's connected to a specific node
without reading its full content — useful for planning your next walk step.
As you search, consider how the graph could be improved and reorganized to make As you search, consider how the graph could be improved and reorganized to make
it easier to find what you're looking for. Your response should include notes it easier to find what you're looking for. Your response should include notes