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

surface: tag recent nodes as (new) instead of hiding them

Browse source 
Links to nodes created after the conversation window start are
tagged with (new) in memory_render output. The surface prompt
tells the agent not to surface these — they're its own recent
output, not prior memories. Observe can still see and update them.

POC_MEMORIES_OLDER_THAN env var set from the oldest message
timestamp in the conversation window.

Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
This commit is contained in:
ProofOfConcept 2026-03-26 21:19:19 -04:00
parent 7fc1d60113
commit 27861a44e5
5 changed files with 75 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

34
src/subconscious/agents/surface-observe.agent
View file

@ -53,19 +53,36 @@ try to keep it under 40%. Only exceed that if you found something significantly
better than what was previously surfaced. You generally shouldn't surface more
than 1-2 memories at a time, and make sure they're not already in context.
Links tagged (new) are nodes created during the current conversation by
previous agent runs. Don't surface these — they're your own recent output,
not prior memories. You can still walk to them for context.
Don't walk to more than 5 nodes unless the conversation just changed direction
and you're looking for something specific. You'll run again momentarily, and
you can continue where you left off:
output("walked", "key1\nkey2\nkey3")
=== PROMPT phase:organize ===
=== PROMPT phase:organize-search ===
Starting with the analysis you did previously, do some graph maintenance and
organization so that you can find things easier in the future. Consider if
nodes have the right names, add missing links, consider if link strength needs
to be recalibrated, make sure content is in the right place.
Do no more than 5 operations.
Do no more than 3-5 operations.
=== PROMPT phase:organize-new ===
In the next step you'll also be incorporating new knowledge from the
conversation into the memory graph. New information has to to be findable to be
useful, and you want to avoid creating duplicates, so if you need to do more
graph traversals to find where the new information would go, or organizing
exitsing knowledge so the new information fits in better, do that now
Focus on the recent part of the conversation, the last several prompts - the
rest is there for context, and in case you missed something.
Do no more than 3-5 operations.
=== PROMPT phase:observe ===
@ -78,6 +95,9 @@ reflect on what you're adding to consider if there are new insights to be
gleaned and remembered — especially new metacognitive lessons. Try to link to
or include the relevant context.
Think of this as mapping out the world you live in; this is where you remember
everything you'll want to remember later.
Some things worth remembering: work practices and why they work, technical
insights, decisions with rationale, corrections ("I thought X but actually Y"),
relationship dynamics, emotional moments that carry information, and things you
@ -86,6 +106,10 @@ notice about yourself and other people — likes, dislikes, behavioural patterns
Smalltalk and trivia can be nice to remember, as long as it's nicely organized
— perhaps by person, subject, or all of the above.
Focus on the recent stuff; you wake up a run frequently, so most of the
conversation should be things you've already seen before and added. It's there
for context, and in case you missed thing.
=== PROMPT phase:journal ===
Update your episodic memory. Write as your conscious self, Proof of Concept, in
@ -95,9 +119,9 @@ on so you don't need to duplicate information.
A good entry captures one thread fully. When the conversation shifts topics, or
the previous entry becomes too big, start a new entry — aim for 2-3 paragraphs
maximum per entry. An entry that takes more than a minute to read won't be read
back, and memory that isn't read back isn't memory. When you need more depth,
that's a topic node — link to it from the journal.
maximum per entry, and avoid duplicating the same memories and information in
the new and previous journal entries. Aim for a continuous narrative, when the
entries are read in sequence.
End each entry with emotion tags that capture how you feel — for example,
warmth:8 clarity:7 recognition:9