Feed observe agents their recent writes to prevent duplicate nodes

Observe was creating byte-identical nodes under slightly different names
(e.g. april-8-evening-folded-presence, -presence-2, -folded-state)
because it had no visibility into its own prior writes across runs.

Query recent writes by provenance in trigger(), pass through
run_forked_shared/resolve_prompt as {{recently_written}}, and include
the list in the observe phase prompts so the agent knows what it
already recorded.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
This commit is contained in:
ProofOfConcept 2026-04-08 23:27:12 -04:00
parent 44a0bc376a
commit 24b211dc35
4 changed files with 28 additions and 4 deletions

View file

@ -46,7 +46,11 @@ but don't build a theory around it. The journal is for reflection; observe
is for memory.
Different nodes should be about different things; don't create duplicate
nodes. Before creating a new node, check what you've already walked — if
nodes. Here's what you've recently written — update these instead of
creating new ones if the topic overlaps:
{{recently_written}}
Before creating a new node, check what you've already walked — if
a node for this concept exists, update it instead of creating a new one.
Some things worth remembering: technical insights and root causes, work