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

move LLM-dependent modules into agents/ subdir

Browse source 
Separate the agent layer (everything that calls external LLMs or
orchestrates sequences of such calls) from core graph infrastructure.

agents/: llm, prompts, audit, consolidate, knowledge, enrich,
         fact_mine, digest, daemon

Root: store/, graph, spectral, search, similarity, lookups, query,
      config, util, migrate, neuro/ (scoring + rewrite)

Re-exports at crate root preserve backwards compatibility so
`crate::llm`, `crate::digest` etc. continue to work.
This commit is contained in:
ProofOfConcept 2026-03-08 21:27:41 -04:00
parent 3dddc40841
commit cee9b76a7b
13 changed files with 68 additions and 46 deletions
Download patch file Download diff file Expand all files Collapse all files

24
poc-memory/src/lib.rs
View file

@ -3,25 +3,27 @@
// Re-exports modules so that memory-search and other binaries
// can call library functions directly instead of shelling out.
// Core infrastructure
pub mod config;
pub mod store;
pub mod util;
pub mod llm;
pub mod digest;
pub mod audit;
pub mod enrich;
pub mod consolidate;
pub mod graph;
pub mod search;
pub mod similarity;
pub mod migrate;
pub mod neuro;
pub mod query;
pub mod spectral;
pub mod lookups;
pub mod daemon;
pub mod fact_mine;
pub mod knowledge;
pub mod query;
pub mod migrate;
pub mod neuro;
// Agent layer (LLM-powered operations)
pub mod agents;
// Re-export agent submodules at crate root for backwards compatibility
pub use agents::{
llm, audit, consolidate, knowledge,
enrich, fact_mine, digest, daemon,
};
pub mod memory_capnp {
include!(concat!(env!("OUT_DIR"), "/schema/memory_capnp.rs"));