move LLM-dependent modules into agents/ subdir

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.

poc-memory/src/neuro/mod.rs

@@ -5,22 +5,17 @@
 //   rewrite  — graph topology mutations: differentiation, closure, linking
 
 mod scoring;
-mod prompts;
 mod rewrite;
 
-// Re-export public API so `neuro::` paths continue to work.
-
 pub use scoring::{
-    replay_queue, detect_interference,
+    ReplayItem,
+    consolidation_priority,
+    replay_queue, replay_queue_with_graph,
+    detect_interference,
     consolidation_plan, format_plan,
     daily_check,
 };
 
-pub use prompts::{
-    load_prompt,
-    consolidation_batch, agent_prompt,
-};
-
 pub use rewrite::{
     refine_target, LinkMove,
     differentiate_hub,