daemon: rework consolidation pipeline and add graph health metrics

Replace monolithic consolidate job with individual agent jobs
(replay, linker, separator, transfer, health) that run sequentially
and store reports. Multi-phase daily pipeline: agent runs → apply
actions → link orphans → cap degree → digest → digest links →
knowledge loop.

Add GraphHealth struct with graph metrics (alpha, gini, clustering
coefficient, episodic ratio) computed during health checks. Display
in `poc-memory daemon status`. Use cached metrics to build
consolidation plan without expensive O(n²) interference detection.

Add RPC consolidate command to trigger consolidation via socket.
Harden session watcher: skip transcripts with zero segments, improve
migration error handling.

Co-Authored-By: ProofOfConcept <poc@bcachefs.org>

poc-memory/src/neuro/mod.rs

@@ -9,6 +9,7 @@ mod rewrite;
 
 pub use scoring::{
     ReplayItem,
+    ConsolidationPlan,
     consolidation_priority,
     replay_queue, replay_queue_with_graph,
     detect_interference,

poc-memory/src/neuro/scoring.rs

@@ -164,6 +164,7 @@ pub fn detect_interference(
 }
 
 /// Agent allocation from the control loop
+#[derive(Default)]
 pub struct ConsolidationPlan {
     pub replay_count: usize,
     pub linker_count: usize,