split agent: parallel execution, agent-driven edges, no MCP overhead

- Refactor split from serial batch to independent per-node tasks
  (run-agent split N spawns N parallel tasks, gated by llm_concurrency)
- Replace cosine similarity edge inheritance with agent-assigned
  neighbors in the plan JSON — the LLM already understands the
  semantic relationships, no need to approximate with bag-of-words
- Add --strict-mcp-config to claude CLI calls to skip MCP server
  startup (saves ~5s per call)
- Remove hardcoded 2000-char split threshold — let the agent decide
  what's worth splitting
- Reload store before mutations to handle concurrent split races

poc-memory/src/agents/prompts.rs

@@ -317,7 +317,6 @@ pub fn split_candidates(store: &Store) -> Vec<String> {
         .filter(|(key, node)| {
             !key.starts_with('_')
                 && !node.deleted
-                && node.content.len() > 2000
                 && matches!(node.node_type, crate::store::NodeType::Semantic)
         })
         .map(|(k, n)| (k.as_str(), n.content.len()))