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/llm.rs

@@ -50,7 +50,8 @@ fn call_model(agent: &str, model: &str, prompt: &str) -> Result<String, String>
         .map_err(|e| format!("write temp prompt: {}", e))?;
 
     let mut cmd = Command::new("claude");
-    cmd.args(["-p", "--model", model, "--tools", "", "--no-session-persistence"])
+    cmd.args(["-p", "--model", model, "--tools", "", "--no-session-persistence",
+              "--strict-mcp-config"])
         .stdin(fs::File::open(&tmp).map_err(|e| format!("open temp: {}", e))?)
         .env_remove("CLAUDECODE");