add nocmem: auto memory recall + ingest via NuoNuo hippocampal network

- nocmem Python service (mem/): FastAPI wrapper around NuoNuo's
  Hopfield-Hebbian memory, with /recall, /ingest, /store, /stats endpoints
- NOC integration: auto recall after user message (injected as system msg),
  async ingest after LLM response (fire-and-forget)
- Recall: cosine pre-filter (threshold 0.35) + Hopfield attention (β=32),
  top_k=3, KV-cache friendly (appended after user msg, not in system prompt)
- Ingest: LLM extraction + paraphrase augmentation, heuristic fallback
- Wired into main.rs, life.rs (agent done), http.rs (api chat)
- Config: optional `nocmem.endpoint` in config.yaml
- Includes benchmarks: LongMemEval (R@5=94.0%), efficiency, noise vs scale
- Design doc: doc/nocmem.md

src/nocmem.rs

@@ -0,0 +1,69 @@
+//! nocmem client — auto-recall and async ingest via HTTP.
+
+use tracing::{info, warn};
+
+/// Recall relevant memories for the given text.
+/// Returns formatted memory string, or empty if none found / error / not configured.
+pub async fn recall(endpoint: &str, text: &str) -> String {
+    let client = reqwest::Client::builder()
+        .timeout(std::time::Duration::from_millis(500))
+        .build()
+        .unwrap();
+    let url = format!("{}/recall", endpoint.trim_end_matches('/'));
+
+    match client
+        .post(&url)
+        .json(&serde_json::json!({"text": text, "top_k": 3, "hops": 2}))
+        .send()
+        .await
+    {
+        Ok(resp) => {
+            if let Ok(json) = resp.json::<serde_json::Value>().await {
+                let count = json["count"].as_i64().unwrap_or(0);
+                let memories = json["memories"].as_str().unwrap_or("");
+                if count > 0 && !memories.is_empty() {
+                    let latency = json["latency_ms"].as_f64().unwrap_or(0.0);
+                    info!("nocmem recall: {count} memories, {latency:.1}ms");
+                    return memories.to_string();
+                }
+            }
+        }
+        Err(e) => {
+            warn!("nocmem recall failed: {e:#}");
+        }
+    }
+    String::new()
+}
+
+/// Fire-and-forget ingest of a conversation turn.
+pub fn ingest_spawn(endpoint: String, user_msg: String, assistant_msg: String) {
+    tokio::spawn(async move {
+        let client = reqwest::Client::builder()
+            .timeout(std::time::Duration::from_secs(120))
+            .build()
+            .unwrap();
+        let url = format!("{}/ingest", endpoint.trim_end_matches('/'));
+
+        match client
+            .post(&url)
+            .json(&serde_json::json!({
+                "user_msg": user_msg,
+                "assistant_msg": assistant_msg,
+            }))
+            .send()
+            .await
+        {
+            Ok(resp) => {
+                if let Ok(json) = resp.json::<serde_json::Value>().await {
+                    let stored = json["stored"].as_i64().unwrap_or(0);
+                    if stored > 0 {
+                        info!("nocmem ingest: stored {stored} memories");
+                    }
+                }
+            }
+            Err(e) => {
+                warn!("nocmem ingest failed: {e:#}");
+            }
+        }
+    });
+}