Add Ollama provider, portable memory, cultivation digest, refugee importer, GLM-OCR spike

- P0: unified soul binary with engram_node_full fix, read-back-verify, search fix
- P0: move API keys from plaintext plists to macOS Keychain
- P0: fix MCP backend URL (port 8742 → 7770)
- P1.6: memory-export/import scripts (AES-256-CBC, versioned .neuronmem format)
- P1.7: nightly cultivation digest with sharpness metric (launchd at 23:55)
- P2.10: Ollama provider in agentic loop (SOUL_LLM_PROVIDER=ollama)
- P3.12: refugee importer for ChatGPT/Screenpipe/generic formats
- P3.13: GLM-OCR spike — SHIP IT (mlx-vlm, 1.59GB, photo-to-memory.sh)

neuron-api.el

@@ -94,7 +94,9 @@ fn api_or_empty(s: String) -> String {
 fn api_persisted(id: String) -> Bool {
     if str_eq(id, "") { return false }
     let node: String = engram_get_node_json(id)
-    return !str_eq(node, "") && !str_eq(node, "null")
+    // engram_get_node_json returns "{}" (empty object) when node is not found — not "" or "null".
+    // Check all three to guard against any runtime variation.
+    return !str_eq(node, "") && !str_eq(node, "null") && !str_eq(node, "{}")
 }
 
 // api_not_persisted — standard error for a write that did not read back.