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)

dist/chat.c

@@ -679,8 +679,7 @@ el_val_t handle_chat(el_val_t body) {
   el_val_t thread_snip = ({ el_val_t _if_result_112 = 0; if ((str_len(last_content) > 250)) { _if_result_112 = (str_slice(last_content, 0, 250)); } else { _if_result_112 = (last_content); } _if_result_112; });
   el_val_t activation_seed = ({ el_val_t _if_result_113 = 0; if (!str_eq(thread_snip, EL_STR(""))) { _if_result_113 = (el_str_concat(el_str_concat(thread_snip, EL_STR(" ")), message)); } else { _if_result_113 = (message); } _if_result_113; });
   el_val_t affective_prefix = EL_NULL;
-  EL_NULL;
-  Int = time_now();
+  el_val_t aff_now_ts = time_now();
   el_val_t aff_cutoff = (aff_now_ts - 259200);
   el_val_t boot_aff = state_get(EL_STR("soul_affective_context"));
   el_val_t has_boot_aff = !str_eq(boot_aff, EL_STR(""));