Encrypt Cloud Sync bundles and clarify privacy

.claude-plugin/marketplace.json

@@ -9,7 +9,7 @@
       "name": "engraphis-memory",
       "source": "./",
       "description": "Discipline for giving agents durable, scoped, explainable memory across sessions and repos with the Engraphis MCP tools.",
-      "version": "1.2.0"
+      "version": "1.2.1"
     }
   ]
 }

.claude-plugin/plugin.json

@@ -1,6 +1,6 @@
 {
   "name": "engraphis-memory",
-  "version": "1.2.0",
+  "version": "1.2.1",
   "description": "Give agents durable, scoped, explainable memory across sessions and repos via the Engraphis MCP tools. Use when you learn something worth keeping, need prior context before acting, or ask why/how a fact changed. Covers remember/recall, why/timeline, forget/pin/correct, sessions, and code search.",
   "author": {
     "name": "The Engraphis Authors",

.claude-plugin/skill-assets.sha256

@@ -1,6 +1,6 @@
-81840a090ae1b8b14fff4eac3bf7ff1832760f4806c510070b78687cb15a0f99  .claude-plugin/marketplace.json
-db1b72e67e25bc29e3220d75ff5ab03a0ab954ebdbb93dd74d715ca509317a0c  .claude-plugin/plugin.json
-656caf07c9064b219eb974e018180e6a7a88f2c058fb1b1c6a8a36074d67e9cc  skills/engraphis-memory/SKILL.md
-9751b6e7310151c14e6bb7f5d683943a53a95951ff207876053d082e65eecfd5  skills/engraphis-memory/references/CONVENTIONS.md
-45f4b4ad9dbfd39f2b377083d9b3eec5eed7cba7cb8fa139e3f420bdd6105343  skills/engraphis-memory/references/SCOPING.md
-dc83c48d1a57122e7b58da29d32ae3b8ebd4ffff0b6d0570a8833e920e365109  skills/engraphis-memory/references/TOOLS.md
+3fb76735c2b1d2fa0b70ba9554d6c76a1bfae0edef8a5632be18af8fb15447e1  .claude-plugin/marketplace.json
+a837836347bdb17330292c071dc2908527435e9f7defa21d6ab4f4f91acaffde  .claude-plugin/plugin.json
+696fe737e83a8d073c8dac77704ada7261332ede2527b4c4d426b1e657e034da  skills/engraphis-memory/SKILL.md
+7ee71fb5ff9bd2b02f50b3ee8dc62f390a0e1bcd849a55739c4a376ac03d9784  skills/engraphis-memory/references/CONVENTIONS.md
+8aafd2daba872be38ec8d42377e886d795d8941bf7c6a39795937ffc1d1f0d88  skills/engraphis-memory/references/SCOPING.md
+4c1478453237643e7b4ee2ab4484b9fea8fd759f19f9a5fbf9eeda216d1d6f1a  skills/engraphis-memory/references/TOOLS.md

BENCHMARKS.md

@@ -9,30 +9,30 @@ been written; when this and the code disagree, the code wins (CLAUDE.md).
 Engraphis's eval harness scores **retrieval**, not end-to-end QA. That distinction is deliberate
 and stated everywhere the numbers appear (`eval/external.py`).
 
-- **Correctness gate** — `eval/harness.py` over `eval/datasets/sample.jsonl` and
+- **Correctness gate**: `eval/harness.py` over `eval/datasets/sample.jsonl` and
   `codemem.jsonl` (conflict resolution) and `graph_multihop.jsonl` (multi-hop graph recall).
   Runs on the deterministic embedder, so it is a plumbing/regression floor, not a public
   performance claim. This is the gate CI enforces.
-- **Ablation** — `eval/ablation.py`: vector-only vs. 1-hop graph vs. Personalized-PageRank arm,
+- **Ablation**: `eval/ablation.py`: vector-only vs. 1-hop graph vs. Personalized-PageRank arm,
   to show the graph arm actually earns its place.
-- **External benchmarks** — `eval/external.py` loads **LoCoMo** and **LongMemEval** and pushes
+- **External benchmarks**: `eval/external.py` loads **LoCoMo** and **LongMemEval** and pushes
   them through the *real* `MemoryEngine` write path (conflict resolution + evolution) and hybrid
   recall with a real sentence-transformers embedder. It reports `recall_at_k` / `hit_at_k` /
-  `answer_token_recall` — i.e. *did the evidence come back*, not *did an LLM answer correctly*.
+  `answer_token_recall`: i.e. *did the evidence come back*, not *did an LLM answer correctly*.
   It retains source categories and abstention/no-evidence questions as explicit exclusions from
   retrieval-only aggregates rather than silently dropping them. `eval.longmemeval_v2` is a local,
   text-only adapter for the official LongMemEval-V2 `insert(trajectory)` / `query(query,
   query_image=None)` memory interface; it does not download data or call a model.
-- **Grounded** — `eval/grounded.py`: answerable → cite, off-topic → abstain.
-- **Chunking (quality per token)** — `eval/chunking_eval.py` over `eval/datasets/longdoc.jsonl`
-  ingests a multi-topic corpus twice — one memory per document (`whole`) vs. sub-file
-  `ChunkingExtractor` (`chunked`) — and queries both through the real recall pipeline. This is
+- **Grounded**: `eval/grounded.py`: answerable → cite, off-topic → abstain.
+- **Chunking (quality per token)**: `eval/chunking_eval.py` over `eval/datasets/longdoc.jsonl`
+  ingests a multi-topic corpus twice: once as one memory per document (`whole`) and once with
+  sub-file `ChunkingExtractor` (`chunked`), then queries both through the real recall pipeline. This is
   the first cut of the context-reduction metric (item 3 below). On the deterministic embedder:
   **recall@5 1.000 for both, at ~73% fewer context tokens (809 → 219) and ~4× smaller
   tokens-to-evidence (162 → 42).** Pass `--embed-model sentence-transformers/all-MiniLM-L6-v2`
   for a real retrieval number (recall should then favour chunked on larger corpora, not just
   tie).
-- **Full-pipeline latency + quality** — `eval/performance.py` times the shipped semantic +
+- **Full-pipeline latency + quality**: `eval/performance.py` times the shipped semantic +
   lexical + graph + fusion + scoring + rerank + packing path after warmup, with reinforcement
   disabled so repeated measurements do not mutate their corpus. It reports p50/p95/p99 latency,
   retrieval quality, and packed context tokens in one JSON-safe schema. `--filler-memories`