Skip to content

armgit / ruflo

Public Imported from GitHub
0

🌊 The original agent harness. Deploy intelligent multi-player swarms, coordinate autonomous workflows, and build conversational AI systems. Features adaptive memory, self-learning intelligence, federation, vector RAG integration, and native Claude Code / Codex / Hermes and many more Integrated

chore(ruflo-rag-memory): 0.3.7 so marketplace users receive the #4153 search-path fixes

rb6e28cb02df2
diff --git a/plugins/ruflo-rag-memory/.claude-plugin/plugin.json b/plugins/ruflo-rag-memory/.claude-plugin/plugin.json
index 324b2ab72f..a9c30aabf7 100644
--- a/plugins/ruflo-rag-memory/.claude-plugin/plugin.json
+++ b/plugins/ruflo-rag-memory/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
{
"name": "ruflo-rag-memory",
"description": "RuVector memory with HNSW search, AgentDB, and semantic retrieval. As a mod (ADR-445): a write guard that keeps secrets out of memory, /rag-mod, and a status file the console shows",
- "version": "0.3.6",
+ "version": "0.3.7",
"author": {
"name": "ruvnet",
"url": "https://github.com/ruvnet"
diff --git a/plugins/ruflo-rag-memory/CHANGELOG.md b/plugins/ruflo-rag-memory/CHANGELOG.md
index a5936e2655..db3d20fb91 100644
--- a/plugins/ruflo-rag-memory/CHANGELOG.md
+++ b/plugins/ruflo-rag-memory/CHANGELOG.md
@@ -2,6 +2,9 @@
Newest first. One `## <version> — <date>` heading per version, then `feat:`, `fix:`, `breaking:` and `chore:` bullets (ADR-478). Built from git history; this is the whole history.
+## 0.3.7 — 2026-10-14
+- fix: memory-search, the memory-specialist agent, `/recall` and `/ruflo-memory` no longer tell the model to run `ruvector search --hybrid` / `--graph-rag` (the ruvector CLI takes a database path and a `--vector` JSON array, not a text query); they use `memory search --type hybrid` and `--smart`, say plainly that this plugin has no text-query Graph RAG, and single-quote the query as untrusted shell input (#4153, thanks @rudycelekli for the PR and @ronmikailov for the report)
+
## 0.3.6 — 2026-10-12
- fix: the shared text screen now catches `.env` and e-mailed credentials, no longer flags a model's token talk (`--max-tokens`, `/oauth/token`, "token usage"), and no longer flags values that only name where a secret lives (`./service-account.json`, `--set-secrets=NAME=NAME:latest`); every rule stays linear (#4094, thanks @proffesor-for-testing)
diff --git a/plugins/ruflo-rag-memory/scripts/smoke.sh b/plugins/ruflo-rag-memory/scripts/smoke.sh
index 99863ee861..54a2849243 100755
--- a/plugins/ruflo-rag-memory/scripts/smoke.sh
+++ b/plugins/ruflo-rag-memory/scripts/smoke.sh
@@ -7,9 +7,9 @@ step() { printf "→ %s ... " "$1"; }
ok() { printf "PASS\n"; PASS=$((PASS+1)); }
bad() { printf "FAIL: %s\n" "$1"; FAIL=$((FAIL+1)); }
-step "1. plugin.json declares 0.3.6 with new keywords"
+step "1. plugin.json declares 0.3.7 with new keywords"
v=$(grep -E '"version"' "$ROOT/.claude-plugin/plugin.json" | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' | head -1)
-if [[ "$v" != "0.3.6" ]]; then bad "expected 0.3.6, got '$v'"; else
+if [[ "$v" != "0.3.7" ]]; then bad "expected 0.3.7, got '$v'"; else
miss=""
for k in mcp claude-memories bridged-memory; do
grep -q "\"$k\"" "$ROOT/.claude-plugin/plugin.json" || miss="$miss $k"