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(ai-team): 0.3.1 for #3995 #3996 #3997 #4004 (changelog)

rffe7b6f93dd3
diff --git a/plugins/ruflo-ai-team/.claude-plugin/plugin.json b/plugins/ruflo-ai-team/.claude-plugin/plugin.json
index 831b1e0877..40241ed820 100644
--- a/plugins/ruflo-ai-team/.claude-plugin/plugin.json
+++ b/plugins/ruflo-ai-team/.claude-plugin/plugin.json
@@ -1,7 +1,7 @@
{
"name": "ruflo-ai-team",
"description": "Give Claude a tenant-isolated AI team that divides work, coordinates progress, recalls approved context, and returns evidence-backed results.",
- "version": "0.3.0",
+ "version": "0.3.1",
"author": {
"name": "ruvnet",
"url": "https://github.com/ruvnet"
diff --git a/plugins/ruflo-ai-team/CHANGELOG.md b/plugins/ruflo-ai-team/CHANGELOG.md
index 04ea758c51..8780c3a13b 100644
--- a/plugins/ruflo-ai-team/CHANGELOG.md
+++ b/plugins/ruflo-ai-team/CHANGELOG.md
@@ -2,6 +2,13 @@
Newest first. One `## <version> — <date>` heading per version, then `feat:`, `fix:`, `breaking:` and `chore:` bullets (ADR-478). Built from git history; older versions: `git log -- plugins/ruflo-ai-team`.
+## 0.3.1 — 2026-10-12
+- fix: stored teams, runs, tasks and memories no longer share mutable objects with the caller or with exported snapshots (#3995)
+- fix: run evidence includes the task history of the run in its audit trail (#3996)
+- fix: re-remembering a memory keeps its original creation time (#3997)
+- fix: a pending vector index build can no longer restore an invalidated tenant index (#4004)
+- chore: thanks to @rudycelekli for all four fixes
+
## 0.3.0 — 2026-10-09
- feat: skills, commands and agents name the connector tools in plain language instead of Claude Code namespaced identifiers (allowed-tools lists only the portable Read tool; the repo audit requires the field), so they read correctly on claude.ai and Cowork
- feat: lifecycle skill covers run_complete (the tasks_incomplete rule); skills state the real status values, template ids and budget range