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

fix(ruflo-ai-team): annotation-review.md missed team_board and run_complete (#4394)

rUvfac6d193ce48
diff --git a/plugins/ruflo-ai-team/.claude-plugin/plugin.json b/plugins/ruflo-ai-team/.claude-plugin/plugin.json
index a722859f75..eea393dc0e 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": "0.3.2",
+ "version": "0.3.3",
"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 570540e619..e7817cec46 100644
--- a/plugins/ruflo-ai-team/CHANGELOG.md
+++ b/plugins/ruflo-ai-team/CHANGELOG.md
@@ -2,6 +2,10 @@
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`.
+## 0.3.3 — 2026-10-22
+- fix: `annotation-review.md` documented only 12 of the 14 live tools, missing `team_board` and `run_complete` (added at 0.2.0/0.2.1) from its readOnly/destructive/idempotent/openWorld classification table
+- chore: smoke now asserts the doc's tool list matches the live server tool set exactly, so this can't silently drift again
+
## 0.3.2 — 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-ai-team/annotation-review.md b/plugins/ruflo-ai-team/annotation-review.md
index 384368c049..e1ef4b9ba9 100644
--- a/plugins/ruflo-ai-team/annotation-review.md
+++ b/plugins/ruflo-ai-team/annotation-review.md
@@ -4,8 +4,8 @@ All hints are explicit booleans. The server tests compare the live tool list wit
| Tools | readOnly | destructive | idempotent | openWorld | Justification |
|---|---:|---:|---:|---:|---|
-| `team_templates_list`, `team_list`, `team_get`, `task_list`, `memory_search`, `evidence_export` | true | false | true | false | Reads tenant-local or first-party state and makes no change. Repeating returns the same logical view. No external entity is contacted. |
+| `team_templates_list`, `team_list`, `team_get`, `task_list`, `memory_search`, `evidence_export`, `team_board` | true | false | true | false | Reads tenant-local or first-party state and makes no change. Repeating returns the same logical view. No external entity is contacted. |
| `team_create`, `run_create`, `task_create` | false | false | false | false | Creates a new tenant-local record on every successful call. It does not delete data or contact an external system. |
-| `team_update`, `task_update`, `memory_remember` | false | false | true | false | Upserts bounded tenant-local state to the requested value. Repeating the same arguments has the same logical result. No external entity is contacted. |
+| `team_update`, `task_update`, `memory_remember`, `run_complete` | false | false | true | false | Upserts bounded tenant-local state to the requested value. Repeating the same arguments has the same logical result. No external entity is contacted. |
-No v0.1 tool is destructive or open-world. External effects, public sharing, deletion, arbitrary execution, and credentials are deliberately absent until their approval and policy contracts are implemented.
+No tool is destructive or open-world. External effects, public sharing, deletion, arbitrary execution, and credentials are deliberately absent until their approval and policy contracts are implemented.
diff --git a/plugins/ruflo-ai-team/scripts/smoke.mjs b/plugins/ruflo-ai-team/scripts/smoke.mjs
index 2e574289ee..ddb4c0b0fc 100644
--- a/plugins/ruflo-ai-team/scripts/smoke.mjs
+++ b/plugins/ruflo-ai-team/scripts/smoke.mjs
@@ -20,6 +20,11 @@ const frontmatter=(text)=>{const m=text.match(/^---\n([\s\S]*?)\n---/);const o={
const names=(dir,file)=>readdirSync(new URL(dir,root),{withFileTypes:true}).filter((e)=>file?e.isDirectory():e.name.endsWith(".md")).map((e)=>file?`${dir}${e.name}/${file}`:`${dir}${e.name}`);
const items=[...names("skills/","SKILL.md"),...names("commands/"),...names("agents/")];
const serverTools=new Set([...server.matchAll(/mcp\.(?:tool|registerTool)\('([a-z_]+)'/g)].map((m)=>m[1]));
+// annotation-review.md's own claim ("server tests compare the live tool list with this
+// classification") must be true: every live tool documented, nothing stale left behind.
+const annotationRows=read('annotation-review.md').split('\n').filter((l)=>l.startsWith('| `'));
+const documentedTools=new Set(annotationRows.flatMap((l)=>[...l.matchAll(/`([a-z_]+)`/g)].map((m)=>m[1])));
+check('annotation-review.md documents every live tool, no more, no less',documentedTools.size===serverTools.size&&[...serverTools].every((t)=>documentedTools.has(t)));
for(const f of items){const text=read(f);const fm=frontmatter(text);
check(`${f}: no namespaced tool names`,!/mcp__/.test(text));
check(`${f}: description present, no angle brackets, under 300 chars`,!!fm.description&&!/[<>]/.test(fm.description)&&fm.description.length<300);