@claude-flow/cli 3.56.1 → 3.56.2

package/.claude/helpers/helpers.manifest.json

@@ -1,6 +1,6 @@
 {
   "manifest": {
-    "version": "3.56.1",
+    "version": "3.56.2",
     "files": {
       "auto-memory-hook.mjs": "c8d218526a3c34034c2a69de23f507f0eb0f70d59c16426a8edc849e6ac22529",
       "hook-handler.cjs": "34d2aacfb59a73ff94b1467bb57ab9d9c4af89c0e470aadf3bd0d74a503a658d",
@@ -9,6 +9,6 @@
       "router.cjs": "16648b3c0d73b6681ac2d8d13def6a68286c57f5a11004de5b19a0fa088c833d"
     }
   },
-  "signature": "eGhCbWbSEhufQTLyjtRuSNc3JX1kDYCMAbqj/mn4IpYUOX+pi9Xs5lPAo/kVgVolhF1JRspGhzFi3Y8spw0EBw==",
+  "signature": "03RFXZ6Pjgky6pMS4AtU7Ba4ohrtwT67+aH8+COTVfhl5eZ0R1LsSXrGfMlROX+5U+FRlrbGoEaiNmNOhHRPDg==",
   "algorithm": "ed25519"
 }

package/catalog-manifest.json

@@ -1,8 +1,8 @@
 {
   "schemaVersion": 1,
   "generation": 7,
-  "generatedAt": "2026-10-09T04:37:42.484Z",
-  "gitSha": "58e0ae7e",
+  "generatedAt": "2026-10-09T17:22:50.548Z",
+  "gitSha": "9f97475f",
   "catalog": {
     "agents": 176,
     "tools": 423,

package/dist/src/mcp-tools/task-tools.d.ts

@@ -4,5 +4,10 @@
  * Tool definitions for task management with file persistence.
  */
 import { type MCPTool } from './types.js';
+export declare const TASK_STATUSES: readonly ["pending", "in_progress", "completed", "failed", "cancelled"];
+type TaskStatus = (typeof TASK_STATUSES)[number];
+/** The canonical status for a written one (trimmed, any case, known aliases), or null when it is none of the five. */
+export declare function statusOf(value: unknown): TaskStatus | null;
 export declare const taskTools: MCPTool[];
+export {};
 //# sourceMappingURL=task-tools.d.ts.map

package/dist/src/mcp-tools/task-tools.js

@@ -12,6 +12,21 @@ import { validateIdentifier, validateText } from './validate-input.js';
 const STORAGE_DIR = '.claude-flow';
 const TASK_DIR = 'tasks';
 const TASK_FILE = 'store.json';
+export const TASK_STATUSES = ['pending', 'in_progress', 'completed', 'failed', 'cancelled'];
+// Spellings agents write for the same five states (seen in the wild: "complete").
+const STATUS_ALIASES = {
+    complete: 'completed', done: 'completed', canceled: 'cancelled',
+    running: 'in_progress', 'in-progress': 'in_progress', inprogress: 'in_progress',
+};
+/** The canonical status for a written one (trimmed, any case, known aliases), or null when it is none of the five. */
+export function statusOf(value) {
+    if (typeof value !== 'string')
+        return null;
+    const key = value.trim().toLowerCase();
+    if (TASK_STATUSES.includes(key))
+        return key;
+    return Object.hasOwn(STATUS_ALIASES, key) ? STATUS_ALIASES[key] : null;
+}
 function getTaskDir() {
     return join(getProjectCwd(), STORAGE_DIR, TASK_DIR);
 }
@@ -290,7 +305,9 @@ export const taskTools = [
             type: 'object',
             properties: {
                 taskId: { type: 'string', description: 'Task ID' },
-                status: { type: 'string', description: 'New status' },
+                // No schema enum: the HTTP/WebSocket registry validates enums before the handler, which would refuse the aliases there
+                // while stdio accepted them. The handler is the one place that normalises and refuses, for every transport.
+                status: { type: 'string', description: 'New status: pending, in_progress, completed, failed or cancelled' },
                 progress: { type: 'number', description: 'Progress percentage (0-100)' },
                 assignTo: { type: 'array', items: { type: 'string' }, description: 'Agent IDs to assign' },
                 result: { type: 'object', description: 'Result data (e.g. the failure of a failed task)' },
@@ -302,26 +319,52 @@ export const taskTools = [
             const vId = validateIdentifier(input.taskId, 'taskId');
             if (!vId.valid)
                 return { success: false, error: vId.error };
+            // A status outside the five is stored as written otherwise, and every reader that buckets
+            // by status (task_list filters, the console kanban) then miscounts it: "complete" read as pending.
+            const status = input.status === undefined ? undefined : statusOf(input.status);
+            if (status === null) {
+                return { success: false, error: `status must be one of ${TASK_STATUSES.join(', ')}` };
+            }
             const store = loadTaskStore();
             const taskId = input.taskId;
             const task = store.tasks[taskId];
             if (task) {
-                if (input.status) {
-                    const newStatus = input.status;
+                // Worker effects run AFTER the task store is saved, as task_complete does: a failed save must not leave
+                // workers freed and counted against a task that still reads unfinished.
+                let afterSave;
+                if (status !== undefined) {
+                    const newStatus = status;
+                    const wasCompleted = task.status === 'completed';
                     task.status = newStatus;
                     if (newStatus === 'in_progress' && !task.startedAt) {
                         task.startedAt = new Date().toISOString();
                     }
-                    // A failed task frees its workers, as task_complete and task_cancel do;
-                    // otherwise a worker whose run failed stays `busy` forever.
-                    if (newStatus === 'failed') {
+                    // A finished task frees its workers, as task_complete and task_cancel do; otherwise a worker
+                    // whose task was finished through task_update stays `busy` forever, and a later task_complete
+                    // returns early because the status already reads completed.
+                    if (newStatus === 'failed' || newStatus === 'cancelled') {
+                        task.completedAt = new Date().toISOString();
+                        afterSave = () => releaseAgents(task.assignedTo, taskId);
+                    }
+                    if (newStatus === 'completed' && !wasCompleted) {
                         task.completedAt = new Date().toISOString();
-                        releaseAgents(task.assignedTo, taskId);
+                        // Credited only to a worker still holding this task, so complete -> pending -> complete
+                        // (no reassignment in between) never counts the same work twice.
+                        afterSave = () => updateAgents(task.assignedTo, (agent) => {
+                            if (agent.currentTask === taskId) {
+                                agent.status = 'idle';
+                                agent.currentTask = null;
+                                agent.taskCount = (agent.taskCount || 0) + 1;
+                            }
+                        });
                     }
                 }
                 if (typeof input.progress === 'number') {
                     task.progress = Math.min(100, Math.max(0, input.progress));
                 }
+                // Completing is 100% whatever progress the same call carried.
+                if (task.status === 'completed')
+                    task.progress = 100;
                 if (input.assignTo) {
                     task.assignedTo = input.assignTo;
                 }
@@ -329,6 +372,7 @@ export const taskTools = [
                     task.result = input.result;
                 }
                 saveTaskStore(store);
+                afterSave?.();
                 return {
                     success: true,
                     taskId: task.taskId,

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@claude-flow/cli",
-  "version": "3.56.1",
+  "version": "3.56.2",
   "type": "module",
   "description": "Ruflo CLI - Enterprise AI agent orchestration with 60+ specialized agents, swarm coordination, MCP server, self-learning hooks, and vector memory for Claude Code",
   "main": "dist/src/index.js",

package/plugins/ruflo-metaharness/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "ruflo-metaharness",
   "description": "MetaHarness integration for ruflo — surfaces score/genome/mint/mcp-scan/threat-model via skills; pairs with @metaharness/router (ADR-148/149) for cost-optimal model routing; honors ADR-150's architectural constraint that MetaHarness remains an optional augmentation, never a required runtime dependency. As a mod (ADR-445): confirms flywheel promotion, keeps secrets out of inputs, /metaharness-mod, and a status file the console shows",
-  "version": "0.2.4",
+  "version": "0.2.5",
   "author": {
     "name": "ruvnet",
     "url": "https://github.com/ruvnet"

package/plugins/ruflo-metaharness/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.
 
+## 0.2.5 — 2026-10-09
+- fix: seven harness-* skill descriptions no longer carry angle-bracket placeholders (claude.ai strips them as XML tags)
+
 ## 0.2.4 — 2026-10-07
 - fix: run the installed ruflo CLI before `npx @claude-flow/cli@latest` in cost-tracker, adr and metaharness
 - chore: 3.55.0 versions, leaf pins, lockfiles, plugin bumps, changelog

package/plugins/ruflo-metaharness/scripts/smoke.sh

@@ -1,5 +1,5 @@
 #!/usr/bin/env bash
-# Structural smoke test for ruflo-metaharness v0.2.4 (ADR-150 Phase 1).
+# Structural smoke test for ruflo-metaharness v0.2.5 (ADR-150 Phase 1).
 set -u
 ROOT="$(cd "$(dirname "$0")/.." && pwd)"
 PASS=0
@@ -32,10 +32,10 @@ else
   bad "extraction-regex-rot: EXPECTED_TOOLS=$EXPECTED_TOOLS EXPECTED_SUBS=$EXPECTED_SUBS"
 fi
 
-step "1. plugin.json declares 0.2.4 with adr-150 keywords"
+step "1. plugin.json declares 0.2.5 with adr-150 keywords"
 v=$(grep -E '"version"' "$ROOT/.claude-plugin/plugin.json" | grep -oE '[0-9]+\.[0-9]+\.[0-9]+' | head -1)
-if [[ "$v" != "0.2.4" ]]; then
-  bad "expected 0.2.4, got '$v'"
+if [[ "$v" != "0.2.5" ]]; then
+  bad "expected 0.2.5, got '$v'"
 else
   miss=""
   for k in ruflo metaharness harness scorecard genome mcp-scan threat-model router adr-150 adr-148 adr-149 optional-dependency graceful-degradation subprocess phase-1-mvp; do

package/plugins/ruflo-metaharness/skills/harness-bench/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-bench
-description: Manage `@metaharness/darwin` bench suites — `bench create <repo>` scaffolds a JSON suite from a repo's test corpus; `bench verify <suite.json>` checks suite well-formedness. Bench suites are the fixed evaluation corpora that `harness-evolve --bench <suite.json>` scores variants against, decoupling evolution from the repo's natural tests. Degrades gracefully when @metaharness/darwin is absent.
+description: Manage `@metaharness/darwin` bench suites — `bench create {repo}` scaffolds a JSON suite from a repo's test corpus; `bench verify {suite.json}` checks suite well-formedness. Bench suites are the fixed evaluation corpora that `harness-evolve --bench {suite.json}` scores variants against, decoupling evolution from the repo's natural tests. Degrades gracefully when @metaharness/darwin is absent.
 argument-hint: "--op create --repo <path> [--out <path>]  |  --op verify --suite <path>"
 allowed-tools: Bash
 ---

package/plugins/ruflo-metaharness/skills/harness-evolve/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-evolve
-description: Run `@metaharness/darwin evolve <repo>` to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, and promote only measured wins. The model is frozen; the harness evolves. Closes the loop ADR-150 opens (score+genome describe; evolve changes). Degrades gracefully when @metaharness/darwin is absent (ADR-150 + ADR-153 architectural constraints).
+description: Run `@metaharness/darwin evolve {repo}` to mutate a harness's seven policy surfaces (planner/contextBuilder/reviewer/retryPolicy/toolPolicy/memoryPolicy/scorePolicy), sandbox-score each variant, and promote only measured wins. The model is frozen; the harness evolves. Closes the loop ADR-150 opens (score+genome describe; evolve changes). Degrades gracefully when @metaharness/darwin is absent (ADR-150 + ADR-153 architectural constraints).
 argument-hint: "--repo <path> [--generations 3] [--children 3] [--concurrency 2] [--sandbox real|mock|agent] [--selection pareto|quality-diversity|...] [--mutator deterministic|ruvllm] [--diagnose] [--confirm]"
 allowed-tools: Bash
 ---

package/plugins/ruflo-metaharness/skills/harness-genome/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-genome
-description: 7-section repo readiness report from `metaharness genome <path>`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (ADR-150).
+description: 7-section repo readiness report from `metaharness genome {path}`. Returns repo_type / agent_topology / risk_score / mcp_surface / test_confidence / publish_readiness. Pure-read; degrades gracefully (ADR-150).
 argument-hint: "[--path .] [--alert-on-risk-above 0.5] [--format table|json]"
 allowed-tools: Bash
 ---

package/plugins/ruflo-metaharness/skills/harness-mcp-scan/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-mcp-scan
-description: Static security scan of a harness's declared MCP surface via `harness mcp-scan <path>`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.
+description: Static security scan of a harness's declared MCP surface via `harness mcp-scan {path}`. Reads `.mcp/servers.json` + `.harness/claims.json`. Pure-read, no dispatch. Exits 1 on findings at or above `--fail-on` severity.
 argument-hint: "[--path .] [--fail-on low|medium|high] [--format table|json]"
 allowed-tools: Bash
 ---

package/plugins/ruflo-metaharness/skills/harness-mint/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-mint
-description: Scaffold a custom AI agent harness via `metaharness new <name> --template <id> --host <id>`. Defaults to DRY-RUN (no writes) unless --confirm is passed. Refuses to write to the calling repo root or anywhere inside it. Honors ADR-150 architectural constraint + ruflo's "destructive-action confirmation" pattern.
+description: Scaffold a custom AI agent harness via `metaharness new {name} --template {id} --host {id}`. Defaults to DRY-RUN (no writes) unless --confirm is passed. Refuses to write to the calling repo root or anywhere inside it. Honors ADR-150 architectural constraint + ruflo's "destructive-action confirmation" pattern.
 argument-hint: "--name <id> --template <vertical:coding|minimal|…> [--host claude-code|codex|…] [--target /abs/path] [--confirm] [--format table|json]"
 allowed-tools: Bash
 ---

package/plugins/ruflo-metaharness/skills/harness-score/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-score
-description: 5-dimension harness readiness scorecard from `metaharness score <path>`. Returns harnessFit / compileConfidence / taskCoverage / toolSafety / memoryUsefulness + estCostPerRunUsd + scaffoldReady. Pure-read; subprocess invocation; degrades gracefully when MetaHarness is absent (ADR-150 architectural constraint).
+description: 5-dimension harness readiness scorecard from `metaharness score {path}`. Returns harnessFit / compileConfidence / taskCoverage / toolSafety / memoryUsefulness + estCostPerRunUsd + scaffoldReady. Pure-read; subprocess invocation; degrades gracefully when MetaHarness is absent (ADR-150 architectural constraint).
 argument-hint: "[--path .] [--alert-on-fit-below 70] [--format table|json]"
 allowed-tools: Bash
 ---

package/plugins/ruflo-metaharness/skills/harness-threat-model/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: harness-threat-model
-description: Enterprise-review-grade threat model from `harness threat-model <path>`. Categorizes MCP-surface threats; emits `worst: 'clean'|'low'|'medium'|'high'` + per-threat findings. Pure-read.
+description: Enterprise-review-grade threat model from `harness threat-model {path}`. Categorizes MCP-surface threats; emits `worst: 'clean'|'low'|'medium'|'high'` + per-threat findings. Pure-read.
 argument-hint: "[--path .] [--fail-on clean|low|medium|high] [--format table|json]"
 allowed-tools: Bash
 ---