🌊 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
TypeScript agentic-aiagentic-frameworkagentic-workflowagentsai-agentsai-assistantai-skillsautonomous-agentsclaudecodexdsh-pluginharnessmcp-servermulti-agentmulti-agent-systemsnpmskillsswarmswarm-intelligencetypescript
ci(federation): validate planner safe descriptor benchmark
rUvfd6014ac5ad9
diff --git a/.github/workflows/planner-safe-agent-descriptor.yml b/.github/workflows/planner-safe-agent-descriptor.ymlnew file mode 100644index 0000000000..a0201026c7--- /dev/null+++ b/.github/workflows/planner-safe-agent-descriptor.yml@@ -0,0 +1,48 @@+name: Planner Safe Agent Descriptor++on:+ pull_request:+ paths:+ - 'v3/@claude-flow/plugin-agent-federation/src/a2a/planner-descriptor.ts'+ - 'v3/@claude-flow/plugin-agent-federation/__tests__/unit/planner-descriptor.test.ts'+ - 'v3/@claude-flow/plugin-agent-federation/scripts/benchmark-planner-descriptor.mjs'+ - 'v3/@claude-flow/plugin-agent-federation/package.json'+ - '.github/workflows/planner-safe-agent-descriptor.yml'+ workflow_dispatch:++permissions:+ contents: read++concurrency:+ group: planner-safe-agent-descriptor-${{ github.ref }}+ cancel-in-progress: true++jobs:+ validate:+ runs-on: ubuntu-24.04+ timeout-minutes: 15+ steps:+ - name: Checkout exact source+ uses: actions/checkout@v4+ - name: Setup pnpm+ uses: pnpm/action-setup@v6+ with:+ version: 8+ - name: Setup Node+ uses: actions/setup-node@v4+ with:+ node-version: '22'+ cache: pnpm+ cache-dependency-path: v3/pnpm-lock.yaml+ - name: Install exact workspace dependencies+ working-directory: v3+ run: pnpm install --frozen-lockfile+ - name: Build federation package+ working-directory: v3+ run: pnpm --dir @claude-flow/plugin-agent-federation run build+ - name: Run focused adversarial tests+ working-directory: v3+ run: pnpm --dir @claude-flow/plugin-agent-federation exec vitest run __tests__/unit/planner-descriptor.test.ts+ - name: Run deterministic 10000 card benchmark+ working-directory: v3+ run: pnpm --dir @claude-flow/plugin-agent-federation run benchmark:planner-descriptor