agentic-qe 3.7.1 → 3.7.2

package/.claude/skills/skills-manifest.json

@@ -904,7 +904,7 @@
   },
   "metadata": {
     "generatedBy": "Agentic QE Fleet",
-    "fleetVersion": "3.7.1",
+    "fleetVersion": "3.7.2",
     "manifestVersion": "1.3.0",
     "lastUpdated": "2026-02-04T00:00:00.000Z",
     "contributors": [

package/README.md

@@ -11,7 +11,7 @@
 
 **V3 (Main)** | [V2 Documentation](v2/docs/V2-README.md) | [Release Notes](docs/releases/README.md) | [Changelog](v3/CHANGELOG.md) | [Contributors](CONTRIBUTORS.md) | [Issues](https://github.com/proffesor-for-testing/agentic-qe/issues) | [Discussions](https://github.com/proffesor-for-testing/agentic-qe/discussions)
 
-> **V3** brings Domain-Driven Design architecture, 13 bounded contexts, 60 specialized QE agents, TinyDancer intelligent model routing, ReasoningBank learning with Dream cycles, HNSW vector search, mathematical Coherence verification, full MinCut/Consensus integration across all 13 domains, RVF cognitive container integration with portable brain export/import, OpenCode multi-client support, and deep integration with [Claude Flow](https://github.com/ruvnet/claude-flow) and [Agentic Flow](https://github.com/ruvnet/agentic-flow).
+> **V3** brings Domain-Driven Design architecture, 13 bounded contexts, 60 specialized QE agents, TinyDancer intelligent model routing, ReasoningBank learning with Dream cycles, HNSW vector search, mathematical Coherence verification, full MinCut/Consensus integration across all 13 domains, RVF cognitive container integration with portable brain export/import, OpenCode multi-client support, AWS Kiro IDE integration, and deep integration with [Claude Flow](https://github.com/ruvnet/claude-flow) and [Agentic Flow](https://github.com/ruvnet/agentic-flow).
 
 🏗️ **DDD Architecture** | 🧠 **ReasoningBank + Dream Cycles** | 🎯 **TinyDancer Model Routing** | 🔍 **HNSW Vector Search** | 👑 **Queen Coordinator** | 📊 **O(log n) Coverage** | 🔗 **Claude Flow Integration** | 🎯 **13 Bounded Contexts** | 📚 **78 QE Skills** | 🧬 **Coherence Verification** | ✅ **Trust Tiers** | 🛡️ **Governance**
 
@@ -36,11 +36,14 @@ aqe init --auto
 
 # Include OpenCode assets (agents, skills, tools, permissions)
 aqe init --auto --with-opencode
+
+# Include AWS Kiro IDE assets (agents, skills, hooks, steering)
+aqe init --auto --with-kiro
 ```
 
 > **Note:** `aqe init` automatically configures the MCP server in `.mcp.json` — Claude Code will auto-start it when connecting. For standalone MCP server usage (non-Claude-Code clients), run `aqe-mcp` or `npx agentic-qe mcp`.
 
-### Use from MCP-compatible agent clients (Claude Code, OpenCode, Codex, others)
+### Use from MCP-compatible agent clients (Claude Code, OpenCode, Kiro, Codex, others)
 
 AQE is exposed as an MCP server and can be used from any client that supports MCP tool connections.
 
@@ -52,6 +55,9 @@ AQE is exposed as an MCP server and can be used from any client that supports MC
 aqe init --auto --with-opencode   # installs agents, skills, tools, permissions, opencode.json
 aqe-mcp                           # starts with SSE auto-detection
 
+# For AWS Kiro: provision Kiro-native assets during init
+aqe init --auto --with-kiro       # installs .kiro/ agents, skills, hooks, steering, MCP config
+
 # For other MCP clients: start the server manually
 aqe-mcp                  # if installed globally
 npx agentic-qe mcp       # without global install
@@ -76,6 +82,7 @@ For client-specific setup examples, see `docs/integration/mcp-clients.md`.
 - ✅ **Coherence Verification** (v3.3.0): Mathematical proof of belief consistency using WASM engines
 - ✅ **RVF Cognitive Containers** (v3.7.0): MinCut task routing, witness chain audit trail, portable brain export/import, unified HNSW search, production dual-write to native RVF
 - ✅ **OpenCode Support** (v3.7.1): 59 agent configs, 86 skill configs (78 QE + 8 general dev), 5 tool wrappers, SSE/WS/HTTP transport, output compaction, graceful degradation, `aqe init --with-opencode` auto-provisioning
+- ✅ **AWS Kiro Support** (v3.7.2): 87 agent configs, 86 skill configs, 5 event-driven hooks, 2 steering files, MCP config, `aqe init --with-kiro` auto-provisioning
 - ✅ **V2 Backward Compatibility**: All V2 agents map to V3 equivalents
 - ✅ **78 QE Skills**: 46 Tier 3 verified + 32 additional QE skills (QCSD swarms, n8n testing, enterprise integration, qe-* domains)
 
@@ -330,6 +337,56 @@ aqe brain info --input ./my-brain
 
 ---
 
+### 🏗️ AWS Kiro IDE Support (v3.7.2)
+
+V3.7.2 adds full **AWS Kiro IDE** integration, converting AQE agents, skills, hooks, and steering files to Kiro-native formats via `aqe init --with-kiro`.
+
+| Asset | Count | Description |
+|-------|-------|-------------|
+| **Agents** | 87 | `.kiro/agents/*.json` — 62 QE + 15 n8n + 10 infra/testing agents |
+| **Skills** | 86 | `.kiro/skills/*/SKILL.md` — full instructional content from Claude Code sources |
+| **Hooks** | 5 | `.kiro/hooks/*.kiro.hook` — event-driven automation (test update, coverage, security, quality gate, pre-commit) |
+| **Steering** | 2 | `.kiro/steering/*.md` — QE standards and testing conventions |
+| **MCP Config** | 1 | `.kiro/settings/mcp.json` — auto-approved AQE tools |
+
+**Setup:**
+
+```bash
+# Provision Kiro assets during init
+aqe init --auto --with-kiro
+
+# Or add Kiro to an existing project
+aqe init --with-kiro
+```
+
+**What gets generated:**
+
+```
+.kiro/
+├── agents/              # 87 agent definitions (Kiro JSON format)
+├── skills/*/SKILL.md    # 86 skill definitions (full markdown content)
+├── hooks/               # 5 event-driven hooks
+│   ├── aqe-test-updater.kiro.hook       # Auto-update tests on source changes
+│   ├── aqe-coverage-check.kiro.hook     # Coverage analysis on test edits
+│   ├── aqe-security-scan.kiro.hook      # Security scan on auth file changes
+│   ├── aqe-spec-quality-gate.kiro.hook  # Quality gate after spec tasks
+│   └── aqe-pre-commit-quality.kiro.hook # Quality check before agent stops
+├── steering/            # 2 project-wide guidance files
+│   ├── qe-standards.md              # QE standards (auto-triggered)
+│   └── testing-conventions.md       # Test file conventions (fileMatch)
+└── settings/mcp.json    # MCP server config with auto-approved tools
+```
+
+**Key features:**
+- Converts OpenCode YAML agents and Claude Code markdown agents to Kiro JSON format
+- Reads full SKILL.md content from Claude Code sources (not thin YAML stubs)
+- Maps `mcp:agentic-qe:` references to Kiro's `@agentic-qe/` format
+- Maps Claude Code tool names to Kiro builtins (`bash`→`shell`, `edit`→`write`)
+- Auto-detects existing `.kiro/` directory in `--auto` mode
+- Safe by default: won't overwrite existing files unless `--upgrade` is used
+
+---
+
 ### 🎯 TinyDancer Intelligent Model Routing
 
 **TinyDancer** (ADR-026) provides 3-tier intelligent model routing for cost optimization:
@@ -837,6 +894,12 @@ agentic-qe/
 ├── .claude/
 │   ├── agents/v3/           # V3 agent definitions (source)
 │   └── skills/              # 15 QE-specific skills
+├── .kiro/                   # AWS Kiro IDE integration (v3.7.2)
+│   ├── agents/              # 87 Kiro agent definitions (JSON)
+│   ├── skills/              # 86 Kiro skill definitions (SKILL.md)
+│   ├── hooks/               # 5 event-driven hooks
+│   ├── steering/            # 2 QE steering files
+│   └── settings/            # MCP server configuration
 ├── docs/                    # Shared documentation
 │   ├── plans/               # Migration plans
 │   ├── policies/            # Project policies

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agentic-qe",
-  "version": "3.7.1",
+  "version": "3.7.2",
   "description": "Agentic Quality Engineering V3 - Domain-Driven Design Architecture with 13 Bounded Contexts, O(log n) coverage analysis, ReasoningBank learning, 60 specialized QE agents, mathematical Coherence verification, deep Claude Flow integration",
   "main": "./v3/dist/index.js",
   "types": "./v3/dist/index.d.ts",

package/scripts/generate-opencode-agents.ts

@@ -481,10 +481,17 @@ async function main(): Promise<void> {
     const domain = frontmatter.domain;
 
     // Build system prompt based on format
-    const systemPrompt = hasXml
+    let systemPrompt = hasXml
       ? buildXmlSystemPrompt(agentName, normalizedContent, frontmatter)
       : buildMarkdownSystemPrompt(agentName, normalizedContent, frontmatter);
 
+    // Cap systemPrompt to ~2000 tokens (~7500 chars) to pass validation
+    const MAX_PROMPT_CHARS = 7500;
+    if (systemPrompt.length > MAX_PROMPT_CHARS) {
+      systemPrompt = systemPrompt.slice(0, MAX_PROMPT_CHARS).replace(/\n[^\n]*$/, '') +
+        '\n\n  [Truncated for token limit. See full agent definition in .claude/agents/v3/]';
+    }
+
     // Map tools from domain and name
     const tools = mapToolsFromDomain(domain, agentName);
 

package/scripts/generate-opencode-skills.ts

@@ -49,7 +49,7 @@ function tierToMinModel(tier: number): string {
   switch (tier) {
     case 0:
     case 1:
-      return 'tier1-fast';
+      return 'tier1-any';
     case 2:
       return 'tier2-good';
     case 3:

package/v3/CHANGELOG.md

@@ -5,6 +5,27 @@ All notable changes to Agentic QE will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.7.2] - 2026-02-25
+
+### Added
+
+- **AWS Kiro IDE integration** — Full Kiro support converting AQE agents, skills, hooks, and steering files to Kiro-native formats via `aqe init --with-kiro`: 87 agent JSON configs, 86 skill SKILL.md files with full content, 5 event-driven hooks (test-updater, coverage-check, security-scan, spec-quality-gate, pre-commit-quality), 2 steering files (qe-standards, testing-conventions), and MCP server configuration
+- **`aqe init --with-kiro` flag** — Provisions `.kiro/` directory with agents, skills, hooks, steering, and MCP config; follows the OpenCode/N8n installer pattern with auto-detection in `--auto` mode when `.kiro/` exists
+- **Kiro installer** (`v3/src/init/kiro-installer.ts`) — 937-line converter that reads OpenCode YAML agents and Claude Code markdown agents, converts `mcp:agentic-qe:` refs to `@agentic-qe/` format, maps tool names to Kiro builtins (`bash`→`shell`, `edit`→`write`), and prioritizes full SKILL.md content over thin YAML stubs
+
+### Fixed
+
+- **Kiro model mapping inconsistency** — `convertMdAgentToKiro()` now reads the `model` field from markdown agent frontmatter and properly maps opus/haiku models, matching the behavior of `convertToKiroAgent()` for YAML agents
+- **Unused variable warnings** — Removed unused `category` and `name` variables in kiro-installer.ts
+
+### Changed
+
+- **README updated** — Added dedicated AWS Kiro IDE section with asset table, directory structure, setup commands, and key features; updated Quick Start, client examples, feature bullets, and project architecture tree
+
+### Security
+
+- **hono 4.12.0 → 4.12.2** — Fixes incorrect `X-Forwarded-For` handling in AWS Lambda adapter that could allow IP-based access control bypass (GHSA-xh87-mx6m-69f3)
+
 ## [3.7.1] - 2026-02-24
 
 ### Added