release: v1.6.4

.claude-plugin/marketplace.json

@@ -5,14 +5,14 @@
   },
   "metadata": {
     "description": "Maestro multi-agent orchestration platform for Claude Code",
-    "version": "1.6.3"
+    "version": "1.6.4"
   },
   "plugins": [
     {
       "name": "maestro",
       "source": "./claude",
       "description": "Multi-agent development orchestration platform — 39 specialists, 4-phase orchestration, native parallel subagents, persistent sessions, and standalone review/debug/security/perf/seo/a11y/compliance commands",
-      "version": "1.6.3",
+      "version": "1.6.4",
       "author": {
         "name": "josstei",
         "email": "hello@josstei.dev",

.github/ISSUE_TEMPLATE/bug_report.md

@@ -11,6 +11,7 @@ assignees: ''
 - [ ] Gemini CLI
 - [ ] Claude Code
 - [ ] Codex
+- [ ] Qwen Code
 
 ## Maestro Version
 
@@ -20,7 +21,7 @@ assignees: ''
 
 - **OS**: <!-- e.g. macOS 15.2, Ubuntu 24.04 -->
 - **Node.js version**: <!-- e.g. 22.12.0 -->
-- **Runtime version**: <!-- e.g. Gemini CLI 0.1.5, Claude Code 1.0.23 -->
+- **Runtime version**: <!-- e.g. Gemini CLI 0.1.5, Claude Code 1.0.23, Qwen Code 0.1.5 -->
 
 ## Description
 

.github/ISSUE_TEMPLATE/feature_request.md

@@ -25,6 +25,7 @@ assignees: ''
 - [ ] Gemini CLI
 - [ ] Claude Code
 - [ ] Codex
+- [ ] Qwen Code
 - [ ] All runtimes
 - [ ] Build/generator only
 

.github/PULL_REQUEST_TEMPLATE.md

@@ -30,6 +30,7 @@
 - [ ] Gemini CLI
 - [ ] Claude Code
 - [ ] Codex
+- [ ] Qwen Code
 - [ ] None (internal/build only)
 
 ## Testing Notes

ARCHITECTURE.md

@@ -7,3 +7,4 @@ Related documentation:
 - [docs/runtime-gemini.md](docs/runtime-gemini.md)
 - [docs/runtime-claude.md](docs/runtime-claude.md)
 - [docs/runtime-codex.md](docs/runtime-codex.md)
+- [docs/runtime-qwen.md](docs/runtime-qwen.md)

CHANGELOG.md

@@ -7,6 +7,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ## [Unreleased]
 
+## [1.6.4] - 2026-04-30
+
 ### Added
 
 - **Maestro cheatsheet**: added an English quick-reference guide covering supported runtimes, common commands, workflow concepts, and suggested reading order.

CONTRIBUTING.md

@@ -5,7 +5,7 @@ Thank you for your interest in contributing to Maestro. This guide covers everyt
 ## Prerequisites
 
 - **Node.js 20+**
-- **One supported runtime**: [Gemini CLI](https://github.com/google-gemini/gemini-cli), [Claude Code](https://docs.anthropic.com/en/docs/claude-code), or [Codex](https://github.com/openai/codex)
+- **One supported runtime**: [Gemini CLI](https://github.com/google-gemini/gemini-cli), [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [Codex](https://github.com/openai/codex), or [Qwen Code](https://github.com/QwenLM/qwen-code)
 - [Just](https://github.com/casey/just) command runner (optional but recommended)
 
 ## Development Setup
@@ -16,12 +16,14 @@ cd maestro-orchestrate
 npm install
 ```
 
-`npm install` runs a `prepare` script that points `core.hooksPath` at `.githooks/`, activating the local `pre-commit`, `commit-msg`, and `pre-push` hooks for this checkout. If you install with `--ignore-scripts` or another tool that skips lifecycle scripts, activate the hooks manually:
+`npm install` installs dependencies only. Local git hook activation is explicit so package, pack, and publish flows do not mutate hook configuration. To activate the repo-local `pre-commit`, `commit-msg`, and `pre-push` hooks for this checkout, run:
 
 ```bash
-git config core.hooksPath .githooks
+npm run install-hooks
 ```
 
+Equivalent manual command: `git config core.hooksPath .githooks`.
+
 The hooks are best-effort — CI re-validates everything on PR submission and on direct pushes to `main`.
 
 ## Key Commands
@@ -36,7 +38,7 @@ All commands are available via `just` or `npm`:
 | `just test-transforms` | Run only transform unit tests |
 | `just test-integration` | Run only integration tests |
 | `just check` | Generate + verify zero drift (`git diff --exit-code`) |
-| `just ci` | Full CI equivalent: check + test |
+| `just ci` | Full CI equivalent: check + check-layers + test |
 | `just dry-run` | Preview changes without writing |
 | `just diff` | Show unified diff of pending changes |
 
@@ -53,6 +55,7 @@ All hand-maintained code lives in `src/`. Everything outside `src/` at the runti
 | `agents/`, `commands/`, `hooks/`, `mcp/`, `policies/` (repo root) | Gemini CLI |
 | `claude/` | Claude Code |
 | `plugins/maestro/` | Codex |
+| `qwen/` plus root `qwen-extension.json` and `QWEN.md` | Qwen Code |
 
 The generator pipeline reads `src/manifest.js` and applies transforms from `src/transforms/` to produce runtime-specific output.
 
@@ -163,7 +166,7 @@ This project uses [Keep a Changelog](https://keepachangelog.com/en/1.1.0/) forma
 
 ## Reporting Bugs and Requesting Features
 
-Use the [issue templates](.github/ISSUE_TEMPLATE/) to file bug reports or feature requests. Include your runtime (Gemini CLI, Claude Code, or Codex), Node.js version, and steps to reproduce.
+Use the [issue templates](.github/ISSUE_TEMPLATE/) to file bug reports or feature requests. Include your runtime (Gemini CLI, Claude Code, Codex, or Qwen Code), Node.js version, and steps to reproduce.
 
 ## Code Review
 

EXAMPLES.md

@@ -247,9 +247,9 @@ Source: `justfile`, `package.json`
 ```bash
 # edit README.md, EXAMPLES.md, docs/*.md, or canonical src/ docs as appropriate
 node --test tests/unit/doc-drift-guard.test.js
-just check
+node scripts/generate.js --diff
 ```
 
-Expected outcome: user-facing docs remain aligned with command names, runtime counts, MCP tool names, and generated-output rules.
+Expected outcome: user-facing docs remain aligned with command names, runtime counts, MCP tool names, and generated-output rules, and the generator reports no additional pending runtime output. In CI or a clean worktree, `just check` covers the same drift check with `git diff --exit-code`.
 
 Source: `tests/unit/doc-drift-guard.test.js`

GEMINI.md

@@ -76,21 +76,24 @@ For each domain, determine if the task has needs that warrant specialist involve
 
 | Domain | Signal questions | Candidate agents |
 | --- | --- | --- |
-| Engineering | Does the task involve code, infrastructure, or data? | `architect`, `api_designer`, `coder`, `code_reviewer`, `tester`, `refactor`, `data_engineer`, `debugger`, `devops_engineer`, `performance_engineer`, `security_engineer`, `technical_writer` |
+| Engineering | Does the task involve code, infrastructure, APIs, data, or delivery? | `architect`, `api_designer`, `coder`, `code_reviewer`, `tester`, `refactor`, `data_engineer`, `database_administrator`, `debugger`, `devops_engineer`, `integration_engineer`, `platform_engineer`, `cloud_architect`, `solutions_architect`, `site_reliability_engineer`, `observability_engineer`, `performance_engineer`, `security_engineer`, `technical_writer`, `release_manager` |
 | Product | Are requirements unclear, or does success depend on user outcomes? | `product_manager` |
 | Design | Does the deliverable have a user-facing interface or interaction? | `ux_designer`, `accessibility_specialist`, `design_system_engineer` |
 | Content | Does the task produce or modify user-visible text, copy, or media? | `content_strategist`, `copywriter` |
 | SEO | Is the deliverable web-facing and discoverable by search engines? | `seo_specialist` |
 | Compliance | Does the task handle user data, payments, or operate in a regulated domain? | `compliance_reviewer` |
 | Internationalization | Must the deliverable support multiple locales? | `i18n_specialist` |
 | Analytics | Does success need to be measured, or does the feature need instrumentation? | `analytics_engineer` |
+| ML/AI | Does the task involve model training, inference, prompts, or model operations? | `ml_engineer`, `mlops_engineer`, `prompt_engineer` |
+| Mobile | Does the task target iOS, Android, React Native, Flutter, or mobile release constraints? | `mobile_engineer` |
+| Mainframe / IBM | Does the task involve COBOL, JCL, DB2 for z/OS or IBM i, HLASM, RACF, CICS, IMS, or USS? | `cobol_engineer`, `db2_dba`, `zos_sysprog`, `hlasm_assembler_specialist`, `ibm_i_specialist` |
 
 Skip domains where the answer is clearly "no." For relevant domains, include appropriate agents in the phase plan alongside engineering agents. Domain agents participate at whatever phase makes sense — design, implementation, or post-build audit — based on the specific task.
 
 Apply domain analysis proportional to `task_complexity`:
 - `simple`: Engineering domain only. Skip other domains unless explicitly requested.
 - `medium`: Engineering + domains with clear signals from the task description.
-- `complex`: Full 8-domain sweep (current behavior).
+- `complex`: Full domain sweep (current behavior).
 
 
 ## Native Parallel Contract
@@ -141,7 +144,7 @@ CORRECT — Delegating via the agent's own tool:
 
 When building delegation prompts:
 
-1. Call the agent's registered tool by its exact name from the Agent Roster (e.g., `coder`, `tester`, `design_system_engineer`). Use `get_agent` to load the full methodology body and declared tool restrictions for the matching kebab-case agent.
+1. Call the agent's registered tool by its exact name from the Agent Roster (e.g., `coder`, `tester`, `design_system_engineer`). Use `get_agent` to load the full methodology body, declared tool restrictions, and runtime `tool_name` for the matching canonical agent.
 2. Do not rely on Maestro-level model, temperature, turn, or timeout overrides. Use agent frontmatter and runtime-level agent configuration for native tuning.
 3. Inject shared protocols from `get_skill_content` with resources: `["agent-base-protocol", "filesystem-safety-protocol"]`.
 4. Include dependency downstream context from session state.
@@ -189,30 +192,47 @@ All agent names use **snake_case** (underscores, not hyphens). When delegating,
 
 ## Agent Roster
 
-| Agent | Focus | Key Tool Profile |
+| Agent | Focus | Capability Tier |
 | --- | --- | --- |
-| `architect` | System design | Read tools + web search/fetch |
-| `api_designer` | API contracts | Read tools + web search/fetch |
-| `code_reviewer` | Code quality review | Read-only |
-| `coder` | Feature implementation | Read/write/shell + todos + skill activation |
-| `data_engineer` | Schema/data/queries | Read/write/shell + todos + web search |
-| `debugger` | Root cause analysis | Read + shell + todos |
-| `devops_engineer` | CI/CD and infra | Read/write/shell + todos + web search/fetch |
-| `performance_engineer` | Performance profiling | Read + shell + todos + web search/fetch |
-| `refactor` | Structural refactoring | Read/write/shell + todos + skill activation |
-| `security_engineer` | Security auditing | Read + shell + todos + web search/fetch |
-| `technical_writer` | Documentation | Read/write + todos + web search |
-| `tester` | Test implementation | Read/write/shell + todos + skill activation + web search |
-| `seo_specialist` | Technical SEO auditing | Read + shell + web search/fetch + todos |
-| `copywriter` | Marketing copy & content | Read/write |
-| `content_strategist` | Content planning & strategy | Read + web search/fetch |
-| `ux_designer` | User experience design | Read/write + web search |
-| `accessibility_specialist` | WCAG compliance auditing | Read + shell + web search + todos |
-| `product_manager` | Requirements & product strategy | Read/write + web search |
-| `analytics_engineer` | Tracking & measurement | Read/write/shell + web search + todos |
-| `i18n_specialist` | Internationalization | Read/write/shell + todos |
-| `design_system_engineer` | Design tokens & theming | Read/write/shell + todos + skill activation |
-| `compliance_reviewer` | Legal & regulatory compliance | Read + web search/fetch |
+| `accessibility_specialist` | WCAG compliance auditing, ARIA review | Read + shell |
+| `analytics_engineer` | Event tracking, conversion funnels | Full access |
+| `api_designer` | API contracts and endpoint design | Read-only |
+| `architect` | System design and architecture decisions | Read-only |
+| `cloud_architect` | AWS/GCP/Azure topology, IaC, multi-region design | Read-only |
+| `cobol_engineer` | Mainframe COBOL, JCL, CICS/IMS on z/OS | Full access |
+| `code_reviewer` | Code quality review and bug identification | Read-only |
+| `coder` | Feature implementation | Full access |
+| `compliance_reviewer` | Legal and regulatory compliance | Read-only |
+| `content_strategist` | Content planning and strategy | Read-only |
+| `copywriter` | Marketing copy and landing-page content | Read + write |
+| `data_engineer` | Schema design, queries, and data pipelines | Full access |
+| `database_administrator` | RDBMS tuning, indexes, and migration safety | Read + shell |
+| `db2_dba` | DB2 for z/OS and LUW, REORG, RUNSTATS, bind/rebind | Read + shell |
+| `debugger` | Root cause analysis and defect investigation | Read + shell |
+| `design_system_engineer` | Design tokens and theming | Full access |
+| `devops_engineer` | CI/CD, containerization, and deployment | Full access |
+| `hlasm_assembler_specialist` | IBM HLASM for z/OS, macros, SVCs | Full access |
+| `i18n_specialist` | Internationalization and locale management | Full access |
+| `ibm_i_specialist` | IBM i RPG/CL, DB2 for i, OS/400 | Full access |
+| `integration_engineer` | B2B APIs, ETL, and message brokers | Full access |
+| `ml_engineer` | Model training, feature pipelines, and evaluation | Full access |
+| `mlops_engineer` | Model registry, CI/CD for models, drift detection | Full access |
+| `mobile_engineer` | iOS/Android/React Native/Flutter platform work | Full access |
+| `observability_engineer` | Metrics, logs, traces, OpenTelemetry, dashboards | Full access |
+| `performance_engineer` | Performance profiling and optimization | Read + shell |
+| `platform_engineer` | Internal developer platforms and paved paths | Full access |
+| `product_manager` | Requirements and product strategy | Read + write |
+| `prompt_engineer` | LLM prompt design, few-shot, and RAG tuning | Read + write |
+| `refactor` | Structural refactoring and technical debt | Full access |
+| `release_manager` | Release notes, changelogs, rollout planning | Read + write |
+| `security_engineer` | Security assessment and vulnerability analysis | Read + shell |
+| `seo_specialist` | Technical SEO auditing and structured data | Read + shell |
+| `site_reliability_engineer` | SLOs, error budgets, runbooks, postmortems | Read + shell |
+| `solutions_architect` | Enterprise integration and cross-team architecture | Read-only |
+| `technical_writer` | Documentation and technical writing | Read + write |
+| `tester` | Test implementation and coverage analysis | Full access |
+| `ux_designer` | User experience design | Read + write |
+| `zos_sysprog` | z/OS systems programming, JCL, USS, RACF | Read + shell |
 
 ## Hooks
 

OVERVIEW.md

@@ -8,3 +8,4 @@ Related documentation:
 - [docs/runtime-gemini.md](docs/runtime-gemini.md)
 - [docs/runtime-claude.md](docs/runtime-claude.md)
 - [docs/runtime-codex.md](docs/runtime-codex.md)
+- [docs/runtime-qwen.md](docs/runtime-qwen.md)