devsquad 3.9.2__tar.gz → 4.0.0__tar.gz

{devsquad-3.9.2 → devsquad-4.0.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devsquad
-Version: 3.9.2
+Version: 4.0.0
 Summary: Production-Ready Multi-Role AI Task Orchestrator
 Author-email: DevSquad Team <devsquad@example.com>
 License: MIT
@@ -48,6 +48,8 @@ Requires-Dist: streamlit>=1.28.0; extra == "visualization"
 Requires-Dist: jupyter>=1.0; extra == "visualization"
 Provides-Extra: alerts
 Requires-Dist: slack-sdk>=3.21.0; extra == "alerts"
+Provides-Extra: qa
+Requires-Dist: Pillow>=10.0.0; extra == "qa"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.21; extra == "dev"
@@ -56,6 +58,7 @@ Requires-Dist: ruff>=0.4.0; extra == "dev"
 Requires-Dist: mypy>=1.0; extra == "dev"
 Requires-Dist: black>=23.0; extra == "dev"
 Requires-Dist: flake8>=6.0; extra == "dev"
+Requires-Dist: httpx2>=2.5.0; extra == "dev"
 Provides-Extra: all
 Requires-Dist: openai>=1.0; extra == "all"
 Requires-Dist: anthropic>=0.18; extra == "all"
@@ -69,6 +72,7 @@ Requires-Dist: pydantic>=2.0; extra == "all"
 Requires-Dist: streamlit>=1.28.0; extra == "all"
 Requires-Dist: jupyter>=1.0; extra == "all"
 Requires-Dist: slack-sdk>=3.21.0; extra == "all"
+Requires-Dist: Pillow>=10.0.0; extra == "all"
 Requires-Dist: pytest>=7.0; extra == "all"
 Requires-Dist: pytest-asyncio>=0.21; extra == "all"
 Requires-Dist: pytest-cov>=4.1; extra == "all"
@@ -76,6 +80,7 @@ Requires-Dist: ruff>=0.4.0; extra == "all"
 Requires-Dist: mypy>=1.0; extra == "all"
 Requires-Dist: black>=23.0; extra == "all"
 Requires-Dist: flake8>=6.0; extra == "all"
+Requires-Dist: httpx2>=2.5.0; extra == "all"
 Dynamic: license-file
 
 # DevSquad — Multi-Role AI Task Orchestrator
@@ -83,14 +88,14 @@ Dynamic: license-file
 <p align="center">
   <strong>🎯 把「单个 AI 助手」升级成「7 人 AI 专业团队」</strong>
   <br>
-  <em>One task → Multi-role AI collaboration → One conclusion | V3.9.2 Enterprise Ready</em>
+  <em>One task → Multi-role AI collaboration → One conclusion | V4.0.0 Enterprise Ready</em>
 </p>
 
 <p align="center">
   <img alt="Python" src="https://img.shields.io/badge/Python-3.10+-blue?logo=python&logoColor=white" />
   <img alt="License" src="https://img.shields.io/badge/License-MIT-green" />
-  <img alt="Tests" src="https://img.shields.io/badge/Tests-2857%2B%20passing-brightgreen" />
-  <img alt="Version" src="https://img.shields.io/badge/V3.9.2-success" />
+  <img alt="Tests" src="https://img.shields.io/badge/Tests-3400%2B%20passing-brightgreen" />
+  <img alt="Version" src="https://img.shields.io/badge/V4.0.0-success" />
   <img alt="CI" src="https://img.shields.io/badge/CI-GitHub_Actions-blue?logo=githubactions" />
   <img alt="Quality" src="https://img.shields.io/badge/Code%20Quality-4.3%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%86-blue" />
   <img alt="Security" src="https://img.shields.io/badge/Security-5%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%85-success" />
@@ -151,9 +156,17 @@ devsquad run "设计一个安全的用户认证系统" --roles architect,securit
 <details>
 <summary>🔍 点击展开：完整功能介绍与架构详解</summary>
 
-## 🚀 V3.9.2: Auto LLM Fallback + Dashboard Split + SQLite Audit Persistence + P3 Cleanup
+## 🚀 V4.0.0: Loop Engineering + UI/UX 巡检 + Adversarial 验证 + DAG 可视化 + Autonomous + 插件热加载
 
-**DevSquad V3.9.2** introduces automatic LLM backend fallback (auto backend tries real LLM first, falls back to mock), splits dashboard.py from 1087 lines into an 8-module package, makes SQLite-backed dispatch audit persistence default, and performs P3 cleanup (magic number extraction + narrowed exception scopes), with 2857+ tests passing.
+**DevSquad V4.0.0** 借鉴上游 TraeMultiAgentSkill v2.7 理念，新增 6 个特性（P1-P3），全面接入 dispatch pipeline，无幽灵功能：
+- **P1-1 Loop Engineering**: Discovery → Handoff → Verification → Persistence → Scheduling 五步闭环
+- **P1-2 UI/UX 巡检**: 4 维度审计（a11y/interaction/layout/ux）+ PIL 像素 diff 视觉回归
+- **P2-1 Adversarial 验证**: 红队攻击 + 蓝队防御 + 裁判仲裁三阶段对抗验证
+- **P2-2 DAG 可视化**: Mermaid / JSON / DOT 三种格式依赖图可视化
+- **P3-1 Autonomous**: plan → dev → verify → fix 4 阶段自主迭代，复用 LoopKernel，不绕过共识门
+- **P3-2 插件热加载**: 三种加载路径 + 路径穿越三层防护 + reload 回滚 + 审计日志
+
+3400+ tests passing。
 
 ---
 
@@ -223,7 +236,7 @@ DEVSQUAD_API_PORT=9000 ./scripts/start.sh
 ./scripts/start.sh --help
 ```
 
-`start.sh` is the unified entry point introduced in V3.9.2 (P0-2). It validates the environment, initializes the database, builds the frontend, and starts the service in one command. Use `requirements.lock` alongside it for reproducible builds (`pip install -r requirements.lock`).
+`start.sh` is the unified entry point introduced in V3.9.2 (P0-2). It validates the environment, initializes the database, builds the frontend, and starts the service in one command. Use `requirements.lock` alongside it for reproducible builds (`pip install -r requirements.lock`). V4.0.0 adds Loop Engineering, UI/UX 巡检, Adversarial 验证, DAG 可视化, Autonomous, and 插件热加载.
 
 ---
 
@@ -537,7 +550,7 @@ devsquad dispatch -t "Design user authentication system"
 ```bash
 # Check version
 devsquad --version
-# Expected: devsquad 3.9.2
+# Expected: devsquad 4.0.0
 
 # Run tests
 pytest tests/ -v --tb=short
@@ -592,7 +605,7 @@ export DEVSQUAD_OPENAI_API_KEY=sk-...
 
 ### Quick Smoke Test (< 30 seconds)
 ```bash
-python3 scripts/cli.py --version       # Expected: DevSquad 3.9.2
+python3 scripts/cli.py --version       # Expected: DevSquad 4.0.0
 python3 scripts/cli.py status          # Expected: System ready
 python3 scripts/cli.py roles           # Expected: 7 core roles listed
 ```
@@ -680,6 +693,6 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 
 ---
 
-*Last updated: 2026-06-26 | Version: V3.9.2*
+*Last updated: 2026-07-07 | Version: V4.0.0*
 
 </details>

{devsquad-3.9.2 → devsquad-4.0.0}/README.md

@@ -3,14 +3,14 @@
 <p align="center">
   <strong>🎯 把「单个 AI 助手」升级成「7 人 AI 专业团队」</strong>
   <br>
-  <em>One task → Multi-role AI collaboration → One conclusion | V3.9.2 Enterprise Ready</em>
+  <em>One task → Multi-role AI collaboration → One conclusion | V4.0.0 Enterprise Ready</em>
 </p>
 
 <p align="center">
   <img alt="Python" src="https://img.shields.io/badge/Python-3.10+-blue?logo=python&logoColor=white" />
   <img alt="License" src="https://img.shields.io/badge/License-MIT-green" />
-  <img alt="Tests" src="https://img.shields.io/badge/Tests-2857%2B%20passing-brightgreen" />
-  <img alt="Version" src="https://img.shields.io/badge/V3.9.2-success" />
+  <img alt="Tests" src="https://img.shields.io/badge/Tests-3400%2B%20passing-brightgreen" />
+  <img alt="Version" src="https://img.shields.io/badge/V4.0.0-success" />
   <img alt="CI" src="https://img.shields.io/badge/CI-GitHub_Actions-blue?logo=githubactions" />
   <img alt="Quality" src="https://img.shields.io/badge/Code%20Quality-4.3%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%86-blue" />
   <img alt="Security" src="https://img.shields.io/badge/Security-5%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%85-success" />
@@ -71,9 +71,17 @@ devsquad run "设计一个安全的用户认证系统" --roles architect,securit
 <details>
 <summary>🔍 点击展开：完整功能介绍与架构详解</summary>
 
-## 🚀 V3.9.2: Auto LLM Fallback + Dashboard Split + SQLite Audit Persistence + P3 Cleanup
+## 🚀 V4.0.0: Loop Engineering + UI/UX 巡检 + Adversarial 验证 + DAG 可视化 + Autonomous + 插件热加载
 
-**DevSquad V3.9.2** introduces automatic LLM backend fallback (auto backend tries real LLM first, falls back to mock), splits dashboard.py from 1087 lines into an 8-module package, makes SQLite-backed dispatch audit persistence default, and performs P3 cleanup (magic number extraction + narrowed exception scopes), with 2857+ tests passing.
+**DevSquad V4.0.0** 借鉴上游 TraeMultiAgentSkill v2.7 理念，新增 6 个特性（P1-P3），全面接入 dispatch pipeline，无幽灵功能：
+- **P1-1 Loop Engineering**: Discovery → Handoff → Verification → Persistence → Scheduling 五步闭环
+- **P1-2 UI/UX 巡检**: 4 维度审计（a11y/interaction/layout/ux）+ PIL 像素 diff 视觉回归
+- **P2-1 Adversarial 验证**: 红队攻击 + 蓝队防御 + 裁判仲裁三阶段对抗验证
+- **P2-2 DAG 可视化**: Mermaid / JSON / DOT 三种格式依赖图可视化
+- **P3-1 Autonomous**: plan → dev → verify → fix 4 阶段自主迭代，复用 LoopKernel，不绕过共识门
+- **P3-2 插件热加载**: 三种加载路径 + 路径穿越三层防护 + reload 回滚 + 审计日志
+
+3400+ tests passing。
 
 ---
 
@@ -143,7 +151,7 @@ DEVSQUAD_API_PORT=9000 ./scripts/start.sh
 ./scripts/start.sh --help
 ```
 
-`start.sh` is the unified entry point introduced in V3.9.2 (P0-2). It validates the environment, initializes the database, builds the frontend, and starts the service in one command. Use `requirements.lock` alongside it for reproducible builds (`pip install -r requirements.lock`).
+`start.sh` is the unified entry point introduced in V3.9.2 (P0-2). It validates the environment, initializes the database, builds the frontend, and starts the service in one command. Use `requirements.lock` alongside it for reproducible builds (`pip install -r requirements.lock`). V4.0.0 adds Loop Engineering, UI/UX 巡检, Adversarial 验证, DAG 可视化, Autonomous, and 插件热加载.
 
 ---
 
@@ -457,7 +465,7 @@ devsquad dispatch -t "Design user authentication system"
 ```bash
 # Check version
 devsquad --version
-# Expected: devsquad 3.9.2
+# Expected: devsquad 4.0.0
 
 # Run tests
 pytest tests/ -v --tb=short
@@ -512,7 +520,7 @@ export DEVSQUAD_OPENAI_API_KEY=sk-...
 
 ### Quick Smoke Test (< 30 seconds)
 ```bash
-python3 scripts/cli.py --version       # Expected: DevSquad 3.9.2
+python3 scripts/cli.py --version       # Expected: DevSquad 4.0.0
 python3 scripts/cli.py status          # Expected: System ready
 python3 scripts/cli.py roles           # Expected: 7 core roles listed
 ```
@@ -600,6 +608,6 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 
 ---
 
-*Last updated: 2026-06-26 | Version: V3.9.2*
+*Last updated: 2026-07-07 | Version: V4.0.0*
 
 </details>

{devsquad-3.9.2 → devsquad-4.0.0}/devsquad.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devsquad
-Version: 3.9.2
+Version: 4.0.0
 Summary: Production-Ready Multi-Role AI Task Orchestrator
 Author-email: DevSquad Team <devsquad@example.com>
 License: MIT
@@ -48,6 +48,8 @@ Requires-Dist: streamlit>=1.28.0; extra == "visualization"
 Requires-Dist: jupyter>=1.0; extra == "visualization"
 Provides-Extra: alerts
 Requires-Dist: slack-sdk>=3.21.0; extra == "alerts"
+Provides-Extra: qa
+Requires-Dist: Pillow>=10.0.0; extra == "qa"
 Provides-Extra: dev
 Requires-Dist: pytest>=7.0; extra == "dev"
 Requires-Dist: pytest-asyncio>=0.21; extra == "dev"
@@ -56,6 +58,7 @@ Requires-Dist: ruff>=0.4.0; extra == "dev"
 Requires-Dist: mypy>=1.0; extra == "dev"
 Requires-Dist: black>=23.0; extra == "dev"
 Requires-Dist: flake8>=6.0; extra == "dev"
+Requires-Dist: httpx2>=2.5.0; extra == "dev"
 Provides-Extra: all
 Requires-Dist: openai>=1.0; extra == "all"
 Requires-Dist: anthropic>=0.18; extra == "all"
@@ -69,6 +72,7 @@ Requires-Dist: pydantic>=2.0; extra == "all"
 Requires-Dist: streamlit>=1.28.0; extra == "all"
 Requires-Dist: jupyter>=1.0; extra == "all"
 Requires-Dist: slack-sdk>=3.21.0; extra == "all"
+Requires-Dist: Pillow>=10.0.0; extra == "all"
 Requires-Dist: pytest>=7.0; extra == "all"
 Requires-Dist: pytest-asyncio>=0.21; extra == "all"
 Requires-Dist: pytest-cov>=4.1; extra == "all"
@@ -76,6 +80,7 @@ Requires-Dist: ruff>=0.4.0; extra == "all"
 Requires-Dist: mypy>=1.0; extra == "all"
 Requires-Dist: black>=23.0; extra == "all"
 Requires-Dist: flake8>=6.0; extra == "all"
+Requires-Dist: httpx2>=2.5.0; extra == "all"
 Dynamic: license-file
 
 # DevSquad — Multi-Role AI Task Orchestrator
@@ -83,14 +88,14 @@ Dynamic: license-file
 <p align="center">
   <strong>🎯 把「单个 AI 助手」升级成「7 人 AI 专业团队」</strong>
   <br>
-  <em>One task → Multi-role AI collaboration → One conclusion | V3.9.2 Enterprise Ready</em>
+  <em>One task → Multi-role AI collaboration → One conclusion | V4.0.0 Enterprise Ready</em>
 </p>
 
 <p align="center">
   <img alt="Python" src="https://img.shields.io/badge/Python-3.10+-blue?logo=python&logoColor=white" />
   <img alt="License" src="https://img.shields.io/badge/License-MIT-green" />
-  <img alt="Tests" src="https://img.shields.io/badge/Tests-2857%2B%20passing-brightgreen" />
-  <img alt="Version" src="https://img.shields.io/badge/V3.9.2-success" />
+  <img alt="Tests" src="https://img.shields.io/badge/Tests-3400%2B%20passing-brightgreen" />
+  <img alt="Version" src="https://img.shields.io/badge/V4.0.0-success" />
   <img alt="CI" src="https://img.shields.io/badge/CI-GitHub_Actions-blue?logo=githubactions" />
   <img alt="Quality" src="https://img.shields.io/badge/Code%20Quality-4.3%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%86-blue" />
   <img alt="Security" src="https://img.shields.io/badge/Security-5%2F5%20%E2%98%85%E2%98%85%E2%98%85%E2%98%85%E2%98%85-success" />
@@ -151,9 +156,17 @@ devsquad run "设计一个安全的用户认证系统" --roles architect,securit
 <details>
 <summary>🔍 点击展开：完整功能介绍与架构详解</summary>
 
-## 🚀 V3.9.2: Auto LLM Fallback + Dashboard Split + SQLite Audit Persistence + P3 Cleanup
+## 🚀 V4.0.0: Loop Engineering + UI/UX 巡检 + Adversarial 验证 + DAG 可视化 + Autonomous + 插件热加载
 
-**DevSquad V3.9.2** introduces automatic LLM backend fallback (auto backend tries real LLM first, falls back to mock), splits dashboard.py from 1087 lines into an 8-module package, makes SQLite-backed dispatch audit persistence default, and performs P3 cleanup (magic number extraction + narrowed exception scopes), with 2857+ tests passing.
+**DevSquad V4.0.0** 借鉴上游 TraeMultiAgentSkill v2.7 理念，新增 6 个特性（P1-P3），全面接入 dispatch pipeline，无幽灵功能：
+- **P1-1 Loop Engineering**: Discovery → Handoff → Verification → Persistence → Scheduling 五步闭环
+- **P1-2 UI/UX 巡检**: 4 维度审计（a11y/interaction/layout/ux）+ PIL 像素 diff 视觉回归
+- **P2-1 Adversarial 验证**: 红队攻击 + 蓝队防御 + 裁判仲裁三阶段对抗验证
+- **P2-2 DAG 可视化**: Mermaid / JSON / DOT 三种格式依赖图可视化
+- **P3-1 Autonomous**: plan → dev → verify → fix 4 阶段自主迭代，复用 LoopKernel，不绕过共识门
+- **P3-2 插件热加载**: 三种加载路径 + 路径穿越三层防护 + reload 回滚 + 审计日志
+
+3400+ tests passing。
 
 ---
 
@@ -223,7 +236,7 @@ DEVSQUAD_API_PORT=9000 ./scripts/start.sh
 ./scripts/start.sh --help
 ```
 
-`start.sh` is the unified entry point introduced in V3.9.2 (P0-2). It validates the environment, initializes the database, builds the frontend, and starts the service in one command. Use `requirements.lock` alongside it for reproducible builds (`pip install -r requirements.lock`).
+`start.sh` is the unified entry point introduced in V3.9.2 (P0-2). It validates the environment, initializes the database, builds the frontend, and starts the service in one command. Use `requirements.lock` alongside it for reproducible builds (`pip install -r requirements.lock`). V4.0.0 adds Loop Engineering, UI/UX 巡检, Adversarial 验证, DAG 可视化, Autonomous, and 插件热加载.
 
 ---
 
@@ -537,7 +550,7 @@ devsquad dispatch -t "Design user authentication system"
 ```bash
 # Check version
 devsquad --version
-# Expected: devsquad 3.9.2
+# Expected: devsquad 4.0.0
 
 # Run tests
 pytest tests/ -v --tb=short
@@ -592,7 +605,7 @@ export DEVSQUAD_OPENAI_API_KEY=sk-...
 
 ### Quick Smoke Test (< 30 seconds)
 ```bash
-python3 scripts/cli.py --version       # Expected: DevSquad 3.9.2
+python3 scripts/cli.py --version       # Expected: DevSquad 4.0.0
 python3 scripts/cli.py status          # Expected: System ready
 python3 scripts/cli.py roles           # Expected: 7 core roles listed
 ```
@@ -680,6 +693,6 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 
 ---
 
-*Last updated: 2026-06-26 | Version: V3.9.2*
+*Last updated: 2026-07-07 | Version: V4.0.0*
 
 </details>

{devsquad-3.9.2 → devsquad-4.0.0}/devsquad.egg-info/SOURCES.txt

@@ -11,6 +11,7 @@ scripts/__init__.py
 scripts/api_server.py
 scripts/auth.py
 scripts/benchmark_async_dispatch.py
+scripts/benchmark_ponytail_smart.py
 scripts/benchmark_real_llm.py
 scripts/check_version_consistency.py
 scripts/cli.py
@@ -35,6 +36,7 @@ scripts/cli/cli_visual.py
 scripts/collaboration/__init__.py
 scripts/collaboration/_version.py
 scripts/collaboration/adaptive_role_selector.py
+scripts/collaboration/adversarial_verify.py
 scripts/collaboration/agent_briefing.py
 scripts/collaboration/ai_semantic_matcher.py
 scripts/collaboration/anchor_checker.py
@@ -45,6 +47,7 @@ scripts/collaboration/async_llm_backend.py
 scripts/collaboration/audit_logger.py
 scripts/collaboration/batch_scheduler.py
 scripts/collaboration/cache_interface.py
+scripts/collaboration/ccr_store.py
 scripts/collaboration/checkpoint_manager.py
 scripts/collaboration/ci_feedback_adapter.py
 scripts/collaboration/code_graph_query.py
@@ -57,6 +60,7 @@ scripts/collaboration/consensus.py
 scripts/collaboration/consensus_gate.py
 scripts/collaboration/constants.py
 scripts/collaboration/content_cache.py
+scripts/collaboration/content_crusher.py
 scripts/collaboration/context_compressor.py
 scripts/collaboration/coordinator.py
 scripts/collaboration/dispatch_audit.py
@@ -96,6 +100,7 @@ scripts/collaboration/input_validator.py
 scripts/collaboration/intent_workflow_mapper.py
 scripts/collaboration/judge_agent.py
 scripts/collaboration/language_parsers.py
+scripts/collaboration/learned_rule_store.py
 scripts/collaboration/lifecycle_gate.py
 scripts/collaboration/lifecycle_protocol.py
 scripts/collaboration/lifecycle_shortcut_adapter.py
@@ -130,6 +135,7 @@ scripts/collaboration/output_slicer.py
 scripts/collaboration/performance_fingerprint.py
 scripts/collaboration/performance_monitor.py
 scripts/collaboration/permission_guard.py
+scripts/collaboration/ponytail_rule_injector.py
 scripts/collaboration/prometheus_metrics.py
 scripts/collaboration/prompt_assembler.py
 scripts/collaboration/prompt_assembler_base.py
@@ -181,14 +187,37 @@ scripts/collaboration/workflow_engine_persistence_mixin.py
 scripts/collaboration/workflow_engine_state_mixin.py
 scripts/collaboration/workflow_engine_transition_mixin.py
 scripts/collaboration/yagni_checker.py
+scripts/collaboration/autonomous/__init__.py
+scripts/collaboration/autonomous/git_driver.py
+scripts/collaboration/autonomous/loop_controller.py
+scripts/collaboration/autonomous/notes_memory.py
+scripts/collaboration/autonomous/run_state.py
+scripts/collaboration/autonomous/sleep_guard.py
+scripts/collaboration/autonomous/smart_confirmation.py
+scripts/collaboration/loop_engineering/__init__.py
+scripts/collaboration/loop_engineering/discovery_probe.py
+scripts/collaboration/loop_engineering/handoff_adapter.py
+scripts/collaboration/loop_engineering/independent_evaluator.py
+scripts/collaboration/loop_engineering/kernel.py
+scripts/collaboration/loop_engineering/loop_scheduler.py
+scripts/collaboration/loop_engineering/models.py
+scripts/collaboration/loop_engineering/protocols.py
+scripts/collaboration/loop_engineering/unified_memory.py
+scripts/collaboration/plugins/__init__.py
+scripts/collaboration/plugins/hot_loader.py
 scripts/dashboard/__init__.py
 scripts/dashboard/app.py
 scripts/dashboard/auth_views.py
 scripts/dashboard/components.py
+scripts/dashboard/dag_views.py
 scripts/dashboard/dispatch_views.py
 scripts/dashboard/lifecycle_views.py
 scripts/dashboard/metrics_views.py
 scripts/dashboard/state.py
+scripts/qa/__init__.py
+scripts/qa/models.py
+scripts/qa/uiux_analyzer.py
+scripts/qa/visual_regression.py
 scripts/utils/__init__.py
 scripts/utils/_find_missing_hints.py
 skills/__init__.py
@@ -201,14 +230,20 @@ skills/review/handler.py
 skills/security/handler.py
 skills/test/__init__.py
 skills/test/handler.py
+tests/test_adversarial_verify.py
 tests/test_agent_briefing.py
 tests/test_anchor_retrospective.py
 tests/test_anti_rationalization.py
+tests/test_api_budget_status_endpoint.py
 tests/test_api_security.py
 tests/test_api_server_v362.py
 tests/test_async_modules.py
 tests/test_audit_logger.py
 tests/test_auth_phase5.py
+tests/test_autonomous.py
+tests/test_benchmark_ponytail_smart.py
+tests/test_ccr_marker_integration.py
+tests/test_ccr_store.py
 tests/test_ci_feedback_adapter.py
 tests/test_cli_deep_v362.py
 tests/test_cli_lifecycle.py
@@ -239,7 +274,12 @@ tests/test_confidence_score.py
 tests/test_config_injection.py
 tests/test_consensus_gate.py
 tests/test_content_cache.py
+tests/test_content_crusher.py
+tests/test_coordinator_budget_ccr_integration.py
+tests/test_coordinator_smart_compression.py
+tests/test_dag_views.py
 tests/test_dashboard_split.py
+tests/test_dashboard_ui_e2e.py
 tests/test_data_backup.py
 tests/test_dependency_lock.py
 tests/test_dispatch_audit.py
@@ -254,9 +294,11 @@ tests/test_history_manager_v362.py
 tests/test_input_validator_phase5.py
 tests/test_intent_workflow_mapper.py
 tests/test_judge_agent.py
+tests/test_learned_rule_phase4.py
 tests/test_lifecycle_protocol.py
 tests/test_llm_auto_fallback.py
 tests/test_llm_cache_protocol.py
+tests/test_loop_engineering.py
 tests/test_mcp_server_v362.py
 tests/test_memory_benchmarks.py
 tests/test_micro_task_planner.py
@@ -270,11 +312,16 @@ tests/test_performance_benchmarks.py
 tests/test_performance_fingerprint.py
 tests/test_performance_monitor_protocol.py
 tests/test_permission_guard_phase5.py
+tests/test_phase4_ghost_feature_defense.py
 tests/test_pipeline_step19_20.py
 tests/test_plan_c_unified_architecture.py
+tests/test_plugins_hot_loader.py
+tests/test_ponytail_rule_injector.py
 tests/test_production_features.py
 tests/test_prompt_dials.py
 tests/test_protocols.py
+tests/test_qa_integration.py
+tests/test_qa_uiux_visual_regression.py
 tests/test_quick_bonus.py
 tests/test_rate_limit.py
 tests/test_rbac_engine.py
@@ -284,18 +331,24 @@ tests/test_retry_jitter_strategies.py
 tests/test_role_skill_loader.py
 tests/test_rule_injection_security.py
 tests/test_severity_router.py
+tests/test_skill_registry_coverage.py
 tests/test_skill_security.py
+tests/test_sleep_guard.py
 tests/test_standardized_role_template.py
 tests/test_start_script.py
 tests/test_step_node_types.py
 tests/test_suggested_next_steps.py
 tests/test_tech_debt_manager.py
+tests/test_token_budget_compressed_scratchpad.py
 tests/test_two_stage_review_gate.py
 tests/test_ue_test_framework.py
+tests/test_usage_tracker_coverage.py
 tests/test_v38_integration.py
 tests/test_v39_e2e.py
 tests/test_v39_integration.py
 tests/test_v39_performance.py
+tests/test_v4_integration.py
 tests/test_verification_gate.py
 tests/test_version.py
+tests/test_workflow_persistence_coverage.py
 tests/test_yagni_checker.py

{devsquad-3.9.2 → devsquad-4.0.0}/devsquad.egg-info/requires.txt

@@ -19,6 +19,7 @@ pydantic>=2.0
 streamlit>=1.28.0
 jupyter>=1.0
 slack-sdk>=3.21.0
+Pillow>=10.0.0
 pytest>=7.0
 pytest-asyncio>=0.21
 pytest-cov>=4.1
@@ -26,6 +27,7 @@ ruff>=0.4.0
 mypy>=1.0
 black>=23.0
 flake8>=6.0
+httpx2>=2.5.0
 
 [anthropic]
 anthropic>=0.18
@@ -46,6 +48,7 @@ ruff>=0.4.0
 mypy>=1.0
 black>=23.0
 flake8>=6.0
+httpx2>=2.5.0
 
 [mcp]
 mcp>=0.9
@@ -57,6 +60,9 @@ prometheus-client>=0.19
 [openai]
 openai>=1.0
 
+[qa]
+Pillow>=10.0.0
+
 [visualization]
 streamlit>=1.28.0
 jupyter>=1.0

{devsquad-3.9.2 → devsquad-4.0.0}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "devsquad"
-version = "3.9.2"
+version = "4.0.0"
 description = "Production-Ready Multi-Role AI Task Orchestrator"
 readme = "README.md"
 license = {text = "MIT"}
@@ -56,6 +56,9 @@ visualization = [
 alerts = [
     "slack-sdk>=3.21.0",
 ]
+qa = [
+    "Pillow>=10.0.0",
+]
 dev = [
     "pytest>=7.0",
     "pytest-asyncio>=0.21",
@@ -64,6 +67,7 @@ dev = [
     "mypy>=1.0",
     "black>=23.0",
     "flake8>=6.0",
+    "httpx2>=2.5.0",
 ]
 all = [
     "openai>=1.0",
@@ -78,6 +82,7 @@ all = [
     "streamlit>=1.28.0",
     "jupyter>=1.0",
     "slack-sdk>=3.21.0",
+    "Pillow>=10.0.0",
     "pytest>=7.0",
     "pytest-asyncio>=0.21",
     "pytest-cov>=4.1",
@@ -85,6 +90,7 @@ all = [
     "mypy>=1.0",
     "black>=23.0",
     "flake8>=6.0",
+    "httpx2>=2.5.0",
 ]
 
 [project.scripts]
@@ -160,6 +166,7 @@ norecursedirs = []
 python_files = ["test_*.py", "*_test.py"]
 python_classes = ["Test*"]
 python_functions = ["test_*"]
+asyncio_mode = "auto"
 addopts = [
     "-v",
     "--tb=short",
@@ -172,6 +179,7 @@ markers = [
     "benchmark: performance benchmark tests",
     "unit: marks tests as unit tests",
     "smoke: marks tests as release smoke tests",
+    "asyncio: async tests using pytest-asyncio",
 ]
 filterwarnings = [
     "ignore::DeprecationWarning",

{devsquad-3.9.2 → devsquad-4.0.0}/scripts/api/routes/dispatch.py

@@ -434,3 +434,44 @@ async def list_roles(
     except Exception as e:
         logger.error("Unexpected error listing roles: %s", e, exc_info=True)
         raise HTTPException(status_code=500, detail=f"Failed to retrieve roles: {str(e)}") from None
+
+
+@router.get(
+    "/api/v1/budget/status",
+    summary="Token Budget Status / Token 预算状态",
+    description="""
+    V3.10.0 Phase 3 — Live token budget status for dashboard/Prometheus polling.
+
+    Returns the Coordinator's current ``used_input_tokens`` against the
+    configured ``TokenBudget`` thresholds (warning_ratio defaults to 0.8).
+    When no budget is configured, returns ``{"configured": false}``.
+
+    Fields:
+      - configured: bool — whether a TokenBudget is attached
+      - total_input_budget / per_role_input_budget / output_budget
+      - warning_ratio / warning_threshold
+      - used_input_tokens / remaining_input_tokens
+      - is_warning / is_exceeded — gate flags for alerting
+    """,
+)
+async def get_budget_status(
+    user_id: str = Depends(require_permission("AUDIT_READ")),
+) -> dict[str, Any]:
+    """Return live token budget status for monitoring/alerting."""
+    try:
+        dispatcher = _get_dispatcher()
+        coordinator = getattr(dispatcher, "coordinator", None)
+        if coordinator is None:
+            return {"configured": False, "reason": "coordinator_unavailable"}
+        status = coordinator.get_budget_status()
+        if status is None:
+            return {"configured": False, "reason": "no_token_budget_attached"}
+        return {"configured": True, **status}
+    except HTTPException:
+        raise
+    except (ImportError, RuntimeError) as e:
+        logger.error("Failed to query budget status: %s", e)
+        raise HTTPException(status_code=503, detail=f"Budget status unavailable: {str(e)}") from None
+    except Exception as e:
+        logger.error("Unexpected error querying budget status: %s", e, exc_info=True)
+        raise HTTPException(status_code=500, detail=f"Failed to query budget: {str(e)}") from None