devsquad 3.6.6__tar.gz → 3.6.7__tar.gz

{devsquad-3.6.6 → devsquad-3.6.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devsquad
-Version: 3.6.6
+Version: 3.6.7
 Summary: Production-Ready Multi-Role AI Task Orchestrator
 Author-email: DevSquad Team <devsquad@example.com>
 License: MIT
@@ -89,8 +89,8 @@ Dynamic: license-file
 <p align="center">
   <img alt="Python" src="https://img.shields.io/badge/Python-3.9+-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-1731%20passing-brightgreen" />
-  <img alt="Version" src="https://img.shields.io/badge/V3.6.6-success" />
+  <img alt="Tests" src="https://img.shields.io/badge/Tests-1855%20passing-brightgreen" />
+  <img alt="Version" src="https://img.shields.io/badge/V3.6.7-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 +151,9 @@ 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>
 
-## 🚀 V3.6.6: Enterprise Edition Release
+## 🚀 V3.6.7: Redis Cache + Async Dispatch + Dispatcher Refactor
 
-**DevSquad V3.6.6** adds enterprise-grade features and comprehensive E2E testing: RBAC Engine with 15+ permissions and 5 roles, Audit Logger with SHA256 integrity chain, Multi-Tenancy Manager with 3 isolation levels, Sensitive Data Masker for PII protection, AsyncIO transformation for 2x throughput improvement, Redis Cache Integration with L1→L2→L3 three-level cache achieving 95%+ hit rate, Prometheus Monitoring with 12 core metrics, E2E Test Suite with 27 test cases covering 5 scenarios (CLI/API/Collaboration/Enterprise/Error Recovery) with 100% pass rate in 9 seconds, Code Quality improvements including print() → logging migration, TODO/FIXME cleanup, pre-commit hooks, and .editorconfig — making DevSquad truly enterprise-ready with 13,000+ lines new code, 1731 tests passing, and 97% maturity score.
+**DevSquad V3.6.7** adds Redis Cache L2 backend for three-tier caching (memory→disk→Redis), async dispatch with `asyncio.gather` for concurrent LLM calls, dispatcher refactored from 788-line monolith into 18 step methods (extracted `dispatch_models.py` and `dispatch_performance.py`), fixed `DispatchResult.to_dict()`/`to_markdown()` missing 5 fields (data loss bug), cleaned up `except:pass` patterns, removed redundant `to_dict()` wrappers, and restored 183 previously xfailed tests — bringing total to 1855 tests passing with CI re-enabled.
 
 ---
 
@@ -254,7 +254,7 @@ User Task → [InputValidator] → [RoleMatcher] → [Coordinator Orchestration]
 
 | Module | Purpose | When to Use |
 |--------|---------|------------|
-| **InputValidator** | Security validation + 21-pattern prompt injection detection | Production environments |
+| **InputValidator** | Security validation + 40-pattern detection (14 forbidden + 21 prompt injection + 5 suspicious) | Production environments |
 | **VerificationGate** | Mandatory evidence requirements + 7 Red Flags detection | Critical decision scenarios |
 | **AntiRationalizationEngine** | Per-role excuse→rebuttal tables to prevent quality shortcuts | High quality requirements |
 | **TestQualityGuard** | Test quality audit (API validation / anti-pattern detection / dimension coverage) | Pre-release verification |
@@ -579,11 +579,11 @@ python3 scripts/cli.py roles           # Expected: 7 core roles listed
 
 ### Full Test Suite
 ```bash
-# Run all tests (1731 tests passing)
+# Run all tests (1855 tests passing)
 python3 -m pytest tests/ -q --tb=line
 
 # With coverage report
-python3 -m pytest tests/ --cov=scripts --cov-report=term-missing --cov-fail-under=80
+python3 -m pytest tests/ --cov=scripts --cov-report=term-missing
 ```
 
 ### Test Layering Strategy
@@ -596,7 +596,7 @@ python3 -m pytest tests/ --cov=scripts --cov-report=term-missing --cov-fail-unde
 | **P2** | Integration & E2E | Full lifecycle dispatch, cross-module integration | ~200 |
 | **P3** | Unit per Module | Core dispatcher, RoleMapping, MCEAdapter, LLM backends | ~400+ |
 
-**Total: 1731 tests**
+**Total: 1855 tests**
 
 Run by priority:
 ```bash
@@ -660,6 +660,6 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 
 ---
 
-*Last updated: 2026-05-23 | Version: V3.6.6*
+*Last updated: 2026-06-07 | Version: V3.6.7*
 
 </details>

{devsquad-3.6.6 → devsquad-3.6.7}/README.md

@@ -9,8 +9,8 @@
 <p align="center">
   <img alt="Python" src="https://img.shields.io/badge/Python-3.9+-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-1731%20passing-brightgreen" />
-  <img alt="Version" src="https://img.shields.io/badge/V3.6.6-success" />
+  <img alt="Tests" src="https://img.shields.io/badge/Tests-1855%20passing-brightgreen" />
+  <img alt="Version" src="https://img.shields.io/badge/V3.6.7-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 +71,9 @@ 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>
 
-## 🚀 V3.6.6: Enterprise Edition Release
+## 🚀 V3.6.7: Redis Cache + Async Dispatch + Dispatcher Refactor
 
-**DevSquad V3.6.6** adds enterprise-grade features and comprehensive E2E testing: RBAC Engine with 15+ permissions and 5 roles, Audit Logger with SHA256 integrity chain, Multi-Tenancy Manager with 3 isolation levels, Sensitive Data Masker for PII protection, AsyncIO transformation for 2x throughput improvement, Redis Cache Integration with L1→L2→L3 three-level cache achieving 95%+ hit rate, Prometheus Monitoring with 12 core metrics, E2E Test Suite with 27 test cases covering 5 scenarios (CLI/API/Collaboration/Enterprise/Error Recovery) with 100% pass rate in 9 seconds, Code Quality improvements including print() → logging migration, TODO/FIXME cleanup, pre-commit hooks, and .editorconfig — making DevSquad truly enterprise-ready with 13,000+ lines new code, 1731 tests passing, and 97% maturity score.
+**DevSquad V3.6.7** adds Redis Cache L2 backend for three-tier caching (memory→disk→Redis), async dispatch with `asyncio.gather` for concurrent LLM calls, dispatcher refactored from 788-line monolith into 18 step methods (extracted `dispatch_models.py` and `dispatch_performance.py`), fixed `DispatchResult.to_dict()`/`to_markdown()` missing 5 fields (data loss bug), cleaned up `except:pass` patterns, removed redundant `to_dict()` wrappers, and restored 183 previously xfailed tests — bringing total to 1855 tests passing with CI re-enabled.
 
 ---
 
@@ -174,7 +174,7 @@ User Task → [InputValidator] → [RoleMatcher] → [Coordinator Orchestration]
 
 | Module | Purpose | When to Use |
 |--------|---------|------------|
-| **InputValidator** | Security validation + 21-pattern prompt injection detection | Production environments |
+| **InputValidator** | Security validation + 40-pattern detection (14 forbidden + 21 prompt injection + 5 suspicious) | Production environments |
 | **VerificationGate** | Mandatory evidence requirements + 7 Red Flags detection | Critical decision scenarios |
 | **AntiRationalizationEngine** | Per-role excuse→rebuttal tables to prevent quality shortcuts | High quality requirements |
 | **TestQualityGuard** | Test quality audit (API validation / anti-pattern detection / dimension coverage) | Pre-release verification |
@@ -499,11 +499,11 @@ python3 scripts/cli.py roles           # Expected: 7 core roles listed
 
 ### Full Test Suite
 ```bash
-# Run all tests (1731 tests passing)
+# Run all tests (1855 tests passing)
 python3 -m pytest tests/ -q --tb=line
 
 # With coverage report
-python3 -m pytest tests/ --cov=scripts --cov-report=term-missing --cov-fail-under=80
+python3 -m pytest tests/ --cov=scripts --cov-report=term-missing
 ```
 
 ### Test Layering Strategy
@@ -516,7 +516,7 @@ python3 -m pytest tests/ --cov=scripts --cov-report=term-missing --cov-fail-unde
 | **P2** | Integration & E2E | Full lifecycle dispatch, cross-module integration | ~200 |
 | **P3** | Unit per Module | Core dispatcher, RoleMapping, MCEAdapter, LLM backends | ~400+ |
 
-**Total: 1731 tests**
+**Total: 1855 tests**
 
 Run by priority:
 ```bash
@@ -580,6 +580,6 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 
 ---
 
-*Last updated: 2026-05-23 | Version: V3.6.6*
+*Last updated: 2026-06-07 | Version: V3.6.7*
 
 </details>

{devsquad-3.6.6 → devsquad-3.6.7}/devsquad.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: devsquad
-Version: 3.6.6
+Version: 3.6.7
 Summary: Production-Ready Multi-Role AI Task Orchestrator
 Author-email: DevSquad Team <devsquad@example.com>
 License: MIT
@@ -89,8 +89,8 @@ Dynamic: license-file
 <p align="center">
   <img alt="Python" src="https://img.shields.io/badge/Python-3.9+-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-1731%20passing-brightgreen" />
-  <img alt="Version" src="https://img.shields.io/badge/V3.6.6-success" />
+  <img alt="Tests" src="https://img.shields.io/badge/Tests-1855%20passing-brightgreen" />
+  <img alt="Version" src="https://img.shields.io/badge/V3.6.7-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 +151,9 @@ 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>
 
-## 🚀 V3.6.6: Enterprise Edition Release
+## 🚀 V3.6.7: Redis Cache + Async Dispatch + Dispatcher Refactor
 
-**DevSquad V3.6.6** adds enterprise-grade features and comprehensive E2E testing: RBAC Engine with 15+ permissions and 5 roles, Audit Logger with SHA256 integrity chain, Multi-Tenancy Manager with 3 isolation levels, Sensitive Data Masker for PII protection, AsyncIO transformation for 2x throughput improvement, Redis Cache Integration with L1→L2→L3 three-level cache achieving 95%+ hit rate, Prometheus Monitoring with 12 core metrics, E2E Test Suite with 27 test cases covering 5 scenarios (CLI/API/Collaboration/Enterprise/Error Recovery) with 100% pass rate in 9 seconds, Code Quality improvements including print() → logging migration, TODO/FIXME cleanup, pre-commit hooks, and .editorconfig — making DevSquad truly enterprise-ready with 13,000+ lines new code, 1731 tests passing, and 97% maturity score.
+**DevSquad V3.6.7** adds Redis Cache L2 backend for three-tier caching (memory→disk→Redis), async dispatch with `asyncio.gather` for concurrent LLM calls, dispatcher refactored from 788-line monolith into 18 step methods (extracted `dispatch_models.py` and `dispatch_performance.py`), fixed `DispatchResult.to_dict()`/`to_markdown()` missing 5 fields (data loss bug), cleaned up `except:pass` patterns, removed redundant `to_dict()` wrappers, and restored 183 previously xfailed tests — bringing total to 1855 tests passing with CI re-enabled.
 
 ---
 
@@ -254,7 +254,7 @@ User Task → [InputValidator] → [RoleMatcher] → [Coordinator Orchestration]
 
 | Module | Purpose | When to Use |
 |--------|---------|------------|
-| **InputValidator** | Security validation + 21-pattern prompt injection detection | Production environments |
+| **InputValidator** | Security validation + 40-pattern detection (14 forbidden + 21 prompt injection + 5 suspicious) | Production environments |
 | **VerificationGate** | Mandatory evidence requirements + 7 Red Flags detection | Critical decision scenarios |
 | **AntiRationalizationEngine** | Per-role excuse→rebuttal tables to prevent quality shortcuts | High quality requirements |
 | **TestQualityGuard** | Test quality audit (API validation / anti-pattern detection / dimension coverage) | Pre-release verification |
@@ -579,11 +579,11 @@ python3 scripts/cli.py roles           # Expected: 7 core roles listed
 
 ### Full Test Suite
 ```bash
-# Run all tests (1731 tests passing)
+# Run all tests (1855 tests passing)
 python3 -m pytest tests/ -q --tb=line
 
 # With coverage report
-python3 -m pytest tests/ --cov=scripts --cov-report=term-missing --cov-fail-under=80
+python3 -m pytest tests/ --cov=scripts --cov-report=term-missing
 ```
 
 ### Test Layering Strategy
@@ -596,7 +596,7 @@ python3 -m pytest tests/ --cov=scripts --cov-report=term-missing --cov-fail-unde
 | **P2** | Integration & E2E | Full lifecycle dispatch, cross-module integration | ~200 |
 | **P3** | Unit per Module | Core dispatcher, RoleMapping, MCEAdapter, LLM backends | ~400+ |
 
-**Total: 1731 tests**
+**Total: 1855 tests**
 
 Run by priority:
 ```bash
@@ -660,6 +660,6 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 
 ---
 
-*Last updated: 2026-05-23 | Version: V3.6.6*
+*Last updated: 2026-06-07 | Version: V3.6.7*
 
 </details>

{devsquad-3.6.6 → devsquad-3.6.7}/devsquad.egg-info/SOURCES.txt

@@ -16,7 +16,6 @@ scripts/alert_manager.py
 scripts/api_server.py
 scripts/auth.py
 scripts/cli.py
-scripts/code_quality.py
 scripts/dashboard.py
 scripts/generate_benchmark_report.py
 scripts/history_manager.py
@@ -34,14 +33,12 @@ scripts/cli/cli_visual.py
 scripts/collaboration/__init__.py
 scripts/collaboration/_version.py
 scripts/collaboration/adaptive_role_selector.py
-scripts/collaboration/adaptive_role_selector_test.py
 scripts/collaboration/agent_briefing.py
 scripts/collaboration/ai_semantic_matcher.py
 scripts/collaboration/anchor_checker.py
 scripts/collaboration/anti_rationalization.py
 scripts/collaboration/async_adapter.py
 scripts/collaboration/async_coordinator.py
-scripts/collaboration/async_integration_example.py
 scripts/collaboration/async_llm_backend.py
 scripts/collaboration/audit_logger.py
 scripts/collaboration/batch_scheduler.py
@@ -55,17 +52,16 @@ scripts/collaboration/config_loader.py
 scripts/collaboration/consensus.py
 scripts/collaboration/context_compressor.py
 scripts/collaboration/coordinator.py
+scripts/collaboration/dispatch_models.py
+scripts/collaboration/dispatch_performance.py
 scripts/collaboration/dispatcher.py
 scripts/collaboration/dual_layer_context.py
 scripts/collaboration/enhanced_worker.py
 scripts/collaboration/execution_guard.py
-scripts/collaboration/execution_guard_test.py
 scripts/collaboration/feature_usage_tracker.py
 scripts/collaboration/feedback_control_loop.py
-scripts/collaboration/feedback_control_loop_test.py
 scripts/collaboration/five_axis_consensus.py
 scripts/collaboration/input_validator.py
-scripts/collaboration/integration_example.py
 scripts/collaboration/intent_workflow_mapper.py
 scripts/collaboration/language_parsers.py
 scripts/collaboration/lifecycle_protocol.py
@@ -98,11 +94,11 @@ scripts/collaboration/role_template_market.py
 scripts/collaboration/rule_collector.py
 scripts/collaboration/scratchpad.py
 scripts/collaboration/similar_task_recommender.py
-scripts/collaboration/similar_task_recommender_test.py
+scripts/collaboration/skill_extractor.py
 scripts/collaboration/skill_registry.py
+scripts/collaboration/skill_storage.py
 scripts/collaboration/skillifier.py
 scripts/collaboration/standardized_role_template.py
-scripts/collaboration/structured_logging.py
 scripts/collaboration/task_completion_checker.py
 scripts/collaboration/test_quality_guard.py
 scripts/collaboration/unified_gate_engine.py
@@ -112,6 +108,16 @@ scripts/collaboration/verification_gate.py
 scripts/collaboration/warmup_manager.py
 scripts/collaboration/worker.py
 scripts/collaboration/workflow_engine.py
+scripts/collaboration/_archived/__init__.py
+scripts/collaboration/_archived/adaptive_role_selector_test.py
+scripts/collaboration/_archived/async_integration_example.py
+scripts/collaboration/_archived/code_quality.py
+scripts/collaboration/_archived/execution_guard_test.py
+scripts/collaboration/_archived/feedback_control_loop_test.py
+scripts/collaboration/_archived/integration_example.py
+scripts/collaboration/_archived/multi_level_cache.py
+scripts/collaboration/_archived/similar_task_recommender_test.py
+scripts/collaboration/_archived/structured_logging.py
 skills/__init__.py
 skills/registry.py
 skills/dispatch/handler.py

{devsquad-3.6.6 → devsquad-3.6.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "devsquad"
-version = "3.6.6"
+version = "3.6.7"
 description = "Production-Ready Multi-Role AI Task Orchestrator"
 readme = "README.md"
 license = {text = "MIT"}
@@ -158,7 +158,7 @@ module = "tests.*"
 disallow_untyped_defs = false
 
 [tool.pytest.ini_options]
-testpaths = ["tests", "scripts/collaboration"]
+testpaths = ["tests"]
 python_files = ["test_*.py", "*_test.py"]
 python_classes = ["Test*"]
 python_functions = ["test_*"]
@@ -166,10 +166,6 @@ addopts = [
     "-v",
     "--tb=short",
     "--strict-markers",
-    "--cov=scripts",
-    "--cov-report=term-missing",
-    "--cov-report=html:htmlcov",
-    "--cov-fail-under=80",
 ]
 markers = [
     "slow: marks tests as slow (deselect with '-m \"not slow\"')",

{devsquad-3.6.6 → devsquad-3.6.7}/scripts/MANUAL_PUBLISHING_GUIDE.md

@@ -27,7 +27,7 @@
 4. **更新 Description** 为以下内容：
 
 ```
-🚀 DevSquad V3.6.6 - Enterprise Multi-Role AI Task Orchestrator | 7-Agent Collaboration | RBAC | Audit Log | E2E Tested | 1731 Tests | PyPI Ready
+🚀 DevSquad V3.6.6 - Enterprise Multi-Role AI Task Orchestrator | 7-Agent Collaboration | RBAC | Audit Log | E2E Tested | 1672 Tests | PyPI Ready
 ```
 
 5. **添加 Topics** (在 Topics 输入框中，用逗号或回车分隔)：

{devsquad-3.6.6 → devsquad-3.6.7}/scripts/PUBLISHING_GUIDE.md

@@ -76,7 +76,7 @@ curl -X PATCH \
 3. 滚动到 "About" 区域
 4. 更新 Description 为：
    ```
-   🚀 DevSquad V3.6.6 - Enterprise Multi-Role AI Task Orchestrator | 7-Agent Collaboration | RBAC | Audit Log | E2E Tested | 1731 Tests | PyPI Ready
+   🚀 DevSquad V3.6.6 - Enterprise Multi-Role AI Task Orchestrator | 7-Agent Collaboration | RBAC | Audit Log | E2E Tested | 1672 Tests | PyPI Ready
    ```
 5. 添加 Topics (最多20个):
    ```
@@ -174,7 +174,7 @@ Great news! DevSquad V3.6.6 is now available with major enterprise features:
 🆕 What's New:
 • Enterprise Security: RBAC + Audit Logging + PII Masking
 • Performance Boost: 2x faster with AsyncIO + Redis cache
-• Quality Assurance: 27 E2E tests (100% pass rate)
+• Quality Assurance: 16 User Journey E2E tests (100% pass rate)
 • Code Quality: Full logging migration + pre-commit hooks
 
 📦 Upgrade Today:

{devsquad-3.6.6 → devsquad-3.6.7}/scripts/api/routes/metrics_gates.py

@@ -330,7 +330,7 @@ async def health_check():
 
         return HealthCheck(
             status=overall_status,
-            version="3.6.0",
+            version="3.6.7",
             uptime_seconds=round(uptime, 2),
             components=components,
             timestamp=datetime.now(),
@@ -340,7 +340,7 @@ async def health_check():
         logger.error(f"Health check failed: {e}")
         return HealthCheck(
             status="unhealthy",
-            version="3.6.0",
+            version="3.6.7",
             uptime_seconds=time.time() - _start_time,
             components={"error": str(e)},
             timestamp=datetime.now(),

{devsquad-3.6.6 → devsquad-3.6.7}/scripts/api_server.py

@@ -83,10 +83,10 @@ app = FastAPI(
 
     ---
 
-    **Version**: 3.6.1
+    **Version**: 3.6.7
     **Base URL**: `/api/v1`
     """,
-    version="3.6.1",
+    version="3.6.7",
     docs_url="/docs",  # Swagger UI
     redoc_url="/redoc",  # ReDoc
     openapi_url="/openapi.json",  # OpenAPI spec
@@ -102,13 +102,20 @@ app = FastAPI(
 )
 
 # Add CORS middleware
-# Configure allowed origins - use wildcard for development, restrict in production
-allowed_origins = [
-    "http://localhost:8501",  # DevSquad Dashboard
-    "http://localhost:8000",  # API Server
-    "http://localhost:3000",  # Frontend dev server
-    "*",  # Allow all origins (restrict in production)
-]
+# ⚠️  Do NOT use wildcard "*" with allow_credentials=True (CORS spec violation)
+# Configure allowed origins explicitly; use env var DEVSQUAD_CORS_ORIGINS in production
+import os as _os
+
+_cors_origins_str = _os.environ.get("DEVSQUAD_CORS_ORIGINS", "")
+if _cors_origins_str:
+    allowed_origins = [o.strip() for o in _cors_origins_str.split(",") if o.strip()]
+else:
+    # Development defaults only - no wildcard with credentials
+    allowed_origins = [
+        "http://localhost:8501",  # DevSquad Dashboard
+        "http://localhost:8000",  # API Server
+        "http://localhost:3000",  # Frontend dev server
+    ]
 
 app.add_middleware(
     CORSMiddleware,
@@ -211,7 +218,7 @@ async def root():
     """
     return {
         "name": "DevSquad API",
-        "version": "3.6.0",
+        "version": "3.6.7",
         "description": "Production REST API for DevSquad multi-agent collaboration",
         "documentation": {"swagger_ui": "/docs", "redoc": "/redoc", "openapi_spec": "/openapi.json"},
         "endpoints": {

{devsquad-3.6.6 → devsquad-3.6.7}/scripts/auth.py

@@ -221,15 +221,21 @@ class AuthManager:
             import streamlit as st
 
             if not self.auth_enabled:
-                # Authentication disabled, set default admin user
+                # Authentication disabled, set default viewer user (NOT admin!)
+                # ⚠️  Without auth, grant minimum privilege only.
+                #     If admin access is needed, enable authentication.
                 if "user" not in st.session_state:
                     st.session_state.user = User(
-                        username="admin",
-                        email="admin@devsquad.local",
-                        name="Administrator",
-                        role=UserRole.ADMIN,
+                        username="anonymous",
+                        email="anonymous@devsquad.local",
+                        name="Anonymous Viewer",
+                        role=UserRole.VIEWER,
                         authenticated_at=datetime.now(),
-                        session_id="dev_mode",
+                        session_id="no_auth_mode",
+                    )
+                    _logger.warning(
+                        "Auth disabled: granting VIEWER role (not admin). "
+                        "Enable authentication for admin access."
                     )
                 return
 
@@ -445,7 +451,7 @@ def create_demo_credentials():
     _logger.info("=" * 50)
     for username, info in demo_users.items():
         _logger.info("Username: %s, Role: %s", username, info["role"])
-        _logger.info("Hashed Password: %s", info["password"][:20] + "...")
+        # ⚠️  Do NOT log password hashes (even partial) - security risk
 
     _logger.info("\n" + "=" * 50)
     _logger.info("⚠️  Set passwords via environment variables:")

{devsquad-3.6.6 → devsquad-3.6.7}/scripts/cli.py

@@ -17,7 +17,7 @@ import os
 import sys
 
 if sys.version_info < (3, 9):
-    logger.error("Error: DevSquad requires Python 3.9+. Current: %s", sys.version)
+    print("Error: DevSquad requires Python 3.9+. Current: %s" % sys.version, file=sys.stderr)
     sys.exit(1)
 
 sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))

{devsquad-3.6.6 → devsquad-3.6.7}/scripts/collaboration/__init__.py

@@ -90,6 +90,12 @@ from .llm_retry import (
     retry_with_fallback,
 )
 
+# Async LLM Retry exports
+from .llm_retry_async import AsyncLLMRetryManager
+
+# Multi-Level Cache exports
+from .multi_level_cache import MemoryCacheBackend, MultiLevelCacheCoordinator
+
 # Data models exports
 from .models import (
     ROLE_WEIGHTS,
@@ -146,6 +152,9 @@ __all__ = [
     "CacheEntry",
     "get_llm_cache",
     "reset_cache",
+    # Multi-Level Cache
+    "MultiLevelCacheCoordinator",
+    "MemoryCacheBackend",
     # Retry
     "LLMRetryManager",
     "RetryConfig",
@@ -154,6 +163,8 @@ __all__ = [
     "CircuitBreakerError",
     "get_retry_manager",
     "retry_with_fallback",
+    # Async Retry
+    "AsyncLLMRetryManager",
     # Monitor
     "PerformanceMonitor",
     "PerformanceMetric",

devsquad-3.6.7/scripts/collaboration/_version.py

@@ -0,0 +1 @@
+__version__ = "3.6.7"

{devsquad-3.6.6 → devsquad-3.6.7}/scripts/collaboration/agent_briefing.py

@@ -58,10 +58,6 @@ class BriefingSection:
     timestamp: float = field(default_factory=lambda: datetime.now().timestamp())
     metadata: dict[str, Any] = field(default_factory=dict)
 
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dictionary"""
-        return asdict(self)
-
 
 @dataclass
 class AgentContext:
@@ -73,10 +69,6 @@ class AgentContext:
     preferences: dict[str, Any] = field(default_factory=dict)
     history: list[dict[str, Any]] = field(default_factory=list)
 
-    def to_dict(self) -> dict[str, Any]:
-        """Convert to dictionary"""
-        return asdict(self)
-
 
 class AgentBriefing:
     """
@@ -302,8 +294,8 @@ class AgentBriefing:
                     stack.setdefault("Database", []).append("SQLite")
                 if "pyyaml" in content.lower() or "yaml" in content.lower():
                     stack.setdefault("Config", []).append("YAML")
-            except Exception:
-                pass
+            except (OSError, UnicodeDecodeError) as e:
+                logger.debug("Could not read %s for tech stack detection: %s", pyproject, e)
 
         dockerfile = root / "Dockerfile"
         if dockerfile.exists():
@@ -508,8 +500,8 @@ class AgentBriefing:
         briefing_data = {
             "agent_role": self.agent_role,
             "project_context": self.project_context,
-            "agent_context": self.agent_context.to_dict(),
-            "sections": {title: section.to_dict() for title, section in self.sections.items()},
+            "agent_context": asdict(self.agent_context),
+            "sections": {title: asdict(section) for title, section in self.sections.items()},
             "exported_at": datetime.now().isoformat(),
         }
 
@@ -540,8 +532,8 @@ class AgentBriefing:
             briefing_data = {
                 "agent_role": self.agent_role,
                 "project_context": self.project_context,
-                "agent_context": self.agent_context.to_dict(),
-                "sections": {title: section.to_dict() for title, section in self.sections.items()},
+                "agent_context": asdict(self.agent_context),
+                "sections": {title: asdict(section) for title, section in self.sections.items()},
                 "updated_at": datetime.now().isoformat(),
             }
 
@@ -589,11 +581,11 @@ def get_agent_briefing(
 
 def reset_briefings() -> None:
     """Reset all briefing instances (for testing)"""
-    global _briefing_instances
+    global _briefing_instances  # noqa: F824
     _briefing_instances.clear()
 
 
-__version__ = "3.6.0"
+__version__ = "3.6.7"
 __all__ = [
     "AgentBriefing",
     "BriefingSection",

{devsquad-3.6.6 → devsquad-3.6.7}/scripts/collaboration/async_coordinator.py

@@ -144,6 +144,7 @@ class AsyncCoordinator:
         briefing_mode: bool = True,
         task_timeout: Optional[float] = None,
         max_concurrency: int = MAX_CONCURRENCY,
+        enable_retry: bool = False,
     ) -> None:
         """
         Initialize AsyncCoordinator.
@@ -158,6 +159,8 @@ class AsyncCoordinator:
             briefing_mode: Enable inter-Agent briefing handoff
             task_timeout: Per-task timeout in seconds (None=no limit)
             max_concurrency: Maximum concurrent workers
+            enable_retry: Enable AsyncLLMRetryManager for LLM calls with
+                exponential backoff, circuit breaker, and fallback support
         """
         self.scratchpad = scratchpad or Scratchpad(persist_dir=persist_dir)
         self.consensus = ConsensusEngine()
@@ -181,6 +184,19 @@ class AsyncCoordinator:
         self.max_concurrency = max_concurrency
         self._semaphore: Optional[asyncio.Semaphore] = None
 
+        # Retry support
+        self.enable_retry = enable_retry
+        self._retry_manager: Optional[Any] = None
+        if enable_retry:
+            try:
+                from .llm_retry_async import AsyncLLMRetryManager
+                self._retry_manager = AsyncLLMRetryManager()
+                logger.info("AsyncLLMRetryManager enabled for AsyncCoordinator")
+            except Exception as e:
+                logger.warning("AsyncLLMRetryManager init failed: %s", e)
+                self.enable_retry = False
+                self._retry_manager = None
+
     async def _get_semaphore(self) -> asyncio.Semaphore:
         if self._semaphore is None:
             self._semaphore = asyncio.Semaphore(self.max_concurrency)
@@ -434,7 +450,10 @@ class AsyncCoordinator:
                     self._inject_briefing_to_worker(worker)
 
                 try:
-                    result = await async_worker.execute(task)
+                    if self.enable_retry and self._retry_manager is not None:
+                        result = await self._execute_with_retry(async_worker, task)
+                    else:
+                        result = await async_worker.execute(task)
                     if self.briefing_mode:
                         self._collect_briefing_from_worker(worker)
                     return result
@@ -475,6 +494,24 @@ class AsyncCoordinator:
             )
         return self._async_workers[worker_id]
 
+    async def _execute_with_retry(
+        self, async_worker: AsyncWorkerWrapper, task: TaskDefinition
+    ) -> WorkerResult:
+        """Execute a worker task with retry and fallback via AsyncLLMRetryManager."""
+        from .llm_retry_async import RetryConfig
+
+        config = RetryConfig(max_retries=3, initial_delay=1.0, max_delay=60.0)
+        current_backend = getattr(self.llm_backend, "backend_name", None)
+
+        return await self._retry_manager.retry_with_fallback(
+            func=async_worker.execute,
+            args=(task,),
+            kwargs={},
+            config=config,
+            fallback_backends=None,
+            current_backend=current_backend,
+        )
+
     def _buffer_worker_messages(
         self, batch_results: List[WorkerResult]
     ) -> None: