agentic-qe 3.7.7 → 3.7.9

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

@@ -1,21 +1,21 @@
 {
   "$schema": "https://agentic-qe.dev/schemas/skill-manifest.json",
   "version": "2.0.0",
-  "generatedAt": "2026-02-02T10:30:07.654Z",
+  "generatedAt": "2026-03-05T12:43:31.955Z",
   "generator": "scripts/update-skill-manifest.ts",
   "trustTierPolicy": "ADR-056",
   "summary": {
-    "tier0": 39,
+    "tier0": 41,
     "tier1": 5,
     "tier2": 7,
-    "tier3": 46,
-    "total": 97
+    "tier3": 51,
+    "total": 104
   },
   "validationStatus": {
-    "passing": 46,
+    "passing": 51,
     "failing": 0,
     "unknown": 12,
-    "skipped": 39
+    "skipped": 41
   },
   "skillsByTier": {
     "tier3": [
@@ -118,6 +118,17 @@
         },
         "file": "database-testing/SKILL.md"
       },
+      {
+        "name": "enterprise-integration-testing",
+        "category": "enterprise-integration",
+        "validation": {
+          "status": "passing",
+          "schemaPath": "schemas/output.json",
+          "validatorPath": "scripts/validate-config.json",
+          "evalPath": "evals/enterprise-integration-testing.yaml"
+        },
+        "file": "enterprise-integration-testing/SKILL.md"
+      },
       {
         "name": "localization-testing",
         "category": "specialized-testing",
@@ -129,6 +140,17 @@
         },
         "file": "localization-testing/SKILL.md"
       },
+      {
+        "name": "middleware-testing-patterns",
+        "category": "enterprise-integration",
+        "validation": {
+          "status": "passing",
+          "schemaPath": "schemas/output.json",
+          "validatorPath": "scripts/validate-config.json",
+          "evalPath": "evals/middleware-testing-patterns.yaml"
+        },
+        "file": "middleware-testing-patterns/SKILL.md"
+      },
       {
         "name": "mobile-testing",
         "category": "specialized-testing",
@@ -206,6 +228,17 @@
         },
         "file": "n8n-workflow-testing-fundamentals/SKILL.md"
       },
+      {
+        "name": "observability-testing-patterns",
+        "category": "specialized-testing",
+        "validation": {
+          "status": "passing",
+          "schemaPath": "schemas/output.json",
+          "validatorPath": "scripts/validate-config.json",
+          "evalPath": "evals/observability-testing-patterns.yaml"
+        },
+        "file": "observability-testing-patterns/SKILL.md"
+      },
       {
         "name": "performance-analysis",
         "category": "monitoring",
@@ -228,6 +261,28 @@
         },
         "file": "performance-testing/SKILL.md"
       },
+      {
+        "name": "qcsd-cicd-swarm",
+        "category": "qcsd-phases",
+        "validation": {
+          "status": "passing",
+          "schemaPath": "schemas/output.json",
+          "validatorPath": "scripts/validate-config.json",
+          "evalPath": "evals/qcsd-cicd-swarm.yaml"
+        },
+        "file": "qcsd-cicd-swarm/SKILL.md"
+      },
+      {
+        "name": "qcsd-development-swarm",
+        "category": "qcsd-phases",
+        "validation": {
+          "status": "passing",
+          "schemaPath": "schemas/output.json",
+          "validatorPath": "scripts/validate-config.json",
+          "evalPath": "evals/qcsd-development-swarm.yaml"
+        },
+        "file": "qcsd-development-swarm/SKILL.md"
+      },
       {
         "name": "qcsd-ideation-swarm",
         "category": "qcsd-phases",
@@ -661,6 +716,14 @@
         "category": "testing-methodologies",
         "file": "context-driven-testing/SKILL.md"
       },
+      {
+        "name": "debug-loop",
+        "category": "debugging",
+        "validation": {
+          "status": "skipped"
+        },
+        "file": "debug-loop/SKILL.md"
+      },
       {
         "name": "exploratory-testing-advanced",
         "category": "testing-methodologies",
@@ -728,6 +791,14 @@
         "name": "pair-programming",
         "file": "pair-programming/SKILL.md"
       },
+      {
+        "name": "pr-review",
+        "category": "code-review",
+        "validation": {
+          "status": "skipped"
+        },
+        "file": "pr-review/SKILL.md"
+      },
       {
         "name": "reasoningbank-agentdb",
         "file": "reasoningbank-agentdb/SKILL.md"
@@ -2330,4 +2401,4 @@
       "lastUpdated": "2025-12-03"
     }
   }
-}
+}

package/CHANGELOG.md

@@ -5,6 +5,45 @@ All notable changes to the Agentic QE project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [3.7.9] - 2026-03-05
+
+### Added
+
+- **Multi-language test generation** — 8 new generators: Go (`go test`), Rust (`#[cfg(test)]`), Kotlin (JUnit5), Java (JUnit5), Swift (Swift Testing), Flutter (`flutter_test`), React Native (Jest), and C# (xUnit). Each generator produces idiomatic tests with language-specific patterns (e.g., Rust ownership analysis, Go table-driven tests)
+- **Compilation validation loop** — Validates generated tests compile before output, with framework-specific fix strategies
+- **Language detection** — Automatic source language detection to route to the correct test generator
+- **Trust tier eval infrastructure** — Full eval configs (YAML test cases, JSON schemas, validator scripts) for 5 skills: qcsd-cicd-swarm, qcsd-development-swarm, enterprise-integration-testing, observability-testing-patterns, middleware-testing-patterns
+
+### Fixed
+
+- **Embedding dimension standardization** — All vector dimensions unified to 384 (all-MiniLM-L6-v2), fixing mixed 384/768 dimensions across providers, tests, and config defaults
+- **Agent memory namespace paths** — Normalized namespace references in agent definitions to prevent orphaned records
+- **Asset sync coverage** — `prepare-assets.sh` now includes all 78 QE skills (previously missed 24 skills including qcsd-*, n8n-*, and other non-prefixed skills)
+
+### Changed
+
+- **Default embedding model** — Switched from `nomic-embed-text` to `all-MiniLM-L6-v2` for consistent 384-dim vectors across all providers
+- **Trust tier adjustments** — debug-loop and pr-review set to tier 0 (advisory-only, no eval infrastructure needed)
+
+## [3.7.8] - 2026-03-04
+
+### Added
+
+- **Loki-Mode adversarial quality gates (ADR-074)** — 7 new features to catch sycophantic AI outputs, hollow tests, and routing drift. All enabled by default (opt-out via config flags):
+  - **Anti-sycophancy scorer**: Detects rubber-stamp consensus via Jaccard similarity, confidence uniformity, and reasoning overlap across model votes
+  - **Test quality gates**: Catches tautological assertions (`expect(true).toBe(true)`), empty test bodies, and missing source imports in generated tests
+  - **Blind review orchestrator**: Runs N parallel test generators with varied temperatures, deduplicates results via Jaccard similarity
+  - **EMA calibration**: Exponential moving average tracks per-agent accuracy and derives dynamic voting weights, with SQLite state persistence
+  - **Edge-case injection**: Queries historical patterns from the learning store and injects proven edge cases into test generation prompts
+  - **Complexity-driven team composition**: Maps 8-dimension complexity analysis (AST + security + concurrency + API surface) to agent team composition
+  - **Auto-escalation tracker**: Consecutive failures auto-promote agent tier; consecutive successes auto-demote for cost optimization
+- **Smart experience consolidation** — Replace destructive pruning with intelligent consolidation that preserves high-value learning patterns while managing memory growth
+- **Multi-language test generation plan** — Architecture decision records (ADR-075 through ADR-079) for unified test framework type system, Tree-sitter WASM parser, compilation validation loop, backward-compatible API, and language-specific path resolution
+
+### Changed
+
+- **Loki-mode features enabled by default** — All 6 config flags (`enableSycophancyCheck`, `enableTestQualityGate`, `enableEdgeCaseInjection`, `enableEMACalibration`, `enableAutoEscalation`, `enableComplexityComposition`) default to `true` for immediate quality improvement
+
 ## [3.7.7] - 2026-03-02
 
 ### Added

package/README.md

@@ -94,6 +94,7 @@ For client-specific setup examples, see [Platform Setup Guide](docs/platform-set
 - ✅ **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
 - ✅ **Multi-Platform Support** (v3.7.4): 8 new platform integrations — GitHub Copilot, Cursor, Cline, Kilo Code, Roo Code, OpenAI Codex CLI, Windsurf, Continue.dev — with JSON/TOML/YAML config generation, behavioral rules, and `aqe platform list/setup/verify` CLI
+- ✅ **Loki-Mode Quality Gates** (v3.7.7): Anti-sycophancy scoring, test quality gates, blind review, EMA calibration, edge-case injection, complexity-driven composition, auto-escalation — enabled by default (opt-out)
 - ✅ **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)
 
@@ -299,6 +300,41 @@ aqe learning stats
 
 ---
 
+### 🛡️ Loki-Mode Quality Gates (v3.7.7)
+
+V3.7.7 adds **7 adversarial quality features** inspired by loki-mode — designed to catch sycophantic AI outputs, hollow tests, and routing drift. All features are **enabled by default** (opt-out via config flags).
+
+| Feature | Config Flag | Description |
+|---------|------------|-------------|
+| **Anti-Sycophancy Scorer** | `enableSycophancyCheck` | Detects rubber-stamp consensus via Jaccard similarity, confidence uniformity, and reasoning overlap |
+| **Test Quality Gates** | `enableTestQualityGate` | Catches tautological assertions (`expect(true).toBe(true)`), empty test bodies, and missing source imports |
+| **Blind Review** | N/A (API option) | Runs N parallel test generators with varied temperatures, deduplicates via Jaccard |
+| **EMA Calibration** | `enableEMACalibration` | Exponential moving average tracks per-agent accuracy, derives dynamic voting weights |
+| **Edge-Case Injection** | `enableEdgeCaseInjection` | Queries historical patterns and injects proven edge cases into test generation prompts |
+| **Complexity Composition** | `enableComplexityComposition` | Maps 8-dimension complexity (AST + security + concurrency) to agent team composition |
+| **Auto-Escalation** | `enableAutoEscalation` | Consecutive failures auto-promote agent tier; consecutive successes auto-demote |
+
+```typescript
+// All features are ON by default. To disable specific features:
+const config: Partial<RoutingConfig> = {
+  enableEMACalibration: false,    // Disable EMA voting weights
+  enableAutoEscalation: false,    // Disable auto tier promotion
+};
+
+const consensusConfig: Partial<ConsensusEngineConfig> = {
+  enableSycophancyCheck: false,   // Disable rubber-stamp detection
+};
+
+const testConfig: Partial<TestGeneratorConfig> = {
+  enableTestQualityGate: false,   // Disable tautology detection
+  enableEdgeCaseInjection: false, // Disable pattern injection
+};
+```
+
+> See [docs/loki-mode-features.md](docs/loki-mode-features.md) for detailed usage examples and configuration reference.
+
+---
+
 ### 🌙 Dream Cycles & Neural Learning
 
 V3 introduces **Dream cycles** for neural consolidation and continuous improvement: