npm - agentic-qe - Versions diffs - 3.10.6 → 3.10.7 - Mend

agentic-qe 3.10.6 → 3.10.7

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (441) hide show

package/.claude/skills/qe-quality-assessment/evals/qe-quality-assessment.yaml CHANGED Viewed

@@ -31,8 +31,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/qe-requirements-validation/evals/qe-requirements-validation.yaml CHANGED Viewed

@@ -31,8 +31,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/qe-test-execution/evals/qe-test-execution.yaml CHANGED Viewed

@@ -31,8 +31,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/qe-test-generation/evals/qe-test-generation.yaml CHANGED Viewed

@@ -5,8 +5,8 @@ description: >
   Tests unit test generation, integration test creation, and edge case coverage.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/qe-visual-accessibility/evals/qe-visual-accessibility.yaml CHANGED Viewed

@@ -5,8 +5,8 @@ description: >
   Tests color blind simulation, contrast analysis, and visual hierarchy validation.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/quality-metrics/evals/quality-metrics.yaml CHANGED Viewed

@@ -31,8 +31,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-haiku-4-5
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/regression-testing/evals/regression-testing.yaml CHANGED Viewed

@@ -31,8 +31,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/risk-based-testing/evals/risk-based-testing.yaml CHANGED Viewed

@@ -5,8 +5,8 @@ description: >
   Tests risk scoring, test prioritization, and coverage optimization.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/security-testing/evals/security-testing.yaml CHANGED Viewed

@@ -32,9 +32,9 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet    # Primary model (high accuracy expected)
-  - claude-3-haiku       # Fast model (minimum quality threshold)
-  - gpt-4o               # Cross-vendor validation
+  - claude-opus-4-8      # Capability ceiling (high-stakes skill)
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/security-visual-testing/evals/security-visual-testing.yaml CHANGED Viewed

@@ -6,8 +6,9 @@ description: >
   are correctly identified and classified across both domains.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-opus-4-8      # Capability ceiling (high-stakes skill)
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/shift-left-testing/evals/shift-left-testing.yaml CHANGED Viewed

@@ -5,8 +5,8 @@ description: >
   Tests early defect detection, pre-commit checks, and development-phase validation.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/shift-right-testing/evals/shift-right-testing.yaml CHANGED Viewed

@@ -5,8 +5,8 @@ description: >
   Tests production monitoring, canary deployments, and runtime validation.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

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

@@ -939,7 +939,7 @@
   },
   "metadata": {
     "generatedBy": "Agentic QE Fleet",
-    "fleetVersion": "3.10.6",
+    "fleetVersion": "3.10.7",
     "manifestVersion": "1.4.0",
     "lastUpdated": "2026-04-13T00:00:00.000Z",
     "contributors": [

package/.claude/skills/test-automation-strategy/evals/test-automation-strategy.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   prioritization, risk assessment, and tool recommendations.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/test-data-management/evals/test-data-management.yaml CHANGED Viewed

@@ -32,8 +32,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/test-design-techniques/evals/test-design-techniques.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   equivalence partitioning, pairwise testing, and state machine modeling.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/test-reporting-analytics/evals/test-reporting-analytics.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   metrics visualization, and trend analysis.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/testability-scoring/evals/testability-scoring.yaml CHANGED Viewed

@@ -29,9 +29,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary model (high accuracy expected)
-  - claude-haiku-4-5                # Fast model (minimum quality threshold)
-  - gpt-4o                      # Cross-vendor validation
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/validation-pipeline/evals/validation-pipeline.yaml CHANGED Viewed

@@ -31,8 +31,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/verification-quality/evals/verification-quality.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   code quality analysis, and comprehensive quality assessment.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/visual-testing-advanced/evals/visual-testing-advanced.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   region analysis, and cross-viewport consistency verification.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/.claude/skills/wms-testing-patterns/evals/wms-testing-patterns.yaml CHANGED Viewed

@@ -10,7 +10,8 @@ description: >
   pick/pack/ship workflows, EDI compliance, RF scanning, and WMS-ERP integration.
 models_to_test:
-  - claude-sonnet-4
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/CHANGELOG.md CHANGED Viewed

@@ -5,6 +5,47 @@ 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).
+## [3.10.7] - 2026-06-12
+A learning-integrity and supply-chain release. Two independent bugs were
+silently halting self-learning — the hook shim swallowed fatal native-binary
+errors, and the SONA learning engine treated reward feedback as a no-op — both
+now fixed. A new CI gate validates the published package the way a real user
+installs it, and the QE skill evaluation suite is back on current models.
+### Fixed
+- **Self-learning silently stopping on a native-binary mismatch.** The hook
+  shim (`aqe-hook.cjs`) discarded all stderr and always exited 0, so a
+  wrong-platform `better-sqlite3` binary (e.g. a macOS build inside a Linux
+  container) failed to open the learning database with zero trace — dropping
+  every captured experience for days while appearing healthy. Fatal native-init
+  failures are now teed to a throttled, durable `.agentic-qe/hooks-health.log`
+  with a one-line fix hint, so the outage is detectable instead of invisible.
+- **Reward feedback not changing SONA weights.** Bumped `@ruvector/sona`
+  0.1.5 → 0.1.7, which fixes an upstream bug where feedback produced zero weight
+  changes (and negative feedback failed to "unlearn"). AQE drives that learning
+  path on every reinforced trajectory, so reward signals were effectively inert
+  until now.
+### Added
+- **Consumer-side supply-chain audit gate (CI).** A new workflow packs the
+  tarball, installs it into a clean consumer project, and audits from the
+  consumer's perspective — on every dependency-affecting PR and push to `main`,
+  not only at publish time. This catches override-masked vulnerabilities (where
+  the in-repo `npm audit` reads clean but installers are exposed) before they
+  merge.
+### Changed
+- **QE skill evaluation model matrix refreshed to current models.** All 54 skill
+  eval suites, the eval templates, the eval JSON schema, and the npm-distribution
+  copy moved off retired model IDs (`claude-3.5-sonnet`, `claude-3-haiku`) to
+  `claude-sonnet-4-6` + `claude-haiku-4-5`, with `claude-opus-4-8` added as a
+  capability ceiling for the seven high-stakes security / chaos / defect skills.
+  Evaluations were previously pinned to model IDs that no longer resolve.
 ## [3.10.6] - 2026-06-11
 The Pattern Space cross-pollination release (#522): a quality review of a

package/assets/skills/.validation/examples/chaos-engineering-output.example.json CHANGED Viewed

@@ -500,7 +500,7 @@
     "executionTimeMs": 2160000,
     "toolsUsed": ["toxiproxy", "kubectl", "stress-ng", "custom"],
     "agentId": "qe-chaos-engineer",
-    "modelUsed": "claude-3.5-sonnet",
+    "modelUsed": "claude-sonnet-4-6",
     "environment": "staging"
   },
   "validation": {

package/assets/skills/.validation/examples/performance-testing-output.example.json CHANGED Viewed

@@ -230,7 +230,7 @@
     "executionTimeMs": 305000,
     "toolsUsed": ["k6", "prometheus", "grafana"],
     "agentId": "qe-performance-tester",
-    "modelUsed": "claude-3.5-sonnet",
+    "modelUsed": "claude-sonnet-4-6",
     "targetUrl": "https://api.example.com",
     "environment": "staging"
   },

package/assets/skills/.validation/examples/security-testing-output.example.json CHANGED Viewed

@@ -380,7 +380,7 @@
     "executionTimeMs": 45230,
     "toolsUsed": ["semgrep", "npm-audit", "owasp-zap", "trivy"],
     "agentId": "qe-security-scanner",
-    "modelUsed": "claude-3.5-sonnet",
+    "modelUsed": "claude-sonnet-4-6",
     "inputHash": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
     "targetUrl": "https://example.com",
     "targetPath": "src/",

package/assets/skills/.validation/examples/testability-scoring-output.example.json CHANGED Viewed

@@ -318,7 +318,7 @@
     "executionTimeMs": 12450,
     "toolsUsed": ["playwright", "chrome-devtools", "axe-core"],
     "agentId": "qe-quality-analyzer",
-    "modelUsed": "claude-3.5-sonnet",
+    "modelUsed": "claude-sonnet-4-6",
     "inputHash": "7d865e959b2466918c9863afca942d0fb89d7c9ac0c99bafc3749504ded97730",
     "targetUrl": "https://example.com",
     "environment": "ci",

package/assets/skills/.validation/schemas/skill-eval.schema.json CHANGED Viewed

@@ -26,19 +26,17 @@
       "items": {
         "type": "string",
         "enum": [
+          "claude-opus-4-8",
           "claude-opus-4-7",
           "claude-sonnet-4-6",
           "claude-haiku-4-5",
           "claude-opus-4-5",
-          "claude-sonnet-4",
-          "claude-3.5-sonnet",
-          "claude-3-haiku",
           "gpt-4o",
           "gpt-4o-mini",
           "gpt-4-turbo"
         ]
       },
-      "default": ["claude-3.5-sonnet"],
+      "default": ["claude-sonnet-4-6"],
       "minItems": 1,
       "uniqueItems": true,
       "description": "Models to run evaluation against for cross-model validation"

package/assets/skills/.validation/schemas/skill-frontmatter.schema.json CHANGED Viewed

@@ -264,7 +264,7 @@
         "validation_models": {
           "type": "array",
           "items": { "type": "string" },
-          "description": "Models used for evaluation testing (e.g., ['claude-3.5-sonnet', 'claude-3-haiku'])"
+          "description": "Models used for evaluation testing (e.g., ['claude-sonnet-4-6', 'claude-haiku-4-5'])"
         },
         "pass_rate": {
           "type": "number",

package/assets/skills/.validation/schemas/skill-output.template.json CHANGED Viewed

@@ -120,7 +120,7 @@
         },
         "modelUsed": {
           "type": "string",
-          "description": "LLM model used for execution (e.g., claude-3.5-sonnet)"
+          "description": "LLM model used for execution (e.g., claude-sonnet-4-6)"
         },
         "inputHash": {
           "type": "string",

package/assets/skills/.validation/templates/eval.template.yaml CHANGED Viewed

@@ -31,9 +31,9 @@ description: >
 # model-specific quirks. Results are compared to detect variance.
 models_to_test:
-  - claude-3.5-sonnet    # Primary model (high accuracy expected)
-  - claude-3-haiku       # Fast model (ensure it meets minimum quality)
-  # - gpt-4o             # Optional: Cross-vendor validation
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
+  # - gpt-4o             # Optional: cross-vendor validation
 # =============================================================================
 # MCP Integration Configuration (NEW in v1.4)

package/assets/skills/.validation/templates/security-testing-eval.template.yaml CHANGED Viewed

@@ -32,8 +32,9 @@ description: >
 # model-specific quirks. Results are compared to detect variance.
 models_to_test:
-  - claude-3.5-sonnet    # Primary model (high accuracy expected)
-  - claude-3-haiku       # Fast model (ensure it meets minimum quality)
+  - claude-opus-4-8      # Capability ceiling (high-stakes skill)
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
   - gpt-4o               # Cross-vendor validation (optional)
 # =============================================================================

package/assets/skills/.validation/templates/skill-frontmatter.example.yaml CHANGED Viewed

@@ -202,8 +202,8 @@ validation:
   # Multi-model testing configuration
   validation_models:
-    - claude-3.5-sonnet
-    - claude-3-haiku
+    - claude-sonnet-4-6
+    - claude-haiku-4-5
     - gpt-4o
   # Evaluation metrics

package/assets/skills/a11y-ally/evals/a11y-ally.yaml CHANGED Viewed

@@ -23,8 +23,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/accessibility-testing/evals/accessibility-testing.yaml CHANGED Viewed

@@ -27,9 +27,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet    # Primary model (high accuracy expected)
-  - claude-haiku-4-5          # Fast model (ensure minimum quality)
-  - gpt-4o               # Cross-vendor validation
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/api-testing-patterns/evals/api-testing-patterns.yaml CHANGED Viewed

@@ -30,9 +30,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6        # Primary model (high accuracy expected)
-  - claude-haiku-4-5          # Fast model (minimum quality bar)
-  - gpt-4o                # Cross-vendor validation
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/chaos-engineering-resilience/evals/chaos-engineering-resilience.yaml CHANGED Viewed

@@ -34,9 +34,9 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet    # Primary model (high accuracy expected)
-  - claude-haiku-4-5          # Fast model (minimum quality threshold)
-  - gpt-4o               # Cross-vendor validation
+  - claude-opus-4-8      # Capability ceiling (high-stakes skill)
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/cicd-pipeline-qe-orchestrator/evals/cicd-pipeline-qe-orchestrator.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   and quality gate configuration across multiple models.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/assets/skills/compatibility-testing/evals/compatibility-testing.yaml CHANGED Viewed

@@ -15,8 +15,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/compliance-testing/evals/compliance-testing.yaml CHANGED Viewed

@@ -31,9 +31,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet    # Primary model (high accuracy expected)
-  - claude-3-haiku       # Fast model (minimum quality threshold)
-  - gpt-4o               # Cross-vendor validation
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/contract-testing/evals/contract-testing.yaml CHANGED Viewed

@@ -30,9 +30,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6        # Primary model (high accuracy expected)
-  - claude-haiku-4-5          # Fast model (minimum quality bar)
-  - gpt-4o                # Cross-vendor validation
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/database-testing/evals/database-testing.yaml CHANGED Viewed

@@ -33,9 +33,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6      # Primary model (high accuracy expected)
-  - claude-haiku-4-5         # Fast model (minimum quality threshold)
-  - gpt-4o               # Cross-vendor validation
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/enterprise-integration-testing/evals/enterprise-integration-testing.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   data validation, middleware testing, and enterprise quality gates.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/assets/skills/localization-testing/evals/localization-testing.yaml CHANGED Viewed

@@ -31,8 +31,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet    # Primary model (high accuracy expected)
-  - claude-haiku-4-5          # Fast model (minimum quality threshold)
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/middleware-testing-patterns/evals/middleware-testing-patterns.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   ESB error handling, and Enterprise Integration Patterns.
 models_to_test:
-  - claude-3.5-sonnet
-  - claude-3-haiku
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:
   enabled: true

package/assets/skills/mobile-testing/evals/mobile-testing.yaml CHANGED Viewed

@@ -31,8 +31,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet    # Primary model
-  - claude-3-haiku       # Fast model (minimum quality)
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/assets/skills/mutation-testing/evals/mutation-testing.yaml CHANGED Viewed

@@ -25,9 +25,8 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet    # Primary model (high accuracy expected)
-  - claude-3-haiku       # Fast model (ensure minimum quality)
-  - gpt-4o               # Cross-vendor validation
+  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration