npm - agentic-qe - Versions diffs - 3.10.6 → 3.10.8 - Mend

agentic-qe 3.10.6 → 3.10.8

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 (475) hide show

package/.claude/hooks/aqe-hook.cjs CHANGED Viewed

@@ -18,7 +18,10 @@
  *     .bin/.cmd wrapper) — or fall back to `npx agentic-qe` for npx-only installs
  *     (disable that fallback with AQE_HOOK_NPX=0);
  *   * if nothing resolves, no-op (a hook must never block a turn);
- *   * SWALLOW stderr;
+ *   * keep stderr OUT of the transcript, but tee fatal native-init markers
+ *     (e.g. better-sqlite3 `invalid ELF header`) to a throttled, durable
+ *     .agentic-qe/hooks-health.log so a dead persistence layer is detectable
+ *     instead of silently dropping all learning;
  *   * emit ONLY the top-level JSON object on stdout (drop leading init noise AND
  *     trailing async daemon logs) so the --json contract stays parseable;
  *   * ALWAYS exit 0.
@@ -71,14 +74,47 @@ if (bundle) {
   process.exit(0); // no project-local AQE and npx disabled -> no-op, never block
 }
+// Fatal init markers that mean the hook ran but its persistence layer is dead
+// (e.g. a host/container native-binary mismatch clobbering better-sqlite3 —
+// `invalid ELF header`). These used to vanish into the swallowed stderr, so a
+// broken binary silently stopped ALL learning for days with zero trace. We
+// still keep stderr OUT of the transcript, but tee fatal markers to a durable,
+// throttled health log so the failure is detectable instead of invisible.
+const FATAL_MARKERS = [
+  'invalid ELF header',
+  'Failed to initialize UnifiedMemoryManager',
+  'ERR_DLOPEN_FAILED',
+  'was compiled against a different Node.js version',
+];
+function recordHookHealth(stderr) {
+  try {
+    if (!stderr) return;
+    const hit = FATAL_MARKERS.find((m) => stderr.includes(m));
+    if (!hit) return;
+    const logPath = path.join(PROJECT, '.agentic-qe', 'hooks-health.log');
+    // Throttle: skip if we logged within the last 5 min (avoid a line/turn).
+    try {
+      const st = fs.statSync(logPath);
+      if (Date.now() - st.mtimeMs < 5 * 60 * 1000) return;
+    } catch { /* no log yet — fall through and create it */ }
+    const subcmd = args[0] || 'unknown';
+    const line = `[${new Date().toISOString()}] FATAL hook persistence failure `
+      + `(cmd=${subcmd}): "${hit}". Learning is NOT being captured. `
+      + `Fix: \`npm rebuild better-sqlite3\` (host/container native-binary mismatch).\n`;
+    fs.appendFileSync(logPath, line);
+  } catch { /* health logging must never block a turn */ }
+}
 let out = '';
 try {
   const res = spawnSync(cmd, cmdArgs, {
-    stdio: ['ignore', 'pipe', 'ignore'], // swallow stdin + stderr
+    stdio: ['ignore', 'pipe', 'pipe'], // swallow stdin; capture stderr to scan
     encoding: 'utf8',
     maxBuffer: 16 * 1024 * 1024,
   });
   out = (res && res.stdout) || '';
+  recordHookHealth((res && res.stderr) || ''); // tee fatal markers to health log
 } catch { /* never block a turn */ }
 // Emit only the top-level JSON object: the first line beginning with '{' through

package/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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/.claude/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

package/.claude/skills/mutation-testing/test-data/sample-output.json CHANGED Viewed

@@ -272,7 +272,7 @@
     "executionTimeMs": 125430,
     "toolsUsed": ["stryker"],
     "agentId": "qe-mutation-tester",
-    "modelUsed": "claude-3.5-sonnet",
+    "modelUsed": "claude-sonnet-4-6",
     "targetPath": "src/auth",
     "testPath": "tests/auth",
     "incremental": false,

package/.claude/skills/n8n-expression-testing/evals/n8n-expression-testing.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/n8n-integration-testing-patterns/evals/n8n-integration-testing-patterns.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/n8n-security-testing/evals/n8n-security-testing.yaml CHANGED Viewed

@@ -32,8 +32,9 @@ description: >
 # =============================================================================
 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 Configuration

package/.claude/skills/n8n-trigger-testing-strategies/evals/n8n-trigger-testing-strategies.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/n8n-workflow-testing-fundamentals/evals/n8n-workflow-testing-fundamentals.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/observability-testing-patterns/evals/observability-testing-patterns.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   and SLA/SLO 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/pentest-validation/evals/pentest-validation.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/performance-testing/evals/performance-testing.yaml CHANGED Viewed

@@ -34,9 +34,8 @@ 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-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================
 # MCP Integration Configuration

package/.claude/skills/qcsd-cicd-swarm/evals/qcsd-cicd-swarm.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   deployment readiness assessment, and SHIP/CONDITIONAL/HOLD decisions.
 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/qcsd-development-swarm/evals/qcsd-development-swarm.yaml CHANGED Viewed

@@ -6,8 +6,8 @@ description: >
   defect prediction, and in-sprint quality signals.
 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/qcsd-ideation-swarm/evals/qcsd-ideation-swarm.yaml CHANGED Viewed

@@ -5,8 +5,8 @@ description: >
   Tests quality criteria generation, agent coordination, and cross-domain 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/qcsd-production-swarm/evals/qcsd-production-swarm.yaml CHANGED Viewed

@@ -5,8 +5,8 @@ description: >
   Tests DORA metrics analysis, root cause analysis, defect prediction, agent coordination, and feedback loop synthesis.
 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/qcsd-refinement-swarm/evals/qcsd-refinement-swarm.yaml CHANGED Viewed

@@ -5,8 +5,8 @@ description: >
   Tests SFDIPOT product factor analysis, BDD generation, agent coordination, and cross-domain 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/qe-browser/evals/qe-browser.yaml CHANGED Viewed

@@ -21,8 +21,8 @@ description: >
   Any non-zero setup exit short-circuits the test as failed.
 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-chaos-resilience/evals/qe-chaos-resilience.yaml CHANGED Viewed

@@ -32,8 +32,9 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-3.5-sonnet    # Primary model (high accuracy expected)
-  - claude-3-haiku       # Fast model (minimum quality threshold)
+  - 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/qe-code-intelligence/evals/qe-code-intelligence.yaml CHANGED Viewed

@@ -30,8 +30,8 @@ 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-coverage-analysis/evals/qe-coverage-analysis.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/qe-defect-intelligence/evals/qe-defect-intelligence.yaml CHANGED Viewed

@@ -31,8 +31,9 @@ description: >
 # =============================================================================
 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 Configuration

package/.claude/skills/qe-learning-optimization/evals/qe-learning-optimization.yaml CHANGED Viewed

@@ -5,8 +5,8 @@ description: >
   Tests pattern learning, cross-model comparison, and ReasoningBank integration.
 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
@@ -62,8 +62,8 @@ test_cases:
     input:
       models:
-        - "claude-3.5-sonnet"
-        - "claude-3-haiku"
+        - "claude-sonnet-4-6"
+        - "claude-haiku-4-5"
       test_case: "security_vulnerability"
     expected_output: