npm - agentic-qe - Versions diffs - 3.14.3 → 3.14.4 - Mend

agentic-qe 3.14.3 → 3.14.4

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 (724) hide show

package/.claude/agents/v3/qe-coverage-specialist.md CHANGED Viewed

@@ -11,7 +11,7 @@ domain: coverage-analysis
 advisor:
   enabled: true
   provider: openrouter
-  model: anthropic/claude-opus-4.7
+  model: anthropic/claude-opus-5.5
   max_uses: 3
   redact: strict
 ---

package/.claude/agents/v3/qe-fleet-commander.md CHANGED Viewed

@@ -8,7 +8,7 @@ domain: cross-domain
 advisor:
   enabled: true
   provider: openrouter
-  model: anthropic/claude-opus-4.7
+  model: anthropic/claude-opus-5.5
   max_uses: 3
   redact: strict
 ---

package/.claude/agents/v3/qe-pentest-validator.md CHANGED Viewed

@@ -10,7 +10,7 @@ effort: max
 advisor:
   enabled: true
   provider: claude
-  model: claude-opus-4-7
+  model: claude-opus-5-5
   max_uses: 3
   redact: strict
 ---

package/.claude/agents/v3/qe-queen-coordinator.md CHANGED Viewed

@@ -14,7 +14,7 @@ dependencies:
 advisor:
   enabled: true
   provider: openrouter
-  model: anthropic/claude-opus-4.7
+  model: anthropic/claude-opus-5.5
   max_uses: 3
   redact: strict
 ---

package/.claude/agents/v3/qe-risk-assessor.md CHANGED Viewed

@@ -8,7 +8,7 @@ v3_new: true
 advisor:
   enabled: true
   provider: openrouter
-  model: anthropic/claude-opus-4.7
+  model: anthropic/claude-opus-5.5
   max_uses: 3
   redact: strict
 ---

package/.claude/agents/v3/qe-root-cause-analyzer.md CHANGED Viewed

@@ -19,7 +19,7 @@ dependencies:
 advisor:
   enabled: true
   provider: openrouter
-  model: anthropic/claude-opus-4.7
+  model: anthropic/claude-opus-5.5
   max_uses: 3
   redact: strict
 ---

package/.claude/agents/v3/qe-security-auditor.md CHANGED Viewed

@@ -10,7 +10,7 @@ effort: max
 advisor:
   enabled: true
   provider: claude
-  model: claude-opus-4-7
+  model: claude-opus-5-5
   max_uses: 3
   redact: strict
 ---

package/.claude/agents/v3/qe-test-architect.md CHANGED Viewed

@@ -11,7 +11,7 @@ domain: test-generation
 advisor:
   enabled: true                    # ADR-092 Phase 0 target agent
   provider: openrouter             # Phase 0 default; any HybridRouter provider supported
-  model: anthropic/claude-opus-4.7   # Strong reasoning model via OpenRouter
+  model: anthropic/claude-opus-5.5   # Strong reasoning model via OpenRouter
   max_uses: 3                      # Per-task advisor call cap
   budget_usd_per_task: 0.05        # Per-call budget ceiling
   required: false                  # Phase 5 flips this to true for quality-gate enforcement

package/.claude/commands/aqe-costs.md CHANGED Viewed

@@ -145,7 +145,7 @@ By Provider:
     Tokens: 891,234
     Cost: $4.5678
     Avg Cost/Request: $0.018644
-    Top Model: claude-sonnet-4-6
+    Top Model: claude-sonnet-5
   ☁️ openrouter:
     Requests: 111
@@ -206,9 +206,9 @@ By Provider:
       "totalTokens": 891234,
       "totalCost": 4.5678,
       "avgCostPerRequest": 0.018644,
-      "topModel": "claude-sonnet-4-6",
+      "topModel": "claude-sonnet-5",
       "modelCounts": {
-        "claude-sonnet-4-6": 187,
+        "claude-sonnet-5": 187,
         "claude-haiku-4-5-20251001": 58
       }
     },
@@ -245,7 +245,7 @@ Recent Requests (Last 20):
   Tokens: 1,234 input / 567 output = 1,801 total
   Cost: $0.0000
-[2025-12-15T23:57:23Z] anthropic/claude-sonnet-4-6
+[2025-12-15T23:57:23Z] anthropic/claude-sonnet-5
   Agent: qe-quality-gate
   Task: quality-check-456
   Tokens: 3,456 input / 1,789 output = 5,245 total
@@ -321,7 +321,7 @@ tracker.trackRequest({
 // Track cloud inference
 tracker.trackRequest({
   provider: 'anthropic',
-  model: 'claude-sonnet-4-6',
+  model: 'claude-sonnet-5',
   tokens: {
     inputTokens: 2000,
     outputTokens: 1000,
@@ -415,11 +415,11 @@ aqe costs --period 7d --detailed
 ### Cloud Inference
-**Anthropic Claude Sonnet 4.5** (January 2025):
-- Input: $3.00 per 1M tokens
-- Output: $15.00 per 1M tokens
-- Cache write: $3.75 per 1M tokens (25% premium)
-- Cache read: $0.30 per 1M tokens (90% discount)
+**Anthropic Claude Sonnet 5** (September 2026):
+- Input: $2.00 per 1M tokens
+- Output: $10.00 per 1M tokens
+- Cache write: $2.50 per 1M tokens (25% premium)
+- Cache read: $0.20 per 1M tokens (90% discount)
 **OpenRouter** (99% savings vs Claude):
 - Llama 3.1 8B: $0.03 input / $0.15 output per 1M tokens

package/.claude/helpers/advisor-call.cjs CHANGED Viewed

@@ -61,7 +61,7 @@ const availableProviders = [];
 if (process.env.OPENROUTER_API_KEY) {
   availableProviders.push({
     name: 'openrouter',
-    model: 'anthropic/claude-opus-4',
+    model: 'anthropic/claude-opus-5.5',
     securityAllowed: false, // third-party proxy
   });
 }
@@ -69,7 +69,7 @@ if (process.env.OPENROUTER_API_KEY) {
 if (process.env.ANTHROPIC_API_KEY) {
   availableProviders.push({
     name: 'claude',
-    model: 'claude-opus-4-6',
+    model: 'claude-opus-5-5',
     securityAllowed: true,
   });
 }
@@ -77,7 +77,7 @@ if (process.env.ANTHROPIC_API_KEY) {
 if (process.env.OLLAMA_HOST || process.env.OLLAMA_BASE_URL) {
   availableProviders.push({
     name: 'ollama',
-    model: process.env.OLLAMA_ADVISOR_MODEL || 'llama3.1:70b',
+    model: process.env.OLLAMA_ADVISOR_MODEL || 'qwen3-coder:30b',
     securityAllowed: true, // self-hosted
   });
 }

package/.claude/helpers/v3/advisor-call.cjs CHANGED Viewed

@@ -61,7 +61,7 @@ const availableProviders = [];
 if (process.env.OPENROUTER_API_KEY) {
   availableProviders.push({
     name: 'openrouter',
-    model: 'anthropic/claude-opus-4',
+    model: 'anthropic/claude-opus-5.5',
     securityAllowed: false, // third-party proxy
   });
 }
@@ -69,7 +69,7 @@ if (process.env.OPENROUTER_API_KEY) {
 if (process.env.ANTHROPIC_API_KEY) {
   availableProviders.push({
     name: 'claude',
-    model: 'claude-opus-4-6',
+    model: 'claude-opus-5-5',
     securityAllowed: true,
   });
 }
@@ -77,7 +77,7 @@ if (process.env.ANTHROPIC_API_KEY) {
 if (process.env.OLLAMA_HOST || process.env.OLLAMA_BASE_URL) {
   availableProviders.push({
     name: 'ollama',
-    model: process.env.OLLAMA_ADVISOR_MODEL || 'llama3.1:70b',
+    model: process.env.OLLAMA_ADVISOR_MODEL || 'qwen3-coder:30b',
     securityAllowed: true, // self-hosted
   });
 }

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-sonnet-4-6",
+    "modelUsed": "claude-sonnet-5",
     "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-sonnet-4-6",
+    "modelUsed": "claude-sonnet-5",
     "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-sonnet-4-6",
+    "modelUsed": "claude-sonnet-5",
     "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-sonnet-4-6",
+    "modelUsed": "claude-sonnet-5",
     "inputHash": "7d865e959b2466918c9863afca942d0fb89d7c9ac0c99bafc3749504ded97730",
     "targetUrl": "https://example.com",
     "environment": "ci",

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

@@ -26,6 +26,9 @@
       "items": {
         "type": "string",
         "enum": [
+          "claude-opus-5-5",
+          "claude-opus-5",
+          "claude-sonnet-5",
           "claude-opus-4-8",
           "claude-opus-4-7",
           "claude-sonnet-4-6",
@@ -36,7 +39,7 @@
           "gpt-4-turbo"
         ]
       },
-      "default": ["claude-sonnet-4-6"],
+      "default": ["claude-sonnet-5"],
       "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-sonnet-4-6', 'claude-haiku-4-5'])"
+          "description": "Models used for evaluation testing (e.g., ['claude-sonnet-5', '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-sonnet-4-6)"
+          "description": "LLM model used for execution (e.g., claude-sonnet-5)"
         },
         "inputHash": {
           "type": "string",

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

@@ -31,7 +31,7 @@ description: >
 # model-specific quirks. Results are compared to detect variance.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
   # - gpt-4o             # Optional: cross-vendor validation

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

@@ -33,7 +33,7 @@ description: >
 models_to_test:
   - claude-opus-4-8      # Capability ceiling (high-stakes skill)
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # 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

@@ -202,7 +202,7 @@ validation:
   # Multi-model testing configuration
   validation_models:
-    - claude-sonnet-4-6
+    - claude-sonnet-5
     - claude-haiku-4-5
     - gpt-4o

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

@@ -60,7 +60,7 @@
     "executionTimeMs": 1250,
     "toolsUsed": ["eslint", "typescript", "custom-analyzer"],
     "agentId": "qe-test-architect",
-    "modelUsed": "claude-sonnet-4-6",
+    "modelUsed": "claude-sonnet-5",
     "inputHash": "sha256:abc123def456",
     "parentTaskId": "task-789"
   },

package/.claude/skills/a11y-ally/SKILL.md CHANGED Viewed

@@ -1230,7 +1230,7 @@ const client = new Anthropic();
 const imageData = fs.readFileSync('/tmp/a11y-work/frames/frame_01.jpg').toString('base64');
 const response = await client.messages.create({
-  model: 'claude-sonnet-4-6',
+  model: 'claude-sonnet-5',
   max_tokens: 500,
   messages: [{
     role: 'user',

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

@@ -23,7 +23,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -27,7 +27,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -30,7 +30,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -35,7 +35,7 @@ description: >
 models_to_test:
   - claude-opus-4-8      # Capability ceiling (high-stakes skill)
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -6,7 +6,7 @@ description: >
   and quality gate configuration across multiple models.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

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

@@ -15,7 +15,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -31,7 +31,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -30,7 +30,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -33,7 +33,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -6,7 +6,7 @@ description: >
   data validation, middleware testing, and enterprise quality gates.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

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

@@ -31,7 +31,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -6,7 +6,7 @@ description: >
   ESB error handling, and Enterprise Integration Patterns.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

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

@@ -31,7 +31,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -25,7 +25,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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-sonnet-4-6",
+    "modelUsed": "claude-sonnet-5",
     "targetPath": "src/auth",
     "testPath": "tests/auth",
     "incremental": false,

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

@@ -32,7 +32,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -32,7 +32,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -33,7 +33,7 @@ description: >
 models_to_test:
   - claude-opus-4-8      # Capability ceiling (high-stakes skill)
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

package/.claude/skills/n8n-trigger-testing-strategies/evals/n8n-trigger-testing-strategies.yaml CHANGED Viewed

@@ -31,7 +31,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

package/.claude/skills/n8n-workflow-testing-fundamentals/evals/n8n-workflow-testing-fundamentals.yaml CHANGED Viewed

@@ -32,7 +32,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -6,7 +6,7 @@ description: >
   and SLA/SLO verification.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

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

@@ -33,7 +33,7 @@ description: >
 models_to_test:
   - claude-opus-4-8      # Capability ceiling (high-stakes skill)
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -34,7 +34,7 @@ description: >
 # =============================================================================
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================

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

@@ -6,7 +6,7 @@ description: >
   deployment readiness assessment, and SHIP/CONDITIONAL/HOLD decisions.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

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

@@ -6,7 +6,7 @@ description: >
   defect prediction, and in-sprint quality signals.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

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

@@ -5,7 +5,7 @@ description: >
   Tests quality criteria generation, agent coordination, and cross-domain analysis.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

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

@@ -5,7 +5,7 @@ description: >
   Tests DORA metrics analysis, root cause analysis, defect prediction, agent coordination, and feedback loop synthesis.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

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

@@ -5,7 +5,7 @@ description: >
   Tests SFDIPOT product factor analysis, BDD generation, agent coordination, and cross-domain analysis.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

package/.claude/skills/qe-browser/evals/qe-browser.yaml CHANGED Viewed

@@ -21,7 +21,7 @@ description: >
   Any non-zero setup exit short-circuits the test as failed.
 models_to_test:
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 mcp_integration:

package/.claude/skills/qe-chaos-resilience/evals/qe-chaos-resilience.yaml CHANGED Viewed

@@ -33,7 +33,7 @@ description: >
 models_to_test:
   - claude-opus-4-8      # Capability ceiling (high-stakes skill)
-  - claude-sonnet-4-6    # Primary (high accuracy expected)
+  - claude-sonnet-5      # Primary (high accuracy expected)
   - claude-haiku-4-5     # Fast model (minimum quality floor)
 # =============================================================================