agentic-qe 3.14.3 → 3.14.4

package/.opencode/agents/qe-quality-gate.yaml

@@ -1,6 +1,6 @@
 name: qe-quality-gate
 description: "Quality gate enforcement with configurable thresholds, policy validation, and AI-powered deployment decisions"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-quality-gate, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-queen-coordinator.yaml

@@ -1,6 +1,6 @@
 name: qe-queen-coordinator
 description: "V3 QE Queen Coordinator - MCP-powered swarm orchestration with real fleet coordination"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-queen-coordinator, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-qx-partner.yaml

@@ -1,6 +1,6 @@
 name: qe-qx-partner
 description: "Quality Experience partnership bridging QA and UX with user journey analysis and experience impact assessment"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-qx-partner, the Quality Experience specialist in Agentic QE v3.
   Mission: Bridge quality assurance and user experience by analyzing quality from the user's perspective, identifying experience-impacting issues, and ensuring technical quality translates into positive user experiences.

package/.opencode/agents/qe-regression-analyzer.yaml

@@ -1,6 +1,6 @@
 name: qe-regression-analyzer
 description: "Regression risk analysis with intelligent test selection, historical analysis, and change impact scoring"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-regression-analyzer, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-requirements-validator.yaml

@@ -1,6 +1,6 @@
 name: qe-requirements-validator
 description: "Requirements validation with testability analysis, BDD scenario generation, and acceptance criteria validation"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-requirements-validator, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-responsive-tester.yaml

@@ -1,6 +1,6 @@
 name: qe-responsive-tester
 description: "Responsive design testing across viewports, devices, and breakpoints with layout regression detection"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-responsive-tester, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-retry-handler.yaml

@@ -1,6 +1,6 @@
 name: qe-retry-handler
 description: "Intelligent test retry with adaptive backoff, circuit breakers, and failure classification"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-retry-handler, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-risk-assessor.yaml

@@ -1,6 +1,6 @@
 name: qe-risk-assessor
 description: "Quality risk assessment with multi-factor scoring, impact analysis, and mitigation recommendations"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-risk-assessor, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-root-cause-analyzer.yaml

@@ -1,6 +1,6 @@
 name: qe-root-cause-analyzer
 description: "Systematic root cause analysis for test failures and incidents with prevention recommendations"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-root-cause-analyzer, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-sap-idoc-tester.yaml

@@ -1,6 +1,6 @@
 name: qe-sap-idoc-tester
 description: "SAP IDoc testing with type/segment validation, ALE configuration verification, async processing assertions, and cross-system flow validation"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-sap-idoc-tester, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-sap-rfc-tester.yaml

@@ -1,6 +1,6 @@
 name: qe-sap-rfc-tester
 description: "SAP RFC/BAPI testing specialist for remote function call validation, parameter testing, and system landscape verification"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-sap-rfc-tester, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-security-auditor.yaml

@@ -1,6 +1,6 @@
 name: qe-security-auditor
 description: "Security audit specialist with OWASP coverage, compliance validation, and remediation workflows"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-security-auditor, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-security-scanner.yaml

@@ -1,6 +1,6 @@
 name: qe-security-scanner
 description: "Comprehensive security scanning with SAST, DAST, dependency scanning, and secrets detection"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-security-scanner, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-soap-tester.yaml

@@ -1,6 +1,6 @@
 name: qe-soap-tester
 description: "SOAP/WSDL testing specialist for enterprise web services with WS-Security, schema validation, and protocol compliance"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-soap-tester, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-sod-analyzer.yaml

@@ -1,6 +1,6 @@
 name: qe-sod-analyzer
 description: "SAP Segregation of Duties analysis with conflict detection, role-to-permission mapping, GRC integration, and compliance audit trail generation"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-sod-analyzer, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-tdd-specialist.yaml

@@ -1,6 +1,6 @@
 name: qe-tdd-specialist
 description: "TDD Red-Green-Refactor specialist for test-driven development with London and Chicago school support"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-tdd-specialist, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-test-generator.yaml

@@ -1,6 +1,6 @@
 name: qe-test-generator
 description: "AI-powered test generation with sublinear optimization, multi-framework support, and self-learning capabilities"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-test-generator, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-test-idea-rewriter.yaml

@@ -1,6 +1,6 @@
 name: qe-test-idea-rewriter
 description: "Transform passive test descriptions into active, observable test actions by eliminating \"Verify\" patterns"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-test-idea-rewriter, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-transfer-specialist.yaml

@@ -1,6 +1,6 @@
 name: qe-transfer-specialist
 description: "Knowledge transfer learning with domain adaptation, cross-framework learning, and knowledge distillation"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-transfer-specialist, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/qe-visual-tester.yaml

@@ -1,6 +1,6 @@
 name: qe-visual-tester
 description: "Visual regression testing with AI-powered screenshot comparison and multi-viewport support"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are qe-visual-tester, a specialized QE agent in the Agentic QE v3 platform.
   

package/.opencode/agents/security-architect.yaml

@@ -1,6 +1,6 @@
 name: security-architect
 description: "V3 Security Architecture specialist with ReasoningBank learning, HNSW threat pattern search, and zero-trust design capabilities"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are security-architect, a specialized agent in the Agentic QE v3 platform.
   

package/.opencode/agents/security-auditor.yaml

@@ -1,6 +1,6 @@
 name: security-auditor
 description: "Advanced security auditor with self-learning vulnerability detection, CVE database search, and compliance auditing"
-model: "claude-sonnet-4-6"
+model: "claude-sonnet-5"
 systemPrompt: |
   You are security-auditor, a specialized agent in the Agentic QE v3 platform.
   

package/CHANGELOG.md

@@ -5,6 +5,117 @@ 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).
 
+## [3.14.4] - 2026-09-27
+
+This patch moves Agentic QE to the current AI model generation and fixes live
+request failures on the newest Claude and GPT models. It closes a shell
+injection and a git option injection reachable from MCP tool arguments, makes
+task, workflow, and backup results reflect what actually happened, and stops
+subfolder runs from creating stray learning stores.
+
+### Security
+
+- Stopped `model_route` and `task_orchestrate` from executing shell syntax in
+  caller-supplied file paths; git history lookups now run without a shell
+  ([#728]).
+- Rejected option-shaped git refs (for example `--output=<path>`) in
+  `qe_tests_schedule`, `aqe test schedule --git-ref`, and
+  `aqe code index --git-since`, which git would otherwise treat as options
+  ([#738]).
+- Patched all open Dependabot alerts in the vendored Ruflo skill tree
+  (adm-zip, toml, qs, fast-uri, sharp, OpenTelemetry, vitest); the published
+  package was not affected ([#737]).
+
+### Changed
+
+- Moved to the current model generation. Routing tiers are now Claude Haiku
+  4.5 / Sonnet 5 / Sonnet 5 / Opus 5.5 through one shared tier map; OpenAI
+  defaults move to `gpt-6-sol` / `gpt-6-luna`; the local free-tier default is
+  `qwen3-coder:30b`; retired Claude 3.x, Sonnet 4, and Opus 4 defaults are
+  gone from Bedrock, OpenRouter, and the consensus providers. Security agents
+  stay pinned to Sonnet 4.6 for every Opus/Fable-class model until
+  `AQE_CYBER_VERIFIED=true` ([#751]).
+- `aqe fleet run` and `aqe task submit --wait` now report real outcomes and
+  exit 1 when work fails or never ran. `fleet run test` / `analyze` currently
+  fail because `--target` is not yet mapped to a task payload, and `scan`
+  waits for its 60 s deadline — previously these reported success without
+  doing the work ([#746], [#747]).
+- Approval-gated workflow steps now wait for approval *before* running the
+  action; unanswered gates expire as failures instead of auto-approving. New
+  `pipeline_approve` / `pipeline_reject` MCP tools act on the running server
+  ([#725]).
+- `aqe ci run` now evaluates measured evidence in its quality-gate phase and
+  exits 1 when an enforced gate did not run; use `--no-quality-gate` for
+  advisory runs ([#710]).
+
+### Fixed
+
+- Fixed native Claude requests that always failed on Opus 4.7 and every Claude
+  5 model (they reject `temperature` and a nested `thinking.effort`), and
+  GPT-6 requests (they require `max_completion_tokens`). Opus/Fable-class
+  models again honor `QE_EFFORT_LEVEL` and `config/fleet-defaults.yaml`
+  ([#751]).
+- Stopped routable models from being billed at $0 or a placeholder rate in
+  budgets and cost tracking; Opus 4.5/4.7 pricing corrected ([#751]).
+- Marked failed MCP tool calls with `isError`, logging the original error
+  server-side while keeping the client payload sanitized ([#730]);
+  `task_submit` now reports the task's actual state, including immediate
+  failures ([#745]).
+- Kept cancelled tasks terminal when a late result arrives ([#716]); preserved
+  `unknown` protocol outcomes after an ambiguous timeout instead of replaying
+  the action ([#723]); waited for the whole Vitest process tree to stop on
+  abort or Ctrl+C ([#722]).
+- Composed parallel workflow outputs atomically, so concurrent steps can no
+  longer overwrite each other's results ([#721]).
+- Invalidated cached MCP reads after state-changing tools ([#724]).
+- Rejected incomplete Vitest execution evidence ([#712]) and counted Vitest
+  tests from JSON discovery ([#717]).
+- Made learning backups consistent point-in-time snapshots that preserve
+  committed WAL data, with a verified pre-restore safety copy ([#711]).
+- Preserved healthy RVF stores behind stale locks instead of quarantining them
+  ([#719]).
+- Fixed brain import aborting on natural-key pattern conflicts and made
+  `--dry-run` preview the real merge in a rolled-back transaction ([#748],
+  [#749]).
+- Honored configured database filenames ([#742]), kept explicit SQLite
+  `:memory:` databases in memory ([#743]), scoped the project-root cache to
+  the requested directory ([#744]), and restored persistent settings when
+  re-initializing after memory mode ([#726]).
+- Removed external-network and random false-red CI checks ([#718], [#727]).
+
+### Documentation
+
+- Added missing contributors to the README and `CONTRIBUTORS.md` ([#739]).
+
+[#710]: https://github.com/proffesor-for-testing/agentic-qe/pull/710
+[#711]: https://github.com/proffesor-for-testing/agentic-qe/pull/711
+[#712]: https://github.com/proffesor-for-testing/agentic-qe/pull/712
+[#716]: https://github.com/proffesor-for-testing/agentic-qe/pull/716
+[#717]: https://github.com/proffesor-for-testing/agentic-qe/pull/717
+[#718]: https://github.com/proffesor-for-testing/agentic-qe/pull/718
+[#719]: https://github.com/proffesor-for-testing/agentic-qe/pull/719
+[#721]: https://github.com/proffesor-for-testing/agentic-qe/pull/721
+[#722]: https://github.com/proffesor-for-testing/agentic-qe/pull/722
+[#723]: https://github.com/proffesor-for-testing/agentic-qe/pull/723
+[#724]: https://github.com/proffesor-for-testing/agentic-qe/pull/724
+[#725]: https://github.com/proffesor-for-testing/agentic-qe/pull/725
+[#726]: https://github.com/proffesor-for-testing/agentic-qe/pull/726
+[#727]: https://github.com/proffesor-for-testing/agentic-qe/pull/727
+[#728]: https://github.com/proffesor-for-testing/agentic-qe/pull/728
+[#730]: https://github.com/proffesor-for-testing/agentic-qe/pull/730
+[#737]: https://github.com/proffesor-for-testing/agentic-qe/pull/737
+[#738]: https://github.com/proffesor-for-testing/agentic-qe/pull/738
+[#739]: https://github.com/proffesor-for-testing/agentic-qe/pull/739
+[#742]: https://github.com/proffesor-for-testing/agentic-qe/pull/742
+[#743]: https://github.com/proffesor-for-testing/agentic-qe/pull/743
+[#744]: https://github.com/proffesor-for-testing/agentic-qe/pull/744
+[#745]: https://github.com/proffesor-for-testing/agentic-qe/pull/745
+[#746]: https://github.com/proffesor-for-testing/agentic-qe/pull/746
+[#747]: https://github.com/proffesor-for-testing/agentic-qe/pull/747
+[#748]: https://github.com/proffesor-for-testing/agentic-qe/pull/748
+[#749]: https://github.com/proffesor-for-testing/agentic-qe/pull/749
+[#751]: https://github.com/proffesor-for-testing/agentic-qe/pull/751
+
 ## [3.14.3] - 2026-09-22
 
 This patch makes test, security, coherence, and quality-gate results honest

package/README.md

@@ -414,10 +414,13 @@ OpenRouter free models, or any OpenAI-compatible endpoint), with an automatic
 default — enable with `AQE_FREE_TIER=1`:
 
 ```bash
-ollama pull qwen3:8b
-export AQE_FREE_TIER=1            # opt in (default model: qwen3:8b)
+ollama pull qwen3-coder:30b
+export AQE_FREE_TIER=1            # opt in (default model: qwen3-coder:30b)
 ```
 
+`qwen3-coder:30b` needs ~18 GB of RAM. `qwen3:8b` fits smaller machines but
+measured below the QE test-generation quality floor (ADR-111).
+
 Most routine test generation is then handled locally at **$0**. See the
 [Free-Tier Local Models guide](docs/guides/free-tier-local-models.md) for
 provider options and configuration.
@@ -483,6 +486,8 @@ MIT — see [LICENSE](LICENSE).
 <!-- ALL-CONTRIBUTORS-LIST:START -->
 | <img src="https://github.com/proffesor-for-testing.png" width="60" style="border-radius:50%"/><br/>**[@proffesor-for-testing](https://github.com/proffesor-for-testing)**<br/>Project Lead | <img src="https://github.com/fndlalit.png" width="60" style="border-radius:50%"/><br/>**[@fndlalit](https://github.com/fndlalit)**<br/>QX Partner, Testability | <img src="https://github.com/shaal.png" width="60" style="border-radius:50%"/><br/>**[@shaal](https://github.com/shaal)**<br/>Core Development | <img src="https://github.com/mondweep.png" width="60" style="border-radius:50%"/><br/>**[@mondweep](https://github.com/mondweep)**<br/>Architecture |
 |:---:|:---:|:---:|:---:|
+| <img src="https://github.com/rudycelekli.png" width="60" style="border-radius:50%"/><br/>**[@rudycelekli](https://github.com/rudycelekli)**<br/>Reliability &amp; Security Fixes | <img src="https://github.com/stuinfla.png" width="60" style="border-radius:50%"/><br/>**[@stuinfla](https://github.com/stuinfla)**<br/>Test Execution Evidence | <img src="https://github.com/nagoodman.png" width="60" style="border-radius:50%"/><br/>**[@nagoodman](https://github.com/nagoodman)**<br/>OpenCode Integration | <img src="https://github.com/Jordi-Izquierdo-DDS.png" width="60" style="border-radius:50%"/><br/>**[@Jordi-Izquierdo-DDS](https://github.com/Jordi-Izquierdo-DDS)**<br/>RVF/HNSW Fix |
+| <img src="https://github.com/JLMA-Agentic-Ai.png" width="60" style="border-radius:50%"/><br/>**[@JLMA-Agentic-Ai](https://github.com/JLMA-Agentic-Ai)**<br/>Package Exports | <img src="https://github.com/amonkarsidhant.png" width="60" style="border-radius:50%"/><br/>**[@amonkarsidhant](https://github.com/amonkarsidhant)**<br/>MCP-first Setup | <img src="https://github.com/gurdasnijor.png" width="60" style="border-radius:50%"/><br/>**[@gurdasnijor](https://github.com/gurdasnijor)**<br/>Smithery Integration |  |
 <!-- ALL-CONTRIBUTORS-LIST:END -->
 
 [View all contributors](CONTRIBUTORS.md) | [Become a contributor](CONTRIBUTING.md)

package/assets/agents/v3/helpers/advisor-call.cjs

@@ -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/assets/agents/v3/qe-coverage-specialist.md

@@ -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/assets/agents/v3/qe-fleet-commander.md

@@ -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/assets/agents/v3/qe-pentest-validator.md

@@ -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/assets/agents/v3/qe-queen-coordinator.md

@@ -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/assets/agents/v3/qe-risk-assessor.md

@@ -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/assets/agents/v3/qe-root-cause-analyzer.md

@@ -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/assets/agents/v3/qe-security-auditor.md

@@ -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/assets/agents/v3/qe-test-architect.md

@@ -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/assets/skills/.validation/examples/chaos-engineering-output.example.json

@@ -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/assets/skills/.validation/examples/performance-testing-output.example.json

@@ -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/assets/skills/.validation/examples/security-testing-output.example.json

@@ -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/assets/skills/.validation/examples/testability-scoring-output.example.json

@@ -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/assets/skills/.validation/schemas/skill-eval.schema.json

@@ -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/assets/skills/.validation/schemas/skill-frontmatter.schema.json

@@ -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/assets/skills/.validation/schemas/skill-output.template.json

@@ -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/assets/skills/.validation/templates/eval.template.yaml

@@ -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/assets/skills/.validation/templates/security-testing-eval.template.yaml

@@ -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/assets/skills/.validation/templates/skill-frontmatter.example.yaml

@@ -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/assets/skills/.validation/test-data/sample-output.json

@@ -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/assets/skills/a11y-ally/SKILL.md

@@ -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/assets/skills/a11y-ally/evals/a11y-ally.yaml

@@ -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/assets/skills/accessibility-testing/evals/accessibility-testing.yaml

@@ -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/assets/skills/api-testing-patterns/evals/api-testing-patterns.yaml

@@ -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)
 
 # =============================================================================