agentic-qe 3.10.9 → 3.11.0

package/.claude/agents/v3/qe-learning-coordinator.md

@@ -180,7 +180,7 @@ Core Skills:
 Advanced Skills:
 - reasoningbank-agentdb: Vector-indexed pattern storage
 - quality-metrics: Measure and optimize quality metrics
-- holistic-testing-pact: PACT principles for comprehensive testing
+- holistic-testing-pact: PACTS principles for comprehensive testing
 
 Use via CLI: `aqe skills show reasoningbank-intelligence`
 Use via Claude Code: `Skill("reasoningbank-agentdb")`

package/.claude/skills/README.md

@@ -19,7 +19,7 @@ Version-agnostic quality engineering best practices from the QE community.
 
 - **a11y-ally**: Comprehensive WCAG accessibility auditing with multi-tool testing (axe-core + pa11y + Lighthouse), TRUE PARALLEL execution with Promise.allSettled, graceful degradation, retry with backoff, context-aware remediation, learning integration, and video accessibility. Uses 3-tier browser cascade: Vibium → agent-browser → Playwright+Stealth.
 - **accessibility-testing**: WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.
-- **agentic-quality-engineering**: AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACT principles.
+- **agentic-quality-engineering**: AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACTS principles.
 - **api-testing-patterns**: Comprehensive API testing patterns including contract testing, REST/GraphQL testing, and integration testing. Use when testing APIs or designing API test strategies.
 - **browser**: Web browser automation with AI-optimized snapshots for claude-flow agents
 - **brutal-honesty-review**: Unvarnished technical criticism combining Linus Torvalds
@@ -36,7 +36,7 @@ Version-agnostic quality engineering best practices from the QE community.
 - **debug-loop**: Hypothesis-driven autonomous debugging with real command validation
 - **enterprise-integration-testing**: Orchestration skill for enterprise integration testing across SAP, middleware, WMS, and backend systems. Covers E2E enterprise flows, SAP-specific patterns (RFC, BAPI, IDoc, OData, Fiori), cross-system data validation, and enterprise quality gates.
 - **exploratory-testing-advanced**: Advanced exploratory testing techniques with Session-Based Test Management (SBTM), RST heuristics, and test tours. Use when planning exploration sessions, investigating bugs, or discovering unknown quality risks.
-- **holistic-testing-pact**: Apply the Holistic Testing Model evolved with PACT (Proactive, Autonomous, Collaborative, Targeted) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices.
+- **holistic-testing-pact**: Apply the Holistic Testing Model evolved with PACTS (Proactive, Autonomous, Collaborative, Targeted, Structured) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices.
 - **localization-testing**: Internationalization (i18n) and localization (l10n) testing for global products including translations, locale formats, RTL languages, and cultural appropriateness. Use when launching in new markets or building multi-language products.
 - **middleware-testing-patterns**: Enterprise middleware testing patterns for message routing, transformation, DLQ, protocol mediation, ESB error handling, and EIP patterns. Use when testing middleware layers, message brokers, ESBs, or integration buses.
 - **mobile-testing**: Comprehensive mobile testing for iOS and Android platforms including gestures, sensors, permissions, device fragmentation, and performance. Use when testing native apps, hybrid apps, or mobile web, ensuring quality across 1000+ device variants.

package/.claude/skills/agentic-quality-engineering/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: agentic-quality-engineering
-description: "Use when orchestrating QE agents, understanding PACT principles, configuring the AQE v3 fleet, or leveraging AI agents as force multipliers for quality work."
+description: "Use when orchestrating QE agents, understanding PACTS principles, configuring the AQE v3 fleet, or leveraging AI agents as force multipliers for quality work."
 category: qe-core
 priority: critical
 tokenEstimate: 1400
@@ -10,7 +10,7 @@ optimization_version: 1.0
 last_optimized: 2025-12-02
 dependencies: []
 quick_reference_card: true
-tags: [pact, agents, fleet, coordination, autonomous, foundational]
+tags: [pacts, agents, fleet, coordination, autonomous, structured, foundational]
 trust_tier: 1
 validation:
   schema_path: schemas/output.json
@@ -22,7 +22,7 @@ validation:
 When implementing agentic QE or coordinating agents:
 1. SPAWN appropriate agent(s) for the task using `Task` tool with agent type
 2. CONFIGURE agent coordination (hierarchical/mesh/sequential)
-3. EXECUTE with PACT principles: Proactive analysis, Autonomous operation, Collaborative feedback, Targeted risk focus
+3. EXECUTE with PACTS principles: Proactive analysis, Autonomous operation, Collaborative feedback, Targeted risk focus, Structured governance (observability and explainability of agent behavior)
 4. VALIDATE results through quality gates before deployment
 5. LEARN from outcomes - store patterns in `aqe/learning/*` namespace
 
@@ -48,13 +48,14 @@ When implementing agentic QE or coordinating agents:
 - Implementing multi-agent coordination
 - Building CI/CD quality pipelines
 
-### PACT Principles
+### PACTS Principles
 | Principle | Agent Behavior | Human Role |
 |-----------|---------------|------------|
 | **P**roactive | Analyze pre-merge, predict risk | Set guardrails |
 | **A**utonomous | Execute tests, fix flaky tests | Review critical |
 | **C**ollaborative | Multi-agent coordination | Provide context |
 | **T**argeted | Risk-based prioritization | Define risk areas |
+| **S**tructured | Governance, observability, explainable decisions (measure confidence, not trust) | Audit behavior, set policy |
 
 ### 19-Agent Fleet
 | Category | Agents | Primary Use |
@@ -294,7 +295,7 @@ agent_assignments:
 ---
 
 ## Related Skills
-- `holistic-testing-pact` - PACT principles deep dive
+- `holistic-testing-pact` - PACTS principles deep dive
 - `risk-based-testing` - Prioritize agent focus
 - `quality-metrics` - Measure agent effectiveness
 - `api-testing-patterns`, `security-testing`, `performance-testing` - Specialized testing

package/.claude/skills/agentic-quality-engineering/schemas/output.json

@@ -2,7 +2,7 @@
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "$id": "https://agentic-qe.dev/schemas/agentic-quality-engineering-output.json",
   "title": "Agentic Quality Engineering Skill Output Schema",
-  "description": "Schema for agentic quality engineering output with fleet status, agent coordination, and PACT principles validation.",
+  "description": "Schema for agentic quality engineering output with fleet status, agent coordination, and PACTS principles validation.",
   "type": "object",
   "required": ["skillName", "version", "timestamp", "status", "trustTier", "output"],
   "properties": {
@@ -52,7 +52,7 @@
         },
         "pactPrinciples": {
           "$ref": "#/$defs/pactPrinciples",
-          "description": "PACT principles assessment (Proactive, Autonomous, Collaborative, Targeted)"
+          "description": "PACTS principles assessment (Proactive, Autonomous, Collaborative, Targeted, Structured)"
         },
         "qualityScore": {
           "$ref": "#/$defs/qualityScore",
@@ -272,11 +272,15 @@
           "$ref": "#/$defs/pactDimension",
           "description": "Targeted testing approach"
         },
+        "structured": {
+          "$ref": "#/$defs/pactDimension",
+          "description": "Structured governance, observability, and explainability of agent behavior (measure confidence, not trust)"
+        },
         "overallScore": {
           "type": "number",
           "minimum": 0,
           "maximum": 100,
-          "description": "Overall PACT score"
+          "description": "Overall PACTS score"
         }
       }
     },

package/.claude/skills/holistic-testing-pact/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: holistic-testing-pact
-description: "Apply the Holistic Testing Model evolved with PACT (Proactive, Autonomous, Collaborative, Targeted) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices."
+description: "Apply the Holistic Testing Model evolved with PACTS (Proactive, Autonomous, Collaborative, Targeted, Structured) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices."
 category: testing-methodologies
 priority: critical
 tokenEstimate: 1100
@@ -10,26 +10,27 @@ optimization_version: 1.0
 last_optimized: 2025-12-02
 dependencies: []
 quick_reference_card: true
-tags: [holistic, pact, quality, whole-team, proactive, autonomous, collaborative, targeted]
+tags: [holistic, pacts, quality, whole-team, proactive, autonomous, collaborative, targeted, structured]
 trust_tier: 0
 validation:
 ---
 
-# Holistic Testing Model with PACT Principles
+# Holistic Testing Model with PACTS Principles
 
 <default_to_action>
 When designing test strategies or building quality into teams:
-1. APPLY PACT principles: Proactive (test before bugs), Autonomous (teams own quality), Collaborative (whole-team responsibility), Targeted (risk-focused)
+1. APPLY PACTS principles: Proactive (test before bugs), Autonomous (teams own quality), Collaborative (whole-team responsibility), Targeted (risk-focused), Structured (governance, observability, and explainability of agent behavior)
 2. IDENTIFY quadrant focus: Technology-facing (unit, integration, performance) or Business-facing (acceptance, exploratory, usability)
-3. SELECT agents based on PACT dimension and testing quadrant
+3. SELECT agents based on PACTS dimension and testing quadrant
 4. IMPLEMENT feedback loops that catch issues in minutes, not days
-5. MEASURE outcomes (bug escape rate, release confidence) not activities (test count)
+5. MEASURE outcomes (bug escape rate, release confidence, agent confidence) not activities (test count)
 
-**Quick PACT Application:**
+**Quick PACTS Application:**
 - Proactive → Design testability into architecture, risk analysis during refinement
 - Autonomous → Devs run tests locally, CI pipeline with no manual gates
 - Collaborative → Three Amigos, QE pairs with dev, shared test ownership
 - Targeted → Risk-based planning, focus on critical flows, kill valueless tests
+- Structured → Governance, observability, and explainability of agent behavior; measure confidence, not trust
 
 **Critical Success Factors:**
 - Quality is a whole-team responsibility, not a QA phase
@@ -45,13 +46,14 @@ When designing test strategies or building quality into teams:
 - Choosing testing approach for new projects
 - Evolving from sequential QA to concurrent quality
 
-### PACT Principles
+### PACTS Principles
 | Principle | Focus | Anti-Pattern |
 |-----------|-------|--------------|
 | **Proactive** | Test before code, design testability | Waiting for bugs to find you |
 | **Autonomous** | Teams deploy when ready | QA as manual gatekeepers |
 | **Collaborative** | Whole-team quality thinking | QA works in isolation |
 | **Targeted** | Risk-based, high-value tests | Exhaustive checkbox testing |
+| **Structured** | Governance, observability, explainability of agent behavior | Bolting agentic AI onto chaos |
 
 ### Holistic Testing Quadrants
 | Quadrant | Purpose | Examples |
@@ -61,17 +63,18 @@ When designing test strategies or building quality into teams:
 | Business + Support | Shared understanding | BDD, acceptance tests |
 | Business + Critique | Discover unknowns | Exploratory, usability, A/B |
 
-### Agent Selection by PACT + Quadrant
-| PACT Dimension | Agents |
+### Agent Selection by PACTS + Quadrant
+| PACTS Dimension | Agents |
 |----------------|--------|
 | Proactive + Tech | qe-test-generator, qe-requirements-validator |
 | Autonomous + Tech | qe-test-executor, qe-coverage-analyzer |
 | Collaborative | qe-fleet-commander (orchestration) |
 | Targeted | qe-regression-risk-analyzer, qe-quality-gate |
+| Structured | qe-fleet-commander, qe-quality-gate (governance, observability, explainability) |
 
 ---
 
-## PACT in Practice
+## PACTS in Practice
 
 ### Proactive: Test Before Bugs
 ```javascript
@@ -105,11 +108,41 @@ await Task("Risk-Based Planning", {
 }, "qe-regression-risk-analyzer");
 ```
 
+### Structured: Governance, Observability, Explainability
+The 5th principle for agentic systems. As agents take on quality work, you need
+governance (boundaries and guardrails), observability (what agents did and why),
+and explainability (decisions you can audit). Especially important in regulated
+industries.
+
+- We measure **CONFIDENCE, not trust** — trust is a human feeling; confidence can
+  be mathematically explained.
+- Ships with a playbook + readiness-assessment guide.
+- Anti-pattern: bolting agentic AI onto chaos. Structure first, then automate.
+
+```javascript
+// Make agent behavior auditable and explainable, not a black box
+await Task("Agent Governance Review", {
+  guardrails: ['scope-boundaries', 'approval-gates'],
+  observability: ['decision-traces', 'confidence-scores'],
+  explainability: 'every-decision-auditable'
+}, "qe-fleet-commander");
+```
+
+---
+
+## From PACT to PACTS
+
+PACT originated with Reuven Cohen (Agentics Foundation) and was adapted to quality
+engineering by Dragan Spiridonov. PACTS adds a fifth principle — **Structured** —
+inspired by DORA's research on AI-assisted delivery and platform-engineering
+quality measurement. The addition reflects that autonomous, agentic quality work
+needs governance, observability, and explainability to be trustworthy at scale.
+
 ---
 
 ## Evolution from Traditional
 
-| Old Way (Sequential) | Holistic + PACT (Concurrent) |
+| Old Way (Sequential) | Holistic + PACTS (Concurrent) |
 |---------------------|------------------------------|
 | Dev writes → QA tests → bugs found → fixes | Team discusses what to build and how to test |
 | Slow feedback, finger-pointing | Fast feedback, shared ownership |
@@ -133,7 +166,7 @@ await Task("Risk-Based Planning", {
 ### Memory Namespace
 ```
 aqe/holistic-testing/
-├── pact-assessment/*     - PACT maturity analysis
+├── pacts-assessment/*    - PACTS maturity analysis
 ├── quadrant-coverage/*   - Coverage per quadrant
 ├── team-metrics/*        - Quality ownership metrics
 └── feedback-loops/*      - Cycle time data
@@ -143,7 +176,7 @@ aqe/holistic-testing/
 ```typescript
 const holisticFleet = await FleetManager.coordinate({
   strategy: 'holistic-testing',
-  pact: { proactive: true, autonomous: true, collaborative: true, targeted: true },
+  pacts: { proactive: true, autonomous: true, collaborative: true, targeted: true, structured: true },
   agents: [
     'qe-fleet-commander',       // Orchestration
     'qe-test-generator',        // Tech quadrant
@@ -166,8 +199,8 @@ const holisticFleet = await FleetManager.coordinate({
 
 ## Remember
 
-**PACT = Proactive + Autonomous + Collaborative + Targeted**
+**PACTS = Proactive + Autonomous + Collaborative + Targeted + Structured**
 
-Quality is built in, not tested in. Teams own quality. QA enables, doesn't gate. Test what matters, skip what doesn't. Measure outcomes, not activities.
+Quality is built in, not tested in. Teams own quality. QA enables, doesn't gate. Test what matters, skip what doesn't. Govern agent behavior with observability and explainability — measure confidence, not trust. Measure outcomes, not activities.
 
-**With Agents:** Agents analyze PACT maturity, recommend quadrant coverage, and coordinate whole-team quality. Use agents to scale holistic thinking while maintaining human judgment.
+**With Agents:** Agents analyze PACTS maturity, recommend quadrant coverage, and coordinate whole-team quality. Use agents to scale holistic thinking while maintaining human judgment.

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

@@ -308,7 +308,7 @@
     "agentic-quality-engineering": {
       "id": "agentic-quality-engineering",
       "name": "Agentic Quality Engineering",
-      "description": "Core foundational skill for all 19 QE agents with PACT principles (Proactive, Autonomous, Collaborative, Targeted).",
+      "description": "Core foundational skill for all 19 QE agents with PACTS principles (Proactive, Autonomous, Collaborative, Targeted, Structured).",
       "category": "qe-core",
       "priority": "critical",
       "file": "agentic-quality-engineering/SKILL.md",
@@ -317,19 +317,19 @@
       "optimizationStatus": "optimized",
       "optimizationVersion": "1.0",
       "lastOptimized": "2025-12-02",
-      "tags": ["agents", "pact", "core", "foundation", "autonomous-testing"],
+      "tags": ["agents", "pacts", "core", "foundation", "autonomous-testing"],
       "dependencies": [],
       "agents": ["qe-test-generator", "qe-test-executor", "qe-coverage-analyzer", "qe-quality-gate", "qe-quality-analyzer", "qe-performance-tester", "qe-security-scanner", "qe-requirements-validator", "qe-production-intelligence", "qe-fleet-commander", "qe-deployment-readiness", "qe-regression-risk-analyzer", "qe-test-data-architect", "qe-api-contract-validator", "qe-flaky-test-hunter", "qe-visual-tester", "qe-chaos-engineer", "qe-code-complexity", "qx-partner"]
     },
     "holistic-testing-pact": {
       "id": "holistic-testing-pact",
-      "name": "Holistic Testing with PACT Principles",
-      "description": "Holistic Testing Model evolved with PACT for whole-team quality in agentic systems.",
+      "name": "Holistic Testing with PACTS Principles",
+      "description": "Holistic Testing Model evolved with PACTS for whole-team quality in agentic systems.",
       "category": "qe-core",
       "priority": "critical",
       "file": "holistic-testing-pact/SKILL.md",
       "tokenEstimate": 1500,
-      "tags": ["pact", "holistic", "whole-team", "testing-quadrants"],
+      "tags": ["pacts", "holistic", "whole-team", "testing-quadrants"],
       "dependencies": ["agentic-quality-engineering"],
       "agents": ["qe-coverage-analyzer", "qe-quality-gate", "qe-fleet-commander"]
     },
@@ -939,7 +939,7 @@
   },
   "metadata": {
     "generatedBy": "Agentic QE Fleet",
-    "fleetVersion": "3.10.9",
+    "fleetVersion": "3.11.0",
     "manifestVersion": "1.4.0",
     "lastUpdated": "2026-04-13T00:00:00.000Z",
     "contributors": [

package/.opencode/skills/qe-agentic-quality-engineering.yaml

@@ -1,13 +1,13 @@
 name: qe-agentic-quality-engineering
-description: "AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACT principles."
+description: "Use when orchestrating QE agents, understanding PACTS principles, configuring the AQE v3 fleet, or leveraging AI agents as force multipliers for quality work."
 minModelTier: tier1-any
-tags: ["pact", "agents", "fleet", "coordination", "autonomous", "foundational", "qe", "quality-engineering", "qe-core"]
+tags: ["pacts", "agents", "fleet", "coordination", "autonomous", "structured", "foundational", "qe", "quality-engineering", "qe-core"]
 steps:
-  - name: pact-principles
-    description: "PACT Principles"
+  - name: pacts-principles
+    description: "PACTS Principles"
     tools: ["bash", "read", "edit"]
     prompt: |
-      PACT Principles
+      PACTS Principles
   - name: 19-agent-fleet
     description: "19-Agent Fleet"
     tools: ["bash", "read"]

package/.opencode/skills/qe-holistic-testing-pact.yaml

@@ -1,28 +1,28 @@
 name: qe-holistic-testing-pact
-description: "Apply the Holistic Testing Model evolved with PACT (Proactive, Autonomous, Collaborative, Targeted) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices."
+description: "Apply the Holistic Testing Model evolved with PACTS (Proactive, Autonomous, Collaborative, Targeted, Structured) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality"
 minModelTier: tier1-any
-tags: ["holistic", "pact", "quality", "whole-team", "proactive", "autonomous", "collaborative", "targeted", "qe", "quality-engineering", "testing-methodologies"]
+tags: ["holistic", "pacts", "quality", "whole-team", "proactive", "autonomous", "collaborative", "targeted", "structured", "qe", "quality-engineering", "testing-methodologies"]
 steps:
-  - name: pact-principles
-    description: "PACT Principles"
+  - name: pacts-principles
+    description: "PACTS Principles"
     tools: ["bash", "read", "grep"]
     prompt: |
-      PACT Principles
+      PACTS Principles
   - name: holistic-testing-quadrants
     description: "Holistic Testing Quadrants"
     tools: ["bash", "read", "grep"]
     prompt: |
       Holistic Testing Quadrants
-  - name: agent-selection-by-pact-quadrant
-    description: "Agent Selection by PACT + Quadrant"
+  - name: agent-selection-by-pacts-quadrant
+    description: "Agent Selection by PACTS + Quadrant"
     tools: ["bash", "read"]
     prompt: |
-      Agent Selection by PACT + Quadrant
-  - name: pact-in-practice
-    description: "PACT in Practice"
+      Agent Selection by PACTS + Quadrant
+  - name: pacts-in-practice
+    description: "PACTS in Practice"
     tools: ["bash", "read"]
     prompt: |
-      PACT in Practice
+      PACTS in Practice
   - name: proactive-test-before-bugs
     description: "Proactive: Test Before Bugs"
     tools: ["bash", "read"]

package/CHANGELOG.md

@@ -5,6 +5,57 @@ 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).
 
+## [3.11.0] - 2026-06-20
+
+Run test generation on **free local models first**, falling back to paid models
+only when needed. This release adds an opt-in "cheap-first" path: a local model
+(Ollama, OpenRouter free tier, or any OpenAI-compatible endpoint) attempts test
+generation with an automatic repair loop, and only the hard cases escalate up to
+your normal LLM tiers — so most routine generation can run at $0. Every cheap-vs-
+escalated outcome feeds routing feedback, so model selection improves over time.
+
+Off by default; nothing changes unless you opt in. Inspired by the "the harness
+matters as much as the model" economics from Ruv's MetaHarness Darwin Mode.
+
+### Added
+
+- **Free-tier local test generation (opt-in).** Enable with `AQE_FREE_TIER=1`
+  (or `enableFreeTier` in the test-generation coordinator config) to generate
+  tests on a free/local model before any paid LLM call. Default model `qwen3:8b`.
+  See the [Free-Tier Local Models guide](docs/guides/free-tier-local-models.md).
+- **Configurable free-tier providers** — local Ollama, cloud Ollama, OpenRouter
+  free models, or any OpenAI-compatible endpoint (vLLM, LM Studio, Groq, …). API
+  keys are read from named environment variables and never stored.
+- **Repair loop** — when the local model's first output isn't a valid test, the
+  failure is fed back and it retries before falling back (configurable retries).
+- **Automatic escalation** — hard cases the local model + repair can't solve
+  escalate up the existing model ladder (Haiku → Sonnet → Opus) via the router.
+- **Self-learning routing feedback** — free-tier outcomes feed the routing
+  calibrator and escalation tracker, improving model-tier confidence over time.
+- **`agentic-qe/routing/free-tier` package export** for programmatic configuration.
+
+### Fixed
+
+- **Restored `@ruvector/ruvllm-*` optional platform packages** dropped from the
+  lockfile by a Dependabot update, which could break `npm ci` for consumers. (#541)
+- **Multi-file test-generation requests** now correctly fall back to the full
+  generation path so every requested file is covered (the free-tier path handles
+  the single-file case).
+- Security bump of the transitive `hono` dev dependency. (#541)
+
+### Changed
+
+- **Auto-escalation tracker is now ladder-configurable** (generic over tier
+  names) so a free local tier can sit below the paid tiers. Fully backward
+  compatible — existing behavior and the default Claude ladder are unchanged.
+- **QE framework evolved PACT → PACTS** — adds a fifth principle, **Structured**
+  (governance, observability, and explainability of agent behavior; measure
+  *confidence*, not trust), inspired by DORA's research on AI-assisted delivery.
+  Ships with a playbook + readiness-assessment guide. The skill id/dir
+  `holistic-testing-pact` and schema slugs are unchanged (cross-repo stable); the
+  output schema gains an **optional** `structured` dimension (non-breaking).
+  PACT originated with Reuven Cohen (Agentics Foundation); PACTS adds Structured. (#545)
+
 ## [3.10.9] - 2026-06-17
 
 MCP server reliability and database-free completeness, all from community-reported

package/README.md

@@ -405,6 +405,22 @@ export AQE_LLM_ROUTER_DISABLED=1   # env-only kill-switch
 
 Or programmatically: `new QEKernelImpl({ llmRouter: { enabled: false } })`.
 
+### Free local models (opt-in) — cheap-first test generation
+
+Run test generation on a **free local model first** (local Ollama, cloud Ollama,
+OpenRouter free models, or any OpenAI-compatible endpoint), with an automatic
+**repair loop**, falling back to your normal LLM path only when needed. Off by
+default — enable with `AQE_FREE_TIER=1`:
+
+```bash
+ollama pull qwen3:8b
+export AQE_FREE_TIER=1            # opt in (default model: qwen3:8b)
+```
+
+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.
+
 ---
 
 ## Documentation
@@ -412,6 +428,7 @@ Or programmatically: `new QEKernelImpl({ llmRouter: { enabled: false } })`.
 | Guide | Description |
 |-------|-------------|
 | [Platform Setup](docs/platform-setup-guide.md) | Per-platform configuration instructions |
+| [Free-Tier Local Models](docs/guides/free-tier-local-models.md) | Cheap-first test generation on local/free models (opt-in) |
 | [Skill Validation](docs/guides/skill-validation.md) | Trust tiers and evaluation system |
 | [Learning System](docs/guides/reasoningbank-learning-system.md) | ReasoningBank pattern learning |
 | [Code Intelligence](docs/guides/fleet-code-intelligence-integration.md) | Knowledge graph and semantic search |

package/assets/agents/v3/qe-learning-coordinator.md

@@ -180,7 +180,7 @@ Core Skills:
 Advanced Skills:
 - reasoningbank-agentdb: Vector-indexed pattern storage
 - quality-metrics: Measure and optimize quality metrics
-- holistic-testing-pact: PACT principles for comprehensive testing
+- holistic-testing-pact: PACTS principles for comprehensive testing
 
 Use via CLI: `aqe skills show reasoningbank-intelligence`
 Use via Claude Code: `Skill("reasoningbank-agentdb")`

package/assets/skills/README.md

@@ -19,7 +19,7 @@ Version-agnostic quality engineering best practices from the QE community.
 
 - **a11y-ally**: Comprehensive WCAG accessibility auditing with multi-tool testing (axe-core + pa11y + Lighthouse), TRUE PARALLEL execution with Promise.allSettled, graceful degradation, retry with backoff, context-aware remediation, learning integration, and video accessibility. Uses 3-tier browser cascade: Vibium → agent-browser → Playwright+Stealth.
 - **accessibility-testing**: WCAG 2.2 compliance testing, screen reader validation, and inclusive design verification. Use when ensuring legal compliance (ADA, Section 508), testing for disabilities, or building accessible applications for 1 billion disabled users globally.
-- **agentic-quality-engineering**: AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACT principles.
+- **agentic-quality-engineering**: AI agents as force multipliers for quality work. Core skill for all 19 QE agents using PACTS principles.
 - **api-testing-patterns**: Comprehensive API testing patterns including contract testing, REST/GraphQL testing, and integration testing. Use when testing APIs or designing API test strategies.
 - **browser**: Web browser automation with AI-optimized snapshots for claude-flow agents
 - **brutal-honesty-review**: Unvarnished technical criticism combining Linus Torvalds
@@ -36,7 +36,7 @@ Version-agnostic quality engineering best practices from the QE community.
 - **debug-loop**: Hypothesis-driven autonomous debugging with real command validation
 - **enterprise-integration-testing**: Orchestration skill for enterprise integration testing across SAP, middleware, WMS, and backend systems. Covers E2E enterprise flows, SAP-specific patterns (RFC, BAPI, IDoc, OData, Fiori), cross-system data validation, and enterprise quality gates.
 - **exploratory-testing-advanced**: Advanced exploratory testing techniques with Session-Based Test Management (SBTM), RST heuristics, and test tours. Use when planning exploration sessions, investigating bugs, or discovering unknown quality risks.
-- **holistic-testing-pact**: Apply the Holistic Testing Model evolved with PACT (Proactive, Autonomous, Collaborative, Targeted) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices.
+- **holistic-testing-pact**: Apply the Holistic Testing Model evolved with PACTS (Proactive, Autonomous, Collaborative, Targeted, Structured) principles. Use when designing comprehensive test strategies for Classical, AI-assisted, Agent based, or Agentic Systems building quality into the team, or implementing whole-team quality practices.
 - **localization-testing**: Internationalization (i18n) and localization (l10n) testing for global products including translations, locale formats, RTL languages, and cultural appropriateness. Use when launching in new markets or building multi-language products.
 - **middleware-testing-patterns**: Enterprise middleware testing patterns for message routing, transformation, DLQ, protocol mediation, ESB error handling, and EIP patterns. Use when testing middleware layers, message brokers, ESBs, or integration buses.
 - **mobile-testing**: Comprehensive mobile testing for iOS and Android platforms including gestures, sensors, permissions, device fragmentation, and performance. Use when testing native apps, hybrid apps, or mobile web, ensuring quality across 1000+ device variants.

package/assets/skills/agentic-quality-engineering/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: agentic-quality-engineering
-description: "Use when orchestrating QE agents, understanding PACT principles, configuring the AQE v3 fleet, or leveraging AI agents as force multipliers for quality work."
+description: "Use when orchestrating QE agents, understanding PACTS principles, configuring the AQE v3 fleet, or leveraging AI agents as force multipliers for quality work."
 category: qe-core
 priority: critical
 tokenEstimate: 1400
@@ -10,7 +10,7 @@ optimization_version: 1.0
 last_optimized: 2025-12-02
 dependencies: []
 quick_reference_card: true
-tags: [pact, agents, fleet, coordination, autonomous, foundational]
+tags: [pacts, agents, fleet, coordination, autonomous, structured, foundational]
 trust_tier: 1
 validation:
   schema_path: schemas/output.json
@@ -22,7 +22,7 @@ validation:
 When implementing agentic QE or coordinating agents:
 1. SPAWN appropriate agent(s) for the task using `Task` tool with agent type
 2. CONFIGURE agent coordination (hierarchical/mesh/sequential)
-3. EXECUTE with PACT principles: Proactive analysis, Autonomous operation, Collaborative feedback, Targeted risk focus
+3. EXECUTE with PACTS principles: Proactive analysis, Autonomous operation, Collaborative feedback, Targeted risk focus, Structured governance (observability and explainability of agent behavior)
 4. VALIDATE results through quality gates before deployment
 5. LEARN from outcomes - store patterns in `aqe/learning/*` namespace
 
@@ -48,13 +48,14 @@ When implementing agentic QE or coordinating agents:
 - Implementing multi-agent coordination
 - Building CI/CD quality pipelines
 
-### PACT Principles
+### PACTS Principles
 | Principle | Agent Behavior | Human Role |
 |-----------|---------------|------------|
 | **P**roactive | Analyze pre-merge, predict risk | Set guardrails |
 | **A**utonomous | Execute tests, fix flaky tests | Review critical |
 | **C**ollaborative | Multi-agent coordination | Provide context |
 | **T**argeted | Risk-based prioritization | Define risk areas |
+| **S**tructured | Governance, observability, explainable decisions (measure confidence, not trust) | Audit behavior, set policy |
 
 ### 19-Agent Fleet
 | Category | Agents | Primary Use |
@@ -294,7 +295,7 @@ agent_assignments:
 ---
 
 ## Related Skills
-- `holistic-testing-pact` - PACT principles deep dive
+- `holistic-testing-pact` - PACTS principles deep dive
 - `risk-based-testing` - Prioritize agent focus
 - `quality-metrics` - Measure agent effectiveness
 - `api-testing-patterns`, `security-testing`, `performance-testing` - Specialized testing

package/assets/skills/agentic-quality-engineering/schemas/output.json

@@ -2,7 +2,7 @@
   "$schema": "https://json-schema.org/draft/2020-12/schema",
   "$id": "https://agentic-qe.dev/schemas/agentic-quality-engineering-output.json",
   "title": "Agentic Quality Engineering Skill Output Schema",
-  "description": "Schema for agentic quality engineering output with fleet status, agent coordination, and PACT principles validation.",
+  "description": "Schema for agentic quality engineering output with fleet status, agent coordination, and PACTS principles validation.",
   "type": "object",
   "required": ["skillName", "version", "timestamp", "status", "trustTier", "output"],
   "properties": {
@@ -52,7 +52,7 @@
         },
         "pactPrinciples": {
           "$ref": "#/$defs/pactPrinciples",
-          "description": "PACT principles assessment (Proactive, Autonomous, Collaborative, Targeted)"
+          "description": "PACTS principles assessment (Proactive, Autonomous, Collaborative, Targeted, Structured)"
         },
         "qualityScore": {
           "$ref": "#/$defs/qualityScore",
@@ -272,11 +272,15 @@
           "$ref": "#/$defs/pactDimension",
           "description": "Targeted testing approach"
         },
+        "structured": {
+          "$ref": "#/$defs/pactDimension",
+          "description": "Structured governance, observability, and explainability of agent behavior (measure confidence, not trust)"
+        },
         "overallScore": {
           "type": "number",
           "minimum": 0,
           "maximum": 100,
-          "description": "Overall PACT score"
+          "description": "Overall PACTS score"
         }
       }
     },