codingbuddy-rules 4.0.1 → 4.1.0

package/.ai-rules/CHANGELOG.md

@@ -5,6 +5,48 @@ All notable changes to the Multi-AI Coding Assistant Common Rules System will be
 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).
 
+## [4.1.0] - 2026-02-17
+
+### Added
+
+- **TUI Dashboard System**
+  - Ink-based terminal UI with Header, AgentCard, AgentTree, AgentGrid, StatusBar, ProgressBar
+  - EventEmitter2-based EventBus with `useEventBus` and `useAgentState` React hooks
+  - Unix Domain Socket IPC for standalone TUI process
+  - Compact single-line design for 24-line terminals
+  - TuiInterceptor MCP tool dispatch layer
+  - Agent Metadata Lookup Service
+
+- **Landing Page**
+  - Next.js 16 multilingual (5 languages) landing page
+  - Widget Slot architecture (AgentsShowcase, CodeExample, QuickStart)
+  - shadcn/ui, self-hosted fonts, next-intl i18n
+  - Vercel deployment with analytics, JSON-LD structured data
+
+- **MCP Server Enhancements**
+  - Bearer token authentication for SSE endpoints (#416)
+  - `dispatch_agents` tool and auto-dispatch in `parse_mode`
+  - `recommendedActAgent` support in EVAL mode (#361)
+  - `frontend-developer` and `devops-engineer` intent patterns
+
+- **Skills**
+  - `widget-slot-architecture` skill for Next.js App Router
+
+### Changed
+
+- Prettier `printWidth: 100` applied to entire codebase (#423)
+- MCP Server: extracted shared `rules-core` and `keyword-core` modules (#415)
+
+### Fixed
+
+- Plugin `isPathSafe()` path normalization and case-insensitive matching (#419)
+- MCP Server `appendContext` `findLastIndex` merge logic (#410)
+- MCP Server unsafe type assertion runtime validation (#411)
+- `validate-rules.sh` `.ai-rules` path reference (#422)
+- Agent count mismatch across documentation (#421)
+
+---
+
 ## [3.1.0] - 2026-01-22
 
 ### Added

package/.ai-rules/adapters/antigravity.md

@@ -300,7 +300,7 @@ task_boundary(
 
 ### Configuration
 
-Configure in `codingbuddy.config.js`:
+Configure in `codingbuddy.config.json`:
 
 ```javascript
 module.exports = {

package/.ai-rules/adapters/claude-code.md

@@ -354,69 +354,105 @@ The `parse_mode` MCP tool returns this field to recommend parallel specialist ex
 }
 ```
 
-### Parallel Execution Workflow
+### Auto-Dispatch Workflow (Recommended)
+
+When `parse_mode` returns `dispatchReady`, use it directly with the Task tool — no extra tool calls needed:
 
 ```
 Call parse_mode
      ↓
-Check parallelAgentsRecommendation
+Check dispatchReady
      ↓ (if exists)
-Display start message to user
+Use dispatchReady.primaryAgent.dispatchParams with Task tool
      ↓
-Call prepare_parallel_agents MCP
-     ↓
-Call each agent.taskPrompt via Task tool in parallel:
-  - subagent_type: "general-purpose"
-  - run_in_background: true
-  - prompt: agent.taskPrompt
+Use dispatchReady.parallelAgents[].dispatchParams with Task tool (run_in_background: true)
      ↓
 Collect results with TaskOutput
      ↓
 Display consolidated results to user
 ```
 
-### Code Example
+### Code Example (Auto-Dispatch)
 
 ```typescript
-// Step 1: Parse mode returns parallelAgentsRecommendation
+// Step 1: parse_mode returns dispatchReady with Task-tool-ready params
 const parseModeResult = await parse_mode({ prompt: "EVAL review auth implementation" });
 
-if (parseModeResult.parallelAgentsRecommendation) {
-  // Step 2: Display start message to user
-  console.log("🚀 Dispatching 4 specialist agents in parallel...");
-  console.log("   → 🔒 security-specialist");
-  console.log("   → ♿ accessibility-specialist");
-  console.log("   → ⚡ performance-specialist");
-  console.log("   → 📏 code-quality-specialist");
-
-  // Step 3: Prepare parallel agents
-  const preparedAgents = await prepare_parallel_agents({
-    mode: "EVAL",
-    specialists: parseModeResult.parallelAgentsRecommendation.specialists,
-    sharedContext: "Review authentication implementation",
-    targetFiles: ["src/auth/login.tsx"]
-  });
-
-  // Step 4: Execute in parallel using Task tool
-  const agentTasks = preparedAgents.agents.map(agent =>
+if (parseModeResult.dispatchReady) {
+  const { primaryAgent, parallelAgents } = parseModeResult.dispatchReady;
+
+  // Step 2: Dispatch primary agent (if present)
+  if (primaryAgent) {
     Task({
-      subagent_type: "general-purpose",
-      prompt: agent.taskPrompt,
-      description: agent.description,
-      run_in_background: true,
-      model: "opus" // Use opus for thorough analysis
-    })
-  );
-
-  // Step 5: Collect results
-  const results = await Promise.all(agentTasks.map(task => TaskOutput(task.id)));
-
-  // Step 6: Display summary
-  console.log("📊 Specialist Analysis Complete:");
+      subagent_type: primaryAgent.dispatchParams.subagent_type,
+      prompt: primaryAgent.dispatchParams.prompt,
+      description: primaryAgent.dispatchParams.description,
+    });
+  }
+
+  // Step 3: Dispatch parallel agents (if present)
+  const tasks = [];
+  if (parallelAgents) {
+    for (const agent of parallelAgents) {
+      tasks.push(Task({
+        subagent_type: agent.dispatchParams.subagent_type,
+        prompt: agent.dispatchParams.prompt,
+        description: agent.dispatchParams.description,
+        run_in_background: true,
+      }));
+    }
+  }
+
+  // Step 4: Collect results
+  const results = await Promise.all(tasks.map(task => TaskOutput(task.id)));
+
+  // Step 5: Display summary
+  console.log("Specialist Analysis Complete:");
   results.forEach(result => console.log(result.summary));
 }
 ```
 
+### Standalone Dispatch Tool
+
+For cases outside the `parse_mode` flow, use the `dispatch_agents` tool directly:
+
+```typescript
+const result = await dispatch_agents({
+  mode: "EVAL",
+  primaryAgent: "security-specialist",
+  specialists: ["accessibility-specialist", "performance-specialist"],
+  includeParallel: true,
+  taskDescription: "Review auth implementation",
+  targetFiles: ["src/auth/login.tsx"]
+});
+
+// result.primaryAgent.dispatchParams → ready for Task tool
+// result.parallelAgents[].dispatchParams → ready for Task tool with run_in_background
+```
+
+### Legacy Workflow (prepare_parallel_agents)
+
+The `prepare_parallel_agents` tool is still available for backward compatibility:
+
+```
+Call parse_mode
+     ↓
+Check parallelAgentsRecommendation
+     ↓ (if exists)
+Display start message to user
+     ↓
+Call prepare_parallel_agents MCP
+     ↓
+Call each agent.taskPrompt via Task tool in parallel:
+  - subagent_type: "general-purpose"
+  - run_in_background: true
+  - prompt: agent.taskPrompt
+     ↓
+Collect results with TaskOutput
+     ↓
+Display consolidated results to user
+```
+
 ### Visibility Pattern
 
 When executing parallel specialists, display clear status messages:
@@ -578,7 +614,7 @@ AUTO implement user authentication with JWT tokens
 
 ### Configuration
 
-Configure AUTO mode in `codingbuddy.config.js`:
+Configure AUTO mode in `codingbuddy.config.json`:
 
 ```javascript
 module.exports = {

package/.ai-rules/adapters/codex.md

@@ -236,7 +236,7 @@ When using GitHub Copilot Chat with AUTO mode:
 
 ### Configuration
 
-Configure in `codingbuddy.config.js`:
+Configure in `codingbuddy.config.json`:
 
 ```javascript
 module.exports = {

package/.ai-rules/adapters/cursor.md

@@ -253,7 +253,7 @@ When AUTO keyword is detected, Cursor calls `parse_mode` MCP tool which returns
 
 ### Configuration
 
-Configure in `codingbuddy.config.js`:
+Configure in `codingbuddy.config.json`:
 
 ```javascript
 module.exports = {

package/.ai-rules/adapters/kiro.md

@@ -219,7 +219,7 @@ Kiro: # Mode: AUTO (Iteration 1/3)
 
 ### Configuration
 
-Configure in `codingbuddy.config.js`:
+Configure in `codingbuddy.config.json`:
 
 ```javascript
 module.exports = {

package/.ai-rules/adapters/opencode.md

@@ -188,7 +188,7 @@ Once connected, you can use:
 
 OpenCode agents get language instructions dynamically from the MCP server:
 
-1. **Set language in codingbuddy.config.js:**
+1. **Set language in codingbuddy.config.json:**
    ```javascript
    module.exports = {
      language: 'ko',  // or 'en', 'ja', 'zh', 'es', etc.
@@ -236,7 +236,7 @@ The `parse_mode` tool now returns additional Mode Agent information and dynamic
 ```
 
 **New Fields:**
-- `language`: Language code from codingbuddy.config.js
+- `language`: Language code from codingbuddy.config.json
 - `languageInstruction`: Formatted instruction text for AI assistants (🆕)
 - `agent`: Mode Agent name (plan-mode, act-mode, eval-mode)
 - `delegates_to`: Which specialist agent the Mode Agent delegates to
@@ -598,7 +598,7 @@ Loop or Exit
 
 ### Configuration
 
-Configure in `codingbuddy.config.js`:
+Configure in `codingbuddy.config.json`:
 
 ```javascript
 module.exports = {

package/.ai-rules/adapters/q.md

@@ -207,7 +207,7 @@ Amazon Q's AWS expertise complements AUTO mode:
 
 ### Configuration
 
-Configure in `codingbuddy.config.js`:
+Configure in `codingbuddy.config.json`:
 
 ```javascript
 module.exports = {

package/.ai-rules/agents/README.md

@@ -626,7 +626,7 @@ Unified specialist agents organized by domain:
 
 **Expertise:**
 
-- Project Configuration (codingbuddy.config.js, .env)
+- Project Configuration (codingbuddy.config.json, .env)
 - TypeScript Configuration (tsconfig.json, paths)
 - Linting & Formatting (ESLint, Prettier, Stylelint)
 - Build Tools (Vite, Webpack, Next.js config, Rollup)

package/.ai-rules/agents/accessibility-specialist.json

@@ -114,10 +114,7 @@
             "Plan predictable navigation",
             "Plan input assistance (labels, errors, suggestions)"
           ],
-          "robust": [
-            "Plan compatible markup (assistive technologies)",
-            "Plan valid markup"
-          ]
+          "robust": ["Plan compatible markup (assistive technologies)", "Plan valid markup"]
         },
         "semantic_html_planning": {
           "elements": "Plan header, nav, main, article, section, aside, footer usage",
@@ -253,10 +250,7 @@
             "Verify predictable navigation",
             "Verify input assistance (labels, errors, suggestions)"
           ],
-          "robust": [
-            "Verify compatible markup (assistive technologies)",
-            "Verify valid markup"
-          ]
+          "robust": ["Verify compatible markup (assistive technologies)", "Verify valid markup"]
         },
         "semantic_html_verification": {
           "elements": "Verify header, nav, main, article, section, aside, footer usage",
@@ -423,11 +417,7 @@
           ]
         },
         "testing_tools": {
-          "automated": [
-            "axe DevTools",
-            "WAVE Browser Extension",
-            "Lighthouse Accessibility audit"
-          ],
+          "automated": ["axe DevTools", "WAVE Browser Extension", "Lighthouse Accessibility audit"],
           "manual": [
             "Keyboard-only navigation",
             "Screen reader testing (VoiceOver, NVDA)",

package/.ai-rules/agents/ai-ml-engineer.json

@@ -23,20 +23,8 @@
         "AWS Bedrock",
         "Azure OpenAI"
       ],
-      "local_models": [
-        "Ollama",
-        "llama.cpp",
-        "vLLM",
-        "HuggingFace Transformers"
-      ],
-      "vector_databases": [
-        "Pinecone",
-        "Weaviate",
-        "ChromaDB",
-        "pgvector",
-        "Milvus",
-        "Qdrant"
-      ],
+      "local_models": ["Ollama", "llama.cpp", "vLLM", "HuggingFace Transformers"],
+      "vector_databases": ["Pinecone", "Weaviate", "ChromaDB", "pgvector", "Milvus", "Qdrant"],
       "version_considerations": {
         "api_versioning": "Always pin SDK versions in package.json; API behavior may change between versions",
         "deprecation_monitoring": "Monitor provider changelogs for deprecated endpoints and models",
@@ -285,10 +273,7 @@
             "Missing caching layer",
             "No streaming support"
           ],
-          "low": [
-            "Minor optimization opportunities",
-            "Documentation improvements"
-          ]
+          "low": ["Minor optimization opportunities", "Documentation improvements"]
         }
       }
     },
@@ -395,11 +380,7 @@
             "Insufficient test coverage",
             "Type safety violations"
           ],
-          "medium": [
-            "Suboptimal performance",
-            "Missing caching",
-            "Inconsistent error messages"
-          ],
+          "medium": ["Suboptimal performance", "Missing caching", "Inconsistent error messages"],
           "low": ["Code style issues", "Documentation gaps"]
         }
       }

package/.ai-rules/agents/architecture-specialist.json

@@ -410,11 +410,7 @@
             "Untyped function parameters",
             "Missing return types"
           ],
-          "high": [
-            "Excessive type inference",
-            "Weak type definitions",
-            "Unsafe type assertions"
-          ],
+          "high": ["Excessive type inference", "Weak type definitions", "Unsafe type assertions"],
           "medium": [
             "Could use more specific types",
             "Type definitions could be improved",
@@ -442,10 +438,7 @@
             "Naming could be clearer",
             "Separation could be more explicit"
           ],
-          "low": [
-            "Minor organization improvements",
-            "File naming could be optimized"
-          ]
+          "low": ["Minor organization improvements", "File naming could be optimized"]
         },
         "risk_assessment": {
           "🔴 critical": "Major architecture violations (layer boundaries broken, circular dependencies, any type usage), blocking maintainability",

package/.ai-rules/agents/auto-mode.json

@@ -0,0 +1,106 @@
+{
+  "name": "Auto Mode Agent",
+  "description": "AUTO mode agent - autonomous PLAN → ACT → EVAL cycle until quality targets met",
+  "role": {
+    "title": "Auto Mode Agent",
+    "mode": "AUTO",
+    "purpose": "Mode Agent - autonomously cycles through PLAN → ACT → EVAL, delegates to Primary Developer Agent",
+    "expertise": [
+      "Autonomous PLAN → ACT → EVAL cycle execution",
+      "Quality-driven iteration (Critical/High issue elimination)",
+      "TDD-oriented planning and implementation",
+      "Multi-dimensional code quality evaluation",
+      "Self-correcting development workflow"
+    ],
+    "delegates_to": "frontend-developer",
+    "responsibilities": [
+      "Execute autonomous PLAN → ACT → EVAL cycles until quality targets met",
+      "PLAN phase: Analyze requirements, define TDD test cases, review architecture",
+      "ACT phase: Implement with strict TDD cycle (Red → Green → Refactor)",
+      "EVAL phase: Multi-dimensional quality evaluation with anti-sycophancy",
+      "Iterate until Critical=0 AND High=0 issues remaining",
+      "Maintain context continuity across cycle iterations",
+      "Track iteration count and quality metrics progression"
+    ]
+  },
+  "context_files": [
+    ".ai-rules/rules/core.md",
+    ".ai-rules/rules/project.md",
+    ".ai-rules/rules/augmented-coding.md"
+  ],
+  "activation": {
+    "trigger": "🔴 **STRICT**: When user types 'AUTO' or equivalent (Korean: 자동, Japanese: 自動, Chinese: 自动, Spanish: AUTOMÁTICO)",
+    "rule": "🔴 **STRICT**: AUTO MODE request must activate this Agent automatically",
+    "mandatory_checklist": {
+      "🔴 language": {
+        "rule": "MUST respond in Korean as specified in communication.language",
+        "verification_key": "language"
+      },
+      "🔴 mode_indicator": {
+        "rule": "MUST print '# Mode: AUTO' with iteration number as first line of response",
+        "verification_key": "mode_indicator"
+      },
+      "🔴 agent_indicator": {
+        "rule": "MUST print '## Agent : Frontend Developer' (or appropriate delegate agent)",
+        "verification_key": "agent_indicator"
+      },
+      "🔴 delegate_activation": {
+        "rule": "MUST activate delegate agent (frontend-developer) framework for autonomous execution",
+        "verification_key": "delegate_activation"
+      },
+      "🔴 autonomous_cycle": {
+        "rule": "MUST execute PLAN → ACT → EVAL cycle autonomously until Critical=0 AND High=0",
+        "verification_key": "autonomous_cycle"
+      },
+      "🔴 iteration_tracking": {
+        "rule": "MUST track and display iteration count (e.g., '# Mode: AUTO [Iteration 1]')",
+        "verification_key": "iteration_tracking"
+      },
+      "🔴 quality_gate": {
+        "rule": "MUST verify Critical=0 AND High=0 before completing AUTO mode",
+        "verification_key": "quality_gate"
+      }
+    }
+  },
+  "workflow": {
+    "autonomous_cycle": {
+      "plan_phase": "Analyze requirements, define TDD test strategy, review architecture",
+      "act_phase": "Execute TDD cycle (Red → Green → Refactor), implement changes",
+      "eval_phase": "Multi-dimensional evaluation with anti-sycophancy, classify issues by severity",
+      "iteration_control": "Continue cycling until Critical=0 AND High=0, then present results"
+    },
+    "quality_gates": {
+      "completion_criteria": "Critical=0 AND High=0 issues",
+      "max_iterations": "Stop after reasonable iterations and report remaining issues",
+      "per_iteration_output": "Show iteration number, phase, progress, and remaining issues"
+    }
+  },
+  "mode_specific": {
+    "autonomous_output": {
+      "iteration_header": "Display '# Mode: AUTO [Iteration N]' with current phase",
+      "phase_tracking": "Show current phase (PLAN/ACT/EVAL) within each iteration",
+      "quality_metrics": "Track Critical/High/Medium/Low issue counts across iterations",
+      "completion_summary": "Final summary with all iterations, changes made, and quality results"
+    }
+  },
+  "delegate_agent": {
+    "primary": "frontend-developer",
+    "description": "This Mode Agent utilizes the Frontend Developer Agent's full workflow across all phases",
+    "integration": "Applies Frontend Developer Agent's planning, TDD implementation, and evaluation capabilities"
+  },
+  "communication": {
+    "style": "Autonomous execution with clear iteration and phase progress reporting",
+    "format": "Structured iteration reports with quality metrics and phase indicators"
+  },
+  "verification_guide": {
+    "mode_compliance": [
+      "✅ Verify '# Mode: AUTO [Iteration N]' is displayed",
+      "✅ Verify '## Agent : Frontend Developer' (or appropriate delegate) is displayed",
+      "✅ Verify response in configured language",
+      "✅ Verify autonomous PLAN → ACT → EVAL cycle execution",
+      "✅ Verify iteration tracking with quality metrics",
+      "✅ Verify completion only when Critical=0 AND High=0",
+      "✅ Verify Delegate Agent's full workflow is applied across all phases"
+    ]
+  }
+}

package/.ai-rules/agents/code-reviewer.json

@@ -423,10 +423,7 @@
         "conditional_branches": {
           "description": "if/else, 삼항연산자, switch 각 분기 추적",
           "question": "각 분기가 의도대로 동작하는가?",
-          "common_bugs": [
-            "조건 누락으로 특정 케이스만 처리",
-            "else 분기 미구현"
-          ]
+          "common_bugs": ["조건 누락으로 특정 케이스만 처리", "else 분기 미구현"]
         },
         "data_transformations": {
           "description": "타입 변환 함수의 입출력 필드 매핑 확인",
@@ -446,11 +443,7 @@
         "edge_cases": {
           "description": "null, undefined, 빈 배열, 경계값 처리",
           "question": "경계 조건이 올바르게 처리되는가?",
-          "common_bugs": [
-            "빈 배열 처리 누락",
-            "null 참조 에러",
-            "경계값 off-by-one"
-          ]
+          "common_bugs": ["빈 배열 처리 누락", "null 참조 에러", "경계값 off-by-one"]
         }
       },
       "skip_conditions": ["신규 파일만 생성", "문서만 변경", "테스트만 추가"],

package/.ai-rules/agents/data-engineer.json

@@ -16,13 +16,7 @@
     ],
     "supported_databases": {
       "note": "This agent supports multiple database systems. See project.md 'Tech Stack' for your project's specific database.",
-      "relational": [
-        "PostgreSQL",
-        "MySQL/MariaDB",
-        "SQLite",
-        "SQL Server",
-        "Oracle"
-      ],
+      "relational": ["PostgreSQL", "MySQL/MariaDB", "SQLite", "SQL Server", "Oracle"],
       "nosql": ["MongoDB", "Redis", "Elasticsearch", "DynamoDB", "Cassandra"],
       "analytical": ["BigQuery", "Snowflake", "Redshift", "ClickHouse"]
     },
@@ -166,11 +160,7 @@
   "workflow": {
     "schema_design": {
       "approach": "Design-First with TDD",
-      "applies_to": [
-        "New table/entity creation",
-        "Schema modifications",
-        "Relationship changes"
-      ],
+      "applies_to": ["New table/entity creation", "Schema modifications", "Relationship changes"],
       "steps": [
         "1. Analyze business requirements",
         "2. Create ERD/data model",
@@ -195,11 +185,7 @@
     },
     "analytics_data": {
       "approach": "Dimensional Modeling",
-      "applies_to": [
-        "Reporting tables",
-        "Dashboard data",
-        "Aggregated metrics"
-      ],
+      "applies_to": ["Reporting tables", "Dashboard data", "Aggregated metrics"],
       "steps": [
         "1. Identify business questions",
         "2. Design fact and dimension tables",

package/.ai-rules/agents/eval-mode.json

@@ -24,10 +24,7 @@
       "Apply Anti-Sycophancy principles (objective evaluation, problem-first identification)"
     ]
   },
-  "context_files": [
-    ".ai-rules/rules/core.md",
-    ".ai-rules/rules/augmented-coding.md"
-  ],
+  "context_files": [".ai-rules/rules/core.md", ".ai-rules/rules/augmented-coding.md"],
   "activation": {
     "trigger": "🔴 **STRICT**: When user types 'EVAL', 'EVALUATE' or equivalent (Korean: 평가해/개선안 제시해, Japanese: 評価, Chinese: 评估, Spanish: EVALUAR)",
     "rule": "🔴 **STRICT**: EVAL MODE request must activate this Agent automatically",

package/.ai-rules/agents/event-architecture-specialist.json

@@ -360,11 +360,7 @@
             "Incomplete error categorization",
             "Missing DLQ alerting"
           ],
-          "low": [
-            "Minor configuration improvements",
-            "Additional metrics",
-            "Documentation updates"
-          ]
+          "low": ["Minor configuration improvements", "Additional metrics", "Documentation updates"]
         }
       }
     },

package/.ai-rules/agents/i18n-specialist.json

@@ -99,11 +99,7 @@
       },
       "planning_framework": {
         "library_selection": {
-          "react": [
-            "react-intl (FormatJS)",
-            "i18next + react-i18next",
-            "next-intl"
-          ],
+          "react": ["react-intl (FormatJS)", "i18next + react-i18next", "next-intl"],
           "vue": ["vue-i18n", "nuxt-i18n"],
           "angular": ["@angular/localize", "ngx-translate"],
           "native_mobile": ["react-native-i18n", "flutter_localizations"],

package/.ai-rules/agents/migration-specialist.json

@@ -249,11 +249,7 @@
             "Communication plan incomplete",
             "Resource constraints not addressed"
           ],
-          "low": [
-            "Documentation gaps",
-            "Training not scheduled",
-            "Minor dependency updates needed"
-          ]
+          "low": ["Documentation gaps", "Training not scheduled", "Minor dependency updates needed"]
         }
       }
     },
@@ -571,11 +567,7 @@
           "Load balancer",
           "Health checks"
         ],
-        "success_criteria": [
-          "Instant switch",
-          "Instant rollback",
-          "Zero downtime"
-        ]
+        "success_criteria": ["Instant switch", "Instant rollback", "Zero downtime"]
       },
       "canary": {
         "description": "Gradually route traffic to new version, monitoring for issues",
@@ -599,11 +591,7 @@
           "Deprecation notices",
           "Client migration tracking"
         ],
-        "success_criteria": [
-          "Old clients work",
-          "New clients work",
-          "Clear deprecation timeline"
-        ]
+        "success_criteria": ["Old clients work", "New clients work", "Clear deprecation timeline"]
       }
     },
     "sli_definitions": {