mirror of
https://github.com/proffesor-for-testing/agentic-qe.git
synced 2026-09-19 08:45:47 +08:00
Dragan Spiridonov
56206c7be2
Follow-up tod95f0d7b/2f4d119c— the earlier passes updated .claude/skills and assets/skills but missed several other eval surfaces that still pinned retired IDs (claude-3.5-sonnet, claude-3-haiku): - `.github/workflows/test-qe-browser.yml` — the `aqe eval run --model` flag (inert in command-eval mode, but a real dead-ID leftover) -> claude-sonnet-4-6. - `plugins/agentic-qe-fleet/skills/` — the tracked plugin-marketplace skill copy (8 eval suites + a sample-output fixture); chaos skills get the opus-4-8 ceiling. - `docs/schemas/skill-eval.schema.json` — models `enum` was missing claude-opus-4-8 and still allowed retired/deprecated IDs; trimmed to current+active, default flipped to claude-sonnet-4-6. Plus description examples in the sibling schemas and the modelUsed values in docs/examples/*.json fixtures. - `docs/templates/skill-frontmatter.example.yaml` validation_models list. - `src/cli/commands/eval.ts` — the `aqe eval` `--model` help example and the `run-all --models` default (`claude-3.5-sonnet` -> `claude-sonnet-4-6`). Verified: typecheck clean; all edited JSON/YAML parse; zero retired IDs remain in any eval suite, schema, template, workflow, or eval-CLI default. Intentionally left untouched: the consensus-provider subsystem (pricing tables / type-unions / defaults — separate routing layer, bucket-2 data) and historical release notes / QE audit reports (which document the old IDs by design). Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
454 lines
14 KiB
JSON
454 lines
14 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"$id": "https://agentic-qe.dev/schemas/skill-eval.json",
|
|
"title": "AQE Skill Evaluation Test Suite Schema",
|
|
"description": "Schema for skill evaluation YAML test suites used in Trust Tier 3 validation. Supports multi-model testing, AQE MCP integration, and ReasoningBank learning.",
|
|
"type": "object",
|
|
"required": ["skill", "version", "test_cases", "success_criteria"],
|
|
"properties": {
|
|
"skill": {
|
|
"type": "string",
|
|
"pattern": "^[a-z][a-z0-9-]*$",
|
|
"description": "Skill name being evaluated (must match .claude/skills/{skill}/SKILL.md)"
|
|
},
|
|
"version": {
|
|
"type": "string",
|
|
"pattern": "^\\d+\\.\\d+\\.\\d+$",
|
|
"description": "Evaluation suite version (semver)"
|
|
},
|
|
"description": {
|
|
"type": "string",
|
|
"maxLength": 1000,
|
|
"description": "Description of evaluation suite purpose and coverage goals"
|
|
},
|
|
"models_to_test": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "string",
|
|
"enum": [
|
|
"claude-opus-4-8",
|
|
"claude-opus-4-7",
|
|
"claude-sonnet-4-6",
|
|
"claude-haiku-4-5",
|
|
"claude-opus-4-5",
|
|
"gpt-4o",
|
|
"gpt-4o-mini",
|
|
"gpt-4-turbo"
|
|
]
|
|
},
|
|
"default": ["claude-sonnet-4-6"],
|
|
"minItems": 1,
|
|
"uniqueItems": true,
|
|
"description": "Models to run evaluation against for cross-model validation"
|
|
},
|
|
"mcp_integration": {
|
|
"$ref": "#/$defs/mcp_integration_config",
|
|
"description": "AQE MCP integration configuration for shared learning"
|
|
},
|
|
"learning": {
|
|
"$ref": "#/$defs/learning_config",
|
|
"description": "ReasoningBank learning configuration"
|
|
},
|
|
"result_format": {
|
|
"$ref": "#/$defs/result_format",
|
|
"description": "Output format configuration"
|
|
},
|
|
"setup": {
|
|
"type": "object",
|
|
"description": "Setup configuration for test environment",
|
|
"properties": {
|
|
"required_tools": {
|
|
"type": "array",
|
|
"items": { "type": "string" },
|
|
"description": "Tools that must be available"
|
|
},
|
|
"environment_variables": {
|
|
"type": "object",
|
|
"additionalProperties": { "type": "string" },
|
|
"description": "Environment variables to set"
|
|
},
|
|
"fixtures": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"name": { "type": "string" },
|
|
"path": { "type": "string" },
|
|
"content": { "type": "string" }
|
|
}
|
|
},
|
|
"description": "Test fixtures to create"
|
|
}
|
|
}
|
|
},
|
|
"test_cases": {
|
|
"type": "array",
|
|
"minItems": 1,
|
|
"items": {
|
|
"$ref": "#/$defs/test_case"
|
|
},
|
|
"description": "Evaluation test cases"
|
|
},
|
|
"success_criteria": {
|
|
"type": "object",
|
|
"required": ["pass_rate"],
|
|
"properties": {
|
|
"pass_rate": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"description": "Minimum pass rate for suite to pass"
|
|
},
|
|
"critical_pass_rate": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"default": 1.0,
|
|
"description": "Pass rate required for critical priority tests"
|
|
},
|
|
"avg_reasoning_quality": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"description": "Minimum average reasoning quality score"
|
|
},
|
|
"max_execution_time_ms": {
|
|
"type": "integer",
|
|
"minimum": 0,
|
|
"description": "Maximum execution time for test suite"
|
|
},
|
|
"cross_model_variance": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"description": "Maximum allowed variance between models"
|
|
}
|
|
}
|
|
},
|
|
"metadata": {
|
|
"type": "object",
|
|
"properties": {
|
|
"author": { "type": "string" },
|
|
"created": { "type": "string", "format": "date" },
|
|
"last_updated": { "type": "string", "format": "date" },
|
|
"coverage_target": { "type": "string" }
|
|
}
|
|
}
|
|
},
|
|
"$defs": {
|
|
"test_case": {
|
|
"type": "object",
|
|
"required": ["id", "description", "input", "expected_output"],
|
|
"properties": {
|
|
"id": {
|
|
"type": "string",
|
|
"pattern": "^tc\\d{3}_[a-z_]+$",
|
|
"description": "Test case ID (e.g., tc001_sql_injection)"
|
|
},
|
|
"description": {
|
|
"type": "string",
|
|
"description": "What this test case validates"
|
|
},
|
|
"category": {
|
|
"type": "string",
|
|
"description": "Test category for grouping"
|
|
},
|
|
"priority": {
|
|
"type": "string",
|
|
"enum": ["critical", "high", "medium", "low"],
|
|
"default": "medium",
|
|
"description": "Test priority"
|
|
},
|
|
"skip": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "Skip this test case"
|
|
},
|
|
"skip_reason": {
|
|
"type": "string",
|
|
"description": "Reason for skipping"
|
|
},
|
|
"input": {
|
|
"$ref": "#/$defs/test_input"
|
|
},
|
|
"expected_output": {
|
|
"$ref": "#/$defs/expected_output"
|
|
},
|
|
"validation": {
|
|
"$ref": "#/$defs/validation_config"
|
|
},
|
|
"timeout_ms": {
|
|
"type": "integer",
|
|
"minimum": 1000,
|
|
"default": 30000,
|
|
"description": "Test timeout in milliseconds"
|
|
}
|
|
}
|
|
},
|
|
"test_input": {
|
|
"type": "object",
|
|
"description": "Input provided to the skill",
|
|
"properties": {
|
|
"code": {
|
|
"type": "string",
|
|
"description": "Code snippet to analyze"
|
|
},
|
|
"file_path": {
|
|
"type": "string",
|
|
"description": "Path to file to analyze"
|
|
},
|
|
"url": {
|
|
"type": "string",
|
|
"format": "uri",
|
|
"description": "URL to analyze"
|
|
},
|
|
"prompt": {
|
|
"type": "string",
|
|
"description": "Custom prompt for the skill"
|
|
},
|
|
"context": {
|
|
"type": "object",
|
|
"properties": {
|
|
"language": {
|
|
"type": "string",
|
|
"description": "Programming language"
|
|
},
|
|
"framework": {
|
|
"type": "string",
|
|
"description": "Framework in use"
|
|
},
|
|
"environment": {
|
|
"type": "string",
|
|
"enum": ["development", "staging", "production"],
|
|
"description": "Target environment"
|
|
}
|
|
}
|
|
},
|
|
"options": {
|
|
"type": "object",
|
|
"additionalProperties": true,
|
|
"description": "Skill-specific options"
|
|
}
|
|
}
|
|
},
|
|
"expected_output": {
|
|
"type": "object",
|
|
"description": "Expected characteristics of skill output",
|
|
"properties": {
|
|
"must_contain": {
|
|
"type": "array",
|
|
"items": { "type": "string" },
|
|
"description": "Strings that must appear in output"
|
|
},
|
|
"must_not_contain": {
|
|
"type": "array",
|
|
"items": { "type": "string" },
|
|
"description": "Strings that must not appear in output"
|
|
},
|
|
"must_match_regex": {
|
|
"type": "array",
|
|
"items": { "type": "string" },
|
|
"description": "Regex patterns output must match"
|
|
},
|
|
"severity_classification": {
|
|
"type": "string",
|
|
"enum": ["critical", "high", "medium", "low", "info"],
|
|
"description": "Expected severity classification"
|
|
},
|
|
"finding_count": {
|
|
"type": "object",
|
|
"properties": {
|
|
"min": { "type": "integer", "minimum": 0 },
|
|
"max": { "type": "integer", "minimum": 0 }
|
|
},
|
|
"description": "Expected range of findings"
|
|
},
|
|
"recommendation_count": {
|
|
"type": "object",
|
|
"properties": {
|
|
"min": { "type": "integer", "minimum": 0 },
|
|
"max": { "type": "integer", "minimum": 0 }
|
|
},
|
|
"description": "Expected range of recommendations"
|
|
},
|
|
"schema_path": {
|
|
"type": "string",
|
|
"description": "Path to JSON schema for output validation"
|
|
},
|
|
"custom_assertions": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "object",
|
|
"properties": {
|
|
"type": {
|
|
"type": "string",
|
|
"enum": ["jsonpath", "semantic", "function"]
|
|
},
|
|
"expression": { "type": "string" },
|
|
"expected": {}
|
|
}
|
|
},
|
|
"description": "Custom assertions for complex validation"
|
|
}
|
|
}
|
|
},
|
|
"validation_config": {
|
|
"type": "object",
|
|
"description": "Validation configuration for test case",
|
|
"properties": {
|
|
"schema_check": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Validate output against schema"
|
|
},
|
|
"keyword_match_threshold": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"default": 0.8,
|
|
"description": "Minimum keyword match ratio for pass"
|
|
},
|
|
"reasoning_quality_min": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"description": "Minimum reasoning quality score"
|
|
},
|
|
"semantic_similarity_min": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"description": "Minimum semantic similarity to expected"
|
|
},
|
|
"allow_partial": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "Allow partial matches"
|
|
},
|
|
"grading_rubric": {
|
|
"type": "object",
|
|
"properties": {
|
|
"completeness": { "type": "number", "minimum": 0, "maximum": 1 },
|
|
"accuracy": { "type": "number", "minimum": 0, "maximum": 1 },
|
|
"actionability": { "type": "number", "minimum": 0, "maximum": 1 }
|
|
},
|
|
"description": "Weighted grading rubric (weights should sum to 1.0)"
|
|
}
|
|
}
|
|
},
|
|
"mcp_integration_config": {
|
|
"type": "object",
|
|
"description": "Configuration for AQE MCP tool integration per MCP Integration Spec",
|
|
"properties": {
|
|
"enabled": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Enable MCP integration for this eval suite"
|
|
},
|
|
"namespace": {
|
|
"type": "string",
|
|
"default": "skill-validation",
|
|
"description": "Memory namespace for storing patterns and outcomes"
|
|
},
|
|
"store_patterns": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Store successful patterns via mcp__agentic-qe__memory_store"
|
|
},
|
|
"query_patterns": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Query existing patterns before running via mcp__agentic-qe__memory_query"
|
|
},
|
|
"track_outcomes": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Track test outcomes via mcp__agentic-qe__test_outcome_track"
|
|
},
|
|
"share_learning": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Share learning with fleet via mcp__agentic-qe__memory_share"
|
|
},
|
|
"update_quality_gate": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Update quality gate metrics via mcp__agentic-qe__quality_assess"
|
|
},
|
|
"target_agents": {
|
|
"type": "array",
|
|
"items": { "type": "string" },
|
|
"default": ["qe-learning-coordinator", "qe-queen-coordinator"],
|
|
"description": "Agent IDs to share learning with"
|
|
}
|
|
}
|
|
},
|
|
"learning_config": {
|
|
"type": "object",
|
|
"description": "Configuration for ReasoningBank learning integration",
|
|
"properties": {
|
|
"store_success_patterns": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Store patterns from successful test runs"
|
|
},
|
|
"store_failure_patterns": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Store patterns from failures for learning"
|
|
},
|
|
"pattern_ttl_days": {
|
|
"type": "integer",
|
|
"minimum": 1,
|
|
"maximum": 365,
|
|
"default": 90,
|
|
"description": "Time-to-live for stored patterns in days"
|
|
},
|
|
"min_confidence_to_store": {
|
|
"type": "number",
|
|
"minimum": 0,
|
|
"maximum": 1,
|
|
"default": 0.7,
|
|
"description": "Minimum confidence score to store pattern"
|
|
},
|
|
"cross_model_comparison": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Store cross-model behavior comparisons"
|
|
}
|
|
}
|
|
},
|
|
"result_format": {
|
|
"type": "object",
|
|
"description": "Output format configuration for evaluation results",
|
|
"properties": {
|
|
"json_output": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Output results as JSON"
|
|
},
|
|
"markdown_report": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "Generate markdown report"
|
|
},
|
|
"include_raw_output": {
|
|
"type": "boolean",
|
|
"default": false,
|
|
"description": "Include raw LLM output in results"
|
|
},
|
|
"include_timing": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Include timing information"
|
|
},
|
|
"include_token_usage": {
|
|
"type": "boolean",
|
|
"default": true,
|
|
"description": "Include token usage statistics"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|