378 lines
11 KiB
JSON
378 lines
11 KiB
JSON
{
|
|
"$schema": "https://json-schema.org/draft/2020-12/schema",
|
|
"$id": "https://schemas.aftech.internal/article-consolidation/v1/manifest-output.schema.json",
|
|
"x-contract-version": "1.0.0",
|
|
"title": "ArticleConsolidationManifest",
|
|
"type": "object",
|
|
"required": [
|
|
"schema_version",
|
|
"fingerprint",
|
|
"source_url",
|
|
"selected_extractor",
|
|
"final_status",
|
|
"generate_markdown",
|
|
"markdown_path",
|
|
"markdown_hash",
|
|
"ecp_classification",
|
|
"enrichment",
|
|
"provider_versions",
|
|
"model_versions",
|
|
"prompt_versions",
|
|
"config_version",
|
|
"trace_id",
|
|
"error_codes"
|
|
],
|
|
"properties": {
|
|
"schema_version": {
|
|
"type": "string",
|
|
"const": "1.0.0"
|
|
},
|
|
"fingerprint": {
|
|
"type": "string",
|
|
"minLength": 64,
|
|
"maxLength": 64
|
|
},
|
|
"source_url": {
|
|
"type": "string"
|
|
},
|
|
"selected_extractor": {
|
|
"type": "string",
|
|
"enum": ["trafilatura", "newspaper4k", "readability"]
|
|
},
|
|
"final_status": {
|
|
"type": "string",
|
|
"enum": [
|
|
"completed_text",
|
|
"rejected_ecp",
|
|
"failed_validation",
|
|
"failed_processing"
|
|
]
|
|
},
|
|
"generate_markdown": {
|
|
"type": "boolean"
|
|
},
|
|
"markdown_path": {
|
|
"type": ["string", "null"]
|
|
},
|
|
"markdown_hash": {
|
|
"type": ["string", "null"],
|
|
"minLength": 64,
|
|
"maxLength": 64
|
|
},
|
|
"ecp_classification": {
|
|
"type": ["object", "null"],
|
|
"required": ["category", "confidence", "rationale", "evidences"],
|
|
"properties": {
|
|
"category": {
|
|
"type": "string",
|
|
"enum": [
|
|
"DIRECT_INHERENT",
|
|
"CONTEXTUAL_INHERENT",
|
|
"TANGENTIAL",
|
|
"NOT_RELATED"
|
|
]
|
|
},
|
|
"confidence": {
|
|
"type": "number",
|
|
"minimum": 0.0,
|
|
"maximum": 1.0
|
|
},
|
|
"rationale": {
|
|
"type": "string"
|
|
},
|
|
"evidences": {
|
|
"type": "array",
|
|
"items": { "type": "string" },
|
|
"description": "Grounded textual fragments from intermediate Markdown"
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"enrichment": {
|
|
"type": ["object", "null"],
|
|
"required": ["sentiment", "tags"],
|
|
"properties": {
|
|
"sentiment": {
|
|
"type": "string",
|
|
"enum": ["positive", "negative", "neutral"]
|
|
},
|
|
"tags": {
|
|
"type": "array",
|
|
"items": { "type": "string", "minLength": 1 },
|
|
"minItems": 3,
|
|
"maxItems": 8,
|
|
"uniqueItems": true
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"provider_versions": {
|
|
"type": ["object", "null"],
|
|
"required": ["hygiene", "enrichment"],
|
|
"properties": {
|
|
"hygiene": {
|
|
"type": ["object", "null"],
|
|
"required": ["provider", "model", "role_config_version"],
|
|
"properties": {
|
|
"provider": { "type": "string" },
|
|
"model": { "type": "string" },
|
|
"role_config_version": { "type": "string" }
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"enrichment": {
|
|
"type": ["object", "null"],
|
|
"required": ["provider", "model", "role_config_version"],
|
|
"properties": {
|
|
"provider": { "type": "string" },
|
|
"model": { "type": "string" },
|
|
"role_config_version": { "type": "string" }
|
|
},
|
|
"additionalProperties": false
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"model_versions": {
|
|
"type": ["object", "null"],
|
|
"required": ["runtime_primary", "runtime_fallback"],
|
|
"properties": {
|
|
"runtime_primary": {
|
|
"type": "object",
|
|
"required": ["provider", "model", "role_config_version"],
|
|
"properties": {
|
|
"provider": { "type": "string" },
|
|
"model": { "type": "string" },
|
|
"role_config_version": { "type": "string" }
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"runtime_fallback": {
|
|
"type": "object",
|
|
"required": ["provider", "model", "role_config_version"],
|
|
"properties": {
|
|
"provider": { "type": "string" },
|
|
"model": { "type": "string" },
|
|
"role_config_version": { "type": "string" }
|
|
},
|
|
"additionalProperties": false
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"prompt_versions": {
|
|
"type": ["object", "null"],
|
|
"required": ["article_content_hygiene", "article_sentiment_tags"],
|
|
"properties": {
|
|
"article_content_hygiene": {
|
|
"type": "object",
|
|
"required": ["version", "hash"],
|
|
"properties": {
|
|
"version": { "type": "string" },
|
|
"hash": { "type": "string" }
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"article_sentiment_tags": {
|
|
"type": "object",
|
|
"required": ["version", "hash"],
|
|
"properties": {
|
|
"version": { "type": "string" },
|
|
"hash": { "type": "string" }
|
|
},
|
|
"additionalProperties": false
|
|
}
|
|
},
|
|
"additionalProperties": false
|
|
},
|
|
"config_version": {
|
|
"type": "string",
|
|
"minLength": 1
|
|
},
|
|
"trace_id": {
|
|
"type": ["string", "null"]
|
|
},
|
|
"error_codes": {
|
|
"type": "array",
|
|
"uniqueItems": true,
|
|
"items": {
|
|
"type": "string",
|
|
"enum": [
|
|
"INVALID_ARTICLE_SCHEMA",
|
|
"MISSING_SELECTED_EXTRACTOR",
|
|
"INVALID_SELECTED_EXTRACTOR",
|
|
"SELECTED_EXTRACTOR_UNAVAILABLE",
|
|
"MISSING_SOURCE_URL",
|
|
"MISSING_TITLE_CANDIDATE",
|
|
"MISSING_CONTENT",
|
|
"INVALID_ECP_SCHEMA",
|
|
"HYGIENE_FAILED",
|
|
"GROUNDING_VIOLATION",
|
|
"INVALID_TEXT_REPAIR",
|
|
"ECP_CLASSIFICATION_FAILED",
|
|
"ECP_REJECTED",
|
|
"ENRICHMENT_FAILED",
|
|
"PERSISTENCE_FAILED",
|
|
"TELEMETRY_PENDING"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"allOf": [
|
|
{
|
|
"if": {
|
|
"properties": { "final_status": { "const": "completed_text" } }
|
|
},
|
|
"then": {
|
|
"properties": {
|
|
"generate_markdown": { "const": true },
|
|
"markdown_path": { "type": "string", "minLength": 1 },
|
|
"markdown_hash": { "type": "string", "minLength": 64, "maxLength": 64 },
|
|
"ecp_classification": {
|
|
"type": "object",
|
|
"properties": {
|
|
"category": { "enum": ["DIRECT_INHERENT", "CONTEXTUAL_INHERENT"] }
|
|
}
|
|
},
|
|
"enrichment": { "type": "object" },
|
|
"provider_versions": {
|
|
"type": "object",
|
|
"properties": {
|
|
"hygiene": { "type": "object" },
|
|
"enrichment": { "type": "object" }
|
|
}
|
|
},
|
|
"model_versions": { "type": "object" },
|
|
"prompt_versions": { "type": "object" },
|
|
"error_codes": {
|
|
"type": "array",
|
|
"items": { "const": "TELEMETRY_PENDING" },
|
|
"maxItems": 1,
|
|
"uniqueItems": true
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"if": {
|
|
"properties": { "final_status": { "const": "rejected_ecp" } }
|
|
},
|
|
"then": {
|
|
"properties": {
|
|
"generate_markdown": { "const": false },
|
|
"markdown_path": { "type": "null" },
|
|
"markdown_hash": { "type": "null" },
|
|
"ecp_classification": {
|
|
"type": "object",
|
|
"properties": {
|
|
"category": { "enum": ["TANGENTIAL", "NOT_RELATED"] }
|
|
}
|
|
},
|
|
"enrichment": { "type": "null" },
|
|
"provider_versions": {
|
|
"type": "object",
|
|
"properties": {
|
|
"hygiene": { "type": "object" },
|
|
"enrichment": { "type": "null" }
|
|
}
|
|
},
|
|
"model_versions": { "type": "object" },
|
|
"prompt_versions": { "type": "object" },
|
|
"error_codes": {
|
|
"type": "array",
|
|
"items": { "enum": ["ECP_REJECTED", "TELEMETRY_PENDING"] },
|
|
"contains": { "const": "ECP_REJECTED" },
|
|
"minContains": 1,
|
|
"maxContains": 1,
|
|
"minItems": 1,
|
|
"maxItems": 2,
|
|
"uniqueItems": true
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"if": {
|
|
"properties": { "final_status": { "const": "failed_validation" } }
|
|
},
|
|
"then": {
|
|
"properties": {
|
|
"generate_markdown": { "const": false },
|
|
"markdown_path": { "type": "null" },
|
|
"markdown_hash": { "type": "null" },
|
|
"provider_versions": { "type": "null" },
|
|
"error_codes": {
|
|
"type": "array",
|
|
"items": {
|
|
"enum": [
|
|
"INVALID_ARTICLE_SCHEMA",
|
|
"MISSING_SELECTED_EXTRACTOR",
|
|
"INVALID_SELECTED_EXTRACTOR",
|
|
"SELECTED_EXTRACTOR_UNAVAILABLE",
|
|
"MISSING_SOURCE_URL",
|
|
"MISSING_TITLE_CANDIDATE",
|
|
"MISSING_CONTENT",
|
|
"INVALID_ECP_SCHEMA",
|
|
"TELEMETRY_PENDING"
|
|
]
|
|
},
|
|
"contains": {
|
|
"enum": [
|
|
"INVALID_ARTICLE_SCHEMA",
|
|
"MISSING_SELECTED_EXTRACTOR",
|
|
"INVALID_SELECTED_EXTRACTOR",
|
|
"SELECTED_EXTRACTOR_UNAVAILABLE",
|
|
"MISSING_SOURCE_URL",
|
|
"MISSING_TITLE_CANDIDATE",
|
|
"MISSING_CONTENT",
|
|
"INVALID_ECP_SCHEMA"
|
|
]
|
|
},
|
|
"minItems": 1,
|
|
"uniqueItems": true
|
|
}
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"if": {
|
|
"properties": { "final_status": { "const": "failed_processing" } }
|
|
},
|
|
"then": {
|
|
"properties": {
|
|
"generate_markdown": { "const": false },
|
|
"markdown_path": { "type": "null" },
|
|
"markdown_hash": { "type": "null" },
|
|
"error_codes": {
|
|
"type": "array",
|
|
"items": {
|
|
"enum": [
|
|
"HYGIENE_FAILED",
|
|
"GROUNDING_VIOLATION",
|
|
"INVALID_TEXT_REPAIR",
|
|
"ECP_CLASSIFICATION_FAILED",
|
|
"ENRICHMENT_FAILED",
|
|
"PERSISTENCE_FAILED",
|
|
"TELEMETRY_PENDING"
|
|
]
|
|
},
|
|
"contains": {
|
|
"enum": [
|
|
"HYGIENE_FAILED",
|
|
"GROUNDING_VIOLATION",
|
|
"INVALID_TEXT_REPAIR",
|
|
"ECP_CLASSIFICATION_FAILED",
|
|
"ENRICHMENT_FAILED",
|
|
"PERSISTENCE_FAILED"
|
|
]
|
|
},
|
|
"minItems": 1,
|
|
"uniqueItems": true
|
|
}
|
|
}
|
|
}
|
|
}
|
|
],
|
|
"additionalProperties": false
|
|
}
|