kami
1de3e94990
The schema declared sources as an array of objects, which correx's flat JsonSchema model can't represent (JsonSchemaProperty has no nested properties). The strict config loader rejected it at startup, silently disabling the source_dossier artifact kind. Flatten sources to an array of strings (URL-prefixed per-source notes), update the gather prompt to match, and add ResearchSchemaLoadTest to guard every shipped research schema against the strict loader.
14 lines
568 B
JSON
14 lines
568 B
JSON
{
|
|
"type": "object",
|
|
"properties": {
|
|
"sources": {
|
|
"type": "array",
|
|
"description": "one entry per fetched source — each a self-contained note in your own words (per-source synthesis; the compression step). Start each entry with the source URL, then summarize what it contributes and which sub-question(s) it bears on. Never copy raw page text. Example: 'https://example.com/x — explains Y; bears on sub-question 2'.",
|
|
"minItems": 1,
|
|
"items": { "type": "string" }
|
|
}
|
|
},
|
|
"required": ["sources"],
|
|
"additionalProperties": true
|
|
}
|