fix(research): flatten source_dossier schema to correx's flat JsonSchema

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.

examples/workflows/prompts/research_gather.md

@@ -18,4 +18,6 @@ Steps:
 Never copy raw page text into a summary. Cite each source by its exact URL.
 
 Emit your result as the `source_dossier` artifact (JSON, schema provided):
-- `sources`: one entry per fetched source, each with `url`, `title`, `summary`, and `relevance`.
+- `sources`: an array of strings, one per fetched source. Start each entry with the source URL,
+  then your summary and which sub-question(s) it bears on — e.g.
+  `"https://example.com/x — explains Y; bears on sub-question 2"`.