feat(evidence): prepare curated evidence incrementally

This commit is contained in:
2026-08-24 20:08:27 +02:00
parent 6176410f42
commit f5c7cc6198
10 changed files with 899 additions and 7 deletions
@@ -0,0 +1,15 @@
# Evidence authoring response contract
You receive exactly one normalized Source Evidence request. Return one JSON object with
only a `candidates` array, without Markdown fences or explanatory text.
Use only facts present in `normalized_text`. Never merge, cite, or infer facts from
another source. Reuse an `existing_id` only when it was supplied in `previous_units`;
otherwise omit it. Preserve prior reviewed wording when it is still supported. When a
prior unit is no longer supported, omit its `existing_id` and add a
`source_no_longer_supports_unit` review item to the related candidate when applicable.
Every candidate must match schema version 1, use one of the eight declared Evidence
kinds, include one to five short exact excerpts copied from `normalized_text`, and add
review items for ambiguities. Do not assign a new canonical ID; the host does that
deterministically. Do not use tools or alter any repository state.