diff --git a/README.md b/README.md index ff6eadd..2b5d0d3 100644 --- a/README.md +++ b/README.md @@ -5,8 +5,8 @@ culture, and constraint, and the planned lowerer that turns an agent's meaning packet into the reader's display language. **What is valuable here.** The interlingua standard and the lowering design: a -meaning packet owns what is meant, the scene state (live: `weksa scene put|dump`; speaker -documents are planned) owns the speaker's relation to the addressee, which selects register, +meaning packet owns what is meant, the scene state (live: `weksa scene put|dump`, labelled by the rule in +`docs/scene-annotation.md`; speaker documents are planned) owns the speaker's relation to the addressee, which selects register, address and politeness, and a lowerer owns surface text and leaves a trace. **The problem it solves.** An agent's outward speech today is one English diff --git a/crates/weksa/tests/original_corpus.rs b/crates/weksa/tests/original_corpus.rs index a3eae63..9036223 100644 --- a/crates/weksa/tests/original_corpus.rs +++ b/crates/weksa/tests/original_corpus.rs @@ -1039,7 +1039,7 @@ fn committed_scenes_cover_original_groups() { let held: BTreeSet = scenes.iter().map(|s| s.group.clone()).collect(); assert_eq!(held, live, "a scene for each live Train or Validation group, none other"); // Revisions append: a group's later revisions re-derived its relation. - assert!(scenes.iter().all(|s| s.n <= 2)); + assert!(scenes.iter().all(|s| s.n <= 3)); const S7: &str = "claude-sonnet-5-5 (Weksa Hands, model-annotated original scenes)"; const GROWTH: &str = "claude-sonnet-5-5 (Weksa Hands, model-annotated validation-growth scenes; annotator is not the writer)"; let grown: BTreeSet = CorpusStore::open(&data.join("corpus.cc")) @@ -1051,16 +1051,31 @@ fn committed_scenes_cover_original_groups() { .map(|i| i.group) .collect(); assert_eq!(grown.len(), 42); + const RUBRIC: &str = + "claude-sonnet-5-5 (Weksa Hands, scene rubric r1, docs/scene-annotation.md)"; + assert!( + Path::new(env!("CARGO_MANIFEST_DIR")) + .join("../../docs/scene-annotation.md") + .is_file(), + "the rubric r1 names a doc, and the doc is in the repo" + ); let mut by_growth = BTreeSet::new(); for s in &scenes { match &s.annotator { Annotator::Model { family, generator } => { assert_eq!(*family, ModelFamily::Anthropic, "{}", s.group); - assert!(generator == S7 || generator == GROWTH, "{}", s.group); + assert!( + generator == S7 || generator == GROWTH || generator == RUBRIC, + "{}", + s.group + ); if generator == GROWTH { by_growth.insert(s.group.clone()); - // One relation, keeper to unnamed, the three Scene features. + // Written once, never revised by its own generator. assert_eq!(s.n, 1, "{}", s.group); + } + if generator == GROWTH || generator == RUBRIC { + // One relation, keeper to unnamed, the three Scene features. assert_eq!(s.relations.len(), 1, "{}", s.group); let rel = &s.relations[0]; assert_eq!(rel.from.as_str(), "entity:keeper", "{}", s.group); @@ -1075,8 +1090,33 @@ fn committed_scenes_cover_original_groups() { by_growth, grown, "the growth scenes are exactly the vgrow groups" ); + // The label a run reads is each group's latest revision: all 98 are rubric r1's. + let mut latest = std::collections::BTreeMap::new(); + for s in &scenes { + if latest.get(&s.group).is_none_or(|l: &&weksa::speaker::Scene| l.n < s.n) { + latest.insert(s.group.clone(), s); + } + } + let mut lines = Vec::new(); + for (group, s) in &latest { + let Annotator::Model { generator, .. } = &s.annotator else { + panic!("{group} is not model-annotated"); + }; + assert_eq!(generator, RUBRIC, "{group}: the latest revision follows rubric r1"); + lines.push(format!("{group}\n{}\n{:?}", s.n, s.relations[0].features)); + } + let parts: Vec<&[u8]> = lines.iter().map(|l| l.as_bytes()).collect(); + assert_eq!( + weksa::split::fnv1a64_of(&parts), + DIGEST_OF_THE_SCENES, + "a latest scene changed without a rubric revision" + ); } +/// Taken over each live group's latest revision (group, n, features) at rubric r1, +/// 2026-11-13. +const DIGEST_OF_THE_SCENES: u64 = 2505219080875817063; + /// The sweep both seed-pair tests share: over a grid of grades per feature (each /// also ABSENT) and the production `Condition::holds`, no listed pair of one /// language's entries co-holds; and each witness entry fires where it should and