changes claude never committed

2026-06-21 18:00:52 -07:00
parent 39386a81c9
commit 2fe989bcb3
33 changed files with 5528 additions and 0 deletions
@@ -0,0 +1,344 @@
+//! `generators` — produce worlds, rune programs, executor sets, semantic
+//! contracts, and perturbation batches. Generators must reject flat cases:
+//! every generated case is checked against the generated-case gates before it
+//! is admitted to the corpus.
+
+use rune_ir::{Op, RuneProgram, RuneToken, ALL_OPS};
+use trace_model::numeric_rank;
+use world_model::{
+    standard_executors, ContractId, ExecutionContext, PerturbationAxis, ProgramId, Rng,
+    TraceDifferenceExpectation, WorldId, WorldSnapshot, HIDDEN_LANES, LANES, NUM_DOMAINS,
+};
+
+/// Minimum domain reference entropy (bits) a generated program must show.
+pub const MIN_DOMAIN_ENTROPY: f64 = 2.5;
+
+/// Semantic contract (per spec) with the default thresholds.
+#[derive(Clone, Copy, PartialEq, Debug)]
+pub struct SemanticContract {
+    pub id: ContractId,
+    pub min_causal_rank: usize,
+    pub min_domain_participation: usize,
+    pub min_future_sensitivity: f64,
+    pub min_context_divergence: f64,
+    pub max_compressibility: f64,
+}
+
+impl SemanticContract {
+    pub fn default_with_seed(seed: u64) -> Self {
+        SemanticContract {
+            id: ContractId(seed),
+            min_causal_rank: 6,
+            min_domain_participation: 4,
+            min_future_sensitivity: 0.50,
+            min_context_divergence: 0.40,
+            max_compressibility: 0.70,
+        }
+    }
+}
+
+/// One perturbed variant of a base world.
+pub struct PerturbedCase {
+    pub axis_name: String,
+    pub world: WorldSnapshot,
+    pub expectation: TraceDifferenceExpectation,
+}
+
+/// A complete generated case (per spec).
+pub struct GeneratedCase {
+    pub world: WorldSnapshot,
+    pub program: RuneProgram,
+    pub contexts: Vec<ExecutionContext>,
+    pub contract: SemanticContract,
+    pub perturbations: Vec<PerturbedCase>,
+    pub world_seed: u64,
+    pub program_seed: u64,
+    pub contract_seed: u64,
+    pub perturbation_seed: u64,
+}
+
+/// Generate a rich world from a seed.
+pub fn generate_world(seed: u64) -> WorldSnapshot {
+    let mut rng = Rng::derive(seed, "world");
+    let mut w = WorldSnapshot::blank(WorldId(seed), seed);
+
+    for (i, d) in w.domains.iter_mut().enumerate() {
+        let spread = 1000 + (i as i64) * 137;
+        for l in 0..LANES {
+            d.observed[l] = rng.range_i64(-spread, spread);
+        }
+        for l in 0..HIDDEN_LANES {
+            let mut v = rng.range_i64(-spread, spread);
+            if v == 0 {
+                v = 1 + i as i64;
+            }
+            d.hidden[l] = v;
+        }
+    }
+
+    for j in 0..NUM_DOMAINS {
+        for i in 0..NUM_DOMAINS {
+            w.causal_state.coupling[j][i] = rng.range_i64(-17, 17);
+        }
+    }
+
+    for di in 0..NUM_DOMAINS {
+        for l in 0..LANES {
+            w.observation_state.visible[di][l] = !rng.chance(0.15);
+        }
+        if (0..LANES).all(|l| !w.observation_state.visible[di][l]) {
+            w.observation_state.visible[di][0] = true;
+        }
+    }
+    w.observation_state.noise_seed = rng.next_u64();
+
+    for r in w.execution_state.accumulator.iter_mut() {
+        *r = rng.range_i64(-50, 50);
+    }
+    w
+}
+
+/// Generate a rune program from a seed. Construction guarantees every opcode
+/// appears and every domain is both read and written, so the case is never
+/// flat.
+pub fn generate_program(seed: u64) -> RuneProgram {
+    let mut rng = Rng::derive(seed, "program");
+    let len = 28 + rng.below(13); // 28..=40
+    let mut tokens = Vec::with_capacity(len);
+    for i in 0..len {
+        let op = if rng.chance(0.7) {
+            ALL_OPS[i % ALL_OPS.len()]
+        } else {
+            Op::from_u8(rng.next_u64() as u8)
+        };
+        // 3 and 5 are coprime with 8, so src/dst sweep all domains.
+        let a = ((i * 3 + rng.below(2)) % NUM_DOMAINS) as u8;
+        let mut b = ((i * 5 + 1 + rng.below(2)) % NUM_DOMAINS) as u8;
+        if b == a {
+            b = (b + 1) % NUM_DOMAINS as u8;
+        }
+        tokens.push(RuneToken {
+            op,
+            a,
+            b,
+            c: rng.next_u64() as u8,
+            imm: rng.range_i64(-100_000, 100_000),
+        });
+    }
+    RuneProgram {
+        id: ProgramId(seed),
+        tokens,
+        seed,
+    }
+}
+
+/// Generate >= 3 executors.
+pub fn generate_contexts(seed: u64) -> Vec<ExecutionContext> {
+    let mut rng = Rng::derive(seed, "context-count");
+    standard_executors(seed, 3 + rng.below(2))
+}
+
+/// Build the perturbation batch for a world (>= 10 perturbations drawn from
+/// domain surfaces).
+pub fn generate_perturbations(world: &WorldSnapshot, seed: u64, count: usize) -> Vec<PerturbedCase> {
+    use world_model::WorldDomain;
+    let count = count.max(10);
+    let mut axes: Vec<Box<dyn PerturbationAxis>> = Vec::new();
+    for d in &world.domains {
+        axes.extend(d.perturbation_axes());
+    }
+    let mut rng = Rng::derive(seed, "perturb");
+    let mut out = Vec::with_capacity(count);
+    for k in 0..count {
+        let idx = (k * 7 + rng.below(axes.len())) % axes.len();
+        let axis = &axes[idx];
+        out.push(PerturbedCase {
+            axis_name: axis.name(),
+            world: axis.apply(world),
+            expectation: axis.expected_trace_difference(),
+        });
+    }
+    out
+}
+
+/// Generate a full case from a master seed.
+pub fn generate_case(master_seed: u64) -> GeneratedCase {
+    let world_seed = derive(master_seed, "world");
+    let program_seed = derive(master_seed, "program");
+    let contract_seed = derive(master_seed, "contract");
+    let perturbation_seed = derive(master_seed, "perturb");
+
+    let world = generate_world(world_seed);
+    let program = generate_program(program_seed);
+    let contexts = generate_contexts(master_seed);
+    let contract = SemanticContract::default_with_seed(contract_seed);
+    let perturbations = generate_perturbations(&world, perturbation_seed, 10);
+
+    GeneratedCase {
+        world,
+        program,
+        contexts,
+        contract,
+        perturbations,
+        world_seed,
+        program_seed,
+        contract_seed,
+        perturbation_seed,
+    }
+}
+
+pub fn derive(seed: u64, tag: &str) -> u64 {
+    let mut h = world_model::Hasher::new();
+    h.write_tag(tag);
+    h.write_u64(seed);
+    h.finish().0
+}
+
+// ---------------------------------------------------------------------------
+// Generated-case gates: reject flat cases.
+// ---------------------------------------------------------------------------
+
+#[derive(Clone, Copy, Debug, PartialEq)]
+pub struct CaseEstimate {
+    pub estimated_causal_rank: usize,
+    pub domain_entropy: f64,
+    pub perturbation_axes: usize,
+    pub executor_count: usize,
+    pub future_dependence: bool,
+    pub hidden_observed_divergence: bool,
+    pub nonuniform_fingerprints: bool,
+}
+
+impl GeneratedCase {
+    /// Estimate the structural richness of the case without running a runtime.
+    pub fn estimate(&self) -> CaseEstimate {
+        let mut adj = [[0.0f64; NUM_DOMAINS]; NUM_DOMAINS];
+        let mut refs = [0u32; NUM_DOMAINS];
+        for t in &self.program.tokens {
+            let s = t.src_domain();
+            let d = t.dst_domain();
+            let phase = 1.0 + t.lane() as f64 + 4.0 * t.lane2() as f64;
+            adj[d][s] += phase;
+            adj[d][d] += 0.5 + t.mode() as f64;
+            refs[s] += 1;
+            refs[d] += 1;
+        }
+        let rows: Vec<Vec<f64>> = adj.iter().map(|r| r.to_vec()).collect();
+        let est_rank = numeric_rank(&rows);
+
+        let total: u32 = refs.iter().sum();
+        let mut entropy = 0.0;
+        if total > 0 {
+            for &c in &refs {
+                if c > 0 {
+                    let p = c as f64 / total as f64;
+                    entropy -= p * p.log2();
+                }
+            }
+        }
+
+        let future = self.program.tokens.iter().any(|t| matches!(t.op, Op::Schedule));
+
+        let hidden_div = self
+            .world
+            .domains
+            .iter()
+            .any(|d| d.hidden.iter().any(|&v| v != 0))
+            || self
+                .world
+                .observation_state
+                .visible
+                .iter()
+                .any(|row| row.iter().any(|&v| !v));
+
+        use world_model::WorldDomain;
+        let mut prints: Vec<_> = self.world.domains.iter().map(|d| d.fingerprint().hash).collect();
+        prints.sort();
+        prints.dedup();
+        let nonuniform = prints.len() > 1;
+
+        CaseEstimate {
+            estimated_causal_rank: est_rank,
+            domain_entropy: entropy,
+            perturbation_axes: self.perturbations.len().max(count_axes(&self.world)),
+            executor_count: self.contexts.len(),
+            future_dependence: future,
+            hidden_observed_divergence: hidden_div,
+            nonuniform_fingerprints: nonuniform,
+        }
+    }
+}
+
+fn count_axes(world: &WorldSnapshot) -> usize {
+    use world_model::WorldDomain;
+    world.domains.iter().map(|d| d.perturbation_axes().len()).sum()
+}
+
+/// Reasons a case failed the generated gates (empty = passed).
+pub fn generated_gate_failures(est: &CaseEstimate) -> Vec<String> {
+    let mut f = Vec::new();
+    if est.estimated_causal_rank < 6 {
+        f.push(format!("estimated_causal_rank {} < 6", est.estimated_causal_rank));
+    }
+    if est.domain_entropy < MIN_DOMAIN_ENTROPY {
+        f.push(format!(
+            "domain_entropy {:.3} < {:.3}",
+            est.domain_entropy, MIN_DOMAIN_ENTROPY
+        ));
+    }
+    if est.perturbation_axes < 10 {
+        f.push(format!("perturbation_axes {} < 10", est.perturbation_axes));
+    }
+    if est.executor_count < 3 {
+        f.push(format!("executor_count {} < 3", est.executor_count));
+    }
+    if !est.future_dependence {
+        f.push("future_dependence absent".into());
+    }
+    if !est.hidden_observed_divergence {
+        f.push("no hidden/observed divergence".into());
+    }
+    if !est.nonuniform_fingerprints {
+        f.push("uniform domain fingerprints".into());
+    }
+    f
+}
+
+/// Generate a case that passes the generated gates, retrying with fresh seeds.
+pub fn generate_accepted_case(master_seed: u64) -> (GeneratedCase, u64) {
+    let mut s = master_seed;
+    for _ in 0..64 {
+        let case = generate_case(s);
+        if generated_gate_failures(&case.estimate()).is_empty() {
+            return (case, s);
+        }
+        s = derive(s, "retry");
+    }
+    let case = generate_case(s);
+    (case, s)
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn accepted_cases_pass_generated_gates() {
+        for i in 0..200u64 {
+            let (case, _) = generate_accepted_case(0x1234 ^ i.wrapping_mul(0x9e3779b97f4a7c15));
+            let failures = generated_gate_failures(&case.estimate());
+            assert!(failures.is_empty(), "case {i} failed: {:?}", failures);
+            assert!(case.contexts.len() >= 3);
+            assert!(case.perturbations.len() >= 10);
+        }
+    }
+
+    #[test]
+    fn generation_is_deterministic() {
+        let (a, sa) = generate_accepted_case(999);
+        let (b, sb) = generate_accepted_case(999);
+        assert_eq!(sa, sb);
+        assert_eq!(a.program.content_hash(), b.program.content_hash());
+        assert_eq!(a.world.content_hash(), b.world.content_hash());
+    }
+}