187661714f
Codex CRITICAL + 4 HIGH + 5 MEDIUM/LOW from RULE 0.23 dual-review and
RULE 0.25 multi-critic swarm — all closed.
CRITICAL fix
- Model::slug() ledger compatibility: posterior.rs + select_kernel.rs
query `WHERE model = ?2 OR model = ?3`, binding canonical + legacy
slug pair via new `Model::legacy_slug()`. Production ledger rows
written under "haiku"/"sonnet"/"opus" remain visible to posterior
aggregation. Regression test ledger_legacy_slug_counted.
HIGH fixes
- cmd_select(): no longer early-returns on profile match. Profile's
default_model_ref now becomes DecisionInput.fallback; select() always
runs, posterior/kernel evidence wins if present. RULE 0.20 cost
optimisation restored for all 18 registered agents.
- Registry pricing SSoT: DecisionInput now carries Option<Arc<Registry>>.
estimated_cost() tries registry first; hardcoded match is documented
fallback only. select_posterior.rs no longer duplicates models.toml
constants.
- registry.rs portability: include_str!() embeds the three TOMLs at
compile time. load_embedded() new; disk path tried first via
KEI_REGISTRIES_DIR, embedded as fallback. `cargo install`d binaries
now find registries unconditionally. embedded_registry_matches_disk
test ensures embedded ≡ disk source.
- next_model() ambiguity: replaced Option<&Model> with EscalationResult
enum (Next(&Model) / AtTop / NotFound). Callers can distinguish typo
from ceiling. 5 new tests.
MEDIUM fixes
- posterior.rs u32 overflow: `(n_plus + n_minus) as u32` →
`u32::try_from(n_plus.saturating_add(n_minus)).unwrap_or(u32::MAX)`.
overflow_guard_on_huge_n test with i64::MAX.
- pick() unknown-model: now returns None when default_model_ref's model
is absent from registry. Inverted the deprecation guard.
- HOME unset: disk_registries_dir() returns None on empty HOME and
falls through to embedded registries. open_ledger() logs warning
and returns None instead of opening at malformed path.
- SQLite WAL + busy_timeout: applied to ledger connection in
open_ledger() — concurrent CLI invocations no longer SQLITE_BUSY.
LOW fixes
- impl Model consolidation: next_tier() moved to pricing.rs.
escalate.rs uses current.next_tier() instead of duplicating logic.
- complexity.rs: removed duplicate "ml-implementer" in HEAVY_ROLES.
- dna_class.rs: role("") now returns None instead of Some("").
Verification (orchestrator-side, RULE 0.13 §Verify-before-commit):
- cargo check → clean
- cargo test --release → 63 passed / 0 failed (was 58 → +5 new tests
cover legacy-slug, EscalationResult, overflow, unknown-model, embedded)
- Constructor Pattern → all files ≤ 200 LOC (max registry.rs 196)
- Largest fn from_ledger 28 LOC / limit 30
DNA-INDEX.md regenerated by kei-registry hook (cosmetic).
=== STATUS-TRUTH MARKER ===
shipped: functional
stubs: 0
cargo-check: PASS
behaviour-verified: yes
follow-up-required:
- (none from this commit; next audit pass before merge to main)
76 lines
2.4 KiB
Rust
76 lines
2.4 KiB
Rust
//! Kernel-smoothed posterior fallback for the empirical selector.
|
|
//!
|
|
//! When a task-class has no direct ledger entries, borrows posterior mass
|
|
//! from neighbouring task-classes weighted by DNA similarity.
|
|
//!
|
|
//! Constructor Pattern: SQL cube — separated from select.rs to keep both files <200 LOC.
|
|
|
|
use crate::kernel::{self, KernelWeights};
|
|
use crate::posterior::Posterior;
|
|
use crate::pricing::Model;
|
|
use rusqlite::{Connection, Result as SqlResult};
|
|
|
|
// Finding 1: accept canonical slug (?2) OR legacy short slug (?3) for
|
|
// backward-compat with pre-migration ledger rows.
|
|
const QUERY: &str = "SELECT task_class_dna,
|
|
SUM(CASE WHEN outcome = 'functional'
|
|
AND COALESCE(escalation_depth, 0) = 0
|
|
THEN 1 ELSE 0 END) AS np,
|
|
SUM(CASE WHEN outcome IS NOT NULL
|
|
AND NOT (outcome = 'functional'
|
|
AND COALESCE(escalation_depth, 0) = 0)
|
|
THEN 1 ELSE 0 END) AS nm
|
|
FROM agents
|
|
WHERE task_class_dna IS NOT NULL
|
|
AND task_class_dna != ?1
|
|
AND (model = ?2 OR model = ?3)
|
|
GROUP BY task_class_dna";
|
|
|
|
/// Weighted-sum posterior borrowing from neighbour task-classes.
|
|
///
|
|
/// Returns a Beta posterior with `alpha`/`beta` inflated by kernel similarity.
|
|
/// Starts from a uniform prior (alpha=1, beta=1) and accumulates evidence.
|
|
pub fn smooth(
|
|
conn: &Connection,
|
|
target_task_class: &str,
|
|
model: Model,
|
|
weights: KernelWeights,
|
|
) -> SqlResult<Posterior> {
|
|
let mut stmt = conn.prepare(QUERY)?;
|
|
|
|
let rows = stmt.query_map(
|
|
rusqlite::params![target_task_class, model.slug(), model.legacy_slug()],
|
|
|r| {
|
|
Ok((
|
|
r.get::<_, String>(0)?,
|
|
r.get::<_, Option<i64>>(1)?.unwrap_or(0),
|
|
r.get::<_, Option<i64>>(2)?.unwrap_or(0),
|
|
))
|
|
},
|
|
)?;
|
|
|
|
accumulate_weighted(rows, target_task_class, weights)
|
|
}
|
|
|
|
fn accumulate_weighted(
|
|
rows: impl Iterator<Item = rusqlite::Result<(String, i64, i64)>>,
|
|
target: &str,
|
|
weights: KernelWeights,
|
|
) -> SqlResult<Posterior> {
|
|
let mut alpha = 1.0_f64;
|
|
let mut beta = 1.0_f64;
|
|
let mut n = 0_u32;
|
|
|
|
for row in rows {
|
|
let (other_tc, np, nm) = row?;
|
|
let sim = kernel::similarity(target, &other_tc, weights);
|
|
if sim <= 0.0 {
|
|
continue;
|
|
}
|
|
alpha += sim * np as f64;
|
|
beta += sim * nm as f64;
|
|
n = n.saturating_add((np + nm) as u32);
|
|
}
|
|
|
|
Ok(Posterior { alpha, beta, n })
|
|
}
|