jordan a776744889 Initial project setup with Claude Code monorepo structure

- Rust workspace with stemedb-core crate
- Full .claude/ configuration (agents, skills, commands, guides)
- ai-lookup/ for token-efficient fact storage
- Quality gates: clippy, fmt, jscpd duplication detection
- Pre-commit hook with 5-phase quality checks
- CLAUDE.md router and CODING_GUIDELINES.md standards

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

2026-01-31 10:56:26 -07:00

1.3 KiB

Raw Blame History

Lens

Last Updated: 2025-01-31 Confidence: High

Summary

A Lens resolves conflicting assertions into a deterministic answer at read time. Multiple truths coexist; the Lens chooses which to return.

Key Facts:

Stateless compute (no side effects)
Deterministic (same input = same output)
Fast (runs on every read, avoid allocations)
Pluggable (implement Lens trait)

File Pointer: crates/stemedb-lens/src/lib.rs (planned)

The Trait

pub trait Lens {
    fn resolve(&self, candidates: &[Assertion], context: &QueryContext) -> LensResult;
}

Standard Lenses

Lens	Strategy	Use Case
Recency	Latest timestamp wins	News, real-time
Consensus	Highest vote count	Democratic truth
Authority	Weighted by agent reputation	Expert truth
Skeptic	Returns variance/conflict	Finding controversy

Query Flow

Client: GET(Subject="Tesla", Predicate="Revenue", Lens="Consensus")
Index lookup: SP:Tesla:Revenue -> [Hash1, Hash2, Hash3]
Hydrate: Load assertions from hashes
Resolve: ConsensusLens.resolve(assertions, context)
Return: Single deterministic answer with confidence

1.3 KiB Raw Blame History