Briefcase Core

The core Rust library for Briefcase AI — high-performance AI observability, replay, and decision tracking.

Features

• AI Decision Tracking — Capture inputs, outputs, and context for every AI decision
• Deterministic Replay — Reproduce AI decisions exactly with full context preservation
• Drift Detection — Monitor model performance and behavior changes
• Cost Calculation — Track and estimate model usage costs
• Data Sanitization — Built-in PII redaction with regex patterns
• Token Counting — Estimate token usage via tiktoken
• Flexible Storage — SQLite backend with VCS provider protocol for custom backends

Installation

[dependencies]
briefcase-core = "3.0"

Quick Start

use briefcase_core::*;
use serde_json::json;

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let decision = DecisionSnapshot::new("ai_function")
        .add_input(Input::new("user_query", json!("Hello world"), "string"))
        .add_output(Output::new("response", json!("Hello back!"), "string").with_confidence(0.95))
        .with_execution_time(120.5);

    let storage = storage::SqliteBackend::in_memory()?;
    let decision_id = storage.save_decision(decision).await?;

    println!("Saved decision: {}", decision_id);
    Ok(())
}

Feature Flags

Storage

// In-memory
let storage = storage::SqliteBackend::in_memory()?;

// File-based
let storage = storage::SqliteBackend::new("decisions.db")?;

Custom Storage

Implement the StorageBackend trait:

use briefcase_core::storage::StorageBackend;
use async_trait::async_trait;

pub struct CustomBackend;

#[async_trait]
impl StorageBackend for CustomBackend {
    // implement required methods
}

Custom VCS Provider

Implement the VcsProvider trait for version-controlled storage:

use briefcase_core::storage::vcs::{VcsProvider, VcsStorageBackend};

// Implement VcsProvider, then wrap:
let backend = VcsStorageBackend::new(my_provider);

License

Apache-2.0 — see LICENSE file for details.