Pattern Memory

Pattern memory tracks the cost and success rate of LLM calls by prompt hash and model, enabling cost-optimal model selection over time. It learns which models perform best for which types of prompts without ever storing the prompts themselves.

Privacy by Construction

Pattern memory never stores raw prompts. Every prompt is reduced to a SHA-256 hash before recording. The original text cannot be recovered from the hash. This is not a policy -- it is enforced by the API design.

Each record contains:

Model Suggestion

The suggestModel() function scores each model that has been used for a given prompt hash:

score = successRate / avgCost

Higher scores indicate models that reliably succeed at lower cost. A model with a 95% success rate and an average cost of 50 usertokens scores higher than one with 98% success at 200 usertokens.

If no patterns exist for a prompt hash, suggestModel() returns null.

API

import {
  recordPattern,
  suggestModel,
  hashPrompt,
  getPatternStats,
} from "usertrust";

// Hash a prompt (SHA-256, irreversible)
const hash = hashPrompt("Summarize this document...");

// Get a model suggestion based on historical patterns
const suggested = suggestModel(hash);
// "claude-haiku-4-5" or null if no data exists

// Record the outcome of a call
await recordPattern({
  promptHash: hash,
  model: "claude-haiku-4-5",
  cost: 42,
  success: true,
});

// Get aggregate statistics
const stats = await getPatternStats();
// { totalEntries, uniqueModels, hitCount }

Storage

Patterns are stored in .usertrust/patterns/memory.json. The file is capped at 10,000 entries. When the cap is reached, the oldest entries are evicted first (FIFO).

A process-local async mutex serializes writes to prevent concurrent corruption.

Configuration

{
  "patterns": {
    "enabled": true,
    "feedProxy": false
  }
}

When patterns.enabled is false, recordPattern() is a no-op and suggestModel() always returns null.