🧠 Self-Learning with ReasoningBank

javascript
const { JjWrapper } = require('agentic-jujutsu');

const jj = new JjWrapper();

// Start learning trajectory
const trajectoryId = jj.startTrajectory('Deploy to production');

// Perform operations (automatically tracked)
await jj.branchCreate('release/v1.0');
await jj.newCommit('Release v1.0');

// Record operations to trajectory
jj.addToTrajectory();

// Finalize with success score (0.0-1.0) and critique
jj.finalizeTrajectory(0.95, 'Deployment successful, no issues');

// Later: Get AI-powered suggestions for similar tasks
const suggestion = JSON.parse(jj.getSuggestion('Deploy to staging'));
console.log('AI Recommendation:', suggestion.reasoning);
console.log('Confidence:', (suggestion.confidence * 100).toFixed(1) + '%');

ReasoningBank Methods:

Method	Description	Returns
startTrajectory(task)	Begin learning trajectory	string (trajectory ID)
addToTrajectory()	Add recent operations	void
finalizeTrajectory(score, critique?)	Complete trajectory (0.0-1.0)	void
getSuggestion(task)	Get AI recommendation	JSON: DecisionSuggestion
getLearningStats()	Get learning metrics	JSON: LearningStats
getPatterns()	Get discovered patterns	JSON: Pattern[]
queryTrajectories(task, limit)	Find similar trajectories	JSON: Trajectory[]