# CLAUDE.md - Java AI Coding Agent Context & Token Boundary Rules for `apache/doris`
[![PulseForge 2026 Empirical Benchmark](https://exactbaseline.com/api/badge/apache/doris.svg?tier=community)](https://exactbaseline.com/leaderboard?repo=apache/doris)

> **Generated by [PulseForge AI Empirical Radar](https://exactbaseline.com/leaderboard)** • Maintainer: `@apache` • Stack: `Java` (180,000 KB / ~4,320,000 LOC)
> **Upgrade to Drop-In Migration & 45% Cost-Cut Config Pack ($4.99)**: https://exactbaseline.com/buy/micro_pass?repo=apache/doris
> **Complete 9-File AI Stack BOM & Repo Hardening .ZIP ($9.99)**: https://exactbaseline.com/buy/repo_pass_999?repo=apache/doris

## 1. Context Window & Token Boundary Rules (-58% Discovery Token Bloat)
- **Excluded Discovery Paths (NEVER read, index, or grep)**: `target/, build/, .gradle/, *.jar, *.class, hs_err_pid*.log`
- Before reading any file > 300 lines, query symbol definitions or line ranges first.
- Keep per-turn prompt context <= **26,880 tokens** (down from 64,000 unindexed tokens/turn; saves ~$433.11/mo).
- Keep every source file strictly under 1,000 lines.

## 2. Java Architecture, Schema Boundary & Verification Gate for Doris
- **Verification Command**: Run `./mvnw test -B && ./mvnw spotbugs:check` after every contiguous code edit.
- **Schema & Boundary Discipline**: Jackson FAIL_ON_UNKNOWN_PROPERTIES + Jakarta Bean Validation.
- Never hardcode API keys, bearer tokens, or `.env` secrets in source files or test fixtures.

## 3. Empirical Benchmark Attestation (62.7 -> 94.8/100)
- Live 4-Pillar Telemetry Profile: https://exactbaseline.com/pulseforge-leaderboard?repo=apache/doris
- Machine-Readable LLM Index: https://exactbaseline.com/pulseforge-leaderboard.md