NeuralBudget v0.2.0 - Production-Ready SLO Platform

NeuralBudget v0.2.0 - Production-Ready SLO Platform

Welcome to NeuralBudget v0.2.0! This release includes the complete feature set for production SLO evaluation with Apache-2.0 licensing.

🎉 Major Features

Command-Line Interface (NEW)

• neuralbudget binary with 4 powerful subcommands:
  • eval - Evaluate SLOs against metrics with human-readable and JSON output
  • gen-rules - Generate Prometheus alerting rules in YAML and Kubernetes CRD formats
  • check - Validate SLO configurations with strict mode and detailed error reporting
  • serve - HTTP server mode (preview, full release in v0.3)
• Multi-platform builds: Linux (x86_64, ARM64), macOS (Intel, Apple Silicon), Windows
• Docker multi-stage build support for optimized distribution

GenAI Quality Features (Complete Suite)

• LLM-as-Judge - Reference-free quality evaluation with cached embeddings
• Hallucination Detection - Groundedness-based quality SLOs
• Cost-Based SLOs - Token usage budgets and cost control
• Agent Reliability - Track LLM agent steps, tools, loops, and success rates
• TTFT SLO (NEW) - Time to First Token tracking for streaming responses with inter-token latency metrics

Composite DAG Evaluation

• Model relationships between services, not just individual SLOs
• Automatic failure propagation through dependency graph
• System-wide health scoring
• Detect cascading failures before they impact users

Streaming & Performance

• High-frequency metric collection: 15,000+ samples per second
• Adaptive windowing: automatic memory management
• Zero-copy streaming aggregator
• Sub-microsecond evaluation latency

Standards & Compatibility

• Apache-2.0 Licensed - Full open-source with commercial flexibility
• OpenSLO Compatible - Bidirectional conversion (parse and generate)
• Prometheus Native - OTLP ingestion and Prometheus exporter
• 87%+ Test Coverage - Comprehensive unit and integration tests

📊 SLO Evaluation Modes

All modes in a single tool:

• HTTP/gRPC - P50/P99 latency, availability, error rate
• Stateful Services - Replication lag, queue depth, saturation
• ML Serving - Latency, GPU utilization, model drift, accuracy
• GenAI Workloads - TTFT, throughput, semantic quality, cost
• Composite DAG - Cross-service dependencies, system-wide health

📈 Multi-Burn-Rate Alerting

Google SRE-inspired alerting strategy:

• Automatic recording rule generation
• Multi-window burn rate calculation (1h, 6h, 24h, 3d)
• Configurable alert severity levels (Info, Warning, Critical)
• Kubernetes PrometheusRule CRD support
• Validation of PromQL expressions

🚀 What's New vs v0.1.3

• ✅ Production CLI tool with 4 subcommands
• ✅ TTFT SLO for streaming GenAI responses
• ✅ Multi-burn-rate alerting with thresholds
• ✅ OpenSLO conversion and compatibility
• ✅ Prometheus rule generation
• ✅ Apache-2.0 relicensing
• ✅ Enhanced documentation with deployment guides

📦 Downloads

Pre-built binaries available for:

• Linux x86_64, ARM64
• macOS Intel, Apple Silicon
• Windows x86_64

Python wheels available on PyPI: pip install neuralbudget==0.2.0

📚 Documentation

• Getting Started - 10-minute quickstart
• User Guide - Complete feature guide
• CLI User Guide - Command-line tool documentation
• Production Deployment - Deploy to production
• GenAI Features - LLM quality SLOs

🐛 Known Issues

None currently. If you find an issue, please open a GitHub issue.

📄 Full Changelog

See CHANGELOG.md for complete details.

---

License: Apache-2.0 | Repository: https://github.com/pristley/NeuralBudget

v0.1.3-r5

[0.1.3-r5] - 2026-06-25

Changed

• ci(release): publish from linux wheel matrix

v0.1.3-r4

[0.1.3-r4] - 2026-06-25

Changed

• build(release): fix wheel license metadata for PyPI

v0.1.3-r3

[0.1.3-r3] - 2026-06-25

Changed

• ci(release): restore canonical PyPI release workflow path

v0.1.3-r2

[0.1.3-r2] - 2026-06-25

Changed

• release: flatten downloaded dist files for PyPI publish

v0.1.3-r1

[0.1.3-r1] - 2026-06-25

Changed

• ci(release): remove redundant CD release logic
• ci(release): split publish into dedicated release pipeline
• release: fix invalid workflow contexts and pypi publish branching
• release: harden pypi publish flow and add local simulator
• ci: align coverage gate threshold with current baseline
• docs: streamline and de-duplicate documentation
• Fix CI fmt and clippy regressions
• Add OpenTelemetry OTLP ingestion integration
• Add native Prometheus exporter for SLO evaluations
• Add property-based coverage tests and document coverage workflow
• feat(rust): add versioned SloConfig schema validation
• feat(config): add versioned schema validation for YAML/JSON
• docs: expand production, kubernetes, and prometheus guides
• ci(cd): simplify release/publish gating conditions
• ci(cd): restore pypi environment claims [release-main-publish]
• ci(cd): include sdist in main publish gate [release-main-publish]
• ci(cd): add main-branch publish gate [release-main-publish]
• ci(cd): allow manual main-run pypi publish path

v0.1.3

[0.1.3] - 2026-06-24

Changed

• ci(cd): move release workflow to release.yml
• ci(cd): publish to pypi via api token fallback
• ci(cd): use explicit manylinux CPython interpreter paths
• ci(cd): use platform-specific maturin interpreter selection
• ci(cd): limit release wheels to CPython interpreters
• ci(cd): simplify macOS wheel matrix for reliable release publishing
• ci(cd): allow PyO3 wheel builds on newer Python interpreters
• docs: update changelog for v0.1.3 [skip ci]
• chore(release): bump version to 0.1.3
• docs: add production deployment, Kubernetes, and Prometheus guides
• docs: detail release automation and refresh changelog
• ci(cd): integrate cross-platform PyPI publish into release workflow
• docs: update changelog for v0.1.2 [skip ci]

v0.1.2

[0.1.2] - 2026-06-24

Changed

• chore(release): bump version to 0.1.2
• ci(pypi): publish cross-platform wheels via GitHub release workflow
• docs: add comprehensive user guide and improve client API docs
• feat(python): add NeuralBudgetClient facade for notebook and CI workflows
• docs: refresh README badges and project summary
• fix: apply rustfmt to satisfy CI/CD format checks
• ci: make coverage gate deterministic for lib and tests
• feat: add composite DAG python API, benchmarking, and docs refresh
• feat: add composite DAG SLO runner with global scoring
• feat: add GenAI convenience helper and first-class user guide docs
• feat: add convenience dataclass returns, presets, tests, and pipeline gates
• docs: add detailed documentation index and convenience reference
• feat: add MlSlo hybrid drift-serving SLO and pipeline coverage
• docs(readme): expand professional Python user guide
• feat(python): add convenience layer for one-shot SLO workflows
• docs: professionalize release notes and refresh badges
• Add Python examples for SLO workflows
• Modularize lib.rs into core and python modules
• Document wheel build in README
• Add Python wheel packaging support
• Add weighted stateful policy profiles
• Enforce coverage gate and update docs
• Add StatefulSlo evaluation and refresh project documentation
• Expand HttpSlo test coverage and align CI/CD docs
• Add web API SLO framework with MAD outlier filtering
• Update README for budget and functional pipeline
• Add budget algorithms and full test tiers
• Automate release notes and badges
• Document time windows and test coverage

v0.1.1

Full Changelog: https://github.com/pristley/NeuralBudget/commits/v0.1.1