Skip to content

Latest commit

 

History

History
57 lines (47 loc) · 2.86 KB

CHANGELOG.md

File metadata and controls

57 lines (47 loc) · 2.86 KB

Changelog

All notable changes to Switchyard are documented here. The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[0.1.0] — Initial release

First public release of Switchyard — a typed, composable control plane for LLM traffic that sits between client applications and LLM backends.

Added

  • Four-role chain — RequestProcessor → LLMBackend → ResponseProcessor → TranslationEngine, executed by the Rust-backed core. See Architecture.
  • Protocol translation — convert between OpenAI Chat Completions, Anthropic Messages, and OpenAI Responses wire formats, so each client keeps speaking its native API regardless of the upstream backend.
  • YAML route bundles (switchyard serve --routing-profiles) — one bundle, many named routes, each its own chain. Supported route types: model, passthrough, random_routing, cascade, deterministic (LLM-as-classifier), latency_service, and noop.
  • Routing strategies — weighted random split, signal-driven cascade escalation (see Cascade Routing), LLM-as-classifier strong/weak routing, and latency-aware multi-endpoint failover.
  • One-command launchers — switchyard launch claude, launch codex, and launch openclaw spin up a local proxy and drop you into the target CLI. All three default to LLM-as-classifier routing (validated coding-agent trio) with --model / --routing-profiles to opt out.
  • CLI — serve, launch, configure (saved defaults, --show, --list-models), and verify / launch --smoke round-trip checks.
  • Observability — Prometheus /metrics, a JSON /v1/stats (/v1/routing/stats alias), and per-request cost/token/latency stats. See Metrics Reference.
  • Python library — SwitchyardRecipes (passthrough_recipe, random_routing_recipe, cascade_recipe, deterministic_routing_recipe, …) and typed ChatRequest / ChatResponse containers for in-process use.
  • Rust core (PyO3) — chain execution, the latency-aware router, and the tool-result signal collector are implemented in Rust and re-exported to Python.
  • Packaging — pip install nemo-switchyard with optional extras [server], [cli], [gpu], [all]. See Installation.

Deprecated

  • --plan-execute launcher flag — slated for removal; plan-execute will be configured through a --routing-profiles YAML bundle instead.

Notes

  • The --deterministic launcher flag was removed during pre-release development — LLM-as-classifier routing is now the implicit default for the claude / codex / openclaw launchers.
  • Inference Hub integration docs are out of scope for this release.